1426 files changed, 90188 insertions, 31436 deletions

diff --git a/Documentation/.gitignore b/Documentation/.gitignore
new file mode 100644
index 000000000000..e74fec8693b2
--- /dev/null
+++ b/Documentation/.gitignore
@@ -0,0 +1,2 @@
+output
+*.pyc
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index cd077ca0e1b8..cb9a6c6fa83b 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -255,10 +255,10 @@ kbuild/
 	- directory with info about the kernel build process.
 kdump/
 	- directory with mini HowTo on getting the crash dump code to work.
-kernel-doc-nano-HOWTO.txt
-	- mini HowTo on generation and location of kernel documentation files.
 kernel-docs.txt
 	- listing of various WWW + books that document kernel internals.
+kernel-documentation.rst
+	- how to write and format reStructuredText kernel documentation
 kernel-parameters.txt
 	- summary listing of command line / boot prompt args for the kernel.
 kernel-per-CPU-kthreads.txt
diff --git a/Documentation/ABI/testing/configfs-acpi b/Documentation/ABI/testing/configfs-acpi
new file mode 100644
index 000000000000..4ab4e99aa863
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-acpi
@@ -0,0 +1,36 @@
+What:		/config/acpi
+Date:		July 2016
+KernelVersion:	4.8
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		This represents the ACPI subsystem entry point directory. It
+		contains sub-groups corresponding to ACPI configurable options.
+
+What:		/config/acpi/table
+Date:		July 2016
+KernelVersion:	4.8
+Description:
+
+		This group contains the configuration for user defined ACPI
+		tables. The attributes of a user define table are:
+
+		aml 		- a binary attribute that the user can use to
+				fill in the ACPI aml definitions. Once the aml
+				data is written to this file and the file is
+				closed the table will be loaded and ACPI devices
+				will be enumerated. To check if the operation is
+				successful the user must check the error code
+				for close(). If the operation is successful,
+				subsequent writes to this attribute will fail.
+
+		The rest of the attributes are read-only and are valid only
+		after the table has been loaded by filling the aml entry:
+
+		signature 	- ASCII table signature
+		length 		- length of table in bytes, including the header
+		revision 	- ACPI Specification minor version number
+		oem_id 		- ASCII OEM identification
+		oem_table_id 	- ASCII OEM table identification
+		oem_revision 	- OEM revision number
+		asl_compiler_id - ASCII ASL compiler vendor ID
+		asl_compiler_revision - ASL compiler version
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index 9a70ddd16584..a096836723ca 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -458,7 +458,7 @@ of the function, telling people what it does, and possibly WHY it does
 it.
 
 When commenting the kernel API functions, please use the kernel-doc format.
-See the files Documentation/kernel-doc-nano-HOWTO.txt and scripts/kernel-doc
+See the files Documentation/kernel-documentation.rst and scripts/kernel-doc
 for details.
 
 Linux style for comments is the C89 "/* ... */" style.
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index d70f9b68174e..01bab5014a4a 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -6,6 +6,8 @@
 # To add a new book the only step required is to add the book to the
 # list of DOCBOOKS.
 
+ifeq ($(IGNORE_DOCBOOKS),)
+
 DOCBOOKS := z8530book.xml device-drivers.xml \
 	    kernel-hacking.xml kernel-locking.xml deviceiobook.xml \
 	    writing_usb_driver.xml networking.xml \
@@ -33,10 +35,6 @@ PDF_METHOD	= $(prefer-db2x)
 PS_METHOD	= $(prefer-db2x)
 
 
-###
-# The targets that may be used.
-PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs cleandocs
-
 targets += $(DOCBOOKS)
 BOOKS := $(addprefix $(obj)/,$(DOCBOOKS))
 xmldocs: $(BOOKS)
@@ -63,6 +61,9 @@ installmandocs: mandocs
 		sort -k 2 -k 1 | uniq -f 1 | sed -e 's: :/:' | \
 		xargs install -m 644 -t /usr/local/man/man9/
 
+# no-op for the DocBook toolchain
+epubdocs:
+
 ###
 #External programs used
 KERNELDOCXMLREF = $(srctree)/scripts/kernel-doc-xml-ref
@@ -216,10 +217,24 @@ silent_gen_xml = :
 	       -e "s/>/\\>/g";     \
 	   echo "</programlisting>")  > $@
 
+else
+
+# Needed, due to cleanmediadocs
+include Documentation/DocBook/media/Makefile
+
+htmldocs:
+pdfdocs:
+psdocs:
+xmldocs:
+installmandocs:
+
+endif # IGNORE_DOCBOOKS
+
+
 ###
 # Help targets as used by the top-level makefile
 dochelp:
-	@echo  ' Linux kernel internal documentation in different formats:'
+	@echo  ' Linux kernel internal documentation in different formats (DocBook):'
 	@echo  '  htmldocs        - HTML'
 	@echo  '  pdfdocs         - PDF'
 	@echo  '  psdocs          - Postscript'
@@ -228,8 +243,11 @@ dochelp:
 	@echo  '  installmandocs  - install man pages generated by mandocs'
 	@echo  '  cleandocs       - clean all generated DocBook files'
 	@echo
-	@echo  'make DOCBOOKS="s1.xml s2.xml" [target] Generate only docs s1.xml s2.xml'
+	@echo  '  make DOCBOOKS="s1.xml s2.xml" [target] Generate only docs s1.xml s2.xml'
 	@echo  '  valid values for DOCBOOKS are: $(DOCBOOKS)'
+	@echo
+	@echo  "  make IGNORE_DOCBOOKS=1 [target] Don't generate docs from Docbook"
+	@echo  '     This is useful to generate only the ReST docs (Sphinx)'
 
 
 ###
diff --git a/Documentation/DocBook/crypto-API.tmpl b/Documentation/DocBook/crypto-API.tmpl
index d55dc5a39bad..fb2a1526f6ec 100644
--- a/Documentation/DocBook/crypto-API.tmpl
+++ b/Documentation/DocBook/crypto-API.tmpl
@@ -440,8 +440,8 @@
      The type flag specifies the type of the cipher algorithm.
      The caller usually provides a 0 when the caller wants the
      default handling. Otherwise, the caller may provide the
-     following selections which match the the aforementioned
-     cipher types:
+     following selections which match the aforementioned cipher
+     types:
     </para>
 
     <itemizedlist>
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index 8c68768ebee5..58af32b01b90 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -300,6 +300,9 @@ X!Isound/sound_firmware.c
 !Iinclude/media/media-devnode.h
 !Iinclude/media/media-entity.h
     </sect1>
+    <sect1><title>Consumer Electronics Control devices</title>
+!Iinclude/media/cec-edid.h
+    </sect1>
 
   </chapter>
 
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index 2840ff483d5a..fdc138624800 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -64,6 +64,7 @@ IOCTLS = \
 	$(shell perl -ne 'print "$$1 " if /\#define\s+([A-Z][^\s]+)\s+_IO/' $(srctree)/include/uapi/linux/dvb/net.h) \
 	$(shell perl -ne 'print "$$1 " if /\#define\s+([^\s]+)\s+_IO/' $(srctree)/include/uapi/linux/dvb/video.h) \
 	$(shell perl -ne 'print "$$1 " if /\#define\s+([^\s]+)\s+_IO/' $(srctree)/include/uapi/linux/media.h) \
+	$(shell perl -ne 'print "$$1 " if /\#define\s+([^\s]+)\s+_IO/' $(srctree)/include/linux/cec.h) \
 	$(shell perl -ne 'print "$$1 " if /\#define\s+([^\s]+)\s+_IO/' $(srctree)/include/uapi/linux/v4l2-subdev.h) \
 
 DEFINES = \
@@ -100,6 +101,7 @@ STRUCTS = \
 	$(shell perl -ne 'print "$$1 " if (/^struct\s+([^\s]+)\s+/ && !/_old/)' $(srctree)/include/uapi/linux/dvb/net.h) \
 	$(shell perl -ne 'print "$$1 " if (/^struct\s+([^\s]+)\s+/)' $(srctree)/include/uapi/linux/dvb/video.h) \
 	$(shell perl -ne 'print "$$1 " if /^struct\s+([^\s]+)\s+/' $(srctree)/include/uapi/linux/media.h) \
+	$(shell perl -ne 'print "$$1 " if /^struct\s+([^\s]+)\s+/' $(srctree)/include/linux/cec.h) \
 	$(shell perl -ne 'print "$$1 " if /^struct\s+([^\s]+)\s+/' $(srctree)/include/uapi/linux/v4l2-subdev.h) \
 	$(shell perl -ne 'print "$$1 " if /^struct\s+([^\s]+)\s+/' $(srctree)/include/uapi/linux/v4l2-mediabus.h)
 
diff --git a/Documentation/DocBook/media/v4l/biblio.xml b/Documentation/DocBook/media/v4l/biblio.xml
index 9beb30f0071b..87f1d24958aa 100644
--- a/Documentation/DocBook/media/v4l/biblio.xml
+++ b/Documentation/DocBook/media/v4l/biblio.xml
@@ -342,6 +342,16 @@ in the frequency range from 87,5 to 108,0 MHz</title>
       <subtitle>Specification Version 1.4a</subtitle>
     </biblioentry>
 
+    <biblioentry id="hdmi2">
+      <abbrev>HDMI2</abbrev>
+      <authorgroup>
+	<corpauthor>HDMI Licensing LLC
+(<ulink url="http://www.hdmi.org">http://www.hdmi.org</ulink>)</corpauthor>
+      </authorgroup>
+      <title>High-Definition Multimedia Interface</title>
+      <subtitle>Specification Version 2.0</subtitle>
+    </biblioentry>
+
     <biblioentry id="dp">
       <abbrev>DP</abbrev>
       <authorgroup>
diff --git a/Documentation/DocBook/media/v4l/cec-api.xml b/Documentation/DocBook/media/v4l/cec-api.xml
new file mode 100644
index 000000000000..7062c1fa4904
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-api.xml
@@ -0,0 +1,75 @@
+<partinfo>
+  <authorgroup>
+    <author>
+      <firstname>Hans</firstname>
+      <surname>Verkuil</surname>
+      <affiliation><address><email>hans.verkuil@cisco.com</email></address></affiliation>
+      <contrib>Initial version.</contrib>
+    </author>
+  </authorgroup>
+  <copyright>
+    <year>2016</year>
+    <holder>Hans Verkuil</holder>
+  </copyright>
+
+  <revhistory>
+    <!-- Put document revisions here, newest first. -->
+    <revision>
+      <revnumber>1.0.0</revnumber>
+      <date>2016-03-17</date>
+      <authorinitials>hv</authorinitials>
+      <revremark>Initial revision</revremark>
+    </revision>
+  </revhistory>
+</partinfo>
+
+<title>CEC API</title>
+
+<chapter id="cec-api">
+  <title>CEC: Consumer Electronics Control</title>
+
+  <section id="cec-intro">
+    <title>Introduction</title>
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+    <para>HDMI connectors provide a single pin for use by the Consumer Electronics
+    Control protocol. This protocol allows different devices connected by an HDMI cable
+    to communicate. The protocol for CEC version 1.4 is defined in supplements 1 (CEC)
+    and 2 (HEAC or HDMI Ethernet and Audio Return Channel) of the HDMI 1.4a
+    (<xref linkend="hdmi" />) specification and the extensions added to CEC version 2.0
+    are defined in chapter 11 of the HDMI 2.0 (<xref linkend="hdmi2" />) specification.
+    </para>
+
+    <para>The bitrate is very slow (effectively no more than 36 bytes per second) and
+    is based on the ancient AV.link protocol used in old SCART connectors. The protocol
+    closely resembles a crazy Rube Goldberg contraption and is an unholy mix of low and
+    high level messages. Some messages, especially those part of the HEAC protocol layered
+    on top of CEC, need to be handled by the kernel, others can be handled either by the
+    kernel or by userspace.</para>
+
+    <para>In addition, CEC can be implemented in HDMI receivers, transmitters and in USB
+    devices that have an HDMI input and an HDMI output and that control just the CEC pin.</para>
+
+    <para>Drivers that support CEC will create a CEC device node (/dev/cecX)
+    to give userspace access to the CEC adapter. The &CEC-ADAP-G-CAPS; ioctl will tell userspace
+    what it is allowed to do.</para>
+  </section>
+</chapter>
+
+<appendix id="cec-user-func">
+  <title>Function Reference</title>
+  <!-- Keep this alphabetically sorted. -->
+  &sub-cec-func-open;
+  &sub-cec-func-close;
+  &sub-cec-func-ioctl;
+  &sub-cec-func-poll;
+  <!-- All ioctls go here. -->
+  &sub-cec-ioc-adap-g-caps;
+  &sub-cec-ioc-adap-g-log-addrs;
+  &sub-cec-ioc-adap-g-phys-addr;
+  &sub-cec-ioc-dqevent;
+  &sub-cec-ioc-g-mode;
+  &sub-cec-ioc-receive;
+</appendix>
diff --git a/Documentation/DocBook/media/v4l/cec-func-close.xml b/Documentation/DocBook/media/v4l/cec-func-close.xml
new file mode 100644
index 000000000000..0812c8cd9634
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-func-close.xml
@@ -0,0 +1,64 @@
+<refentry id="cec-func-close">
+  <refmeta>
+    <refentrytitle>cec close()</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>cec-close</refname>
+    <refpurpose>Close a cec device</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcsynopsisinfo>#include &lt;unistd.h&gt;</funcsynopsisinfo>
+      <funcprototype>
+	<funcdef>int <function>close</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>Closes the cec device. Resources associated with the file descriptor
+    are freed. The device configuration remain unchanged.</para>
+  </refsect1>
+
+  <refsect1>
+    <title>Return Value</title>
+
+    <para><function>close</function> returns 0 on success. On error, -1 is
+    returned, and <varname>errno</varname> is set appropriately. Possible error
+    codes are:</para>
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EBADF</errorcode></term>
+	<listitem>
+	  <para><parameter>fd</parameter> is not a valid open file descriptor.
+	  </para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-func-ioctl.xml b/Documentation/DocBook/media/v4l/cec-func-ioctl.xml
new file mode 100644
index 000000000000..f92817a2dc80
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-func-ioctl.xml
@@ -0,0 +1,78 @@
+<refentry id="cec-func-ioctl">
+  <refmeta>
+    <refentrytitle>cec ioctl()</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>cec-ioctl</refname>
+    <refpurpose>Control a cec device</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcsynopsisinfo>#include &lt;sys/ioctl.h&gt;</funcsynopsisinfo>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>void *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>CEC ioctl request code as defined in the cec.h header file,
+	  for example CEC_ADAP_G_CAPS.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para>Pointer to a request-specific structure.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>The <function>ioctl()</function> function manipulates cec device
+    parameters. The argument <parameter>fd</parameter> must be an open file
+    descriptor.</para>
+    <para>The ioctl <parameter>request</parameter> code specifies the cec
+    function to be called. It has encoded in it whether the argument is an
+    input, output or read/write parameter, and the size of the argument
+    <parameter>argp</parameter> in bytes.</para>
+    <para>Macros and structures definitions specifying cec ioctl requests and
+    their parameters are located in the cec.h header file. All cec ioctl
+    requests, their respective function and parameters are specified in
+    <xref linkend="cec-user-func" />.</para>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <para>Request-specific error codes are listed in the
+    individual requests descriptions.</para>
+    <para>When an ioctl that takes an output or read/write parameter fails,
+    the parameter remains unmodified.</para>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-func-open.xml b/Documentation/DocBook/media/v4l/cec-func-open.xml
new file mode 100644
index 000000000000..2edc5555b81a
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-func-open.xml
@@ -0,0 +1,104 @@
+<refentry id="cec-func-open">
+  <refmeta>
+    <refentrytitle>cec open()</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>cec-open</refname>
+    <refpurpose>Open a cec device</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcsynopsisinfo>#include &lt;fcntl.h&gt;</funcsynopsisinfo>
+      <funcprototype>
+	<funcdef>int <function>open</function></funcdef>
+	<paramdef>const char *<parameter>device_name</parameter></paramdef>
+	<paramdef>int <parameter>flags</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>device_name</parameter></term>
+	<listitem>
+	  <para>Device to be opened.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>flags</parameter></term>
+	<listitem>
+	  <para>Open flags. Access mode must be <constant>O_RDWR</constant>.
+	  </para>
+	  <para>When the <constant>O_NONBLOCK</constant> flag is
+given, the &CEC-RECEIVE; ioctl will return &EAGAIN; when no message is
+available, and the &CEC-TRANSMIT;, &CEC-ADAP-S-PHYS-ADDR; and
+&CEC-ADAP-S-LOG-ADDRS; ioctls all act in non-blocking mode.</para>
+	  <para>Other flags have no effect.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>To open a cec device applications call <function>open()</function>
+    with the desired device name. The function has no side effects; the device
+    configuration remain unchanged.</para>
+    <para>When the device is opened in read-only mode, attempts to modify its
+    configuration will result in an error, and <varname>errno</varname> will be
+    set to <errorcode>EBADF</errorcode>.</para>
+  </refsect1>
+  <refsect1>
+    <title>Return Value</title>
+
+    <para><function>open</function> returns the new file descriptor on success.
+    On error, -1 is returned, and <varname>errno</varname> is set appropriately.
+    Possible error codes include:</para>
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EACCES</errorcode></term>
+	<listitem>
+	  <para>The requested access to the file is not allowed.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EMFILE</errorcode></term>
+	<listitem>
+	  <para>The  process  already  has  the  maximum number of files open.
+	  </para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>ENFILE</errorcode></term>
+	<listitem>
+	  <para>The system limit on the total number of open files has been
+	  reached.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>ENOMEM</errorcode></term>
+	<listitem>
+	  <para>Insufficient kernel memory was available.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>ENXIO</errorcode></term>
+	<listitem>
+	  <para>No device corresponding to this device special file exists.
+	  </para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-func-poll.xml b/Documentation/DocBook/media/v4l/cec-func-poll.xml
new file mode 100644
index 000000000000..1bddbde0142d
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-func-poll.xml
@@ -0,0 +1,94 @@
+<refentry id="cec-func-poll">
+  <refmeta>
+    <refentrytitle>cec poll()</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>cec-poll</refname>
+    <refpurpose>Wait for some event on a file descriptor</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcsynopsisinfo>#include &lt;sys/poll.h&gt;</funcsynopsisinfo>
+      <funcprototype>
+	<funcdef>int <function>poll</function></funcdef>
+	<paramdef>struct pollfd *<parameter>ufds</parameter></paramdef>
+	<paramdef>unsigned int <parameter>nfds</parameter></paramdef>
+	<paramdef>int <parameter>timeout</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>With the <function>poll()</function> function applications
+can wait for CEC events.</para>
+
+    <para>On success <function>poll()</function> returns the number of
+file descriptors that have been selected (that is, file descriptors
+for which the <structfield>revents</structfield> field of the
+respective <structname>pollfd</structname> structure is non-zero).
+CEC devices set the <constant>POLLIN</constant> and
+<constant>POLLRDNORM</constant> flags in the
+<structfield>revents</structfield> field if there are messages in the
+receive queue. If the transmit queue has room for new messages, the
+<constant>POLLOUT</constant> and <constant>POLLWRNORM</constant>
+flags are set. If there are events in the event queue, then the
+<constant>POLLPRI</constant> flag is set.
+When the function timed out it returns a value of zero, on
+failure it returns <returnvalue>-1</returnvalue> and the
+<varname>errno</varname> variable is set appropriately.
+</para>
+
+    <para>For more details see the
+<function>poll()</function> manual page.</para>
+  </refsect1>
+
+  <refsect1>
+    <title>Return Value</title>
+
+    <para>On success, <function>poll()</function> returns the number
+structures which have non-zero <structfield>revents</structfield>
+fields, or zero if the call timed out. On error
+<returnvalue>-1</returnvalue> is returned, and the
+<varname>errno</varname> variable is set appropriately:</para>
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EBADF</errorcode></term>
+	<listitem>
+	  <para>One or more of the <parameter>ufds</parameter> members
+specify an invalid file descriptor.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EFAULT</errorcode></term>
+	<listitem>
+	  <para><parameter>ufds</parameter> references an inaccessible
+memory area.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EINTR</errorcode></term>
+	<listitem>
+	  <para>The call was interrupted by a signal.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EINVAL</errorcode></term>
+	<listitem>
+	  <para>The <parameter>nfds</parameter> argument is greater
+than <constant>OPEN_MAX</constant>.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-ioc-adap-g-caps.xml b/Documentation/DocBook/media/v4l/cec-ioc-adap-g-caps.xml
new file mode 100644
index 000000000000..3523ef2259b1
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-ioc-adap-g-caps.xml
@@ -0,0 +1,151 @@
+<refentry id="cec-ioc-adap-g-caps">
+  <refmeta>
+    <refentrytitle>ioctl CEC_ADAP_G_CAPS</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>CEC_ADAP_G_CAPS</refname>
+    <refpurpose>Query device capabilities</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct cec_caps *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>File descriptor returned by
+	  <link linkend='cec-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>CEC_ADAP_G_CAPS</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>All cec devices must support the <constant>CEC_ADAP_G_CAPS</constant>
+    ioctl. To query device information, applications call the ioctl with a
+    pointer to a &cec-caps;. The driver fills the structure and returns
+    the information to the application.
+    The ioctl never fails.</para>
+
+    <table pgwide="1" frame="none" id="cec-caps">
+      <title>struct <structname>cec_caps</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>char</entry>
+	    <entry><structfield>driver[32]</structfield></entry>
+	    <entry>The name of the cec adapter driver.</entry>
+	  </row>
+	  <row>
+	    <entry>char</entry>
+	    <entry><structfield>name[32]</structfield></entry>
+	    <entry>The name of this CEC adapter. The combination <structfield>driver</structfield>
+	    and <structfield>name</structfield> must be unique.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>capabilities</structfield></entry>
+	    <entry>The capabilities of the CEC adapter, see <xref
+		linkend="cec-capabilities" />.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>version</structfield></entry>
+	    <entry>CEC Framework API version, formatted with the
+	    <constant>KERNEL_VERSION()</constant> macro.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-capabilities">
+      <title>CEC Capabilities Flags</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_CAP_PHYS_ADDR</constant></entry>
+	    <entry>0x00000001</entry>
+	    <entry>Userspace has to configure the physical address by
+	    calling &CEC-ADAP-S-PHYS-ADDR;. If this capability isn't set,
+	    then setting the physical address is handled by the kernel
+	    whenever the EDID is set (for an HDMI receiver) or read (for
+	    an HDMI transmitter).</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_CAP_LOG_ADDRS</constant></entry>
+	    <entry>0x00000002</entry>
+	    <entry>Userspace has to configure the logical addresses by
+	    calling &CEC-ADAP-S-LOG-ADDRS;. If this capability isn't set,
+	    then the kernel will have configured this.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_CAP_TRANSMIT</constant></entry>
+	    <entry>0x00000004</entry>
+	    <entry>Userspace can transmit CEC messages by calling &CEC-TRANSMIT;. This
+	    implies that userspace can be a follower as well, since being able to
+	    transmit messages is a prerequisite of becoming a follower. If this
+	    capability isn't set, then the kernel will handle all CEC transmits
+	    and process all CEC messages it receives.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_CAP_PASSTHROUGH</constant></entry>
+	    <entry>0x00000008</entry>
+	    <entry>Userspace can use the passthrough mode by
+	    calling &CEC-S-MODE;.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_CAP_RC</constant></entry>
+	    <entry>0x00000010</entry>
+	    <entry>This adapter supports the remote control protocol.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_CAP_MONITOR_ALL</constant></entry>
+	    <entry>0x00000020</entry>
+	    <entry>The CEC hardware can monitor all messages, not just directed and
+	    broadcast messages.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-ioc-adap-g-log-addrs.xml b/Documentation/DocBook/media/v4l/cec-ioc-adap-g-log-addrs.xml
new file mode 100644
index 000000000000..302b8294f7fc
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-ioc-adap-g-log-addrs.xml
@@ -0,0 +1,329 @@
+<refentry id="cec-ioc-adap-g-log-addrs">
+  <refmeta>
+    <refentrytitle>ioctl CEC_ADAP_G_LOG_ADDRS, CEC_ADAP_S_LOG_ADDRS</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>CEC_ADAP_G_LOG_ADDRS</refname>
+    <refname>CEC_ADAP_S_LOG_ADDRS</refname>
+    <refpurpose>Get or set the logical addresses</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct cec_log_addrs *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>File descriptor returned by
+	  <link linkend='cec-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>CEC_ADAP_G_LOG_ADDRS, CEC_ADAP_S_LOG_ADDRS</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>To query the current CEC logical addresses, applications call the
+<constant>CEC_ADAP_G_LOG_ADDRS</constant> ioctl with a pointer to a
+<structname>cec_log_addrs</structname> structure where the drivers stores the
+logical addresses.</para>
+
+    <para>To set new logical addresses, applications fill in struct <structname>cec_log_addrs</structname>
+and call the <constant>CEC_ADAP_S_LOG_ADDRS</constant> ioctl with a pointer to this struct.
+The <constant>CEC_ADAP_S_LOG_ADDRS</constant> ioctl is only available if
+<constant>CEC_CAP_LOG_ADDRS</constant> is set (&ENOTTY; is returned otherwise). This ioctl will block until all
+requested logical addresses have been claimed. <constant>CEC_ADAP_S_LOG_ADDRS</constant>
+can only be called by a file handle in initiator mode (see &CEC-S-MODE;).</para>
+
+    <table pgwide="1" frame="none" id="cec-log-addrs">
+      <title>struct <structname>cec_log_addrs</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>log_addr</structfield>[CEC_MAX_LOG_ADDRS]</entry>
+	    <entry>The actual logical addresses that were claimed. This is set by the
+	    driver. If no logical address could be claimed, then it is set to
+	    <constant>CEC_LOG_ADDR_INVALID</constant>. If this adapter is Unregistered,
+	    then <structfield>log_addr[0]</structfield> is set to 0xf and all others to
+	    <constant>CEC_LOG_ADDR_INVALID</constant>.</entry>
+	  </row>
+	  <row>
+	    <entry>__u16</entry>
+	    <entry><structfield>log_addr_mask</structfield></entry>
+	    <entry>The bitmask of all logical addresses this adapter has claimed.
+	    If this adapter is Unregistered then <structfield>log_addr_mask</structfield>
+	    sets bit 15 and clears all other bits. If this adapter is not configured at all, then
+	    <structfield>log_addr_mask</structfield> is set to 0. Set by the driver.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>cec_version</structfield></entry>
+	    <entry>The CEC version that this adapter shall use. See
+	    <xref linkend="cec-versions" />.
+	    Used to implement the <constant>CEC_MSG_CEC_VERSION</constant> and
+	    <constant>CEC_MSG_REPORT_FEATURES</constant> messages. Note that
+	    <constant>CEC_OP_CEC_VERSION_1_3A</constant> is not allowed
+	    by the CEC framework.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>num_log_addrs</structfield></entry>
+	    <entry>Number of logical addresses to set up. Must be &le;
+	    <structfield>available_log_addrs</structfield> as returned by
+	    &CEC-ADAP-G-CAPS;. All arrays in this structure are only filled up to
+	    index <structfield>available_log_addrs</structfield>-1. The remaining
+	    array elements will be ignored. Note that the CEC 2.0 standard allows
+	    for a maximum of 2 logical addresses, although some hardware has support
+	    for more. <constant>CEC_MAX_LOG_ADDRS</constant> is 4. The driver will
+	    return the actual number of logical addresses it could claim, which may
+	    be less than what was requested. If this field is set to 0, then the
+	    CEC adapter shall clear all claimed logical addresses and all other
+	    fields will be ignored.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>vendor_id</structfield></entry>
+	    <entry>The vendor ID is a 24-bit number that identifies the specific
+	    vendor or entity. Based on this ID vendor specific commands may be
+	    defined. If you do not want a vendor ID then set it to
+	    <constant>CEC_VENDOR_ID_NONE</constant>.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry>Flags. No flags are defined yet, so set this to 0.</entry>
+	  </row>
+	  <row>
+	    <entry>char</entry>
+	    <entry><structfield>osd_name</structfield>[15]</entry>
+	    <entry>The On-Screen Display name as is returned by the
+	    <constant>CEC_MSG_SET_OSD_NAME</constant> message.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>primary_device_type</structfield>[CEC_MAX_LOG_ADDRS]</entry>
+	    <entry>Primary device type for each logical address. See
+	    <xref linkend="cec-prim-dev-types" /> for possible types.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>log_addr_type</structfield>[CEC_MAX_LOG_ADDRS]</entry>
+	    <entry>Logical address types. See <xref linkend="cec-log-addr-types" /> for
+	    possible types. The driver will update this with the actual logical address
+	    type that it claimed (e.g. it may have to fallback to
+	    <constant>CEC_LOG_ADDR_TYPE_UNREGISTERED</constant>).</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>all_device_types</structfield>[CEC_MAX_LOG_ADDRS]</entry>
+	    <entry>CEC 2.0 specific: all device types. See <xref linkend="cec-all-dev-types-flags" />.
+	    Used to implement the <constant>CEC_MSG_REPORT_FEATURES</constant> message.
+	    This field is ignored if <structfield>cec_version</structfield> &lt;
+	    <constant>CEC_OP_CEC_VERSION_2_0</constant>.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>features</structfield>[CEC_MAX_LOG_ADDRS][12]</entry>
+	    <entry>Features for each logical address. Used to implement the
+	    <constant>CEC_MSG_REPORT_FEATURES</constant> message. The 12 bytes include
+	    both the RC Profile and the Device Features.
+	    This field is ignored if <structfield>cec_version</structfield> &lt;
+	    <constant>CEC_OP_CEC_VERSION_2_0</constant>.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-versions">
+      <title>CEC Versions</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_OP_CEC_VERSION_1_3A</constant></entry>
+	    <entry>4</entry>
+	    <entry>CEC version according to the HDMI 1.3a standard.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_CEC_VERSION_1_4B</constant></entry>
+	    <entry>5</entry>
+	    <entry>CEC version according to the HDMI 1.4b standard.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_CEC_VERSION_2_0</constant></entry>
+	    <entry>6</entry>
+	    <entry>CEC version according to the HDMI 2.0 standard.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-prim-dev-types">
+      <title>CEC Primary Device Types</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_OP_PRIM_DEVTYPE_TV</constant></entry>
+	    <entry>0</entry>
+	    <entry>Use for a TV.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_PRIM_DEVTYPE_RECORD</constant></entry>
+	    <entry>1</entry>
+	    <entry>Use for a recording device.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_PRIM_DEVTYPE_TUNER</constant></entry>
+	    <entry>3</entry>
+	    <entry>Use for a device with a tuner.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_PRIM_DEVTYPE_PLAYBACK</constant></entry>
+	    <entry>4</entry>
+	    <entry>Use for a playback device.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM</constant></entry>
+	    <entry>5</entry>
+	    <entry>Use for an audio system (e.g. an audio/video receiver).</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_PRIM_DEVTYPE_SWITCH</constant></entry>
+	    <entry>6</entry>
+	    <entry>Use for a CEC switch.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_PRIM_DEVTYPE_VIDEOPROC</constant></entry>
+	    <entry>7</entry>
+	    <entry>Use for a video processor device.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-log-addr-types">
+      <title>CEC Logical Address Types</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_LOG_ADDR_TYPE_TV</constant></entry>
+	    <entry>0</entry>
+	    <entry>Use for a TV.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_LOG_ADDR_TYPE_RECORD</constant></entry>
+	    <entry>1</entry>
+	    <entry>Use for a recording device.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_LOG_ADDR_TYPE_TUNER</constant></entry>
+	    <entry>2</entry>
+	    <entry>Use for a tuner device.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_LOG_ADDR_TYPE_PLAYBACK</constant></entry>
+	    <entry>3</entry>
+	    <entry>Use for a playback device.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_LOG_ADDR_TYPE_AUDIOSYSTEM</constant></entry>
+	    <entry>4</entry>
+	    <entry>Use for an audio system device.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_LOG_ADDR_TYPE_SPECIFIC</constant></entry>
+	    <entry>5</entry>
+	    <entry>Use for a second TV or for a video processor device.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_LOG_ADDR_TYPE_UNREGISTERED</constant></entry>
+	    <entry>6</entry>
+	    <entry>Use this if you just want to remain unregistered.
+	    Used for pure CEC switches or CDC-only devices (CDC:
+	    Capability Discovery and Control).</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-all-dev-types-flags">
+      <title>CEC All Device Types Flags</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_OP_ALL_DEVTYPE_TV</constant></entry>
+	    <entry>0x80</entry>
+	    <entry>This supports the TV type.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_ALL_DEVTYPE_RECORD</constant></entry>
+	    <entry>0x40</entry>
+	    <entry>This supports the Recording type.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_ALL_DEVTYPE_TUNER</constant></entry>
+	    <entry>0x20</entry>
+	    <entry>This supports the Tuner type.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_ALL_DEVTYPE_PLAYBACK</constant></entry>
+	    <entry>0x10</entry>
+	    <entry>This supports the Playback type.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_ALL_DEVTYPE_AUDIOSYSTEM</constant></entry>
+	    <entry>0x08</entry>
+	    <entry>This supports the Audio System type.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_OP_ALL_DEVTYPE_SWITCH</constant></entry>
+	    <entry>0x04</entry>
+	    <entry>This supports the CEC Switch or Video Processing type.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-ioc-adap-g-phys-addr.xml b/Documentation/DocBook/media/v4l/cec-ioc-adap-g-phys-addr.xml
new file mode 100644
index 000000000000..d95f1785080c
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-ioc-adap-g-phys-addr.xml
@@ -0,0 +1,86 @@
+<refentry id="cec-ioc-adap-g-phys-addr">
+  <refmeta>
+    <refentrytitle>ioctl CEC_ADAP_G_PHYS_ADDR, CEC_ADAP_S_PHYS_ADDR</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>CEC_ADAP_G_PHYS_ADDR</refname>
+    <refname>CEC_ADAP_S_PHYS_ADDR</refname>
+    <refpurpose>Get or set the physical address</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>__u16 *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>File descriptor returned by
+	  <link linkend='cec-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>CEC_ADAP_G_PHYS_ADDR, CEC_ADAP_S_PHYS_ADDR</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>To query the current physical address applications call the
+<constant>CEC_ADAP_G_PHYS_ADDR</constant> ioctl with a pointer to an __u16
+where the driver stores the physical address.</para>
+
+    <para>To set a new physical address applications store the physical address in
+an __u16 and call the <constant>CEC_ADAP_S_PHYS_ADDR</constant> ioctl with a
+pointer to this integer. <constant>CEC_ADAP_S_PHYS_ADDR</constant> is only
+available if <constant>CEC_CAP_PHYS_ADDR</constant> is set (&ENOTTY; will be returned
+otherwise). <constant>CEC_ADAP_S_PHYS_ADDR</constant>
+can only be called by a file handle in initiator mode (see &CEC-S-MODE;), if not
+&EBUSY; will be returned.</para>
+
+    <para>The physical address is a 16-bit number where each group of 4 bits
+represent a digit of the physical address a.b.c.d where the most significant
+4 bits represent 'a'. The CEC root device (usually the TV) has address 0.0.0.0.
+Every device that is hooked up to an input of the TV has address a.0.0.0 (where
+'a' is &ge; 1), devices hooked up to those in turn have addresses a.b.0.0, etc.
+So a topology of up to 5 devices deep is supported. The physical address a
+device shall use is stored in the EDID of the sink.</para>
+
+<para>For example, the EDID for each HDMI input of the TV will have a different
+physical address of the form a.0.0.0 that the sources will read out and use as
+their physical address.</para>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-ioc-dqevent.xml b/Documentation/DocBook/media/v4l/cec-ioc-dqevent.xml
new file mode 100644
index 000000000000..697dde575cd4
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-ioc-dqevent.xml
@@ -0,0 +1,202 @@
+<refentry id="cec-ioc-g-event">
+  <refmeta>
+    <refentrytitle>ioctl CEC_DQEVENT</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>CEC_DQEVENT</refname>
+    <refpurpose>Dequeue a CEC event</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct cec_event *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>File descriptor returned by
+	  <link linkend='cec-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>CEC_DQEVENT</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>CEC devices can send asynchronous events. These can be retrieved by calling
+    the <constant>CEC_DQEVENT</constant> ioctl. If the file descriptor is in non-blocking
+    mode and no event is pending, then it will return -1 and set errno to the &EAGAIN;.</para>
+
+    <para>The internal event queues are per-filehandle and per-event type. If there is
+    no more room in a queue then the last event is overwritten with the new one. This
+    means that intermediate results can be thrown away but that the latest event is always
+    available. This also means that is it possible to read two successive events that have
+    the same value (e.g. two CEC_EVENT_STATE_CHANGE events with the same state). In that
+    case the intermediate state changes were lost but it is guaranteed that the state
+    did change in between the two events.</para>
+
+    <table pgwide="1" frame="none" id="cec-event-state-change">
+      <title>struct <structname>cec_event_state_change</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u16</entry>
+	    <entry><structfield>phys_addr</structfield></entry>
+	    <entry>The current physical address.</entry>
+	  </row>
+	  <row>
+	    <entry>__u16</entry>
+	    <entry><structfield>log_addr_mask</structfield></entry>
+	    <entry>The current set of claimed logical addresses.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-event-lost-msgs">
+      <title>struct <structname>cec_event_lost_msgs</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>lost_msgs</structfield></entry>
+	    <entry>Set to the number of lost messages since the filehandle
+	    was opened or since the last time this event was dequeued for
+	    this filehandle. The messages lost are the oldest messages. So
+	    when a new message arrives and there is no more room, then the
+	    oldest message is discarded to make room for the new one. The
+	    internal size of the message queue guarantees that all messages
+	    received in the last two seconds will be stored. Since messages
+	    should be replied to within a second according to the CEC
+	    specification, this is more than enough.
+	    </entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-event">
+      <title>struct <structname>cec_event</structname></title>
+      <tgroup cols="4">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ts</structfield></entry>
+	    <entry>Timestamp of the event in ns.</entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>event</structfield></entry>
+	    <entry>The CEC event type, see <xref linkend="cec-events" />.</entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry>Event flags, see <xref linkend="cec-event-flags" />.</entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry>union</entry>
+	    <entry>(anonymous)</entry>
+	    <entry></entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry>struct cec_event_state_change</entry>
+	    <entry><structfield>state_change</structfield></entry>
+	    <entry>The new adapter state as sent by the <constant>CEC_EVENT_STATE_CHANGE</constant>
+	    event.</entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry>struct cec_event_lost_msgs</entry>
+	    <entry><structfield>lost_msgs</structfield></entry>
+	    <entry>The number of lost messages as sent by the <constant>CEC_EVENT_LOST_MSGS</constant>
+	    event.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-events">
+      <title>CEC Events Types</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_EVENT_STATE_CHANGE</constant></entry>
+	    <entry>1</entry>
+	    <entry>Generated when the CEC Adapter's state changes. When open() is
+	    called an initial event will be generated for that filehandle with the
+	    CEC Adapter's state at that time.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_EVENT_LOST_MSGS</constant></entry>
+	    <entry>2</entry>
+	    <entry>Generated if one or more CEC messages were lost because the
+	    application didn't dequeue CEC messages fast enough.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-event-flags">
+      <title>CEC Event Flags</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_EVENT_FL_INITIAL_VALUE</constant></entry>
+	    <entry>1</entry>
+	    <entry>Set for the initial events that are generated when the device is
+	    opened. See the table above for which events do this. This allows
+	    applications to learn the initial state of the CEC adapter at open()
+	    time.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-ioc-g-mode.xml b/Documentation/DocBook/media/v4l/cec-ioc-g-mode.xml
new file mode 100644
index 000000000000..26b4282ad134
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-ioc-g-mode.xml
@@ -0,0 +1,255 @@
+<refentry id="cec-ioc-g-mode">
+  <refmeta>
+    <refentrytitle>ioctl CEC_G_MODE, CEC_S_MODE</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>CEC_G_MODE</refname>
+    <refname>CEC_S_MODE</refname>
+    <refpurpose>Get or set exclusive use of the CEC adapter</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>__u32 *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>File descriptor returned by
+	  <link linkend='cec-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>CEC_G_MODE, CEC_S_MODE</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>By default any filehandle can use &CEC-TRANSMIT; and &CEC-RECEIVE;, but
+in order to prevent applications from stepping on each others toes it must be possible
+to obtain exclusive access to the CEC adapter. This ioctl sets the filehandle
+to initiator and/or follower mode which can be exclusive depending on the chosen
+mode. The initiator is the filehandle that is used
+to initiate messages, i.e. it commands other CEC devices. The follower is the filehandle
+that receives messages sent to the CEC adapter and processes them. The same filehandle
+can be both initiator and follower, or this role can be taken by two different
+filehandles.</para>
+
+    <para>When a CEC message is received, then the CEC framework will decide how
+it will be processed. If the message is a reply to an earlier transmitted message,
+then the reply is sent back to the filehandle that is waiting for it. In addition
+the CEC framework will process it.</para>
+
+    <para>If the message is not a reply, then the CEC framework will process it
+first. If there is no follower, then the message is just discarded and a feature
+abort is sent back to the initiator if the framework couldn't process it. If there
+is a follower, then the message is passed on to the follower who will use
+&CEC-RECEIVE; to dequeue the new message. The framework expects the follower to
+make the right decisions.</para>
+
+    <para>The CEC framework will process core messages unless requested otherwise
+by the follower. The follower can enable the passthrough mode. In that case, the
+CEC framework will pass on most core messages without processing them and
+the follower will have to implement those messages. There are some messages
+that the core will always process, regardless of the passthrough mode. See
+<xref linkend="cec-core-processing" /> for details.</para>
+
+    <para>If there is no initiator, then any CEC filehandle can use &CEC-TRANSMIT;.
+If there is an exclusive initiator then only that initiator can call &CEC-TRANSMIT;.
+The follower can of course always call &CEC-TRANSMIT;.</para>
+
+    <para>Available initiator modes are:</para>
+
+    <table pgwide="1" frame="none" id="cec-mode-initiator">
+      <title>Initiator Modes</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_MODE_NO_INITIATOR</constant></entry>
+	    <entry>0x0</entry>
+	    <entry>This is not an initiator, i.e. it cannot transmit CEC messages
+	    or make any other changes to the CEC adapter.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MODE_INITIATOR</constant></entry>
+	    <entry>0x1</entry>
+	    <entry>This is an initiator (the default when the device is opened) and it
+	    can transmit CEC messages and make changes to the CEC adapter, unless there
+	    is an exclusive initiator.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MODE_EXCL_INITIATOR</constant></entry>
+	    <entry>0x2</entry>
+	    <entry>This is an exclusive initiator and this file descriptor is the only one
+	    that can transmit CEC messages and make changes to the CEC adapter. If someone
+	    else is already the exclusive initiator then an attempt to become one will return
+	    the &EBUSY; error.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <para>Available follower modes are:</para>
+
+    <table pgwide="1" frame="none" id="cec-mode-follower">
+      <title>Follower Modes</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_MODE_NO_FOLLOWER</constant></entry>
+	    <entry>0x00</entry>
+	    <entry>This is not a follower (the default when the device is opened).</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MODE_FOLLOWER</constant></entry>
+	    <entry>0x10</entry>
+	    <entry>This is a follower and it will receive CEC messages unless there is
+	    an exclusive follower. You cannot become a follower if <constant>CEC_CAP_TRANSMIT</constant>
+	    is not set or if <constant>CEC_MODE_NO_INITIATOR</constant> was specified,
+	    &EINVAL; is returned in that case.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MODE_EXCL_FOLLOWER</constant></entry>
+	    <entry>0x20</entry>
+	    <entry>This is an exclusive follower and only this file descriptor will receive
+	    CEC messages for processing. If someone else is already the exclusive follower
+	    then an attempt to become one will return the &EBUSY; error. You cannot become
+	    a follower if <constant>CEC_CAP_TRANSMIT</constant> is not set or if
+	    <constant>CEC_MODE_NO_INITIATOR</constant> was specified, &EINVAL; is returned
+	    in that case.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MODE_EXCL_FOLLOWER_PASSTHRU</constant></entry>
+	    <entry>0x30</entry>
+	    <entry>This is an exclusive follower and only this file descriptor will receive
+	    CEC messages for processing. In addition it will put the CEC device into
+	    passthrough mode, allowing the exclusive follower to handle most core messages
+	    instead of relying on the CEC framework for that. If someone else is already the
+	    exclusive follower then an attempt to become one will return the &EBUSY; error.
+	    You cannot become a follower if <constant>CEC_CAP_TRANSMIT</constant>
+            is not set or if <constant>CEC_MODE_NO_INITIATOR</constant> was specified,
+            &EINVAL; is returned in that case.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MODE_MONITOR</constant></entry>
+	    <entry>0xe0</entry>
+	    <entry>Put the file descriptor into monitor mode. Can only be used in combination
+	    with <constant>CEC_MODE_NO_INITIATOR</constant>, otherwise &EINVAL; will be
+	    returned. In monitor mode all messages this CEC device transmits and all messages
+	    it receives (both broadcast messages and directed messages for one its logical
+	    addresses) will be reported. This is very useful for debugging. This is only
+	    allowed if the process has the <constant>CAP_NET_ADMIN</constant>
+	    capability. If that is not set, then &EPERM; is returned.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MODE_MONITOR_ALL</constant></entry>
+	    <entry>0xf0</entry>
+	    <entry>Put the file descriptor into 'monitor all' mode. Can only be used in combination
+            with <constant>CEC_MODE_NO_INITIATOR</constant>, otherwise &EINVAL; will be
+            returned. In 'monitor all' mode all messages this CEC device transmits and all messages
+            it receives, including directed messages for other CEC devices will be reported. This
+	    is very useful for debugging, but not all devices support this. This mode requires that
+	    the <constant>CEC_CAP_MONITOR_ALL</constant> capability is set, otherwise &EINVAL; is
+	    returned. This is only allowed if the process has the <constant>CAP_NET_ADMIN</constant>
+	    capability. If that is not set, then &EPERM; is returned.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <para>Core message processing details:</para>
+
+    <table pgwide="1" frame="none" id="cec-core-processing">
+      <title>Core Message Processing</title>
+      <tgroup cols="2">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_MSG_GET_CEC_VERSION</constant></entry>
+	    <entry>When in passthrough mode this message has to be handled by userspace,
+	    otherwise the core will return the CEC version that was set with &CEC-ADAP-S-LOG-ADDRS;.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_GIVE_DEVICE_VENDOR_ID</constant></entry>
+	    <entry>When in passthrough mode this message has to be handled by userspace,
+	    otherwise the core will return the vendor ID that was set with &CEC-ADAP-S-LOG-ADDRS;.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_ABORT</constant></entry>
+	    <entry>When in passthrough mode this message has to be handled by userspace,
+	    otherwise the core will return a feature refused message as per the specification.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_GIVE_PHYSICAL_ADDR</constant></entry>
+	    <entry>When in passthrough mode this message has to be handled by userspace,
+	    otherwise the core will report the current physical address.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_GIVE_OSD_NAME</constant></entry>
+	    <entry>When in passthrough mode this message has to be handled by userspace,
+	    otherwise the core will report the current OSD name as was set with
+	    &CEC-ADAP-S-LOG-ADDRS;.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_GIVE_FEATURES</constant></entry>
+	    <entry>When in passthrough mode this message has to be handled by userspace,
+	    otherwise the core will report the current features as was set with
+	    &CEC-ADAP-S-LOG-ADDRS; or the message is ignore if the CEC version was
+	    older than 2.0.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_USER_CONTROL_PRESSED</constant></entry>
+	    <entry>If <constant>CEC_CAP_RC</constant> is set, then generate a remote control
+	    key press. This message is always passed on to userspace.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_USER_CONTROL_RELEASED</constant></entry>
+	    <entry>If <constant>CEC_CAP_RC</constant> is set, then generate a remote control
+	    key release. This message is always passed on to userspace.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_MSG_REPORT_PHYSICAL_ADDR</constant></entry>
+	    <entry>The CEC framework will make note of the reported physical address
+	    and then just pass the message on to userspace.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/cec-ioc-receive.xml b/Documentation/DocBook/media/v4l/cec-ioc-receive.xml
new file mode 100644
index 000000000000..fde9f8678e67
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/cec-ioc-receive.xml
@@ -0,0 +1,274 @@
+<refentry id="cec-ioc-receive">
+  <refmeta>
+    <refentrytitle>ioctl CEC_RECEIVE, CEC_TRANSMIT</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>CEC_RECEIVE</refname>
+    <refname>CEC_TRANSMIT</refname>
+    <refpurpose>Receive or transmit a CEC message</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct cec_msg *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>File descriptor returned by
+	  <link linkend='cec-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>CEC_RECEIVE, CEC_TRANSMIT</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Note: this documents the proposed CEC API. This API is not yet finalized and
+      is currently only available as a staging kernel module.
+    </para>
+
+    <para>To receive a CEC message the application has to fill in the
+    <structname>cec_msg</structname> structure and pass it to the
+    <constant>CEC_RECEIVE</constant> ioctl. <constant>CEC_RECEIVE</constant> is
+    only available if <constant>CEC_CAP_RECEIVE</constant> is set. If the
+    file descriptor is in non-blocking mode and there are no received
+    messages pending, then it will return -1 and set errno to the &EAGAIN;.
+    If the file descriptor is in blocking mode and <structfield>timeout</structfield>
+    is non-zero and no message arrived within <structfield>timeout</structfield>
+    milliseconds, then it will return -1 and set errno to the &ETIMEDOUT;.</para>
+
+    <para>To send a CEC message the application has to fill in the
+    <structname>cec_msg</structname> structure and pass it to the
+    <constant>CEC_TRANSMIT</constant> ioctl. <constant>CEC_TRANSMIT</constant> is
+    only available if <constant>CEC_CAP_TRANSMIT</constant> is set.
+    If there is no more room in the transmit queue, then it will return
+    -1 and set errno to the &EBUSY;.</para>
+
+    <table pgwide="1" frame="none" id="cec-msg">
+      <title>struct <structname>cec_msg</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ts</structfield></entry>
+	    <entry>Timestamp of when the message was transmitted in ns in the case
+	    of <constant>CEC_TRANSMIT</constant> with <structfield>reply</structfield>
+	    set to 0, or the timestamp of the received message in all other cases.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>len</structfield></entry>
+	    <entry>The length of the message. For <constant>CEC_TRANSMIT</constant> this
+	    is filled in by the application. The driver will fill this in for
+	    <constant>CEC_RECEIVE</constant> and for <constant>CEC_TRANSMIT</constant>
+	    it will be filled in with the length of the reply message if
+	    <structfield>reply</structfield> was set.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>timeout</structfield></entry>
+	    <entry>The timeout in milliseconds. This is the time the device will wait for a message to
+	    be received before timing out. If it is set to 0, then it will wait indefinitely when it
+	    is called by <constant>CEC_RECEIVE</constant>. If it is 0 and it is called by
+	    <constant>CEC_TRANSMIT</constant>, then it will be replaced by 1000 if the
+	    <structfield>reply</structfield> is non-zero or ignored if <structfield>reply</structfield>
+	    is 0.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>sequence</structfield></entry>
+	    <entry>The sequence number is automatically assigned by the CEC
+	    framework for all transmitted messages. It can be later used by the
+	    framework to generate an event if a reply for a message was
+	    requested and the message was transmitted in a non-blocking mode.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry>Flags. No flags are defined yet, so set this to 0.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>rx_status</structfield></entry>
+	    <entry>The status bits of the received message. See <xref linkend="cec-rx-status" />
+	    for the possible status values. It is 0 if this message was transmitted, not
+	    received, unless this is the reply to a transmitted message. In that case both
+	    <structfield>rx_status</structfield> and <structfield>tx_status</structfield>
+	    are set.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>tx_status</structfield></entry>
+	    <entry>The status bits of the transmitted message. See <xref linkend="cec-tx-status" />
+	    for the possible status values. It is 0 if this messages was received, not
+	    transmitted.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>msg</structfield>[16]</entry>
+	    <entry>The message payload. For <constant>CEC_TRANSMIT</constant> this
+	    is filled in by the application. The driver will fill this in for
+	    <constant>CEC_RECEIVE</constant> and for <constant>CEC_TRANSMIT</constant>
+	    it will be filled in with the payload of the reply message if
+	    <structfield>reply</structfield> was set.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>reply</structfield></entry>
+	    <entry>Wait until this message is replied. If <structfield>reply</structfield>
+	    is 0 and the <structfield>timeout</structfield> is 0, then don't wait for a reply but
+	    return after transmitting the message. If there was an error as indicated by a non-zero
+	    <structfield>tx_status</structfield> field, then <structfield>reply</structfield> and
+	    <structfield>timeout</structfield> are both set to 0 by the driver. Ignored by
+	    <constant>CEC_RECEIVE</constant>. The case where <structfield>reply</structfield> is 0
+	    (this is the opcode for the Feature Abort message) and <structfield>timeout</structfield>
+	    is non-zero is specifically allowed to send a message and wait up to <structfield>timeout</structfield>
+	    milliseconds for a Feature Abort reply. In this case <structfield>rx_status</structfield>
+	    will either be set to <constant>CEC_RX_STATUS_TIMEOUT</constant> or
+	    <constant>CEC_RX_STATUS_FEATURE_ABORT</constant>.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>tx_arb_lost_cnt</structfield></entry>
+	    <entry>A counter of the number of transmit attempts that resulted in the
+	    Arbitration Lost error. This is only set if the hardware supports this, otherwise
+	    it is always 0. This counter is only valid if the <constant>CEC_TX_STATUS_ARB_LOST</constant>
+	    status bit is set.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>tx_nack_cnt</structfield></entry>
+	    <entry>A counter of the number of transmit attempts that resulted in the
+	    Not Acknowledged error. This is only set if the hardware supports this, otherwise
+	    it is always 0. This counter is only valid if the <constant>CEC_TX_STATUS_NACK</constant>
+            status bit is set.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>tx_low_drive_cnt</structfield></entry>
+	    <entry>A counter of the number of transmit attempts that resulted in the
+	    Arbitration Lost error. This is only set if the hardware supports this, otherwise
+	    it is always 0. This counter is only valid if the <constant>CEC_TX_STATUS_LOW_DRIVE</constant>
+            status bit is set.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>tx_error_cnt</structfield></entry>
+	    <entry>A counter of the number of transmit errors other than Arbitration Lost
+	    or Not Acknowledged. This is only set if the hardware supports this, otherwise
+	    it is always 0. This counter is only valid if the <constant>CEC_TX_STATUS_ERROR</constant>
+	    status bit is set.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-tx-status">
+      <title>CEC Transmit Status</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_TX_STATUS_OK</constant></entry>
+	    <entry>0x01</entry>
+	    <entry>The message was transmitted successfully. This is mutually exclusive with
+	    <constant>CEC_TX_STATUS_MAX_RETRIES</constant>. Other bits can still be set if
+	    earlier attempts met with failure before the transmit was eventually successful.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_TX_STATUS_ARB_LOST</constant></entry>
+	    <entry>0x02</entry>
+	    <entry>CEC line arbitration was lost.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_TX_STATUS_NACK</constant></entry>
+	    <entry>0x04</entry>
+	    <entry>Message was not acknowledged.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_TX_STATUS_LOW_DRIVE</constant></entry>
+	    <entry>0x08</entry>
+	    <entry>Low drive was detected on the CEC bus. This indicates that a follower
+	    detected an error on the bus and requests a retransmission.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_TX_STATUS_ERROR</constant></entry>
+	    <entry>0x10</entry>
+	    <entry>Some error occurred. This is used for any errors that do not
+	    fit the previous two, either because the hardware could not tell
+	    which error occurred, or because the hardware tested for other conditions
+	    besides those two.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_TX_STATUS_MAX_RETRIES</constant></entry>
+	    <entry>0x20</entry>
+	    <entry>The transmit failed after one or more retries. This status bit is mutually
+	    exclusive with <constant>CEC_TX_STATUS_OK</constant>. Other bits can still be set
+	    to explain which failures were seen.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="cec-rx-status">
+      <title>CEC Receive Status</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>CEC_RX_STATUS_OK</constant></entry>
+	    <entry>0x01</entry>
+	    <entry>The message was received successfully.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_RX_STATUS_TIMEOUT</constant></entry>
+	    <entry>0x02</entry>
+	    <entry>The reply to an earlier transmitted message timed out.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>CEC_RX_STATUS_FEATURE_ABORT</constant></entry>
+	    <entry>0x04</entry>
+	    <entry>The message was received successfully but the reply was
+	    <constant>CEC_MSG_FEATURE_ABORT</constant>. This status is only
+	    set if this message was the reply to an earlier transmitted
+	    message.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/io.xml b/Documentation/DocBook/media/v4l/io.xml
index e09025db92bd..21a3dde8f95d 100644
--- a/Documentation/DocBook/media/v4l/io.xml
+++ b/Documentation/DocBook/media/v4l/io.xml
@@ -88,7 +88,7 @@ function.<footnote>
 <structfield>capabilities</structfield> field of &v4l2-capability;
 returned by the &VIDIOC-QUERYCAP; ioctl is set. There are two
 streaming methods, to determine if the memory mapping flavor is
-supported applications must call the &VIDIOC-REQBUFS; ioctl.</para>
+supported applications must call the &VIDIOC-REQBUFS; ioctl with the memory type set to <constant>V4L2_MEMORY_MMAP</constant>.</para>
 
     <para>Streaming is an I/O method where only pointers to buffers
 are exchanged between application and driver, the data itself is not
@@ -369,7 +369,7 @@ rest should be evident.</para>
 <structfield>capabilities</structfield> field of &v4l2-capability;
 returned by the &VIDIOC-QUERYCAP; ioctl is set. If the particular user
 pointer method (not only memory mapping) is supported must be
-determined by calling the &VIDIOC-REQBUFS; ioctl.</para>
+determined by calling the &VIDIOC-REQBUFS; ioctl with the memory type set to <constant>V4L2_MEMORY_USERPTR</constant>.</para>
 
     <para>This I/O method combines advantages of the read/write and
 memory mapping methods. Buffers (planes) are allocated by the application
diff --git a/Documentation/DocBook/media/v4l/lirc_device_interface.xml b/Documentation/DocBook/media/v4l/lirc_device_interface.xml
index 34cada2ca710..71f9dbb81ec7 100644
--- a/Documentation/DocBook/media/v4l/lirc_device_interface.xml
+++ b/Documentation/DocBook/media/v4l/lirc_device_interface.xml
@@ -157,7 +157,7 @@ on working with the default settings initially.</para>
   <varlistentry>
     <term>LIRC_SET_{SEND,REC}_CARRIER</term>
     <listitem>
-      <para>Set send/receive carrier (in Hz).</para>
+      <para>Set send/receive carrier (in Hz). Return 0 on success.</para>
     </listitem>
   </varlistentry>
   <varlistentry>
diff --git a/Documentation/DocBook/media/v4l/media-types.xml b/Documentation/DocBook/media/v4l/media-types.xml
index 5e3f20fdcf17..95aa1f9c836a 100644
--- a/Documentation/DocBook/media/v4l/media-types.xml
+++ b/Documentation/DocBook/media/v4l/media-types.xml
@@ -121,6 +121,70 @@
 	    <entry><constant>MEDIA_ENT_F_AUDIO_MIXER</constant></entry>
 	    <entry>Audio Mixer Function Entity.</entry>
 	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_PROC_VIDEO_COMPOSER</constant></entry>
+	    <entry>Video composer (blender). An entity capable of video
+		   composing must have at least two sink pads and one source
+		   pad, and composes input video frames onto output video
+		   frames. Composition can be performed using alpha blending,
+		   color keying, raster operations (ROP), stitching or any other
+		   means.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER</constant></entry>
+	    <entry>Video pixel formatter. An entity capable of pixel formatting
+		   must have at least one sink pad and one source pad. Read
+		   pixel formatters read pixels from memory and perform a subset
+		   of unpacking, cropping, color keying, alpha multiplication
+		   and pixel encoding conversion. Write pixel formatters perform
+		   a subset of dithering, pixel encoding conversion and packing
+		   and write pixels to memory.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV</constant></entry>
+	    <entry>Video pixel encoding converter. An entity capable of pixel
+		   enconding conversion must have at least one sink pad and one
+		   source pad, and convert the encoding of pixels received on
+		   its sink pad(s) to a different encoding output on its source
+		   pad(s). Pixel encoding conversion includes but isn't limited
+		   to RGB to/from HSV, RGB to/from YUV and CFA (Bayer) to RGB
+		   conversions.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_PROC_VIDEO_LUT</constant></entry>
+	    <entry>Video look-up table. An entity capable of video lookup table
+		   processing must have one sink pad and one source pad. It uses
+		   the values of the pixels received on its sink pad to look up
+		   entries in internal tables and output them on its source pad.
+		   The lookup processing can be performed on all components
+		   separately or combine them for multi-dimensional table
+		   lookups.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_PROC_VIDEO_SCALER</constant></entry>
+	    <entry>Video scaler. An entity capable of video scaling must have
+		   at least one sink pad and one source pad, and scale the
+		   video frame(s) received on its sink pad(s) to a different
+		   resolution output on its source pad(s). The range of
+		   supported scaling ratios is entity-specific and can differ
+		   between the horizontal and vertical directions (in particular
+		   scaling can be supported in one direction only). Binning and
+		   skipping are considered as scaling.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_PROC_VIDEO_STATISTICS</constant></entry>
+	    <entry>Video statistics computation (histogram, 3A, ...). An entity
+		   capable of statistics computation must have one sink pad and
+		   one source pad. It computes statistics over the frames
+		   received on its sink pad and outputs the statistics data on
+		   its source pad.
+	    </entry>
+	  </row>
 	</tbody>
       </tgroup>
     </table>
diff --git a/Documentation/DocBook/media/v4l/pixfmt-z16.xml b/Documentation/DocBook/media/v4l/pixfmt-z16.xml
index 3d87e4bf87b8..1d9cb1684bd3 100644
--- a/Documentation/DocBook/media/v4l/pixfmt-z16.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt-z16.xml
@@ -5,7 +5,7 @@
   </refmeta>
   <refnamediv>
     <refname><constant>V4L2_PIX_FMT_Z16</constant></refname>
-    <refpurpose>Interleaved grey-scale image, e.g. from a stereo-pair</refpurpose>
+    <refpurpose>16-bit depth data with distance values at each pixel</refpurpose>
   </refnamediv>
   <refsect1>
     <title>Description</title>
diff --git a/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml b/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml
index 0f193fda0470..6f529e100ea4 100644
--- a/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml
@@ -6,7 +6,7 @@
 
   <refnamediv>
     <refname>VIDIOC_REQBUFS</refname>
-    <refpurpose>Initiate Memory Mapping or User Pointer I/O</refpurpose>
+    <refpurpose>Initiate Memory Mapping, User Pointer or DMA Buffer I/O</refpurpose>
   </refnamediv>
 
   <refsynopsisdiv>
diff --git a/Documentation/DocBook/media_api.tmpl b/Documentation/DocBook/media_api.tmpl
index 7b77e0f7b87d..a2765d8ad05c 100644
--- a/Documentation/DocBook/media_api.tmpl
+++ b/Documentation/DocBook/media_api.tmpl
@@ -75,7 +75,7 @@
 	    </mediaobject>
 	</figure>
 	<para>The media infrastructure API was designed to control such
-	    devices. It is divided into four parts.</para>
+	    devices. It is divided into five parts.</para>
 	<para>The first part covers radio, video capture and output,
 		cameras, analog TV devices and codecs.</para>
 	<para>The second part covers the
@@ -87,6 +87,7 @@
 		<xref linkend="fe-delivery-system-t" />.</para>
 	<para>The third part covers the Remote Controller API.</para>
 	<para>The fourth part covers the Media Controller API.</para>
+	<para>The fifth part covers the CEC (Consumer Electronics Control) API.</para>
 	<para>It should also be noted that a media device may also have audio
 	      components, like mixers, PCM capture, PCM playback, etc, which
 	      are controlled via ALSA API.</para>
@@ -107,6 +108,9 @@
 <part id="media_common">
 &sub-media-controller;
 </part>
+<part id="cec">
+&sub-cec-api;
+</part>
 
 <chapter id="gen_errors">
 &sub-gen-errors;
diff --git a/Documentation/Makefile.sphinx b/Documentation/Makefile.sphinx
new file mode 100644
index 000000000000..d8d13c92a178
--- /dev/null
+++ b/Documentation/Makefile.sphinx
@@ -0,0 +1,78 @@
+# -*- makefile -*-
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXBUILD   = sphinx-build
+SPHINXOPTS    =
+PAPER         =
+BUILDDIR      = $(obj)/output
+
+# User-friendly check for sphinx-build
+HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi)
+
+ifeq ($(HAVE_SPHINX),0)
+
+.DEFAULT:
+	$(warning The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed and in PATH, or set the SPHINXBUILD make variable to point to the full path of the '$(SPHINXBUILD)' executable.)
+	@echo "  SKIP    Sphinx $@ target."
+
+else ifneq ($(DOCBOOKS),)
+
+# Skip Sphinx build if the user explicitly requested DOCBOOKS.
+.DEFAULT:
+	@echo "  SKIP    Sphinx $@ target (DOCBOOKS specified)."
+
+else # HAVE_SPHINX
+
+# User-friendly check for rst2pdf
+HAVE_RST2PDF := $(shell if python -c "import rst2pdf" >/dev/null 2>&1; then echo 1; else echo 0; fi)
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+KERNELDOC       = $(srctree)/scripts/kernel-doc
+KERNELDOC_CONF  = -D kerneldoc_srctree=$(srctree) -D kerneldoc_bin=$(KERNELDOC)
+ALLSPHINXOPTS   = -D version=$(KERNELVERSION) -D release=$(KERNELRELEASE) -d $(BUILDDIR)/.doctrees $(KERNELDOC_CONF) $(PAPEROPT_$(PAPER)) -c $(srctree)/$(src) $(SPHINXOPTS) $(srctree)/$(src)
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+quiet_cmd_sphinx = SPHINX  $@
+      cmd_sphinx = $(SPHINXBUILD) -b $2 $(ALLSPHINXOPTS) $(BUILDDIR)/$2
+
+htmldocs:
+	$(call cmd,sphinx,html)
+
+pdfdocs:
+ifeq ($(HAVE_RST2PDF),0)
+	$(warning The Python 'rst2pdf' module was not found. Make sure you have the module installed to produce PDF output.)
+	@echo "  SKIP    Sphinx $@ target."
+else # HAVE_RST2PDF
+	$(call cmd,sphinx,pdf)
+endif # HAVE_RST2PDF
+
+epubdocs:
+	$(call cmd,sphinx,epub)
+
+xmldocs:
+	$(call cmd,sphinx,xml)
+
+# no-ops for the Sphinx toolchain
+sgmldocs:
+psdocs:
+mandocs:
+installmandocs:
+cleanmediadocs:
+
+cleandocs:
+	$(Q)rm -rf $(BUILDDIR)
+
+dochelp:
+	@echo  ' Linux kernel internal documentation in different formats (Sphinx):'
+	@echo  '  htmldocs        - HTML'
+	@echo  '  pdfdocs         - PDF'
+	@echo  '  epubdocs        - EPUB'
+	@echo  '  xmldocs         - XML'
+	@echo  '  cleandocs       - clean all generated files'
+
+endif # HAVE_SPHINX
diff --git a/Documentation/acpi/aml-debugger.txt b/Documentation/acpi/aml-debugger.txt
new file mode 100644
index 000000000000..5f62aa4a493b
--- /dev/null
+++ b/Documentation/acpi/aml-debugger.txt
@@ -0,0 +1,66 @@
+The AML Debugger
+
+Copyright (C) 2016, Intel Corporation
+Author: Lv Zheng <lv.zheng@intel.com>
+
+
+This document describes the usage of the AML debugger embedded in the Linux
+kernel.
+
+1. Build the debugger
+
+   The following kernel configuration items are required to enable the AML
+   debugger interface from the Linux kernel:
+
+   CONFIG_ACPI_DEBUGGER=y
+   CONFIG_ACPI_DEBUGGER_USER=m
+
+   The userspace utlities can be built from the kernel source tree using
+   the following commands:
+
+   $ cd tools
+   $ make acpi
+
+   The resultant userspace tool binary is then located at:
+
+     tools/acpi/power/acpi/acpidbg/acpidbg
+
+   It can be installed to system directories by running "make install" (as a
+   sufficiently privileged user).
+
+2. Start the userspace debugger interface
+
+   After booting the kernel with the debugger built-in, the debugger can be
+   started by using the following commands:
+
+   # mount -t debugfs none /sys/kernel/debug
+   # modprobe acpi_dbg
+   # tools/acpi/power/acpi/acpidbg/acpidbg
+
+   That spawns the interactive AML debugger environment where you can execute
+   debugger commands.
+
+   The commands are documented in the "ACPICA Overview and Programmer Reference"
+   that can be downloaded from
+
+   https://acpica.org/documentation
+
+   The detailed debugger commands reference is located in Chapter 12 "ACPICA
+   Debugger Reference".  The "help" command can be used for a quick reference.
+
+3. Stop the userspace debugger interface
+
+   The interactive debugger interface can be closed by pressing Ctrl+C or using
+   the "quit" or "exit" commands.  When finished, unload the module with:
+
+   # rmmod acpi_dbg
+
+   The module unloading may fail if there is an acpidbg instance running.
+
+4. Run the debugger in a script
+
+   It may be useful to run the AML debugger in a test script. "acpidbg" supports
+   this in a special "batch" mode.  For example, the following command outputs
+   the entire ACPI namespace:
+
+   # acpidbg -b "namespace"
diff --git a/Documentation/acpi/linuxized-acpica.txt b/Documentation/acpi/linuxized-acpica.txt
new file mode 100644
index 000000000000..defe2eec5331
--- /dev/null
+++ b/Documentation/acpi/linuxized-acpica.txt
@@ -0,0 +1,262 @@
+Linuxized ACPICA - Introduction to ACPICA Release Automation
+
+Copyright (C) 2013-2016, Intel Corporation
+Author: Lv Zheng <lv.zheng@intel.com>
+
+
+Abstract:
+
+This document describes the ACPICA project and the relationship between
+ACPICA and Linux.  It also describes how ACPICA code in drivers/acpi/acpica,
+include/acpi and tools/power/acpi is automatically updated to follow the
+upstream.
+
+
+1. ACPICA Project
+
+   The ACPI Component Architecture (ACPICA) project provides an operating
+   system (OS)-independent reference implementation of the Advanced
+   Configuration and Power Interface Specification (ACPI).  It has been
+   adapted by various host OSes.  By directly integrating ACPICA, Linux can
+   also benefit from the application experiences of ACPICA from other host
+   OSes.
+
+   The homepage of ACPICA project is: www.acpica.org, it is maintained and
+   supported by Intel Corporation.
+
+   The following figure depicts the Linux ACPI subystem where the ACPICA
+   adaptation is included:
+
+      +---------------------------------------------------------+
+      |                                                         |
+      |   +---------------------------------------------------+ |
+      |   | +------------------+                              | |
+      |   | | Table Management |                              | |
+      |   | +------------------+                              | |
+      |   | +----------------------+                          | |
+      |   | | Namespace Management |                          | |
+      |   | +----------------------+                          | |
+      |   | +------------------+       ACPICA Components      | |
+      |   | | Event Management |                              | |
+      |   | +------------------+                              | |
+      |   | +---------------------+                           | |
+      |   | | Resource Management |                           | |
+      |   | +---------------------+                           | |
+      |   | +---------------------+                           | |
+      |   | | Hardware Management |                           | |
+      |   | +---------------------+                           | |
+      | +---------------------------------------------------+ | |
+      | | |                            +------------------+ | | |
+      | | |                            | OS Service Layer | | | |
+      | | |                            +------------------+ | | |
+      | | +-------------------------------------------------|-+ |
+      | |   +--------------------+                          |   |
+      | |   | Device Enumeration |                          |   |
+      | |   +--------------------+                          |   |
+      | |   +------------------+                            |   |
+      | |   | Power Management |                            |   |
+      | |   +------------------+     Linux/ACPI Components  |   |
+      | |   +--------------------+                          |   |
+      | |   | Thermal Management |                          |   |
+      | |   +--------------------+                          |   |
+      | |   +--------------------------+                    |   |
+      | |   | Drivers for ACPI Devices |                    |   |
+      | |   +--------------------------+                    |   |
+      | |   +--------+                                      |   |
+      | |   | ...... |                                      |   |
+      | |   +--------+                                      |   |
+      | +---------------------------------------------------+   |
+      |                                                         |
+      +---------------------------------------------------------+
+
+                 Figure 1. Linux ACPI Software Components
+
+   NOTE:
+    A. OS Service Layer - Provided by Linux to offer OS dependent
+       implementation of the predefined ACPICA interfaces (acpi_os_*).
+         include/acpi/acpiosxf.h
+         drivers/acpi/osl.c
+         include/acpi/platform
+         include/asm/acenv.h
+    B. ACPICA Functionality - Released from ACPICA code base to offer
+       OS independent implementation of the ACPICA interfaces (acpi_*).
+         drivers/acpi/acpica
+         include/acpi/ac*.h
+         tools/power/acpi
+    C. Linux/ACPI Functionality - Providing Linux specific ACPI
+       functionality to the other Linux kernel subsystems and user space
+       programs.
+         drivers/acpi
+         include/linux/acpi.h
+         include/linux/acpi*.h
+         include/acpi
+         tools/power/acpi
+    D. Architecture Specific ACPICA/ACPI Functionalities - Provided by the
+       ACPI subsystem to offer architecture specific implementation of the
+       ACPI interfaces.  They are Linux specific components and are out of
+       the scope of this document.
+         include/asm/acpi.h
+         include/asm/acpi*.h
+         arch/*/acpi
+
+2. ACPICA Release
+
+   The ACPICA project maintains its code base at the following repository URL:
+   https://github.com/acpica/acpica.git. As a rule, a release is made every
+   month.
+
+   As the coding style adopted by the ACPICA project is not acceptable by
+   Linux, there is a release process to convert the ACPICA git commits into
+   Linux patches.  The patches generated by this process are referred to as
+   "linuxized ACPICA patches".  The release process is carried out on a local
+   copy the ACPICA git repository.  Each commit in the monthly release is
+   converted into a linuxized ACPICA patch.  Together, they form the montly
+   ACPICA release patchset for the Linux ACPI community.  This process is
+   illustrated in the following figure:
+
+    +-----------------------------+
+    | acpica / master (-) commits |
+    +-----------------------------+
+       /|\         |
+        |         \|/
+        |  /---------------------\    +----------------------+
+        | < Linuxize repo Utility >-->| old linuxized acpica |--+
+        |  \---------------------/    +----------------------+  |
+        |                                                       |
+     /---------\                                                |
+    < git reset >                                                \
+     \---------/                                                  \
+       /|\                                                        /+-+
+        |                                                        /   |
+    +-----------------------------+                             |    |
+    | acpica / master (+) commits |                             |    |
+    +-----------------------------+                             |    |
+                   |                                            |    |
+                  \|/                                           |    |
+         /-----------------------\    +----------------------+  |    |
+        < Linuxize repo Utilities >-->| new linuxized acpica |--+    |
+         \-----------------------/    +----------------------+       |
+                                                                    \|/
+    +--------------------------+                  /----------------------\
+    | Linuxized ACPICA Patches |<----------------< Linuxize patch Utility >
+    +--------------------------+                  \----------------------/
+                   |
+                  \|/
+     /---------------------------\
+    < Linux ACPI Community Review >
+     \---------------------------/
+                   |
+                  \|/
+    +-----------------------+    /------------------\    +----------------+
+    | linux-pm / linux-next |-->< Linux Merge Window >-->| linux / master |
+    +-----------------------+    \------------------/    +----------------+
+
+                Figure 2. ACPICA -> Linux Upstream Process
+
+   NOTE:
+    A. Linuxize Utilities - Provided by the ACPICA repository, including a
+       utility located in source/tools/acpisrc folder and a number of
+       scripts located in generate/linux folder.
+    B. acpica / master - "master" branch of the git repository at
+       <https://github.com/acpica/acpica.git>.
+    C. linux-pm / linux-next - "linux-next" branch of the git repository at
+       <http://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git>.
+    D. linux / master - "master" branch of the git repository at
+       <http://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git>.
+
+   Before the linuxized ACPICA patches are sent to the Linux ACPI community
+   for review, there is a quality ensurance build test process to reduce
+   porting issues.  Currently this build process only takes care of the
+   following kernel configuration options:
+   CONFIG_ACPI/CONFIG_ACPI_DEBUG/CONFIG_ACPI_DEBUGGER
+
+3. ACPICA Divergences
+
+   Ideally, all of the ACPICA commits should be converted into Linux patches
+   automatically without manual modifications, the "linux / master" tree should
+   contain the ACPICA code that exactly corresponds to the ACPICA code
+   contained in "new linuxized acpica" tree and it should be possible to run
+   the release process fully automatically.
+
+   As a matter of fact, however, there are source code differences between
+   the ACPICA code in Linux and the upstream ACPICA code, referred to as
+   "ACPICA Divergences".
+
+   The various sources of ACPICA divergences include:
+   1. Legacy divergences - Before the current ACPICA release process was
+      established, there already had been divergences between Linux and
+      ACPICA. Over the past several years those divergences have been greatly
+      reduced, but there still are several ones and it takes time to figure
+      out the underlying reasons for their existence.
+   2. Manual modifications - Any manual modification (eg. coding style fixes)
+      made directly in the Linux sources obviously hurts the ACPICA release
+      automation.  Thus it is recommended to fix such issues in the ACPICA
+      upstream source code and generate the linuxized fix using the ACPICA
+      release utilities (please refer to Section 4 below for the details).
+   3. Linux specific features - Sometimes it's impossible to use the
+      current ACPICA APIs to implement features required by the Linux kernel,
+      so Linux developers occasionaly have to change ACPICA code directly.
+      Those changes may not be acceptable by ACPICA upstream and in such cases
+      they are left as committed ACPICA divergences unless the ACPICA side can
+      implement new mechanisms as replacements for them.
+   4. ACPICA release fixups - ACPICA only tests commits using a set of the
+      user space simulation utilies, thus the linuxized ACPICA patches may
+      break the Linux kernel, leaving us build/boot failures.  In order to
+      avoid breaking Linux bisection, fixes are applied directly to the
+      linuxized ACPICA patches during the release process.  When the release
+      fixups are backported to the upstream ACPICA sources, they must follow
+      the upstream ACPICA rules and so further modifications may appear.
+      That may result in the appearance of new divergences.
+   5. Fast tracking of ACPICA commits - Some ACPICA commits are regression
+      fixes or stable-candidate material, so they are applied in advance with
+      respect to the ACPICA release process.  If such commits are reverted or
+      rebased on the ACPICA side in order to offer better solutions, new ACPICA
+      divergences are generated.
+
+4. ACPICA Development
+
+   This paragraph guides Linux developers to use the ACPICA upstream release
+   utilities to obtain Linux patches corresponding to upstream ACPICA commits
+   before they become available from the ACPICA release process.
+
+   1. Cherry-pick an ACPICA commit
+
+   First you need to git clone the ACPICA repository and the ACPICA change
+   you want to cherry pick must be committed into the local repository.
+
+   Then the gen-patch.sh command can help to cherry-pick an ACPICA commit
+   from the ACPICA local repository:
+
+   $ git clone https://github.com/acpica/acpica
+   $ cd acpica
+   $ generate/linux/gen-patch.sh -u [commit ID]
+
+   Here the commit ID is the ACPICA local repository commit ID you want to
+   cherry pick.  It can be omitted if the commit is "HEAD".
+
+   2. Cherry-pick recent ACPICA commits
+
+   Sometimes you need to rebase your code on top of the most recent ACPICA
+   changes that haven't been applied to Linux yet.
+
+   You can generate the ACPICA release series yourself and rebase your code on
+   top of the generated ACPICA release patches:
+
+   $ git clone https://github.com/acpica/acpica
+   $ cd acpica
+   $ generate/linux/make-patches.sh -u [commit ID]
+
+   The commit ID should be the last ACPICA commit accepted by Linux.  Usually,
+   it is the commit modifying ACPI_CA_VERSION.  It can be found by executing
+   "git blame source/include/acpixf.h" and referencing the line that contains
+   "ACPI_CA_VERSION".
+
+   3. Inspect the current divergences
+
+   If you have local copies of both Linux and upstream ACPICA, you can generate
+   a diff file indicating the state of the current divergences:
+
+   # git clone https://github.com/acpica/acpica
+   # git clone http://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+   # cd acpica
+   # generate/linux/divergences.sh -s ../linux
diff --git a/Documentation/acpi/ssdt-overlays.txt b/Documentation/acpi/ssdt-overlays.txt
new file mode 100644
index 000000000000..5ae13f161ea2
--- /dev/null
+++ b/Documentation/acpi/ssdt-overlays.txt
@@ -0,0 +1,172 @@
+
+In order to support ACPI open-ended hardware configurations (e.g. development
+boards) we need a way to augment the ACPI configuration provided by the firmware
+image. A common example is connecting sensors on I2C / SPI buses on development
+boards.
+
+Although this can be accomplished by creating a kernel platform driver or
+recompiling the firmware image with updated ACPI tables, neither is practical:
+the former proliferates board specific kernel code while the latter requires
+access to firmware tools which are often not publicly available.
+
+Because ACPI supports external references in AML code a more practical
+way to augment firmware ACPI configuration is by dynamically loading
+user defined SSDT tables that contain the board specific information.
+
+For example, to enumerate a Bosch BMA222E accelerometer on the I2C bus of the
+Minnowboard MAX development board exposed via the LSE connector [1], the
+following ASL code can be used:
+
+DefinitionBlock ("minnowmax.aml", "SSDT", 1, "Vendor", "Accel", 0x00000003)
+{
+    External (\_SB.I2C6, DeviceObj)
+
+    Scope (\_SB.I2C6)
+    {
+        Device (STAC)
+        {
+            Name (_ADR, Zero)
+            Name (_HID, "BMA222E")
+
+            Method (_CRS, 0, Serialized)
+            {
+                Name (RBUF, ResourceTemplate ()
+                {
+                    I2cSerialBus (0x0018, ControllerInitiated, 0x00061A80,
+                                  AddressingMode7Bit, "\\_SB.I2C6", 0x00,
+                                  ResourceConsumer, ,)
+                    GpioInt (Edge, ActiveHigh, Exclusive, PullDown, 0x0000,
+                             "\\_SB.GPO2", 0x00, ResourceConsumer, , )
+                    { // Pin list
+                        0
+                    }
+                })
+                Return (RBUF)
+            }
+        }
+    }
+}
+
+which can then be compiled to AML binary format:
+
+$ iasl minnowmax.asl
+
+Intel ACPI Component Architecture
+ASL Optimizing Compiler version 20140214-64 [Mar 29 2014]
+Copyright (c) 2000 - 2014 Intel Corporation
+
+ASL Input:     minnomax.asl - 30 lines, 614 bytes, 7 keywords
+AML Output:    minnowmax.aml - 165 bytes, 6 named objects, 1 executable opcodes
+
+[1] http://wiki.minnowboard.org/MinnowBoard_MAX#Low_Speed_Expansion_Connector_.28Top.29
+
+The resulting AML code can then be loaded by the kernel using one of the methods
+below.
+
+== Loading ACPI SSDTs from initrd ==
+
+This option allows loading of user defined SSDTs from initrd and it is useful
+when the system does not support EFI or when there is not enough EFI storage.
+
+It works in a similar way with initrd based ACPI tables override/upgrade: SSDT
+aml code must be placed in the first, uncompressed, initrd under the
+"kernel/firmware/acpi" path. Multiple files can be used and this will translate
+in loading multiple tables. Only SSDT and OEM tables are allowed. See
+initrd_table_override.txt for more details.
+
+Here is an example:
+
+# Add the raw ACPI tables to an uncompressed cpio archive.
+# They must be put into a /kernel/firmware/acpi directory inside the
+# cpio archive.
+# The uncompressed cpio archive must be the first.
+# Other, typically compressed cpio archives, must be
+# concatenated on top of the uncompressed one.
+mkdir -p kernel/firmware/acpi
+cp ssdt.aml kernel/firmware/acpi
+
+# Create the uncompressed cpio archive and concatenate the original initrd
+# on top:
+find kernel | cpio -H newc --create > /boot/instrumented_initrd
+cat /boot/initrd >>/boot/instrumented_initrd
+
+== Loading ACPI SSDTs from EFI variables ==
+
+This is the preferred method, when EFI is supported on the platform, because it
+allows a persistent, OS independent way of storing the user defined SSDTs. There
+is also work underway to implement EFI support for loading user defined SSDTs
+and using this method will make it easier to convert to the EFI loading
+mechanism when that will arrive.
+
+In order to load SSDTs from an EFI variable the efivar_ssdt kernel command line
+parameter can be used. The argument for the option is the variable name to
+use. If there are multiple variables with the same name but with different
+vendor GUIDs, all of them will be loaded.
+
+In order to store the AML code in an EFI variable the efivarfs filesystem can be
+used. It is enabled and mounted by default in /sys/firmware/efi/efivars in all
+recent distribution.
+
+Creating a new file in /sys/firmware/efi/efivars will automatically create a new
+EFI variable. Updating a file in /sys/firmware/efi/efivars will update the EFI
+variable. Please note that the file name needs to be specially formatted as
+"Name-GUID" and that the first 4 bytes in the file (little-endian format)
+represent the attributes of the EFI variable (see EFI_VARIABLE_MASK in
+include/linux/efi.h). Writing to the file must also be done with one write
+operation.
+
+For example, you can use the following bash script to create/update an EFI
+variable with the content from a given file:
+
+#!/bin/sh -e
+
+while ! [ -z "$1" ]; do
+        case "$1" in
+        "-f") filename="$2"; shift;;
+        "-g") guid="$2"; shift;;
+        *) name="$1";;
+        esac
+        shift
+done
+
+usage()
+{
+        echo "Syntax: ${0##*/} -f filename [ -g guid ] name"
+        exit 1
+}
+
+[ -n "$name" -a -f "$filename" ] || usage
+
+EFIVARFS="/sys/firmware/efi/efivars"
+
+[ -d "$EFIVARFS" ] || exit 2
+
+if stat -tf $EFIVARFS | grep -q -v de5e81e4; then
+        mount -t efivarfs none $EFIVARFS
+fi
+
+# try to pick up an existing GUID
+[ -n "$guid" ] || guid=$(find "$EFIVARFS" -name "$name-*" | head -n1 | cut -f2- -d-)
+
+# use a randomly generated GUID
+[ -n "$guid" ] || guid="$(cat /proc/sys/kernel/random/uuid)"
+
+# efivarfs expects all of the data in one write
+tmp=$(mktemp)
+/bin/echo -ne "\007\000\000\000" | cat - $filename > $tmp
+dd if=$tmp of="$EFIVARFS/$name-$guid" bs=$(stat -c %s $tmp)
+rm $tmp
+
+== Loading ACPI SSDTs from configfs ==
+
+This option allows loading of user defined SSDTs from userspace via the configfs
+interface. The CONFIG_ACPI_CONFIGFS option must be select and configfs must be
+mounted. In the following examples, we assume that configfs has been mounted in
+/config.
+
+New tables can be loading by creating new directories in /config/acpi/table/ and
+writing the SSDT aml code in the aml attribute:
+
+cd /config/acpi/table
+mkdir my_ssdt
+cat ~/ssdt.aml > my_ssdt/aml
diff --git a/Documentation/bcache.txt b/Documentation/bcache.txt
index 32b6c3189d98..a9259b562d5c 100644
--- a/Documentation/bcache.txt
+++ b/Documentation/bcache.txt
@@ -1,4 +1,4 @@
-Say you've got a big slow raid 6, and an X-25E or three. Wouldn't it be
+Say you've got a big slow raid 6, and an ssd or three. Wouldn't it be
 nice if you could use them as cache... Hence bcache.
 
 Wiki and git repositories are at:
@@ -8,7 +8,7 @@ Wiki and git repositories are at:
 
 It's designed around the performance characteristics of SSDs - it only allocates
 in erase block sized buckets, and it uses a hybrid btree/log to track cached
-extants (which can be anywhere from a single sector to the bucket size). It's
+extents (which can be anywhere from a single sector to the bucket size). It's
 designed to avoid random writes at all costs; it fills up an erase block
 sequentially, then issues a discard before reusing it.
 
@@ -55,7 +55,10 @@ immediately.  Without udev, you can manually register devices like this:
 Registering the backing device makes the bcache device show up in /dev; you can
 now format it and use it as normal. But the first time using a new bcache
 device, it'll be running in passthrough mode until you attach it to a cache.
-See the section on attaching.
+If you are thinking about using bcache later, it is recommended to setup all your
+slow devices as bcache backing devices without a cache, and you can choose to add
+a caching device later.
+See 'ATTACHING' section below.
 
 The devices show up as:
 
@@ -72,12 +75,14 @@ To get started:
   mount /dev/bcache0 /mnt
 
 You can control bcache devices through sysfs at /sys/block/bcache<N>/bcache .
+You can also control them through /sys/fs//bcache/<cset-uuid>/ .
 
 Cache devices are managed as sets; multiple caches per set isn't supported yet
 but will allow for mirroring of metadata and dirty data in the future. Your new
 cache set shows up as /sys/fs/bcache/<UUID>
 
-ATTACHING:
+ATTACHING
+---------
 
 After your cache device and backing device are registered, the backing device
 must be attached to your cache set to enable caching. Attaching a backing
@@ -105,7 +110,8 @@ but all the cached data will be invalidated. If there was dirty data in the
 cache, don't expect the filesystem to be recoverable - you will have massive
 filesystem corruption, though ext4's fsck does work miracles.
 
-ERROR HANDLING:
+ERROR HANDLING
+--------------
 
 Bcache tries to transparently handle IO errors to/from the cache device without
 affecting normal operation; if it sees too many errors (the threshold is
@@ -127,12 +133,181 @@ the backing devices to passthrough mode.
    writeback mode). It currently doesn't do anything intelligent if it fails to
    read some of the dirty data, though.
 
-TROUBLESHOOTING PERFORMANCE:
+
+HOWTO/COOKBOOK
+--------------
+
+A) Starting a bcache with a missing caching device
+
+If registering the backing device doesn't help, it's already there, you just need
+to force it to run without the cache:
+	host:~# echo /dev/sdb1 > /sys/fs/bcache/register
+	[  119.844831] bcache: register_bcache() error opening /dev/sdb1: device already registered
+
+Next, you try to register your caching device if it's present. However
+if it's absent, or registration fails for some reason, you can still
+start your bcache without its cache, like so:
+	host:/sys/block/sdb/sdb1/bcache# echo 1 > running
+
+Note that this may cause data loss if you were running in writeback mode.
+
+
+B) Bcache does not find its cache
+
+	host:/sys/block/md5/bcache# echo 0226553a-37cf-41d5-b3ce-8b1e944543a8 > attach
+	[ 1933.455082] bcache: bch_cached_dev_attach() Couldn't find uuid for md5 in set
+	[ 1933.478179] bcache: __cached_dev_store() Can't attach 0226553a-37cf-41d5-b3ce-8b1e944543a8
+	[ 1933.478179] : cache set not found
+
+In this case, the caching device was simply not registered at boot
+or disappeared and came back, and needs to be (re-)registered:
+	host:/sys/block/md5/bcache# echo /dev/sdh2 > /sys/fs/bcache/register
+
+
+C) Corrupt bcache crashes the kernel at device registration time:
+
+This should never happen.  If it does happen, then you have found a bug!
+Please report it to the bcache development list: linux-bcache@vger.kernel.org
+
+Be sure to provide as much information that you can including kernel dmesg
+output if available so that we may assist.
+
+
+D) Recovering data without bcache:
+
+If bcache is not available in the kernel, a filesystem on the backing
+device is still available at an 8KiB offset. So either via a loopdev
+of the backing device created with --offset 8K, or any value defined by
+--data-offset when you originally formatted bcache with `make-bcache`.
+
+For example:
+	losetup -o 8192 /dev/loop0 /dev/your_bcache_backing_dev
+
+This should present your unmodified backing device data in /dev/loop0
+
+If your cache is in writethrough mode, then you can safely discard the
+cache device without loosing data.
+
+
+E) Wiping a cache device
+
+host:~# wipefs -a /dev/sdh2
+16 bytes were erased at offset 0x1018 (bcache)
+they were: c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
+
+After you boot back with bcache enabled, you recreate the cache and attach it:
+host:~# make-bcache -C /dev/sdh2
+UUID:                   7be7e175-8f4c-4f99-94b2-9c904d227045
+Set UUID:               5bc072a8-ab17-446d-9744-e247949913c1
+version:                0
+nbuckets:               106874
+block_size:             1
+bucket_size:            1024
+nr_in_set:              1
+nr_this_dev:            0
+first_bucket:           1
+[  650.511912] bcache: run_cache_set() invalidating existing data
+[  650.549228] bcache: register_cache() registered cache device sdh2
+
+start backing device with missing cache:
+host:/sys/block/md5/bcache# echo 1 > running
+
+attach new cache:
+host:/sys/block/md5/bcache# echo 5bc072a8-ab17-446d-9744-e247949913c1 > attach
+[  865.276616] bcache: bch_cached_dev_attach() Caching md5 as bcache0 on set 5bc072a8-ab17-446d-9744-e247949913c1
+
+
+F) Remove or replace a caching device
+
+	host:/sys/block/sda/sda7/bcache# echo 1 > detach
+	[  695.872542] bcache: cached_dev_detach_finish() Caching disabled for sda7
+
+	host:~# wipefs -a /dev/nvme0n1p4
+	wipefs: error: /dev/nvme0n1p4: probing initialization failed: Device or resource busy
+	Ooops, it's disabled, but not unregistered, so it's still protected
+
+We need to go and unregister it:
+	host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# ls -l cache0
+	lrwxrwxrwx 1 root root 0 Feb 25 18:33 cache0 -> ../../../devices/pci0000:00/0000:00:1d.0/0000:70:00.0/nvme/nvme0/nvme0n1/nvme0n1p4/bcache/
+	host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# echo 1 > stop
+	kernel: [  917.041908] bcache: cache_set_free() Cache set b7ba27a1-2398-4649-8ae3-0959f57ba128 unregistered
+
+Now we can wipe it:
+	host:~# wipefs -a /dev/nvme0n1p4
+	/dev/nvme0n1p4: 16 bytes were erased at offset 0x00001018 (bcache): c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
+
+
+G) dm-crypt and bcache
+
+First setup bcache unencrypted and then install dmcrypt on top of
+/dev/bcache<N> This will work faster than if you dmcrypt both the backing
+and caching devices and then install bcache on top. [benchmarks?]
+
+
+H) Stop/free a registered bcache to wipe and/or recreate it
+
+Suppose that you need to free up all bcache references so that you can
+fdisk run and re-register a changed partition table, which won't work
+if there are any active backing or caching devices left on it:
+
+1) Is it present in /dev/bcache* ? (there are times where it won't be)
+
+If so, it's easy:
+	host:/sys/block/bcache0/bcache# echo 1 > stop
+
+2) But if your backing device is gone, this won't work:
+	host:/sys/block/bcache0# cd bcache
+	bash: cd: bcache: No such file or directory
+
+In this case, you may have to unregister the dmcrypt block device that
+references this bcache to free it up:
+	host:~# dmsetup remove oldds1
+	bcache: bcache_device_free() bcache0 stopped
+	bcache: cache_set_free() Cache set 5bc072a8-ab17-446d-9744-e247949913c1 unregistered
+
+This causes the backing bcache to be removed from /sys/fs/bcache and
+then it can be reused.  This would be true of any block device stacking
+where bcache is a lower device.
+
+3) In other cases, you can also look in /sys/fs/bcache/:
+
+host:/sys/fs/bcache# ls -l */{cache?,bdev?}
+lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/bdev1 -> ../../../devices/virtual/block/dm-1/bcache/
+lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/cache0 -> ../../../devices/virtual/block/dm-4/bcache/
+lrwxrwxrwx 1 root root 0 Mar  5 09:39 5bc072a8-ab17-446d-9744-e247949913c1/cache0 -> ../../../devices/pci0000:00/0000:00:01.0/0000:01:00.0/ata10/host9/target9:0:0/9:0:0:0/block/sdl/sdl2/bcache/
+
+The device names will show which UUID is relevant, cd in that directory
+and stop the cache:
+	host:/sys/fs/bcache/5bc072a8-ab17-446d-9744-e247949913c1# echo 1 > stop
+
+This will free up bcache references and let you reuse the partition for
+other purposes.
+
+
+
+TROUBLESHOOTING PERFORMANCE
+---------------------------
 
 Bcache has a bunch of config options and tunables. The defaults are intended to
 be reasonable for typical desktop and server workloads, but they're not what you
 want for getting the best possible numbers when benchmarking.
 
+ - Backing device alignment
+
+   The default metadata size in bcache is 8k.  If your backing device is
+   RAID based, then be sure to align this by a multiple of your stride
+   width using `make-bcache --data-offset`. If you intend to expand your
+   disk array in the future, then multiply a series of primes by your
+   raid stripe size to get the disk multiples that you would like.
+
+   For example:  If you have a 64k stripe size, then the following offset
+   would provide alignment for many common RAID5 data spindle counts:
+	64k * 2*2*2*3*3*5*7 bytes = 161280k
+
+   That space is wasted, but for only 157.5MB you can grow your RAID 5
+   volume to the following data-spindle counts without re-aligning:
+	3,4,5,6,7,8,9,10,12,14,15,18,20,21 ...
+
  - Bad write performance
 
    If write performance is not what you expected, you probably wanted to be
@@ -140,7 +315,7 @@ want for getting the best possible numbers when benchmarking.
    maturity, but simply because in writeback mode you'll lose data if something
    happens to your SSD)
 
-   # echo writeback > /sys/block/bcache0/cache_mode
+   # echo writeback > /sys/block/bcache0/bcache/cache_mode
 
  - Bad performance, or traffic not going to the SSD that you'd expect
 
@@ -193,7 +368,9 @@ want for getting the best possible numbers when benchmarking.
    Solution: warm the cache by doing writes, or use the testing branch (there's
    a fix for the issue there).
 
-SYSFS - BACKING DEVICE:
+
+SYSFS - BACKING DEVICE
+----------------------
 
 Available at /sys/block/<bdev>/bcache, /sys/block/bcache*/bcache and
 (if attached) /sys/fs/bcache/<cset-uuid>/bdev*
@@ -238,7 +415,7 @@ sequential_merge
   against all new requests to determine which new requests are sequential
   continuations of previous requests for the purpose of determining sequential
   cutoff. This is necessary if the sequential cutoff value is greater than the
-  maximum acceptable sequential size for any single request. 
+  maximum acceptable sequential size for any single request.
 
 state
   The backing device can be in one of four different states:
@@ -325,7 +502,7 @@ bucket_size
   Size of buckets
 
 cache<0..n>
-  Symlink to each of the cache devices comprising this cache set. 
+  Symlink to each of the cache devices comprising this cache set.
 
 cache_available_percent
   Percentage of cache device which doesn't contain dirty data, and could
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index dce25d848d92..d515d58962b9 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -53,7 +53,7 @@ disk.
 
 logical_block_size (RO)
 -----------------------
-This is the logcal block size of the device, in bytes.
+This is the logical block size of the device, in bytes.
 
 max_hw_sectors_kb (RO)
 ----------------------
diff --git a/Documentation/block/writeback_cache_control.txt b/Documentation/block/writeback_cache_control.txt
index 59e0516cbf6b..8a6bdada5f6b 100644
--- a/Documentation/block/writeback_cache_control.txt
+++ b/Documentation/block/writeback_cache_control.txt
@@ -20,11 +20,11 @@ a forced cache flush, and the Force Unit Access (FUA) flag for requests.
 Explicit cache flushes
 ----------------------
 
-The REQ_FLUSH flag can be OR ed into the r/w flags of a bio submitted from
+The REQ_PREFLUSH flag can be OR ed into the r/w flags of a bio submitted from
 the filesystem and will make sure the volatile cache of the storage device
 has been flushed before the actual I/O operation is started.  This explicitly
 guarantees that previously completed write requests are on non-volatile
-storage before the flagged bio starts. In addition the REQ_FLUSH flag can be
+storage before the flagged bio starts. In addition the REQ_PREFLUSH flag can be
 set on an otherwise empty bio structure, which causes only an explicit cache
 flush without any dependent I/O.  It is recommend to use
 the blkdev_issue_flush() helper for a pure cache flush.
@@ -41,21 +41,21 @@ signaled after the data has been committed to non-volatile storage.
 Implementation details for filesystems
 --------------------------------------
 
-Filesystems can simply set the REQ_FLUSH and REQ_FUA bits and do not have to
+Filesystems can simply set the REQ_PREFLUSH and REQ_FUA bits and do not have to
 worry if the underlying devices need any explicit cache flushing and how
-the Forced Unit Access is implemented.  The REQ_FLUSH and REQ_FUA flags
+the Forced Unit Access is implemented.  The REQ_PREFLUSH and REQ_FUA flags
 may both be set on a single bio.
 
 
 Implementation details for make_request_fn based block drivers
 --------------------------------------------------------------
 
-These drivers will always see the REQ_FLUSH and REQ_FUA bits as they sit
+These drivers will always see the REQ_PREFLUSH and REQ_FUA bits as they sit
 directly below the submit_bio interface.  For remapping drivers the REQ_FUA
 bits need to be propagated to underlying devices, and a global flush needs
-to be implemented for bios with the REQ_FLUSH bit set.  For real device
-drivers that do not have a volatile cache the REQ_FLUSH and REQ_FUA bits
-on non-empty bios can simply be ignored, and REQ_FLUSH requests without
+to be implemented for bios with the REQ_PREFLUSH bit set.  For real device
+drivers that do not have a volatile cache the REQ_PREFLUSH and REQ_FUA bits
+on non-empty bios can simply be ignored, and REQ_PREFLUSH requests without
 data can be completed successfully without doing any work.  Drivers for
 devices with volatile caches need to implement the support for these
 flags themselves without any help from the block layer.
@@ -65,17 +65,17 @@ Implementation details for request_fn based block drivers
 --------------------------------------------------------------
 
 For devices that do not support volatile write caches there is no driver
-support required, the block layer completes empty REQ_FLUSH requests before
-entering the driver and strips off the REQ_FLUSH and REQ_FUA bits from
+support required, the block layer completes empty REQ_PREFLUSH requests before
+entering the driver and strips off the REQ_PREFLUSH and REQ_FUA bits from
 requests that have a payload.  For devices with volatile write caches the
 driver needs to tell the block layer that it supports flushing caches by
 doing:
 
 	blk_queue_write_cache(sdkp->disk->queue, true, false);
 
-and handle empty REQ_FLUSH requests in its prep_fn/request_fn.  Note that
-REQ_FLUSH requests with a payload are automatically turned into a sequence
-of an empty REQ_FLUSH request followed by the actual write by the block
+and handle empty REQ_OP_FLUSH requests in its prep_fn/request_fn.  Note that
+REQ_PREFLUSH requests with a payload are automatically turned into a sequence
+of an empty REQ_OP_FLUSH request followed by the actual write by the block
 layer.  For devices that also support the FUA bit the block layer needs
 to be told to pass through the REQ_FUA bit using:
 
@@ -83,4 +83,4 @@ to be told to pass through the REQ_FUA bit using:
 
 and the driver must handle write requests that have the REQ_FUA bit set
 in prep_fn/request_fn.  If the FUA bit is not natively supported the block
-layer turns it into an empty REQ_FLUSH request after the actual write.
+layer turns it into an empty REQ_OP_FLUSH request after the actual write.
diff --git a/Documentation/cec.txt b/Documentation/cec.txt
new file mode 100644
index 000000000000..75155fe37153
--- /dev/null
+++ b/Documentation/cec.txt
@@ -0,0 +1,267 @@
+CEC Kernel Support
+==================
+
+The CEC framework provides a unified kernel interface for use with HDMI CEC
+hardware. It is designed to handle a multiple types of hardware (receivers,
+transmitters, USB dongles). The framework also gives the option to decide
+what to do in the kernel driver and what should be handled by userspace
+applications. In addition it integrates the remote control passthrough
+feature into the kernel's remote control framework.
+
+
+The CEC Protocol
+----------------
+
+The CEC protocol enables consumer electronic devices to communicate with each
+other through the HDMI connection. The protocol uses logical addresses in the
+communication. The logical address is strictly connected with the functionality
+provided by the device. The TV acting as the communication hub is always
+assigned address 0. The physical address is determined by the physical
+connection between devices.
+
+The CEC framework described here is up to date with the CEC 2.0 specification.
+It is documented in the HDMI 1.4 specification with the new 2.0 bits documented
+in the HDMI 2.0 specification. But for most of the features the freely available
+HDMI 1.3a specification is sufficient:
+
+http://www.microprocessor.org/HDMISpecification13a.pdf
+
+
+The Kernel Interface
+====================
+
+CEC Adapter
+-----------
+
+The struct cec_adapter represents the CEC adapter hardware. It is created by
+calling cec_allocate_adapter() and deleted by calling cec_delete_adapter():
+
+struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops,
+	       void *priv, const char *name, u32 caps, u8 available_las,
+	       struct device *parent);
+void cec_delete_adapter(struct cec_adapter *adap);
+
+To create an adapter you need to pass the following information:
+
+ops: adapter operations which are called by the CEC framework and that you
+have to implement.
+
+priv: will be stored in adap->priv and can be used by the adapter ops.
+
+name: the name of the CEC adapter. Note: this name will be copied.
+
+caps: capabilities of the CEC adapter. These capabilities determine the
+	capabilities of the hardware and which parts are to be handled
+	by userspace and which parts are handled by kernelspace. The
+	capabilities are returned by CEC_ADAP_G_CAPS.
+
+available_las: the number of simultaneous logical addresses that this
+	adapter can handle. Must be 1 <= available_las <= CEC_MAX_LOG_ADDRS.
+
+parent: the parent device.
+
+
+To register the /dev/cecX device node and the remote control device (if
+CEC_CAP_RC is set) you call:
+
+int cec_register_adapter(struct cec_adapter *adap);
+
+To unregister the devices call:
+
+void cec_unregister_adapter(struct cec_adapter *adap);
+
+Note: if cec_register_adapter() fails, then call cec_delete_adapter() to
+clean up. But if cec_register_adapter() succeeded, then only call
+cec_unregister_adapter() to clean up, never cec_delete_adapter(). The
+unregister function will delete the adapter automatically once the last user
+of that /dev/cecX device has closed its file handle.
+
+
+Implementing the Low-Level CEC Adapter
+--------------------------------------
+
+The following low-level adapter operations have to be implemented in
+your driver:
+
+struct cec_adap_ops {
+	/* Low-level callbacks */
+	int (*adap_enable)(struct cec_adapter *adap, bool enable);
+	int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable);
+	int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr);
+	int (*adap_transmit)(struct cec_adapter *adap, u8 attempts,
+			     u32 signal_free_time, struct cec_msg *msg);
+	void (*adap_log_status)(struct cec_adapter *adap);
+
+	/* High-level callbacks */
+	...
+};
+
+The three low-level ops deal with various aspects of controlling the CEC adapter
+hardware:
+
+
+To enable/disable the hardware:
+
+	int (*adap_enable)(struct cec_adapter *adap, bool enable);
+
+This callback enables or disables the CEC hardware. Enabling the CEC hardware
+means powering it up in a state where no logical addresses are claimed. This
+op assumes that the physical address (adap->phys_addr) is valid when enable is
+true and will not change while the CEC adapter remains enabled. The initial
+state of the CEC adapter after calling cec_allocate_adapter() is disabled.
+
+Note that adap_enable must return 0 if enable is false.
+
+
+To enable/disable the 'monitor all' mode:
+
+	int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable);
+
+If enabled, then the adapter should be put in a mode to also monitor messages
+that not for us. Not all hardware supports this and this function is only
+called if the CEC_CAP_MONITOR_ALL capability is set. This callback is optional
+(some hardware may always be in 'monitor all' mode).
+
+Note that adap_monitor_all_enable must return 0 if enable is false.
+
+
+To program a new logical address:
+
+	int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr);
+
+If logical_addr == CEC_LOG_ADDR_INVALID then all programmed logical addresses
+are to be erased. Otherwise the given logical address should be programmed.
+If the maximum number of available logical addresses is exceeded, then it
+should return -ENXIO. Once a logical address is programmed the CEC hardware
+can receive directed messages to that address.
+
+Note that adap_log_addr must return 0 if logical_addr is CEC_LOG_ADDR_INVALID.
+
+
+To transmit a new message:
+
+	int (*adap_transmit)(struct cec_adapter *adap, u8 attempts,
+			     u32 signal_free_time, struct cec_msg *msg);
+
+This transmits a new message. The attempts argument is the suggested number of
+attempts for the transmit.
+
+The signal_free_time is the number of data bit periods that the adapter should
+wait when the line is free before attempting to send a message. This value
+depends on whether this transmit is a retry, a message from a new initiator or
+a new message for the same initiator. Most hardware will handle this
+automatically, but in some cases this information is needed.
+
+The CEC_FREE_TIME_TO_USEC macro can be used to convert signal_free_time to
+microseconds (one data bit period is 2.4 ms).
+
+
+To log the current CEC hardware status:
+
+	void (*adap_status)(struct cec_adapter *adap, struct seq_file *file);
+
+This optional callback can be used to show the status of the CEC hardware.
+The status is available through debugfs: cat /sys/kernel/debug/cec/cecX/status
+
+
+Your adapter driver will also have to react to events (typically interrupt
+driven) by calling into the framework in the following situations:
+
+When a transmit finished (successfully or otherwise):
+
+void cec_transmit_done(struct cec_adapter *adap, u8 status, u8 arb_lost_cnt,
+		       u8 nack_cnt, u8 low_drive_cnt, u8 error_cnt);
+
+The status can be one of:
+
+CEC_TX_STATUS_OK: the transmit was successful.
+CEC_TX_STATUS_ARB_LOST: arbitration was lost: another CEC initiator
+took control of the CEC line and you lost the arbitration.
+CEC_TX_STATUS_NACK: the message was nacked (for a directed message) or
+acked (for a broadcast message). A retransmission is needed.
+CEC_TX_STATUS_LOW_DRIVE: low drive was detected on the CEC bus. This
+indicates that a follower detected an error on the bus and requested a
+retransmission.
+CEC_TX_STATUS_ERROR: some unspecified error occurred: this can be one of
+the previous two if the hardware cannot differentiate or something else
+entirely.
+CEC_TX_STATUS_MAX_RETRIES: could not transmit the message after
+trying multiple times. Should only be set by the driver if it has hardware
+support for retrying messages. If set, then the framework assumes that it
+doesn't have to make another attempt to transmit the message since the
+hardware did that already.
+
+The *_cnt arguments are the number of error conditions that were seen.
+This may be 0 if no information is available. Drivers that do not support
+hardware retry can just set the counter corresponding to the transmit error
+to 1, if the hardware does support retry then either set these counters to
+0 if the hardware provides no feedback of which errors occurred and how many
+times, or fill in the correct values as reported by the hardware.
+
+When a CEC message was received:
+
+void cec_received_msg(struct cec_adapter *adap, struct cec_msg *msg);
+
+Speaks for itself.
+
+Implementing the High-Level CEC Adapter
+---------------------------------------
+
+The low-level operations drive the hardware, the high-level operations are
+CEC protocol driven. The following high-level callbacks are available:
+
+struct cec_adap_ops {
+	/* Low-level callbacks */
+	...
+
+	/* High-level CEC message callback */
+	int (*received)(struct cec_adapter *adap, struct cec_msg *msg);
+};
+
+The received() callback allows the driver to optionally handle a newly
+received CEC message
+
+	int (*received)(struct cec_adapter *adap, struct cec_msg *msg);
+
+If the driver wants to process a CEC message, then it can implement this
+callback. If it doesn't want to handle this message, then it should return
+-ENOMSG, otherwise the CEC framework assumes it processed this message and
+it will not no anything with it.
+
+
+CEC framework functions
+-----------------------
+
+CEC Adapter drivers can call the following CEC framework functions:
+
+int cec_transmit_msg(struct cec_adapter *adap, struct cec_msg *msg,
+		     bool block);
+
+Transmit a CEC message. If block is true, then wait until the message has been
+transmitted, otherwise just queue it and return.
+
+void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block);
+
+Change the physical address. This function will set adap->phys_addr and
+send an event if it has changed. If cec_s_log_addrs() has been called and
+the physical address has become valid, then the CEC framework will start
+claiming the logical addresses. If block is true, then this function won't
+return until this process has finished.
+
+When the physical address is set to a valid value the CEC adapter will
+be enabled (see the adap_enable op). When it is set to CEC_PHYS_ADDR_INVALID,
+then the CEC adapter will be disabled. If you change a valid physical address
+to another valid physical address, then this function will first set the
+address to CEC_PHYS_ADDR_INVALID before enabling the new physical address.
+
+int cec_s_log_addrs(struct cec_adapter *adap,
+		    struct cec_log_addrs *log_addrs, bool block);
+
+Claim the CEC logical addresses. Should never be called if CEC_CAP_LOG_ADDRS
+is set. If block is true, then wait until the logical addresses have been
+claimed, otherwise just queue it and return. To unconfigure all logical
+addresses call this function with log_addrs set to NULL or with
+log_addrs->num_log_addrs set to 0. The block argument is ignored when
+unconfiguring. This function will just return if the physical address is
+invalid. Once the physical address becomes valid, then the framework will
+attempt to claim these logical addresses.
diff --git a/Documentation/conf.py b/Documentation/conf.py
new file mode 100644
index 000000000000..792b6338ef19
--- /dev/null
+++ b/Documentation/conf.py
@@ -0,0 +1,414 @@
+# -*- coding: utf-8 -*-
+#
+# The Linux Kernel documentation build configuration file, created by
+# sphinx-quickstart on Fri Feb 12 13:51:46 2016.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import sys
+import os
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+sys.path.insert(0, os.path.abspath('sphinx'))
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = ['kernel-doc', 'rstFlatTable']
+
+# Gracefully handle missing rst2pdf.
+try:
+    import rst2pdf
+    extensions += ['rst2pdf.pdfbuilder']
+except ImportError:
+    pass
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The encoding of source files.
+#source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'The Linux Kernel'
+copyright = '2016, The kernel development community'
+author = 'The kernel development community'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# In a normal build, version and release are are set to KERNELVERSION and
+# KERNELRELEASE, respectively, from the Makefile via Sphinx command line
+# arguments.
+#
+# The following code tries to extract the information by reading the Makefile,
+# when Sphinx is run directly (e.g. by Read the Docs).
+try:
+    makefile_version = None
+    makefile_patchlevel = None
+    for line in open('../Makefile'):
+        key, val = [x.strip() for x in line.split('=', 2)]
+        if key == 'VERSION':
+            makefile_version = val
+        elif key == 'PATCHLEVEL':
+            makefile_patchlevel = val
+        if makefile_version and makefile_patchlevel:
+            break
+except:
+    pass
+finally:
+    if makefile_version and makefile_patchlevel:
+        version = release = makefile_version + '.' + makefile_patchlevel
+    else:
+        sys.stderr.write('Warning: Could not extract kernel version\n')
+        version = release = "unknown version"
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#today = ''
+# Else, today_fmt is used as the format for a strftime call.
+#today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ['output']
+
+# The reST default role (used for this markup: `text`) to use for all
+# documents.
+#default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+#add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+#add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# A list of ignored prefixes for module index sorting.
+#modindex_common_prefix = []
+
+# If true, keep warnings as "system message" paragraphs in the built documents.
+#keep_warnings = False
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+primary_domain = 'C'
+highlight_language = 'C'
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+
+# The Read the Docs theme is available from
+# - https://github.com/snide/sphinx_rtd_theme
+# - https://pypi.python.org/pypi/sphinx_rtd_theme
+# - python-sphinx-rtd-theme package (on Debian)
+try:
+    import sphinx_rtd_theme
+    html_theme = 'sphinx_rtd_theme'
+    html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
+except ImportError:
+    sys.stderr.write('Warning: The Sphinx \'sphinx_rtd_theme\' HTML theme was not found. Make sure you have the theme installed to produce pretty HTML output. Falling back to the default theme.\n')
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#html_theme_options = {}
+
+# Add any paths that contain custom themes here, relative to this directory.
+#html_theme_path = []
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+#html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+#html_logo = None
+
+# The name of an image file (within the static path) to use as favicon of the
+# docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+#html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+#html_static_path = ['_static']
+
+# Add any extra paths that contain custom files (such as robots.txt or
+# .htaccess) here, relative to this directory. These files are copied
+# directly to the root of the documentation.
+#html_extra_path = []
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+#html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+#html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+#html_sidebars = {}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+#html_additional_pages = {}
+
+# If false, no module index is generated.
+#html_domain_indices = True
+
+# If false, no index is generated.
+#html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+#html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+#html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+#html_file_suffix = None
+
+# Language to be used for generating the HTML full-text search index.
+# Sphinx supports the following languages:
+#   'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja'
+#   'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr'
+#html_search_language = 'en'
+
+# A dictionary with options for the search language support, empty by default.
+# Now only 'ja' uses this config value
+#html_search_options = {'type': 'default'}
+
+# The name of a javascript file (relative to the configuration directory) that
+# implements a search results scorer. If empty, the default will be used.
+#html_search_scorer = 'scorer.js'
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'TheLinuxKerneldoc'
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+# The paper size ('letterpaper' or 'a4paper').
+#'papersize': 'letterpaper',
+
+# The font size ('10pt', '11pt' or '12pt').
+#'pointsize': '10pt',
+
+# Additional stuff for the LaTeX preamble.
+#'preamble': '',
+
+# Latex figure (float) alignment
+#'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'TheLinuxKernel.tex', 'The Linux Kernel Documentation',
+     'The kernel development community', 'manual'),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#latex_use_parts = False
+
+# If true, show page references after internal links.
+#latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+#latex_appendices = []
+
+# If false, no module index is generated.
+#latex_domain_indices = True
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'thelinuxkernel', 'The Linux Kernel Documentation',
+     [author], 1)
+]
+
+# If true, show URL addresses after external links.
+#man_show_urls = False
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'TheLinuxKernel', 'The Linux Kernel Documentation',
+     author, 'TheLinuxKernel', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+# Documents to append as an appendix to all manuals.
+#texinfo_appendices = []
+
+# If false, no module index is generated.
+#texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#texinfo_show_urls = 'footnote'
+
+# If true, do not generate a @detailmenu in the "Top" node's menu.
+#texinfo_no_detailmenu = False
+
+
+# -- Options for Epub output ----------------------------------------------
+
+# Bibliographic Dublin Core info.
+epub_title = project
+epub_author = author
+epub_publisher = author
+epub_copyright = copyright
+
+# The basename for the epub file. It defaults to the project name.
+#epub_basename = project
+
+# The HTML theme for the epub output. Since the default themes are not
+# optimized for small screen space, using the same theme for HTML and epub
+# output is usually not wise. This defaults to 'epub', a theme designed to save
+# visual space.
+#epub_theme = 'epub'
+
+# The language of the text. It defaults to the language option
+# or 'en' if the language is not set.
+#epub_language = ''
+
+# The scheme of the identifier. Typical schemes are ISBN or URL.
+#epub_scheme = ''
+
+# The unique identifier of the text. This can be a ISBN number
+# or the project homepage.
+#epub_identifier = ''
+
+# A unique identification for the text.
+#epub_uid = ''
+
+# A tuple containing the cover image and cover page html template filenames.
+#epub_cover = ()
+
+# A sequence of (type, uri, title) tuples for the guide element of content.opf.
+#epub_guide = ()
+
+# HTML files that should be inserted before the pages created by sphinx.
+# The format is a list of tuples containing the path and title.
+#epub_pre_files = []
+
+# HTML files that should be inserted after the pages created by sphinx.
+# The format is a list of tuples containing the path and title.
+#epub_post_files = []
+
+# A list of files that should not be packed into the epub file.
+epub_exclude_files = ['search.html']
+
+# The depth of the table of contents in toc.ncx.
+#epub_tocdepth = 3
+
+# Allow duplicate toc entries.
+#epub_tocdup = True
+
+# Choose between 'default' and 'includehidden'.
+#epub_tocscope = 'default'
+
+# Fix unsupported image types using the Pillow.
+#epub_fix_images = False
+
+# Scale large images.
+#epub_max_image_width = 0
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#epub_show_urls = 'inline'
+
+# If false, no index is generated.
+#epub_use_index = True
+
+#=======
+# rst2pdf
+#
+# Grouping the document tree into PDF files. List of tuples
+# (source start file, target name, title, author, options).
+#
+# See the Sphinx chapter of http://ralsina.me/static/manual.pdf
+#
+# FIXME: Do not add the index file here; the result will be too big. Adding
+# multiple PDF files here actually tries to get the cross-referencing right
+# *between* PDF files.
+pdf_documents = [
+    ('index', u'Kernel', u'Kernel', u'J. Random Bozo'),
+]
+
+# kernel-doc extension configuration for running Sphinx directly (e.g. by Read
+# the Docs). In a normal build, these are supplied from the Makefile via command
+# line arguments.
+kerneldoc_bin = '../scripts/kernel-doc'
+kerneldoc_srctree = '..'
diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt
index ba78e7c2a069..4bc7287806de 100644
--- a/Documentation/cpu-freq/core.txt
+++ b/Documentation/cpu-freq/core.txt
@@ -96,7 +96,7 @@ new	- new frequency
 For details about OPP, see Documentation/power/opp.txt
 
 dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with
-	cpufreq_frequency_table_cpuinfo which is provided with the list of
+	cpufreq_table_validate_and_show() which is provided with the list of
 	frequencies that are available for operation. This function provides
 	a ready to use conversion routine to translate the OPP layer's internal
 	information about the available frequencies into a format readily
@@ -110,7 +110,7 @@ dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with
 		/* Do things */
 		r = dev_pm_opp_init_cpufreq_table(dev, &freq_table);
 		if (!r)
-			cpufreq_frequency_table_cpuinfo(policy, freq_table);
+			cpufreq_table_validate_and_show(policy, freq_table);
 		/* Do other things */
 	 }
 
diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index 14f4e6336d88..772b94fde264 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -231,7 +231,7 @@ if you want to skip one entry in the table, set the frequency to
 CPUFREQ_ENTRY_INVALID. The entries don't need to be in ascending
 order.
 
-By calling cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
+By calling cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 					struct cpufreq_frequency_table *table);
 the cpuinfo.min_freq and cpuinfo.max_freq values are detected, and
 policy->min and policy->max are set to the same values. This is
@@ -244,14 +244,12 @@ policy->max, and all other criteria are met. This is helpful for the
 ->verify call.
 
 int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
-                                   struct cpufreq_frequency_table *table,
                                    unsigned int target_freq,
-                                   unsigned int relation,
-                                   unsigned int *index);
+                                   unsigned int relation);
 
 is the corresponding frequency table helper for the ->target
-stage. Just pass the values to this function, and the unsigned int
-index returns the number of the frequency table entry which contains
+stage. Just pass the values to this function, and this function
+returns the number of the frequency table entry which contains
 the frequency the CPU shall be set to.
 
 The following macros can be used as iterators over cpufreq_frequency_table:
diff --git a/Documentation/cpu-freq/pcc-cpufreq.txt b/Documentation/cpu-freq/pcc-cpufreq.txt
index 0a94224ad296..9e3c3b33514c 100644
--- a/Documentation/cpu-freq/pcc-cpufreq.txt
+++ b/Documentation/cpu-freq/pcc-cpufreq.txt
@@ -159,8 +159,8 @@ to be strictly associated with a P-state.
 
 2.2 cpuinfo_transition_latency:
 -------------------------------
-The cpuinfo_transition_latency field is CPUFREQ_ETERNAL. The PCC specification
-does not include a field to expose this value currently.
+The cpuinfo_transition_latency field is 0. The PCC specification does
+not include a field to expose this value currently.
 
 2.3 cpuinfo_cur_freq:
 ---------------------
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 12b1b25b4da9..f722f227a73b 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -20,48 +20,70 @@ to /proc/cpuinfo output of some architectures:
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+4) /sys/devices/system/cpu/cpuX/topology/drawer_id:
+
+	the drawer ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).	The actual value is
+	architecture and platform dependent.
+
+5) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	core as cpuX.
 
-5) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+6) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	core as cpuX.
 
-6) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+7) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-7) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+8) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	physical_package_id.
 
-8) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+9) /sys/devices/system/cpu/cpuX/topology/book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
-9) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+10) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	book_id.
 
+11) /sys/devices/system/cpu/cpuX/topology/drawer_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	drawer_id.
+
+12) /sys/devices/system/cpu/cpuX/topology/drawer_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	drawer_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 6 or 9 attributes. The three book
-related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
+drivers/base/topology.c, is to export the 6 to 12 attributes. The book
+and drawer related sysfs files will only be created if CONFIG_SCHED_BOOK
+and CONFIG_SCHED_DRAWER are selected.
+
+CONFIG_SCHED_BOOK and CONFIG_DRAWER are currently only used on s390, where
+they reflect the cpu and cache hierarchy.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
 #define topology_book_id(cpu)
+#define topology_drawer_id(cpu)
 #define topology_sibling_cpumask(cpu)
 #define topology_core_cpumask(cpu)
 #define topology_book_cpumask(cpu)
+#define topology_drawer_cpumask(cpu)
 
 The type of **_id macros is int.
 The type of **_cpumask macros is (const) struct cpumask *. The latter
@@ -78,6 +100,8 @@ not defined by include/asm-XXX/topology.h:
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().
+For architectures that don't support drawes (CONFIG_SCHED_DRAWER) there are
+no default definitions for topology_drawer_id() and topology_drawer_cpumask().
 
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
diff --git a/Documentation/crypto/asymmetric-keys.txt b/Documentation/crypto/asymmetric-keys.txt
index 8c07e0ea6bc0..2b7816dea370 100644
--- a/Documentation/crypto/asymmetric-keys.txt
+++ b/Documentation/crypto/asymmetric-keys.txt
@@ -76,7 +76,7 @@ the criterion string:
 Looking in /proc/keys, the last 8 hex digits of the key fingerprint are
 displayed, along with the subtype:
 
-	1a39e171 I-----     1 perm 3f010000     0     0 asymmetri modsign.0: DSA 5acc2142 []
+	1a39e171 I-----     1 perm 3f010000     0     0 asymmetric modsign.0: DSA 5acc2142 []
 
 
 =========================
diff --git a/Documentation/development-process/4.Coding b/Documentation/development-process/4.Coding
index e3cb6a56653a..9a3ee77cefb1 100644
--- a/Documentation/development-process/4.Coding
+++ b/Documentation/development-process/4.Coding
@@ -346,7 +346,7 @@ which have not been so documented, there is no harm in adding kerneldoc
 comments for the future; indeed, this can be a useful activity for
 beginning kernel developers.  The format of these comments, along with some
 information on how to create kerneldoc templates can be found in the file
-Documentation/kernel-doc-nano-HOWTO.txt.
+Documentation/kernel-documentation.rst.
 
 Anybody who reads through a significant amount of existing kernel code will
 note that, often, comments are most notable by their absence.  Once again,
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index df2d636b6088..e5b6497116f4 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -14,8 +14,12 @@ The target is named "raid" and it accepts the following parameters:
     <#raid_devs> <metadata_dev0> <dev0> [.. <metadata_devN> <devN>]
 
 <raid_type>:
+  raid0		RAID0 striping (no resilience)
   raid1		RAID1 mirroring
-  raid4		RAID4 dedicated parity disk
+  raid4		RAID4 with dedicated last parity disk
+  raid5_n 	RAID5 with dedicated last parity disk suporting takeover
+		Same as raid4
+		-Transitory layout
   raid5_la	RAID5 left asymmetric
 		- rotating parity 0 with data continuation
   raid5_ra	RAID5 right asymmetric
@@ -30,7 +34,19 @@ The target is named "raid" and it accepts the following parameters:
 		- rotating parity N (right-to-left) with data restart
   raid6_nc	RAID6 N continue
 		- rotating parity N (right-to-left) with data continuation
+  raid6_n_6	RAID6 with dedicate parity disks
+		- parity and Q-syndrome on the last 2 disks;
+		  laylout for takeover from/to raid4/raid5_n
+  raid6_la_6	Same as "raid_la" plus dedicated last Q-syndrome disk
+		- layout for takeover from raid5_la from/to raid6
+  raid6_ra_6	Same as "raid5_ra" dedicated last Q-syndrome disk
+		- layout for takeover from raid5_ra from/to raid6
+  raid6_ls_6	Same as "raid5_ls" dedicated last Q-syndrome disk
+		- layout for takeover from raid5_ls from/to raid6
+  raid6_rs_6	Same as "raid5_rs" dedicated last Q-syndrome disk
+		- layout for takeover from raid5_rs from/to raid6
   raid10        Various RAID10 inspired algorithms chosen by additional params
+		(see raid10_format and raid10_copies below)
 		- RAID10: Striped Mirrors (aka 'Striping on top of mirrors')
 		- RAID1E: Integrated Adjacent Stripe Mirroring
 		- RAID1E: Integrated Offset Stripe Mirroring
@@ -116,10 +132,41 @@ The target is named "raid" and it accepts the following parameters:
 		Here we see layouts closely akin to 'RAID1E - Integrated
 		Offset Stripe Mirroring'.
 
+        [delta_disks <N>]
+		The delta_disks option value (-251 < N < +251) triggers
+		device removal (negative value) or device addition (positive
+		value) to any reshape supporting raid levels 4/5/6 and 10.
+		RAID levels 4/5/6 allow for addition of devices (metadata
+		and data device tupel), raid10_near and raid10_offset only
+		allow for device addtion. raid10_far does not support any
+		reshaping at all.
+		A minimum of devices have to be kept to enforce resilience,
+		which is 3 devices for raid4/5 and 4 devices for raid6.
+
+        [data_offset <sectors>]
+		This option value defines the offset into each data device
+		where the data starts. This is used to provide out-of-place
+		reshaping space to avoid writing over data whilst
+		changing the layout of stripes, hence an interruption/crash
+		may happen at any time without the risk of losing data.
+		E.g. when adding devices to an existing raid set during
+		forward reshaping, the out-of-place space will be allocated
+		at the beginning of each raid device. The kernel raid4/5/6/10
+		MD personalities supporting such device addition will read the data from
+		the existing first stripes (those with smaller number of stripes)
+		starting at data_offset to fill up a new stripe with the larger
+		number of stripes, calculate the redundancy blocks (CRC/Q-syndrome)
+		and write that new stripe to offset 0. Same will be applied to all
+		N-1 other new stripes. This out-of-place scheme is used to change
+		the RAID type (i.e. the allocation algorithm) as well, e.g.
+		changing from raid5_ls to raid5_n.
+
 <#raid_devs>: The number of devices composing the array.
 	Each device consists of two entries.  The first is the device
 	containing the metadata (if any); the second is the one containing the
-	data.
+	data. A Maximum of 64 metadata/data device entries are supported
+	up to target version 1.8.0.
+	1.9.0 supports up to 253 which is enforced by the used MD kernel runtime.
 
 	If a drive has failed or is missing at creation time, a '-' can be
 	given for both the metadata and data drives for a given position.
@@ -207,7 +254,6 @@ include:
 	"recover"- Initiate/continue a recover process.
 	"check"  - Initiate a check (i.e. a "scrub") of the array.
 	"repair" - Initiate a repair of the array.
-	"reshape"- Currently unsupported (-EINVAL).
 
 
 Discard Support
@@ -257,3 +303,9 @@ Version History
 1.5.2   'mismatch_cnt' is zero unless [last_]sync_action is "check".
 1.6.0   Add discard support (and devices_handle_discard_safely module param).
 1.7.0   Add support for MD RAID0 mappings.
+1.8.0   Explictely check for compatible flags in the superblock metadata
+	and reject to start the raid set if any are set by a newer
+	target version, thus avoiding data corruption on a raid set
+	with a reshape in progress.
+1.9.0   Add support for RAID level takeover/reshape/region size
+	and set size reduction.
diff --git a/Documentation/device-mapper/log-writes.txt b/Documentation/device-mapper/log-writes.txt
index c10f30c9b534..f4ebcbaf50f3 100644
--- a/Documentation/device-mapper/log-writes.txt
+++ b/Documentation/device-mapper/log-writes.txt
@@ -14,14 +14,14 @@ Log Ordering
 
 We log things in order of completion once we are sure the write is no longer in
 cache.  This means that normal WRITE requests are not actually logged until the
-next REQ_FLUSH request.  This is to make it easier for userspace to replay the
-log in a way that correlates to what is on disk and not what is in cache, to
-make it easier to detect improper waiting/flushing.
+next REQ_PREFLUSH request.  This is to make it easier for userspace to replay
+the log in a way that correlates to what is on disk and not what is in cache,
+to make it easier to detect improper waiting/flushing.
 
 This works by attaching all WRITE requests to a list once the write completes.
-Once we see a REQ_FLUSH request we splice this list onto the request and once
+Once we see a REQ_PREFLUSH request we splice this list onto the request and once
 the FLUSH request completes we log all of the WRITEs and then the FLUSH.  Only
-completed WRITEs, at the time the REQ_FLUSH is issued, are added in order to
+completed WRITEs, at the time the REQ_PREFLUSH is issued, are added in order to
 simulate the worst case scenario with regard to power failures.  Consider the
 following example (W means write, C means complete):
 
diff --git a/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt b/Documentation/devicetree/bindings/ata/brcm,sata-brcm.txt
index 60872838f1ad..0a5b3b47f217 100644
--- a/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt
+++ b/Documentation/devicetree/bindings/ata/brcm,sata-brcm.txt
@@ -1,13 +1,14 @@
-* Broadcom SATA3 AHCI Controller for STB
+* Broadcom SATA3 AHCI Controller
 
 SATA nodes are defined to describe on-chip Serial ATA controllers.
 Each SATA controller should have its own node.
 
 Required properties:
 - compatible         : should be one or more of
-                       "brcm,bcm7425-ahci"
-                       "brcm,bcm7445-ahci"
-                       "brcm,sata3-ahci"
+			"brcm,bcm7425-ahci"
+			"brcm,bcm7445-ahci"
+			"brcm,bcm-nsp-ahci"
+			"brcm,sata3-ahci"
 - reg                : register mappings for AHCI and SATA_TOP_CTRL
 - reg-names          : "ahci" and "top-ctrl"
 - interrupts         : interrupt mapping for SATA IRQ
diff --git a/Documentation/devicetree/bindings/gpio/cirrus,clps711x-mctrl-gpio.txt b/Documentation/devicetree/bindings/gpio/cirrus,clps711x-mctrl-gpio.txt
index 94ae9f82dcf8..fd42e7280f72 100644
--- a/Documentation/devicetree/bindings/gpio/cirrus,clps711x-mctrl-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/cirrus,clps711x-mctrl-gpio.txt
@@ -1,7 +1,7 @@
 * ARM Cirrus Logic CLPS711X SYSFLG1 MCTRL GPIOs
 
 Required properties:
-- compatible: Should contain "cirrus,clps711x-mctrl-gpio".
+- compatible: Should contain "cirrus,ep7209-mctrl-gpio".
 - gpio-controller: Marks the device node as a gpio controller.
 - #gpio-cells: Should be two. The first cell is the pin number and
   the second cell is used to specify the gpio polarity:
@@ -11,7 +11,7 @@ Required properties:
 Example:
 	sysgpio: sysgpio {
 		compatible = "cirrus,ep7312-mctrl-gpio",
-			     "cirrus,clps711x-mctrl-gpio";
+			     "cirrus,ep7209-mctrl-gpio";
 		gpio-controller;
 		#gpio-cells = <2>;
 	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-clps711x.txt b/Documentation/devicetree/bindings/gpio/gpio-clps711x.txt
index e0d0446a6b78..0a304ad29d81 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-clps711x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-clps711x.txt
@@ -1,7 +1,7 @@
 Cirrus Logic CLPS711X GPIO controller
 
 Required properties:
-- compatible: Should be "cirrus,clps711x-gpio"
+- compatible: Should be "cirrus,ep7209-gpio"
 - reg: Physical base GPIO controller registers location and length.
   There should be two registers, first is DATA register, the second
   is DIRECTION.
@@ -21,7 +21,7 @@ aliases {
 };
 
 porta: gpio@80000000 {
-	compatible = "cirrus,clps711x-gpio";
+	compatible = "cirrus,ep7312-gpio","cirrus,ep7209-gpio";
 	reg = <0x80000000 0x1>, <0x80000040 0x1>;
 	gpio-controller;
 	#gpio-cells = <2>;
diff --git a/Documentation/devicetree/bindings/gpio/gpio-max77620.txt b/Documentation/devicetree/bindings/gpio/gpio-max77620.txt
new file mode 100644
index 000000000000..410e716fd3d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-max77620.txt
@@ -0,0 +1,25 @@
+GPIO driver for MAX77620 Power management IC from Maxim Semiconductor.
+
+Device has 8 GPIO pins which can be configured as GPIO as well as the
+special IO functions.
+
+Required properties:
+-------------------
+- gpio-controller : 	Marks the device node as a gpio controller.
+- #gpio-cells : 	Should be two.  The first cell is the pin number and
+			the second cell is used to specify the gpio polarity:
+				0 = active high
+				1 = active low
+For more details, please refer generic GPIO DT binding document
+<devicetree/bindings/gpio/gpio.txt>.
+
+Example:
+--------
+#include <dt-bindings/mfd/max77620.h>
+...
+max77620@3c {
+	compatible = "maxim,max77620";
+
+	gpio-controller;
+	#gpio-cells = <2>;
+};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
index 6b4a98f74be3..08dd15f89ba9 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
@@ -21,6 +21,7 @@ Required properties:
 	maxim,max7313
 	maxim,max7315
 	ti,pca6107
+	ti,pca9536
 	ti,tca6408
 	ti,tca6416
 	ti,tca6424
diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index f60e2f477e93..8da26b35b5c3 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -7,6 +7,7 @@ Required Properties:
     - "renesas,gpio-r8a7779": for R8A7779 (R-Car H1) compatible GPIO controller.
     - "renesas,gpio-r8a7790": for R8A7790 (R-Car H2) compatible GPIO controller.
     - "renesas,gpio-r8a7791": for R8A7791 (R-Car M2-W) compatible GPIO controller.
+    - "renesas,gpio-r8a7792": for R8A7792 (R-Car V2H) compatible GPIO controller.
     - "renesas,gpio-r8a7793": for R8A7793 (R-Car M2-N) compatible GPIO controller.
     - "renesas,gpio-r8a7794": for R8A7794 (R-Car E2) compatible GPIO controller.
     - "renesas,gpio-r8a7795": for R8A7795 (R-Car H3) compatible GPIO controller.
diff --git a/Documentation/devicetree/bindings/media/mediatek-vcodec.txt b/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
new file mode 100644
index 000000000000..59a47a5b924b
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
@@ -0,0 +1,59 @@
+Mediatek Video Codec
+
+Mediatek Video Codec is the video codec hw present in Mediatek SoCs which
+supports high resolution encoding functionalities.
+
+Required properties:
+- compatible : "mediatek,mt8173-vcodec-enc" for encoder
+- reg : Physical base address of the video codec registers and length of
+  memory mapped region.
+- interrupts : interrupt number to the cpu.
+- mediatek,larb : must contain the local arbiters in the current Socs.
+- clocks : list of clock specifiers, corresponding to entries in
+  the clock-names property.
+- clock-names: encoder must contain "venc_sel_src", "venc_sel",
+- "venc_lt_sel_src", "venc_lt_sel".
+- iommus : should point to the respective IOMMU block with master port as
+  argument, see Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
+  for details.
+- mediatek,vpu : the node of video processor unit
+
+Example:
+vcodec_enc: vcodec@0x18002000 {
+    compatible = "mediatek,mt8173-vcodec-enc";
+    reg = <0 0x18002000 0 0x1000>,    /*VENC_SYS*/
+          <0 0x19002000 0 0x1000>;    /*VENC_LT_SYS*/
+    interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_LOW>,
+		 <GIC_SPI 202 IRQ_TYPE_LEVEL_LOW>;
+    mediatek,larb = <&larb3>,
+		    <&larb5>;
+    iommus = <&iommu M4U_PORT_VENC_RCPU>,
+             <&iommu M4U_PORT_VENC_REC>,
+             <&iommu M4U_PORT_VENC_BSDMA>,
+             <&iommu M4U_PORT_VENC_SV_COMV>,
+             <&iommu M4U_PORT_VENC_RD_COMV>,
+             <&iommu M4U_PORT_VENC_CUR_LUMA>,
+             <&iommu M4U_PORT_VENC_CUR_CHROMA>,
+             <&iommu M4U_PORT_VENC_REF_LUMA>,
+             <&iommu M4U_PORT_VENC_REF_CHROMA>,
+             <&iommu M4U_PORT_VENC_NBM_RDMA>,
+             <&iommu M4U_PORT_VENC_NBM_WDMA>,
+             <&iommu M4U_PORT_VENC_RCPU_SET2>,
+             <&iommu M4U_PORT_VENC_REC_FRM_SET2>,
+             <&iommu M4U_PORT_VENC_BSDMA_SET2>,
+             <&iommu M4U_PORT_VENC_SV_COMA_SET2>,
+             <&iommu M4U_PORT_VENC_RD_COMA_SET2>,
+             <&iommu M4U_PORT_VENC_CUR_LUMA_SET2>,
+             <&iommu M4U_PORT_VENC_CUR_CHROMA_SET2>,
+             <&iommu M4U_PORT_VENC_REF_LUMA_SET2>,
+             <&iommu M4U_PORT_VENC_REC_CHROMA_SET2>;
+    mediatek,vpu = <&vpu>;
+    clocks = <&topckgen CLK_TOP_VENCPLL_D2>,
+             <&topckgen CLK_TOP_VENC_SEL>,
+             <&topckgen CLK_TOP_UNIVPLL1_D2>,
+             <&topckgen CLK_TOP_VENC_LT_SEL>;
+    clock-names = "venc_sel_src",
+                  "venc_sel",
+                  "venc_lt_sel_src",
+                  "venc_lt_sel";
+  };
diff --git a/Documentation/devicetree/bindings/media/mediatek-vpu.txt b/Documentation/devicetree/bindings/media/mediatek-vpu.txt
new file mode 100644
index 000000000000..2a5bac37f9a2
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/mediatek-vpu.txt
@@ -0,0 +1,31 @@
+* Mediatek Video Processor Unit
+
+Video Processor Unit is a HW video controller. It controls HW Codec including
+H.264/VP8/VP9 Decode, H.264/VP8 Encode and Image Processor (scale/rotate/color convert).
+
+Required properties:
+  - compatible: "mediatek,mt8173-vpu"
+  - reg: Must contain an entry for each entry in reg-names.
+  - reg-names: Must include the following entries:
+    "tcm": tcm base
+    "cfg_reg": Main configuration registers base
+  - interrupts: interrupt number to the cpu.
+  - clocks : clock name from clock manager
+  - clock-names: must be main. It is the main clock of VPU
+
+Optional properties:
+  - memory-region: phandle to a node describing memory (see
+    Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt)
+    to be used for VPU extended memory; if not present, VPU may be located
+    anywhere in the memory
+
+Example:
+	vpu: vpu@10020000 {
+		compatible = "mediatek,mt8173-vpu";
+		reg = <0 0x10020000 0 0x30000>,
+		      <0 0x10050000 0 0x100>;
+		reg-names = "tcm", "cfg_reg";
+		interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&topckgen TOP_SCP_SEL>;
+		clock-names = "main";
+	};
diff --git a/Documentation/devicetree/bindings/media/renesas,fcp.txt b/Documentation/devicetree/bindings/media/renesas,fcp.txt
new file mode 100644
index 000000000000..6a12960609d8
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/renesas,fcp.txt
@@ -0,0 +1,32 @@
+Renesas R-Car Frame Compression Processor (FCP)
+-----------------------------------------------
+
+The FCP is a companion module of video processing modules in the Renesas R-Car
+Gen3 SoCs. It provides data compression and decompression, data caching, and
+conversion of AXI transactions in order to reduce the memory bandwidth.
+
+There are three types of FCP: FCP for Codec (FCPC), FCP for VSP (FCPV) and FCP
+for FDP (FCPF). Their configuration and behaviour depend on the module they
+are paired with. These DT bindings currently support the FCPV only.
+
+ - compatible: Must be one or more of the following
+
+   - "renesas,r8a7795-fcpv" for R8A7795 (R-Car H3) compatible 'FCP for VSP'
+   - "renesas,fcpv" for generic compatible 'FCP for VSP'
+
+   When compatible with the generic version, nodes must list the
+   SoC-specific version corresponding to the platform first, followed by the
+   family-specific and/or generic versions.
+
+ - reg: the register base and size for the device registers
+ - clocks: Reference to the functional clock
+
+
+Device node example
+-------------------
+
+	fcpvd1: fcp@fea2f000 {
+		compatible = "renesas,r8a7795-fcpv", "renesas,fcpv";
+		reg = <0 0xfea2f000 0 0x200>;
+		clocks = <&cpg CPG_MOD 602>;
+	};
diff --git a/Documentation/devicetree/bindings/media/renesas,vsp1.txt b/Documentation/devicetree/bindings/media/renesas,vsp1.txt
index 627405abd144..9b695bcbf219 100644
--- a/Documentation/devicetree/bindings/media/renesas,vsp1.txt
+++ b/Documentation/devicetree/bindings/media/renesas,vsp1.txt
@@ -14,6 +14,11 @@ Required properties:
   - interrupts: VSP interrupt specifier.
   - clocks: A phandle + clock-specifier pair for the VSP functional clock.
 
+Optional properties:
+
+  - renesas,fcp: A phandle referencing the FCP that handles memory accesses
+                 for the VSP. Not needed on Gen2, mandatory on Gen3.
+
 
 Example: R8A7790 (R-Car H2) VSP1-S node
 
diff --git a/Documentation/devicetree/bindings/media/s5p-cec.txt b/Documentation/devicetree/bindings/media/s5p-cec.txt
new file mode 100644
index 000000000000..925ab4d72eaa
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/s5p-cec.txt
@@ -0,0 +1,31 @@
+* Samsung HDMI CEC driver
+
+The HDMI CEC module is present is Samsung SoCs and its purpose is to
+handle communication between HDMI connected devices over the CEC bus.
+
+Required properties:
+  - compatible : value should be following
+	"samsung,s5p-cec"
+
+  - reg : Physical base address of the IP registers and length of memory
+	  mapped region.
+
+  - interrupts : HDMI CEC interrupt number to the CPU.
+  - clocks : from common clock binding: handle to HDMI CEC clock.
+  - clock-names : from common clock binding: must contain "hdmicec",
+		  corresponding to entry in the clocks property.
+  - samsung,syscon-phandle - phandle to the PMU system controller
+
+Example:
+
+hdmicec: cec@100B0000 {
+	compatible = "samsung,s5p-cec";
+	reg = <0x100B0000 0x200>;
+	interrupts = <0 114 0>;
+	clocks = <&clock CLK_HDMI_CEC>;
+	clock-names = "hdmicec";
+	samsung,syscon-phandle = <&pmu_system_controller>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&hdmi_cec>;
+	status = "okay";
+};
diff --git a/Documentation/devicetree/bindings/media/s5p-mfc.txt b/Documentation/devicetree/bindings/media/s5p-mfc.txt
index 2d5787eac91a..92c94f5ecbf1 100644
--- a/Documentation/devicetree/bindings/media/s5p-mfc.txt
+++ b/Documentation/devicetree/bindings/media/s5p-mfc.txt
@@ -21,15 +21,18 @@ Required properties:
   - clock-names : from common clock binding: must contain "mfc",
 		  corresponding to entry in the clocks property.
 
-  - samsung,mfc-r : Base address of the first memory bank used by MFC
-		    for DMA contiguous memory allocation and its size.
-
-  - samsung,mfc-l : Base address of the second memory bank used by MFC
-		    for DMA contiguous memory allocation and its size.
-
 Optional properties:
   - power-domains : power-domain property defined with a phandle
 			   to respective power domain.
+  - memory-region : from reserved memory binding: phandles to two reserved
+	memory regions, first is for "left" mfc memory bus interfaces,
+	second if for the "right" mfc memory bus, used when no SYSMMU
+	support is available
+
+Obsolete properties:
+  - samsung,mfc-r, samsung,mfc-l : support removed, please use memory-region
+	property instead
+
 
 Example:
 SoC specific DT entry:
@@ -43,9 +46,29 @@ mfc: codec@13400000 {
 	clock-names = "mfc";
 };
 
+Reserved memory specific DT entry for given board (see reserved memory binding
+for more information):
+
+reserved-memory {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	ranges;
+
+	mfc_left: region@51000000 {
+		compatible = "shared-dma-pool";
+		no-map;
+		reg = <0x51000000 0x800000>;
+	};
+
+	mfc_right: region@43000000 {
+		compatible = "shared-dma-pool";
+		no-map;
+		reg = <0x43000000 0x800000>;
+	};
+};
+
 Board specific DT entry:
 
 codec@13400000 {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
+	memory-region = <&mfc_left>, <&mfc_right>;
 };
diff --git a/Documentation/devicetree/bindings/mfd/axp20x.txt b/Documentation/devicetree/bindings/mfd/axp20x.txt
index d20b1034e967..585a95546288 100644
--- a/Documentation/devicetree/bindings/mfd/axp20x.txt
+++ b/Documentation/devicetree/bindings/mfd/axp20x.txt
@@ -22,6 +22,11 @@ Optional properties:
 		      AXP152/20X: range:  750-1875, Default: 1.5 MHz
 		      AXP22X/80X: range: 1800-4050, Default: 3   MHz
 
+- x-powers,drive-vbus-en: axp221 / axp223 only boolean, set this when the
+		  N_VBUSEN pin is used as an output pin to control an external
+		  regulator to drive the OTG VBus, rather then as an input pin
+		  which signals whether the board is driving OTG VBus or not.
+
 - <input>-supply: a phandle to the regulator supply node. May be omitted if
 		  inputs are unregulated, such as using the IPSOUT output
 		  from the PMIC.
@@ -79,6 +84,7 @@ ELDO3		: LDO		: eldoin-supply		: shared supply
 LDO_IO0		: LDO		: ips-supply		: GPIO 0
 LDO_IO1		: LDO		: ips-supply		: GPIO 1
 RTC_LDO		: LDO		: ips-supply		: always on
+DRIVEVBUS	: Enable output	: drivevbus-supply	: external regulator
 
 AXP809 regulators, type, and corresponding input supply names:
 
diff --git a/Documentation/devicetree/bindings/mfd/rn5t618.txt b/Documentation/devicetree/bindings/mfd/rn5t618.txt
index 937785a3eddc..9e6770b105c9 100644
--- a/Documentation/devicetree/bindings/mfd/rn5t618.txt
+++ b/Documentation/devicetree/bindings/mfd/rn5t618.txt
@@ -1,18 +1,21 @@
-* Ricoh RN5T618 PMIC
+* Ricoh RN5T567/RN5T618 PMIC
 
-Ricoh RN5T618 is a power management IC which integrates 3 step-down
-DCDC converters, 7 low-dropout regulators, a Li-ion battery charger,
-fuel gauge, ADC, GPIOs and a watchdog timer. It can be controlled
-through a I2C interface.
+Ricoh RN5T567/RN5T618 is a power management IC family which integrates
+3 to 4 step-down DCDC converters, 7 low-dropout regulators, GPIOs and
+a watchdog timer. The RN5T618 provides additionally a Li-ion battery
+charger, fuel gauge and an ADC. It can be controlled through an I2C
+interface.
 
 Required properties:
- - compatible: should be "ricoh,rn5t618"
+ - compatible: must be one of
+		"ricoh,rn5t567"
+		"ricoh,rn5t618"
  - reg: the I2C slave address of the device
 
 Sub-nodes:
  - regulators: the node is required if the regulator functionality is
-   needed. The valid regulator names are: DCDC1, DCDC2, DCDC3, LDO1,
-   LDO2, LDO3, LDO4, LDO5, LDORTC1 and LDORTC2.
+   needed. The valid regulator names are: DCDC1, DCDC2, DCDC3, DCDC4
+   (RN5T567), LDO1, LDO2, LDO3, LDO4, LDO5, LDORTC1 and LDORTC2.
    The common bindings for each individual regulator can be found in:
    Documentation/devicetree/bindings/regulator/regulator.txt
 
diff --git a/Documentation/devicetree/bindings/misc/ramoops.txt b/Documentation/devicetree/bindings/misc/ramoops.txt
new file mode 100644
index 000000000000..cd02cec67d38
--- /dev/null
+++ b/Documentation/devicetree/bindings/misc/ramoops.txt
@@ -0,0 +1,48 @@
+Ramoops oops/panic logger
+=========================
+
+ramoops provides persistent RAM storage for oops and panics, so they can be
+recovered after a reboot. It is a backend to pstore, so this node is named
+"ramoops" after the backend, rather than "pstore" which is the subsystem.
+
+Parts of this storage may be set aside for other persistent log buffers, such
+as kernel log messages, or for optional ECC error-correction data.  The total
+size of these optional buffers must fit in the reserved region.
+
+Any remaining space will be used for a circular buffer of oops and panic
+records.  These records have a configurable size, with a size of 0 indicating
+that they should be disabled.
+
+At least one of "record-size", "console-size", "ftrace-size", or "pmsg-size"
+must be set non-zero, but are otherwise optional as listed below.
+
+
+Required properties:
+
+- compatible: must be "ramoops"
+
+- memory-region: phandle to a region of memory that is preserved between
+  reboots
+
+
+Optional properties:
+
+- ecc-size: enables ECC support and specifies ECC buffer size in bytes
+  (defaults to 0: no ECC)
+
+- record-size: maximum size in bytes of each dump done on oops/panic
+  (defaults to 0: disabled)
+
+- console-size: size in bytes of log buffer reserved for kernel messages
+  (defaults to 0: disabled)
+
+- ftrace-size: size in bytes of log buffer reserved for function tracing and
+  profiling (defaults to 0: disabled)
+
+- pmsg-size: size in bytes of log buffer reserved for userspace messages
+  (defaults to 0: disabled)
+
+- unbuffered: if present, use unbuffered mappings to map the reserved region
+  (defaults to buffered mappings)
+
+- no-dump-oops: if present, only dump panics (defaults to panics and oops)
diff --git a/Documentation/devicetree/bindings/phy/brcm-sata-phy.txt b/Documentation/devicetree/bindings/phy/brcm-sata-phy.txt
index d0231209d846..6ccce09d8bbf 100644
--- a/Documentation/devicetree/bindings/phy/brcm-sata-phy.txt
+++ b/Documentation/devicetree/bindings/phy/brcm-sata-phy.txt
@@ -5,6 +5,7 @@ Required properties:
      "brcm,bcm7425-sata-phy"
      "brcm,bcm7445-sata-phy"
      "brcm,iproc-ns2-sata-phy"
+     "brcm,iproc-nsp-sata-phy"
      "brcm,phy-sata3"
 - address-cells: should be 1
 - size-cells: should be 0
@@ -22,7 +23,8 @@ Sub-nodes required properties:
 
 Sub-nodes optional properties:
 - brcm,enable-ssc: use spread spectrum clocking (SSC) on this port
-     This property is not applicable for "brcm,iproc-ns2-sata-phy".
+     This property is not applicable for "brcm,iproc-ns2-sata-phy" and
+     "brcm,iproc-nsp-sata-phy".
 
 Example:
 	sata-phy@f0458100 {
diff --git a/Documentation/devicetree/bindings/power/max8903-charger.txt b/Documentation/devicetree/bindings/power/max8903-charger.txt
new file mode 100644
index 000000000000..f0f4e12b076e
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/max8903-charger.txt
@@ -0,0 +1,25 @@
+Maxim Semiconductor MAX8903 Battery Charger bindings
+
+Required properties:
+- compatible: "maxim,max8903" for MAX8903 Battery Charger
+- dok-gpios: Valid DC power has been detected (active low, input), optional if uok-gpios is provided
+- uok-gpios: Valid USB power has been detected (active low, input), optional if dok-gpios is provided
+
+Optional properties:
+- cen-gpios: Charge enable pin (active low, output)
+- chg-gpios: Charger status pin (active low, input)
+- flt-gpios: Fault pin (active low, output)
+- dcm-gpios: Current limit mode setting (DC=1 or USB=0, output)
+- usus-gpios: USB suspend pin (active high, output)
+
+
+Example:
+
+	max8903-charger {
+		compatible = "maxim,max8903";
+		dok-gpios = <&gpio2 3 GPIO_ACTIVE_LOW>;
+		flt-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
+		chg-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>;
+		cen-gpios = <&gpio2 5 GPIO_ACTIVE_LOW>;
+		status = "okay";
+	};
diff --git a/Documentation/devicetree/bindings/reset/brcm,bcm21664-resetmgr.txt b/Documentation/devicetree/bindings/power/reset/brcm,bcm21664-resetmgr.txt
index 93f31ca1ef4b..93f31ca1ef4b 100644
--- a/Documentation/devicetree/bindings/reset/brcm,bcm21664-resetmgr.txt
+++ b/Documentation/devicetree/bindings/power/reset/brcm,bcm21664-resetmgr.txt
diff --git a/Documentation/devicetree/bindings/power/reset/reboot-mode.txt b/Documentation/devicetree/bindings/power/reset/reboot-mode.txt
new file mode 100644
index 000000000000..de34f27d509e
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/reset/reboot-mode.txt
@@ -0,0 +1,25 @@
+Generic reboot mode core map driver
+
+This driver get reboot mode arguments and call the write
+interface to store the magic value in special register
+or ram. Then the bootloader can read it and take different
+action according to the argument stored.
+
+All mode properties are vendor specific, it is a indication to tell
+the bootloader what to do when the system reboots, and should be named
+as mode-xxx = <magic> (xxx is mode name, magic should be a none-zero value).
+
+For example modes common on Android platform:
+- mode-normal: Normal reboot mode, system reboot with command "reboot".
+- mode-recovery: Android Recovery mode, it is a mode to format the device or update a new image.
+- mode-bootloader: Android fastboot mode, it's a mode to re-flash partitions on the Android based device.
+- mode-loader: A bootloader mode, it's a mode used to download image on Rockchip platform,
+	       usually used in development.
+
+Example:
+	reboot-mode {
+		mode-normal = <BOOT_NORMAL>;
+		mode-recovery = <BOOT_RECOVERY>;
+		mode-bootloader = <BOOT_FASTBOOT>;
+		mode-loader = <BOOT_BL_DOWNLOAD>;
+	}
diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.txt b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.txt
new file mode 100644
index 000000000000..f7ce1d8af04a
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot-mode.txt
@@ -0,0 +1,35 @@
+SYSCON reboot mode driver
+
+This driver gets reboot mode magic value form reboot-mode driver
+and stores it in a SYSCON mapped register. Then the bootloader
+can read it and take different action according to the magic
+value stored.
+
+This DT node should be represented as a sub-node of a "syscon", "simple-mfd"
+node.
+
+Required properties:
+- compatible: should be "syscon-reboot-mode"
+- offset: offset in the register map for the storage register (in bytes)
+
+Optional property:
+- mask: bits mask of the bits in the register to store the reboot mode magic value,
+  default set to 0xffffffff if missing.
+
+The rest of the properties should follow the generic reboot-mode description
+found in reboot-mode.txt
+
+Example:
+	pmu: pmu@20004000 {
+		compatible = "rockchip,rk3066-pmu", "syscon", "simple-mfd";
+		reg = <0x20004000 0x100>;
+
+		reboot-mode {
+			compatible = "syscon-reboot-mode";
+			offset = <0x40>;
+			mode-normal = <BOOT_NORMAL>;
+			mode-recovery = <BOOT_RECOVERY>;
+			mode-bootloader = <BOOT_FASTBOOT>;
+			mode-loader = <BOOT_BL_DOWNLOAD>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/power_supply/axp20x_usb_power.txt b/Documentation/devicetree/bindings/power_supply/axp20x_usb_power.txt
index 862f4a49dc49..f1d7beec45bf 100644
--- a/Documentation/devicetree/bindings/power_supply/axp20x_usb_power.txt
+++ b/Documentation/devicetree/bindings/power_supply/axp20x_usb_power.txt
@@ -1,7 +1,8 @@
 AXP20x USB power supply
 
 Required Properties:
--compatible: "x-powers,axp202-usb-power-supply"
+-compatible: One of: "x-powers,axp202-usb-power-supply"
+                     "x-powers,axp221-usb-power-supply"
 
 This node is a subnode of the axp20x PMIC.
 
diff --git a/Documentation/devicetree/bindings/regulator/da9210.txt b/Documentation/devicetree/bindings/regulator/da9210.txt
index 7aa9b1fa6b21..58065ca9e3b4 100644
--- a/Documentation/devicetree/bindings/regulator/da9210.txt
+++ b/Documentation/devicetree/bindings/regulator/da9210.txt
@@ -1,4 +1,4 @@
-* Dialog Semiconductor DA9210 Voltage Regulator
+* Dialog Semiconductor DA9210 Multi-phase 12A DCDC BUCK Converter
 
 Required properties:
 
@@ -18,8 +18,12 @@ Example:
 		compatible = "dlg,da9210";
 		reg = <0x68>;
 
-		regulator-min-microvolt = <900000>;
-		regulator-max-microvolt = <1000000>;
+		interrupt-parent = <...>;
+		interrupts = <...>;
+
+		regulator-min-microvolt = <300000>;
+		regulator-max-microvolt = <1570000>;
+		regulator-min-microamp = <1600000>;
+		regulator-max-microamp = <4600000>;
 		regulator-boot-on;
-		regulator-always-on;
 	};
diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt
index c620493e8dbe..0f2a6f8fcafd 100644
--- a/Documentation/devicetree/bindings/regulator/da9211.txt
+++ b/Documentation/devicetree/bindings/regulator/da9211.txt
@@ -1,7 +1,8 @@
-* Dialog Semiconductor DA9211/DA9213/DA9215 Voltage Regulator
+* Dialog Semiconductor DA9211/DA9212/DA9213/DA9214/DA9215 Voltage Regulator
 
 Required properties:
-- compatible: "dlg,da9211" or "dlg,da9213" or "dlg,da9215"
+- compatible: "dlg,da9211" or "dlg,da9212" or "dlg,da9213"
+  or "dlg,da9214" or "dlg,da9215"
 - reg: I2C slave address, usually 0x68.
 - interrupts: the interrupt outputs of the controller
 - regulators: A node that houses a sub-node for each regulator within the
@@ -30,6 +31,25 @@ Example 1) DA9211
 				regulator-max-microamp 	= <5000000>;
 				enable-gpios = <&gpio 27 0>;
 			};
+		};
+	};
+
+Example 2) DA9212
+
+	pmic: da9212@68 {
+		compatible = "dlg,da9212";
+		reg = <0x68>;
+		interrupts = <3 27>;
+
+		regulators {
+			BUCKA {
+				regulator-name = "VBUCKA";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <2000000>;
+				regulator-max-microamp 	= <5000000>;
+				enable-gpios = <&gpio 27 0>;
+			};
 			BUCKB {
 				regulator-name = "VBUCKB";
 				regulator-min-microvolt = < 300000>;
@@ -41,7 +61,7 @@ Example 1) DA9211
 		};
 	};
 
-Example 2) DA9213
+Example 3) DA9213
 	pmic: da9213@68 {
 		compatible = "dlg,da9213";
 		reg = <0x68>;
@@ -56,6 +76,24 @@ Example 2) DA9213
 				regulator-max-microamp 	= <6000000>;
 				enable-gpios = <&gpio 27 0>;
 			};
+		};
+	};
+
+Example 4) DA9214
+	pmic: da9214@68 {
+		compatible = "dlg,da9214";
+		reg = <0x68>;
+		interrupts = <3 27>;
+
+		regulators {
+			BUCKA {
+				regulator-name = "VBUCKA";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <3000000>;
+				regulator-max-microamp 	= <6000000>;
+				enable-gpios = <&gpio 27 0>;
+			};
 			BUCKB {
 				regulator-name = "VBUCKB";
 				regulator-min-microvolt = < 300000>;
@@ -67,8 +105,7 @@ Example 2) DA9213
 		};
 	};
 
-
-Example 3) DA9215
+Example 5) DA9215
 	pmic: da9215@68 {
 		compatible = "dlg,da9215";
 		reg = <0x68>;
diff --git a/Documentation/devicetree/bindings/regulator/mt6323-regulator.txt b/Documentation/devicetree/bindings/regulator/mt6323-regulator.txt
new file mode 100644
index 000000000000..c35d878b0960
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/mt6323-regulator.txt
@@ -0,0 +1,237 @@
+Mediatek MT6323 Regulator Driver
+
+All voltage regulators are defined as subnodes of the regulators node. A list
+of regulators provided by this controller are defined as subnodes of the
+PMIC's node. Each regulator is named according to its regulator type,
+buck_<name> and ldo_<name>. The definition for each of these nodes is defined
+using the standard binding for regulators at
+Documentation/devicetree/bindings/regulator/regulator.txt.
+
+The valid names for regulators are::
+BUCK:
+  buck_vproc, buck_vsys, buck_vpa
+LDO:
+  ldo_vtcxo, ldo_vcn28, ldo_vcn33_bt, ldo_vcn33_wifi, ldo_va, ldo_vcama,
+  ldo_vio28, ldo_vusb, ldo_vmc, ldo_vmch, ldo_vemc3v3, ldo_vgp1, ldo_vgp2,
+  ldo_vgp3, ldo_vcn18, ldo_vsim1, ldo_vsim2, ldo_vrtc, ldo_vcamaf, ldo_vibr,
+  ldo_vrf18, ldo_vm, ldo_vio18, ldo_vcamd, ldo_vcamio
+
+Example:
+
+	pmic: mt6323 {
+		mt6323regulator: regulators {
+			mt6323_vproc_reg: buck_vproc{
+				regulator-name = "vproc";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vsys_reg: buck_vsys{
+				regulator-name = "vsys";
+				regulator-min-microvolt = <1400000>;
+				regulator-max-microvolt = <2987500>;
+				regulator-ramp-delay = <25000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vpa_reg: buck_vpa{
+				regulator-name = "vpa";
+				regulator-min-microvolt = < 500000>;
+				regulator-max-microvolt = <3650000>;
+			};
+
+			mt6323_vtcxo_reg: ldo_vtcxo{
+				regulator-name = "vtcxo";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <90>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vcn28_reg: ldo_vcn28{
+				regulator-name = "vcn28";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <185>;
+			};
+
+			mt6323_vcn33_bt_reg: ldo_vcn33_bt{
+				regulator-name = "vcn33_bt";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3600000>;
+				regulator-enable-ramp-delay = <185>;
+			};
+
+			mt6323_vcn33_wifi_reg: ldo_vcn33_wifi{
+				regulator-name = "vcn33_wifi";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3600000>;
+				regulator-enable-ramp-delay = <185>;
+			};
+
+			mt6323_va_reg: ldo_va{
+				regulator-name = "va";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <216>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vcama_reg: ldo_vcama{
+				regulator-name = "vcama";
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vio28_reg: ldo_vio28{
+				regulator-name = "vio28";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <216>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vusb_reg: ldo_vusb{
+				regulator-name = "vusb";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <216>;
+				regulator-boot-on;
+			};
+
+			mt6323_vmc_reg: ldo_vmc{
+				regulator-name = "vmc";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <36>;
+				regulator-boot-on;
+			};
+
+			mt6323_vmch_reg: ldo_vmch{
+				regulator-name = "vmch";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <36>;
+				regulator-boot-on;
+			};
+
+			mt6323_vemc3v3_reg: ldo_vemc3v3{
+				regulator-name = "vemc3v3";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <36>;
+				regulator-boot-on;
+			};
+
+			mt6323_vgp1_reg: ldo_vgp1{
+				regulator-name = "vgp1";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vgp2_reg: ldo_vgp2{
+				regulator-name = "vgp2";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vgp3_reg: ldo_vgp3{
+				regulator-name = "vgp3";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vcn18_reg: ldo_vcn18{
+				regulator-name = "vcn18";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vsim1_reg: ldo_vsim1{
+				regulator-name = "vsim1";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vsim2_reg: ldo_vsim2{
+				regulator-name = "vsim2";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vrtc_reg: ldo_vrtc{
+				regulator-name = "vrtc";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vcamaf_reg: ldo_vcamaf{
+				regulator-name = "vcamaf";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vibr_reg: ldo_vibr{
+				regulator-name = "vibr";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <36>;
+			};
+
+			mt6323_vrf18_reg: ldo_vrf18{
+				regulator-name = "vrf18";
+				regulator-min-microvolt = <1825000>;
+				regulator-max-microvolt = <1825000>;
+				regulator-enable-ramp-delay = <187>;
+			};
+
+			mt6323_vm_reg: ldo_vm{
+				regulator-name = "vm";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <216>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vio18_reg: ldo_vio18{
+				regulator-name = "vio18";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <216>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			mt6323_vcamd_reg: ldo_vcamd{
+				regulator-name = "vcamd";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+
+			mt6323_vcamio_reg: ldo_vcamio{
+				regulator-name = "vcamio";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <216>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/pwm-regulator.txt b/Documentation/devicetree/bindings/regulator/pwm-regulator.txt
index ed936f0f34f2..dd6f59cf1455 100644
--- a/Documentation/devicetree/bindings/regulator/pwm-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/pwm-regulator.txt
@@ -38,13 +38,18 @@ NB: To be clear, if voltage-table is provided, then the device will be used
 in Voltage Table Mode.  If no voltage-table is provided, then the device will
 be used in Continuous Voltage Mode.
 
+Optional properties:
+--------------------
+- enable-gpios:		GPIO to use to enable/disable the regulator
+
 Any property defined as part of the core regulator binding can also be used.
 (See: ../regulator/regulator.txt)
 
-Continuous Voltage Example:
+Continuous Voltage With Enable GPIO Example:
 	pwm_regulator {
 		compatible = "pwm-regulator;
 		pwms = <&pwm1 0 8448 0>;
+		enable-gpios = <&gpio0 23 GPIO_ACTIVE_HIGH>;
 		regulator-min-microvolt = <1016000>;
 		regulator-max-microvolt = <1114000>;
 		regulator-name = "vdd_logic";
diff --git a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
index 46c6f3ed1a1c..0fa3b0fac129 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
@@ -113,9 +113,9 @@ pm8916:
 	l14, l15, l16, l17, l18
 
 pm8941:
-	s1, s2, s3, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13, l14,
-	l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2, lvs3,
-	mvs1, mvs2
+	s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13,
+	l14, l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2, lvs3,
+	5vs1, 5vs2
 
 pm8994:
 	s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, l1, l2, l3, l4, l5,
diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt b/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
index 07ccdaa68324..26542690b578 100644
--- a/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
+++ b/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
@@ -2,7 +2,8 @@ BCM2835 Random number generator
 
 Required properties:
 
-- compatible : should be "brcm,bcm2835-rng"
+- compatible : should be "brcm,bcm2835-rng"  or "brcm,bcm-nsp-rng" or
+  "brcm,bcm5301x-rng"
 - reg : Specifies base physical address and size of the registers.
 
 Example:
@@ -11,3 +12,8 @@ rng {
         compatible = "brcm,bcm2835-rng";
         reg = <0x7e104000 0x10>;
 };
+
+rng@18033000 {
+	compatible = "brcm,bcm-nsp-rng";
+	reg = <0x18033000 0x14>;
+};
diff --git a/Documentation/dmaengine/provider.txt b/Documentation/dmaengine/provider.txt
index 122b7f4876bb..91ce82d5f0c4 100644
--- a/Documentation/dmaengine/provider.txt
+++ b/Documentation/dmaengine/provider.txt
@@ -323,7 +323,7 @@ supported.
    * device_resume
      - Resumes a transfer on the channel
      - This command should operate synchronously on the channel,
-       pausing right away the work of the given channel
+       resuming right away the work of the given channel
 
    * device_terminate_all
      - Aborts all the pending and ongoing transfers on the channel
diff --git a/Documentation/filesystems/ocfs2-online-filecheck.txt b/Documentation/filesystems/ocfs2-online-filecheck.txt
index 1ab07860430d..139fab175c8a 100644
--- a/Documentation/filesystems/ocfs2-online-filecheck.txt
+++ b/Documentation/filesystems/ocfs2-online-filecheck.txt
@@ -5,12 +5,12 @@ This document will describe OCFS2 online file check feature.
 
 Introduction
 ============
-OCFS2 is often used in high-availaibility systems. However, OCFS2 usually
+OCFS2 is often used in high-availability systems. However, OCFS2 usually
 converts the filesystem to read-only when encounters an error. This may not be
 necessary, since turning the filesystem read-only would affect other running
 processes as well, decreasing availability.
 Then, a mount option (errors=continue) is introduced, which would return the
--EIO errno to the calling process and terminate furhter processing so that the
+-EIO errno to the calling process and terminate further processing so that the
 filesystem is not corrupted further. The filesystem is not converted to
 read-only, and the problematic file's inode number is reported in the kernel
 log. The user can try to check/fix this file via online filecheck feature.
@@ -44,7 +44,7 @@ There is a sysfs directory for each OCFS2 file system mounting:
 
   /sys/fs/ocfs2/<devname>/filecheck
 
-Here, <devname> indicates the name of OCFS2 volumn device which has been already
+Here, <devname> indicates the name of OCFS2 volume device which has been already
 mounted. The file above would accept inode numbers. This could be used to
 communicate with kernel space, tell which file(inode number) will be checked or
 fixed. Currently, three operations are supported, which includes checking
@@ -76,14 +76,14 @@ The output is like this:
 This time, the <ERROR> column indicates whether this fix is successful or not.
 
 3. The record cache is used to store the history of check/fix results. It's
-defalut size is 10, and can be adjust between the range of 10 ~ 100. You can
+default size is 10, and can be adjust between the range of 10 ~ 100. You can
 adjust the size like this:
 
   # echo "<size>" > /sys/fs/ocfs2/<devname>/filecheck/set
 
 Fixing stuff
 ============
-On receivng the inode, the filesystem would read the inode and the
+On receiving the inode, the filesystem would read the inode and the
 file metadata. In case of errors, the filesystem would fix the errors
 and report the problems it fixed in the kernel log. As a precautionary measure,
 the inode must first be checked for errors before performing a final fix.
diff --git a/Documentation/gpio/drivers-on-gpio.txt b/Documentation/gpio/drivers-on-gpio.txt
index 14bf95a13bae..306513251713 100644
--- a/Documentation/gpio/drivers-on-gpio.txt
+++ b/Documentation/gpio/drivers-on-gpio.txt
@@ -37,15 +37,16 @@ hardware descriptions such as device tree or ACPI:
   external connector status, such as a headset line for an audio driver or an
   HDMI connector. It will provide a better userspace sysfs interface than GPIO.
 
-- restart-gpio: drivers/power/gpio-restart.c is used to restart/reboot the
-  system by pulling a GPIO line and will register a restart handler so
+- restart-gpio: drivers/power/reset/gpio-restart.c is used to restart/reboot
+  the system by pulling a GPIO line and will register a restart handler so
   userspace can issue the right system call to restart the system.
 
-- poweroff-gpio: drivers/power/gpio-poweroff.c is used to power the system down
-  by pulling a GPIO line and will register a pm_power_off() callback so that
-  userspace can issue the right system call to power down the system.
+- poweroff-gpio: drivers/power/reset/gpio-poweroff.c is used to power the
+  system down by pulling a GPIO line and will register a pm_power_off()
+  callback so that userspace can issue the right system call to power down the
+  system.
 
-- gpio-gate-clock: drivers/clk/clk-gpio-gate.c is used to control a gated clock
+- gpio-gate-clock: drivers/clk/clk-gpio.c is used to control a gated clock
   (off/on) that uses a GPIO, and integrated with the clock subsystem.
 
 - i2c-gpio: drivers/i2c/busses/i2c-gpio.c is used to drive an I2C bus
diff --git a/Documentation/index.rst b/Documentation/index.rst
new file mode 100644
index 000000000000..f92854f01773
--- /dev/null
+++ b/Documentation/index.rst
@@ -0,0 +1,22 @@
+.. The Linux Kernel documentation master file, created by
+   sphinx-quickstart on Fri Feb 12 13:51:46 2016.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to The Linux Kernel's documentation!
+============================================
+
+Nothing for you to see here *yet*. Please move along.
+
+Contents:
+
+.. toctree::
+   :maxdepth: 2
+
+   kernel-documentation
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`search`
diff --git a/Documentation/ioctl/cdrom.txt b/Documentation/ioctl/cdrom.txt
index 59df81c8da2b..a4d62a9d6771 100644
--- a/Documentation/ioctl/cdrom.txt
+++ b/Documentation/ioctl/cdrom.txt
@@ -340,7 +340,8 @@ CDROMSUBCHNL			Read subchannel data (struct cdrom_subchnl)
 	  EINVAL	format not CDROM_MSF or CDROM_LBA
 
 	notes:
-	  Format is converted to CDROM_MSF on return
+	  Format is converted to CDROM_MSF or CDROM_LBA
+	  as per user request on return
 
 
 
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index 78f69cdc9b3f..062e3af271b7 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -1,3 +1,6 @@
+NOTE: this document is outdated and will eventually be removed.  See
+Documentation/kernel-documentation.rst for current information.
+
 kernel-doc nano-HOWTO
 =====================
 
diff --git a/Documentation/kernel-documentation.rst b/Documentation/kernel-documentation.rst
new file mode 100644
index 000000000000..c4eb5049da39
--- /dev/null
+++ b/Documentation/kernel-documentation.rst
@@ -0,0 +1,654 @@
+==========================
+Linux Kernel Documentation
+==========================
+
+Introduction
+============
+
+The Linux kernel uses `Sphinx`_ to generate pretty documentation from
+`reStructuredText`_ files under ``Documentation``. To build the documentation in
+HTML or PDF formats, use ``make htmldocs`` or ``make pdfdocs``. The generated
+documentation is placed in ``Documentation/output``.
+
+.. _Sphinx: http://www.sphinx-doc.org/
+.. _reStructuredText: http://docutils.sourceforge.net/rst.html
+
+The reStructuredText files may contain directives to include structured
+documentation comments, or kernel-doc comments, from source files. Usually these
+are used to describe the functions and types and design of the code. The
+kernel-doc comments have some special structure and formatting, but beyond that
+they are also treated as reStructuredText.
+
+There is also the deprecated DocBook toolchain to generate documentation from
+DocBook XML template files under ``Documentation/DocBook``. The DocBook files
+are to be converted to reStructuredText, and the toolchain is slated to be
+removed.
+
+Finally, there are thousands of plain text documentation files scattered around
+``Documentation``. Some of these will likely be converted to reStructuredText
+over time, but the bulk of them will remain in plain text.
+
+Sphinx Build
+============
+
+The usual way to generate the documentation is to run ``make htmldocs`` or
+``make pdfdocs``. There are also other formats available, see the documentation
+section of ``make help``. The generated documentation is placed in
+format-specific subdirectories under ``Documentation/output``.
+
+To generate documentation, Sphinx (``sphinx-build``) must obviously be
+installed. For prettier HTML output, the Read the Docs Sphinx theme
+(``sphinx_rtd_theme``) is used if available. For PDF output, ``rst2pdf`` is also
+needed. All of these are widely available and packaged in distributions.
+
+To pass extra options to Sphinx, you can use the ``SPHINXOPTS`` make
+variable. For example, use ``make SPHINXOPTS=-v htmldocs`` to get more verbose
+output.
+
+To remove the generated documentation, run ``make cleandocs``.
+
+Writing Documentation
+=====================
+
+Adding new documentation can be as simple as:
+
+1. Add a new ``.rst`` file somewhere under ``Documentation``.
+2. Refer to it from the Sphinx main `TOC tree`_ in ``Documentation/index.rst``.
+
+.. _TOC tree: http://www.sphinx-doc.org/en/stable/markup/toctree.html
+
+This is usually good enough for simple documentation (like the one you're
+reading right now), but for larger documents it may be advisable to create a
+subdirectory (or use an existing one). For example, the graphics subsystem
+documentation is under ``Documentation/gpu``, split to several ``.rst`` files,
+and has a separate ``index.rst`` (with a ``toctree`` of its own) referenced from
+the main index.
+
+See the documentation for `Sphinx`_ and `reStructuredText`_ on what you can do
+with them. In particular, the Sphinx `reStructuredText Primer`_ is a good place
+to get started with reStructuredText. There are also some `Sphinx specific
+markup constructs`_.
+
+.. _reStructuredText Primer: http://www.sphinx-doc.org/en/stable/rest.html
+.. _Sphinx specific markup constructs: http://www.sphinx-doc.org/en/stable/markup/index.html
+
+Specific guidelines for the kernel documentation
+------------------------------------------------
+
+Here are some specific guidelines for the kernel documentation:
+
+* Please don't go overboard with reStructuredText markup. Keep it simple.
+
+* Please stick to this order of heading adornments:
+
+  1. ``=`` with overline for document title::
+
+       ==============
+       Document title
+       ==============
+
+  2. ``=`` for chapters::
+
+       Chapters
+       ========
+
+  3. ``-`` for sections::
+
+       Section
+       -------
+
+  4. ``~`` for subsections::
+
+       Subsection
+       ~~~~~~~~~~
+
+  Although RST doesn't mandate a specific order ("Rather than imposing a fixed
+  number and order of section title adornment styles, the order enforced will be
+  the order as encountered."), having the higher levels the same overall makes
+  it easier to follow the documents.
+
+list tables
+-----------
+
+We recommend the use of *list table* formats. The *list table* formats are
+double-stage lists. Compared to the ASCII-art they might not be as
+comfortable for 
+readers of the text files. Their advantage is that they are easy to
+create or modify and that the diff of a modification is much more meaningful,
+because it is limited to the modified content.
+
+The ``flat-table`` is a double-stage list similar to the ``list-table`` with
+some additional features:
+
+* column-span: with the role ``cspan`` a cell can be extended through
+  additional columns
+
+* row-span: with the role ``rspan`` a cell can be extended through
+  additional rows
+
+* auto span rightmost cell of a table row over the missing cells on the right
+  side of that table-row.  With Option ``:fill-cells:`` this behavior can
+  changed from *auto span* to *auto fill*, which automatically inserts (empty)
+  cells instead of spanning the last cell.
+
+options:
+
+* ``:header-rows:``   [int] count of header rows
+* ``:stub-columns:``  [int] count of stub columns
+* ``:widths:``        [[int] [int] ... ] widths of columns
+* ``:fill-cells:``    instead of auto-spanning missing cells, insert missing cells
+
+roles:
+
+* ``:cspan:`` [int] additional columns (*morecols*)
+* ``:rspan:`` [int] additional rows (*morerows*)
+
+The example below shows how to use this markup.  The first level of the staged
+list is the *table-row*. In the *table-row* there is only one markup allowed,
+the list of the cells in this *table-row*. Exceptions are *comments* ( ``..`` )
+and *targets* (e.g. a ref to ``:ref:`last row <last row>``` / :ref:`last row
+<last row>`).
+
+.. code-block:: rst
+
+   .. flat-table:: table title
+      :widths: 2 1 1 3
+
+      * - head col 1
+        - head col 2
+        - head col 3
+        - head col 4
+
+      * - column 1
+        - field 1.1
+        - field 1.2 with autospan
+
+      * - column 2
+        - field 2.1
+        - :rspan:`1` :cspan:`1` field 2.2 - 3.3
+
+      * .. _`last row`:
+
+        - column 3
+
+Rendered as:
+
+   .. flat-table:: table title
+      :widths: 2 1 1 3
+
+      * - head col 1
+        - head col 2
+        - head col 3
+        - head col 4
+
+      * - column 1
+        - field 1.1
+        - field 1.2 with autospan
+
+      * - column 2
+        - field 2.1
+        - :rspan:`1` :cspan:`1` field 2.2 - 3.3
+
+      * .. _`last row`:
+
+        - column 3
+
+
+Including kernel-doc comments
+=============================
+
+The Linux kernel source files may contain structured documentation comments, or
+kernel-doc comments to describe the functions and types and design of the
+code. The documentation comments may be included to any of the reStructuredText
+documents using a dedicated kernel-doc Sphinx directive extension.
+
+The kernel-doc directive is of the format::
+
+  .. kernel-doc:: source
+     :option:
+
+The *source* is the path to a source file, relative to the kernel source
+tree. The following directive options are supported:
+
+export: *[source-pattern ...]*
+  Include documentation for all functions in *source* that have been exported
+  using ``EXPORT_SYMBOL`` or ``EXPORT_SYMBOL_GPL`` either in *source* or in any
+  of the files specified by *source-pattern*.
+
+  The *source-pattern* is useful when the kernel-doc comments have been placed
+  in header files, while ``EXPORT_SYMBOL`` and ``EXPORT_SYMBOL_GPL`` are next to
+  the function definitions.
+
+  Examples::
+
+    .. kernel-doc:: lib/bitmap.c
+       :export:
+
+    .. kernel-doc:: include/net/mac80211.h
+       :export: net/mac80211/*.c
+
+internal: *[source-pattern ...]*
+  Include documentation for all functions and types in *source* that have
+  **not** been exported using ``EXPORT_SYMBOL`` or ``EXPORT_SYMBOL_GPL`` either
+  in *source* or in any of the files specified by *source-pattern*.
+
+  Example::
+
+    .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+       :internal:
+
+doc: *title*
+  Include documentation for the ``DOC:`` paragraph identified by *title* in
+  *source*. Spaces are allowed in *title*; do not quote the *title*. The *title*
+  is only used as an identifier for the paragraph, and is not included in the
+  output. Please make sure to have an appropriate heading in the enclosing
+  reStructuredText document.
+
+  Example::
+
+    .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+       :doc: High Definition Audio over HDMI and Display Port
+
+functions: *function* *[...]*
+  Include documentation for each *function* in *source*.
+
+  Example::
+
+    .. kernel-doc:: lib/bitmap.c
+       :functions: bitmap_parselist bitmap_parselist_user
+
+Without options, the kernel-doc directive includes all documentation comments
+from the source file.
+
+The kernel-doc extension is included in the kernel source tree, at
+``Documentation/sphinx/kernel-doc.py``. Internally, it uses the
+``scripts/kernel-doc`` script to extract the documentation comments from the
+source.
+
+Writing kernel-doc comments
+===========================
+
+In order to provide embedded, "C" friendly, easy to maintain, but consistent and
+extractable overview, function and type documentation, the Linux kernel has
+adopted a consistent style for documentation comments. The format for this
+documentation is called the kernel-doc format, described below. This style
+embeds the documentation within the source files, using a few simple conventions
+for adding documentation paragraphs and documenting functions and their
+parameters, structures and unions and their members, enumerations, and typedefs.
+
+.. note:: The kernel-doc format is deceptively similar to gtk-doc or Doxygen,
+   yet distinctively different, for historical reasons. The kernel source
+   contains tens of thousands of kernel-doc comments. Please stick to the style
+   described here.
+
+The ``scripts/kernel-doc`` script is used by the Sphinx kernel-doc extension in
+the documentation build to extract this embedded documentation into the various
+HTML, PDF, and other format documents.
+
+In order to provide good documentation of kernel functions and data structures,
+please use the following conventions to format your kernel-doc comments in the
+Linux kernel source.
+
+How to format kernel-doc comments
+---------------------------------
+
+The opening comment mark ``/**`` is reserved for kernel-doc comments. Only
+comments so marked will be considered by the ``kernel-doc`` tool. Use it only
+for comment blocks that contain kernel-doc formatted comments. The usual ``*/``
+should be used as the closing comment marker. The lines in between should be
+prefixed by `` * `` (space star space).
+
+The function and type kernel-doc comments should be placed just before the
+function or type being described. The overview kernel-doc comments may be freely
+placed at the top indentation level.
+
+Example kernel-doc function comment::
+
+  /**
+   * foobar() - Brief description of foobar.
+   * @arg: Description of argument of foobar.
+   *
+   * Longer description of foobar.
+   *
+   * Return: Description of return value of foobar.
+   */
+  int foobar(int arg)
+
+The format is similar for documentation for structures, enums, paragraphs,
+etc. See the sections below for details.
+
+The kernel-doc structure is extracted from the comments, and proper `Sphinx C
+Domain`_ function and type descriptions with anchors are generated for them. The
+descriptions are filtered for special kernel-doc highlights and
+cross-references. See below for details.
+
+.. _Sphinx C Domain: http://www.sphinx-doc.org/en/stable/domains.html
+
+Highlights and cross-references
+-------------------------------
+
+The following special patterns are recognized in the kernel-doc comment
+descriptive text and converted to proper reStructuredText markup and `Sphinx C
+Domain`_ references.
+
+.. attention:: The below are **only** recognized within kernel-doc comments,
+	       **not** within normal reStructuredText documents.
+
+``funcname()``
+  Function reference.
+
+``@parameter``
+  Name of a function parameter. (No cross-referencing, just formatting.)
+
+``%CONST``
+  Name of a constant. (No cross-referencing, just formatting.)
+
+``$ENVVAR``
+  Name of an environment variable. (No cross-referencing, just formatting.)
+
+``&struct name``
+  Structure reference.
+
+``&enum name``
+  Enum reference.
+
+``&typedef name``
+  Typedef reference.
+
+``&struct_name->member`` or ``&struct_name.member``
+  Structure or union member reference. The cross-reference will be to the struct
+  or union definition, not the member directly.
+
+``&name``
+  A generic type reference. Prefer using the full reference described above
+  instead. This is mostly for legacy comments.
+
+Cross-referencing from reStructuredText
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. highlight:: none
+
+To cross-reference the functions and types defined in the kernel-doc comments
+from reStructuredText documents, please use the `Sphinx C Domain`_
+references. For example::
+
+  See function :c:func:`foo` and struct/union/enum/typedef :c:type:`bar`.
+
+While the type reference works with just the type name, without the
+struct/union/enum/typedef part in front, you may want to use::
+
+  See :c:type:`struct foo <foo>`.
+  See :c:type:`union bar <bar>`.
+  See :c:type:`enum baz <baz>`.
+  See :c:type:`typedef meh <meh>`.
+
+This will produce prettier links, and is in line with how kernel-doc does the
+cross-references.
+
+For further details, please refer to the `Sphinx C Domain`_ documentation.
+
+Function documentation
+----------------------
+
+.. highlight:: c
+
+The general format of a function and function-like macro kernel-doc comment is::
+
+  /**
+   * function_name() - Brief description of function.
+   * @arg1: Describe the first argument.
+   * @arg2: Describe the second argument.
+   *        One can provide multiple line descriptions
+   *        for arguments.
+   *
+   * A longer description, with more discussion of the function function_name()
+   * that might be useful to those using or modifying it. Begins with an
+   * empty comment line, and may include additional embedded empty
+   * comment lines.
+   *
+   * The longer description may have multiple paragraphs.
+   *
+   * Return: Describe the return value of foobar.
+   *
+   * The return value description can also have multiple paragraphs, and should
+   * be placed at the end of the comment block.
+   */
+
+The brief description following the function name may span multiple lines, and
+ends with an ``@argument:`` description, a blank comment line, or the end of the
+comment block.
+
+The kernel-doc function comments describe each parameter to the function, in
+order, with the ``@argument:`` descriptions. The ``@argument:`` descriptions
+must begin on the very next line following the opening brief function
+description line, with no intervening blank comment lines. The ``@argument:``
+descriptions may span multiple lines. The continuation lines may contain
+indentation. If a function parameter is ``...`` (varargs), it should be listed
+in kernel-doc notation as: ``@...:``.
+
+The return value, if any, should be described in a dedicated section at the end
+of the comment starting with "Return:".
+
+Structure, union, and enumeration documentation
+-----------------------------------------------
+
+The general format of a struct, union, and enum kernel-doc comment is::
+
+  /**
+   * struct struct_name - Brief description.
+   * @member_name: Description of member member_name.
+   *
+   * Description of the structure.
+   */
+
+Below, "struct" is used to mean structs, unions and enums, and "member" is used
+to mean struct and union members as well as enumerations in an enum.
+
+The brief description following the structure name may span multiple lines, and
+ends with a ``@member:`` description, a blank comment line, or the end of the
+comment block.
+
+The kernel-doc data structure comments describe each member of the structure, in
+order, with the ``@member:`` descriptions. The ``@member:`` descriptions must
+begin on the very next line following the opening brief function description
+line, with no intervening blank comment lines. The ``@member:`` descriptions may
+span multiple lines. The continuation lines may contain indentation.
+
+In-line member documentation comments
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The structure members may also be documented in-line within the definition::
+
+  /**
+   * struct foo - Brief description.
+   * @foo: The Foo member.
+   */
+  struct foo {
+        int foo;
+        /**
+         * @bar: The Bar member.
+         */
+        int bar;
+        /**
+         * @baz: The Baz member.
+         *
+         * Here, the member description may contain several paragraphs.
+         */
+        int baz;
+  }
+
+Private members
+~~~~~~~~~~~~~~~
+
+Inside a struct description, you can use the "private:" and "public:" comment
+tags. Structure fields that are inside a "private:" area are not listed in the
+generated output documentation.  The "private:" and "public:" tags must begin
+immediately following a ``/*`` comment marker.  They may optionally include
+comments between the ``:`` and the ending ``*/`` marker.
+
+Example::
+
+  /**
+   * struct my_struct - short description
+   * @a: first member
+   * @b: second member
+   *
+   * Longer description
+   */
+  struct my_struct {
+      int a;
+      int b;
+  /* private: internal use only */
+      int c;
+  };
+
+
+Typedef documentation
+---------------------
+
+The general format of a typedef kernel-doc comment is::
+
+  /**
+   * typedef type_name - Brief description.
+   *
+   * Description of the type.
+   */
+
+Overview documentation comments
+-------------------------------
+
+To facilitate having source code and comments close together, you can include
+kernel-doc documentation blocks that are free-form comments instead of being
+kernel-doc for functions, structures, unions, enums, or typedefs. This could be
+used for something like a theory of operation for a driver or library code, for
+example.
+
+This is done by using a ``DOC:`` section keyword with a section title.
+
+The general format of an overview or high-level documentation comment is::
+
+  /**
+   * DOC: Theory of Operation
+   *
+   * The whizbang foobar is a dilly of a gizmo. It can do whatever you
+   * want it to do, at any time. It reads your mind. Here's how it works.
+   *
+   * foo bar splat
+   *
+   * The only drawback to this gizmo is that is can sometimes damage
+   * hardware, software, or its subject(s).
+   */
+
+The title following ``DOC:`` acts as a heading within the source file, but also
+as an identifier for extracting the documentation comment. Thus, the title must
+be unique within the file.
+
+Recommendations
+---------------
+
+We definitely need kernel-doc formatted documentation for functions that are
+exported to loadable modules using ``EXPORT_SYMBOL`` or ``EXPORT_SYMBOL_GPL``.
+
+We also look to provide kernel-doc formatted documentation for functions
+externally visible to other kernel files (not marked "static").
+
+We also recommend providing kernel-doc formatted documentation for private (file
+"static") routines, for consistency of kernel source code layout. But this is
+lower priority and at the discretion of the MAINTAINER of that kernel source
+file.
+
+Data structures visible in kernel include files should also be documented using
+kernel-doc formatted comments.
+
+DocBook XML [DEPRECATED]
+========================
+
+.. attention::
+
+   This section describes the deprecated DocBook XML toolchain. Please do not
+   create new DocBook XML template files. Please consider converting existing
+   DocBook XML templates files to Sphinx/reStructuredText.
+
+Converting DocBook to Sphinx
+----------------------------
+
+.. highlight:: none
+
+Over time, we expect all of the documents under ``Documentation/DocBook`` to be
+converted to Sphinx and reStructuredText. For most DocBook XML documents, a good
+enough solution is to use the simple ``Documentation/sphinx/tmplcvt`` script,
+which uses ``pandoc`` under the hood. For example::
+
+  $ cd Documentation/sphinx
+  $ ./tmplcvt ../DocBook/in.tmpl ../out.rst
+
+Then edit the resulting rst files to fix any remaining issues, and add the
+document in the ``toctree`` in ``Documentation/index.rst``.
+
+Components of the kernel-doc system
+-----------------------------------
+
+Many places in the source tree have extractable documentation in the form of
+block comments above functions. The components of this system are:
+
+- ``scripts/kernel-doc``
+
+  This is a perl script that hunts for the block comments and can mark them up
+  directly into reStructuredText, DocBook, man, text, and HTML. (No, not
+  texinfo.)
+
+- ``Documentation/DocBook/*.tmpl``
+
+  These are XML template files, which are normal XML files with special
+  place-holders for where the extracted documentation should go.
+
+- ``scripts/docproc.c``
+
+  This is a program for converting XML template files into XML files. When a
+  file is referenced it is searched for symbols exported (EXPORT_SYMBOL), to be
+  able to distinguish between internal and external functions.
+
+  It invokes kernel-doc, giving it the list of functions that are to be
+  documented.
+
+  Additionally it is used to scan the XML template files to locate all the files
+  referenced herein. This is used to generate dependency information as used by
+  make.
+
+- ``Makefile``
+
+  The targets 'xmldocs', 'psdocs', 'pdfdocs', and 'htmldocs' are used to build
+  DocBook XML files, PostScript files, PDF files, and html files in
+  Documentation/DocBook. The older target 'sgmldocs' is equivalent to 'xmldocs'.
+
+- ``Documentation/DocBook/Makefile``
+
+  This is where C files are associated with SGML templates.
+
+How to use kernel-doc comments in DocBook XML template files
+------------------------------------------------------------
+
+DocBook XML template files (\*.tmpl) are like normal XML files, except that they
+can contain escape sequences where extracted documentation should be inserted.
+
+``!E<filename>`` is replaced by the documentation, in ``<filename>``, for
+functions that are exported using ``EXPORT_SYMBOL``: the function list is
+collected from files listed in ``Documentation/DocBook/Makefile``.
+
+``!I<filename>`` is replaced by the documentation for functions that are **not**
+exported using ``EXPORT_SYMBOL``.
+
+``!D<filename>`` is used to name additional files to search for functions
+exported using ``EXPORT_SYMBOL``.
+
+``!F<filename> <function [functions...]>`` is replaced by the documentation, in
+``<filename>``, for the functions listed.
+
+``!P<filename> <section title>`` is replaced by the contents of the ``DOC:``
+section titled ``<section title>`` from ``<filename>``. Spaces are allowed in
+``<section title>``; do not quote the ``<section title>``.
+
+``!C<filename>`` is replaced by nothing, but makes the tools check that all DOC:
+sections and documented functions, symbols, etc. are used. This makes sense to
+use when you use ``!F`` or ``!P`` only and want to verify that all documentation
+is included.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 17e33dbbf226..769db8399ac8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -582,6 +582,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	bootmem_debug	[KNL] Enable bootmem allocator debug messages.
 
+	bert_disable	[ACPI]
+			Disable BERT OS support on buggy BIOSes.
+
 	bttv.card=	[HW,V4L] bttv (bt848 + bt878 based grabber cards)
 	bttv.radio=	Most important insmod options are available as
 			kernel args too.
@@ -1193,6 +1196,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Address Range Mirroring feature even if your box
 			doesn't support it.
 
+	efivar_ssdt=	[EFI; X86] Name of an EFI variable that contains an SSDT
+			that is to be dynamically loaded by Linux. If there are
+			multiple variables with the same name but with different
+			vendor GUIDs, all of them will be loaded. See
+			Documentation/acpi/ssdt-overlays.txt for details.
+
+
 	eisa_irq_edge=	[PARISC,HW]
 			See header of drivers/parisc/eisa.c.
 
@@ -2794,8 +2804,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			timer: [X86] Force use of architectural NMI
 				timer mode (see also oprofile.timer
 				for generic hr timer mode)
-				[s390] Force legacy basic mode sampling
-                                (report cpu_type "timer")
 
 	oops=panic	Always panic on oopses. Default is to just kill the
 			process, but there is a small probability of
@@ -3600,6 +3608,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				present during boot.
 		nocompress	Don't compress/decompress hibernation images.
 		no		Disable hibernation and resume.
+		protect_image	Turn on image protection during restoration
+				(that will set all pages holding image data
+				during restoration read-only).
 
 	retain_initrd	[RAM] Keep initrd memory after extraction
 
@@ -3998,8 +4009,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	trace_event=[event-list]
 			[FTRACE] Set and start specified trace events in order
-			to facilitate early boot debugging.
-			See also Documentation/trace/events.txt
+			to facilitate early boot debugging. The event-list is a
+			comma separated list of trace events to enable. See
+			also Documentation/trace/events.txt
 
 	trace_options=[option-list]
 			[FTRACE] Enable or disable tracer options at boot.
diff --git a/Documentation/md.txt b/Documentation/md.txt
index 1a2ada46aaed..d6e2fcf27337 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -602,7 +602,7 @@ These currently include
 
   stripe_cache_size  (currently raid5 only)
       number of entries in the stripe cache.  This is writable, but
-      there are upper and lower limits (32768, 16).  Default is 128.
+      there are upper and lower limits (32768, 17).  Default is 256.
   strip_cache_active (currently raid5 only)
       number of active entries in the stripe cache
   preread_bypass_threshold (currently raid5 only)
diff --git a/Documentation/mic/mpssd/mpssd.c b/Documentation/mic/mpssd/mpssd.c
index 30fb842a976d..49db1def1721 100644
--- a/Documentation/mic/mpssd/mpssd.c
+++ b/Documentation/mic/mpssd/mpssd.c
@@ -1538,9 +1538,9 @@ set_cmdline(struct mic_info *mic)
 
 	len = snprintf(buffer, PATH_MAX,
 		"clocksource=tsc highres=off nohz=off ");
-	len += snprintf(buffer + len, PATH_MAX,
+	len += snprintf(buffer + len, PATH_MAX - len,
 		"cpufreq_on;corec6_off;pc3_off;pc6_off ");
-	len += snprintf(buffer + len, PATH_MAX,
+	len += snprintf(buffer + len, PATH_MAX - len,
 		"ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0",
 		mic->id + 1);
 
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
index 5d8675615e59..9264bcab4099 100644
--- a/Documentation/ramoops.txt
+++ b/Documentation/ramoops.txt
@@ -45,7 +45,7 @@ corrupt, but usually it is restorable.
 
 2. Setting the parameters
 
-Setting the ramoops parameters can be done in 2 different manners:
+Setting the ramoops parameters can be done in 3 different manners:
  1. Use the module parameters (which have the names of the variables described
  as before).
  For quick debugging, you can also reserve parts of memory during boot
@@ -54,7 +54,9 @@ Setting the ramoops parameters can be done in 2 different manners:
  kernel to use only the first 128 MB of memory, and place ECC-protected ramoops
  region at 128 MB boundary:
  "mem=128M ramoops.mem_address=0x8000000 ramoops.ecc=1"
- 2. Use a platform device and set the platform data. The parameters can then
+ 2. Use Device Tree bindings, as described in
+ Documentation/device-tree/bindings/misc/ramoops.txt.
+ 3. Use a platform device and set the platform data. The parameters can then
  be set through that platform data. An example of doing that is:
 
 #include <linux/pstore_ram.h>
diff --git a/Documentation/s390/s390dbf.txt b/Documentation/s390/s390dbf.txt
index 3da163383c93..61329fd62e89 100644
--- a/Documentation/s390/s390dbf.txt
+++ b/Documentation/s390/s390dbf.txt
@@ -405,7 +405,7 @@ Example:
 
 > ls /sys/kernel/debug/s390dbf/dasd
 flush  hex_ascii  level pages raw
-> cat /sys/kernel/debug/s390dbf/dasd/hex_ascii | sort +1
+> cat /sys/kernel/debug/s390dbf/dasd/hex_ascii | sort -k2,2 -s
 00 00974733272:680099 2 - 02 0006ad7e  07 ea 4a 90 | ....
 00 00974733272:682210 2 - 02 0006ade6  46 52 45 45 | FREE
 00 00974733272:682213 2 - 02 0006adf6  07 ea 4a 90 | ....
diff --git a/Documentation/security/self-protection.txt b/Documentation/security/self-protection.txt
index babd6378ec05..3010576c9fca 100644
--- a/Documentation/security/self-protection.txt
+++ b/Documentation/security/self-protection.txt
@@ -183,8 +183,9 @@ provide meaningful defenses.
 ### Canaries, blinding, and other secrets
 
 It should be noted that things like the stack canary discussed earlier
-are technically statistical defenses, since they rely on a (leakable)
-secret value.
+are technically statistical defenses, since they rely on a secret value,
+and such values may become discoverable through an information exposure
+flaw.
 
 Blinding literal values for things like JITs, where the executable
 contents may be partially under the control of userspace, need a similar
@@ -199,8 +200,8 @@ working?) in order to maximize their success.
 Since the location of kernel memory is almost always instrumental in
 mounting a successful attack, making the location non-deterministic
 raises the difficulty of an exploit. (Note that this in turn makes
-the value of leaks higher, since they may be used to discover desired
-memory locations.)
+the value of information exposures higher, since they may be used to
+discover desired memory locations.)
 
 #### Text and module base
 
@@ -222,14 +223,21 @@ become more difficult to locate.
 Much of the kernel's dynamic memory (e.g. kmalloc, vmalloc, etc) ends up
 being relatively deterministic in layout due to the order of early-boot
 initializations. If the base address of these areas is not the same
-between boots, targeting them is frustrated, requiring a leak specific
-to the region.
+between boots, targeting them is frustrated, requiring an information
+exposure specific to the region.
+
+#### Structure layout
+
+By performing a per-build randomization of the layout of sensitive
+structures, attacks must either be tuned to known kernel builds or expose
+enough kernel memory to determine structure layouts before manipulating
+them.
 
 
-## Preventing Leaks
+## Preventing Information Exposures
 
 Since the locations of sensitive structures are the primary target for
-attacks, it is important to defend against leaks of both kernel memory
+attacks, it is important to defend against exposure of both kernel memory
 addresses and kernel memory contents (since they may contain kernel
 addresses or other sensitive things like canary values).
 
@@ -250,8 +258,8 @@ sure structure holes are cleared.
 When releasing memory, it is best to poison the contents (clear stack on
 syscall return, wipe heap memory on a free), to avoid reuse attacks that
 rely on the old contents of memory. This frustrates many uninitialized
-variable attacks, stack info leaks, heap info leaks, and use-after-free
-attacks.
+variable attacks, stack content exposures, heap content exposures, and
+use-after-free attacks.
 
 ### Destination tracking
 
diff --git a/Documentation/sphinx/convert_template.sed b/Documentation/sphinx/convert_template.sed
new file mode 100644
index 000000000000..c1503fcca4ec
--- /dev/null
+++ b/Documentation/sphinx/convert_template.sed
@@ -0,0 +1,18 @@
+#
+# Pandoc doesn't grok <function> or <structname>, so convert them
+# ahead of time.
+#
+# Use the following escapes to pass through pandoc:
+#	$bq = "`"
+#	$lt = "<"
+#	$gt = ">"
+#
+s%<function>\([^<(]\+\)()</function>%:c:func:$bq\1()$bq%g
+s%<function>\([^<(]\+\)</function>%:c:func:$bq\1()$bq%g
+s%<structname>struct *\([^<]\+\)</structname>%:c:type:$bqstruct \1 $lt\1$gt$bq%g
+s%struct <structname>\([^<]\+\)</structname>%:c:type:$bqstruct \1 $lt\1$gt$bq%g
+s%<structname>\([^<]\+\)</structname>%:c:type:$bqstruct \1 $lt\1$gt$bq%g
+#
+# Wrap docproc directives in para and code blocks.
+#
+s%^\(!.*\)$%<para><code>DOCPROC: \1</code></para>%
diff --git a/Documentation/sphinx/kernel-doc.py b/Documentation/sphinx/kernel-doc.py
new file mode 100644
index 000000000000..f6920c0af6ee
--- /dev/null
+++ b/Documentation/sphinx/kernel-doc.py
@@ -0,0 +1,141 @@
+# coding=utf-8
+#
+# Copyright © 2016 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:
+#    Jani Nikula <jani.nikula@intel.com>
+#
+# Please make sure this works on both python2 and python3.
+#
+
+import os
+import subprocess
+import sys
+import re
+import glob
+
+from docutils import nodes, statemachine
+from docutils.statemachine import ViewList
+from docutils.parsers.rst import directives
+from sphinx.util.compat import Directive
+from sphinx.ext.autodoc import AutodocReporter
+
+class KernelDocDirective(Directive):
+    """Extract kernel-doc comments from the specified file"""
+    required_argument = 1
+    optional_arguments = 4
+    option_spec = {
+        'doc': directives.unchanged_required,
+        'functions': directives.unchanged_required,
+        'export': directives.unchanged,
+        'internal': directives.unchanged,
+    }
+    has_content = False
+
+    def run(self):
+        env = self.state.document.settings.env
+        cmd = [env.config.kerneldoc_bin, '-rst', '-enable-lineno']
+
+        filename = env.config.kerneldoc_srctree + '/' + self.arguments[0]
+        export_file_patterns = []
+
+        # Tell sphinx of the dependency
+        env.note_dependency(os.path.abspath(filename))
+
+        tab_width = self.options.get('tab-width', self.state.document.settings.tab_width)
+
+        # FIXME: make this nicer and more robust against errors
+        if 'export' in self.options:
+            cmd += ['-export']
+            export_file_patterns = str(self.options.get('export')).split()
+        elif 'internal' in self.options:
+            cmd += ['-internal']
+            export_file_patterns = str(self.options.get('internal')).split()
+        elif 'doc' in self.options:
+            cmd += ['-function', str(self.options.get('doc'))]
+        elif 'functions' in self.options:
+            for f in str(self.options.get('functions')).split():
+                cmd += ['-function', f]
+
+        for pattern in export_file_patterns:
+            for f in glob.glob(env.config.kerneldoc_srctree + '/' + pattern):
+                env.note_dependency(os.path.abspath(f))
+                cmd += ['-export-file', f]
+
+        cmd += [filename]
+
+        try:
+            env.app.verbose('calling kernel-doc \'%s\'' % (" ".join(cmd)))
+
+            p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
+            out, err = p.communicate()
+
+            # python2 needs conversion to unicode.
+            # python3 with universal_newlines=True returns strings.
+            if sys.version_info.major < 3:
+                out, err = unicode(out, 'utf-8'), unicode(err, 'utf-8')
+
+            if p.returncode != 0:
+                sys.stderr.write(err)
+
+                env.app.warn('kernel-doc \'%s\' failed with return code %d' % (" ".join(cmd), p.returncode))
+                return [nodes.error(None, nodes.paragraph(text = "kernel-doc missing"))]
+            elif env.config.kerneldoc_verbosity > 0:
+                sys.stderr.write(err)
+
+            lines = statemachine.string2lines(out, tab_width, convert_whitespace=True)
+            result = ViewList()
+
+            lineoffset = 0;
+            line_regex = re.compile("^#define LINENO ([0-9]+)$")
+            for line in lines:
+                match = line_regex.search(line)
+                if match:
+                    # sphinx counts lines from 0
+                    lineoffset = int(match.group(1)) - 1
+                    # we must eat our comments since the upset the markup
+                else:
+                    result.append(line, filename, lineoffset)
+                    lineoffset += 1
+
+            node = nodes.section()
+            buf = self.state.memo.title_styles, self.state.memo.section_level, self.state.memo.reporter
+            self.state.memo.reporter = AutodocReporter(result, self.state.memo.reporter)
+            self.state.memo.title_styles, self.state.memo.section_level = [], 0
+            try:
+                self.state.nested_parse(result, 0, node, match_titles=1)
+            finally:
+                self.state.memo.title_styles, self.state.memo.section_level, self.state.memo.reporter = buf
+
+            return node.children
+
+        except Exception as e:  # pylint: disable=W0703
+            env.app.warn('kernel-doc \'%s\' processing failed with: %s' %
+                         (" ".join(cmd), str(e)))
+            return [nodes.error(None, nodes.paragraph(text = "kernel-doc missing"))]
+
+def setup(app):
+    app.add_config_value('kerneldoc_bin', None, 'env')
+    app.add_config_value('kerneldoc_srctree', None, 'env')
+    app.add_config_value('kerneldoc_verbosity', 1, 'env')
+
+    app.add_directive('kernel-doc', KernelDocDirective)
diff --git a/Documentation/sphinx/post_convert.sed b/Documentation/sphinx/post_convert.sed
new file mode 100644
index 000000000000..392770bac53b
--- /dev/null
+++ b/Documentation/sphinx/post_convert.sed
@@ -0,0 +1,23 @@
+#
+# Unescape.
+#
+s/$bq/`/g
+s/$lt/</g
+s/$gt/>/g
+#
+# pandoc thinks that both "_" needs to be escaped.  Remove the extra
+# backslashes.
+#
+s/\\_/_/g
+#
+# Unwrap docproc directives.
+#
+s/^``DOCPROC: !E\(.*\)``$/.. kernel-doc:: \1\n   :export:/
+s/^``DOCPROC: !I\(.*\)``$/.. kernel-doc:: \1\n   :internal:/
+s/^``DOCPROC: !F\([^ ]*\) \(.*\)``$/.. kernel-doc:: \1\n   :functions: \2/
+s/^``DOCPROC: !P\([^ ]*\) \(.*\)``$/.. kernel-doc:: \1\n   :doc: \2/
+s/^``DOCPROC: \(!.*\)``$/.. WARNING: DOCPROC directive not supported: \1/
+#
+# Trim trailing whitespace.
+#
+s/[[:space:]]*$//
diff --git a/Documentation/sphinx/rstFlatTable.py b/Documentation/sphinx/rstFlatTable.py
new file mode 100644
index 000000000000..26db852e3c74
--- /dev/null
+++ b/Documentation/sphinx/rstFlatTable.py
@@ -0,0 +1,365 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8; mode: python -*-
+# pylint: disable=C0330, R0903, R0912
+
+u"""
+    flat-table
+    ~~~~~~~~~~
+
+    Implementation of the ``flat-table`` reST-directive.
+
+    :copyright:  Copyright (C) 2016  Markus Heiser
+    :license:    GPL Version 2, June 1991 see linux/COPYING for details.
+
+    The ``flat-table`` (:py:class:`FlatTable`) is a double-stage list similar to
+    the ``list-table`` with some additional features:
+
+    * *column-span*: with the role ``cspan`` a cell can be extended through
+      additional columns
+
+    * *row-span*: with the role ``rspan`` a cell can be extended through
+      additional rows
+
+    * *auto span* rightmost cell of a table row over the missing cells on the
+      right side of that table-row.  With Option ``:fill-cells:`` this behavior
+      can changed from *auto span* to *auto fill*, which automaticly inserts
+      (empty) cells instead of spanning the last cell.
+
+    Options:
+
+    * header-rows:   [int] count of header rows
+    * stub-columns:  [int] count of stub columns
+    * widths:        [[int] [int] ... ] widths of columns
+    * fill-cells:    instead of autospann missing cells, insert missing cells
+
+    roles:
+
+    * cspan: [int] additionale columns (*morecols*)
+    * rspan: [int] additionale rows (*morerows*)
+"""
+
+# ==============================================================================
+# imports
+# ==============================================================================
+
+import sys
+
+from docutils import nodes
+from docutils.parsers.rst import directives, roles
+from docutils.parsers.rst.directives.tables import Table
+from docutils.utils import SystemMessagePropagation
+
+# ==============================================================================
+# common globals
+# ==============================================================================
+
+# The version numbering follows numbering of the specification
+# (Documentation/books/kernel-doc-HOWTO).
+__version__  = '1.0'
+
+PY3 = sys.version_info[0] == 3
+PY2 = sys.version_info[0] == 2
+
+if PY3:
+    # pylint: disable=C0103, W0622
+    unicode     = str
+    basestring  = str
+
+# ==============================================================================
+def setup(app):
+# ==============================================================================
+
+    app.add_directive("flat-table", FlatTable)
+    roles.register_local_role('cspan', c_span)
+    roles.register_local_role('rspan', r_span)
+
+# ==============================================================================
+def c_span(name, rawtext, text, lineno, inliner, options=None, content=None):
+# ==============================================================================
+    # pylint: disable=W0613
+
+    options  = options if options is not None else {}
+    content  = content if content is not None else []
+    nodelist = [colSpan(span=int(text))]
+    msglist  = []
+    return nodelist, msglist
+
+# ==============================================================================
+def r_span(name, rawtext, text, lineno, inliner, options=None, content=None):
+# ==============================================================================
+    # pylint: disable=W0613
+
+    options  = options if options is not None else {}
+    content  = content if content is not None else []
+    nodelist = [rowSpan(span=int(text))]
+    msglist  = []
+    return nodelist, msglist
+
+
+# ==============================================================================
+class rowSpan(nodes.General, nodes.Element): pass # pylint: disable=C0103,C0321
+class colSpan(nodes.General, nodes.Element): pass # pylint: disable=C0103,C0321
+# ==============================================================================
+
+# ==============================================================================
+class FlatTable(Table):
+# ==============================================================================
+
+    u"""FlatTable (``flat-table``) directive"""
+
+    option_spec = {
+        'name': directives.unchanged
+        , 'class': directives.class_option
+        , 'header-rows': directives.nonnegative_int
+        , 'stub-columns': directives.nonnegative_int
+        , 'widths': directives.positive_int_list
+        , 'fill-cells' : directives.flag }
+
+    def run(self):
+
+        if not self.content:
+            error = self.state_machine.reporter.error(
+                'The "%s" directive is empty; content required.' % self.name,
+                nodes.literal_block(self.block_text, self.block_text),
+                line=self.lineno)
+            return [error]
+
+        title, messages = self.make_title()
+        node = nodes.Element()          # anonymous container for parsing
+        self.state.nested_parse(self.content, self.content_offset, node)
+
+        tableBuilder = ListTableBuilder(self)
+        tableBuilder.parseFlatTableNode(node)
+        tableNode = tableBuilder.buildTableNode()
+        # SDK.CONSOLE()  # print --> tableNode.asdom().toprettyxml()
+        if title:
+            tableNode.insert(0, title)
+        return [tableNode] + messages
+
+
+# ==============================================================================
+class ListTableBuilder(object):
+# ==============================================================================
+
+    u"""Builds a table from a double-stage list"""
+
+    def __init__(self, directive):
+        self.directive = directive
+        self.rows      = []
+        self.max_cols  = 0
+
+    def buildTableNode(self):
+
+        colwidths    = self.directive.get_column_widths(self.max_cols)
+        stub_columns = self.directive.options.get('stub-columns', 0)
+        header_rows  = self.directive.options.get('header-rows', 0)
+
+        table = nodes.table()
+        tgroup = nodes.tgroup(cols=len(colwidths))
+        table += tgroup
+
+
+        for colwidth in colwidths:
+            colspec = nodes.colspec(colwidth=colwidth)
+            # FIXME: It seems, that the stub method only works well in the
+            # absence of rowspan (observed by the html buidler, the docutils-xml
+            # build seems OK).  This is not extraordinary, because there exists
+            # no table directive (except *this* flat-table) which allows to
+            # define coexistent of rowspan and stubs (there was no use-case
+            # before flat-table). This should be reviewed (later).
+            if stub_columns:
+                colspec.attributes['stub'] = 1
+                stub_columns -= 1
+            tgroup += colspec
+        stub_columns = self.directive.options.get('stub-columns', 0)
+
+        if header_rows:
+            thead = nodes.thead()
+            tgroup += thead
+            for row in self.rows[:header_rows]:
+                thead += self.buildTableRowNode(row)
+
+        tbody = nodes.tbody()
+        tgroup += tbody
+
+        for row in self.rows[header_rows:]:
+            tbody += self.buildTableRowNode(row)
+        return table
+
+    def buildTableRowNode(self, row_data, classes=None):
+        classes = [] if classes is None else classes
+        row = nodes.row()
+        for cell in row_data:
+            if cell is None:
+                continue
+            cspan, rspan, cellElements = cell
+
+            attributes = {"classes" : classes}
+            if rspan:
+                attributes['morerows'] = rspan
+            if cspan:
+                attributes['morecols'] = cspan
+            entry = nodes.entry(**attributes)
+            entry.extend(cellElements)
+            row += entry
+        return row
+
+    def raiseError(self, msg):
+        error =  self.directive.state_machine.reporter.error(
+            msg
+            , nodes.literal_block(self.directive.block_text
+                                  , self.directive.block_text)
+            , line = self.directive.lineno )
+        raise SystemMessagePropagation(error)
+
+    def parseFlatTableNode(self, node):
+        u"""parses the node from a :py:class:`FlatTable` directive's body"""
+
+        if len(node) != 1 or not isinstance(node[0], nodes.bullet_list):
+            self.raiseError(
+                'Error parsing content block for the "%s" directive: '
+                'exactly one bullet list expected.' % self.directive.name )
+
+        for rowNum, rowItem in enumerate(node[0]):
+            row = self.parseRowItem(rowItem, rowNum)
+            self.rows.append(row)
+        self.roundOffTableDefinition()
+
+    def roundOffTableDefinition(self):
+        u"""Round off the table definition.
+
+        This method rounds off the table definition in :py:member:`rows`.
+
+        * This method inserts the needed ``None`` values for the missing cells
+        arising from spanning cells over rows and/or columns.
+
+        * recount the :py:member:`max_cols`
+
+        * Autospan or fill (option ``fill-cells``) missing cells on the right
+          side of the table-row
+        """
+
+        y = 0
+        while y < len(self.rows):
+            x = 0
+
+            while x < len(self.rows[y]):
+                cell = self.rows[y][x]
+                if cell is None:
+                    x += 1
+                    continue
+                cspan, rspan = cell[:2]
+                # handle colspan in current row
+                for c in range(cspan):
+                    try:
+                        self.rows[y].insert(x+c+1, None)
+                    except: # pylint: disable=W0702
+                        # the user sets ambiguous rowspans
+                        pass # SDK.CONSOLE()
+                # handle colspan in spanned rows
+                for r in range(rspan):
+                    for c in range(cspan + 1):
+                        try:
+                            self.rows[y+r+1].insert(x+c, None)
+                        except: # pylint: disable=W0702
+                            # the user sets ambiguous rowspans
+                            pass # SDK.CONSOLE()
+                x += 1
+            y += 1
+
+        # Insert the missing cells on the right side. For this, first
+        # re-calculate the max columns.
+
+        for row in self.rows:
+            if self.max_cols < len(row):
+                self.max_cols = len(row)
+
+        # fill with empty cells or cellspan?
+
+        fill_cells = False
+        if 'fill-cells' in self.directive.options:
+            fill_cells = True
+
+        for row in self.rows:
+            x =  self.max_cols - len(row)
+            if x and not fill_cells:
+                if row[-1] is None:
+                    row.append( ( x - 1, 0, []) )
+                else:
+                    cspan, rspan, content = row[-1]
+                    row[-1] = (cspan + x, rspan, content)
+            elif x and fill_cells:
+                for i in range(x):
+                    row.append( (0, 0, nodes.comment()) )
+
+    def pprint(self):
+        # for debugging
+        retVal = "[   "
+        for row in self.rows:
+            retVal += "[ "
+            for col in row:
+                if col is None:
+                    retVal += ('%r' % col)
+                    retVal += "\n    , "
+                else:
+                    content = col[2][0].astext()
+                    if len (content) > 30:
+                        content = content[:30] + "..."
+                    retVal += ('(cspan=%s, rspan=%s, %r)'
+                               % (col[0], col[1], content))
+                    retVal += "]\n    , "
+            retVal = retVal[:-2]
+            retVal += "]\n  , "
+        retVal = retVal[:-2]
+        return retVal + "]"
+
+    def parseRowItem(self, rowItem, rowNum):
+        row = []
+        childNo = 0
+        error   = False
+        cell    = None
+        target  = None
+
+        for child in rowItem:
+            if (isinstance(child , nodes.comment)
+                or isinstance(child, nodes.system_message)):
+                pass
+            elif isinstance(child , nodes.target):
+                target = child
+            elif isinstance(child, nodes.bullet_list):
+                childNo += 1
+                cell = child
+            else:
+                error = True
+                break
+
+        if childNo != 1 or error:
+            self.raiseError(
+                'Error parsing content block for the "%s" directive: '
+                'two-level bullet list expected, but row %s does not '
+                'contain a second-level bullet list.'
+                % (self.directive.name, rowNum + 1))
+
+        for cellItem in cell:
+            cspan, rspan, cellElements = self.parseCellItem(cellItem)
+            if target is not None:
+                cellElements.insert(0, target)
+            row.append( (cspan, rspan, cellElements) )
+        return row
+
+    def parseCellItem(self, cellItem):
+        # search and remove cspan, rspan colspec from the first element in
+        # this listItem (field).
+        cspan = rspan = 0
+        if not len(cellItem):
+            return cspan, rspan, []
+        for elem in cellItem[0]:
+            if isinstance(elem, colSpan):
+                cspan = elem.get("span")
+                elem.parent.remove(elem)
+                continue
+            if isinstance(elem, rowSpan):
+                rspan = elem.get("span")
+                elem.parent.remove(elem)
+                continue
+        return cspan, rspan, cellItem[:]
diff --git a/Documentation/sphinx/tmplcvt b/Documentation/sphinx/tmplcvt
new file mode 100755
index 000000000000..909a73065e0a
--- /dev/null
+++ b/Documentation/sphinx/tmplcvt
@@ -0,0 +1,19 @@
+#!/bin/bash
+#
+# Convert a template file into something like RST
+#
+# fix <function>
+# feed to pandoc
+# fix \_
+# title line?
+#
+
+in=$1
+rst=$2
+tmp=$rst.tmp
+
+cp $in $tmp
+sed --in-place -f convert_template.sed $tmp
+pandoc -s -S -f docbook -t rst -o $rst $tmp
+sed --in-place -f post_convert.sed $rst
+rm $tmp
diff --git a/Documentation/sync_file.txt b/Documentation/sync_file.txt
index eaf8297dbca2..e8e2ebafe5fa 100644
--- a/Documentation/sync_file.txt
+++ b/Documentation/sync_file.txt
@@ -6,8 +6,8 @@
 
 This document serves as a guide for device drivers writers on what the
 sync_file API is, and how drivers can support it. Sync file is the carrier of
-the fences(struct fence) that needs to synchronized between drivers or across
-process boundaries.
+the fences(struct fence) that are needed to synchronize between drivers or
+across process boundaries.
 
 The sync_file API is meant to be used to send and receive fence information
 to/from userspace. It enables userspace to do explicit fencing, where instead
@@ -32,7 +32,7 @@ in-fences and out-fences
 Sync files can go either to or from userspace. When a sync_file is sent from
 the driver to userspace we call the fences it contains 'out-fences'. They are
 related to a buffer that the driver is processing or is going to process, so
-the driver an create out-fence to be able to notify, through fence_signal(),
+the driver creates an out-fence to be able to notify, through fence_signal(),
 when it has finished using (or processing) that buffer. Out-fences are fences
 that the driver creates.
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 720355cbdf45..95ccbe6d79ce 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -61,6 +61,7 @@ Currently, these files are in /proc/sys/vm:
 - swappiness
 - user_reserve_kbytes
 - vfs_cache_pressure
+- watermark_scale_factor
 - zone_reclaim_mode
 
 ==============================================================
diff --git a/Documentation/thermal/intel_powerclamp.txt b/Documentation/thermal/intel_powerclamp.txt
index 332de4a39b5a..60073dc9f748 100644
--- a/Documentation/thermal/intel_powerclamp.txt
+++ b/Documentation/thermal/intel_powerclamp.txt
@@ -121,7 +121,7 @@ time is considered largely as a non-causal system where its behavior
 cannot be based on the past or current input. Therefore, the
 intel_powerclamp driver attempts to enforce the desired idle time
 instantly as given input (target idle ratio). After injection,
-powerclamp moniors the actual idle for a given time window and adjust
+powerclamp monitors the actual idle for a given time window and adjust
 the next injection accordingly to avoid over/under correction.
 
 When used in a causal control system, such as a temperature control,
diff --git a/Documentation/usb/gadget_multi.txt b/Documentation/usb/gadget_multi.txt
index 5faf514047e9..b3146dd7aa43 100644
--- a/Documentation/usb/gadget_multi.txt
+++ b/Documentation/usb/gadget_multi.txt
@@ -36,7 +36,7 @@ configuration with CDC ECM which should work better under Linux.
 
 ** Windows host drivers
 
-For the gadget two work under Windows two conditions have to be met:
+For the gadget to work under Windows two conditions have to be met:
 
 *** Detecting as composite gadget
 
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 85a8fdcfcdaa..c9b4959fd04e 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -54,3 +54,4 @@
  53 -> Hauppauge WinTV Starburst                           [0070:c12a]
  54 -> ViewCast 260e                                       [1576:0260]
  55 -> ViewCast 460e                                       [1576:0460]
+ 56 -> Hauppauge WinTV-quadHD (DVB)               [0070:6a28,0070:6b28]
diff --git a/Documentation/video4linux/v4l2-controls.txt b/Documentation/video4linux/v4l2-controls.txt
index 5e759cab4538..f930b80e9111 100644
--- a/Documentation/video4linux/v4l2-controls.txt
+++ b/Documentation/video4linux/v4l2-controls.txt
@@ -96,21 +96,6 @@ Basic usage for V4L2 and sub-device drivers
 
   Where foo->sd is of type struct v4l2_subdev.
 
-  And set all core control ops in your struct v4l2_subdev_core_ops to these
-  helpers:
-
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
-	.g_ctrl = v4l2_subdev_g_ctrl,
-	.s_ctrl = v4l2_subdev_s_ctrl,
-	.g_ext_ctrls = v4l2_subdev_g_ext_ctrls,
-	.try_ext_ctrls = v4l2_subdev_try_ext_ctrls,
-	.s_ext_ctrls = v4l2_subdev_s_ext_ctrls,
-
-  Note: this is a temporary solution only. Once all V4L2 drivers that depend
-  on subdev drivers are converted to the control framework these helpers will
-  no longer be needed.
-
 1.4) Clean up the handler at the end:
 
 	v4l2_ctrl_handler_free(&foo->ctrl_handler);
diff --git a/Documentation/video4linux/vivid.txt b/Documentation/video4linux/vivid.txt
index 8da5d2a576bc..1b26519c6ddc 100644
--- a/Documentation/video4linux/vivid.txt
+++ b/Documentation/video4linux/vivid.txt
@@ -74,7 +74,8 @@ Section 11: Cropping, Composing, Scaling
 Section 12: Formats
 Section 13: Capture Overlay
 Section 14: Output Overlay
-Section 15: Some Future Improvements
+Section 15: CEC (Consumer Electronics Control)
+Section 16: Some Future Improvements
 
 
 Section 1: Configuring the driver
@@ -364,7 +365,11 @@ For HDMI inputs it is possible to set the EDID. By default a simple EDID
 is provided. You can only set the EDID for HDMI inputs. Internally, however,
 the EDID is shared between all HDMI inputs.
 
-No interpretation is done of the EDID data.
+No interpretation is done of the EDID data with the exception of the
+physical address. See the CEC section for more details.
+
+There is a maximum of 15 HDMI inputs (if there are more, then they will be
+reduced to 15) since that's the limitation of the EDID physical address.
 
 
 Section 3: Video Output
@@ -409,6 +414,9 @@ standard, and for all others a 1:1 pixel aspect ratio is returned.
 
 An HDMI output has a valid EDID which can be obtained through VIDIOC_G_EDID.
 
+There is a maximum of 15 HDMI outputs (if there are more, then they will be
+reduced to 15) since that's the limitation of the EDID physical address. See
+also the CEC section for more details.
 
 Section 4: VBI Capture
 ----------------------
@@ -1108,7 +1116,26 @@ capabilities will slow down the video loop considerably as a lot of checks have
 to be done per pixel.
 
 
-Section 15: Some Future Improvements
+Section 15: CEC (Consumer Electronics Control)
+----------------------------------------------
+
+If there are HDMI inputs then a CEC adapter will be created that has
+the same number of input ports. This is the equivalent of e.g. a TV that
+has that number of inputs. Each HDMI output will also create a
+CEC adapter that is hooked up to the corresponding input port, or (if there
+are more outputs than inputs) is not hooked up at all. In other words,
+this is the equivalent of hooking up each output device to an input port of
+the TV. Any remaining output devices remain unconnected.
+
+The EDID that each output reads reports a unique CEC physical address that is
+based on the physical address of the EDID of the input. So if the EDID of the
+receiver has physical address A.B.0.0, then each output will see an EDID
+containing physical address A.B.C.0 where C is 1 to the number of inputs. If
+there are more outputs than inputs then the remaining outputs have a CEC adapter
+that is disabled and reports an invalid physical address.
+
+
+Section 16: Some Future Improvements
 ------------------------------------
 
 Just as a reminder and in no particular order:
@@ -1121,8 +1148,6 @@ Just as a reminder and in no particular order:
 - Fix sequence/field numbering when looping of video with alternate fields
 - Add support for V4L2_CID_BG_COLOR for video outputs
 - Add ARGB888 overlay support: better testing of the alpha channel
-- Add custom DV timings support
-- Add support for V4L2_DV_FL_REDUCED_FPS
 - Improve pixel aspect support in the tpg code by passing a real v4l2_fract
 - Use per-queue locks and/or per-device locks to improve throughput
 - Add support to loop from a specific output to a specific input across
@@ -1133,3 +1158,4 @@ Just as a reminder and in no particular order:
 - Make a thread for the RDS generation, that would help in particular for the
   "Controls" RDS Rx I/O Mode as the read-only RDS controls could be updated
   in real-time.
+- Changing the EDID should cause hotplug detect emulation to happen.
diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt
index 5e0e05c5183e..c49e3178178d 100644
--- a/Documentation/workqueue.txt
+++ b/Documentation/workqueue.txt
@@ -169,7 +169,7 @@ resources, scheduled and executed.
   WQ_UNBOUND
 
 	Work items queued to an unbound wq are served by the special
-	woker-pools which host workers which are not bound to any
+	worker-pools which host workers which are not bound to any
 	specific CPU.  This makes the wq behave as a simple execution
 	context provider without concurrency management.  The unbound
 	worker-pools try to start execution of work items as soon as
diff --git a/Documentation/zh_CN/CodingStyle b/Documentation/zh_CN/CodingStyle
index 654afd72eb24..12717791baac 100644
--- a/Documentation/zh_CN/CodingStyle
+++ b/Documentation/zh_CN/CodingStyle
@@ -24,34 +24,33 @@ Documentation/CodingStyle的中文翻译
 
 		Linux内核代�风格
 
-这是一个简短的文档，�述了linux内核的首选代�风格。代�风格是因人而异的，而且我
-�愿�把我的观点强加给任何人，�过这里所讲述的是我必须�维护的代�所�守的风格，
-并且我也希望�大多数其他代�也能�守这个风格。请在写代�时至少考虑一下本文所述的
-风格。
+这是一个简短的文档，�述了 linux 内核的首选代�风格。代�风格是因人而异的，而且我
+�愿�把自己的观点强加给任何人，但这就�我去�任何事情都必须�循的原则那样，我也
+希望在�大多数事上��这�的�度。请（在写代�时）至少考虑一下这里的代�风格。
 
-首先，我建议你打�一份GNU代�规范，然���读它。烧了它，这是一个具有�大象�性
-�义的动作。
+首先，我建议你打�一份 GNU 代�规范，然���读。烧了它，这是一个具有�大象�性�义
+的动作。
 
 �管怎样，现在我们开始：
 
 
-	 	第一章：缩进
+		第一章：缩进
 
-制表符是8个字符，所以缩进也是8个字符。有些异端�动试图将缩进�为4（乃至2）个字符
-深，这几乎相当于�试将圆周率的值定义为3。
+制表符是 8 个字符，所以缩进也是 8 个字符。有些异端�动试图将缩进�为 4（甚至 2�）
+个字符深，这几乎相当于�试将圆周率的值定义为 3。
 
 �由：缩进的全部�义就在于清楚的定义一个控制�起止于何处。尤其是当你盯�你的�幕
-连续看了20�时之�，你将会�现大一点的缩进会使你更容易分辨缩进。
+连续看了 20 �时之�，你将会�现大一点的缩进会使你更容易分辨缩进。
 
-现在，有些人会抱怨8个字符的缩进会使代���边移动的太远，在80个字符的终端�幕上
-就很难读这样的代�。这个问题的答案是，如果你需�3级以上的缩进，�管用何�方�你
+现在，有些人会抱怨 8 个字符的缩进会使代���边移动的太远，在 80 个字符的终端�幕上
+就很难读这样的代�。这个问题的答案是，如果你需� 3 级以上的缩进，�管用何�方�你
 的代�已�有问题了，应该修正你的程�。
 
-简而言之，8个字符的缩进�以让代�更容易阅读，还有一个好处是当你的函数嵌套太深的
+简而言之，8 个字符的缩进�以让代�更容易阅读，还有一个好处是当你的函数嵌套太深的
 时候�以给你警告。留心这个警告。
 
-在switch语�中消除多级缩进的首选的方�是让“switch�和从属于它的“case�标签对�于�
-一列，而��“两次缩进�“case�标签。比如：
+在 switch 语�中消除多级缩进的首选的方�是让 “switch� 和从属于它的 “case� 标签
+对�于�一列，而�� “两次缩进� “case� 标签。比如：
 
 	switch (suffix) {
 	case 'G':
@@ -70,7 +69,6 @@ Documentation/CodingStyle的中文翻译
 		break;
 	}
 
-
 ��把多个语�放在一行里，除�你有什么东西���：
 
 	if (condition) do_this;
@@ -79,7 +77,7 @@ Documentation/CodingStyle的中文翻译
 也��在一行里放多个赋值语�。内核代�风格超级简�。就是���能导致别人误读的表
 达�。
 
-除了注释�文档和Kconfig之外，��使用空格�缩进，��的例�是例外，是有�为之。
+除了注释�文档和 Kconfig 之外，��使用空格�缩进，��的例�是例外，是有�为之。
 
 选用一个好的编辑器，��在行尾留空格。
 
@@ -88,27 +86,18 @@ Documentation/CodingStyle的中文翻译
 
 代�风格的�义就在于使用平常使用的工具�维�代�的�读性和�维护性。
 
-�一行的长度的�制是80列，我们强烈建议您�守这个惯例。
+�一行的长度的�制是 80 列，我们强烈建议您�守这个惯例。
 
-长于80列的语��打散�有�义的片段。�个片段�明显短于原�的语�，而且放置的�置
-也明显的��。�样的规则也适用于有很长�数列表的函数头。长字符串也�打散�较短的
-字符串。唯一的例外是超过80列�以大幅度�高�读性并且�会��信�的情况。
-
-void fun(int a, int b, int c)
-{
-	if (condition)
-		printk(KERN_WARNING "Warning this is a long printk with "
-						"3 parameters a: %u b: %u "
-						"c: %u \n", a, b, c);
-	else
-		next_statement;
-}
+长于 80 列的语��打散�有�义的片段。除�超过 80 列能显著增加�读性，并且�会��
+信�。�片段�明显短于�片段，并明显��。这�样适用于有�很长�数列表的函数头。
+然而，�对��打散对用户��的字符串，例如 printk 信�，因为这将导致无法 grep 这些
+信�。
 
 		第三章：大括�和空格的放置
 
 C语言风格中�外一个常�问题是大括�的放置。和缩进大���，选择或弃用��放置策
-略并没有多少技术上的原因，�过首选的方�，就�Kernighan和Ritchie展示给我们的，是
-把起始大括�放在行尾，而把结�大括�放在行首，所以：
+略并没有多少技术上的原因，�过首选的方�，就� Kernighan 和 Ritchie 展示给我们的，
+是把起始大括�放在行尾，而把结�大括�放在行首，所以：
 
 	if (x is true) {
 		we do y
@@ -134,12 +123,12 @@ C语言风格中å�¦å¤–一个常è§�问题是大括å�·çš„放置。和缩进大å°�ä
 		body of function
 	}
 
-全世界的异端�能会抱怨这个�一致性是……呃……�一致的，�过所有�维�全的人都知�（
-a）K&R是_正确的_，并且（b）K&R是正确的。此外，�管怎样函数都是特殊的（在C语言中
-，函数是�能嵌套的）。
+全世界的异端�能会抱怨这个�一致性是……呃……�一致的，�过所有�维�全的人都知�
+(a) K&R 是 _正确的_，并且 (b) K&R 是正确的。此外，�管怎样函数都是特殊的（C
+函数是�能嵌套的）。
 
-注�结�大括�独自��一行，除�它��跟��一个语�的剩余部分，也就是do语�中的
-“while�或者if语�中的“else�，�这样：
+注�结�大括�独自��一行，除�它��跟��一个语�的剩余部分，也就是 do 语�中的
+“while� 或者 if 语�中的 “else�，�这样：
 
 	do {
 		body of do-loop
@@ -158,41 +147,50 @@ a）K&R是_正确的_，并且（b）K&R是正确的。此外，ä¸�管怎样函æ
 �由：K&R。
 
 也请注�这�大括�的放置方�也能使空（或者差�多空的）行的数�最�化，�时�失�
-读性。因此，由于你的�幕上的新行是���生资�（想想25行的终端�幕），你将会有更
+读性。因此，由于你的�幕上的新行是���生资�（想想 25 行的终端�幕），你将会有更
 多的空行�放置注释。
 
 当�有一个�独的语�的时候，�用加�必�的大括�。
 
-if (condition)
-	action();
+	if (condition)
+		action();
+
+和
+
+	if (condition)
+		do_this();
+	else
+		do_that();
 
-这点�适用于本身为�个�件语�的一个分支的�独语�。这时需�在两个分支里都使用大
-括�。
+这并�适用于�有一个�件分支是�语�的情况；这时所有分支都�使用大括�：
 
-if (condition) {
-	do_this();
-	do_that();
-} else {
-	otherwise();
-}
+	if (condition) {
+		do_this();
+		do_that();
+	} else {
+		otherwise();
+	}
 
 		3.1：空格
 
-Linux内核的空格使用方�（主�）�决于它是用于函数还是关键字。（大多数）关键字�
-�加一个空格。值得注�的例外是sizeof�typeof�alignof和__attribute__，这些关键字
-�些程度上看起�更�函数（它们在Linux里也常常伴��括�而使用，尽管在C语言里这样
-的�括��是必需的，就�“struct fileinfo info�声明过�的“sizeof info�）。
+Linux 内核的空格使用方�（主�）�决于它是用于函数还是关键字。（大多数）关键字�
+�加一个空格。值得注�的例外是 sizeof�typeof�alignof 和 __attribute__，这些
+关键字�些程度上看起�更�函数（它们在 Linux 里也常常伴��括�而使用，尽管在 C 里
+这样的�括��是必需的，就� “struct fileinfo info� 声明过�的 “sizeof info�）。
 
 所以在这些关键字之�放一个空格：
+
 	if, switch, case, for, do, while
-但是��在sizeof�typeof�alignof或者__attribute__这些关键字之�放空格。例如，
+
+但是��在 sizeof�typeof�alignof 或者 __attribute__ 这些关键字之�放空格。例如，
+
 	s = sizeof(struct file);
 
 ��在�括�里的表达�两侧加空格。这是一个�例：
 
 	s = sizeof( struct file );
 
-当声明指针类型或者返回指针类型的函数时，“*�的首选使用方�是使之�近���或者函
+当声明指针类型或者返回指针类型的函数时，“*� 的首选使用方�是使之�近���或者函
 数�，而�是�近类型�。例�：
 
 	char *linux_banner;
@@ -204,15 +202,18 @@ Linux内核的空格使用方�（主�）�决于它是用于函数还是关
 	=  +  -  <  >  *  /  %  |  &  ^  <=  >=  ==  !=  ?  :
 
 但是一元�作符���加空格：
+
 	&  *  +  -  ~  !  sizeof  typeof  alignof  __attribute__  defined
 
 �缀自加和自�一元�作符��加空格：
+
 	++  --
 
 �缀自加和自�一元�作符��加空格：
+
 	++  --
 
-“.�和“->�结构体�员�作符���加空格。
+‘.’ 和 “->� 结构体�员�作符���加空格。
 
 ��在行尾留空白。有些�以自动缩进的编辑器会在新行的行首加入适�的空白，然�你
 就�以直接在那一行输入代�。�过�如你最�没有在那一行输入代�，有些编辑器就�
@@ -225,23 +226,23 @@ Linux内核的空格使用方�（主�）�决于它是用于函数还是关
 
 		第四章：命�
 
-C是一个简朴的语言，你的命�也应该这样。和Modula-2和Pascal程�员��，C程�员�使
-用类似ThisVariableIsATemporaryCounter这样�丽的�字。C程�员会称那个��为“tmp�
-，这样写起�会更容易，而且至少�会令其难于�解。
+C是一个简朴的语言，你的命�也应该这样。和 Modula-2 和 Pascal 程�员��，C 程�员
+�使用类似 ThisVariableIsATemporaryCounter 这样�丽的�字。C 程�员会称那个��
+为 “tmp�，这样写起�会更容易，而且至少�会令其难于�解。
 
 �过，虽然混用大�写的�字是��倡使用的，但是全局��还是需�一个具�述性的�字
-。称一个全局函数为“foo�是一个难以饶�的错误。
+。称一个全局函数为 “foo� 是一个难以饶�的错误。
 
 全局��（�有当你真正需�它们的时候�用它）需�有一个具�述性的�字，就�全局函
-数。如果你有一个�以计算活动用户数�的函数，你应该�它“count_active_users()�或者
-类似的�字，你�应该�它“cntuser()�。
+数。如果你有一个�以计算活动用户数�的函数，你应该�它 “count_active_users()�
+或者类似的�字，你�应该�它 “cntuser()�。
 
 在函数�中包�函数类型（所谓的匈牙利命�法）是脑�出了问题——编译器知�那些类型而
 且能够检查那些类型，这样��能把程�员弄糊涂了。难怪微软总是制造出有问题的程�。
 
 本地���应该简短，而且能够表达相关的�义。如果你有一些�机的整数型的循环计数器
-，它应该被称为“i�。�它“loop_counter�并无益处，如果它没有被误解的�能的�。类似
-的，“tmp��以用�称呼任�类型的临时��。
+，它应该被称为 “i�。�它 “loop_counter� 并无益处，如果它没有被误解的�能的�。
+类似的，“tmp� �以用�称呼任�类型的临时��。
 
 如果你怕混淆了你的本地���，你就�到�一个问题了，��函数增长�尔蒙失衡综�症
 。请看第六章（函数）。
@@ -249,9 +250,9 @@ C是一个简朴的语言，你的命å��也应该这样。和Modula-2å’ŒPascalç¨
 
 		第五章：Typedef
 
-��使用类似“vps_t�之类的东西。
+��使用类似 “vps_t� 之类的东西。
 
-对结构体和指针使用typedef是一个错误。当你在代�里看到：
+对结构体和指针使用 typedef 是一个错误。当你在代�里看到：
 
 	vps_t a;
 
@@ -261,91 +262,91 @@ C是一个简朴的语言，你的命å��也应该这样。和Modula-2å’ŒPascalç¨
 
 	struct virtual_container *a;
 
-你就知�“a�是什么了。
+你就知� “a� 是什么了。
 
-很多人认为typedef“能�高�读性�。实际�是这样的。它们�在下列情况下有用：
+很多人认为 typedef “能�高�读性�。实际�是这样的。它们�在下列情况下有用：
 
- (a) 完全��明的对象（这�情况下�主动使用typedef���这个对象实际上是什么）。
+ (a) 完全��明的对象（这�情况下�主动使用 typedef ���这个对象实际上是什么）。
 
-     例如：“pte_t�等��明对象，你�能用�适的访问函数�访问它们。
+     例如：“pte_t� 等��明对象，你�能用�适的访问函数�访问它们。
 
-     注����明性和“访问函数�本身是�好的。我们使用pte_t等类型的原因在于真的是
+     注����明性和“访问函数�本身是�好的。我们使用 pte_t 等类型的原因在于真的是
      完全没有任何共用的�访问信�。
 
- (b) 清楚的整数类型，如此，这层抽象就�以帮助消除到底是“int�还是“long�的混淆。
+ (b) 清楚的整数类型，如此，这层抽象就�以帮助消除到底是 “int� 还是 “long� 的混淆。
 
-     u8/u16/u32是完全没有问题的typedef，�过它们更符�类别(d)而�是这里。
+     u8/u16/u32 是完全没有问题的 typedef，�过它们更符�类别 (d) 而�是这里。
 
-     �次注���这样�，必须事出有因。如果�个��是“unsigned long“，那么没有必�
+     �次注���这样�，必须事出有因。如果�个��是 “unsigned long“，那么没有必�
 
 	typedef unsigned long myflags_t;
 
-     �过如果有一个明确的原因，比如它在��情况下�能会是一个“unsigned int�而在
-     其他情况下�能为“unsigned long�，那么就��犹豫，请务必使用typedef。
+     �过如果有一个明确的原因，比如它在��情况下�能会是一个 “unsigned int� 而在
+     其他情况下�能为 “unsigned long�，那么就��犹豫，请务必使用 typedef。
 
  (c) 当你使用sparse按字�的创建一个新类型��类型检查的时候。
 
  (d) 和标准C99类型相�的类型，在�些例外的情况下。
 
-     虽然让眼�和脑筋�适应新的标准类型比如“uint32_t��需�花很多时间，�是有些
+     虽然让眼�和脑筋�适应新的标准类型比如 “uint32_t� �需�花很多时间，�是有些
      人�然拒�使用它们。
 
-     因此，Linux特有的等�于标准类型的“u8/u16/u32/u64�类型和它们的有符�类型是被
+     因此，Linux 特有的等�于标准类型的 “u8/u16/u32/u64� 类型和它们的有符�类型是被
      �许的——尽管在你自己的新代�中，它们�是强制�求�使用的。
 
      当编辑已�使用了�个类型集的已有代�时，你应该�循那些代�中已��出的选择。
 
  (e) �以在用户空间安全使用的类型。
 
-     在�些用户空间��的结构体里，我们�能�求C99类型而且�能用上��到的“u32�
-     类型。因此，我们在与用户空间共享的所有结构体中使用__u32和类似的类型。
+     在�些用户空间��的结构体里，我们�能�求C99类型而且�能用上��到的 “u32�
+     类型。因此，我们在与用户空间共享的所有结构体中使用 __u32 和类似的类型。
 
-�能还有其他的情况，�过基本的规则是永远��使用typedef，除�你�以明确的应用上
+�能还有其他的情况，�过基本的规则是永远��使用 typedef，除�你�以明确的应用上
 述�个规则中的一个。
 
 总的�说，如果一个指针或者一个结构体里的元素�以��的被直接访问到，那么它们就�
-应该是一个typedef。
+应该是一个 typedef。
 
 
 		第六章：函数
 
 函数应该简短而漂亮，并且�完�一件事情。函数应该�以一�或者两�显示完（我们都知
-�ISO/ANSI�幕大�是80x24），��一件事情，而且把它�好。
+� ISO/ANSI �幕大�是 80x24），��一件事情，而且把它�好。
 
 一个函数的最大长度是和该函数的��度和缩进级数��比的。所以，如果你有一个�论上
-很简�的�有一个很长（但是简�）的case语�的函数，而且你需�在�个case里�很多很
-�的事情，这样的函数尽管很长，但也是�以的。
+很简�的�有一个很长（但是简�）的 case 语�的函数，而且你需�在�个 case 里�
+很多很�的事情，这样的函数尽管很长，但也是�以的。
 
 �过，如果你有一个��的函数，而且你怀疑一个天分�是很高的高中一年级学生�能甚至
 ��清楚这个函数的目的，你应该严格的�守���到的长度�制。使用辅助函数，并为之
 �个具�述性的�字（如果你觉得它们的性能很��的�，�以让编译器内�它们，这样的
 效果往往会比你写一个��函数的效果�好。）
 
-函数的�外一个衡�标准是本地��的数�。此数��应超过5�10个，�则你的函数就有
+函数的�外一个衡�标准是本地��的数�。此数��应超过 5�10 个，�则你的函数就有
 问题了。�新考虑一下你的函数，把它分拆�更�的函数。人的大脑一般�以轻�的�时跟
-踪7个��的事物，如果�增多的�，就会糊涂了。�便你�颖过人，你也�能会记�清你2
-个星期��过的事情。
+踪 7 个��的事物，如果�增多的�，就会糊涂了。�便你�颖过人，你也�能会记�清你
+2 个星期��过的事情。
 
-在�文件里，使用空行隔开��的函数。如果该函数需�被导出，它的EXPORT*�应该紧贴
+在�文件里，使用空行隔开��的函数。如果该函数需�被导出，它的 EXPORT* �应该紧贴
 在它的结�大括�之下。比如：
 
-int system_is_up(void)
-{
-	return system_state == SYSTEM_RUNNING;
-}
-EXPORT_SYMBOL(system_is_up);
+	int system_is_up(void)
+	{
+		return system_state == SYSTEM_RUNNING;
+	}
+	EXPORT_SYMBOL(system_is_up);
 
-在函数原型中，包�函数�和它们的数�类型。虽然C语言里没有这样的�求，在Linux里这
+在函数原型中，包�函数�和它们的数�类型。虽然C语言里没有这样的�求，在 Linux 里这
 是�倡的�法，因为这样�以很简�的给读者�供更多的有价值的信�。
 
 
 		第七章：集中的函数退出途径
 
-虽然被�些人声称已�过时，但是goto语�的等价物还是�常被编译器所使用，具体形�是
+虽然被�些人声称已�过时，但是 goto 语�的等价物还是�常被编译器所使用，具体形�是
 无�件跳转指令。
 
-当一个函数从多个�置退出并且需��一些通用的清�工作的时候，goto的好处就显现出�
-了。
+当一个函数从多个�置退出，并且需��一些类似清�的常��作时，goto 语�就很方便了。
+如果并�需�清��作，那么直接 return ��。
 
 �由是：
 
@@ -354,26 +355,37 @@ EXPORT_SYMBOL(system_is_up);
 - �以��由于修改时忘记更新�个�独的退出点而导致的错误
 - �轻了编译器的工作，无需删除冗余代�;)
 
-int fun(int a)
-{
-	int result = 0;
-	char *buffer = kmalloc(SIZE);
-
-	if (buffer == NULL)
-		return -ENOMEM;
-
-	if (condition1) {
-		while (loop1) {
-			...
+	int fun(int a)
+	{
+		int result = 0;
+		char *buffer;
+
+		buffer = kmalloc(SIZE, GFP_KERNEL);
+		if (!buffer)
+			return -ENOMEM;
+
+		if (condition1) {
+			while (loop1) {
+				...
+			}
+			result = 1;
+			goto out_buffer;
 		}
-		result = 1;
-		goto out;
+		...
+	out_buffer:
+		kfree(buffer);
+		return result;
 	}
-	...
-out:
-	kfree(buffer);
-	return result;
-}
+
+一个需�注�的常�错误是“一个 err 错误�，就�这样：
+
+	err:
+		kfree(foo->bar);
+		kfree(foo);
+		return ret;
+
+这段代�的错误是，在�些退出路径上 “foo� 是 NULL。通常情况下，通过把它分离�两个
+错误标签 “err_bar:� 和 “err_foo:� �修�这个错误。
 
 		第八章：注释
 
@@ -386,10 +398,10 @@ out:
 加太多。你应该�的，是把注释放在函数的头部，告诉人们它�了什么，也�以加上它�这
 些事情的原因。
 
-当注释内核API函数时，请使用kernel-doc格�。请看
-Documentation/kernel-doc-nano-HOWTO.txt和scripts/kernel-doc以获得详细信�。
+当注释内核API函数时，请使用 kernel-doc 格�。请看
+Documentation/kernel-documentation.rst和scripts/kernel-doc 以获得详细信�。
 
-Linux的注释风格是C89“/* ... */�风格。��使用C99风格“// ...�注释。
+Linux的注释风格是 C89 “/* ... */� 风格。��使用 C99 风格 “// ...� 注释。
 
 长（多行）的首选注释风格是：
 
@@ -402,6 +414,15 @@ Linux的注释风格是C89“/* ... */�风格。��使用C99风格“// ...
 	 * with beginning and ending almost-blank lines.
 	 */
 
+对于在 net/ 和 drivers/net/ 的文件，首选的长（多行）注释风格有些��。
+
+	/* The preferred comment style for files in net/ and drivers/net
+	 * looks like this.
+	 *
+	 * It is nearly the same as the generally preferred comment style,
+	 * but there is no initial almost-blank line.
+	 */
+
 注释数�也是很��的，�管是基本类型还是�生类型。为了方便实现这一点，�一行应�
 声明一个数�（��使用逗��一次声明多个数�）。这样你就有空间�为�个数�写一段
 �注释�解释它们的用途了。
@@ -409,49 +430,63 @@ Linux的注释风格是C89“/* ... */�风格。��使用C99风格“// ...
 
 		第�章：你已�把事情弄糟了
 
-这没什么，我们都是这样。�能你的使用了很长时间Unix的朋�已�告诉你“GNU emacs�能
-自动帮你格�化C�代�，而且你也注�到了，确实是这样，�过它所使用的默认值和我们
-想�的相去甚远（实际上，甚至比�机打的还�差——无数个猴�在GNU emacs里打字永远�
-会创造出一个好程�）（译注：请�考Infinite Monkey Theorem）
-
-所以你�么放弃GNU emacs，�么改�它让它使用更��的设定。�采用�一个方案，你�
-以把下�这段粘贴到你的.emacs文件里。
-
-(defun linux-c-mode ()
-  "C mode with adjusted defaults for use with the Linux kernel."
-  (interactive)
-  (c-mode)
-  (c-set-style "K&R")
-  (setq tab-width 8)
-  (setq indent-tabs-mode t)
-  (setq c-basic-offset 8))
-
-这样就定义了M-x linux-c-mode命令。当你hack一个模�的时候，如果你把字符串
--*- linux-c -*-放在头两行的�个�置，这个模�将会被自动调用。如果你希望在你修改
-/usr/src/linux里的文件时魔术般自动打开linux-c-mode的�，你也�能需�添加
-
-(setq auto-mode-alist (cons '("/usr/src/linux.*/.*\\.[ch]$" . linux-c-mode)
-			auto-mode-alist))
-
-到你的.emacs文件里。
-
-�过就算你�试让emacs正确的格�化代�失败了，也并��味�你失去了一切：还�以用“
-indent�。
-
-�过，GNU indent也有和GNU emacs一样有问题的设定，所以你需�给它一些命令选项。�
-过，这还�算太糟糕，因为就算是GNU indent的作者也认�K&R的��性（GNU的人并�是�
-人，他们�是在这个问题上被严�的误导了），所以你��给indent指定选项“-kr -i8�
-（代表“K&R，8个字符缩进�），或者使用“scripts/Lindent�，这样就�以以最时髦的方�
+这没什么，我们都是这样。�能你的使用了很长时间 Unix 的朋�已�告诉你 “GNU emacs� 能
+自动帮你格�化 C �代�，而且你也注�到了，确实是这样，�过它所使用的默认值和我们
+想�的相去甚远（实际上，甚至比�机打的还�差——无数个猴�在 GNU emacs 里打字永远�
+会创造出一个好程�）（译注：请�考 Infinite Monkey Theorem）
+
+所以你�么放弃 GNU emacs，�么改�它让它使用更��的设定。�采用�一个方案，你�
+以把下�这段粘贴到你的 .emacs 文件里。
+
+(defun c-lineup-arglist-tabs-only (ignored)
+  "Line up argument lists by tabs, not spaces"
+  (let* ((anchor (c-langelem-pos c-syntactic-element))
+         (column (c-langelem-2nd-pos c-syntactic-element))
+         (offset (- (1+ column) anchor))
+         (steps (floor offset c-basic-offset)))
+    (* (max steps 1)
+       c-basic-offset)))
+
+(add-hook 'c-mode-common-hook
+          (lambda ()
+            ;; Add kernel style
+            (c-add-style
+             "linux-tabs-only"
+             '("linux" (c-offsets-alist
+                        (arglist-cont-nonempty
+                         c-lineup-gcc-asm-reg
+                         c-lineup-arglist-tabs-only))))))
+
+(add-hook 'c-mode-hook
+          (lambda ()
+            (let ((filename (buffer-file-name)))
+              ;; Enable kernel mode for the appropriate files
+              (when (and filename
+                         (string-match (expand-file-name "~/src/linux-trees")
+                                       filename))
+                (setq indent-tabs-mode t)
+                (setq show-trailing-whitespace t)
+                (c-set-style "linux-tabs-only")))))
+
+这会让 emacs 在 ~/src/linux-trees 目录下的 C �文件获得更好的内核代�风格。
+
+�过就算你�试让 emacs 正确的格�化代�失败了，也并��味�你失去了一切：还�以用
+“indent�。
+
+�过，GNU indent 也有和 GNU emacs 一样有问题的设定，所以你需�给它一些命令选项。�
+过，这还�算太糟糕，因为就算是 GNU indent 的作者也认� K&R 的��性（GNU 的人并�是
+�人，他们�是在这个问题上被严�的误导了），所以你��给 indent 指定选项 “-kr -i8�
+（代表 “K&R，8 个字符缩进�），或者使用 “scripts/Lindent�，这样就�以以最时髦的方�
 缩进�代�。
 
-“indent�有很多选项，特别是�新格�化注释的时候，你�能需�看一下它的手册页。�过
-记�：“indent��能修正�的编程习惯。
+“indent� 有很多选项，特别是�新格�化注释的时候，你�能需�看一下它的手册页。�过
+记�：“indent� �能修正�的编程习惯。
 
 
-		第�章：Kconfig�置文件
+		第�章：Kconfig �置文件
 
-对于�布��树的所有Kconfig*�置文件�说，它们缩进方�与C代�相比有所��。紧挨
-在“config�定义下�的行缩进一个制表符，帮助信�则�多缩进2个空格。比如：
+对于�布��树的所有 Kconfig* �置文件�说，它们缩进方�与 C 代�相比有所��。紧挨
+在 “config� 定义下�的行缩进一个制表符，帮助信�则�多缩进 2 个空格。比如：
 
 config AUDIT
 	bool "Auditing support"
@@ -470,7 +505,7 @@ config ADFS_FS_RW
 	depends on ADFS_FS
 	...
 
-�查看�置文件的完整文档，请看Documentation/kbuild/kconfig-language.txt。
+�查看�置文件的完整文档，请看 Documentation/kbuild/kconfig-language.txt。
 
 
 		第�一章：数�结构
@@ -489,11 +524,11 @@ config ADFS_FS_RW
 很多数�结构实际上有2级引用计数，它们通常有��“类�的用户。�类计数器统计�类用
 户的数�，�当�类计数器�至零时，全局计数器�一。
 
-这�“多级引用计数�的例��以在内存管�（“struct mm_struct�：mm_users和mm_count）
+这�“多级引用计数�的例��以在内存管�（“struct mm_struct�：mm_users 和 mm_count）
 和文件系统（“struct super_block�：s_count和s_active）中找到。
 
 记�：如果�一个执行线索�以找到你的数�结构，但是这个数�结构没有引用计数器，这
-里几乎肯定是一个bug。
+里几乎肯定是一个 bug。
 
 
 		第�二章：�，枚举和RTL
@@ -508,102 +543,128 @@ config ADFS_FS_RW
 
 一般的，如果能写�内�函数就��写��函数的�。
 
-�有多个语�的�应该被包�在一个do-while代��里：
+�有多个语�的�应该被包�在一个 do-while 代��里：
 
-#define macrofun(a, b, c) 			\
-	do {					\
-		if (a == 5)			\
-			do_this(b, c);		\
-	} while (0)
+	#define macrofun(a, b, c)			\
+		do {					\
+			if (a == 5)			\
+				do_this(b, c);		\
+		} while (0)
 
 使用�的时候应��的事情：
 
 1) 影�控制�程的�：
 
-#define FOO(x)					\
-	do {					\
-		if (blah(x) < 0)		\
-			return -EBUGGERED;	\
-	} while(0)
+	#define FOO(x)					\
+		do {					\
+			if (blah(x) < 0)		\
+				return -EBUGGERED;	\
+		} while (0)
 
 �常�好。它看起��一个函数，�过�能导致“调用�它的函数退出；��打乱读者大脑里
 的语法分�器。
 
 2) �赖于一个固定�字的本地��的�：
 
-#define FOO(val) bar(index, val)
+	#define FOO(val) bar(index, val)
 
 �能看起��是个�错的东西，�过它�常容易把读代�的人�糊涂，而且容易导致看起�
 �相关的改动带�错误。
 
-3) 作为左值的带�数的�： FOO(x) = y；如果有人把FOO��一个内�函数的�，这�用
+3) 作为左值的带�数的�： FOO(x) = y；如果有人把 FOO ��一个内�函数的�，这�用
 法就会出错了。
 
 4) 忘记了优先级：使用表达�定义常�的�必须将表达�置于一对�括�之内。带�数的
 �也�注�此类问题。
 
-#define CONSTANT 0x4000
-#define CONSTEXP (CONSTANT | 3)
+	#define CONSTANT 0x4000
+	#define CONSTEXP (CONSTANT | 3)
+
+5) 在�里定义类似函数的本地��时命�冲�：
 
-cpp手册对�的讲解很详细。Gcc internals手册也详细讲解了RTL（译注：register
+	#define FOO(x)				\
+	({					\
+		typeof(x) ret;			\
+		ret = calc_ret(x);		\
+		(ret);				\
+	})
+
+ret 是本地��的通用�字 - __foo_ret 更�容易与一个已存在的��冲�。
+
+cpp 手册对�的讲解很详细。gcc internals 手册也详细讲解了 RTL（译注：register
 transfer language），内核里的汇编语言�常用到它。
 
 
 		第�三章：打�内核消�
 
 内核开�者应该是�过良好教育的。请一定注�内核信�的拼写，以给人以好的�象。��
-用�规范的��比如“dont�，而�用“do not�或者“don't�。��这些信�简��明了�无
-歧义。
+用�规范的��比如 “dont�，而�用 “do not�或者 “don't�。��这些信�简��明了�
+无歧义。
 
 内核信��必以��（译注：英文��，�点）结�。
 
-在�括�里打�数字(%d)没有任何价值，应该��这样�。
+在�括�里打�数字 (%d) 没有任何价值，应该��这样�。
 
-<linux/device.h>里有一些驱动模型诊断�，你应该使用它们，以确�信�对应于正确的
-设备和驱动，并且被标记了正确的消�级别。这些�有：dev_err(), dev_warn(),
-dev_info()等等。对于那些�和�个特定设备相关连的信�，<linux/kernel.h>定义了
-pr_debug()和pr_info()。
+<linux/device.h> 里有一些驱动模型诊断�，你应该使用它们，以确�信�对应于正确的
+设备和驱动，并且被标记了正确的消�级别。这些�有：dev_err()，dev_warn()，
+dev_info() 等等。对于那些�和�个特定设备相关连的信�，<linux/printk.h> 定义了
+pr_notice()，pr_info()，pr_warn()，pr_err() 和其他。
 
-写出好的调试信��以是一个很大的挑战；当你写出�之�，这些信�在远程除错的时候
-就会�为�大的帮助。当DEBUG符�没有被定义的时候，这些信��应该被编译进内核里
-（也就是说，默认地，它们�应该被包�在内）。如果你使用dev_dbg()或者pr_debug()，
-就能自动达到这个效果。很多�系统拥有Kconfig选项��用-DDEBUG。还有一个相关的惯例
-是使用VERBOSE_DEBUG�添加dev_vdbg()消�到那些已�由DEBUG�用的消�之上。
+写出好的调试信��以是一个很大的挑战；一旦你写出�，这些信�在远程除错时能�供�大
+的帮助。然而打�调试信�的处�方��打��调试信���。其他 pr_XXX() 函数能无�件地
+打�，pr_debug() ��；默认情况下它�会被编译，除�定义了 DEBUG 或设定了
+CONFIG_DYNAMIC_DEBUG。实际这�样是为了 dev_dbg()，一个相关约定是在一个已�开�了
+DEBUG 时，使用 VERBOSE_DEBUG �添加 dev_vdbg()。
+
+许多�系统拥有 Kconfig 调试选项�开� -DDEBUG 在对应的 Makefile 里�；在其他
+情况下，特殊文件使用 #define DEBUG。当一�调试信�需�被无�件打�时，例如，如果
+已�包�一个调试相关的 #ifdef �件，printk(KERN_DEBUG ...) 就�被使用。
 
 
 		第�四章：分�内存
 
-内核�供了下�的一般用途的内存分�函数：kmalloc()，kzalloc()，kcalloc()和
-vmalloc()。请�考API文档以获�有关它们的详细信�。
+内核�供了下�的一般用途的内存分�函数：
+kmalloc()，kzalloc()，kmalloc_array()，kcalloc()，vmalloc() 和 vzalloc()。
+请�考 API 文档以获�有关它们的详细信�。
 
 传递结构体大�的首选形�是这样的：
 
 	p = kmalloc(sizeof(*p), ...);
 
-�外一�传递方�中，sizeof的�作数是结构体的�字，这样会�低�读性，并且�能会引
-入bug。有�能指针��类型被改�时，而对应的传递给内存分�函数的sizeof的结果��。
+�外一�传递方�中，sizeof 的�作数是结构体的�字，这样会�低�读性，并且�能会引
+入 bug。有�能指针��类型被改�时，而对应的传递给内存分�函数的 sizeof 的结果��。
 
-强制转�一个void指针返回值是多余的。C语言本身��了从void指针到其他任何指针类型
+强制转�一个 void 指针返回值是多余的。C 语言本身��了从 void 指针到其他任何指针类型
 的转�是没有问题的。
 
+分�一个数组的首选形�是这样的：
+
+	p = kmalloc_array(n, sizeof(...), ...);
+
+分�一个零长数组的首选形�是这样的：
+
+	p = kcalloc(n, sizeof(...), ...);
+
+两�形�检查分�大� n * sizeof(...) 的溢出，如果溢出返回 NULL。
+
 
 		第�五章：内�弊病
 
-有一个常�的误解是内�函数是gcc�供的�以让代��行更快的一个选项。虽然使用内�
+有一个常�的误解是内�函数是 gcc �供的�以让代��行更快的一个选项。虽然使用内�
 函数有时候是�当的（比如作为一�替代�的方�，请看第�二章），�过很多情况下�是
-这样。inline关键字的过度使用会使内核�大，从而使整个系统�行速度�慢。因为大内核
+这样。inline 关键字的过度使用会使内核�大，从而使整个系统�行速度�慢。因为大内核
 会�用更多的指令高速缓存（译注：一级缓存通常是指令缓存和数�缓存分开的）而且会导
-致pagecache的�用内存�少。想象一下，一次pagecache未命中就会导致一次�盘寻�，将
-耗时5毫秒。5毫秒的时间内CPU能执行很多很多指令。
+致 pagecache 的�用内存�少。想象一下，一次pagecache未命中就会导致一次�盘寻�，
+将耗时 5 毫秒。5 毫秒的时间内 CPU 能执行很多很多指令。
 
-一个基本的原则是如果一个函数有3行以上，就��把它��内�函数。这个原则的一个例
+一个基本的原则是如果一个函数有 3 行以上，就��把它��内�函数。这个原则的一个例
 外是，如果你知��个�数是一个编译时常�，而且因为这个常�你确定编译器在编译时能
-优化掉你的函数的大部分代�，那�然�以给它加上inline关键字。kmalloc()内�函数就
+优化掉你的函数的大部分代�，那�然�以给它加上 inline 关键字。kmalloc() 内�函数就
 是一个很好的例�。
 
-人们�常主张给static的而且�用了一次的函数加上inline，如此�会有任何�失，因为没
-有什么好�衡的。虽然从技术上说这是正确的，但是实际上这�情况下�使�加inline gcc
-也�以自动使其内�。而且其他用户�能会�求移除inline，由此而�的争论会抵消inline
+人们�常主张给 static 的而且�用了一次的函数加上 inline，如此�会有任何�失，因为没
+有什么好�衡的。虽然从技术上说这是正确的，但是实际上这�情况下�使�加 inline gcc
+也�以自动使其内�。而且其他用户�能会�求移除 inline，由此而�的争论会抵消 inline
 自身的潜在价值，得��失。
 
 
@@ -613,37 +674,37 @@ vmalloc()。请�考API文档以获�有关它们的详细信�。
 的一个值�以表示为一个错误代�整数（-Exxx�失败，0��功）或者一个“�功�布尔值（
 0�失败，�0��功）。
 
-混�使用这两�表达方�是难于�现的bug的��。如果C语言本身严格区分整形和布尔型�
-�，那么编译器就能够帮我们�现这些错误……�过C语言�区分。为了��产生这�bug，请
+混�使用这两�表达方�是难于�现的 bug 的��。如果 C 语言本身严格区分整形和布尔型�
+�，那么编译器就能够帮我们�现这些错误……�过 C 语言�区分。为了��产生这� bug，请
 �循下�的惯例：
 
 	如果函数的�字是一个动作或者强制性的命令，那么这个函数应该返回错误代�整
 	数。如果是一个判断，那么函数应该返回一个“�功�布尔值。
 
-比如，“add work�是一个命令，所以add_work()函数在�功时返回0，在失败时返回-EBUSY。
-类似的，因为“PCI device present�是一个判断，所以pci_dev_present()函数在�功找到
-一个匹�的设备时应该返回1，如果找�到时应该返回0。
+比如，“add work� 是一个命令，所以 add_work() 函数在�功时返回 0，在失败时返回 -EBUSY。
+类似的，因为 “PCI device present� 是一个判断，所以 pci_dev_present() 函数在�功找到
+一个匹�的设备时应该返回 1，如果找�到时应该返回 0。
 
 所有导出（译注：EXPORT）的函数都必须�守这个惯例，所有的公共函数也都应该如此。�
 有（static）函数�需�如此，但是我们也推�这样�。
 
 返回值是实际计算结果而�是计算是��功的标志的函数��此惯例的�制。一般的，他们
 通过返回一些正常值范围之外的结果�表示出错。典型的例�是返回指针的函数，他们使用
-NULL或者ERR_PTR机制�报告错误。
+NULL 或者 ERR_PTR 机制�报告错误。
 
 
 		第�七章：���新�明内核�
 
-头文件include/linux/kernel.h包�了一些�，你应该使用它们，而��自己写一些它们的
+头文件 include/linux/kernel.h 包�了一些�，你应该使用它们，而��自己写一些它们的
 ��。比如，如果你需�计算一个数组的长度，使用这个�
 
-  #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+	#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 
 类似的，如果你�计算�结构体�员的大�，使用
 
-  #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
+	#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
 
-还有�以�严格的类型检查的min()和max()�，如果你需��以使用它们。你�以自己看看
+还有�以�严格的类型检查的 min() 和 max() �，如果你需��以使用它们。你�以自己看看
 那个头文件里还定义了什么你�以拿�用的东西，如果有定义的�，你就�应在你的代�里
 自己�新定义。
 
@@ -653,42 +714,100 @@ NULL或者ERR_PTR机制�报告错误。
 有一些编辑器�以解释嵌入在�文件里的由一些特殊标记标明的�置信�。比如，emacs
 能够解释被标记�这样的行：
 
--*- mode: c -*-
+	-*- mode: c -*-
 
 或者这样的：
 
-/*
-Local Variables:
-compile-command: "gcc -DMAGIC_DEBUG_FLAG foo.c"
-End:
-*/
+	/*
+	Local Variables:
+	compile-command: "gcc -DMAGIC_DEBUG_FLAG foo.c"
+	End:
+	*/
 
-Vim能够解释这样的标记：
+Vim 能够解释这样的标记：
 
-/* vim:set sw=8 noet */
+	/* vim:set sw=8 noet */
 
 ��在�代�中包�任何这样的内容。�个人都有他自己的编辑器�置，你的�文件�应
 该覆盖别人的�置。这包括有关缩进和模��置的标记。人们�以使用他们自己定制的模
 �，或者使用其他�以产生正确的缩进的巧妙方法。
 
 
+		第��章：内�汇编
+
+在特定架构的代�中，你也许需�内�汇编�使用 CPU 接�和平�相关功能。在需�
+这么�时，��犹豫。然而，当 C �以完�工作时，��无端地使用内�汇编。如果
+�能，你�以并且应该用 C 和硬件交互。
+
+考虑去写通用一点的内�汇编作为简明的辅助函数，而�是��写下它们的细节。记�
+内�汇编�以使用 C �数。
+
+大而特殊的汇编函数应该放在 .S 文件中，对应 C 的原型定义在 C 头文件中。汇编
+函数的 C 原型应该使用 “asmlinkage�。
+
+你�能需�将你的汇编语�标记为 volatile，�阻止 GCC 在没�现任何副作用�就
+移除了它。你�必总是这样�，虽然，这样�以�制�必�的优化。
+
+在写一个包�多�指令的�个内�汇编语�时，把��指令用引�字符串分离，并写在
+�独一行，在�个字符串结尾，除了 \n\t 结尾之外，在汇编输出中适当地缩进下
+一�指令：
+
+	asm ("magic %reg1, #42\n\t"
+	     "more_magic %reg2, %reg3"
+	     : /* outputs */ : /* inputs */ : /* clobbers */);
+
+
+		第二�章：�件编译
+
+���能，就��在 .c 文件里�使用预处��件；这样�让代�更难阅读并且逻辑难以
+跟踪。替代方案是，在头文件定义函数在这些 .c 文件中使用这类的�件表达�，�供空
+�作的桩版本（译注：桩程�，是指用�替�一部分功能的程�段）在 #else 情况下，
+�从 .c 文件中无�件地调用这些函数。编译器会��生�任何桩调用的代�，产生一致
+的结果，但逻辑将更加清晰。
+
+��编译整个函数，而�是部分函数或部分表达�。而�是在一个表达�添加 ifdef，
+解�部分或全部表达�到一个�独的辅助函数，并应用�件到该函数内。
+
+如果你有一个在特定�置中�能是未使用的函数或��，编译器将警告它定义了但未使用，
+标记这个定义为 __maybe_unused 而�是将它包�在一个预处��件中。（然而，如果
+一个函数或��总是未使用的，就直接删除它。）
+
+在代�中，�能的情况下，使用 IS_ENABLED ��转化�个 Kconfig 标记为 C 的布尔
+表达�，并在正常的 C �件中使用它：
+
+	if (IS_ENABLED(CONFIG_SOMETHING)) {
+		...
+	}
+
+编译器会无�件地�常数�并，就�使用 #ifdef 那样，包�或排除代��，所以这�会
+带�任何�行时开销。然而，这�方法�旧�许 C 编译器查看�内的代�，并检查它的正确
+性（语法，类型，符�引用，等等）。因此，如果�件�满足，代��内的引用符�将�存在，
+你必须继续使用 #ifdef。
+
+在任何有�义的 #if 或 #ifdef �的末尾（超过几行），在 #endif �一行的��写下
+注释，指出该�件表达�被使用。例如：
+
+	#ifdef CONFIG_SOMETHING
+	...
+	#endif /* CONFIG_SOMETHING */
+
 
 		附录 I：�考
 
-The C Programming Language, 第二版, 作者Brian W. Kernighan和Denni
-M. Ritchie. Prentice Hall, Inc., 1988. ISBN 0-13-110362-8 (软皮),
-0-13-110370-9 (硬皮). URL: http://cm.bell-labs.com/cm/cs/cbook/
+The C Programming Language, 第二版
+作者：Brian W. Kernighan 和 Denni M. Ritchie.
+Prentice Hall, Inc., 1988.
+ISBN 0-13-110362-8 (软皮), 0-13-110370-9 (硬皮).
 
-The Practice of Programming 作者Brian W. Kernighan和Rob Pike.  Addison-Wesley,
-Inc., 1999.  ISBN 0-201-61586-X.  URL: http://cm.bell-labs.com/cm/cs/tpop/
+The Practice of Programming
+作者：Brian W. Kernighan 和 Rob Pike.
+Addison-Wesley, Inc., 1999.
+ISBN 0-201-61586-X.
 
-cpp，gcc，gcc internals和indent的GNU手册——和K&R�本文相符�的部分，全部�以在
-http://www.gnu.org/manual/找到
+GNU 手册 - �循 K&R 标准和此文本 - cpp, gcc, gcc internals and indent,
+都�以从 http://www.gnu.org/manual/ 找到
 
 WG14是C语言的国际标准化工作组，URL: http://www.open-std.org/JTC1/SC22/WG14/
 
-Kernel CodingStyle，作者greg@kroah.com�表于OLS 2002：
+Kernel CodingStyle，作者 greg@kroah.com �表于OLS 2002：
 http://www.kroah.com/linux/talks/ols_2002_kernel_codingstyle_talk/html/
-
---
-最�更新于2007年7月13日。
diff --git a/MAINTAINERS b/MAINTAINERS
index 92a3f42449df..771c31c73172 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -288,6 +288,7 @@ F:	include/linux/acpi.h
 F:	include/acpi/
 F:	Documentation/acpi/
 F:	Documentation/ABI/testing/sysfs-bus-acpi
+F:	Documentation/ABI/testing/configfs-acpi
 F:	drivers/pci/*acpi*
 F:	drivers/pci/*/*acpi*
 F:	drivers/pci/*/*/*acpi*
@@ -1647,6 +1648,13 @@ L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/platform/s5p-tv/
 
+ARM/SAMSUNG S5P SERIES HDMI CEC SUBSYSTEM SUPPORT
+M:	Kyungmin Park <kyungmin.park@samsung.com>
+L:	linux-arm-kernel@lists.infradead.org
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/staging/media/platform/s5p-cec/
+
 ARM/SAMSUNG S5P SERIES JPEG CODEC SUPPORT
 M:	Andrzej Pietrasiewicz <andrzej.p@samsung.com>
 M:	Jacek Anaszewski <j.anaszewski@samsung.com>
@@ -2850,6 +2858,22 @@ F:	drivers/net/ieee802154/cc2520.c
 F:	include/linux/spi/cc2520.h
 F:	Documentation/devicetree/bindings/net/ieee802154/cc2520.txt
 
+CEC DRIVER
+M:	Hans Verkuil <hans.verkuil@cisco.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+W:	http://linuxtv.org
+S:	Supported
+F:	Documentation/cec.txt
+F:	Documentation/DocBook/media/v4l/cec*
+F:	drivers/staging/media/cec/
+F:	drivers/media/cec-edid.c
+F:	drivers/media/rc/keymaps/rc-cec.c
+F:	include/media/cec.h
+F:	include/media/cec-edid.h
+F:	include/linux/cec.h
+F:	include/linux/cec-funcs.h
+
 CELL BROADBAND ENGINE ARCHITECTURE
 M:	Arnd Bergmann <arnd@arndb.de>
 L:	linuxppc-dev@lists.ozlabs.org
@@ -3286,6 +3310,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6.git
 S:	Maintained
 F:	Documentation/crypto/
+F:	Documentation/devicetree/bindings/crypto/
 F:	Documentation/DocBook/crypto-API.tmpl
 F:	arch/*/crypto/
 F:	crypto/
@@ -4940,6 +4965,13 @@ F:	Documentation/filesystems/caching/
 F:	fs/fscache/
 F:	include/linux/fscache*.h
 
+FS-CRYPTO: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
+M:	Theodore Y. Ts'o <tytso@mit.edu>
+M:	Jaegeuk Kim <jaegeuk@kernel.org>
+S:	Supported
+F:	fs/crypto/
+F:	include/linux/fscrypto.h
+
 F2FS FILE SYSTEM
 M:	Jaegeuk Kim <jaegeuk@kernel.org>
 M:	Changman Lee <cm224.lee@samsung.com>
@@ -5168,10 +5200,10 @@ S:	Maintained
 F:	drivers/media/usb/gspca/m5602/
 
 GSPCA PAC207 SONIXB SUBDRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/media/usb/gspca/pac207.c
 
 GSPCA SN9C20X SUBDRIVER
@@ -5189,10 +5221,10 @@ S:	Maintained
 F:	drivers/media/usb/gspca/t613.c
 
 GSPCA USB WEBCAM DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/media/usb/gspca/
 
 GUID PARTITION TABLE (GPT)
@@ -5273,6 +5305,7 @@ M:	Matt Mackall <mpm@selenic.com>
 M:	Herbert Xu <herbert@gondor.apana.org.au>
 L:	linux-crypto@vger.kernel.org
 S:	Odd fixes
+F:	Documentation/devicetree/bindings/rng/
 F:	Documentation/hw_random.txt
 F:	drivers/char/hw_random/
 F:	include/linux/hw_random.h
@@ -5919,6 +5952,12 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/intel-hid.c
 
+INTEL VIRTUAL BUTTON DRIVER
+M:	AceLan Kao <acelan.kao@canonical.com>
+L:	platform-driver-x86@vger.kernel.org
+S:	Maintained
+F:	drivers/platform/x86/intel-vbtn.c
+
 INTEL IDLE DRIVER
 M:	Len Brown <lenb@kernel.org>
 L:	linux-pm@vger.kernel.org
@@ -6021,6 +6060,12 @@ L:     linux-rdma@vger.kernel.org
 S:     Supported
 F:     drivers/infiniband/hw/i40iw/
 
+INTEL MERRIFIELD GPIO DRIVER
+M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+L:	linux-gpio@vger.kernel.org
+S:	Maintained
+F:	drivers/gpio/gpio-merrifield.c
+
 INTEL-MID GPIO DRIVER
 M:	David Cohen <david.a.cohen@linux.intel.com>
 L:	linux-gpio@vger.kernel.org
@@ -6766,6 +6811,7 @@ S:	Maintained
 F:	drivers/ata/
 F:	include/linux/ata.h
 F:	include/linux/libata.h
+F:	Documentation/devicetree/bindings/ata/
 
 LIBATA PATA ARASAN COMPACT FLASH CONTROLLER
 M:	Viresh Kumar <vireshk@kernel.org>
@@ -7327,6 +7373,16 @@ L:	linux-iio@vger.kernel.org
 S:	Maintained
 F:	drivers/iio/potentiometer/mcp4531.c
 
+MEDIA DRIVERS FOR RENESAS - FCP
+M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+L:	linux-media@vger.kernel.org
+L:	linux-renesas-soc@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	Documentation/devicetree/bindings/media/renesas,fcp.txt
+F:	drivers/media/platform/rcar-fcp.c
+F:	include/media/rcar-fcp.h
+
 MEDIA DRIVERS FOR RENESAS - VSP1
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
@@ -7336,8 +7392,18 @@ S:	Supported
 F:	Documentation/devicetree/bindings/media/renesas,vsp1.txt
 F:	drivers/media/platform/vsp1/
 
+MEDIA DRIVERS FOR HELENE
+M:	Abylay Ospan <aospan@netup.ru>
+L:	linux-media@vger.kernel.org
+W:	https://linuxtv.org
+W:	http://netup.tv/
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	drivers/media/dvb-frontends/helene*
+
 MEDIA DRIVERS FOR ASCOT2E
 M:	Sergey Kozlov <serjk@netup.ru>
+M:	Abylay Ospan <aospan@netup.ru>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
 W:	http://netup.tv/
@@ -7347,6 +7413,7 @@ F:	drivers/media/dvb-frontends/ascot2e*
 
 MEDIA DRIVERS FOR CXD2841ER
 M:	Sergey Kozlov <serjk@netup.ru>
+M:	Abylay Ospan <aospan@netup.ru>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
 W:	http://netup.tv/
@@ -7356,6 +7423,7 @@ F:	drivers/media/dvb-frontends/cxd2841er*
 
 MEDIA DRIVERS FOR HORUS3A
 M:	Sergey Kozlov <serjk@netup.ru>
+M:	Abylay Ospan <aospan@netup.ru>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
 W:	http://netup.tv/
@@ -7365,6 +7433,7 @@ F:	drivers/media/dvb-frontends/horus3a*
 
 MEDIA DRIVERS FOR LNBH25
 M:	Sergey Kozlov <serjk@netup.ru>
+M:	Abylay Ospan <aospan@netup.ru>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
 W:	http://netup.tv/
@@ -7374,6 +7443,7 @@ F:	drivers/media/dvb-frontends/lnbh25*
 
 MEDIA DRIVERS FOR NETUP PCI UNIVERSAL DVB devices
 M:	Sergey Kozlov <serjk@netup.ru>
+M:	Abylay Ospan <aospan@netup.ru>
 L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
 W:	http://netup.tv/
@@ -7623,10 +7693,8 @@ L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
-F:	drivers/staging/media/mn88472/
-F:	drivers/media/dvb-frontends/mn88472.h
+F:	drivers/media/dvb-frontends/mn88472*
 
 MN88473 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
@@ -8181,6 +8249,13 @@ S:	Supported
 F:	drivers/nvme/host/
 F:	include/linux/nvme.h
 
+NVM EXPRESS TARGET DRIVER
+M:	Christoph Hellwig <hch@lst.de>
+M:	Sagi Grimberg <sagi@grimberg.me>
+L:	linux-nvme@lists.infradead.org
+S:	Supported
+F:	drivers/nvme/target/
+
 NVMEM FRAMEWORK
 M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
 M:	Maxime Ripard <maxime.ripard@free-electrons.com>
@@ -9094,6 +9169,8 @@ M:	David Woodhouse <dwmw2@infradead.org>
 L:	linux-pm@vger.kernel.org
 T:	git git://git.infradead.org/battery-2.6.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/power/
+F:	Documentation/devicetree/bindings/power_supply/
 F:	include/linux/power_supply.h
 F:	drivers/power/
 X:	drivers/power/avs/
@@ -9231,6 +9308,13 @@ F:	include/linux/tracehook.h
 F:	include/uapi/linux/ptrace.h
 F:	kernel/ptrace.c
 
+PULSE8-CEC DRIVER
+M:	Hans Verkuil <hverkuil@xs4all.nl>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/staging/media/pulse8-cec
+
 PVRUSB2 VIDEO4LINUX DRIVER
 M:	Mike Isely <isely@pobox.com>
 L:	pvrusb2@isely.net	(subscribers-only)
@@ -9242,10 +9326,10 @@ F:	Documentation/video4linux/README.pvrusb2
 F:	drivers/media/usb/pvrusb2/
 
 PWC WEBCAM DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/media/usb/pwc/*
 
 PWM FAN DRIVER
@@ -9318,7 +9402,8 @@ L:	rtc-linux@googlegroups.com
 S:	Maintained
 
 QAT DRIVER
-M:	Tadeusz Struk <tadeusz.struk@intel.com>
+M:	Giovanni Cabiddu <giovanni.cabiddu@intel.com>
+M:	Salvatore Benedetto <salvatore.benedetto@intel.com>
 L:	qat-linux@intel.com
 S:	Supported
 F:	drivers/crypto/qat/
@@ -9460,14 +9545,14 @@ F:	drivers/video/fbdev/aty/radeon*
 F:	include/uapi/linux/radeonfb.h
 
 RADIOSHARK RADIO DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/radio/radio-shark.c
 
 RADIOSHARK2 RADIO DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
@@ -9608,6 +9693,7 @@ M:	Mark Brown <broonie@kernel.org>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap.git
 S:	Supported
+F:	Documentation/devicetree/bindings/regmap/
 F:	drivers/base/regmap/
 F:	include/linux/regmap.h
 
diff --git a/Makefile b/Makefile
index ce8ef5d0bd29..776b6a3c40f1 100644
--- a/Makefile
+++ b/Makefile
@@ -1381,6 +1381,8 @@ help:
 	@$(MAKE) $(build)=$(package-dir) help
 	@echo  ''
 	@echo  'Documentation targets:'
+	@$(MAKE) -f $(srctree)/Documentation/Makefile.sphinx dochelp
+	@echo  ''
 	@$(MAKE) -f $(srctree)/Documentation/DocBook/Makefile dochelp
 	@echo  ''
 	@echo  'Architecture specific targets ($(SRCARCH)):'
@@ -1429,8 +1431,11 @@ $(help-board-dirs): help-%:
 
 # Documentation targets
 # ---------------------------------------------------------------------------
-%docs: scripts_basic FORCE
+DOC_TARGETS := xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs epubdocs cleandocs cleanmediadocs
+PHONY += $(DOC_TARGETS)
+$(DOC_TARGETS): scripts_basic FORCE
 	$(Q)$(MAKE) $(build)=scripts build_docproc build_check-lc_ctype
+	$(Q)$(MAKE) $(build)=Documentation -f $(srctree)/Documentation/Makefile.sphinx $@
 	$(Q)$(MAKE) $(build)=Documentation/DocBook $@
 
 else # KBUILD_EXTMOD
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index def9e783b5c6..6a40ed7d0502 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -206,6 +206,11 @@
 			brcm,nand-has-wp;
 		};
 
+		rng: rng@33000 {
+			compatible = "brcm,bcm-nsp-rng";
+			reg = <0x33000 0x14>;
+		};
+
 		ccbtimer0: timer@34000 {
 			compatible = "arm,sp804";
 			reg = <0x34000 0x1000>;
@@ -266,6 +271,48 @@
 			      <0x30028 0x04>,
 			      <0x3f408 0x04>;
 		};
+
+		sata_phy: sata_phy@40100 {
+			compatible = "brcm,iproc-nsp-sata-phy";
+			reg = <0x40100 0x340>;
+			reg-names = "phy";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			sata_phy0: sata-phy@0 {
+				reg = <0>;
+				#phy-cells = <0>;
+				status = "disabled";
+			};
+
+			sata_phy1: sata-phy@1 {
+				reg = <1>;
+				#phy-cells = <0>;
+				status = "disabled";
+			};
+		};
+
+		sata: ahci@41000 {
+			compatible = "brcm,bcm-nsp-ahci";
+			reg-names = "ahci", "top-ctrl";
+			reg = <0x41000 0x1000>, <0x40020 0x1c>;
+			interrupts = <GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+
+			sata0: sata-port@0 {
+				reg = <0>;
+				phys = <&sata_phy0>;
+				phy-names = "sata-phy";
+			};
+
+			sata1: sata-port@1 {
+				reg = <1>;
+				phys = <&sata_phy1>;
+				phy-names = "sata-phy";
+			};
+		};
 	};
 
 	pcie0: pcie@18012000 {
diff --git a/arch/arm/boot/dts/bcm958625k.dts b/arch/arm/boot/dts/bcm958625k.dts
index e298450b49b2..2d8422632b2b 100644
--- a/arch/arm/boot/dts/bcm958625k.dts
+++ b/arch/arm/boot/dts/bcm958625k.dts
@@ -68,6 +68,18 @@
 	status = "okay";
 };
 
+&sata_phy0 {
+	status = "okay";
+};
+
+&sata_phy1 {
+	status = "okay";
+};
+
+&sata {
+	status = "okay";
+};
+
 &nand {
 	nandcs@0 {
 		compatible = "brcm,nandcs";
diff --git a/arch/arm/boot/dts/meson8-minix-neo-x8.dts b/arch/arm/boot/dts/meson8-minix-neo-x8.dts
index 4f536bb1f002..8bceb8d343f6 100644
--- a/arch/arm/boot/dts/meson8-minix-neo-x8.dts
+++ b/arch/arm/boot/dts/meson8-minix-neo-x8.dts
@@ -80,6 +80,7 @@
 	pmic@32 {
 		compatible = "ricoh,rn5t618";
 		reg = <0x32>;
+		system-power-controller;
 
 		regulators {
 		};
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 03a39fe29246..1568cb5cd870 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -154,30 +154,23 @@ static int ghash_async_init(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
-	if (!may_use_simd()) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_init(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		desc->flags = req->base.flags;
-		return crypto_shash_init(desc);
-	}
+	desc->tfm = child;
+	desc->flags = req->base.flags;
+	return crypto_shash_init(desc);
 }
 
 static int ghash_async_update(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_update(cryptd_req);
@@ -190,12 +183,12 @@ static int ghash_async_update(struct ahash_request *req)
 static int ghash_async_final(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_final(cryptd_req);
@@ -212,7 +205,8 @@ static int ghash_async_digest(struct ahash_request *req)
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_digest(cryptd_req);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5a0a691d4220..20d5a60530b1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -4,6 +4,7 @@ config ARM64
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
index f895fc02ab06..40846319be69 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
@@ -49,6 +49,10 @@
 
 / {
 	model = "LS1043A RDB Board";
+
+	aliases {
+		crypto = &crypto;
+	};
 };
 
 &i2c0 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index de0323b48b1e..6bd46c133010 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -159,6 +159,49 @@
 			big-endian;
 		};
 
+		crypto: crypto@1700000 {
+			compatible = "fsl,sec-v5.4", "fsl,sec-v5.0",
+				     "fsl,sec-v4.0";
+			fsl,sec-era = <3>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0x00 0x1700000 0x100000>;
+			reg = <0x00 0x1700000 0x0 0x100000>;
+			interrupts = <0 75 0x4>;
+
+			sec_jr0: jr@10000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x10000 0x10000>;
+				interrupts = <0 71 0x4>;
+			};
+
+			sec_jr1: jr@20000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x20000 0x10000>;
+				interrupts = <0 72 0x4>;
+			};
+
+			sec_jr2: jr@30000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x30000 0x10000>;
+				interrupts = <0 73 0x4>;
+			};
+
+			sec_jr3: jr@40000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x40000 0x10000>;
+				interrupts = <0 74 0x4>;
+			};
+		};
+
 		dcfg: dcfg@1ee0000 {
 			compatible = "fsl,ls1043a-dcfg", "syscon";
 			reg = <0x0 0x1ee0000 0x0 0x10000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 05f89c4a5413..77b8c4e388ca 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -168,6 +168,18 @@
 		};
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		vpu_dma_reserved: vpu_dma_mem_region {
+			compatible = "shared-dma-pool";
+			reg = <0 0xb7000000 0 0x500000>;
+			alignment = <0x1000>;
+			no-map;
+		};
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupt-parent = <&gic>;
@@ -312,6 +324,17 @@
 			clock-names = "spi", "wrap";
 		};
 
+		vpu: vpu@10020000 {
+			compatible = "mediatek,mt8173-vpu";
+			reg = <0 0x10020000 0 0x30000>,
+			      <0 0x10050000 0 0x100>;
+			reg-names = "tcm", "cfg_reg";
+			interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&topckgen CLK_TOP_SCP_SEL>;
+			clock-names = "main";
+			memory-region = <&vpu_dma_reserved>;
+		};
+
 		sysirq: intpol-controller@10200620 {
 			compatible = "mediatek,mt8173-sysirq",
 				     "mediatek,mt6577-sysirq";
@@ -754,6 +777,45 @@
 			clock-names = "apb", "smi";
 		};
 
+		vcodec_enc: vcodec@18002000 {
+			compatible = "mediatek,mt8173-vcodec-enc";
+			reg = <0 0x18002000 0 0x1000>,	/* VENC_SYS */
+			      <0 0x19002000 0 0x1000>;	/* VENC_LT_SYS */
+			interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_LOW>,
+				     <GIC_SPI 202 IRQ_TYPE_LEVEL_LOW>;
+			mediatek,larb = <&larb3>,
+					<&larb5>;
+			iommus = <&iommu M4U_PORT_VENC_RCPU>,
+				 <&iommu M4U_PORT_VENC_REC>,
+				 <&iommu M4U_PORT_VENC_BSDMA>,
+				 <&iommu M4U_PORT_VENC_SV_COMV>,
+				 <&iommu M4U_PORT_VENC_RD_COMV>,
+				 <&iommu M4U_PORT_VENC_CUR_LUMA>,
+				 <&iommu M4U_PORT_VENC_CUR_CHROMA>,
+				 <&iommu M4U_PORT_VENC_REF_LUMA>,
+				 <&iommu M4U_PORT_VENC_REF_CHROMA>,
+				 <&iommu M4U_PORT_VENC_NBM_RDMA>,
+				 <&iommu M4U_PORT_VENC_NBM_WDMA>,
+				 <&iommu M4U_PORT_VENC_RCPU_SET2>,
+				 <&iommu M4U_PORT_VENC_REC_FRM_SET2>,
+				 <&iommu M4U_PORT_VENC_BSDMA_SET2>,
+				 <&iommu M4U_PORT_VENC_SV_COMA_SET2>,
+				 <&iommu M4U_PORT_VENC_RD_COMA_SET2>,
+				 <&iommu M4U_PORT_VENC_CUR_LUMA_SET2>,
+				 <&iommu M4U_PORT_VENC_CUR_CHROMA_SET2>,
+				 <&iommu M4U_PORT_VENC_REF_LUMA_SET2>,
+				 <&iommu M4U_PORT_VENC_REC_CHROMA_SET2>;
+			mediatek,vpu = <&vpu>;
+			clocks = <&topckgen CLK_TOP_VENCPLL_D2>,
+				 <&topckgen CLK_TOP_VENC_SEL>,
+				 <&topckgen CLK_TOP_UNIVPLL1_D2>,
+				 <&topckgen CLK_TOP_VENC_LT_SEL>;
+			clock-names = "venc_sel_src",
+				      "venc_sel",
+				      "venc_lt_sel_src",
+				      "venc_lt_sel";
+		};
+
 		vencltsys: clock-controller@19000000 {
 			compatible = "mediatek,mt8173-vencltsys", "syscon";
 			reg = <0 0x19000000 0 0x1000>;
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index aee323b13802..5420cb0fcb3e 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -113,4 +113,14 @@ static inline const char *acpi_get_enable_method(int cpu)
 pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
 #endif
 
+#ifdef CONFIG_ACPI_NUMA
+int arm64_acpi_numa_init(void);
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid);
+#else
+static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
+static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; }
+#endif /* CONFIG_ACPI_NUMA */
+
+#define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE
+
 #endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 44be1e03ed65..9b6e408cfa51 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -174,13 +174,15 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 #define iounmap				__iounmap
 
 /*
- * io{read,write}{16,32}be() macros
+ * io{read,write}{16,32,64}be() macros
  */
 #define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
 #define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+#define ioread64be(p)		({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(); __v; })
 
 #define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
 #define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
+#define iowrite64be(v,p)	({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
index e9b4f2942335..600887e491fd 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -5,6 +5,8 @@
 
 #ifdef CONFIG_NUMA
 
+#define NR_NODE_MEMBLKS		(MAX_NUMNODES * 2)
+
 /* currently, arm64 implements flat NUMA topology */
 #define parent_node(node)	(node)
 
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2173149d8954..a5125c6d1f87 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -42,6 +42,7 @@ arm64-obj-$(CONFIG_EFI)			+= efi.o efi-entry.stub.o
 arm64-obj-$(CONFIG_PCI)			+= pci.o
 arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
 arm64-obj-$(CONFIG_ACPI)		+= acpi.o
+arm64-obj-$(CONFIG_ACPI_NUMA)		+= acpi_numa.o
 arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
 arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
new file mode 100644
index 000000000000..f85149cc7c71
--- /dev/null
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -0,0 +1,112 @@
+/*
+ * ACPI 5.1 based NUMA setup for ARM64
+ * Lots of code was borrowed from arch/x86/mm/srat.c
+ *
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2013-2016, Linaro Ltd.
+ *		Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#define pr_fmt(fmt) "ACPI: NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/bootmem.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include <acpi/processor.h>
+#include <asm/numa.h>
+
+static int cpus_in_srat;
+
+struct __node_cpu_hwid {
+	u32 node_id;    /* logical node containing this CPU */
+	u64 cpu_hwid;   /* MPIDR for this CPU */
+};
+
+static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
+[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid)
+{
+	int i;
+
+	for (i = 0; i < cpus_in_srat; i++) {
+		if (hwid == early_node_cpu_hwid[i].cpu_hwid)
+			return early_node_cpu_hwid[i].node_id;
+	}
+
+	return NUMA_NO_NODE;
+}
+
+/* Callback for Proximity Domain -> ACPI processor UID mapping */
+void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
+{
+	int pxm, node;
+	phys_cpuid_t mpidr;
+
+	if (srat_disabled())
+		return;
+
+	if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) {
+		pr_err("SRAT: Invalid SRAT header length: %d\n",
+			pa->header.length);
+		bad_srat();
+		return;
+	}
+
+	if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+		return;
+
+	if (cpus_in_srat >= NR_CPUS) {
+		pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
+			     NR_CPUS);
+		return;
+	}
+
+	pxm = pa->proximity_domain;
+	node = acpi_map_pxm_to_node(pxm);
+
+	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+		pr_err("SRAT: Too many proximity domains %d\n", pxm);
+		bad_srat();
+		return;
+	}
+
+	mpidr = acpi_map_madt_entry(pa->acpi_processor_uid);
+	if (mpidr == PHYS_CPUID_INVALID) {
+		pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
+			pxm, pa->acpi_processor_uid);
+		bad_srat();
+		return;
+	}
+
+	early_node_cpu_hwid[cpus_in_srat].node_id = node;
+	early_node_cpu_hwid[cpus_in_srat].cpu_hwid =  mpidr;
+	node_set(node, numa_nodes_parsed);
+	cpus_in_srat++;
+	pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n",
+		pxm, mpidr, node);
+}
+
+int __init arm64_acpi_numa_init(void)
+{
+	int ret;
+
+	ret = acpi_numa_init();
+	if (ret)
+		return ret;
+
+	return srat_disabled() ? -EINVAL : 0;
+}
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index e11857fce05f..75a0f8acef66 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -9,13 +9,16 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/acpi.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
 #include <asm/cpuidle.h>
 #include <asm/cpu_ops.h>
 
-int __init arm_cpuidle_init(unsigned int cpu)
+int arm_cpuidle_init(unsigned int cpu)
 {
 	int ret = -EOPNOTSUPP;
 
@@ -39,3 +42,18 @@ int arm_cpuidle_suspend(int index)
 
 	return cpu_ops[cpu]->cpu_suspend(index);
 }
+
+#ifdef CONFIG_ACPI
+
+#include <acpi/processor.h>
+
+int acpi_processor_ffh_lpi_probe(unsigned int cpu)
+{
+	return arm_cpuidle_init(cpu);
+}
+
+int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+{
+	return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+}
+#endif
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 3279defabaa2..92f0e1e767cf 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -260,11 +260,13 @@ void __init setup_arch(char **cmdline_p)
 	efi_init();
 	arm64_memblock_init();
 
+	paging_init();
+
+	acpi_table_upgrade();
+
 	/* Parse the ACPI tables for possible boot-time configuration */
 	acpi_boot_table_init();
 
-	paging_init();
-
 	if (acpi_disabled)
 		unflatten_device_tree();
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 62ff3c0622e2..a68e0ccd9f4b 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -560,6 +560,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 	 */
 	acpi_set_mailbox_entry(cpu_count, processor);
 
+	early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
+
 	cpu_count++;
 }
 
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 0f7c40eb3f53..934137647837 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -27,8 +27,8 @@ static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host must save tpidr*_el[01], actlr_el1, sp0, pc, pstate, and
- * guest must save everything.
+ * VHE: Host must save tpidr*_el[01], actlr_el1, mdscr_el1, sp0, pc,
+ * pstate, and guest must save everything.
  */
 
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
@@ -37,6 +37,7 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
+	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
@@ -61,7 +62,6 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(amair);
 	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(cntkctl);
 	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
-	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
 	ctxt->gp_regs.elr_el1		= read_sysreg_el1(elr);
@@ -90,6 +90,7 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],	  tpidr_el1);
+	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
 	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
 	write_sysreg_el2(ctxt->gp_regs.regs.pc,	  elr);
 	write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
@@ -114,7 +115,6 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	amair);
 	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], 	cntkctl);
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],		mdscr_el1);
 
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		elr);
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 98dc1047f2a2..c7fe3ec70774 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/module.h>
@@ -29,7 +30,7 @@ static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
 
 static int numa_distance_cnt;
 static u8 *numa_distance;
-static int numa_off;
+static bool numa_off;
 
 static __init int numa_parse_early_param(char *opt)
 {
@@ -37,7 +38,7 @@ static __init int numa_parse_early_param(char *opt)
 		return -EINVAL;
 	if (!strncmp(opt, "off", 3)) {
 		pr_info("%s\n", "NUMA turned off");
-		numa_off = 1;
+		numa_off = true;
 	}
 	return 0;
 }
@@ -131,25 +132,25 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
  * numa_add_memblk - Set node id to memblk
  * @nid: NUMA node ID of the new memblk
  * @start: Start address of the new memblk
- * @size:  Size of the new memblk
+ * @end:  End address of the new memblk
  *
  * RETURNS:
  * 0 on success, -errno on failure.
  */
-int __init numa_add_memblk(int nid, u64 start, u64 size)
+int __init numa_add_memblk(int nid, u64 start, u64 end)
 {
 	int ret;
 
-	ret = memblock_set_node(start, size, &memblock.memory, nid);
+	ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
 	if (ret < 0) {
 		pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
-			start, (start + size - 1), nid);
+			start, (end - 1), nid);
 		return ret;
 	}
 
 	node_set(nid, numa_nodes_parsed);
 	pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
-			start, (start + size - 1), nid);
+			start, (end - 1), nid);
 	return ret;
 }
 
@@ -362,12 +363,15 @@ static int __init dummy_numa_init(void)
 	int ret;
 	struct memblock_region *mblk;
 
-	pr_info("%s\n", "No NUMA configuration found");
+	if (numa_off)
+		pr_info("NUMA disabled\n"); /* Forced off on command line. */
+	else
+		pr_info("No NUMA configuration found\n");
 	pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
 	       0LLU, PFN_PHYS(max_pfn) - 1);
 
 	for_each_memblock(memory, mblk) {
-		ret = numa_add_memblk(0, mblk->base, mblk->size);
+		ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
 		if (!ret)
 			continue;
 
@@ -375,7 +379,7 @@ static int __init dummy_numa_init(void)
 		return ret;
 	}
 
-	numa_off = 1;
+	numa_off = true;
 	return 0;
 }
 
@@ -388,7 +392,9 @@ static int __init dummy_numa_init(void)
 void __init arm64_numa_init(void)
 {
 	if (!numa_off) {
-		if (!numa_init(of_numa_init))
+		if (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
+			return;
+		if (acpi_disabled && !numa_init(of_numa_init))
 			return;
 	}
 
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index aad5d7416886..9231e5a72b93 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -1002,14 +1002,12 @@ static struct adv7842_output_format adv7842_opf[] = {
 	{
 		.op_ch_sel = ADV7842_OP_CH_SEL_BRG,
 		.op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_8,
-		.op_656_range = 1,
 		.blank_data = 1,
 		.insert_av_codes = 1,
 	},
 	{
 		.op_ch_sel = ADV7842_OP_CH_SEL_RGB,
 		.op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_16,
-		.op_656_range = 1,
 		.blank_data = 1,
 	},
 };
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 57298e7b4867..1941e4baaee6 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -8,8 +8,7 @@ config HEXAGON
 	# select HAVE_REGS_AND_STACK_ACCESS_API
 	# select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	# select ARCH_HAS_CPU_IDLE_WAIT
-	# select ARCH_WANT_OPTIONAL_GPIOLIB
-	# select ARCH_REQUIRE_GPIOLIB
+	# select GPIOLIB
 	# select HAVE_CLK
 	# select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_ATOMIC64
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index e109ee95e919..6a15083cc366 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -39,7 +39,6 @@ config IA64
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_LEGACY
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_IOMAP
 	select GENERIC_SMP_IDLE_THREAD
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index aa0fdf125aba..a3d0211970e9 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -140,6 +140,9 @@ static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus)
 		}
 	}
 }
+
+extern void acpi_numa_fixup(void);
+
 #endif /* CONFIG_ACPI_NUMA */
 
 #endif /*__KERNEL__*/
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index b1698bc042c8..92b7bc956795 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -524,7 +524,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	return 0;
 }
 
-void __init acpi_numa_arch_fixup(void)
+void __init acpi_numa_fixup(void)
 {
 	int i, j, node_from, node_to;
 
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 2029a38a72ae..afddb3e80a29 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -552,6 +552,7 @@ setup_arch (char **cmdline_p)
 	early_acpi_boot_init();
 # ifdef CONFIG_ACPI_NUMA
 	acpi_numa_init();
+	acpi_numa_fixup();
 #  ifdef CONFIG_ACPI_HOTPLUG_CPU
 	prefill_possible_map();
 #  endif
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 636e0720fb20..86f65721e629 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -3,7 +3,6 @@ config MICROBLAZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select BUILDTIME_EXTABLE_SORT
 	select CLKSRC_OF
 	select CLONE_BACKWARDS3
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 142cb057c41b..489e7f909286 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -10,7 +10,7 @@ config OPENRISC
 	select IRQ_DOMAIN
 	select HANDLE_DOMAIN_IRQ
 	select HAVE_MEMBLOCK
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
         select HAVE_ARCH_TRACEHOOK
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_PROBE
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 0a9d439bcda6..d111044f41a2 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -98,7 +98,6 @@ config PPC
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select SYSCTL_EXCEPTION_TRACE
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select VIRT_TO_BUS if !PPC64
 	select HAVE_IDE
 	select HAVE_IOREMAP_PROT
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 9c221b69c181..7998c177f0a2 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -9,9 +9,11 @@ obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
 obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
+obj-$(CONFIG_CRYPT_CRC32C_VPMSUM) += crc32c-vpmsum.o
 
 aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
 md5-ppc-y := md5-asm.o md5-glue.o
 sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
 sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
 sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
+crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
diff --git a/arch/powerpc/crypto/aes-spe-regs.h b/arch/powerpc/crypto/aes-spe-regs.h
index 30d217b399c3..2cc3a2caadae 100644
--- a/arch/powerpc/crypto/aes-spe-regs.h
+++ b/arch/powerpc/crypto/aes-spe-regs.h
@@ -18,7 +18,7 @@
 #define rLN r7	/* length of data to be processed			*/
 #define rIP r8	/* potiner to IV (CBC/CTR/XTS modes)			*/
 #define rKT r9	/* pointer to tweak key (XTS mode)			*/
-#define rT0 r11	/* pointers to en-/decrpytion tables			*/
+#define rT0 r11	/* pointers to en-/decryption tables			*/
 #define rT1 r10
 #define rD0 r9	/* data 						*/
 #define rD1 r14
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
new file mode 100644
index 000000000000..dc640b212299
--- /dev/null
+++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
@@ -0,0 +1,1553 @@
+/*
+ * Calculate the checksum of data that is 16 byte aligned and a multiple of
+ * 16 bytes.
+ *
+ * The first step is to reduce it to 1024 bits. We do this in 8 parallel
+ * chunks in order to mask the latency of the vpmsum instructions. If we
+ * have more than 32 kB of data to checksum we repeat this step multiple
+ * times, passing in the previous 1024 bits.
+ *
+ * The next step is to reduce the 1024 bits to 64 bits. This step adds
+ * 32 bits of 0s to the end - this matches what a CRC does. We just
+ * calculate constants that land the data in this 32 bits.
+ *
+ * We then use fixed point Barrett reduction to compute a mod n over GF(2)
+ * for n = CRC using POWER8 instructions. We use x = 32.
+ *
+ * http://en.wikipedia.org/wiki/Barrett_reduction
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+
+	.section	.rodata
+.balign 16
+
+.byteswap_constant:
+	/* byte reverse permute constant */
+	.octa 0x0F0E0D0C0B0A09080706050403020100
+
+#define MAX_SIZE	32768
+.constants:
+
+	/* Reduce 262144 kbits to 1024 bits */
+	/* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */
+	.octa 0x00000000b6ca9e20000000009c37c408
+
+	/* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */
+	.octa 0x00000000350249a800000001b51df26c
+
+	/* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */
+	.octa 0x00000001862dac54000000000724b9d0
+
+	/* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */
+	.octa 0x00000001d87fb48c00000001c00532fe
+
+	/* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */
+	.octa 0x00000001f39b699e00000000f05a9362
+
+	/* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */
+	.octa 0x0000000101da11b400000001e1007970
+
+	/* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */
+	.octa 0x00000001cab571e000000000a57366ee
+
+	/* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */
+	.octa 0x00000000c7020cfe0000000192011284
+
+	/* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */
+	.octa 0x00000000cdaed1ae0000000162716d9a
+
+	/* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */
+	.octa 0x00000001e804effc00000000cd97ecde
+
+	/* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */
+	.octa 0x0000000077c3ea3a0000000058812bc0
+
+	/* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */
+	.octa 0x0000000068df31b40000000088b8c12e
+
+	/* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */
+	.octa 0x00000000b059b6c200000001230b234c
+
+	/* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */
+	.octa 0x0000000145fb8ed800000001120b416e
+
+	/* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */
+	.octa 0x00000000cbc0916800000001974aecb0
+
+	/* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */
+	.octa 0x000000005ceeedc2000000008ee3f226
+
+	/* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */
+	.octa 0x0000000047d74e8600000001089aba9a
+
+	/* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */
+	.octa 0x00000001407e9e220000000065113872
+
+	/* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */
+	.octa 0x00000001da967bda000000005c07ec10
+
+	/* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */
+	.octa 0x000000006c8983680000000187590924
+
+	/* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */
+	.octa 0x00000000f2d14c9800000000e35da7c6
+
+	/* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */
+	.octa 0x00000001993c6ad4000000000415855a
+
+	/* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */
+	.octa 0x000000014683d1ac0000000073617758
+
+	/* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */
+	.octa 0x00000001a7c93e6c0000000176021d28
+
+	/* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */
+	.octa 0x000000010211e90a00000001c358fd0a
+
+	/* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */
+	.octa 0x000000001119403e00000001ff7a2c18
+
+	/* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */
+	.octa 0x000000001c3261aa00000000f2d9f7e4
+
+	/* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */
+	.octa 0x000000014e37a634000000016cf1f9c8
+
+	/* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */
+	.octa 0x0000000073786c0c000000010af9279a
+
+	/* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */
+	.octa 0x000000011dc037f80000000004f101e8
+
+	/* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */
+	.octa 0x0000000031433dfc0000000070bcf184
+
+	/* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */
+	.octa 0x000000009cde8348000000000a8de642
+
+	/* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */
+	.octa 0x0000000038d3c2a60000000062ea130c
+
+	/* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */
+	.octa 0x000000011b25f26000000001eb31cbb2
+
+	/* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */
+	.octa 0x000000001629e6f00000000170783448
+
+	/* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */
+	.octa 0x0000000160838b4c00000001a684b4c6
+
+	/* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */
+	.octa 0x000000007a44011c00000000253ca5b4
+
+	/* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */
+	.octa 0x00000000226f417a0000000057b4b1e2
+
+	/* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */
+	.octa 0x0000000045eb2eb400000000b6bd084c
+
+	/* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */
+	.octa 0x000000014459d70c0000000123c2d592
+
+	/* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */
+	.octa 0x00000001d406ed8200000000159dafce
+
+	/* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */
+	.octa 0x0000000160c8e1a80000000127e1a64e
+
+	/* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */
+	.octa 0x0000000027ba80980000000056860754
+
+	/* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */
+	.octa 0x000000006d92d01800000001e661aae8
+
+	/* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */
+	.octa 0x000000012ed7e3f200000000f82c6166
+
+	/* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */
+	.octa 0x000000002dc8778800000000c4f9c7ae
+
+	/* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */
+	.octa 0x0000000018240bb80000000074203d20
+
+	/* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */
+	.octa 0x000000001ad381580000000198173052
+
+	/* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */
+	.octa 0x00000001396b78f200000001ce8aba54
+
+	/* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */
+	.octa 0x000000011a68133400000001850d5d94
+
+	/* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */
+	.octa 0x000000012104732e00000001d609239c
+
+	/* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */
+	.octa 0x00000000a140d90c000000001595f048
+
+	/* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */
+	.octa 0x00000001b7215eda0000000042ccee08
+
+	/* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */
+	.octa 0x00000001aaf1df3c000000010a389d74
+
+	/* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */
+	.octa 0x0000000029d15b8a000000012a840da6
+
+	/* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */
+	.octa 0x00000000f1a96922000000001d181c0c
+
+	/* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */
+	.octa 0x00000001ac80d03c0000000068b7d1f6
+
+	/* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */
+	.octa 0x000000000f11d56a000000005b0f14fc
+
+	/* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */
+	.octa 0x00000001f1c022a20000000179e9e730
+
+	/* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */
+	.octa 0x0000000173d00ae200000001ce1368d6
+
+	/* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */
+	.octa 0x00000001d4ffe4ac0000000112c3a84c
+
+	/* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */
+	.octa 0x000000016edc5ae400000000de940fee
+
+	/* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */
+	.octa 0x00000001f1a0214000000000fe896b7e
+
+	/* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */
+	.octa 0x00000000ca0b28a000000001f797431c
+
+	/* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */
+	.octa 0x00000001928e30a20000000053e989ba
+
+	/* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */
+	.octa 0x0000000097b1b002000000003920cd16
+
+	/* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */
+	.octa 0x00000000b15bf90600000001e6f579b8
+
+	/* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */
+	.octa 0x00000000411c5d52000000007493cb0a
+
+	/* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */
+	.octa 0x00000001c36f330000000001bdd376d8
+
+	/* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */
+	.octa 0x00000001119227e0000000016badfee6
+
+	/* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */
+	.octa 0x00000000114d47020000000071de5c58
+
+	/* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */
+	.octa 0x00000000458b5b9800000000453f317c
+
+	/* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */
+	.octa 0x000000012e31fb8e0000000121675cce
+
+	/* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */
+	.octa 0x000000005cf619d800000001f409ee92
+
+	/* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */
+	.octa 0x0000000063f4d8b200000000f36b9c88
+
+	/* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */
+	.octa 0x000000004138dc8a0000000036b398f4
+
+	/* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */
+	.octa 0x00000001d29ee8e000000001748f9adc
+
+	/* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */
+	.octa 0x000000006a08ace800000001be94ec00
+
+	/* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */
+	.octa 0x0000000127d4201000000000b74370d6
+
+	/* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */
+	.octa 0x0000000019d76b6200000001174d0b98
+
+	/* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */
+	.octa 0x00000001b1471f6e00000000befc06a4
+
+	/* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */
+	.octa 0x00000001f64c19cc00000001ae125288
+
+	/* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */
+	.octa 0x00000000003c0ea00000000095c19b34
+
+	/* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */
+	.octa 0x000000014d73abf600000001a78496f2
+
+	/* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */
+	.octa 0x00000001620eb84400000001ac5390a0
+
+	/* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */
+	.octa 0x0000000147655048000000002a80ed6e
+
+	/* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */
+	.octa 0x0000000067b5077e00000001fa9b0128
+
+	/* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */
+	.octa 0x0000000010ffe20600000001ea94929e
+
+	/* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */
+	.octa 0x000000000fee8f1e0000000125f4305c
+
+	/* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */
+	.octa 0x00000001da26fbae00000001471e2002
+
+	/* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */
+	.octa 0x00000001b3a8bd880000000132d2253a
+
+	/* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */
+	.octa 0x00000000e8f3898e00000000f26b3592
+
+	/* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */
+	.octa 0x00000000b0d0d28c00000000bc8b67b0
+
+	/* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */
+	.octa 0x0000000030f2a798000000013a826ef2
+
+	/* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */
+	.octa 0x000000000fba10020000000081482c84
+
+	/* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */
+	.octa 0x00000000bdb9bd7200000000e77307c2
+
+	/* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */
+	.octa 0x0000000075d3bf5a00000000d4a07ec8
+
+	/* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */
+	.octa 0x00000000ef1f98a00000000017102100
+
+	/* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */
+	.octa 0x00000000689c760200000000db406486
+
+	/* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */
+	.octa 0x000000016d5fa5fe0000000192db7f88
+
+	/* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */
+	.octa 0x00000001d0d2b9ca000000018bf67b1e
+
+	/* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */
+	.octa 0x0000000041e7b470000000007c09163e
+
+	/* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */
+	.octa 0x00000001cbb6495e000000000adac060
+
+	/* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */
+	.octa 0x000000010052a0b000000000bd8316ae
+
+	/* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */
+	.octa 0x00000001d8effb5c000000019f09ab54
+
+	/* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */
+	.octa 0x00000001d969853c0000000125155542
+
+	/* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */
+	.octa 0x00000000523ccce2000000018fdb5882
+
+	/* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */
+	.octa 0x000000001e2436bc00000000e794b3f4
+
+	/* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */
+	.octa 0x00000000ddd1c3a2000000016f9bb022
+
+	/* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */
+	.octa 0x0000000019fcfe3800000000290c9978
+
+	/* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */
+	.octa 0x00000001ce95db640000000083c0f350
+
+	/* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */
+	.octa 0x00000000af5828060000000173ea6628
+
+	/* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */
+	.octa 0x00000001006388f600000001c8b4e00a
+
+	/* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */
+	.octa 0x0000000179eca00a00000000de95d6aa
+
+	/* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */
+	.octa 0x0000000122410a6a000000010b7f7248
+
+	/* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */
+	.octa 0x000000004288e87c00000001326e3a06
+
+	/* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */
+	.octa 0x000000016c5490da00000000bb62c2e6
+
+	/* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */
+	.octa 0x00000000d1c71f6e0000000156a4b2c2
+
+	/* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */
+	.octa 0x00000001b4ce08a6000000011dfe763a
+
+	/* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */
+	.octa 0x00000001466ba60c000000007bcca8e2
+
+	/* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */
+	.octa 0x00000001f6c488a40000000186118faa
+
+	/* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */
+	.octa 0x000000013bfb06820000000111a65a88
+
+	/* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */
+	.octa 0x00000000690e9e54000000003565e1c4
+
+	/* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */
+	.octa 0x00000000281346b6000000012ed02a82
+
+	/* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */
+	.octa 0x000000015646402400000000c486ecfc
+
+	/* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */
+	.octa 0x000000016063a8dc0000000001b951b2
+
+	/* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */
+	.octa 0x0000000116a663620000000048143916
+
+	/* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */
+	.octa 0x000000017e8aa4d200000001dc2ae124
+
+	/* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */
+	.octa 0x00000001728eb10c00000001416c58d6
+
+	/* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */
+	.octa 0x00000001b08fd7fa00000000a479744a
+
+	/* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */
+	.octa 0x00000001092a16e80000000096ca3a26
+
+	/* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */
+	.octa 0x00000000a505637c00000000ff223d4e
+
+	/* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */
+	.octa 0x00000000d94869b2000000010e84da42
+
+	/* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */
+	.octa 0x00000001c8b203ae00000001b61ba3d0
+
+	/* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */
+	.octa 0x000000005704aea000000000680f2de8
+
+	/* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */
+	.octa 0x000000012e295fa2000000008772a9a8
+
+	/* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */
+	.octa 0x000000011d0908bc0000000155f295bc
+
+	/* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */
+	.octa 0x0000000193ed97ea00000000595f9282
+
+	/* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */
+	.octa 0x000000013a0f1c520000000164b1c25a
+
+	/* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */
+	.octa 0x000000010c2c40c000000000fbd67c50
+
+	/* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */
+	.octa 0x00000000ff6fac3e0000000096076268
+
+	/* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */
+	.octa 0x000000017b3609c000000001d288e4cc
+
+	/* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */
+	.octa 0x0000000088c8c92200000001eaac1bdc
+
+	/* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */
+	.octa 0x00000001751baae600000001f1ea39e2
+
+	/* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */
+	.octa 0x000000010795297200000001eb6506fc
+
+	/* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */
+	.octa 0x0000000162b00abe000000010f806ffe
+
+	/* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */
+	.octa 0x000000000d7b404c000000010408481e
+
+	/* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */
+	.octa 0x00000000763b13d40000000188260534
+
+	/* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */
+	.octa 0x00000000f6dc22d80000000058fc73e0
+
+	/* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */
+	.octa 0x000000007daae06000000000391c59b8
+
+	/* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */
+	.octa 0x000000013359ab7c000000018b638400
+
+	/* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */
+	.octa 0x000000008add438a000000011738f5c4
+
+	/* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */
+	.octa 0x00000001edbefdea000000008cf7c6da
+
+	/* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */
+	.octa 0x000000004104e0f800000001ef97fb16
+
+	/* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */
+	.octa 0x00000000b48a82220000000102130e20
+
+	/* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */
+	.octa 0x00000001bcb4684400000000db968898
+
+	/* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */
+	.octa 0x000000013293ce0a00000000b5047b5e
+
+	/* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */
+	.octa 0x00000001710d0844000000010b90fdb2
+
+	/* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */
+	.octa 0x0000000117907f6e000000004834a32e
+
+	/* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */
+	.octa 0x0000000087ddf93e0000000059c8f2b0
+
+	/* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */
+	.octa 0x000000005970e9b00000000122cec508
+
+	/* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */
+	.octa 0x0000000185b2b7d0000000000a330cda
+
+	/* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */
+	.octa 0x00000001dcee0efc000000014a47148c
+
+	/* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */
+	.octa 0x0000000030da27220000000042c61cb8
+
+	/* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */
+	.octa 0x000000012f925a180000000012fe6960
+
+	/* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */
+	.octa 0x00000000dd2e357c00000000dbda2c20
+
+	/* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */
+	.octa 0x00000000071c80de000000011122410c
+
+	/* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */
+	.octa 0x000000011513140a00000000977b2070
+
+	/* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */
+	.octa 0x00000001df876e8e000000014050438e
+
+	/* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */
+	.octa 0x000000015f81d6ce0000000147c840e8
+
+	/* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */
+	.octa 0x000000019dd94dbe00000001cc7c88ce
+
+	/* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */
+	.octa 0x00000001373d206e00000001476b35a4
+
+	/* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */
+	.octa 0x00000000668ccade000000013d52d508
+
+	/* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */
+	.octa 0x00000001b192d268000000008e4be32e
+
+	/* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */
+	.octa 0x00000000e30f3a7800000000024120fe
+
+	/* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */
+	.octa 0x000000010ef1f7bc00000000ddecddb4
+
+	/* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */
+	.octa 0x00000001f5ac738000000000d4d403bc
+
+	/* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */
+	.octa 0x000000011822ea7000000001734b89aa
+
+	/* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */
+	.octa 0x00000000c3a33848000000010e7a58d6
+
+	/* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */
+	.octa 0x00000001bd151c2400000001f9f04e9c
+
+	/* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */
+	.octa 0x0000000056002d7600000000b692225e
+
+	/* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */
+	.octa 0x000000014657c4f4000000019b8d3f3e
+
+	/* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */
+	.octa 0x0000000113742d7c00000001a874f11e
+
+	/* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */
+	.octa 0x000000019c5920ba000000010d5a4254
+
+	/* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */
+	.octa 0x000000005216d2d600000000bbb2f5d6
+
+	/* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */
+	.octa 0x0000000136f5ad8a0000000179cc0e36
+
+	/* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */
+	.octa 0x000000018b07beb600000001dca1da4a
+
+	/* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */
+	.octa 0x00000000db1e93b000000000feb1a192
+
+	/* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */
+	.octa 0x000000000b96fa3a00000000d1eeedd6
+
+	/* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */
+	.octa 0x00000001d9968af0000000008fad9bb4
+
+	/* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */
+	.octa 0x000000000e4a77a200000001884938e4
+
+	/* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */
+	.octa 0x00000000508c2ac800000001bc2e9bc0
+
+	/* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */
+	.octa 0x0000000021572a8000000001f9658a68
+
+	/* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */
+	.octa 0x00000001b859daf2000000001b9224fc
+
+	/* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */
+	.octa 0x000000016f7884740000000055b2fb84
+
+	/* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */
+	.octa 0x00000001b438810e000000018b090348
+
+	/* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */
+	.octa 0x0000000095ddc6f2000000011ccbd5ea
+
+	/* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */
+	.octa 0x00000001d977c20c0000000007ae47f8
+
+	/* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */
+	.octa 0x00000000ebedb99a0000000172acbec0
+
+	/* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */
+	.octa 0x00000001df9e9e9200000001c6e3ff20
+
+	/* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */
+	.octa 0x00000001a4a3f95200000000e1b38744
+
+	/* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */
+	.octa 0x00000000e2f5122000000000791585b2
+
+	/* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */
+	.octa 0x000000004aa01f3e00000000ac53b894
+
+	/* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */
+	.octa 0x00000000b3e90a5800000001ed5f2cf4
+
+	/* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */
+	.octa 0x000000000c9ca2aa00000001df48b2e0
+
+	/* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */
+	.octa 0x000000015168231600000000049c1c62
+
+	/* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */
+	.octa 0x0000000036fce78c000000017c460c12
+
+	/* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */
+	.octa 0x000000009037dc10000000015be4da7e
+
+	/* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */
+	.octa 0x00000000d3298582000000010f38f668
+
+	/* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */
+	.octa 0x00000001b42e8ad60000000039f40a00
+
+	/* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */
+	.octa 0x00000000142a983800000000bd4c10c4
+
+	/* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */
+	.octa 0x0000000109c7f1900000000042db1d98
+
+	/* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */
+	.octa 0x0000000056ff931000000001c905bae6
+
+	/* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */
+	.octa 0x00000001594513aa00000000069d40ea
+
+	/* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */
+	.octa 0x00000001e3b5b1e8000000008e4fbad0
+
+	/* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */
+	.octa 0x000000011dd5fc080000000047bedd46
+
+	/* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */
+	.octa 0x00000001675f0cc20000000026396bf8
+
+	/* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */
+	.octa 0x00000000d1c8dd4400000000379beb92
+
+	/* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */
+	.octa 0x0000000115ebd3d8000000000abae54a
+
+	/* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */
+	.octa 0x00000001ecbd0dac0000000007e6a128
+
+	/* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */
+	.octa 0x00000000cdf67af2000000000ade29d2
+
+	/* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */
+	.octa 0x000000004c01ff4c00000000f974c45c
+
+	/* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */
+	.octa 0x00000000f2d8657e00000000e77ac60a
+
+	/* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */
+	.octa 0x000000006bae74c40000000145895816
+
+	/* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */
+	.octa 0x0000000152af8aa00000000038e362be
+
+	/* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */
+	.octa 0x0000000004663802000000007f991a64
+
+	/* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */
+	.octa 0x00000001ab2f5afc00000000fa366d3a
+
+	/* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */
+	.octa 0x0000000074a4ebd400000001a2bb34f0
+
+	/* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */
+	.octa 0x00000001d7ab3a4c0000000028a9981e
+
+	/* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */
+	.octa 0x00000001a8da60c600000001dbc672be
+
+	/* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */
+	.octa 0x000000013cf6382000000000b04d77f6
+
+	/* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */
+	.octa 0x00000000bec12e1e0000000124400d96
+
+	/* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */
+	.octa 0x00000001c6368010000000014ca4b414
+
+	/* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */
+	.octa 0x00000001e6e78758000000012fe2c938
+
+	/* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */
+	.octa 0x000000008d7f2b3c00000001faed01e6
+
+	/* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */
+	.octa 0x000000016b4a156e000000007e80ecfe
+
+	/* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */
+	.octa 0x00000001c63cfeb60000000098daee94
+
+	/* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */
+	.octa 0x000000015f902670000000010a04edea
+
+	/* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */
+	.octa 0x00000001cd5de11e00000001c00b4524
+
+	/* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */
+	.octa 0x000000001acaec540000000170296550
+
+	/* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */
+	.octa 0x000000002bd0ca780000000181afaa48
+
+	/* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */
+	.octa 0x0000000032d63d5c0000000185a31ffa
+
+	/* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */
+	.octa 0x000000001c6d4e4c000000002469f608
+
+	/* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */
+	.octa 0x0000000106a60b92000000006980102a
+
+	/* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */
+	.octa 0x00000000d3855e120000000111ea9ca8
+
+	/* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */
+	.octa 0x00000000e312563600000001bd1d29ce
+
+	/* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */
+	.octa 0x000000009e8f7ea400000001b34b9580
+
+	/* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */
+	.octa 0x00000001c82e562c000000003076054e
+
+	/* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */
+	.octa 0x00000000ca9f09ce000000012a608ea4
+
+	/* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */
+	.octa 0x00000000c63764e600000000784d05fe
+
+	/* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */
+	.octa 0x0000000168d2e49e000000016ef0d82a
+
+	/* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */
+	.octa 0x00000000e986c1480000000075bda454
+
+	/* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */
+	.octa 0x00000000cfb65894000000003dc0a1c4
+
+	/* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */
+	.octa 0x0000000111cadee400000000e9a5d8be
+
+	/* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */
+	.octa 0x0000000171fb63ce00000001609bc4b4
+
+.short_constants:
+
+	/* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
+	/* x^1952 mod p(x)`, x^1984 mod p(x)`, x^2016 mod p(x)`, x^2048 mod p(x)` */
+	.octa 0x7fec2963e5bf80485cf015c388e56f72
+
+	/* x^1824 mod p(x)`, x^1856 mod p(x)`, x^1888 mod p(x)`, x^1920 mod p(x)` */
+	.octa 0x38e888d4844752a9963a18920246e2e6
+
+	/* x^1696 mod p(x)`, x^1728 mod p(x)`, x^1760 mod p(x)`, x^1792 mod p(x)` */
+	.octa 0x42316c00730206ad419a441956993a31
+
+	/* x^1568 mod p(x)`, x^1600 mod p(x)`, x^1632 mod p(x)`, x^1664 mod p(x)` */
+	.octa 0x543d5c543e65ddf9924752ba2b830011
+
+	/* x^1440 mod p(x)`, x^1472 mod p(x)`, x^1504 mod p(x)`, x^1536 mod p(x)` */
+	.octa 0x78e87aaf56767c9255bd7f9518e4a304
+
+	/* x^1312 mod p(x)`, x^1344 mod p(x)`, x^1376 mod p(x)`, x^1408 mod p(x)` */
+	.octa 0x8f68fcec1903da7f6d76739fe0553f1e
+
+	/* x^1184 mod p(x)`, x^1216 mod p(x)`, x^1248 mod p(x)`, x^1280 mod p(x)` */
+	.octa 0x3f4840246791d588c133722b1fe0b5c3
+
+	/* x^1056 mod p(x)`, x^1088 mod p(x)`, x^1120 mod p(x)`, x^1152 mod p(x)` */
+	.octa 0x34c96751b04de25a64b67ee0e55ef1f3
+
+	/* x^928 mod p(x)`, x^960 mod p(x)`, x^992 mod p(x)`, x^1024 mod p(x)` */
+	.octa 0x156c8e180b4a395b069db049b8fdb1e7
+
+	/* x^800 mod p(x)`, x^832 mod p(x)`, x^864 mod p(x)`, x^896 mod p(x)` */
+	.octa 0xe0b99ccbe661f7bea11bfaf3c9e90b9e
+
+	/* x^672 mod p(x)`, x^704 mod p(x)`, x^736 mod p(x)`, x^768 mod p(x)` */
+	.octa 0x041d37768cd75659817cdc5119b29a35
+
+	/* x^544 mod p(x)`, x^576 mod p(x)`, x^608 mod p(x)`, x^640 mod p(x)` */
+	.octa 0x3a0777818cfaa9651ce9d94b36c41f1c
+
+	/* x^416 mod p(x)`, x^448 mod p(x)`, x^480 mod p(x)`, x^512 mod p(x)` */
+	.octa 0x0e148e8252377a554f256efcb82be955
+
+	/* x^288 mod p(x)`, x^320 mod p(x)`, x^352 mod p(x)`, x^384 mod p(x)` */
+	.octa 0x9c25531d19e65ddeec1631edb2dea967
+
+	/* x^160 mod p(x)`, x^192 mod p(x)`, x^224 mod p(x)`, x^256 mod p(x)` */
+	.octa 0x790606ff9957c0a65d27e147510ac59a
+
+	/* x^32 mod p(x)`, x^64 mod p(x)`, x^96 mod p(x)`, x^128 mod p(x)` */
+	.octa 0x82f63b786ea2d55ca66805eb18b8ea18
+
+
+.barrett_constants:
+	/* 33 bit reflected Barrett constant m - (4^32)/n */
+	.octa 0x000000000000000000000000dea713f1	/* x^64 div p(x)` */
+	/* 33 bit reflected Barrett constant n */
+	.octa 0x00000000000000000000000105ec76f1
+
+	.text
+
+#if defined(__BIG_ENDIAN__)
+#define BYTESWAP_DATA
+#else
+#undef BYTESWAP_DATA
+#endif
+
+#define off16		r25
+#define off32		r26
+#define off48		r27
+#define off64		r28
+#define off80		r29
+#define off96		r30
+#define off112		r31
+
+#define const1		v24
+#define const2		v25
+
+#define byteswap	v26
+#define	mask_32bit	v27
+#define	mask_64bit	v28
+#define zeroes		v29
+
+#ifdef BYTESWAP_DATA
+#define VPERM(A, B, C, D) vperm	A, B, C, D
+#else
+#define VPERM(A, B, C, D)
+#endif
+
+/* unsigned int __crc32c_vpmsum(unsigned int crc, void *p, unsigned long len) */
+FUNC_START(__crc32c_vpmsum)
+	std	r31,-8(r1)
+	std	r30,-16(r1)
+	std	r29,-24(r1)
+	std	r28,-32(r1)
+	std	r27,-40(r1)
+	std	r26,-48(r1)
+	std	r25,-56(r1)
+
+	li	off16,16
+	li	off32,32
+	li	off48,48
+	li	off64,64
+	li	off80,80
+	li	off96,96
+	li	off112,112
+	li	r0,0
+
+	/* Enough room for saving 10 non volatile VMX registers */
+	subi	r6,r1,56+10*16
+	subi	r7,r1,56+2*16
+
+	stvx	v20,0,r6
+	stvx	v21,off16,r6
+	stvx	v22,off32,r6
+	stvx	v23,off48,r6
+	stvx	v24,off64,r6
+	stvx	v25,off80,r6
+	stvx	v26,off96,r6
+	stvx	v27,off112,r6
+	stvx	v28,0,r7
+	stvx	v29,off16,r7
+
+	mr	r10,r3
+
+	vxor	zeroes,zeroes,zeroes
+	vspltisw v0,-1
+
+	vsldoi	mask_32bit,zeroes,v0,4
+	vsldoi	mask_64bit,zeroes,v0,8
+
+	/* Get the initial value into v8 */
+	vxor	v8,v8,v8
+	MTVRD(v8, R3)
+	vsldoi	v8,zeroes,v8,8	/* shift into bottom 32 bits */
+
+#ifdef BYTESWAP_DATA
+	addis	r3,r2,.byteswap_constant@toc@ha
+	addi	r3,r3,.byteswap_constant@toc@l
+
+	lvx	byteswap,0,r3
+	addi	r3,r3,16
+#endif
+
+	cmpdi	r5,256
+	blt	.Lshort
+
+	rldicr	r6,r5,0,56
+
+	/* Checksum in blocks of MAX_SIZE */
+1:	lis	r7,MAX_SIZE@h
+	ori	r7,r7,MAX_SIZE@l
+	mr	r9,r7
+	cmpd	r6,r7
+	bgt	2f
+	mr	r7,r6
+2:	subf	r6,r7,r6
+
+	/* our main loop does 128 bytes at a time */
+	srdi	r7,r7,7
+
+	/*
+	 * Work out the offset into the constants table to start at. Each
+	 * constant is 16 bytes, and it is used against 128 bytes of input
+	 * data - 128 / 16 = 8
+	 */
+	sldi	r8,r7,4
+	srdi	r9,r9,3
+	subf	r8,r8,r9
+
+	/* We reduce our final 128 bytes in a separate step */
+	addi	r7,r7,-1
+	mtctr	r7
+
+	addis	r3,r2,.constants@toc@ha
+	addi	r3,r3,.constants@toc@l
+
+	/* Find the start of our constants */
+	add	r3,r3,r8
+
+	/* zero v0-v7 which will contain our checksums */
+	vxor	v0,v0,v0
+	vxor	v1,v1,v1
+	vxor	v2,v2,v2
+	vxor	v3,v3,v3
+	vxor	v4,v4,v4
+	vxor	v5,v5,v5
+	vxor	v6,v6,v6
+	vxor	v7,v7,v7
+
+	lvx	const1,0,r3
+
+	/*
+	 * If we are looping back to consume more data we use the values
+	 * already in v16-v23.
+	 */
+	cmpdi	r0,1
+	beq	2f
+
+	/* First warm up pass */
+	lvx	v16,0,r4
+	lvx	v17,off16,r4
+	VPERM(v16,v16,v16,byteswap)
+	VPERM(v17,v17,v17,byteswap)
+	lvx	v18,off32,r4
+	lvx	v19,off48,r4
+	VPERM(v18,v18,v18,byteswap)
+	VPERM(v19,v19,v19,byteswap)
+	lvx	v20,off64,r4
+	lvx	v21,off80,r4
+	VPERM(v20,v20,v20,byteswap)
+	VPERM(v21,v21,v21,byteswap)
+	lvx	v22,off96,r4
+	lvx	v23,off112,r4
+	VPERM(v22,v22,v22,byteswap)
+	VPERM(v23,v23,v23,byteswap)
+	addi	r4,r4,8*16
+
+	/* xor in initial value */
+	vxor	v16,v16,v8
+
+2:	bdz	.Lfirst_warm_up_done
+
+	addi	r3,r3,16
+	lvx	const2,0,r3
+
+	/* Second warm up pass */
+	VPMSUMD(v8,v16,const1)
+	lvx	v16,0,r4
+	VPERM(v16,v16,v16,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v9,v17,const1)
+	lvx	v17,off16,r4
+	VPERM(v17,v17,v17,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v10,v18,const1)
+	lvx	v18,off32,r4
+	VPERM(v18,v18,v18,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v11,v19,const1)
+	lvx	v19,off48,r4
+	VPERM(v19,v19,v19,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v12,v20,const1)
+	lvx	v20,off64,r4
+	VPERM(v20,v20,v20,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v13,v21,const1)
+	lvx	v21,off80,r4
+	VPERM(v21,v21,v21,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v14,v22,const1)
+	lvx	v22,off96,r4
+	VPERM(v22,v22,v22,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v15,v23,const1)
+	lvx	v23,off112,r4
+	VPERM(v23,v23,v23,byteswap)
+
+	addi	r4,r4,8*16
+
+	bdz	.Lfirst_cool_down
+
+	/*
+	 * main loop. We modulo schedule it such that it takes three iterations
+	 * to complete - first iteration load, second iteration vpmsum, third
+	 * iteration xor.
+	 */
+	.balign	16
+4:	lvx	const1,0,r3
+	addi	r3,r3,16
+	ori	r2,r2,0
+
+	vxor	v0,v0,v8
+	VPMSUMD(v8,v16,const2)
+	lvx	v16,0,r4
+	VPERM(v16,v16,v16,byteswap)
+	ori	r2,r2,0
+
+	vxor	v1,v1,v9
+	VPMSUMD(v9,v17,const2)
+	lvx	v17,off16,r4
+	VPERM(v17,v17,v17,byteswap)
+	ori	r2,r2,0
+
+	vxor	v2,v2,v10
+	VPMSUMD(v10,v18,const2)
+	lvx	v18,off32,r4
+	VPERM(v18,v18,v18,byteswap)
+	ori	r2,r2,0
+
+	vxor	v3,v3,v11
+	VPMSUMD(v11,v19,const2)
+	lvx	v19,off48,r4
+	VPERM(v19,v19,v19,byteswap)
+	lvx	const2,0,r3
+	ori	r2,r2,0
+
+	vxor	v4,v4,v12
+	VPMSUMD(v12,v20,const1)
+	lvx	v20,off64,r4
+	VPERM(v20,v20,v20,byteswap)
+	ori	r2,r2,0
+
+	vxor	v5,v5,v13
+	VPMSUMD(v13,v21,const1)
+	lvx	v21,off80,r4
+	VPERM(v21,v21,v21,byteswap)
+	ori	r2,r2,0
+
+	vxor	v6,v6,v14
+	VPMSUMD(v14,v22,const1)
+	lvx	v22,off96,r4
+	VPERM(v22,v22,v22,byteswap)
+	ori	r2,r2,0
+
+	vxor	v7,v7,v15
+	VPMSUMD(v15,v23,const1)
+	lvx	v23,off112,r4
+	VPERM(v23,v23,v23,byteswap)
+
+	addi	r4,r4,8*16
+
+	bdnz	4b
+
+.Lfirst_cool_down:
+	/* First cool down pass */
+	lvx	const1,0,r3
+	addi	r3,r3,16
+
+	vxor	v0,v0,v8
+	VPMSUMD(v8,v16,const1)
+	ori	r2,r2,0
+
+	vxor	v1,v1,v9
+	VPMSUMD(v9,v17,const1)
+	ori	r2,r2,0
+
+	vxor	v2,v2,v10
+	VPMSUMD(v10,v18,const1)
+	ori	r2,r2,0
+
+	vxor	v3,v3,v11
+	VPMSUMD(v11,v19,const1)
+	ori	r2,r2,0
+
+	vxor	v4,v4,v12
+	VPMSUMD(v12,v20,const1)
+	ori	r2,r2,0
+
+	vxor	v5,v5,v13
+	VPMSUMD(v13,v21,const1)
+	ori	r2,r2,0
+
+	vxor	v6,v6,v14
+	VPMSUMD(v14,v22,const1)
+	ori	r2,r2,0
+
+	vxor	v7,v7,v15
+	VPMSUMD(v15,v23,const1)
+	ori	r2,r2,0
+
+.Lsecond_cool_down:
+	/* Second cool down pass */
+	vxor	v0,v0,v8
+	vxor	v1,v1,v9
+	vxor	v2,v2,v10
+	vxor	v3,v3,v11
+	vxor	v4,v4,v12
+	vxor	v5,v5,v13
+	vxor	v6,v6,v14
+	vxor	v7,v7,v15
+
+	/*
+	 * vpmsumd produces a 96 bit result in the least significant bits
+	 * of the register. Since we are bit reflected we have to shift it
+	 * left 32 bits so it occupies the least significant bits in the
+	 * bit reflected domain.
+	 */
+	vsldoi	v0,v0,zeroes,4
+	vsldoi	v1,v1,zeroes,4
+	vsldoi	v2,v2,zeroes,4
+	vsldoi	v3,v3,zeroes,4
+	vsldoi	v4,v4,zeroes,4
+	vsldoi	v5,v5,zeroes,4
+	vsldoi	v6,v6,zeroes,4
+	vsldoi	v7,v7,zeroes,4
+
+	/* xor with last 1024 bits */
+	lvx	v8,0,r4
+	lvx	v9,off16,r4
+	VPERM(v8,v8,v8,byteswap)
+	VPERM(v9,v9,v9,byteswap)
+	lvx	v10,off32,r4
+	lvx	v11,off48,r4
+	VPERM(v10,v10,v10,byteswap)
+	VPERM(v11,v11,v11,byteswap)
+	lvx	v12,off64,r4
+	lvx	v13,off80,r4
+	VPERM(v12,v12,v12,byteswap)
+	VPERM(v13,v13,v13,byteswap)
+	lvx	v14,off96,r4
+	lvx	v15,off112,r4
+	VPERM(v14,v14,v14,byteswap)
+	VPERM(v15,v15,v15,byteswap)
+
+	addi	r4,r4,8*16
+
+	vxor	v16,v0,v8
+	vxor	v17,v1,v9
+	vxor	v18,v2,v10
+	vxor	v19,v3,v11
+	vxor	v20,v4,v12
+	vxor	v21,v5,v13
+	vxor	v22,v6,v14
+	vxor	v23,v7,v15
+
+	li	r0,1
+	cmpdi	r6,0
+	addi	r6,r6,128
+	bne	1b
+
+	/* Work out how many bytes we have left */
+	andi.	r5,r5,127
+
+	/* Calculate where in the constant table we need to start */
+	subfic	r6,r5,128
+	add	r3,r3,r6
+
+	/* How many 16 byte chunks are in the tail */
+	srdi	r7,r5,4
+	mtctr	r7
+
+	/*
+	 * Reduce the previously calculated 1024 bits to 64 bits, shifting
+	 * 32 bits to include the trailing 32 bits of zeros
+	 */
+	lvx	v0,0,r3
+	lvx	v1,off16,r3
+	lvx	v2,off32,r3
+	lvx	v3,off48,r3
+	lvx	v4,off64,r3
+	lvx	v5,off80,r3
+	lvx	v6,off96,r3
+	lvx	v7,off112,r3
+	addi	r3,r3,8*16
+
+	VPMSUMW(v0,v16,v0)
+	VPMSUMW(v1,v17,v1)
+	VPMSUMW(v2,v18,v2)
+	VPMSUMW(v3,v19,v3)
+	VPMSUMW(v4,v20,v4)
+	VPMSUMW(v5,v21,v5)
+	VPMSUMW(v6,v22,v6)
+	VPMSUMW(v7,v23,v7)
+
+	/* Now reduce the tail (0 - 112 bytes) */
+	cmpdi	r7,0
+	beq	1f
+
+	lvx	v16,0,r4
+	lvx	v17,0,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off32,r4
+	lvx	v17,off32,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off64,r4
+	lvx	v17,off64,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off96,r4
+	lvx	v17,off96,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+
+	/* Now xor all the parallel chunks together */
+1:	vxor	v0,v0,v1
+	vxor	v2,v2,v3
+	vxor	v4,v4,v5
+	vxor	v6,v6,v7
+
+	vxor	v0,v0,v2
+	vxor	v4,v4,v6
+
+	vxor	v0,v0,v4
+
+.Lbarrett_reduction:
+	/* Barrett constants */
+	addis	r3,r2,.barrett_constants@toc@ha
+	addi	r3,r3,.barrett_constants@toc@l
+
+	lvx	const1,0,r3
+	lvx	const2,off16,r3
+
+	vsldoi	v1,v0,v0,8
+	vxor	v0,v0,v1		/* xor two 64 bit results together */
+
+	/* shift left one bit */
+	vspltisb v1,1
+	vsl	v0,v0,v1
+
+	vand	v0,v0,mask_64bit
+
+	/*
+	 * The reflected version of Barrett reduction. Instead of bit
+	 * reflecting our data (which is expensive to do), we bit reflect our
+	 * constants and our algorithm, which means the intermediate data in
+	 * our vector registers goes from 0-63 instead of 63-0. We can reflect
+	 * the algorithm because we don't carry in mod 2 arithmetic.
+	 */
+	vand	v1,v0,mask_32bit	/* bottom 32 bits of a */
+	VPMSUMD(v1,v1,const1)		/* ma */
+	vand	v1,v1,mask_32bit	/* bottom 32bits of ma */
+	VPMSUMD(v1,v1,const2)		/* qn */
+	vxor	v0,v0,v1		/* a - qn, subtraction is xor in GF(2) */
+
+	/*
+	 * Since we are bit reflected, the result (ie the low 32 bits) is in
+	 * the high 32 bits. We just need to shift it left 4 bytes
+	 * V0 [ 0 1 X 3 ]
+	 * V0 [ 0 X 2 3 ]
+	 */
+	vsldoi	v0,v0,zeroes,4		/* shift result into top 64 bits of */
+
+	/* Get it into r3 */
+	MFVRD(R3, v0)
+
+.Lout:
+	subi	r6,r1,56+10*16
+	subi	r7,r1,56+2*16
+
+	lvx	v20,0,r6
+	lvx	v21,off16,r6
+	lvx	v22,off32,r6
+	lvx	v23,off48,r6
+	lvx	v24,off64,r6
+	lvx	v25,off80,r6
+	lvx	v26,off96,r6
+	lvx	v27,off112,r6
+	lvx	v28,0,r7
+	lvx	v29,off16,r7
+
+	ld	r31,-8(r1)
+	ld	r30,-16(r1)
+	ld	r29,-24(r1)
+	ld	r28,-32(r1)
+	ld	r27,-40(r1)
+	ld	r26,-48(r1)
+	ld	r25,-56(r1)
+
+	blr
+
+.Lfirst_warm_up_done:
+	lvx	const1,0,r3
+	addi	r3,r3,16
+
+	VPMSUMD(v8,v16,const1)
+	VPMSUMD(v9,v17,const1)
+	VPMSUMD(v10,v18,const1)
+	VPMSUMD(v11,v19,const1)
+	VPMSUMD(v12,v20,const1)
+	VPMSUMD(v13,v21,const1)
+	VPMSUMD(v14,v22,const1)
+	VPMSUMD(v15,v23,const1)
+
+	b	.Lsecond_cool_down
+
+.Lshort:
+	cmpdi	r5,0
+	beq	.Lzero
+
+	addis	r3,r2,.short_constants@toc@ha
+	addi	r3,r3,.short_constants@toc@l
+
+	/* Calculate where in the constant table we need to start */
+	subfic	r6,r5,256
+	add	r3,r3,r6
+
+	/* How many 16 byte chunks? */
+	srdi	r7,r5,4
+	mtctr	r7
+
+	vxor	v19,v19,v19
+	vxor	v20,v20,v20
+
+	lvx	v0,0,r4
+	lvx	v16,0,r3
+	VPERM(v0,v0,v16,byteswap)
+	vxor	v0,v0,v8	/* xor in initial value */
+	VPMSUMW(v0,v0,v16)
+	bdz	.Lv0
+
+	lvx	v1,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v1,v1,v17,byteswap)
+	VPMSUMW(v1,v1,v17)
+	bdz	.Lv1
+
+	lvx	v2,off32,r4
+	lvx	v16,off32,r3
+	VPERM(v2,v2,v16,byteswap)
+	VPMSUMW(v2,v2,v16)
+	bdz	.Lv2
+
+	lvx	v3,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v3,v3,v17,byteswap)
+	VPMSUMW(v3,v3,v17)
+	bdz	.Lv3
+
+	lvx	v4,off64,r4
+	lvx	v16,off64,r3
+	VPERM(v4,v4,v16,byteswap)
+	VPMSUMW(v4,v4,v16)
+	bdz	.Lv4
+
+	lvx	v5,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v5,v5,v17,byteswap)
+	VPMSUMW(v5,v5,v17)
+	bdz	.Lv5
+
+	lvx	v6,off96,r4
+	lvx	v16,off96,r3
+	VPERM(v6,v6,v16,byteswap)
+	VPMSUMW(v6,v6,v16)
+	bdz	.Lv6
+
+	lvx	v7,off112,r4
+	lvx	v17,off112,r3
+	VPERM(v7,v7,v17,byteswap)
+	VPMSUMW(v7,v7,v17)
+	bdz	.Lv7
+
+	addi	r3,r3,128
+	addi	r4,r4,128
+
+	lvx	v8,0,r4
+	lvx	v16,0,r3
+	VPERM(v8,v8,v16,byteswap)
+	VPMSUMW(v8,v8,v16)
+	bdz	.Lv8
+
+	lvx	v9,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v9,v9,v17,byteswap)
+	VPMSUMW(v9,v9,v17)
+	bdz	.Lv9
+
+	lvx	v10,off32,r4
+	lvx	v16,off32,r3
+	VPERM(v10,v10,v16,byteswap)
+	VPMSUMW(v10,v10,v16)
+	bdz	.Lv10
+
+	lvx	v11,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v11,v11,v17,byteswap)
+	VPMSUMW(v11,v11,v17)
+	bdz	.Lv11
+
+	lvx	v12,off64,r4
+	lvx	v16,off64,r3
+	VPERM(v12,v12,v16,byteswap)
+	VPMSUMW(v12,v12,v16)
+	bdz	.Lv12
+
+	lvx	v13,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v13,v13,v17,byteswap)
+	VPMSUMW(v13,v13,v17)
+	bdz	.Lv13
+
+	lvx	v14,off96,r4
+	lvx	v16,off96,r3
+	VPERM(v14,v14,v16,byteswap)
+	VPMSUMW(v14,v14,v16)
+	bdz	.Lv14
+
+	lvx	v15,off112,r4
+	lvx	v17,off112,r3
+	VPERM(v15,v15,v17,byteswap)
+	VPMSUMW(v15,v15,v17)
+
+.Lv15:	vxor	v19,v19,v15
+.Lv14:	vxor	v20,v20,v14
+.Lv13:	vxor	v19,v19,v13
+.Lv12:	vxor	v20,v20,v12
+.Lv11:	vxor	v19,v19,v11
+.Lv10:	vxor	v20,v20,v10
+.Lv9:	vxor	v19,v19,v9
+.Lv8:	vxor	v20,v20,v8
+.Lv7:	vxor	v19,v19,v7
+.Lv6:	vxor	v20,v20,v6
+.Lv5:	vxor	v19,v19,v5
+.Lv4:	vxor	v20,v20,v4
+.Lv3:	vxor	v19,v19,v3
+.Lv2:	vxor	v20,v20,v2
+.Lv1:	vxor	v19,v19,v1
+.Lv0:	vxor	v20,v20,v0
+
+	vxor	v0,v19,v20
+
+	b	.Lbarrett_reduction
+
+.Lzero:
+	mr	r3,r10
+	b	.Lout
+
+FUNC_END(__crc32_vpmsum)
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
new file mode 100644
index 000000000000..bfe3d37a24ef
--- /dev/null
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -0,0 +1,167 @@
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <asm/switch_to.h>
+
+#define CHKSUM_BLOCK_SIZE	1
+#define CHKSUM_DIGEST_SIZE	4
+
+#define VMX_ALIGN		16
+#define VMX_ALIGN_MASK		(VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT	512
+
+u32 __crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len);
+
+static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
+{
+	unsigned int prealign;
+	unsigned int tail;
+
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+		return __crc32c_le(crc, p, len);
+
+	if ((unsigned long)p & VMX_ALIGN_MASK) {
+		prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+		crc = __crc32c_le(crc, p, prealign);
+		len -= prealign;
+		p += prealign;
+	}
+
+	if (len & ~VMX_ALIGN_MASK) {
+		pagefault_disable();
+		enable_kernel_altivec();
+		crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+		pagefault_enable();
+	}
+
+	tail = len & VMX_ALIGN_MASK;
+	if (tail) {
+		p += len & ~VMX_ALIGN_MASK;
+		crc = __crc32c_le(crc, p, tail);
+	}
+
+	return crc;
+}
+
+static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
+{
+	u32 *key = crypto_tfm_ctx(tfm);
+
+	*key = 0;
+
+	return 0;
+}
+
+/*
+ * Setting the seed allows arbitrary accumulators and flexible XOR policy
+ * If your algorithm starts with ~0, then XOR with ~0 before you set
+ * the seed.
+ */
+static int crc32c_vpmsum_setkey(struct crypto_shash *hash, const u8 *key,
+			       unsigned int keylen)
+{
+	u32 *mctx = crypto_shash_ctx(hash);
+
+	if (keylen != sizeof(u32)) {
+		crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	*mctx = le32_to_cpup((__le32 *)key);
+	return 0;
+}
+
+static int crc32c_vpmsum_init(struct shash_desc *desc)
+{
+	u32 *mctx = crypto_shash_ctx(desc->tfm);
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = *mctx;
+
+	return 0;
+}
+
+static int crc32c_vpmsum_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = crc32c_vpmsum(*crcp, data, len);
+
+	return 0;
+}
+
+static int __crc32c_vpmsum_finup(u32 *crcp, const u8 *data, unsigned int len,
+				u8 *out)
+{
+	*(__le32 *)out = ~cpu_to_le32(crc32c_vpmsum(*crcp, data, len));
+
+	return 0;
+}
+
+static int crc32c_vpmsum_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return __crc32c_vpmsum_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32c_vpmsum_final(struct shash_desc *desc, u8 *out)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*(__le32 *)out = ~cpu_to_le32p(crcp);
+
+	return 0;
+}
+
+static int crc32c_vpmsum_digest(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *out)
+{
+	return __crc32c_vpmsum_finup(crypto_shash_ctx(desc->tfm), data, len,
+				     out);
+}
+
+static struct shash_alg alg = {
+	.setkey		= crc32c_vpmsum_setkey,
+	.init		= crc32c_vpmsum_init,
+	.update		= crc32c_vpmsum_update,
+	.final		= crc32c_vpmsum_final,
+	.finup		= crc32c_vpmsum_finup,
+	.digest		= crc32c_vpmsum_digest,
+	.descsize	= sizeof(u32),
+	.digestsize	= CHKSUM_DIGEST_SIZE,
+	.base		= {
+		.cra_name		= "crc32c",
+		.cra_driver_name	= "crc32c-vpmsum",
+		.cra_priority		= 200,
+		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(u32),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= crc32c_vpmsum_cra_init,
+	}
+};
+
+static int __init crc32c_vpmsum_mod_init(void)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crc32c_vpmsum_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crc32c_vpmsum_mod_init);
+module_exit(crc32c_vpmsum_mod_fini);
+
+MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
+MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-vpmsum");
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 1d035c1cc889..49cd8760aa7c 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -174,6 +174,8 @@
 #define PPC_INST_MFSPR_DSCR_USER_MASK	0xfc1fffff
 #define PPC_INST_MTSPR_DSCR_USER	0x7c0303a6
 #define PPC_INST_MTSPR_DSCR_USER_MASK	0xfc1fffff
+#define PPC_INST_MFVSRD			0x7c000066
+#define PPC_INST_MTVSRD			0x7c000166
 #define PPC_INST_SLBFEE			0x7c0007a7
 
 #define PPC_INST_STRING			0x7c00042a
@@ -188,6 +190,8 @@
 #define PPC_INST_WAIT			0x7c00007c
 #define PPC_INST_TLBIVAX		0x7c000624
 #define PPC_INST_TLBSRX_DOT		0x7c0006a5
+#define PPC_INST_VPMSUMW		0x10000488
+#define PPC_INST_VPMSUMD		0x100004c8
 #define PPC_INST_XXLOR			0xf0000510
 #define PPC_INST_XXSWAPD		0xf0000250
 #define PPC_INST_XVCPSGNDP		0xf0000780
@@ -359,6 +363,14 @@
 					       VSX_XX1((s), a, b))
 #define LXVD2X(s, a, b)		stringify_in_c(.long PPC_INST_LXVD2X | \
 					       VSX_XX1((s), a, b))
+#define MFVRD(a, t)		stringify_in_c(.long PPC_INST_MFVSRD | \
+					       VSX_XX1((t)+32, a, R0))
+#define MTVRD(t, a)		stringify_in_c(.long PPC_INST_MTVSRD | \
+					       VSX_XX1((t)+32, a, R0))
+#define VPMSUMW(t, a, b)	stringify_in_c(.long PPC_INST_VPMSUMW | \
+					       VSX_XX3((t), a, b))
+#define VPMSUMD(t, a, b)	stringify_in_c(.long PPC_INST_VPMSUMD | \
+					       VSX_XX3((t), a, b))
 #define XXLOR(t, a, b)		stringify_in_c(.long PPC_INST_XXLOR | \
 					       VSX_XX3((t), a, b))
 #define XXSWAPD(t, a)		stringify_in_c(.long PPC_INST_XXSWAPD | \
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 2b31632376a5..051af612a7e1 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -286,6 +286,9 @@ n:
 
 #endif
 
+#define FUNC_START(name)	_GLOBAL(name)
+#define FUNC_END(name)
+
 /* 
  * LOAD_REG_IMMEDIATE(rn, expr)
  *   Loads the value of the constant expression 'expr' into register 'rn'
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 12e48d56f771..3963f0b68d52 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -38,6 +38,18 @@ EXPORT_SYMBOL(ioread16);
 EXPORT_SYMBOL(ioread16be);
 EXPORT_SYMBOL(ioread32);
 EXPORT_SYMBOL(ioread32be);
+#ifdef __powerpc64__
+u64 ioread64(void __iomem *addr)
+{
+	return readq(addr);
+}
+u64 ioread64be(void __iomem *addr)
+{
+	return readq_be(addr);
+}
+EXPORT_SYMBOL(ioread64);
+EXPORT_SYMBOL(ioread64be);
+#endif /* __powerpc64__ */
 
 void iowrite8(u8 val, void __iomem *addr)
 {
@@ -64,6 +76,18 @@ EXPORT_SYMBOL(iowrite16);
 EXPORT_SYMBOL(iowrite16be);
 EXPORT_SYMBOL(iowrite32);
 EXPORT_SYMBOL(iowrite32be);
+#ifdef __powerpc64__
+void iowrite64(u64 val, void __iomem *addr)
+{
+	writeq(val, addr);
+}
+void iowrite64be(u64 val, void __iomem *addr)
+{
+	writeq_be(val, addr);
+}
+EXPORT_SYMBOL(iowrite64);
+EXPORT_SYMBOL(iowrite64be);
+#endif /* __powerpc64__ */
 
 /*
  * These are the "repeat read/write" functions. Note the
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 856f9a7944cd..64174bf95611 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -444,7 +444,8 @@ static int nvram_pstore_write(enum pstore_type_id type,
  */
 static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 				int *count, struct timespec *time, char **buf,
-				bool *compressed, struct pstore_info *psi)
+				bool *compressed, ssize_t *ecc_notice_size,
+				struct pstore_info *psi)
 {
 	struct oops_log_info *oops_hdr;
 	unsigned int err_type, id_no, size = 0;
@@ -545,6 +546,7 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 			return -ENOMEM;
 		kfree(buff);
 
+		*ecc_notice_size = 0;
 		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
 			*compressed = true;
 		else
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
index 6e287f1294fa..e3257f24a8a1 100644
--- a/arch/powerpc/platforms/40x/Kconfig
+++ b/arch/powerpc/platforms/40x/Kconfig
@@ -137,7 +137,7 @@ config STB03xxx
 config PPC4xx_GPIO
 	bool "PPC4xx GPIO support"
 	depends on 40x
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  Enable gpiolib support for ppc40x based boards
 
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 5538e57c36c1..48fc18041ff6 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -273,7 +273,7 @@ config PPC44x_SIMPLE
 config PPC4xx_GPIO
 	bool "PPC4xx GPIO support"
 	depends on 44x
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  Enable gpiolib support for ppc440 based boards
 
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index f09016f6b3a6..bf7ae5cbd07a 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -6,7 +6,6 @@ config PPC_MPC512x
 	select IPIC
 	select PPC_PCI_CHOICE
 	select FSL_PCI if PCI
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select USB_EHCI_BIG_ENDIAN_MMIO if USB_EHCI_HCD
 	select USB_EHCI_BIG_ENDIAN_DESC if USB_EHCI_HCD
 
diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig
index 2bdc8c862c46..4ef7f1cd05b7 100644
--- a/arch/powerpc/platforms/83xx/Kconfig
+++ b/arch/powerpc/platforms/83xx/Kconfig
@@ -116,7 +116,6 @@ endif
 # used for usb & gpio
 config PPC_MPC831x
 	bool
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 
 # used for math-emu
 config PPC_MPC832x
@@ -125,9 +124,7 @@ config PPC_MPC832x
 # used for usb & gpio
 config PPC_MPC834x
 	bool
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 
 # used for usb & gpio
 config PPC_MPC837x
 	bool
-	select ARCH_WANT_OPTIONAL_GPIOLIB
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index e626461a63bd..df25a3ed489d 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -225,7 +225,7 @@ config GE_IMP3A
 	select DEFAULT_UIMAGE
 	select SWIOTLB
 	select MMIO_NVRAM
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select GE_FPGA
 	help
 	  This option enables support for the GE Intelligent Platforms IMP3A
@@ -272,7 +272,7 @@ config CORENET_GENERIC
 	select PPC_E500MC
 	select PHYS_64BIT
 	select SWIOTLB
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select GPIO_MPC8XXX
 	select HAS_RAPIDIO
 	select PPC_EPAPR_HV_PIC
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 1afd1e4a2dd2..3988f16e46c1 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -4,7 +4,6 @@ menuconfig PPC_86xx
 	depends on 6xx
 	select FSL_SOC
 	select ALTIVEC
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	help
 	  The Freescale E600 SoCs have 74xx cores.
 
@@ -37,7 +36,7 @@ config GEF_PPC9A
 	bool "GE PPC9A"
 	select DEFAULT_UIMAGE
 	select MMIO_NVRAM
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select GE_FPGA
 	help
 	  This option enables support for the GE PPC9A.
@@ -46,7 +45,7 @@ config GEF_SBC310
 	bool "GE SBC310"
 	select DEFAULT_UIMAGE
 	select MMIO_NVRAM
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select GE_FPGA
 	help
 	  This option enables support for the GE SBC310.
@@ -55,7 +54,7 @@ config GEF_SBC610
 	bool "GE SBC610"
 	select DEFAULT_UIMAGE
 	select MMIO_NVRAM
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select GE_FPGA
 	select HAS_RAPIDIO
 	help
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index 157250426b56..564d99bb2a26 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -109,7 +109,7 @@ config 8xx_COPYBACK
 
 config 8xx_GPIO
 	bool "GPIO API Support"
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  Saying Y here will cause the ports on an MPC8xx processor to be used
 	  with the GPIO API.  If you say N here, the kernel needs less memory.
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 46a3533d3acb..3663f71fd913 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -275,7 +275,7 @@ config TAU_AVERAGE
 config QE_GPIO
 	bool "QE GPIO support"
 	depends on QUICC_ENGINE
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  Say Y here if you're going to use hardware that connects to the
 	  QE GPIOs.
@@ -285,7 +285,7 @@ config CPM2
 	depends on (FSL_SOC_BOOKE && PPC32) || 8260
 	select CPM
 	select PPC_PCI_CHOICE
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  The CPM2 (Communications Processor Module) is a coprocessor on
 	  embedded CPUs made by Freescale.  Selecting this option means that
@@ -324,7 +324,7 @@ config OF_RTC
 config SIMPLE_GPIO
 	bool "Support for simple, memory-mapped GPIO controllers"
 	depends on PPC
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  Say Y here to support simple, memory-mapped GPIO controllers.
 	  These are usually BCSRs used to control board's switches, LEDs,
@@ -334,7 +334,7 @@ config SIMPLE_GPIO
 config MCU_MPC8349EMITX
 	bool "MPC8349E-mITX MCU driver"
 	depends on I2C=y && PPC_83xx
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  Say Y here to enable soft power-off functionality on the Freescale
 	  boards with the MPC8349E-mITX-compatible MCU chips. This driver will
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
index 82607d621aca..88301e53f085 100644
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -85,61 +85,57 @@ static void spu_gov_cancel_work(struct spu_gov_info_struct *info)
 	cancel_delayed_work_sync(&info->work);
 }
 
-static int spu_gov_govern(struct cpufreq_policy *policy, unsigned int event)
+static int spu_gov_start(struct cpufreq_policy *policy)
 {
 	unsigned int cpu = policy->cpu;
-	struct spu_gov_info_struct *info, *affected_info;
+	struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu);
+	struct spu_gov_info_struct *affected_info;
 	int i;
-	int ret = 0;
 
-	info = &per_cpu(spu_gov_info, cpu);
-
-	switch (event) {
-	case CPUFREQ_GOV_START:
-		if (!cpu_online(cpu)) {
-			printk(KERN_ERR "cpu %d is not online\n", cpu);
-			ret = -EINVAL;
-			break;
-		}
+	if (!cpu_online(cpu)) {
+		printk(KERN_ERR "cpu %d is not online\n", cpu);
+		return -EINVAL;
+	}
 
-		if (!policy->cur) {
-			printk(KERN_ERR "no cpu specified in policy\n");
-			ret = -EINVAL;
-			break;
-		}
+	if (!policy->cur) {
+		printk(KERN_ERR "no cpu specified in policy\n");
+		return -EINVAL;
+	}
 
-		/* initialize spu_gov_info for all affected cpus */
-		for_each_cpu(i, policy->cpus) {
-			affected_info = &per_cpu(spu_gov_info, i);
-			affected_info->policy = policy;
-		}
+	/* initialize spu_gov_info for all affected cpus */
+	for_each_cpu(i, policy->cpus) {
+		affected_info = &per_cpu(spu_gov_info, i);
+		affected_info->policy = policy;
+	}
 
-		info->poll_int = POLL_TIME;
+	info->poll_int = POLL_TIME;
 
-		/* setup timer */
-		spu_gov_init_work(info);
+	/* setup timer */
+	spu_gov_init_work(info);
 
-		break;
+	return 0;
+}
 
-	case CPUFREQ_GOV_STOP:
-		/* cancel timer */
-		spu_gov_cancel_work(info);
+static void spu_gov_stop(struct cpufreq_policy *policy)
+{
+	unsigned int cpu = policy->cpu;
+	struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu);
+	int i;
 
-		/* clean spu_gov_info for all affected cpus */
-		for_each_cpu (i, policy->cpus) {
-			info = &per_cpu(spu_gov_info, i);
-			info->policy = NULL;
-		}
+	/* cancel timer */
+	spu_gov_cancel_work(info);
 
-		break;
+	/* clean spu_gov_info for all affected cpus */
+	for_each_cpu (i, policy->cpus) {
+		info = &per_cpu(spu_gov_info, i);
+		info->policy = NULL;
 	}
-
-	return ret;
 }
 
 static struct cpufreq_governor spu_governor = {
 	.name = "spudemand",
-	.governor = spu_gov_govern,
+	.start = spu_gov_start,
+	.stop = spu_gov_stop,
 	.owner = THIS_MODULE,
 };
 
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ff75d70f7285..f9af6461521a 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -223,7 +223,6 @@ static int axon_ram_probe(struct platform_device *device)
 	bank->disk->first_minor = azfs_minor;
 	bank->disk->fops = &axon_ram_devops;
 	bank->disk->private_data = bank;
-	bank->disk->driverfs_dev = &device->dev;
 
 	sprintf(bank->disk->disk_name, "%s%d",
 			AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
@@ -238,7 +237,7 @@ static int axon_ram_probe(struct platform_device *device)
 	set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT);
 	blk_queue_make_request(bank->disk->queue, axon_ram_make_request);
 	blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
-	add_disk(bank->disk);
+	device_add_disk(&device->dev, bank->disk);
 
 	bank->irq_id = irq_of_parse_and_map(device->dev.of_node, 0);
 	if (bank->irq_id == NO_IRQ) {
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a8c259059adf..9e607bf2d640 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -72,6 +72,7 @@ config S390
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_KCOV
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK
@@ -163,6 +164,7 @@ config S390
 	select NO_BOOTMEM
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
+	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select TTY
 	select VIRT_CPU_ACCOUNTING
@@ -477,6 +479,9 @@ config SCHED_MC
 config SCHED_BOOK
 	def_bool n
 
+config SCHED_DRAWER
+	def_bool n
+
 config SCHED_TOPOLOGY
 	def_bool y
 	prompt "Topology scheduler support"
@@ -484,6 +489,7 @@ config SCHED_TOPOLOGY
 	select SCHED_SMT
 	select SCHED_MC
 	select SCHED_BOOK
+	select SCHED_DRAWER
 	help
 	  Topology scheduler support improves the CPU scheduler's decision
 	  making when dealing with machines that have multi-threading,
@@ -605,16 +611,6 @@ config PCI_NR_FUNCTIONS
 	  This allows you to specify the maximum number of PCI functions which
 	  this kernel will support.
 
-config PCI_NR_MSI
-	int "Maximum number of MSI interrupts (64-32768)"
-	range 64 32768
-	default "256"
-	help
-	  This defines the number of virtual interrupts the kernel will
-	  provide for MSI interrupts. If you configure your system to have
-	  too few drivers will fail to allocate MSI interrupts for all
-	  PCI devices.
-
 source "drivers/pci/Kconfig"
 
 endif	# PCI
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 1dd210347e12..98ec652cc332 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -4,6 +4,8 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
+KCOV_INSTRUMENT := n
+
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
 targets += misc.o piggy.o sizes.h head.o
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index d5ec71b2ed02..889ea3450210 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -678,6 +678,7 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
+CONFIG_CRYPTO_CRC32_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=y
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
 CONFIG_X509_CERTIFICATE_PARSER=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index f46a35115d2d..1bcfd764910a 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -616,6 +616,7 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
+CONFIG_CRYPTO_CRC32_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=y
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
 CONFIG_X509_CERTIFICATE_PARSER=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index ba0f2a58b8cd..13ff090139c8 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -615,6 +615,7 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
+CONFIG_CRYPTO_CRC32_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=y
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
 CONFIG_X509_CERTIFICATE_PARSER=m
diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile
index 7f0b7cda6259..d1033de4c4ee 100644
--- a/arch/s390/crypto/Makefile
+++ b/arch/s390/crypto/Makefile
@@ -9,3 +9,6 @@ obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o
 obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o
 obj-$(CONFIG_S390_PRNG) += prng.o
 obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o
+obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o
+
+crc32-vx_s390-y := crc32-vx.o crc32le-vx.o crc32be-vx.o
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 7554a8bb2adc..2ea18b050309 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -22,6 +22,7 @@
 
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
@@ -44,7 +45,7 @@ struct s390_aes_ctx {
 	long dec;
 	int key_len;
 	union {
-		struct crypto_blkcipher *blk;
+		struct crypto_skcipher *blk;
 		struct crypto_cipher *cip;
 	} fallback;
 };
@@ -63,7 +64,7 @@ struct s390_xts_ctx {
 	long enc;
 	long dec;
 	int key_len;
-	struct crypto_blkcipher *fallback;
+	struct crypto_skcipher *fallback;
 };
 
 /*
@@ -237,16 +238,16 @@ static int setkey_fallback_blk(struct crypto_tfm *tfm, const u8 *key,
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 	unsigned int ret;
 
-	sctx->fallback.blk->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	sctx->fallback.blk->base.crt_flags |= (tfm->crt_flags &
-			CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(sctx->fallback.blk, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(sctx->fallback.blk, tfm->crt_flags &
+						      CRYPTO_TFM_REQ_MASK);
+
+	ret = crypto_skcipher_setkey(sctx->fallback.blk, key, len);
+
+	tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
+	tfm->crt_flags |= crypto_skcipher_get_flags(sctx->fallback.blk) &
+			  CRYPTO_TFM_RES_MASK;
 
-	ret = crypto_blkcipher_setkey(sctx->fallback.blk, key, len);
-	if (ret) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (sctx->fallback.blk->base.crt_flags &
-				CRYPTO_TFM_RES_MASK);
-	}
 	return ret;
 }
 
@@ -255,15 +256,17 @@ static int fallback_blk_dec(struct blkcipher_desc *desc,
 		unsigned int nbytes)
 {
 	unsigned int ret;
-	struct crypto_blkcipher *tfm;
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
 
-	tfm = desc->tfm;
-	desc->tfm = sctx->fallback.blk;
+	skcipher_request_set_tfm(req, sctx->fallback.blk);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_decrypt_iv(desc, dst, src, nbytes);
+	ret = crypto_skcipher_decrypt(req);
 
-	desc->tfm = tfm;
+	skcipher_request_zero(req);
 	return ret;
 }
 
@@ -272,15 +275,15 @@ static int fallback_blk_enc(struct blkcipher_desc *desc,
 		unsigned int nbytes)
 {
 	unsigned int ret;
-	struct crypto_blkcipher *tfm;
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
 
-	tfm = desc->tfm;
-	desc->tfm = sctx->fallback.blk;
+	skcipher_request_set_tfm(req, sctx->fallback.blk);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_encrypt_iv(desc, dst, src, nbytes);
-
-	desc->tfm = tfm;
+	ret = crypto_skcipher_encrypt(req);
 	return ret;
 }
 
@@ -370,8 +373,9 @@ static int fallback_init_blk(struct crypto_tfm *tfm)
 	const char *name = tfm->__crt_alg->cra_name;
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 
-	sctx->fallback.blk = crypto_alloc_blkcipher(name, 0,
-			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+	sctx->fallback.blk = crypto_alloc_skcipher(name, 0,
+						   CRYPTO_ALG_ASYNC |
+						   CRYPTO_ALG_NEED_FALLBACK);
 
 	if (IS_ERR(sctx->fallback.blk)) {
 		pr_err("Allocating AES fallback algorithm %s failed\n",
@@ -386,8 +390,7 @@ static void fallback_exit_blk(struct crypto_tfm *tfm)
 {
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_blkcipher(sctx->fallback.blk);
-	sctx->fallback.blk = NULL;
+	crypto_free_skcipher(sctx->fallback.blk);
 }
 
 static struct crypto_alg ecb_aes_alg = {
@@ -536,16 +539,16 @@ static int xts_fallback_setkey(struct crypto_tfm *tfm, const u8 *key,
 	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
 	unsigned int ret;
 
-	xts_ctx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	xts_ctx->fallback->base.crt_flags |= (tfm->crt_flags &
-			CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(xts_ctx->fallback, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(xts_ctx->fallback, tfm->crt_flags &
+						     CRYPTO_TFM_REQ_MASK);
+
+	ret = crypto_skcipher_setkey(xts_ctx->fallback, key, len);
+
+	tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
+	tfm->crt_flags |= crypto_skcipher_get_flags(xts_ctx->fallback) &
+			  CRYPTO_TFM_RES_MASK;
 
-	ret = crypto_blkcipher_setkey(xts_ctx->fallback, key, len);
-	if (ret) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (xts_ctx->fallback->base.crt_flags &
-				CRYPTO_TFM_RES_MASK);
-	}
 	return ret;
 }
 
@@ -553,16 +556,18 @@ static int xts_fallback_decrypt(struct blkcipher_desc *desc,
 		struct scatterlist *dst, struct scatterlist *src,
 		unsigned int nbytes)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct crypto_blkcipher *tfm;
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
 	unsigned int ret;
 
-	tfm = desc->tfm;
-	desc->tfm = xts_ctx->fallback;
+	skcipher_request_set_tfm(req, xts_ctx->fallback);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_decrypt_iv(desc, dst, src, nbytes);
+	ret = crypto_skcipher_decrypt(req);
 
-	desc->tfm = tfm;
+	skcipher_request_zero(req);
 	return ret;
 }
 
@@ -570,16 +575,18 @@ static int xts_fallback_encrypt(struct blkcipher_desc *desc,
 		struct scatterlist *dst, struct scatterlist *src,
 		unsigned int nbytes)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct crypto_blkcipher *tfm;
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
 	unsigned int ret;
 
-	tfm = desc->tfm;
-	desc->tfm = xts_ctx->fallback;
+	skcipher_request_set_tfm(req, xts_ctx->fallback);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_encrypt_iv(desc, dst, src, nbytes);
+	ret = crypto_skcipher_encrypt(req);
 
-	desc->tfm = tfm;
+	skcipher_request_zero(req);
 	return ret;
 }
 
@@ -700,8 +707,9 @@ static int xts_fallback_init(struct crypto_tfm *tfm)
 	const char *name = tfm->__crt_alg->cra_name;
 	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
 
-	xts_ctx->fallback = crypto_alloc_blkcipher(name, 0,
-			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+	xts_ctx->fallback = crypto_alloc_skcipher(name, 0,
+						  CRYPTO_ALG_ASYNC |
+						  CRYPTO_ALG_NEED_FALLBACK);
 
 	if (IS_ERR(xts_ctx->fallback)) {
 		pr_err("Allocating XTS fallback algorithm %s failed\n",
@@ -715,8 +723,7 @@ static void xts_fallback_exit(struct crypto_tfm *tfm)
 {
 	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_blkcipher(xts_ctx->fallback);
-	xts_ctx->fallback = NULL;
+	crypto_free_skcipher(xts_ctx->fallback);
 }
 
 static struct crypto_alg xts_aes_alg = {
diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c
new file mode 100644
index 000000000000..577ae1d4ae89
--- /dev/null
+++ b/arch/s390/crypto/crc32-vx.c
@@ -0,0 +1,310 @@
+/*
+ * Crypto-API module for CRC-32 algorithms implemented with the
+ * z/Architecture Vector Extension Facility.
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+#define KMSG_COMPONENT	"crc32-vx"
+#define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+#include <asm/fpu/api.h>
+
+
+#define CRC32_BLOCK_SIZE	1
+#define CRC32_DIGEST_SIZE	4
+
+#define VX_MIN_LEN		64
+#define VX_ALIGNMENT		16L
+#define VX_ALIGN_MASK		(VX_ALIGNMENT - 1)
+
+struct crc_ctx {
+	u32 key;
+};
+
+struct crc_desc_ctx {
+	u32 crc;
+};
+
+/* Prototypes for functions in assembly files */
+u32 crc32_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
+u32 crc32_be_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
+u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
+
+/*
+ * DEFINE_CRC32_VX() - Define a CRC-32 function using the vector extension
+ *
+ * Creates a function to perform a particular CRC-32 computation. Depending
+ * on the message buffer, the hardware-accelerated or software implementation
+ * is used.   Note that the message buffer is aligned to improve fetch
+ * operations of VECTOR LOAD MULTIPLE instructions.
+ *
+ */
+#define DEFINE_CRC32_VX(___fname, ___crc32_vx, ___crc32_sw)		    \
+	static u32 __pure ___fname(u32 crc,				    \
+				unsigned char const *data, size_t datalen)  \
+	{								    \
+		struct kernel_fpu vxstate;				    \
+		unsigned long prealign, aligned, remaining;		    \
+									    \
+		if ((unsigned long)data & VX_ALIGN_MASK) {		    \
+			prealign = VX_ALIGNMENT -			    \
+				  ((unsigned long)data & VX_ALIGN_MASK);    \
+			datalen -= prealign;				    \
+			crc = ___crc32_sw(crc, data, prealign);		    \
+			data = (void *)((unsigned long)data + prealign);    \
+		}							    \
+									    \
+		if (datalen < VX_MIN_LEN)				    \
+			return ___crc32_sw(crc, data, datalen);		    \
+									    \
+		aligned = datalen & ~VX_ALIGN_MASK;			    \
+		remaining = datalen & VX_ALIGN_MASK;			    \
+									    \
+		kernel_fpu_begin(&vxstate, KERNEL_VXR_LOW);		    \
+		crc = ___crc32_vx(crc, data, aligned);			    \
+		kernel_fpu_end(&vxstate);				    \
+									    \
+		if (remaining)						    \
+			crc = ___crc32_sw(crc, data + aligned, remaining);  \
+									    \
+		return crc;						    \
+	}
+
+DEFINE_CRC32_VX(crc32_le_vx, crc32_le_vgfm_16, crc32_le)
+DEFINE_CRC32_VX(crc32_be_vx, crc32_be_vgfm_16, crc32_be)
+DEFINE_CRC32_VX(crc32c_le_vx, crc32c_le_vgfm_16, __crc32c_le)
+
+
+static int crc32_vx_cra_init_zero(struct crypto_tfm *tfm)
+{
+	struct crc_ctx *mctx = crypto_tfm_ctx(tfm);
+
+	mctx->key = 0;
+	return 0;
+}
+
+static int crc32_vx_cra_init_invert(struct crypto_tfm *tfm)
+{
+	struct crc_ctx *mctx = crypto_tfm_ctx(tfm);
+
+	mctx->key = ~0;
+	return 0;
+}
+
+static int crc32_vx_init(struct shash_desc *desc)
+{
+	struct crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
+	struct crc_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = mctx->key;
+	return 0;
+}
+
+static int crc32_vx_setkey(struct crypto_shash *tfm, const u8 *newkey,
+			   unsigned int newkeylen)
+{
+	struct crc_ctx *mctx = crypto_shash_ctx(tfm);
+
+	if (newkeylen != sizeof(mctx->key)) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	mctx->key = le32_to_cpu(*(__le32 *)newkey);
+	return 0;
+}
+
+static int crc32be_vx_setkey(struct crypto_shash *tfm, const u8 *newkey,
+			     unsigned int newkeylen)
+{
+	struct crc_ctx *mctx = crypto_shash_ctx(tfm);
+
+	if (newkeylen != sizeof(mctx->key)) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	mctx->key = be32_to_cpu(*(__be32 *)newkey);
+	return 0;
+}
+
+static int crc32le_vx_final(struct shash_desc *desc, u8 *out)
+{
+	struct crc_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*(__le32 *)out = cpu_to_le32p(&ctx->crc);
+	return 0;
+}
+
+static int crc32be_vx_final(struct shash_desc *desc, u8 *out)
+{
+	struct crc_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*(__be32 *)out = cpu_to_be32p(&ctx->crc);
+	return 0;
+}
+
+static int crc32c_vx_final(struct shash_desc *desc, u8 *out)
+{
+	struct crc_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	/*
+	 * Perform a final XOR with 0xFFFFFFFF to be in sync
+	 * with the generic crc32c shash implementation.
+	 */
+	*(__le32 *)out = ~cpu_to_le32p(&ctx->crc);
+	return 0;
+}
+
+static int __crc32le_vx_finup(u32 *crc, const u8 *data, unsigned int len,
+			      u8 *out)
+{
+	*(__le32 *)out = cpu_to_le32(crc32_le_vx(*crc, data, len));
+	return 0;
+}
+
+static int __crc32be_vx_finup(u32 *crc, const u8 *data, unsigned int len,
+			      u8 *out)
+{
+	*(__be32 *)out = cpu_to_be32(crc32_be_vx(*crc, data, len));
+	return 0;
+}
+
+static int __crc32c_vx_finup(u32 *crc, const u8 *data, unsigned int len,
+			     u8 *out)
+{
+	/*
+	 * Perform a final XOR with 0xFFFFFFFF to be in sync
+	 * with the generic crc32c shash implementation.
+	 */
+	*(__le32 *)out = ~cpu_to_le32(crc32c_le_vx(*crc, data, len));
+	return 0;
+}
+
+
+#define CRC32_VX_FINUP(alg, func)					      \
+	static int alg ## _vx_finup(struct shash_desc *desc, const u8 *data,  \
+				   unsigned int datalen, u8 *out)	      \
+	{								      \
+		return __ ## alg ## _vx_finup(shash_desc_ctx(desc),	      \
+					      data, datalen, out);	      \
+	}
+
+CRC32_VX_FINUP(crc32le, crc32_le_vx)
+CRC32_VX_FINUP(crc32be, crc32_be_vx)
+CRC32_VX_FINUP(crc32c, crc32c_le_vx)
+
+#define CRC32_VX_DIGEST(alg, func)					      \
+	static int alg ## _vx_digest(struct shash_desc *desc, const u8 *data, \
+				     unsigned int len, u8 *out)		      \
+	{								      \
+		return __ ## alg ## _vx_finup(crypto_shash_ctx(desc->tfm),    \
+					      data, len, out);		      \
+	}
+
+CRC32_VX_DIGEST(crc32le, crc32_le_vx)
+CRC32_VX_DIGEST(crc32be, crc32_be_vx)
+CRC32_VX_DIGEST(crc32c, crc32c_le_vx)
+
+#define CRC32_VX_UPDATE(alg, func)					      \
+	static int alg ## _vx_update(struct shash_desc *desc, const u8 *data, \
+				     unsigned int datalen)		      \
+	{								      \
+		struct crc_desc_ctx *ctx = shash_desc_ctx(desc);	      \
+		ctx->crc = func(ctx->crc, data, datalen);		      \
+		return 0;						      \
+	}
+
+CRC32_VX_UPDATE(crc32le, crc32_le_vx)
+CRC32_VX_UPDATE(crc32be, crc32_be_vx)
+CRC32_VX_UPDATE(crc32c, crc32c_le_vx)
+
+
+static struct shash_alg crc32_vx_algs[] = {
+	/* CRC-32 LE */
+	{
+		.init		=	crc32_vx_init,
+		.setkey		=	crc32_vx_setkey,
+		.update		=	crc32le_vx_update,
+		.final		=	crc32le_vx_final,
+		.finup		=	crc32le_vx_finup,
+		.digest		=	crc32le_vx_digest,
+		.descsize	=	sizeof(struct crc_desc_ctx),
+		.digestsize	=	CRC32_DIGEST_SIZE,
+		.base		=	{
+			.cra_name	 = "crc32",
+			.cra_driver_name = "crc32-vx",
+			.cra_priority	 = 200,
+			.cra_blocksize	 = CRC32_BLOCK_SIZE,
+			.cra_ctxsize	 = sizeof(struct crc_ctx),
+			.cra_module	 = THIS_MODULE,
+			.cra_init	 = crc32_vx_cra_init_zero,
+		},
+	},
+	/* CRC-32 BE */
+	{
+		.init		=	crc32_vx_init,
+		.setkey		=	crc32be_vx_setkey,
+		.update		=	crc32be_vx_update,
+		.final		=	crc32be_vx_final,
+		.finup		=	crc32be_vx_finup,
+		.digest		=	crc32be_vx_digest,
+		.descsize	=	sizeof(struct crc_desc_ctx),
+		.digestsize	=	CRC32_DIGEST_SIZE,
+		.base		=	{
+			.cra_name	 = "crc32be",
+			.cra_driver_name = "crc32be-vx",
+			.cra_priority	 = 200,
+			.cra_blocksize	 = CRC32_BLOCK_SIZE,
+			.cra_ctxsize	 = sizeof(struct crc_ctx),
+			.cra_module	 = THIS_MODULE,
+			.cra_init	 = crc32_vx_cra_init_zero,
+		},
+	},
+	/* CRC-32C LE */
+	{
+		.init		=	crc32_vx_init,
+		.setkey		=	crc32_vx_setkey,
+		.update		=	crc32c_vx_update,
+		.final		=	crc32c_vx_final,
+		.finup		=	crc32c_vx_finup,
+		.digest		=	crc32c_vx_digest,
+		.descsize	=	sizeof(struct crc_desc_ctx),
+		.digestsize	=	CRC32_DIGEST_SIZE,
+		.base		=	{
+			.cra_name	 = "crc32c",
+			.cra_driver_name = "crc32c-vx",
+			.cra_priority	 = 200,
+			.cra_blocksize	 = CRC32_BLOCK_SIZE,
+			.cra_ctxsize	 = sizeof(struct crc_ctx),
+			.cra_module	 = THIS_MODULE,
+			.cra_init	 = crc32_vx_cra_init_invert,
+		},
+	},
+};
+
+
+static int __init crc_vx_mod_init(void)
+{
+	return crypto_register_shashes(crc32_vx_algs,
+				       ARRAY_SIZE(crc32_vx_algs));
+}
+
+static void __exit crc_vx_mod_exit(void)
+{
+	crypto_unregister_shashes(crc32_vx_algs, ARRAY_SIZE(crc32_vx_algs));
+}
+
+module_cpu_feature_match(VXRS, crc_vx_mod_init);
+module_exit(crc_vx_mod_exit);
+
+MODULE_AUTHOR("Hendrik Brueckner <brueckner@linux.vnet.ibm.com>");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-vx");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-vx");
diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S
new file mode 100644
index 000000000000..8013989cd2e5
--- /dev/null
+++ b/arch/s390/crypto/crc32be-vx.S
@@ -0,0 +1,207 @@
+/*
+ * Hardware-accelerated CRC-32 variants for Linux on z Systems
+ *
+ * Use the z/Architecture Vector Extension Facility to accelerate the
+ * computing of CRC-32 checksums.
+ *
+ * This CRC-32 implementation algorithm processes the most-significant
+ * bit first (BE).
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/vx-insn.h>
+
+/* Vector register range containing CRC-32 constants */
+#define CONST_R1R2		%v9
+#define CONST_R3R4		%v10
+#define CONST_R5		%v11
+#define CONST_R6		%v12
+#define CONST_RU_POLY		%v13
+#define CONST_CRC_POLY		%v14
+
+.data
+.align 8
+
+/*
+ * The CRC-32 constant block contains reduction constants to fold and
+ * process particular chunks of the input data stream in parallel.
+ *
+ * For the CRC-32 variants, the constants are precomputed according to
+ * these defintions:
+ *
+ *	R1 = x4*128+64 mod P(x)
+ *	R2 = x4*128    mod P(x)
+ *	R3 = x128+64   mod P(x)
+ *	R4 = x128      mod P(x)
+ *	R5 = x96       mod P(x)
+ *	R6 = x64       mod P(x)
+ *
+ *	Barret reduction constant, u, is defined as floor(x**64 / P(x)).
+ *
+ *	where P(x) is the polynomial in the normal domain and the P'(x) is the
+ *	polynomial in the reversed (bitreflected) domain.
+ *
+ * Note that the constant definitions below are extended in order to compute
+ * intermediate results with a single VECTOR GALOIS FIELD MULTIPLY instruction.
+ * The righmost doubleword can be 0 to prevent contribution to the result or
+ * can be multiplied by 1 to perform an XOR without the need for a separate
+ * VECTOR EXCLUSIVE OR instruction.
+ *
+ * CRC-32 (IEEE 802.3 Ethernet, ...) polynomials:
+ *
+ *	P(x)  = 0x04C11DB7
+ *	P'(x) = 0xEDB88320
+ */
+
+.Lconstants_CRC_32_BE:
+	.quad		0x08833794c, 0x0e6228b11	# R1, R2
+	.quad		0x0c5b9cd4c, 0x0e8a45605	# R3, R4
+	.quad		0x0f200aa66, 1 << 32		# R5, x32
+	.quad		0x0490d678d, 1			# R6, 1
+	.quad		0x104d101df, 0			# u
+	.quad		0x104C11DB7, 0			# P(x)
+
+.previous
+
+.text
+/*
+ * The CRC-32 function(s) use these calling conventions:
+ *
+ * Parameters:
+ *
+ *	%r2:	Initial CRC value, typically ~0; and final CRC (return) value.
+ *	%r3:	Input buffer pointer, performance might be improved if the
+ *		buffer is on a doubleword boundary.
+ *	%r4:	Length of the buffer, must be 64 bytes or greater.
+ *
+ * Register usage:
+ *
+ *	%r5:	CRC-32 constant pool base pointer.
+ *	V0:	Initial CRC value and intermediate constants and results.
+ *	V1..V4:	Data for CRC computation.
+ *	V5..V8:	Next data chunks that are fetched from the input buffer.
+ *
+ *	V9..V14: CRC-32 constants.
+ */
+ENTRY(crc32_be_vgfm_16)
+	/* Load CRC-32 constants */
+	larl	%r5,.Lconstants_CRC_32_BE
+	VLM	CONST_R1R2,CONST_CRC_POLY,0,%r5
+
+	/* Load the initial CRC value into the leftmost word of V0. */
+	VZERO	%v0
+	VLVGF	%v0,%r2,0
+
+	/* Load a 64-byte data chunk and XOR with CRC */
+	VLM	%v1,%v4,0,%r3		/* 64-bytes into V1..V4 */
+	VX	%v1,%v0,%v1		/* V1 ^= CRC */
+	aghi	%r3,64			/* BUF = BUF + 64 */
+	aghi	%r4,-64			/* LEN = LEN - 64 */
+
+	/* Check remaining buffer size and jump to proper folding method */
+	cghi	%r4,64
+	jl	.Lless_than_64bytes
+
+.Lfold_64bytes_loop:
+	/* Load the next 64-byte data chunk into V5 to V8 */
+	VLM	%v5,%v8,0,%r3
+
+	/*
+	 * Perform a GF(2) multiplication of the doublewords in V1 with
+	 * the reduction constants in V0.  The intermediate result is
+	 * then folded (accumulated) with the next data chunk in V5 and
+	 * stored in V1.  Repeat this step for the register contents
+	 * in V2, V3, and V4 respectively.
+	 */
+	VGFMAG	%v1,CONST_R1R2,%v1,%v5
+	VGFMAG	%v2,CONST_R1R2,%v2,%v6
+	VGFMAG	%v3,CONST_R1R2,%v3,%v7
+	VGFMAG	%v4,CONST_R1R2,%v4,%v8
+
+	/* Adjust buffer pointer and length for next loop */
+	aghi	%r3,64			/* BUF = BUF + 64 */
+	aghi	%r4,-64			/* LEN = LEN - 64 */
+
+	cghi	%r4,64
+	jnl	.Lfold_64bytes_loop
+
+.Lless_than_64bytes:
+	/* Fold V1 to V4 into a single 128-bit value in V1 */
+	VGFMAG	%v1,CONST_R3R4,%v1,%v2
+	VGFMAG	%v1,CONST_R3R4,%v1,%v3
+	VGFMAG	%v1,CONST_R3R4,%v1,%v4
+
+	/* Check whether to continue with 64-bit folding */
+	cghi	%r4,16
+	jl	.Lfinal_fold
+
+.Lfold_16bytes_loop:
+
+	VL	%v2,0,,%r3		/* Load next data chunk */
+	VGFMAG	%v1,CONST_R3R4,%v1,%v2	/* Fold next data chunk */
+
+	/* Adjust buffer pointer and size for folding next data chunk */
+	aghi	%r3,16
+	aghi	%r4,-16
+
+	/* Process remaining data chunks */
+	cghi	%r4,16
+	jnl	.Lfold_16bytes_loop
+
+.Lfinal_fold:
+	/*
+	 * The R5 constant is used to fold a 128-bit value into an 96-bit value
+	 * that is XORed with the next 96-bit input data chunk.  To use a single
+	 * VGFMG instruction, multiply the rightmost 64-bit with x^32 (1<<32) to
+	 * form an intermediate 96-bit value (with appended zeros) which is then
+	 * XORed with the intermediate reduction result.
+	 */
+	VGFMG	%v1,CONST_R5,%v1
+
+	/*
+	 * Further reduce the remaining 96-bit value to a 64-bit value using a
+	 * single VGFMG, the rightmost doubleword is multiplied with 0x1. The
+	 * intermediate result is then XORed with the product of the leftmost
+	 * doubleword with R6.	The result is a 64-bit value and is subject to
+	 * the Barret reduction.
+	 */
+	VGFMG	%v1,CONST_R6,%v1
+
+	/*
+	 * The input values to the Barret reduction are the degree-63 polynomial
+	 * in V1 (R(x)), degree-32 generator polynomial, and the reduction
+	 * constant u.	The Barret reduction result is the CRC value of R(x) mod
+	 * P(x).
+	 *
+	 * The Barret reduction algorithm is defined as:
+	 *
+	 *    1. T1(x) = floor( R(x) / x^32 ) GF2MUL u
+	 *    2. T2(x) = floor( T1(x) / x^32 ) GF2MUL P(x)
+	 *    3. C(x)  = R(x) XOR T2(x) mod x^32
+	 *
+	 * Note: To compensate the division by x^32, use the vector unpack
+	 * instruction to move the leftmost word into the leftmost doubleword
+	 * of the vector register.  The rightmost doubleword is multiplied
+	 * with zero to not contribute to the intermedate results.
+	 */
+
+	/* T1(x) = floor( R(x) / x^32 ) GF2MUL u */
+	VUPLLF	%v2,%v1
+	VGFMG	%v2,CONST_RU_POLY,%v2
+
+	/*
+	 * Compute the GF(2) product of the CRC polynomial in VO with T1(x) in
+	 * V2 and XOR the intermediate result, T2(x),  with the value in V1.
+	 * The final result is in the rightmost word of V2.
+	 */
+	VUPLLF	%v2,%v2
+	VGFMAG	%v2,CONST_CRC_POLY,%v2,%v1
+
+.Ldone:
+	VLGVF	%r2,%v2,3
+	br	%r14
+
+.previous
diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S
new file mode 100644
index 000000000000..17f2504c2633
--- /dev/null
+++ b/arch/s390/crypto/crc32le-vx.S
@@ -0,0 +1,268 @@
+/*
+ * Hardware-accelerated CRC-32 variants for Linux on z Systems
+ *
+ * Use the z/Architecture Vector Extension Facility to accelerate the
+ * computing of bitreflected CRC-32 checksums for IEEE 802.3 Ethernet
+ * and Castagnoli.
+ *
+ * This CRC-32 implementation algorithm is bitreflected and processes
+ * the least-significant bit first (Little-Endian).
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/vx-insn.h>
+
+/* Vector register range containing CRC-32 constants */
+#define CONST_PERM_LE2BE	%v9
+#define CONST_R2R1		%v10
+#define CONST_R4R3		%v11
+#define CONST_R5		%v12
+#define CONST_RU_POLY		%v13
+#define CONST_CRC_POLY		%v14
+
+.data
+.align 8
+
+/*
+ * The CRC-32 constant block contains reduction constants to fold and
+ * process particular chunks of the input data stream in parallel.
+ *
+ * For the CRC-32 variants, the constants are precomputed according to
+ * these definitions:
+ *
+ *	R1 = [(x4*128+32 mod P'(x) << 32)]' << 1
+ *	R2 = [(x4*128-32 mod P'(x) << 32)]' << 1
+ *	R3 = [(x128+32 mod P'(x) << 32)]'   << 1
+ *	R4 = [(x128-32 mod P'(x) << 32)]'   << 1
+ *	R5 = [(x64 mod P'(x) << 32)]'	    << 1
+ *	R6 = [(x32 mod P'(x) << 32)]'	    << 1
+ *
+ *	The bitreflected Barret reduction constant, u', is defined as
+ *	the bit reversal of floor(x**64 / P(x)).
+ *
+ *	where P(x) is the polynomial in the normal domain and the P'(x) is the
+ *	polynomial in the reversed (bitreflected) domain.
+ *
+ * CRC-32 (IEEE 802.3 Ethernet, ...) polynomials:
+ *
+ *	P(x)  = 0x04C11DB7
+ *	P'(x) = 0xEDB88320
+ *
+ * CRC-32C (Castagnoli) polynomials:
+ *
+ *	P(x)  = 0x1EDC6F41
+ *	P'(x) = 0x82F63B78
+ */
+
+.Lconstants_CRC_32_LE:
+	.octa		0x0F0E0D0C0B0A09080706050403020100	# BE->LE mask
+	.quad		0x1c6e41596, 0x154442bd4		# R2, R1
+	.quad		0x0ccaa009e, 0x1751997d0		# R4, R3
+	.octa		0x163cd6124				# R5
+	.octa		0x1F7011641				# u'
+	.octa		0x1DB710641				# P'(x) << 1
+
+.Lconstants_CRC_32C_LE:
+	.octa		0x0F0E0D0C0B0A09080706050403020100	# BE->LE mask
+	.quad		0x09e4addf8, 0x740eef02			# R2, R1
+	.quad		0x14cd00bd6, 0xf20c0dfe			# R4, R3
+	.octa		0x0dd45aab8				# R5
+	.octa		0x0dea713f1				# u'
+	.octa		0x105ec76f0				# P'(x) << 1
+
+.previous
+
+
+.text
+
+/*
+ * The CRC-32 functions use these calling conventions:
+ *
+ * Parameters:
+ *
+ *	%r2:	Initial CRC value, typically ~0; and final CRC (return) value.
+ *	%r3:	Input buffer pointer, performance might be improved if the
+ *		buffer is on a doubleword boundary.
+ *	%r4:	Length of the buffer, must be 64 bytes or greater.
+ *
+ * Register usage:
+ *
+ *	%r5:	CRC-32 constant pool base pointer.
+ *	V0:	Initial CRC value and intermediate constants and results.
+ *	V1..V4:	Data for CRC computation.
+ *	V5..V8:	Next data chunks that are fetched from the input buffer.
+ *	V9:	Constant for BE->LE conversion and shift operations
+ *
+ *	V10..V14: CRC-32 constants.
+ */
+
+ENTRY(crc32_le_vgfm_16)
+	larl	%r5,.Lconstants_CRC_32_LE
+	j	crc32_le_vgfm_generic
+
+ENTRY(crc32c_le_vgfm_16)
+	larl	%r5,.Lconstants_CRC_32C_LE
+	j	crc32_le_vgfm_generic
+
+
+crc32_le_vgfm_generic:
+	/* Load CRC-32 constants */
+	VLM	CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5
+
+	/*
+	 * Load the initial CRC value.
+	 *
+	 * The CRC value is loaded into the rightmost word of the
+	 * vector register and is later XORed with the LSB portion
+	 * of the loaded input data.
+	 */
+	VZERO	%v0			/* Clear V0 */
+	VLVGF	%v0,%r2,3		/* Load CRC into rightmost word */
+
+	/* Load a 64-byte data chunk and XOR with CRC */
+	VLM	%v1,%v4,0,%r3		/* 64-bytes into V1..V4 */
+	VPERM	%v1,%v1,%v1,CONST_PERM_LE2BE
+	VPERM	%v2,%v2,%v2,CONST_PERM_LE2BE
+	VPERM	%v3,%v3,%v3,CONST_PERM_LE2BE
+	VPERM	%v4,%v4,%v4,CONST_PERM_LE2BE
+
+	VX	%v1,%v0,%v1		/* V1 ^= CRC */
+	aghi	%r3,64			/* BUF = BUF + 64 */
+	aghi	%r4,-64			/* LEN = LEN - 64 */
+
+	cghi	%r4,64
+	jl	.Lless_than_64bytes
+
+.Lfold_64bytes_loop:
+	/* Load the next 64-byte data chunk into V5 to V8 */
+	VLM	%v5,%v8,0,%r3
+	VPERM	%v5,%v5,%v5,CONST_PERM_LE2BE
+	VPERM	%v6,%v6,%v6,CONST_PERM_LE2BE
+	VPERM	%v7,%v7,%v7,CONST_PERM_LE2BE
+	VPERM	%v8,%v8,%v8,CONST_PERM_LE2BE
+
+	/*
+	 * Perform a GF(2) multiplication of the doublewords in V1 with
+	 * the R1 and R2 reduction constants in V0.  The intermediate result
+	 * is then folded (accumulated) with the next data chunk in V5 and
+	 * stored in V1. Repeat this step for the register contents
+	 * in V2, V3, and V4 respectively.
+	 */
+	VGFMAG	%v1,CONST_R2R1,%v1,%v5
+	VGFMAG	%v2,CONST_R2R1,%v2,%v6
+	VGFMAG	%v3,CONST_R2R1,%v3,%v7
+	VGFMAG	%v4,CONST_R2R1,%v4,%v8
+
+	aghi	%r3,64			/* BUF = BUF + 64 */
+	aghi	%r4,-64			/* LEN = LEN - 64 */
+
+	cghi	%r4,64
+	jnl	.Lfold_64bytes_loop
+
+.Lless_than_64bytes:
+	/*
+	 * Fold V1 to V4 into a single 128-bit value in V1.  Multiply V1 with R3
+	 * and R4 and accumulating the next 128-bit chunk until a single 128-bit
+	 * value remains.
+	 */
+	VGFMAG	%v1,CONST_R4R3,%v1,%v2
+	VGFMAG	%v1,CONST_R4R3,%v1,%v3
+	VGFMAG	%v1,CONST_R4R3,%v1,%v4
+
+	cghi	%r4,16
+	jl	.Lfinal_fold
+
+.Lfold_16bytes_loop:
+
+	VL	%v2,0,,%r3		/* Load next data chunk */
+	VPERM	%v2,%v2,%v2,CONST_PERM_LE2BE
+	VGFMAG	%v1,CONST_R4R3,%v1,%v2	/* Fold next data chunk */
+
+	aghi	%r3,16
+	aghi	%r4,-16
+
+	cghi	%r4,16
+	jnl	.Lfold_16bytes_loop
+
+.Lfinal_fold:
+	/*
+	 * Set up a vector register for byte shifts.  The shift value must
+	 * be loaded in bits 1-4 in byte element 7 of a vector register.
+	 * Shift by 8 bytes: 0x40
+	 * Shift by 4 bytes: 0x20
+	 */
+	VLEIB	%v9,0x40,7
+
+	/*
+	 * Prepare V0 for the next GF(2) multiplication: shift V0 by 8 bytes
+	 * to move R4 into the rightmost doubleword and set the leftmost
+	 * doubleword to 0x1.
+	 */
+	VSRLB	%v0,CONST_R4R3,%v9
+	VLEIG	%v0,1,0
+
+	/*
+	 * Compute GF(2) product of V1 and V0.	The rightmost doubleword
+	 * of V1 is multiplied with R4.  The leftmost doubleword of V1 is
+	 * multiplied by 0x1 and is then XORed with rightmost product.
+	 * Implicitly, the intermediate leftmost product becomes padded
+	 */
+	VGFMG	%v1,%v0,%v1
+
+	/*
+	 * Now do the final 32-bit fold by multiplying the rightmost word
+	 * in V1 with R5 and XOR the result with the remaining bits in V1.
+	 *
+	 * To achieve this by a single VGFMAG, right shift V1 by a word
+	 * and store the result in V2 which is then accumulated.  Use the
+	 * vector unpack instruction to load the rightmost half of the
+	 * doubleword into the rightmost doubleword element of V1; the other
+	 * half is loaded in the leftmost doubleword.
+	 * The vector register with CONST_R5 contains the R5 constant in the
+	 * rightmost doubleword and the leftmost doubleword is zero to ignore
+	 * the leftmost product of V1.
+	 */
+	VLEIB	%v9,0x20,7		  /* Shift by words */
+	VSRLB	%v2,%v1,%v9		  /* Store remaining bits in V2 */
+	VUPLLF	%v1,%v1			  /* Split rightmost doubleword */
+	VGFMAG	%v1,CONST_R5,%v1,%v2	  /* V1 = (V1 * R5) XOR V2 */
+
+	/*
+	 * Apply a Barret reduction to compute the final 32-bit CRC value.
+	 *
+	 * The input values to the Barret reduction are the degree-63 polynomial
+	 * in V1 (R(x)), degree-32 generator polynomial, and the reduction
+	 * constant u.	The Barret reduction result is the CRC value of R(x) mod
+	 * P(x).
+	 *
+	 * The Barret reduction algorithm is defined as:
+	 *
+	 *    1. T1(x) = floor( R(x) / x^32 ) GF2MUL u
+	 *    2. T2(x) = floor( T1(x) / x^32 ) GF2MUL P(x)
+	 *    3. C(x)  = R(x) XOR T2(x) mod x^32
+	 *
+	 *  Note: The leftmost doubleword of vector register containing
+	 *  CONST_RU_POLY is zero and, thus, the intermediate GF(2) product
+	 *  is zero and does not contribute to the final result.
+	 */
+
+	/* T1(x) = floor( R(x) / x^32 ) GF2MUL u */
+	VUPLLF	%v2,%v1
+	VGFMG	%v2,CONST_RU_POLY,%v2
+
+	/*
+	 * Compute the GF(2) product of the CRC polynomial with T1(x) in
+	 * V2 and XOR the intermediate result, T2(x), with the value in V1.
+	 * The final result is stored in word element 2 of V2.
+	 */
+	VUPLLF	%v2,%v2
+	VGFMAG	%v2,CONST_CRC_POLY,%v2,%v1
+
+.Ldone:
+	VLGVF	%r2,%v2,2
+	br	%r14
+
+.previous
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 3f571ea89509..ccccebeeaaf6 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -225,12 +225,16 @@ CONFIG_CRYPTO_DEFLATE=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_USER_API_SKCIPHER=m
+CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_ZCRYPT=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_CRC32_S390=m
 CONFIG_CRC7=m
 # CONFIG_XZ_DEC_X86 is not set
 # CONFIG_XZ_DEC_POWERPC is not set
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 045035796ca7..67d43a0eabb4 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -337,25 +337,27 @@ static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr)
 
 /* Diagnose 204 functions */
 
-static inline int __diag204(unsigned long subcode, unsigned long size, void *addr)
+static inline int __diag204(unsigned long *subcode, unsigned long size, void *addr)
 {
-	register unsigned long _subcode asm("0") = subcode;
+	register unsigned long _subcode asm("0") = *subcode;
 	register unsigned long _size asm("1") = size;
 
 	asm volatile(
 		"	diag	%2,%0,0x204\n"
-		"0:\n"
+		"0:	nopr	%%r7\n"
 		EX_TABLE(0b,0b)
 		: "+d" (_subcode), "+d" (_size) : "d" (addr) : "memory");
-	if (_subcode)
-		return -1;
+	*subcode = _subcode;
 	return _size;
 }
 
 static int diag204(unsigned long subcode, unsigned long size, void *addr)
 {
 	diag_stat_inc(DIAG_STAT_X204);
-	return __diag204(subcode, size, addr);
+	size = __diag204(&subcode, size, addr);
+	if (subcode)
+		return -1;
+	return size;
 }
 
 /*
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index 44feac38ccfc..012919d9833b 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -70,7 +70,7 @@ static int diag2fc(int size, char* query, void *addr)
 	diag_stat_inc(DIAG_STAT_X2FC);
 	asm volatile(
 		"	diag    %0,%1,0x2fc\n"
-		"0:\n"
+		"0:	nopr	%%r7\n"
 		EX_TABLE(0b,0b)
 		: "=d" (residual_cnt), "+d" (rc) : "0" (&parm_list) : "memory");
 
diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h
index 22da3b34c655..05219a5e0b2f 100644
--- a/arch/s390/include/asm/cache.h
+++ b/arch/s390/include/asm/cache.h
@@ -13,9 +13,6 @@
 #define L1_CACHE_SHIFT     8
 #define NET_SKB_PAD	   32
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
-
-/* Read-only memory is marked before mark_rodata_ro() is called. */
-#define __ro_after_init __read_mostly
+#define __read_mostly __section(.data..read_mostly)
 
 #endif
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index d1e7b0a0feeb..f7ed88cc066e 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -320,7 +320,7 @@ struct cio_iplinfo {
 extern int cio_get_iplinfo(struct cio_iplinfo *iplinfo);
 
 /* Function from drivers/s390/cio/chsc.c */
-int chsc_sstpc(void *page, unsigned int op, u16 ctrl);
+int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta);
 int chsc_sstpi(void *page, void *result, size_t size);
 
 #endif
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 9dd04b9e9782..03516476127b 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -169,16 +169,27 @@ static inline int lcctl(u64 ctl)
 }
 
 /* Extract CPU counter */
-static inline int ecctr(u64 ctr, u64 *val)
+static inline int __ecctr(u64 ctr, u64 *content)
 {
-	register u64 content asm("4") = 0;
+	register u64 _content asm("4") = 0;
 	int cc;
 
 	asm volatile (
 		"	.insn	rre,0xb2e40000,%0,%2\n"
 		"	ipm	%1\n"
 		"	srl	%1,28\n"
-		: "=d" (content), "=d" (cc) : "d" (ctr) : "cc");
+		: "=d" (_content), "=d" (cc) : "d" (ctr) : "cc");
+	*content = _content;
+	return cc;
+}
+
+/* Extract CPU counter */
+static inline int ecctr(u64 ctr, u64 *val)
+{
+	u64 content;
+	int cc;
+
+	cc = __ecctr(ctr, &content);
 	if (!cc)
 		*val = content;
 	return cc;
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 5fac921c1c42..86cae09e076a 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -49,7 +49,7 @@ static inline void diag10_range(unsigned long start_pfn, unsigned long num_pfn)
 	diag_stat_inc(DIAG_STAT_X010);
 	asm volatile(
 		"0:	diag	%0,%1,0x10\n"
-		"1:\n"
+		"1:	nopr	%%r7\n"
 		EX_TABLE(0b, 1b)
 		EX_TABLE(1b, 1b)
 		: : "a" (start_addr), "a" (end_addr));
diff --git a/arch/s390/include/asm/etr.h b/arch/s390/include/asm/etr.h
deleted file mode 100644
index 105f90e63a0e..000000000000
--- a/arch/s390/include/asm/etr.h
+++ /dev/null
@@ -1,261 +0,0 @@
-/*
- *  Copyright IBM Corp. 2006
- *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- */
-#ifndef __S390_ETR_H
-#define __S390_ETR_H
-
-/* ETR attachment control register */
-struct etr_eacr {
-	unsigned int e0		: 1;	/* port 0 stepping control */
-	unsigned int e1		: 1;	/* port 1 stepping control */
-	unsigned int _pad0	: 5;	/* must be 00100 */
-	unsigned int dp		: 1;	/* data port control */
-	unsigned int p0		: 1;	/* port 0 change recognition control */
-	unsigned int p1		: 1;	/* port 1 change recognition control */
-	unsigned int _pad1	: 3;	/* must be 000 */
-	unsigned int ea		: 1;	/* ETR alert control */
-	unsigned int es		: 1;	/* ETR sync check control */
-	unsigned int sl		: 1;	/* switch to local control */
-} __attribute__ ((packed));
-
-/* Port state returned by steai */
-enum etr_psc {
-	etr_psc_operational = 0,
-	etr_psc_semi_operational = 1,
-	etr_psc_protocol_error =  4,
-	etr_psc_no_symbols = 8,
-	etr_psc_no_signal = 12,
-	etr_psc_pps_mode = 13
-};
-
-/* Logical port state returned by stetr */
-enum etr_lpsc {
-	etr_lpsc_operational_step = 0,
-	etr_lpsc_operational_alt = 1,
-	etr_lpsc_semi_operational = 2,
-	etr_lpsc_protocol_error =  4,
-	etr_lpsc_no_symbol_sync = 8,
-	etr_lpsc_no_signal = 12,
-	etr_lpsc_pps_mode = 13
-};
-
-/* ETR status words */
-struct etr_esw {
-	struct etr_eacr eacr;		/* attachment control register */
-	unsigned int y		: 1;	/* stepping mode */
-	unsigned int _pad0	: 5;	/* must be 00000 */
-	unsigned int p		: 1;	/* stepping port number */
-	unsigned int q		: 1;	/* data port number */
-	unsigned int psc0	: 4;	/* port 0 state code */
-	unsigned int psc1	: 4;	/* port 1 state code */
-} __attribute__ ((packed));
-
-/* Second level data register status word */
-struct etr_slsw {
-	unsigned int vv1	: 1;	/* copy of validity bit data frame 1 */
-	unsigned int vv2	: 1;	/* copy of validity bit data frame 2 */
-	unsigned int vv3	: 1;	/* copy of validity bit data frame 3 */
-	unsigned int vv4	: 1;	/* copy of validity bit data frame 4 */
-	unsigned int _pad0	: 19;	/* must by all zeroes */
-	unsigned int n		: 1;	/* EAF port number */
-	unsigned int v1		: 1;	/* validity bit ETR data frame 1 */
-	unsigned int v2		: 1;	/* validity bit ETR data frame 2 */
-	unsigned int v3		: 1;	/* validity bit ETR data frame 3 */
-	unsigned int v4		: 1;	/* validity bit ETR data frame 4 */
-	unsigned int _pad1	: 4;	/* must be 0000 */
-} __attribute__ ((packed));
-
-/* ETR data frames */
-struct etr_edf1 {
-	unsigned int u		: 1;	/* untuned bit */
-	unsigned int _pad0	: 1;	/* must be 0 */
-	unsigned int r		: 1;	/* service request bit */
-	unsigned int _pad1	: 4;	/* must be 0000 */
-	unsigned int a		: 1;	/* time adjustment bit */
-	unsigned int net_id	: 8;	/* ETR network id */
-	unsigned int etr_id	: 8;	/* id of ETR which sends data frames */
-	unsigned int etr_pn	: 8;	/* port number of ETR output port */
-} __attribute__ ((packed));
-
-struct etr_edf2 {
-	unsigned int etv	: 32;	/* Upper 32 bits of TOD. */
-} __attribute__ ((packed));
-
-struct etr_edf3 {
-	unsigned int rc		: 8;	/* failure reason code */
-	unsigned int _pad0	: 3;	/* must be 000 */
-	unsigned int c		: 1;	/* ETR coupled bit */
-	unsigned int tc		: 4;	/* ETR type code */
-	unsigned int blto	: 8;	/* biased local time offset */
-					/* (blto - 128) * 15 = minutes */
-	unsigned int buo	: 8;	/* biased utc offset */
-					/* (buo - 128) = leap seconds */
-} __attribute__ ((packed));
-
-struct etr_edf4 {
-	unsigned int ed		: 8;	/* ETS device dependent data */
-	unsigned int _pad0	: 1;	/* must be 0 */
-	unsigned int buc	: 5;	/* biased ut1 correction */
-					/* (buc - 16) * 0.1 seconds */
-	unsigned int em		: 6;	/* ETS error magnitude */
-	unsigned int dc		: 6;	/* ETS drift code */
-	unsigned int sc		: 6;	/* ETS steering code */
-} __attribute__ ((packed));
-
-/*
- * ETR attachment information block, two formats
- * format 1 has 4 reserved words with a size of 64 bytes
- * format 2 has 16 reserved words with a size of 96 bytes
- */
-struct etr_aib {
-	struct etr_esw esw;
-	struct etr_slsw slsw;
-	unsigned long long tsp;
-	struct etr_edf1 edf1;
-	struct etr_edf2 edf2;
-	struct etr_edf3 edf3;
-	struct etr_edf4 edf4;
-	unsigned int reserved[16];
-} __attribute__ ((packed,aligned(8)));
-
-/* ETR interruption parameter */
-struct etr_irq_parm {
-	unsigned int _pad0	: 8;
-	unsigned int pc0	: 1;	/* port 0 state change */
-	unsigned int pc1	: 1;	/* port 1 state change */
-	unsigned int _pad1	: 3;
-	unsigned int eai	: 1;	/* ETR alert indication */
-	unsigned int _pad2	: 18;
-} __attribute__ ((packed));
-
-/* Query TOD offset result */
-struct etr_ptff_qto {
-	unsigned long long physical_clock;
-	unsigned long long tod_offset;
-	unsigned long long logical_tod_offset;
-	unsigned long long tod_epoch_difference;
-} __attribute__ ((packed));
-
-/* Inline assembly helper functions */
-static inline int etr_setr(struct etr_eacr *ctrl)
-{
-	int rc = -EOPNOTSUPP;
-
-	asm volatile(
-		"	.insn	s,0xb2160000,%1\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (rc) : "Q" (*ctrl));
-	return rc;
-}
-
-/* Stores a format 1 aib with 64 bytes */
-static inline int etr_stetr(struct etr_aib *aib)
-{
-	int rc = -EOPNOTSUPP;
-
-	asm volatile(
-		"	.insn	s,0xb2170000,%1\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (rc) : "Q" (*aib));
-	return rc;
-}
-
-/* Stores a format 2 aib with 96 bytes for specified port */
-static inline int etr_steai(struct etr_aib *aib, unsigned int func)
-{
-	register unsigned int reg0 asm("0") = func;
-	int rc = -EOPNOTSUPP;
-
-	asm volatile(
-		"	.insn	s,0xb2b30000,%1\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (rc) : "Q" (*aib), "d" (reg0));
-	return rc;
-}
-
-/* Function codes for the steai instruction. */
-#define ETR_STEAI_STEPPING_PORT		0x10
-#define ETR_STEAI_ALTERNATE_PORT	0x11
-#define ETR_STEAI_PORT_0		0x12
-#define ETR_STEAI_PORT_1		0x13
-
-static inline int etr_ptff(void *ptff_block, unsigned int func)
-{
-	register unsigned int reg0 asm("0") = func;
-	register unsigned long reg1 asm("1") = (unsigned long) ptff_block;
-	int rc = -EOPNOTSUPP;
-
-	asm volatile(
-		"	.word	0x0104\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (rc), "=m" (ptff_block)
-		: "d" (reg0), "d" (reg1), "m" (ptff_block) : "cc");
-	return rc;
-}
-
-/* Function codes for the ptff instruction. */
-#define ETR_PTFF_QAF	0x00	/* query available functions */
-#define ETR_PTFF_QTO	0x01	/* query tod offset */
-#define ETR_PTFF_QSI	0x02	/* query steering information */
-#define ETR_PTFF_ATO	0x40	/* adjust tod offset */
-#define ETR_PTFF_STO	0x41	/* set tod offset */
-#define ETR_PTFF_SFS	0x42	/* set fine steering rate */
-#define ETR_PTFF_SGS	0x43	/* set gross steering rate */
-
-/* Functions needed by the machine check handler */
-int etr_switch_to_local(void);
-int etr_sync_check(void);
-void etr_queue_work(void);
-
-/* notifier for syncs */
-extern struct atomic_notifier_head s390_epoch_delta_notifier;
-
-/* STP interruption parameter */
-struct stp_irq_parm {
-	unsigned int _pad0	: 14;
-	unsigned int tsc	: 1;	/* Timing status change */
-	unsigned int lac	: 1;	/* Link availability change */
-	unsigned int tcpc	: 1;	/* Time control parameter change */
-	unsigned int _pad2	: 15;
-} __attribute__ ((packed));
-
-#define STP_OP_SYNC	1
-#define STP_OP_CTRL	3
-
-struct stp_sstpi {
-	unsigned int rsvd0;
-	unsigned int rsvd1 : 8;
-	unsigned int stratum : 8;
-	unsigned int vbits : 16;
-	unsigned int leaps : 16;
-	unsigned int tmd : 4;
-	unsigned int ctn : 4;
-	unsigned int rsvd2 : 3;
-	unsigned int c : 1;
-	unsigned int tst : 4;
-	unsigned int tzo : 16;
-	unsigned int dsto : 16;
-	unsigned int ctrl : 16;
-	unsigned int rsvd3 : 16;
-	unsigned int tto;
-	unsigned int rsvd4;
-	unsigned int ctnid[3];
-	unsigned int rsvd5;
-	unsigned int todoff[4];
-	unsigned int rsvd6[48];
-} __attribute__ ((packed));
-
-/* Functions needed by the machine check handler */
-int stp_sync_check(void);
-int stp_island_check(void);
-void stp_queue_work(void);
-
-#endif /* __S390_ETR_H */
diff --git a/arch/s390/include/asm/fcx.h b/arch/s390/include/asm/fcx.h
index 7ecb92b469b6..04cb4b4bcc5f 100644
--- a/arch/s390/include/asm/fcx.h
+++ b/arch/s390/include/asm/fcx.h
@@ -6,7 +6,7 @@
  */
 
 #ifndef _ASM_S390_FCX_H
-#define _ASM_S390_FCX_H _ASM_S390_FCX_H
+#define _ASM_S390_FCX_H
 
 #include <linux/types.h>
 
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index 8ae236b0f80b..6aba6fc406ad 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -1,6 +1,41 @@
 /*
  * In-kernel FPU support functions
  *
+ *
+ * Consider these guidelines before using in-kernel FPU functions:
+ *
+ *  1. Use kernel_fpu_begin() and kernel_fpu_end() to enclose all in-kernel
+ *     use of floating-point or vector registers and instructions.
+ *
+ *  2. For kernel_fpu_begin(), specify the vector register range you want to
+ *     use with the KERNEL_VXR_* constants. Consider these usage guidelines:
+ *
+ *     a) If your function typically runs in process-context, use the lower
+ *	  half of the vector registers, for example, specify KERNEL_VXR_LOW.
+ *     b) If your function typically runs in soft-irq or hard-irq context,
+ *	  prefer using the upper half of the vector registers, for example,
+ *	  specify KERNEL_VXR_HIGH.
+ *
+ *     If you adhere to these guidelines, an interrupted process context
+ *     does not require to save and restore vector registers because of
+ *     disjoint register ranges.
+ *
+ *     Also note that the __kernel_fpu_begin()/__kernel_fpu_end() functions
+ *     includes logic to save and restore up to 16 vector registers at once.
+ *
+ *  3. You can nest kernel_fpu_begin()/kernel_fpu_end() by using different
+ *     struct kernel_fpu states.  Vector registers that are in use by outer
+ *     levels are saved and restored.  You can minimize the save and restore
+ *     effort by choosing disjoint vector register ranges.
+ *
+ *  5. To use vector floating-point instructions, specify the KERNEL_FPC
+ *     flag to save and restore floating-point controls in addition to any
+ *     vector register range.
+ *
+ *  6. To use floating-point registers and instructions only, specify the
+ *     KERNEL_FPR flag.  This flag triggers a save and restore of vector
+ *     registers V0 to V15 and floating-point controls.
+ *
  * Copyright IBM Corp. 2015
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
@@ -8,6 +43,8 @@
 #ifndef _ASM_S390_FPU_API_H
 #define _ASM_S390_FPU_API_H
 
+#include <linux/preempt.h>
+
 void save_fpu_regs(void);
 
 static inline int test_fp_ctl(u32 fpc)
@@ -27,4 +64,42 @@ static inline int test_fp_ctl(u32 fpc)
 	return rc;
 }
 
+#define KERNEL_VXR_V0V7		1
+#define KERNEL_VXR_V8V15	2
+#define KERNEL_VXR_V16V23	4
+#define KERNEL_VXR_V24V31	8
+#define KERNEL_FPR		16
+#define KERNEL_FPC		256
+
+#define KERNEL_VXR_LOW		(KERNEL_VXR_V0V7|KERNEL_VXR_V8V15)
+#define KERNEL_VXR_MID		(KERNEL_VXR_V8V15|KERNEL_VXR_V16V23)
+#define KERNEL_VXR_HIGH		(KERNEL_VXR_V16V23|KERNEL_VXR_V24V31)
+
+#define KERNEL_FPU_MASK		(KERNEL_VXR_LOW|KERNEL_VXR_HIGH|KERNEL_FPR)
+
+struct kernel_fpu;
+
+/*
+ * Note the functions below must be called with preemption disabled.
+ * Do not enable preemption before calling __kernel_fpu_end() to prevent
+ * an corruption of an existing kernel FPU state.
+ *
+ * Prefer using the kernel_fpu_begin()/kernel_fpu_end() pair of functions.
+ */
+void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags);
+void __kernel_fpu_end(struct kernel_fpu *state);
+
+
+static inline void kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
+{
+	preempt_disable();
+	__kernel_fpu_begin(state, flags);
+}
+
+static inline void kernel_fpu_end(struct kernel_fpu *state)
+{
+	__kernel_fpu_end(state);
+	preempt_enable();
+}
+
 #endif /* _ASM_S390_FPU_API_H */
diff --git a/arch/s390/include/asm/fpu/types.h b/arch/s390/include/asm/fpu/types.h
index fe937c9b6471..bce255ead72b 100644
--- a/arch/s390/include/asm/fpu/types.h
+++ b/arch/s390/include/asm/fpu/types.h
@@ -24,4 +24,14 @@ struct fpu {
 /* VX array structure for address operand constraints in inline assemblies */
 struct vx_array { __vector128 _[__NUM_VXRS]; };
 
+/* In-kernel FPU state structure */
+struct kernel_fpu {
+	u32	    mask;
+	u32	    fpc;
+	union {
+		freg_t fprs[__NUM_FPRS];
+		__vector128 vxrs[__NUM_VXRS];
+	};
+};
+
 #endif /* _ASM_S390_FPU_TYPES_H */
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index d9be7c0c1291..4c7fac75090e 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -41,7 +41,10 @@ static inline int prepare_hugepage_range(struct file *file,
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep)
 {
-	pte_val(*ptep) = _SEGMENT_ENTRY_EMPTY;
+	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
+		pte_val(*ptep) = _REGION3_ENTRY_EMPTY;
+	else
+		pte_val(*ptep) = _SEGMENT_ENTRY_EMPTY;
 }
 
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index 6fc44dca193e..4da22b2f0521 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -141,11 +141,11 @@ extern void setup_ipl(void);
  * DIAG 308 support
  */
 enum diag308_subcode  {
-	DIAG308_REL_HSA	= 2,
-	DIAG308_IPL	= 3,
-	DIAG308_DUMP	= 4,
-	DIAG308_SET	= 5,
-	DIAG308_STORE	= 6,
+	DIAG308_REL_HSA = 2,
+	DIAG308_LOAD_CLEAR = 3,
+	DIAG308_LOAD_NORMAL_DUMP = 4,
+	DIAG308_SET = 5,
+	DIAG308_STORE = 6,
 };
 
 enum diag308_ipl_type {
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index f97b055de76a..70c9bce766f5 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -7,11 +7,8 @@
 
 #define NR_IRQS_BASE	3
 
-#ifdef CONFIG_PCI_NR_MSI
-# define NR_IRQS	(NR_IRQS_BASE + CONFIG_PCI_NR_MSI)
-#else
-# define NR_IRQS	NR_IRQS_BASE
-#endif
+#define NR_IRQS	NR_IRQS_BASE
+#define NR_IRQS_LEGACY NR_IRQS_BASE
 
 /* External interruption codes */
 #define EXT_IRQ_INTERRUPT_KEY	0x0040
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 7f9fd5e3f1bf..9be198f5ee79 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -4,6 +4,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <linux/stringify.h>
 
 #define JUMP_LABEL_NOP_SIZE 6
 #define JUMP_LABEL_NOP_OFFSET 2
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index b47ad3b642cc..591e5a5279b0 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -43,9 +43,9 @@ typedef u16 kprobe_opcode_t;
 #define MAX_INSN_SIZE		0x0003
 #define MAX_STACK_SIZE		64
 #define MIN_STACK_SIZE(ADDR) (((MAX_STACK_SIZE) < \
-	(((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) \
+	(((unsigned long)task_stack_page(current)) + THREAD_SIZE - (ADDR))) \
 	? (MAX_STACK_SIZE) \
-	: (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR)))
+	: (((unsigned long)task_stack_page(current)) + THREAD_SIZE - (ADDR)))
 
 #define kretprobe_blacklist_size 0
 
diff --git a/arch/s390/include/asm/mathemu.h b/arch/s390/include/asm/mathemu.h
deleted file mode 100644
index 614dfaf47f71..000000000000
--- a/arch/s390/include/asm/mathemu.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *    IEEE floating point emulation.
- *
- *  S390 version
- *    Copyright IBM Corp. 1999
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- */
-
-#ifndef __MATHEMU__
-#define __MATHEMU__
-
-extern int math_emu_b3(__u8 *, struct pt_regs *);
-extern int math_emu_ed(__u8 *, struct pt_regs *);
-extern int math_emu_ldr(__u8 *);
-extern int math_emu_ler(__u8 *);
-extern int math_emu_std(__u8 *, struct pt_regs *);
-extern int math_emu_ld(__u8 *, struct pt_regs *);
-extern int math_emu_ste(__u8 *, struct pt_regs *);
-extern int math_emu_le(__u8 *, struct pt_regs *);
-extern int math_emu_lfpc(__u8 *, struct pt_regs *);
-extern int math_emu_stfpc(__u8 *, struct pt_regs *);
-extern int math_emu_srnm(__u8 *, struct pt_regs *);
-
-#endif                                 /* __MATHEMU__                      */
-
-
-
-
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 081b2ad99d73..18226437a832 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -6,7 +6,7 @@
 
 typedef struct {
 	cpumask_t cpu_attach_mask;
-	atomic_t attach_count;
+	atomic_t flush_count;
 	unsigned int flush_mm;
 	spinlock_t list_lock;
 	struct list_head pgtable_list;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index c837b79b455d..f77c638bf397 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -19,7 +19,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
 	INIT_LIST_HEAD(&mm->context.gmap_list);
 	cpumask_clear(&mm->context.cpu_attach_mask);
-	atomic_set(&mm->context.attach_count, 0);
+	atomic_set(&mm->context.flush_count, 0);
 	mm->context.flush_mm = 0;
 #ifdef CONFIG_PGSTE
 	mm->context.alloc_pgste = page_table_allocate_pgste;
@@ -90,15 +90,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	S390_lowcore.user_asce = next->context.asce;
 	if (prev == next)
 		return;
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
+	cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
+	cpumask_set_cpu(cpu, mm_cpumask(next));
 	/* Clear old ASCE by loading the kernel ASCE. */
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
-	atomic_inc(&next->context.attach_count);
-	atomic_dec(&prev->context.attach_count);
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+	cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
 }
 
 #define finish_arch_post_lock_switch finish_arch_post_lock_switch
@@ -110,10 +107,9 @@ static inline void finish_arch_post_lock_switch(void)
 	load_kernel_asce();
 	if (mm) {
 		preempt_disable();
-		while (atomic_read(&mm->context.attach_count) >> 16)
+		while (atomic_read(&mm->context.flush_count))
 			cpu_relax();
 
-		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
 		if (mm->context.flush_mm)
 			__tlb_flush_mm(mm);
 		preempt_enable();
@@ -128,7 +124,6 @@ static inline void activate_mm(struct mm_struct *prev,
                                struct mm_struct *next)
 {
 	switch_mm(prev, next, current);
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
 	set_user_asce(next);
 }
 
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 53eacbd4f09b..b2146c4119b2 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -21,6 +21,7 @@
 #define HPAGE_SIZE	(1UL << HPAGE_SHIFT)
 #define HPAGE_MASK	(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+#define HUGE_MAX_HSTATE		2
 
 #define ARCH_HAS_SETCLEAR_HUGE_PTE
 #define ARCH_HAS_HUGE_PTE_TYPE
@@ -30,11 +31,12 @@
 #include <asm/setup.h>
 #ifndef __ASSEMBLY__
 
+void __storage_key_init_range(unsigned long start, unsigned long end);
+
 static inline void storage_key_init_range(unsigned long start, unsigned long end)
 {
-#if PAGE_DEFAULT_KEY
-	__storage_key_init_range(start, end);
-#endif
+	if (PAGE_DEFAULT_KEY)
+		__storage_key_init_range(start, end);
 }
 
 #define clear_page(page)	memset((page), 0, PAGE_SIZE)
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 1f7ff85c5e4c..c64c0befd3f3 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -86,16 +86,4 @@ struct sf_raw_sample {
 	u8		    padding[];	  /* Padding to next multiple of 8 */
 } __packed;
 
-/* Perf hardware reserve and release functions */
-#ifdef CONFIG_PERF_EVENTS
-int perf_reserve_sampling(void);
-void perf_release_sampling(void);
-#else /* CONFIG_PERF_EVENTS */
-static inline int perf_reserve_sampling(void)
-{
-	return 0;
-}
-static inline void perf_release_sampling(void) {}
-#endif /* CONFIG_PERF_EVENTS */
-
 #endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 18d2beb89340..ea1533e07271 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -28,12 +28,33 @@
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
 #include <linux/radix-tree.h>
+#include <linux/atomic.h>
 #include <asm/bug.h>
 #include <asm/page.h>
 
-extern pgd_t swapper_pg_dir[] __attribute__ ((aligned (4096)));
+extern pgd_t swapper_pg_dir[];
 extern void paging_init(void);
 extern void vmem_map_init(void);
+pmd_t *vmem_pmd_alloc(void);
+pte_t *vmem_pte_alloc(void);
+
+enum {
+	PG_DIRECT_MAP_4K = 0,
+	PG_DIRECT_MAP_1M,
+	PG_DIRECT_MAP_2G,
+	PG_DIRECT_MAP_MAX
+};
+
+extern atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX];
+
+static inline void update_page_count(int level, long count)
+{
+	if (IS_ENABLED(CONFIG_PROC_FS))
+		atomic_long_add(count, &direct_pages_count[level]);
+}
+
+struct seq_file;
+void arch_report_meminfo(struct seq_file *m);
 
 /*
  * The S390 doesn't have any external MMU info: the kernel page
@@ -270,8 +291,23 @@ static inline int is_module_addr(void *addr)
 #define _REGION3_ENTRY		(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
 #define _REGION3_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID)
 
-#define _REGION3_ENTRY_LARGE	0x400	/* RTTE-format control, large page  */
-#define _REGION3_ENTRY_RO	0x200	/* page protection bit		    */
+#define _REGION3_ENTRY_ORIGIN_LARGE ~0x7fffffffUL /* large page address	     */
+#define _REGION3_ENTRY_ORIGIN  ~0x7ffUL/* region third table origin	     */
+
+#define _REGION3_ENTRY_DIRTY	0x2000	/* SW region dirty bit */
+#define _REGION3_ENTRY_YOUNG	0x1000	/* SW region young bit */
+#define _REGION3_ENTRY_LARGE	0x0400	/* RTTE-format control, large page  */
+#define _REGION3_ENTRY_READ	0x0002	/* SW region read bit */
+#define _REGION3_ENTRY_WRITE	0x0001	/* SW region write bit */
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _REGION3_ENTRY_SOFT_DIRTY 0x4000 /* SW region soft dirty bit */
+#else
+#define _REGION3_ENTRY_SOFT_DIRTY 0x0000 /* SW region soft dirty bit */
+#endif
+
+#define _REGION_ENTRY_BITS	 0xfffffffffffff227UL
+#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe27UL
 
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
@@ -297,7 +333,8 @@ static inline int is_module_addr(void *addr)
 #endif
 
 /*
- * Segment table entry encoding (R = read-only, I = invalid, y = young bit):
+ * Segment table and region3 table entry encoding
+ * (R = read-only, I = invalid, y = young bit):
  *				dy..R...I...rw
  * prot-none, clean, old	00..1...1...00
  * prot-none, clean, young	01..1...1...00
@@ -391,6 +428,33 @@ static inline int is_module_addr(void *addr)
 				 _SEGMENT_ENTRY_READ)
 #define SEGMENT_WRITE	__pgprot(_SEGMENT_ENTRY_READ | \
 				 _SEGMENT_ENTRY_WRITE)
+#define SEGMENT_KERNEL	__pgprot(_SEGMENT_ENTRY |	\
+				 _SEGMENT_ENTRY_LARGE |	\
+				 _SEGMENT_ENTRY_READ |	\
+				 _SEGMENT_ENTRY_WRITE | \
+				 _SEGMENT_ENTRY_YOUNG | \
+				 _SEGMENT_ENTRY_DIRTY)
+#define SEGMENT_KERNEL_RO __pgprot(_SEGMENT_ENTRY |	\
+				 _SEGMENT_ENTRY_LARGE |	\
+				 _SEGMENT_ENTRY_READ |	\
+				 _SEGMENT_ENTRY_YOUNG |	\
+				 _SEGMENT_ENTRY_PROTECT)
+
+/*
+ * Region3 entry (large page) protection definitions.
+ */
+
+#define REGION3_KERNEL	__pgprot(_REGION_ENTRY_TYPE_R3 | \
+				 _REGION3_ENTRY_LARGE |	 \
+				 _REGION3_ENTRY_READ |	 \
+				 _REGION3_ENTRY_WRITE |	 \
+				 _REGION3_ENTRY_YOUNG |	 \
+				 _REGION3_ENTRY_DIRTY)
+#define REGION3_KERNEL_RO __pgprot(_REGION_ENTRY_TYPE_R3 | \
+				   _REGION3_ENTRY_LARGE |  \
+				   _REGION3_ENTRY_READ |   \
+				   _REGION3_ENTRY_YOUNG |  \
+				   _REGION_ENTRY_PROTECT)
 
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
@@ -424,6 +488,53 @@ static inline int mm_use_skey(struct mm_struct *mm)
 	return 0;
 }
 
+static inline void csp(unsigned int *ptr, unsigned int old, unsigned int new)
+{
+	register unsigned long reg2 asm("2") = old;
+	register unsigned long reg3 asm("3") = new;
+	unsigned long address = (unsigned long)ptr | 1;
+
+	asm volatile(
+		"	csp	%0,%3"
+		: "+d" (reg2), "+m" (*ptr)
+		: "d" (reg3), "d" (address)
+		: "cc");
+}
+
+static inline void cspg(unsigned long *ptr, unsigned long old, unsigned long new)
+{
+	register unsigned long reg2 asm("2") = old;
+	register unsigned long reg3 asm("3") = new;
+	unsigned long address = (unsigned long)ptr | 1;
+
+	asm volatile(
+		"	.insn	rre,0xb98a0000,%0,%3"
+		: "+d" (reg2), "+m" (*ptr)
+		: "d" (reg3), "d" (address)
+		: "cc");
+}
+
+#define CRDTE_DTT_PAGE		0x00UL
+#define CRDTE_DTT_SEGMENT	0x10UL
+#define CRDTE_DTT_REGION3	0x14UL
+#define CRDTE_DTT_REGION2	0x18UL
+#define CRDTE_DTT_REGION1	0x1cUL
+
+static inline void crdte(unsigned long old, unsigned long new,
+			 unsigned long table, unsigned long dtt,
+			 unsigned long address, unsigned long asce)
+{
+	register unsigned long reg2 asm("2") = old;
+	register unsigned long reg3 asm("3") = new;
+	register unsigned long reg4 asm("4") = table | dtt;
+	register unsigned long reg5 asm("5") = address;
+
+	asm volatile(".insn rrf,0xb98f0000,%0,%2,%4,0"
+		     : "+d" (reg2)
+		     : "d" (reg3), "d" (reg4), "d" (reg5), "a" (asce)
+		     : "memory", "cc");
+}
+
 /*
  * pgd/pmd/pte query functions
  */
@@ -465,7 +576,7 @@ static inline int pud_none(pud_t pud)
 {
 	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
 		return 0;
-	return (pud_val(pud) & _REGION_ENTRY_INVALID) != 0UL;
+	return pud_val(pud) == _REGION3_ENTRY_EMPTY;
 }
 
 static inline int pud_large(pud_t pud)
@@ -475,17 +586,35 @@ static inline int pud_large(pud_t pud)
 	return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
 }
 
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	unsigned long origin_mask;
+
+	origin_mask = _REGION3_ENTRY_ORIGIN;
+	if (pud_large(pud))
+		origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
+	return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
+}
+
+static inline int pmd_large(pmd_t pmd)
+{
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+	if (pmd_large(pmd))
+		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
+	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
+}
+
 static inline int pud_bad(pud_t pud)
 {
-	/*
-	 * With dynamic page table levels the pud can be a region table
-	 * entry or a segment table entry. Check for the bit that are
-	 * invalid for either table entry.
-	 */
-	unsigned long mask =
-		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
-		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
-	return (pud_val(pud) & mask) != 0;
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
+		return pmd_bad(__pmd(pud_val(pud)));
+	if (pud_large(pud))
+		return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
+	return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
 }
 
 static inline int pmd_present(pmd_t pmd)
@@ -498,11 +627,6 @@ static inline int pmd_none(pmd_t pmd)
 	return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID;
 }
 
-static inline int pmd_large(pmd_t pmd)
-{
-	return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
-}
-
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
 	unsigned long origin_mask;
@@ -513,13 +637,6 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
 }
 
-static inline int pmd_bad(pmd_t pmd)
-{
-	if (pmd_large(pmd))
-		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
-	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
-}
-
 #define __HAVE_ARCH_PMD_WRITE
 static inline int pmd_write(pmd_t pmd)
 {
@@ -963,6 +1080,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 #define pte_page(x) pfn_to_page(pte_pfn(x))
 
 #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd))
+#define pud_page(pud) pfn_to_page(pud_pfn(pud))
 
 /* Find an entry in the lowest level page table.. */
 #define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
@@ -970,20 +1088,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
 #define pte_unmap(pte) do { } while (0)
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
-static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
-{
-	/*
-	 * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx)
-	 * Convert to segment table entry format.
-	 */
-	if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
-		return pgprot_val(SEGMENT_NONE);
-	if (pgprot_val(pgprot) == pgprot_val(PAGE_READ))
-		return pgprot_val(SEGMENT_READ);
-	return pgprot_val(SEGMENT_WRITE);
-}
-
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
 	pmd_val(pmd) &= ~_SEGMENT_ENTRY_WRITE;
@@ -1020,6 +1124,56 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd;
 }
 
+static inline pud_t pud_wrprotect(pud_t pud)
+{
+	pud_val(pud) &= ~_REGION3_ENTRY_WRITE;
+	pud_val(pud) |= _REGION_ENTRY_PROTECT;
+	return pud;
+}
+
+static inline pud_t pud_mkwrite(pud_t pud)
+{
+	pud_val(pud) |= _REGION3_ENTRY_WRITE;
+	if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY))
+		return pud;
+	pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
+	return pud;
+}
+
+static inline pud_t pud_mkclean(pud_t pud)
+{
+	if (pud_large(pud)) {
+		pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
+		pud_val(pud) |= _REGION_ENTRY_PROTECT;
+	}
+	return pud;
+}
+
+static inline pud_t pud_mkdirty(pud_t pud)
+{
+	if (pud_large(pud)) {
+		pud_val(pud) |= _REGION3_ENTRY_DIRTY |
+				_REGION3_ENTRY_SOFT_DIRTY;
+		if (pud_val(pud) & _REGION3_ENTRY_WRITE)
+			pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
+	}
+	return pud;
+}
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
+{
+	/*
+	 * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx)
+	 * Convert to segment table entry format.
+	 */
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
+		return pgprot_val(SEGMENT_NONE);
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_READ))
+		return pgprot_val(SEGMENT_READ);
+	return pgprot_val(SEGMENT_WRITE);
+}
+
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
 	if (pmd_large(pmd)) {
@@ -1068,15 +1222,8 @@ static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot)
 
 static inline void __pmdp_csp(pmd_t *pmdp)
 {
-	register unsigned long reg2 asm("2") = pmd_val(*pmdp);
-	register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
-					       _SEGMENT_ENTRY_INVALID;
-	register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
-
-	asm volatile(
-		"	csp %1,%3"
-		: "=m" (*pmdp)
-		: "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+	csp((unsigned int *)pmdp + 1, pmd_val(*pmdp),
+	    pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
 }
 
 static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp)
@@ -1091,6 +1238,19 @@ static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp)
 		: "cc" );
 }
 
+static inline void __pudp_idte(unsigned long address, pud_t *pudp)
+{
+	unsigned long r3o;
+
+	r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t);
+	r3o |= _ASCE_TYPE_REGION3;
+	asm volatile(
+		"	.insn	rrf,0xb98e0000,%2,%3,0,0"
+		: "=m" (*pudp)
+		: "m" (*pudp), "a" (r3o), "a" ((address & PUD_MASK))
+		: "cc");
+}
+
 static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp)
 {
 	unsigned long sto;
@@ -1103,8 +1263,22 @@ static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp)
 		: "cc" );
 }
 
+static inline void __pudp_idte_local(unsigned long address, pud_t *pudp)
+{
+	unsigned long r3o;
+
+	r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t);
+	r3o |= _ASCE_TYPE_REGION3;
+	asm volatile(
+		"	.insn	rrf,0xb98e0000,%2,%3,0,1"
+		: "=m" (*pudp)
+		: "m" (*pudp), "a" (r3o), "a" ((address & PUD_MASK))
+		: "cc");
+}
+
 pmd_t pmdp_xchg_direct(struct mm_struct *, unsigned long, pmd_t *, pmd_t);
 pmd_t pmdp_xchg_lazy(struct mm_struct *, unsigned long, pmd_t *, pmd_t);
+pud_t pudp_xchg_direct(struct mm_struct *, unsigned long, pud_t *, pud_t);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 9d4d311d7e52..09529202ea77 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -77,7 +77,10 @@ static inline void get_cpu_id(struct cpuid *ptr)
 	asm volatile("stidp %0" : "=Q" (*ptr));
 }
 
-extern void s390_adjust_jiffies(void);
+void s390_adjust_jiffies(void);
+void s390_update_cpu_mhz(void);
+void cpu_detect_mhz_feature(void);
+
 extern const struct seq_operations cpuinfo_op;
 extern int sysctl_ieee_emulation_warnings;
 extern void execve_tail(void);
@@ -233,6 +236,18 @@ void cpu_relax(void);
 
 #define cpu_relax_lowlatency()  barrier()
 
+#define ECAG_CACHE_ATTRIBUTE	0
+#define ECAG_CPU_ATTRIBUTE	1
+
+static inline unsigned long __ecag(unsigned int asi, unsigned char parm)
+{
+	unsigned long val;
+
+	asm volatile(".insn	rsy,0xeb000000004c,%0,0,0(%1)" /* ecag */
+		     : "=d" (val) : "a" (asi << 8 | parm));
+	return val;
+}
+
 static inline void psw_set_key(unsigned int key)
 {
 	asm volatile("spka 0(%0)" : : "d" (key));
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index fbd9116eb17b..5ce29fe100ba 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -4,5 +4,6 @@
 #include <asm-generic/sections.h>
 
 extern char _eshared[], _ehead[];
+extern char __start_ro_after_init[], __end_ro_after_init[];
 
 #endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index c0f0efbb6ab5..5e8d57e1cc5e 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -86,9 +86,13 @@ extern char vmpoff_cmd[];
 #define CONSOLE_IS_SCLP		(console_mode == 1)
 #define CONSOLE_IS_3215		(console_mode == 2)
 #define CONSOLE_IS_3270		(console_mode == 3)
+#define CONSOLE_IS_VT220	(console_mode == 4)
+#define CONSOLE_IS_HVC		(console_mode == 5)
 #define SET_CONSOLE_SCLP	do { console_mode = 1; } while (0)
 #define SET_CONSOLE_3215	do { console_mode = 2; } while (0)
 #define SET_CONSOLE_3270	do { console_mode = 3; } while (0)
+#define SET_CONSOLE_VT220	do { console_mode = 4; } while (0)
+#define SET_CONSOLE_HVC		do { console_mode = 5; } while (0)
 
 #define NSS_NAME_SIZE	8
 extern char kernel_nss_name[];
diff --git a/arch/s390/include/asm/sfp-machine.h b/arch/s390/include/asm/sfp-machine.h
deleted file mode 100644
index 4e16aede4b06..000000000000
--- a/arch/s390/include/asm/sfp-machine.h
+++ /dev/null
@@ -1,142 +0,0 @@
-/* Machine-dependent software floating-point definitions.
-   S/390 kernel version.
-   Copyright (C) 1997,1998,1999 Free Software Foundation, Inc.
-   This file is part of the GNU C Library.
-   Contributed by Richard Henderson (rth@cygnus.com),
-		  Jakub Jelinek (jj@ultra.linux.cz),
-		  David S. Miller (davem@redhat.com) and
-		  Peter Maydell (pmaydell@chiark.greenend.org.uk).
-
-   The GNU C Library is free software; you can redistribute it and/or
-   modify it under the terms of the GNU Library General Public License as
-   published by the Free Software Foundation; either version 2 of the
-   License, or (at your option) any later version.
-
-   The GNU C Library is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-   Library General Public License for more details.
-
-   You should have received a copy of the GNU Library General Public
-   License along with the GNU C Library; see the file COPYING.LIB.  If
-   not, write to the Free Software Foundation, Inc.,
-   59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */
-
-#ifndef _SFP_MACHINE_H
-#define _SFP_MACHINE_H
-   
-
-#define _FP_W_TYPE_SIZE		32
-#define _FP_W_TYPE		unsigned int
-#define _FP_WS_TYPE		signed int
-#define _FP_I_TYPE		int
-
-#define _FP_MUL_MEAT_S(R,X,Y)					\
-  _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm)
-#define _FP_MUL_MEAT_D(R,X,Y)					\
-  _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
-#define _FP_MUL_MEAT_Q(R,X,Y)					\
-  _FP_MUL_MEAT_4_wide(_FP_WFRACBITS_Q,R,X,Y,umul_ppmm)
-
-#define _FP_DIV_MEAT_S(R,X,Y)	_FP_DIV_MEAT_1_udiv(S,R,X,Y)
-#define _FP_DIV_MEAT_D(R,X,Y)	_FP_DIV_MEAT_2_udiv(D,R,X,Y)
-#define _FP_DIV_MEAT_Q(R,X,Y)	_FP_DIV_MEAT_4_udiv(Q,R,X,Y)
-
-#define _FP_NANFRAC_S		((_FP_QNANBIT_S << 1) - 1)
-#define _FP_NANFRAC_D		((_FP_QNANBIT_D << 1) - 1), -1
-#define _FP_NANFRAC_Q		((_FP_QNANBIT_Q << 1) - 1), -1, -1, -1
-#define _FP_NANSIGN_S		0
-#define _FP_NANSIGN_D		0
-#define _FP_NANSIGN_Q		0
-
-#define _FP_KEEPNANFRACP 1
-
-/*
- * If one NaN is signaling and the other is not,
- * we choose that one, otherwise we choose X.
- */
-#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)                      \
-  do {                                                          \
-    if ((_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs)          \
-        && !(_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs))     \
-      {                                                         \
-        R##_s = Y##_s;                                          \
-        _FP_FRAC_COPY_##wc(R,Y);                                \
-      }                                                         \
-    else                                                        \
-      {                                                         \
-        R##_s = X##_s;                                          \
-        _FP_FRAC_COPY_##wc(R,X);                                \
-      }                                                         \
-    R##_c = FP_CLS_NAN;                                         \
-  } while (0)
-
-/* Some assembly to speed things up. */
-#define __FP_FRAC_ADD_3(r2,r1,r0,x2,x1,x0,y2,y1,y0) ({		\
-	unsigned int __r2 = (x2) + (y2);			\
-	unsigned int __r1 = (x1);				\
-	unsigned int __r0 = (x0);				\
-	asm volatile(						\
-		"	alr	%2,%3\n"			\
-		"	brc	12,0f\n"			\
-		"	lhi	0,1\n"				\
-		"	alr	%1,0\n"				\
-		"	brc	12,0f\n"			\
-		"	alr	%0,0\n"				\
-		"0:"						\
-		: "+&d" (__r2), "+&d" (__r1), "+&d" (__r0)	\
-		: "d" (y0), "i" (1) : "cc", "0" );		\
-	asm volatile(						\
-		"	alr	%1,%2\n"			\
-		"	brc	12,0f\n"			\
-		"	ahi	%0,1\n"				\
-		"0:"						\
-		: "+&d" (__r2), "+&d" (__r1)			\
-		: "d" (y1) : "cc");				\
-	(r2) = __r2;						\
-	(r1) = __r1;						\
-	(r0) = __r0;						\
-})
-
-#define __FP_FRAC_SUB_3(r2,r1,r0,x2,x1,x0,y2,y1,y0) ({		\
-	unsigned int __r2 = (x2) - (y2);			\
-	unsigned int __r1 = (x1);				\
-	unsigned int __r0 = (x0);				\
-	asm volatile(						\
-		"	slr   %2,%3\n"				\
-		"	brc	3,0f\n"				\
-		"	lhi	0,1\n"				\
-		"	slr	%1,0\n"				\
-		"	brc	3,0f\n"				\
-		"	slr	%0,0\n"				\
-		"0:"						\
-		: "+&d" (__r2), "+&d" (__r1), "+&d" (__r0)	\
-		: "d" (y0) : "cc", "0");			\
-	asm volatile(						\
-		"	slr	%1,%2\n"			\
-		"	brc	3,0f\n"				\
-		"	ahi	%0,-1\n"			\
-		"0:"						\
-		: "+&d" (__r2), "+&d" (__r1)			\
-		: "d" (y1) : "cc");				\
-	(r2) = __r2;						\
-	(r1) = __r1;						\
-	(r0) = __r0;						\
-})
-
-#define __FP_FRAC_DEC_3(x2,x1,x0,y2,y1,y0) __FP_FRAC_SUB_3(x2,x1,x0,x2,x1,x0,y2,y1,y0)
-
-/* Obtain the current rounding mode. */
-#define FP_ROUNDMODE	mode
-
-/* Exception flags. */
-#define FP_EX_INVALID		0x800000
-#define FP_EX_DIVZERO		0x400000
-#define FP_EX_OVERFLOW		0x200000
-#define FP_EX_UNDERFLOW		0x100000
-#define FP_EX_INEXACT		0x080000
-
-/* We write the results always */
-#define FP_INHIBIT_RESULTS 0
-
-#endif
diff --git a/arch/s390/include/asm/sfp-util.h b/arch/s390/include/asm/sfp-util.h
deleted file mode 100644
index c8b7cf9d6279..000000000000
--- a/arch/s390/include/asm/sfp-util.h
+++ /dev/null
@@ -1,67 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <asm/byteorder.h>
-
-#define add_ssaaaa(sh, sl, ah, al, bh, bl) ({		\
-	unsigned int __sh = (ah);			\
-	unsigned int __sl = (al);			\
-	asm volatile(					\
-		"	alr	%1,%3\n"		\
-		"	brc	12,0f\n"		\
-		"	ahi	%0,1\n"			\
-		"0:	alr  %0,%2"			\
-		: "+&d" (__sh), "+d" (__sl)		\
-		: "d" (bh), "d" (bl) : "cc");		\
-	(sh) = __sh;					\
-	(sl) = __sl;					\
-})
-
-#define sub_ddmmss(sh, sl, ah, al, bh, bl) ({		\
-	unsigned int __sh = (ah);			\
-	unsigned int __sl = (al);			\
-	asm volatile(					\
-		"	slr	%1,%3\n"		\
-		"	brc	3,0f\n"			\
-		"	ahi	%0,-1\n"		\
-		"0:	slr	%0,%2"			\
-		: "+&d" (__sh), "+d" (__sl)		\
-		: "d" (bh), "d" (bl) : "cc");		\
-	(sh) = __sh;					\
-	(sl) = __sl;					\
-})
-
-/* a umul b = a mul b + (a>=2<<31) ? b<<32:0 + (b>=2<<31) ? a<<32:0 */
-#define umul_ppmm(wh, wl, u, v) ({			\
-	unsigned int __wh = u;				\
-	unsigned int __wl = v;				\
-	asm volatile(					\
-		"	ltr	1,%0\n"			\
-		"	mr	0,%1\n"			\
-		"	jnm	0f\n"				\
-		"	alr	0,%1\n"			\
-		"0:	ltr	%1,%1\n"			\
-		"	jnm	1f\n"				\
-		"	alr	0,%0\n"			\
-		"1:	lr	%0,0\n"			\
-		"	lr	%1,1\n"			\
-		: "+d" (__wh), "+d" (__wl)		\
-		: : "0", "1", "cc");			\
-	wh = __wh;					\
-	wl = __wl;					\
-})
-
-#define udiv_qrnnd(q, r, n1, n0, d)			\
-  do { unsigned long __n;				\
-       unsigned int __r, __d;				\
-    __n = ((unsigned long)(n1) << 32) + n0;		\
-    __d = (d);						\
-    (q) = __n / __d;					\
-    (r) = __n % __d;					\
-  } while (0)
-
-#define UDIV_NEEDS_NORMALIZATION 0
-
-#define abort() BUG()
-
-#define __BYTE_ORDER __BIG_ENDIAN
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index 1c8f33fca356..72df5f2de6b0 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -37,8 +37,8 @@
 
 #ifndef __ASSEMBLY__
 
-static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm,
-			      u32 *status)
+static inline int ____pcpu_sigp(u16 addr, u8 order, unsigned long parm,
+				u32 *status)
 {
 	register unsigned long reg1 asm ("1") = parm;
 	int cc;
@@ -48,8 +48,19 @@ static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm,
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
 		: "=d" (cc), "+d" (reg1) : "d" (addr), "a" (order) : "cc");
+	*status = reg1;
+	return cc;
+}
+
+static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm,
+			      u32 *status)
+{
+	u32 _status;
+	int cc;
+
+	cc = ____pcpu_sigp(addr, order, parm, &_status);
 	if (status && cc == 1)
-		*status = reg1;
+		*status = _status;
 	return cc;
 }
 
diff --git a/arch/s390/include/asm/stp.h b/arch/s390/include/asm/stp.h
new file mode 100644
index 000000000000..7689727585b2
--- /dev/null
+++ b/arch/s390/include/asm/stp.h
@@ -0,0 +1,51 @@
+/*
+ *  Copyright IBM Corp. 2006
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ */
+#ifndef __S390_STP_H
+#define __S390_STP_H
+
+/* notifier for syncs */
+extern struct atomic_notifier_head s390_epoch_delta_notifier;
+
+/* STP interruption parameter */
+struct stp_irq_parm {
+	unsigned int _pad0	: 14;
+	unsigned int tsc	: 1;	/* Timing status change */
+	unsigned int lac	: 1;	/* Link availability change */
+	unsigned int tcpc	: 1;	/* Time control parameter change */
+	unsigned int _pad2	: 15;
+} __attribute__ ((packed));
+
+#define STP_OP_SYNC	1
+#define STP_OP_CTRL	3
+
+struct stp_sstpi {
+	unsigned int rsvd0;
+	unsigned int rsvd1 : 8;
+	unsigned int stratum : 8;
+	unsigned int vbits : 16;
+	unsigned int leaps : 16;
+	unsigned int tmd : 4;
+	unsigned int ctn : 4;
+	unsigned int rsvd2 : 3;
+	unsigned int c : 1;
+	unsigned int tst : 4;
+	unsigned int tzo : 16;
+	unsigned int dsto : 16;
+	unsigned int ctrl : 16;
+	unsigned int rsvd3 : 16;
+	unsigned int tto;
+	unsigned int rsvd4;
+	unsigned int ctnid[3];
+	unsigned int rsvd5;
+	unsigned int todoff[4];
+	unsigned int rsvd6[48];
+} __attribute__ ((packed));
+
+/* Functions needed by the machine check handler */
+int stp_sync_check(void);
+int stp_island_check(void);
+void stp_queue_work(void);
+
+#endif /* __S390_STP_H */
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index dcb6312a0b91..0bb08f341c09 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -52,6 +52,70 @@ static inline void store_clock_comparator(__u64 *time)
 
 void clock_comparator_work(void);
 
+void __init ptff_init(void);
+
+extern unsigned char ptff_function_mask[16];
+extern unsigned long lpar_offset;
+extern unsigned long initial_leap_seconds;
+
+/* Function codes for the ptff instruction. */
+#define PTFF_QAF	0x00	/* query available functions */
+#define PTFF_QTO	0x01	/* query tod offset */
+#define PTFF_QSI	0x02	/* query steering information */
+#define PTFF_QUI	0x04	/* query UTC information */
+#define PTFF_ATO	0x40	/* adjust tod offset */
+#define PTFF_STO	0x41	/* set tod offset */
+#define PTFF_SFS	0x42	/* set fine steering rate */
+#define PTFF_SGS	0x43	/* set gross steering rate */
+
+/* Query TOD offset result */
+struct ptff_qto {
+	unsigned long long physical_clock;
+	unsigned long long tod_offset;
+	unsigned long long logical_tod_offset;
+	unsigned long long tod_epoch_difference;
+} __packed;
+
+static inline int ptff_query(unsigned int nr)
+{
+	unsigned char *ptr;
+
+	ptr = ptff_function_mask + (nr >> 3);
+	return (*ptr & (0x80 >> (nr & 7))) != 0;
+}
+
+/* Query UTC information result */
+struct ptff_qui {
+	unsigned int tm : 2;
+	unsigned int ts : 2;
+	unsigned int : 28;
+	unsigned int pad_0x04;
+	unsigned long leap_event;
+	short old_leap;
+	short new_leap;
+	unsigned int pad_0x14;
+	unsigned long prt[5];
+	unsigned long cst[3];
+	unsigned int skew;
+	unsigned int pad_0x5c[41];
+} __packed;
+
+static inline int ptff(void *ptff_block, size_t len, unsigned int func)
+{
+	typedef struct { char _[len]; } addrtype;
+	register unsigned int reg0 asm("0") = func;
+	register unsigned long reg1 asm("1") = (unsigned long) ptff_block;
+	int rc;
+
+	asm volatile(
+		"	.word	0x0104\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (rc), "+m" (*(addrtype *) ptff_block)
+		: "d" (reg0), "d" (reg1) : "cc");
+	return rc;
+}
+
 static inline unsigned long long local_tick_disable(void)
 {
 	unsigned long long old;
@@ -105,7 +169,7 @@ static inline cycles_t get_cycles(void)
 	return (cycles_t) get_tod_clock() >> 2;
 }
 
-int get_sync_clock(unsigned long long *clock);
+int get_phys_clock(unsigned long long *clock);
 void init_cpu_timer(void);
 unsigned long long monotonic_clock(void);
 
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index a2e6ef32e054..1a691ef740cf 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <asm/processor.h>
 #include <asm/pgalloc.h>
+#include <asm/pgtable.h>
 
 /*
  * Flush all TLB entries on the local CPU.
@@ -44,17 +45,9 @@ void smp_ptlb_all(void);
  */
 static inline void __tlb_flush_global(void)
 {
-	register unsigned long reg2 asm("2");
-	register unsigned long reg3 asm("3");
-	register unsigned long reg4 asm("4");
-	long dummy;
-
-	dummy = 0;
-	reg2 = reg3 = 0;
-	reg4 = ((unsigned long) &dummy) + 1;
-	asm volatile(
-		"	csp	%0,%2"
-		: : "d" (reg2), "d" (reg3), "d" (reg4), "m" (dummy) : "cc" );
+	unsigned int dummy = 0;
+
+	csp(&dummy, 0, 0);
 }
 
 /*
@@ -64,7 +57,7 @@ static inline void __tlb_flush_global(void)
 static inline void __tlb_flush_full(struct mm_struct *mm)
 {
 	preempt_disable();
-	atomic_add(0x10000, &mm->context.attach_count);
+	atomic_inc(&mm->context.flush_count);
 	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
 		/* Local TLB flush */
 		__tlb_flush_local();
@@ -76,21 +69,19 @@ static inline void __tlb_flush_full(struct mm_struct *mm)
 			cpumask_copy(mm_cpumask(mm),
 				     &mm->context.cpu_attach_mask);
 	}
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	preempt_enable();
 }
 
 /*
- * Flush TLB entries for a specific ASCE on all CPUs.
+ * Flush TLB entries for a specific ASCE on all CPUs. Should never be used
+ * when more than one asce (e.g. gmap) ran on this mm.
  */
 static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 {
-	int active, count;
-
 	preempt_disable();
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+	atomic_inc(&mm->context.flush_count);
+	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
 		__tlb_flush_idte_local(asce);
 	} else {
@@ -103,7 +94,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 			cpumask_copy(mm_cpumask(mm),
 				     &mm->context.cpu_attach_mask);
 	}
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	preempt_enable();
 }
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 6b53962e807e..f15f5571ca2b 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -14,10 +14,12 @@ struct cpu_topology_s390 {
 	unsigned short core_id;
 	unsigned short socket_id;
 	unsigned short book_id;
+	unsigned short drawer_id;
 	unsigned short node_id;
 	cpumask_t thread_mask;
 	cpumask_t core_mask;
 	cpumask_t book_mask;
+	cpumask_t drawer_mask;
 };
 
 DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology);
@@ -30,6 +32,8 @@ DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology);
 #define topology_core_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).core_mask)
 #define topology_book_id(cpu)		  (per_cpu(cpu_topology, cpu).book_id)
 #define topology_book_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).book_mask)
+#define topology_drawer_id(cpu)		  (per_cpu(cpu_topology, cpu).drawer_id)
+#define topology_drawer_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).drawer_mask)
 
 #define mc_capable() 1
 
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index e0900ddf91dd..9b49cf1daa8f 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -151,8 +151,65 @@ unsigned long __must_check __copy_to_user(void __user *to, const void *from,
 	__rc;							\
 })
 
-#define __put_user_fn(x, ptr, size) __put_get_user_asm(ptr, x, size, 0x810000UL)
-#define __get_user_fn(x, ptr, size) __put_get_user_asm(x, ptr, size, 0x81UL)
+static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
+{
+	unsigned long spec = 0x810000UL;
+	int rc;
+
+	switch (size) {
+	case 1:
+		rc = __put_get_user_asm((unsigned char __user *)ptr,
+					(unsigned char *)x,
+					size, spec);
+		break;
+	case 2:
+		rc = __put_get_user_asm((unsigned short __user *)ptr,
+					(unsigned short *)x,
+					size, spec);
+		break;
+	case 4:
+		rc = __put_get_user_asm((unsigned int __user *)ptr,
+					(unsigned int *)x,
+					size, spec);
+		break;
+	case 8:
+		rc = __put_get_user_asm((unsigned long __user *)ptr,
+					(unsigned long *)x,
+					size, spec);
+		break;
+	};
+	return rc;
+}
+
+static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
+{
+	unsigned long spec = 0x81UL;
+	int rc;
+
+	switch (size) {
+	case 1:
+		rc = __put_get_user_asm((unsigned char *)x,
+					(unsigned char __user *)ptr,
+					size, spec);
+		break;
+	case 2:
+		rc = __put_get_user_asm((unsigned short *)x,
+					(unsigned short __user *)ptr,
+					size, spec);
+		break;
+	case 4:
+		rc = __put_get_user_asm((unsigned int *)x,
+					(unsigned int __user *)ptr,
+					size, spec);
+		break;
+	case 8:
+		rc = __put_get_user_asm((unsigned long *)x,
+					(unsigned long __user *)ptr,
+					size, spec);
+		break;
+	};
+	return rc;
+}
 
 #else /* CONFIG_HAVE_MARCH_Z10_FEATURES */
 
@@ -191,7 +248,7 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s
 		__put_user_bad();				\
 		break;						\
 	 }							\
-	__pu_err;						\
+	__builtin_expect(__pu_err, 0);				\
 })
 
 #define put_user(x, ptr)					\
@@ -240,7 +297,7 @@ int __put_user_bad(void) __attribute__((noreturn));
 		__get_user_bad();				\
 		break;						\
 	}							\
-	__gu_err;						\
+	__builtin_expect(__gu_err, 0);				\
 })
 
 #define get_user(x, ptr)					\
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index a150f4fabe43..77630c74f13b 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -359,9 +359,9 @@ typedef struct
 		per_cr_bits    bits;
 	} control_regs;
 	/*
-	 * Use these flags instead of setting em_instruction_fetch
-	 * directly they are used so that single stepping can be
-	 * switched on & off while not affecting other tracing
+	 * The single_step and instruction_fetch bits are obsolete,
+	 * the kernel always sets them to zero. To enable single
+	 * stepping use ptrace(PTRACE_SINGLESTEP) instead.
 	 */
 	unsigned  single_step       : 1;
 	unsigned  instruction_fetch : 1;
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2f5586ab8a6a..f37be37edd3a 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -2,6 +2,9 @@
 # Makefile for the linux kernel.
 #
 
+KCOV_INSTRUMENT_early.o := n
+KCOV_INSTRUMENT_sclp.o := n
+
 ifdef CONFIG_FUNCTION_TRACER
 # Don't trace early setup code and tracing code
 CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
@@ -45,7 +48,7 @@ obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
-obj-y	+= runtime_instr.o cache.o dumpstack.o
+obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o
 obj-y	+= entry.o reipl.o relocate_kernel.o
 
 extra-y				+= head.o head64.o vmlinux.lds
diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
index 77a84bd78be2..c8a83276a4dc 100644
--- a/arch/s390/kernel/cache.c
+++ b/arch/s390/kernel/cache.c
@@ -99,12 +99,7 @@ static inline enum cache_type get_cache_type(struct cache_info *ci, int level)
 
 static inline unsigned long ecag(int ai, int li, int ti)
 {
-	unsigned long cmd, val;
-
-	cmd = ai << 4 | li << 1 | ti;
-	asm volatile(".insn	rsy,0xeb000000004c,%0,0,0(%1)" /* ecag */
-		     : "=d" (val) : "a" (cmd));
-	return val;
+	return __ecag(ECAG_CACHE_ATTRIBUTE, ai << 4 | li << 1 | ti);
 }
 
 static void ci_leaf_init(struct cacheinfo *this_leaf, int private,
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 8cb9bfdd3ea8..43446fa2a4e5 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -26,7 +26,6 @@
 #include <asm/dis.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
-#include <asm/mathemu.h>
 #include <asm/cpcmd.h>
 #include <asm/lowcore.h>
 #include <asm/debug.h>
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 69f9908ac44c..6693383bc01b 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -78,14 +78,10 @@ void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
 	sp = __dump_trace(func, data, sp,
 			  S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
 			  S390_lowcore.async_stack + frame_size);
-	if (task)
-		__dump_trace(func, data, sp,
-			     (unsigned long)task_stack_page(task),
-			     (unsigned long)task_stack_page(task) + THREAD_SIZE);
-	else
-		__dump_trace(func, data, sp,
-			     S390_lowcore.thread_info,
-			     S390_lowcore.thread_info + THREAD_SIZE);
+	task = task ?: current;
+	__dump_trace(func, data, sp,
+		     (unsigned long)task_stack_page(task),
+		     (unsigned long)task_stack_page(task) + THREAD_SIZE);
 }
 EXPORT_SYMBOL_GPL(dump_trace);
 
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index a0684de5a93b..717b03aa16b5 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -231,6 +231,26 @@ static noinline __init void detect_machine_type(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
 }
 
+static noinline __init void setup_arch_string(void)
+{
+	struct sysinfo_1_1_1 *mach = (struct sysinfo_1_1_1 *)&sysinfo_page;
+
+	if (stsi(mach, 1, 1, 1))
+		return;
+	EBCASC(mach->manufacturer, sizeof(mach->manufacturer));
+	EBCASC(mach->type, sizeof(mach->type));
+	EBCASC(mach->model, sizeof(mach->model));
+	EBCASC(mach->model_capacity, sizeof(mach->model_capacity));
+	dump_stack_set_arch_desc("%-16.16s %-4.4s %-16.16s %-16.16s (%s)",
+				 mach->manufacturer,
+				 mach->type,
+				 mach->model,
+				 mach->model_capacity,
+				 MACHINE_IS_LPAR ? "LPAR" :
+				 MACHINE_IS_VM ? "z/VM" :
+				 MACHINE_IS_KVM ? "KVM" : "unknown");
+}
+
 static __init void setup_topology(void)
 {
 	int max_mnest;
@@ -447,11 +467,13 @@ void __init startup_init(void)
 	ipl_save_parameters();
 	rescue_initrd();
 	clear_bss_section();
+	ptff_init();
 	init_kernel_storage_key();
 	lockdep_off();
 	setup_lowcore_early();
 	setup_facility_list();
 	detect_machine_type();
+	setup_arch_string();
 	ipl_update_parameters();
 	setup_boot_command_line();
 	create_kernel_nss();
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 2d47f9cfcb36..c51650a1ed16 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -163,6 +163,16 @@ _PIF_WORK	= (_PIF_PER_TRAP)
 	.endm
 
 	.section .kprobes.text, "ax"
+.Ldummy:
+	/*
+	 * This nop exists only in order to avoid that __switch_to starts at
+	 * the beginning of the kprobes text section. In that case we would
+	 * have several symbols at the same address. E.g. objdump would take
+	 * an arbitrary symbol name when disassembling this code.
+	 * With the added nop in between the __switch_to symbol is unique
+	 * again.
+	 */
+	nop	0
 
 /*
  * Scheduler resume function, called by switch_to
@@ -175,7 +185,6 @@ ENTRY(__switch_to)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
 	lgr	%r1,%r2
 	aghi	%r1,__TASK_thread		# thread_struct of prev task
-	lg	%r4,__TASK_thread_info(%r2)	# get thread_info of prev
 	lg	%r5,__TASK_thread_info(%r3)	# get thread_info of next
 	stg	%r15,__THREAD_ksp(%r1)		# store kernel stack of prev
 	lgr	%r1,%r3
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
new file mode 100644
index 000000000000..81d1d1887507
--- /dev/null
+++ b/arch/s390/kernel/fpu.c
@@ -0,0 +1,249 @@
+/*
+ * In-kernel vector facility support functions
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+#include <linux/kernel.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <asm/fpu/types.h>
+#include <asm/fpu/api.h>
+
+/*
+ * Per-CPU variable to maintain FPU register ranges that are in use
+ * by the kernel.
+ */
+static DEFINE_PER_CPU(u32, kernel_fpu_state);
+
+#define KERNEL_FPU_STATE_MASK	(KERNEL_FPU_MASK|KERNEL_FPC)
+
+
+void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
+{
+	if (!__this_cpu_read(kernel_fpu_state)) {
+		/*
+		 * Save user space FPU state and register contents.  Multiple
+		 * calls because of interruptions do not matter and return
+		 * immediately.  This also sets CIF_FPU to lazy restore FP/VX
+		 * register contents when returning to user space.
+		 */
+		save_fpu_regs();
+	}
+
+	/* Update flags to use the vector facility for KERNEL_FPR */
+	if (MACHINE_HAS_VX && (state->mask & KERNEL_FPR)) {
+		flags |= KERNEL_VXR_LOW | KERNEL_FPC;
+		flags &= ~KERNEL_FPR;
+	}
+
+	/* Save and update current kernel VX state */
+	state->mask = __this_cpu_read(kernel_fpu_state);
+	__this_cpu_or(kernel_fpu_state, flags & KERNEL_FPU_STATE_MASK);
+
+	/*
+	 * If this is the first call to __kernel_fpu_begin(), no additional
+	 * work is required.
+	 */
+	if (!(state->mask & KERNEL_FPU_STATE_MASK))
+		return;
+
+	/*
+	 * If KERNEL_FPR is still set, the vector facility is not available
+	 * and, thus, save floating-point control and registers only.
+	 */
+	if (state->mask & KERNEL_FPR) {
+		asm volatile("stfpc %0" : "=Q" (state->fpc));
+		asm volatile("std 0,%0" : "=Q" (state->fprs[0]));
+		asm volatile("std 1,%0" : "=Q" (state->fprs[1]));
+		asm volatile("std 2,%0" : "=Q" (state->fprs[2]));
+		asm volatile("std 3,%0" : "=Q" (state->fprs[3]));
+		asm volatile("std 4,%0" : "=Q" (state->fprs[4]));
+		asm volatile("std 5,%0" : "=Q" (state->fprs[5]));
+		asm volatile("std 6,%0" : "=Q" (state->fprs[6]));
+		asm volatile("std 7,%0" : "=Q" (state->fprs[7]));
+		asm volatile("std 8,%0" : "=Q" (state->fprs[8]));
+		asm volatile("std 9,%0" : "=Q" (state->fprs[9]));
+		asm volatile("std 10,%0" : "=Q" (state->fprs[10]));
+		asm volatile("std 11,%0" : "=Q" (state->fprs[11]));
+		asm volatile("std 12,%0" : "=Q" (state->fprs[12]));
+		asm volatile("std 13,%0" : "=Q" (state->fprs[13]));
+		asm volatile("std 14,%0" : "=Q" (state->fprs[14]));
+		asm volatile("std 15,%0" : "=Q" (state->fprs[15]));
+		return;
+	}
+
+	/*
+	 * If this is a nested call to __kernel_fpu_begin(), check the saved
+	 * state mask to save and later restore the vector registers that
+	 * are already in use.	Let's start with checking floating-point
+	 * controls.
+	 */
+	if (state->mask & KERNEL_FPC)
+		asm volatile("stfpc %0" : "=m" (state->fpc));
+
+	/* Test and save vector registers */
+	asm volatile (
+		/*
+		 * Test if any vector register must be saved and, if so,
+		 * test if all register can be saved.
+		 */
+		"	tmll	%[m],15\n"	/* KERNEL_VXR_MASK */
+		"	jz	20f\n"		/* no work -> done */
+		"	la	1,%[vxrs]\n"	/* load save area */
+		"	jo	18f\n"		/* -> save V0..V31 */
+
+		/*
+		 * Test if V8..V23 can be saved at once... this speeds up
+		 * for KERNEL_fpu_MID only. Otherwise continue to split the
+		 * range of vector registers into two halves and test them
+		 * separately.
+		 */
+		"	tmll	%[m],6\n"	/* KERNEL_VXR_MID */
+		"	jo	17f\n"		/* -> save V8..V23 */
+
+		/* Test and save the first half of 16 vector registers */
+		"1:	tmll	%[m],3\n"	/* KERNEL_VXR_LOW */
+		"	jz	10f\n"		/* -> KERNEL_VXR_HIGH */
+		"	jo	2f\n"		/* 11 -> save V0..V15 */
+		"	brc	4,3f\n"		/* 01 -> save V0..V7  */
+		"	brc	2,4f\n"		/* 10 -> save V8..V15 */
+
+		/* Test and save the second half of 16 vector registers */
+		"10:	tmll	%[m],12\n"	/* KERNEL_VXR_HIGH */
+		"	jo	19f\n"		/* 11 -> save V16..V31 */
+		"	brc	4,11f\n"	/* 01 -> save V16..V23	*/
+		"	brc	2,12f\n"	/* 10 -> save V24..V31 */
+		"	j	20f\n"		/* 00 -> done */
+
+		/*
+		 * Below are the vstm combinations to save multiple vector
+		 * registers at once.
+		 */
+		"2:	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
+		"	j	10b\n"			/* -> VXR_HIGH */
+		"3:	.word	0xe707,0x1000,0x003e\n" /* vstm 0,7,0(1) */
+		"	j	10b\n"			/* -> VXR_HIGH */
+		"4:	.word	0xe78f,0x1080,0x003e\n" /* vstm 8,15,128(1) */
+		"	j	10b\n"			/* -> VXR_HIGH */
+		"\n"
+		"11:	.word	0xe707,0x1100,0x0c3e\n"	/* vstm 16,23,256(1) */
+		"	j	20f\n"			/* -> done */
+		"12:	.word	0xe78f,0x1180,0x0c3e\n" /* vstm 24,31,384(1) */
+		"	j	20f\n"			/* -> done */
+		"\n"
+		"17:	.word	0xe787,0x1080,0x043e\n"	/* vstm 8,23,128(1) */
+		"	nill	%[m],249\n"		/* m &= ~VXR_MID    */
+		"	j	1b\n"			/* -> VXR_LOW */
+		"\n"
+		"18:	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
+		"19:	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
+		"20:"
+		: [vxrs] "=Q" (*(struct vx_array *) &state->vxrs)
+		: [m] "d" (state->mask)
+		: "1", "cc");
+}
+EXPORT_SYMBOL(__kernel_fpu_begin);
+
+void __kernel_fpu_end(struct kernel_fpu *state)
+{
+	/* Just update the per-CPU state if there is nothing to restore */
+	if (!(state->mask & KERNEL_FPU_STATE_MASK))
+		goto update_fpu_state;
+
+	/*
+	 * If KERNEL_FPR is specified, the vector facility is not available
+	 * and, thus, restore floating-point control and registers only.
+	 */
+	if (state->mask & KERNEL_FPR) {
+		asm volatile("lfpc %0" : : "Q" (state->fpc));
+		asm volatile("ld 0,%0" : : "Q" (state->fprs[0]));
+		asm volatile("ld 1,%0" : : "Q" (state->fprs[1]));
+		asm volatile("ld 2,%0" : : "Q" (state->fprs[2]));
+		asm volatile("ld 3,%0" : : "Q" (state->fprs[3]));
+		asm volatile("ld 4,%0" : : "Q" (state->fprs[4]));
+		asm volatile("ld 5,%0" : : "Q" (state->fprs[5]));
+		asm volatile("ld 6,%0" : : "Q" (state->fprs[6]));
+		asm volatile("ld 7,%0" : : "Q" (state->fprs[7]));
+		asm volatile("ld 8,%0" : : "Q" (state->fprs[8]));
+		asm volatile("ld 9,%0" : : "Q" (state->fprs[9]));
+		asm volatile("ld 10,%0" : : "Q" (state->fprs[10]));
+		asm volatile("ld 11,%0" : : "Q" (state->fprs[11]));
+		asm volatile("ld 12,%0" : : "Q" (state->fprs[12]));
+		asm volatile("ld 13,%0" : : "Q" (state->fprs[13]));
+		asm volatile("ld 14,%0" : : "Q" (state->fprs[14]));
+		asm volatile("ld 15,%0" : : "Q" (state->fprs[15]));
+		goto update_fpu_state;
+	}
+
+	/* Test and restore floating-point controls */
+	if (state->mask & KERNEL_FPC)
+		asm volatile("lfpc %0" : : "Q" (state->fpc));
+
+	/* Test and restore (load) vector registers */
+	asm volatile (
+		/*
+		 * Test if any vector registers must be loaded and, if so,
+		 * test if all registers can be loaded at once.
+		 */
+		"	tmll	%[m],15\n"	/* KERNEL_VXR_MASK */
+		"	jz	20f\n"		/* no work -> done */
+		"	la	1,%[vxrs]\n"	/* load load area */
+		"	jo	18f\n"		/* -> load V0..V31 */
+
+		/*
+		 * Test if V8..V23 can be restored at once... this speeds up
+		 * for KERNEL_VXR_MID only. Otherwise continue to split the
+		 * range of vector registers into two halves and test them
+		 * separately.
+		 */
+		"	tmll	%[m],6\n"	/* KERNEL_VXR_MID */
+		"	jo	17f\n"		/* -> load V8..V23 */
+
+		/* Test and load the first half of 16 vector registers */
+		"1:	tmll	%[m],3\n"	/* KERNEL_VXR_LOW */
+		"	jz	10f\n"		/* -> KERNEL_VXR_HIGH */
+		"	jo	2f\n"		/* 11 -> load V0..V15 */
+		"	brc	4,3f\n"		/* 01 -> load V0..V7  */
+		"	brc	2,4f\n"		/* 10 -> load V8..V15 */
+
+		/* Test and load the second half of 16 vector registers */
+		"10:	tmll	%[m],12\n"	/* KERNEL_VXR_HIGH */
+		"	jo	19f\n"		/* 11 -> load V16..V31 */
+		"	brc	4,11f\n"	/* 01 -> load V16..V23	*/
+		"	brc	2,12f\n"	/* 10 -> load V24..V31 */
+		"	j	20f\n"		/* 00 -> done */
+
+		/*
+		 * Below are the vstm combinations to load multiple vector
+		 * registers at once.
+		 */
+		"2:	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
+		"	j	10b\n"			/* -> VXR_HIGH */
+		"3:	.word	0xe707,0x1000,0x0036\n" /* vlm 0,7,0(1) */
+		"	j	10b\n"			/* -> VXR_HIGH */
+		"4:	.word	0xe78f,0x1080,0x0036\n" /* vlm 8,15,128(1) */
+		"	j	10b\n"			/* -> VXR_HIGH */
+		"\n"
+		"11:	.word	0xe707,0x1100,0x0c36\n"	/* vlm 16,23,256(1) */
+		"	j	20f\n"			/* -> done */
+		"12:	.word	0xe78f,0x1180,0x0c36\n" /* vlm 24,31,384(1) */
+		"	j	20f\n"			/* -> done */
+		"\n"
+		"17:	.word	0xe787,0x1080,0x0436\n"	/* vlm 8,23,128(1) */
+		"	nill	%[m],249\n"		/* m &= ~VXR_MID    */
+		"	j	1b\n"			/* -> VXR_LOW */
+		"\n"
+		"18:	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
+		"19:	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
+		"20:"
+		:
+		: [vxrs] "Q" (*(struct vx_array *) &state->vxrs),
+		  [m] "d" (state->mask)
+		: "1", "cc");
+
+update_fpu_state:
+	/* Update current kernel VX state */
+	__this_cpu_write(kernel_fpu_state, state->mask);
+}
+EXPORT_SYMBOL(__kernel_fpu_end);
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index d14069d4b88d..295bfb7124bc 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -121,9 +121,9 @@ static char *dump_type_str(enum dump_type type)
  * Must be in data section since the bss section
  * is not cleared when these are accessed.
  */
-static u8 ipl_ssid __attribute__((__section__(".data"))) = 0;
-static u16 ipl_devno __attribute__((__section__(".data"))) = 0;
-u32 ipl_flags __attribute__((__section__(".data"))) = 0;
+static u8 ipl_ssid __section(.data) = 0;
+static u16 ipl_devno __section(.data) = 0;
+u32 ipl_flags __section(.data) = 0;
 
 enum ipl_method {
 	REIPL_METHOD_CCW_CIO,
@@ -174,7 +174,7 @@ static inline int __diag308(unsigned long subcode, void *addr)
 
 	asm volatile(
 		"	diag	%0,%2,0x308\n"
-		"0:\n"
+		"0:	nopr	%%r7\n"
 		EX_TABLE(0b,0b)
 		: "+d" (_addr), "+d" (_rc)
 		: "d" (subcode) : "cc", "memory");
@@ -563,7 +563,7 @@ static struct kset *ipl_kset;
 
 static void __ipl_run(void *unused)
 {
-	diag308(DIAG308_IPL, NULL);
+	diag308(DIAG308_LOAD_CLEAR, NULL);
 	if (MACHINE_IS_VM)
 		__cpcmd("IPL", NULL, 0, NULL);
 	else if (ipl_info.type == IPL_TYPE_CCW)
@@ -1085,21 +1085,24 @@ static void __reipl_run(void *unused)
 		break;
 	case REIPL_METHOD_CCW_DIAG:
 		diag308(DIAG308_SET, reipl_block_ccw);
-		diag308(DIAG308_IPL, NULL);
+		if (MACHINE_IS_LPAR)
+			diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
+		else
+			diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case REIPL_METHOD_FCP_RW_DIAG:
 		diag308(DIAG308_SET, reipl_block_fcp);
-		diag308(DIAG308_IPL, NULL);
+		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case REIPL_METHOD_FCP_RO_DIAG:
-		diag308(DIAG308_IPL, NULL);
+		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case REIPL_METHOD_FCP_RO_VM:
 		__cpcmd("IPL", NULL, 0, NULL);
 		break;
 	case REIPL_METHOD_NSS_DIAG:
 		diag308(DIAG308_SET, reipl_block_nss);
-		diag308(DIAG308_IPL, NULL);
+		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case REIPL_METHOD_NSS:
 		get_ipl_string(buf, reipl_block_nss, REIPL_METHOD_NSS);
@@ -1108,7 +1111,7 @@ static void __reipl_run(void *unused)
 	case REIPL_METHOD_DEFAULT:
 		if (MACHINE_IS_VM)
 			__cpcmd("IPL", NULL, 0, NULL);
-		diag308(DIAG308_IPL, NULL);
+		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case REIPL_METHOD_FCP_DUMP:
 		break;
@@ -1423,7 +1426,7 @@ static void diag308_dump(void *dump_block)
 {
 	diag308(DIAG308_SET, dump_block);
 	while (1) {
-		if (diag308(DIAG308_DUMP, NULL) != 0x302)
+		if (diag308(DIAG308_LOAD_NORMAL_DUMP, NULL) != 0x302)
 			break;
 		udelay_simple(USEC_PER_SEC);
 	}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index c373a1d41d10..285d6561076d 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -127,9 +127,7 @@ int show_interrupts(struct seq_file *p, void *v)
 			seq_printf(p, "CPU%d       ", cpu);
 		seq_putc(p, '\n');
 	}
-	if (index < NR_IRQS) {
-		if (index >= NR_IRQS_BASE)
-			goto out;
+	if (index < NR_IRQS_BASE) {
 		seq_printf(p, "%s: ", irqclass_main_desc[index].name);
 		irq = irqclass_main_desc[index].irq;
 		for_each_online_cpu(cpu)
@@ -137,6 +135,9 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 		goto out;
 	}
+	if (index > NR_IRQS_BASE)
+		goto out;
+
 	for (index = 0; index < NR_ARCH_IRQS; index++) {
 		seq_printf(p, "%s: ", irqclass_sub_desc[index].name);
 		irq = irqclass_sub_desc[index].irq;
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 0e64f08d3d69..3074c1d83829 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -24,6 +24,7 @@
 #include <asm/diag.h>
 #include <asm/elf.h>
 #include <asm/asm-offsets.h>
+#include <asm/cacheflush.h>
 #include <asm/os_info.h>
 #include <asm/switch_to.h>
 
@@ -60,8 +61,6 @@ static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action,
 static int __init machine_kdump_pm_init(void)
 {
 	pm_notifier(machine_kdump_pm_cb, 0);
-	/* Create initial mapping for crashkernel memory */
-	arch_kexec_unprotect_crashkres();
 	return 0;
 }
 arch_initcall(machine_kdump_pm_init);
@@ -150,42 +149,40 @@ static int kdump_csum_valid(struct kimage *image)
 
 #ifdef CONFIG_CRASH_DUMP
 
-/*
- * Map or unmap crashkernel memory
- */
-static void crash_map_pages(int enable)
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
 {
-	unsigned long size = resource_size(&crashk_res);
-
-	BUG_ON(crashk_res.start % KEXEC_CRASH_MEM_ALIGN ||
-	       size % KEXEC_CRASH_MEM_ALIGN);
-	if (enable)
-		vmem_add_mapping(crashk_res.start, size);
-	else {
-		vmem_remove_mapping(crashk_res.start, size);
-		if (size)
-			os_info_crashkernel_add(crashk_res.start, size);
-		else
-			os_info_crashkernel_add(0, 0);
-	}
+	unsigned long addr, size;
+
+	for (addr = begin; addr < end; addr += PAGE_SIZE)
+		free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
+	size = begin - crashk_res.start;
+	if (size)
+		os_info_crashkernel_add(crashk_res.start, size);
+	else
+		os_info_crashkernel_add(0, 0);
+}
+
+static void crash_protect_pages(int protect)
+{
+	unsigned long size;
+
+	if (!crashk_res.end)
+		return;
+	size = resource_size(&crashk_res);
+	if (protect)
+		set_memory_ro(crashk_res.start, size >> PAGE_SHIFT);
+	else
+		set_memory_rw(crashk_res.start, size >> PAGE_SHIFT);
 }
 
-/*
- * Unmap crashkernel memory
- */
 void arch_kexec_protect_crashkres(void)
 {
-	if (crashk_res.end)
-		crash_map_pages(0);
+	crash_protect_pages(1);
 }
 
-/*
- * Map crashkernel memory
- */
 void arch_kexec_unprotect_crashkres(void)
 {
-	if (crashk_res.end)
-		crash_map_pages(1);
+	crash_protect_pages(0);
 }
 
 #endif
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 07302ce37648..29376f0e725c 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <asm/lowcore.h>
 #include <asm/smp.h>
-#include <asm/etr.h>
+#include <asm/stp.h>
 #include <asm/cputime.h>
 #include <asm/nmi.h>
 #include <asm/crw.h>
@@ -27,7 +27,6 @@ struct mcck_struct {
 	unsigned int kill_task : 1;
 	unsigned int channel_report : 1;
 	unsigned int warning : 1;
-	unsigned int etr_queue : 1;
 	unsigned int stp_queue : 1;
 	unsigned long mcck_code;
 };
@@ -82,8 +81,6 @@ void s390_handle_mcck(void)
 		if (xchg(&mchchk_wng_posted, 1) == 0)
 			kill_cad_pid(SIGPWR, 1);
 	}
-	if (mcck.etr_queue)
-		etr_queue_work();
 	if (mcck.stp_queue)
 		stp_queue_work();
 	if (mcck.kill_task) {
@@ -241,8 +238,6 @@ static int notrace s390_validate_registers(union mci mci)
 
 #define ED_STP_ISLAND	6	/* External damage STP island check */
 #define ED_STP_SYNC	7	/* External damage STP sync check */
-#define ED_ETR_SYNC	12	/* External damage ETR sync check */
-#define ED_ETR_SWITCH	13	/* External damage ETR switch to local */
 
 /*
  * machine check handler.
@@ -325,15 +320,11 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	}
 	if (mci.ed && mci.ec) {
 		/* External damage */
-		if (S390_lowcore.external_damage_code & (1U << ED_ETR_SYNC))
-			mcck->etr_queue |= etr_sync_check();
-		if (S390_lowcore.external_damage_code & (1U << ED_ETR_SWITCH))
-			mcck->etr_queue |= etr_switch_to_local();
 		if (S390_lowcore.external_damage_code & (1U << ED_STP_SYNC))
 			mcck->stp_queue |= stp_sync_check();
 		if (S390_lowcore.external_damage_code & (1U << ED_STP_ISLAND))
 			mcck->stp_queue |= stp_island_check();
-		if (mcck->etr_queue || mcck->stp_queue)
+		if (mcck->stp_queue)
 			set_cpu_flag(CIF_MCCK_PENDING);
 	}
 	if (mci.se)
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index a8e832166417..9ea26dface38 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -601,17 +601,12 @@ static void release_pmc_hardware(void)
 
 	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
-	perf_release_sampling();
 }
 
 static int reserve_pmc_hardware(void)
 {
 	int flags = PMC_INIT;
-	int err;
 
-	err = perf_reserve_sampling();
-	if (err)
-		return err;
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
 	if (flags & PMC_FAILURE) {
 		release_pmc_hardware();
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 87035fa58bbe..17431f63de00 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -248,33 +248,3 @@ ssize_t cpumf_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%04llx,name=%s\n",
 		       pmu_attr->id, attr->attr.name);
 }
-
-/* Reserve/release functions for sharing perf hardware */
-static DEFINE_SPINLOCK(perf_hw_owner_lock);
-static void *perf_sampling_owner;
-
-int perf_reserve_sampling(void)
-{
-	int err;
-
-	err = 0;
-	spin_lock(&perf_hw_owner_lock);
-	if (perf_sampling_owner) {
-		pr_warn("The sampling facility is already reserved by %p\n",
-			perf_sampling_owner);
-		err = -EBUSY;
-	} else
-		perf_sampling_owner = __builtin_return_address(0);
-	spin_unlock(&perf_hw_owner_lock);
-	return err;
-}
-EXPORT_SYMBOL(perf_reserve_sampling);
-
-void perf_release_sampling(void)
-{
-	spin_lock(&perf_hw_owner_lock);
-	WARN_ON(!perf_sampling_owner);
-	perf_sampling_owner = NULL;
-	spin_unlock(&perf_hw_owner_lock);
-}
-EXPORT_SYMBOL(perf_release_sampling);
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index de7451065c34..81d0808085e6 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -13,12 +13,45 @@
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <asm/diag.h>
+#include <asm/facility.h>
 #include <asm/elf.h>
 #include <asm/lowcore.h>
 #include <asm/param.h>
 #include <asm/smp.h>
 
-static DEFINE_PER_CPU(struct cpuid, cpu_id);
+struct cpu_info {
+	unsigned int cpu_mhz_dynamic;
+	unsigned int cpu_mhz_static;
+	struct cpuid cpu_id;
+};
+
+static DEFINE_PER_CPU(struct cpu_info, cpu_info);
+
+static bool machine_has_cpu_mhz;
+
+void __init cpu_detect_mhz_feature(void)
+{
+	if (test_facility(34) && __ecag(ECAG_CPU_ATTRIBUTE, 0) != -1UL)
+		machine_has_cpu_mhz = 1;
+}
+
+static void update_cpu_mhz(void *arg)
+{
+	unsigned long mhz;
+	struct cpu_info *c;
+
+	mhz = __ecag(ECAG_CPU_ATTRIBUTE, 0);
+	c = this_cpu_ptr(&cpu_info);
+	c->cpu_mhz_dynamic = mhz >> 32;
+	c->cpu_mhz_static = mhz & 0xffffffff;
+}
+
+void s390_update_cpu_mhz(void)
+{
+	s390_adjust_jiffies();
+	if (machine_has_cpu_mhz)
+		on_each_cpu(update_cpu_mhz, NULL, 0);
+}
 
 void notrace cpu_relax(void)
 {
@@ -35,9 +68,11 @@ EXPORT_SYMBOL(cpu_relax);
  */
 void cpu_init(void)
 {
-	struct cpuid *id = this_cpu_ptr(&cpu_id);
+	struct cpuid *id = this_cpu_ptr(&cpu_info.cpu_id);
 
 	get_cpu_id(id);
+	if (machine_has_cpu_mhz)
+		update_cpu_mhz(NULL);
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
 	BUG_ON(current->mm);
@@ -53,10 +88,7 @@ int cpu_have_feature(unsigned int num)
 }
 EXPORT_SYMBOL(cpu_have_feature);
 
-/*
- * show_cpuinfo - Get information on one CPU for use by procfs.
- */
-static int show_cpuinfo(struct seq_file *m, void *v)
+static void show_cpu_summary(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
@@ -65,34 +97,55 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	static const char * const int_hwcap_str[] = {
 		"sie"
 	};
-	unsigned long n = (unsigned long) v - 1;
-	int i;
-
-	if (!n) {
-		s390_adjust_jiffies();
-		seq_printf(m, "vendor_id       : IBM/S390\n"
-			   "# processors    : %i\n"
-			   "bogomips per cpu: %lu.%02lu\n",
-			   num_online_cpus(), loops_per_jiffy/(500000/HZ),
-			   (loops_per_jiffy/(5000/HZ))%100);
-		seq_puts(m, "features\t: ");
-		for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
-			if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
-				seq_printf(m, "%s ", hwcap_str[i]);
-		for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++)
-			if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
-				seq_printf(m, "%s ", int_hwcap_str[i]);
-		seq_puts(m, "\n");
-		show_cacheinfo(m);
-	}
-	if (cpu_online(n)) {
-		struct cpuid *id = &per_cpu(cpu_id, n);
-		seq_printf(m, "processor %li: "
+	int i, cpu;
+
+	seq_printf(m, "vendor_id       : IBM/S390\n"
+		   "# processors    : %i\n"
+		   "bogomips per cpu: %lu.%02lu\n",
+		   num_online_cpus(), loops_per_jiffy/(500000/HZ),
+		   (loops_per_jiffy/(5000/HZ))%100);
+	seq_printf(m, "max thread id   : %d\n", smp_cpu_mtid);
+	seq_puts(m, "features\t: ");
+	for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
+		if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
+			seq_printf(m, "%s ", hwcap_str[i]);
+	for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++)
+		if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
+			seq_printf(m, "%s ", int_hwcap_str[i]);
+	seq_puts(m, "\n");
+	show_cacheinfo(m);
+	for_each_online_cpu(cpu) {
+		struct cpuid *id = &per_cpu(cpu_info.cpu_id, cpu);
+
+		seq_printf(m, "processor %d: "
 			   "version = %02X,  "
 			   "identification = %06X,  "
 			   "machine = %04X\n",
-			   n, id->version, id->ident, id->machine);
+			   cpu, id->version, id->ident, id->machine);
 	}
+}
+
+static void show_cpu_mhz(struct seq_file *m, unsigned long n)
+{
+	struct cpu_info *c = per_cpu_ptr(&cpu_info, n);
+
+	seq_printf(m, "cpu MHz dynamic : %d\n", c->cpu_mhz_dynamic);
+	seq_printf(m, "cpu MHz static  : %d\n", c->cpu_mhz_static);
+}
+
+/*
+ * show_cpuinfo - Get information on one CPU for use by procfs.
+ */
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	unsigned long n = (unsigned long) v - 1;
+
+	if (!n)
+		show_cpu_summary(m, v);
+	if (!machine_has_cpu_mhz)
+		return 0;
+	seq_printf(m, "\ncpu number      : %ld\n", n);
+	show_cpu_mhz(m, n);
 	return 0;
 }
 
@@ -126,4 +179,3 @@ const struct seq_operations cpuinfo_op = {
 	.stop	= c_stop,
 	.show	= show_cpuinfo,
 };
-
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f31939147ccd..ba5f456edaa9 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -130,17 +130,14 @@ __setup("condev=", condev_setup);
 
 static void __init set_preferred_console(void)
 {
-	if (MACHINE_IS_KVM) {
-		if (sclp.has_vt220)
-			add_preferred_console("ttyS", 1, NULL);
-		else if (sclp.has_linemode)
-			add_preferred_console("ttyS", 0, NULL);
-		else
-			add_preferred_console("hvc", 0, NULL);
-	} else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP)
+	if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP)
 		add_preferred_console("ttyS", 0, NULL);
 	else if (CONSOLE_IS_3270)
 		add_preferred_console("tty3270", 0, NULL);
+	else if (CONSOLE_IS_VT220)
+		add_preferred_console("ttyS", 1, NULL);
+	else if (CONSOLE_IS_HVC)
+		add_preferred_console("hvc", 0, NULL);
 }
 
 static int __init conmode_setup(char *str)
@@ -206,6 +203,15 @@ static void __init conmode_default(void)
 			SET_CONSOLE_SCLP;
 #endif
 		}
+	} else if (MACHINE_IS_KVM) {
+		if (sclp.has_vt220 &&
+		    config_enabled(CONFIG_SCLP_VT220_CONSOLE))
+			SET_CONSOLE_VT220;
+		else if (sclp.has_linemode &&
+			 config_enabled(CONFIG_SCLP_CONSOLE))
+			SET_CONSOLE_SCLP;
+		else
+			SET_CONSOLE_HVC;
 	} else {
 #if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
 		SET_CONSOLE_SCLP;
@@ -289,7 +295,7 @@ static int __init parse_vmalloc(char *arg)
 }
 early_param("vmalloc", parse_vmalloc);
 
-void *restart_stack __attribute__((__section__(".data")));
+void *restart_stack __section(.data);
 
 static void __init setup_lowcore(void)
 {
@@ -432,6 +438,20 @@ static void __init setup_resources(void)
 			}
 		}
 	}
+#ifdef CONFIG_CRASH_DUMP
+	/*
+	 * Re-add removed crash kernel memory as reserved memory. This makes
+	 * sure it will be mapped with the identity mapping and struct pages
+	 * will be created, so it can be resized later on.
+	 * However add it later since the crash kernel resource should not be
+	 * part of the System RAM resource.
+	 */
+	if (crashk_res.end) {
+		memblock_add(crashk_res.start, resource_size(&crashk_res));
+		memblock_reserve(crashk_res.start, resource_size(&crashk_res));
+		insert_resource(&iomem_resource, &crashk_res);
+	}
+#endif
 }
 
 static void __init setup_memory_end(void)
@@ -602,7 +622,6 @@ static void __init reserve_crashkernel(void)
 		diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
-	insert_resource(&iomem_resource, &crashk_res);
 	memblock_remove(crash_base, crash_size);
 	pr_info("Reserving %lluMB of memory at %lluMB "
 		"for crashkernel (System RAM: %luMB)\n",
@@ -901,6 +920,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
+	cpu_detect_mhz_feature();
         cpu_init();
 	numa_setup();
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 7b89a7572100..35531fe1c5ea 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -242,10 +242,8 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 {
 	struct lowcore *lc = pcpu->lowcore;
 
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
+	cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
 	cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
-	atomic_inc(&init_mm.context.attach_count);
 	lc->cpu_nr = cpu;
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
 	lc->percpu_offset = __per_cpu_offset[cpu];
@@ -320,17 +318,11 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *),
  */
 static int pcpu_set_smt(unsigned int mtid)
 {
-	register unsigned long reg1 asm ("1") = (unsigned long) mtid;
 	int cc;
 
 	if (smp_cpu_mtid == mtid)
 		return 0;
-	asm volatile(
-		"	sigp	%1,0,%2	# sigp set multi-threading\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (cc) : "d" (reg1), "K" (SIGP_SET_MULTI_THREADING)
-		: "cc");
+	cc = __pcpu_sigp(0, SIGP_SET_MULTI_THREADING, mtid, NULL);
 	if (cc == 0) {
 		smp_cpu_mtid = mtid;
 		smp_cpu_mt_shift = 0;
@@ -876,10 +868,8 @@ void __cpu_die(unsigned int cpu)
 	while (!pcpu_stopped(pcpu))
 		cpu_relax();
 	pcpu_free_lowcore(pcpu);
-	atomic_dec(&init_mm.context.attach_count);
 	cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
+	cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
 }
 
 void __noreturn cpu_die(void)
@@ -897,7 +887,7 @@ void __init smp_fill_possible_mask(void)
 
 	sclp_max = max(sclp.mtid, sclp.mtid_cp) + 1;
 	sclp_max = min(smp_max_threads, sclp_max);
-	sclp_max = sclp.max_cores * sclp_max ?: nr_cpu_ids;
+	sclp_max = (sclp.max_cores * sclp_max) ?: nr_cpu_ids;
 	possible = setup_possible_cpus ?: nr_cpu_ids;
 	possible = min(possible, sclp_max);
 	for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index f7dba3887a54..050b8d067d3b 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -16,21 +16,11 @@
 #include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
 #include <asm/topology.h>
-
-/* Sigh, math-emu. Don't ask. */
-#include <asm/sfp-util.h>
-#include <math-emu/soft-fp.h>
-#include <math-emu/single.h>
+#include <asm/fpu/api.h>
 
 int topology_max_mnest;
 
-/*
- * stsi - store system information
- *
- * Returns the current configuration level if function code 0 was specified.
- * Otherwise returns 0 on success or a negative value on error.
- */
-int stsi(void *sysinfo, int fc, int sel1, int sel2)
+static inline int __stsi(void *sysinfo, int fc, int sel1, int sel2, int *lvl)
 {
 	register int r0 asm("0") = (fc << 28) | sel1;
 	register int r1 asm("1") = sel2;
@@ -45,9 +35,24 @@ int stsi(void *sysinfo, int fc, int sel1, int sel2)
 		: "+d" (r0), "+d" (rc)
 		: "d" (r1), "a" (sysinfo), "K" (-EOPNOTSUPP)
 		: "cc", "memory");
+	*lvl = ((unsigned int) r0) >> 28;
+	return rc;
+}
+
+/*
+ * stsi - store system information
+ *
+ * Returns the current configuration level if function code 0 was specified.
+ * Otherwise returns 0 on success or a negative value on error.
+ */
+int stsi(void *sysinfo, int fc, int sel1, int sel2)
+{
+	int lvl, rc;
+
+	rc = __stsi(sysinfo, fc, sel1, sel2, &lvl);
 	if (rc)
 		return rc;
-	return fc ? 0 : ((unsigned int) r0) >> 28;
+	return fc ? 0 : lvl;
 }
 EXPORT_SYMBOL(stsi);
 
@@ -414,10 +419,8 @@ subsys_initcall(create_proc_service_level);
 void s390_adjust_jiffies(void)
 {
 	struct sysinfo_1_2_2 *info;
-	const unsigned int fmil = 0x4b189680;	/* 1e7 as 32-bit float. */
-	FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR);
-	FP_DECL_EX;
-	unsigned int capability;
+	unsigned long capability;
+	struct kernel_fpu fpu;
 
 	info = (void *) get_zeroed_page(GFP_KERNEL);
 	if (!info)
@@ -433,15 +436,25 @@ void s390_adjust_jiffies(void)
 		 * higher cpu capacity. Bogomips are the other way round.
 		 * To get to a halfway suitable number we divide 1e7
 		 * by the cpu capability number. Yes, that means a floating
-		 * point division .. math-emu here we come :-)
+		 * point division ..
 		 */
-		FP_UNPACK_SP(SA, &fmil);
-		if ((info->capability >> 23) == 0)
-			FP_FROM_INT_S(SB, (long) info->capability, 64, long);
-		else
-			FP_UNPACK_SP(SB, &info->capability);
-		FP_DIV_S(SR, SA, SB);
-		FP_TO_INT_S(capability, SR, 32, 0);
+		kernel_fpu_begin(&fpu, KERNEL_FPR);
+		asm volatile(
+			"	sfpc	%3\n"
+			"	l	%0,%1\n"
+			"	tmlh	%0,0xff80\n"
+			"	jnz	0f\n"
+			"	cefbr	%%f2,%0\n"
+			"	j	1f\n"
+			"0:	le	%%f2,%1\n"
+			"1:	cefbr	%%f0,%2\n"
+			"	debr	%%f0,%%f2\n"
+			"	cgebr	%0,5,%%f0\n"
+			: "=&d" (capability)
+			: "Q" (info->capability), "d" (10000000), "d" (0)
+			: "cc"
+			);
+		kernel_fpu_end(&fpu);
 	} else
 		/*
 		 * Really old machine without stsi block for basic
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 9409d32f285e..4e9949800562 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -39,13 +39,14 @@
 #include <linux/gfp.h>
 #include <linux/kprobes.h>
 #include <asm/uaccess.h>
+#include <asm/facility.h>
 #include <asm/delay.h>
 #include <asm/div64.h>
 #include <asm/vdso.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/vtimer.h>
-#include <asm/etr.h>
+#include <asm/stp.h>
 #include <asm/cio.h>
 #include "entry.h"
 
@@ -61,6 +62,32 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators);
 ATOMIC_NOTIFIER_HEAD(s390_epoch_delta_notifier);
 EXPORT_SYMBOL(s390_epoch_delta_notifier);
 
+unsigned char ptff_function_mask[16];
+unsigned long lpar_offset;
+unsigned long initial_leap_seconds;
+
+/*
+ * Get time offsets with PTFF
+ */
+void __init ptff_init(void)
+{
+	struct ptff_qto qto;
+	struct ptff_qui qui;
+
+	if (!test_facility(28))
+		return;
+	ptff(&ptff_function_mask, sizeof(ptff_function_mask), PTFF_QAF);
+
+	/* get LPAR offset */
+	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
+		lpar_offset = qto.tod_epoch_difference;
+
+	/* get initial leap seconds */
+	if (ptff_query(PTFF_QUI) && ptff(&qui, sizeof(qui), PTFF_QUI) == 0)
+		initial_leap_seconds = (unsigned long)
+			((long) qui.old_leap * 4096000000L);
+}
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -162,30 +189,32 @@ static void clock_comparator_interrupt(struct ext_code ext_code,
 		set_clock_comparator(S390_lowcore.clock_comparator);
 }
 
-static void etr_timing_alert(struct etr_irq_parm *);
 static void stp_timing_alert(struct stp_irq_parm *);
 
 static void timing_alert_interrupt(struct ext_code ext_code,
 				   unsigned int param32, unsigned long param64)
 {
 	inc_irq_stat(IRQEXT_TLA);
-	if (param32 & 0x00c40000)
-		etr_timing_alert((struct etr_irq_parm *) &param32);
 	if (param32 & 0x00038000)
 		stp_timing_alert((struct stp_irq_parm *) &param32);
 }
 
-static void etr_reset(void);
 static void stp_reset(void);
 
 void read_persistent_clock64(struct timespec64 *ts)
 {
-	tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts);
+	__u64 clock;
+
+	clock = get_tod_clock() - initial_leap_seconds;
+	tod_to_timeval(clock - TOD_UNIX_EPOCH, ts);
 }
 
 void read_boot_clock64(struct timespec64 *ts)
 {
-	tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
+	__u64 clock;
+
+	clock = sched_clock_base_cc - initial_leap_seconds;
+	tod_to_timeval(clock - TOD_UNIX_EPOCH, ts);
 }
 
 static cycle_t read_tod_clock(struct clocksource *cs)
@@ -269,7 +298,6 @@ void update_vsyscall_tz(void)
 void __init time_init(void)
 {
 	/* Reset time synchronization interfaces. */
-	etr_reset();
 	stp_reset();
 
 	/* request the clock comparator external interrupt */
@@ -337,20 +365,20 @@ static unsigned long clock_sync_flags;
 #define CLOCK_SYNC_STP		3
 
 /*
- * The synchronous get_clock function. It will write the current clock
- * value to the clock pointer and return 0 if the clock is in sync with
- * the external time source. If the clock mode is local it will return
- * -EOPNOTSUPP and -EAGAIN if the clock is not in sync with the external
- * reference.
+ * The get_clock function for the physical clock. It will get the current
+ * TOD clock, subtract the LPAR offset and write the result to *clock.
+ * The function returns 0 if the clock is in sync with the external time
+ * source. If the clock mode is local it will return -EOPNOTSUPP and
+ * -EAGAIN if the clock is not in sync with the external reference.
  */
-int get_sync_clock(unsigned long long *clock)
+int get_phys_clock(unsigned long long *clock)
 {
 	atomic_t *sw_ptr;
 	unsigned int sw0, sw1;
 
 	sw_ptr = &get_cpu_var(clock_sync_word);
 	sw0 = atomic_read(sw_ptr);
-	*clock = get_tod_clock();
+	*clock = get_tod_clock() - lpar_offset;
 	sw1 = atomic_read(sw_ptr);
 	put_cpu_var(clock_sync_word);
 	if (sw0 == sw1 && (sw0 & 0x80000000U))
@@ -364,7 +392,7 @@ int get_sync_clock(unsigned long long *clock)
 		return -EACCES;
 	return -EAGAIN;
 }
-EXPORT_SYMBOL(get_sync_clock);
+EXPORT_SYMBOL(get_phys_clock);
 
 /*
  * Make get_sync_clock return -EAGAIN.
@@ -416,301 +444,6 @@ static void __init time_init_wq(void)
 	time_sync_wq = create_singlethread_workqueue("timesync");
 }
 
-/*
- * External Time Reference (ETR) code.
- */
-static int etr_port0_online;
-static int etr_port1_online;
-static int etr_steai_available;
-
-static int __init early_parse_etr(char *p)
-{
-	if (strncmp(p, "off", 3) == 0)
-		etr_port0_online = etr_port1_online = 0;
-	else if (strncmp(p, "port0", 5) == 0)
-		etr_port0_online = 1;
-	else if (strncmp(p, "port1", 5) == 0)
-		etr_port1_online = 1;
-	else if (strncmp(p, "on", 2) == 0)
-		etr_port0_online = etr_port1_online = 1;
-	return 0;
-}
-early_param("etr", early_parse_etr);
-
-enum etr_event {
-	ETR_EVENT_PORT0_CHANGE,
-	ETR_EVENT_PORT1_CHANGE,
-	ETR_EVENT_PORT_ALERT,
-	ETR_EVENT_SYNC_CHECK,
-	ETR_EVENT_SWITCH_LOCAL,
-	ETR_EVENT_UPDATE,
-};
-
-/*
- * Valid bit combinations of the eacr register are (x = don't care):
- * e0 e1 dp p0 p1 ea es sl
- *  0  0  x  0	0  0  0  0  initial, disabled state
- *  0  0  x  0	1  1  0  0  port 1 online
- *  0  0  x  1	0  1  0  0  port 0 online
- *  0  0  x  1	1  1  0  0  both ports online
- *  0  1  x  0	1  1  0  0  port 1 online and usable, ETR or PPS mode
- *  0  1  x  0	1  1  0  1  port 1 online, usable and ETR mode
- *  0  1  x  0	1  1  1  0  port 1 online, usable, PPS mode, in-sync
- *  0  1  x  0	1  1  1  1  port 1 online, usable, ETR mode, in-sync
- *  0  1  x  1	1  1  0  0  both ports online, port 1 usable
- *  0  1  x  1	1  1  1  0  both ports online, port 1 usable, PPS mode, in-sync
- *  0  1  x  1	1  1  1  1  both ports online, port 1 usable, ETR mode, in-sync
- *  1  0  x  1	0  1  0  0  port 0 online and usable, ETR or PPS mode
- *  1  0  x  1	0  1  0  1  port 0 online, usable and ETR mode
- *  1  0  x  1	0  1  1  0  port 0 online, usable, PPS mode, in-sync
- *  1  0  x  1	0  1  1  1  port 0 online, usable, ETR mode, in-sync
- *  1  0  x  1	1  1  0  0  both ports online, port 0 usable
- *  1  0  x  1	1  1  1  0  both ports online, port 0 usable, PPS mode, in-sync
- *  1  0  x  1	1  1  1  1  both ports online, port 0 usable, ETR mode, in-sync
- *  1  1  x  1	1  1  1  0  both ports online & usable, ETR, in-sync
- *  1  1  x  1	1  1  1  1  both ports online & usable, ETR, in-sync
- */
-static struct etr_eacr etr_eacr;
-static u64 etr_tolec;			/* time of last eacr update */
-static struct etr_aib etr_port0;
-static int etr_port0_uptodate;
-static struct etr_aib etr_port1;
-static int etr_port1_uptodate;
-static unsigned long etr_events;
-static struct timer_list etr_timer;
-
-static void etr_timeout(unsigned long dummy);
-static void etr_work_fn(struct work_struct *work);
-static DEFINE_MUTEX(etr_work_mutex);
-static DECLARE_WORK(etr_work, etr_work_fn);
-
-/*
- * Reset ETR attachment.
- */
-static void etr_reset(void)
-{
-	etr_eacr =  (struct etr_eacr) {
-		.e0 = 0, .e1 = 0, ._pad0 = 4, .dp = 0,
-		.p0 = 0, .p1 = 0, ._pad1 = 0, .ea = 0,
-		.es = 0, .sl = 0 };
-	if (etr_setr(&etr_eacr) == 0) {
-		etr_tolec = get_tod_clock();
-		set_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags);
-		if (etr_port0_online && etr_port1_online)
-			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
-	} else if (etr_port0_online || etr_port1_online) {
-		pr_warn("The real or virtual hardware system does not provide an ETR interface\n");
-		etr_port0_online = etr_port1_online = 0;
-	}
-}
-
-static int __init etr_init(void)
-{
-	struct etr_aib aib;
-
-	if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
-		return 0;
-	time_init_wq();
-	/* Check if this machine has the steai instruction. */
-	if (etr_steai(&aib, ETR_STEAI_STEPPING_PORT) == 0)
-		etr_steai_available = 1;
-	setup_timer(&etr_timer, etr_timeout, 0UL);
-	if (etr_port0_online) {
-		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
-		queue_work(time_sync_wq, &etr_work);
-	}
-	if (etr_port1_online) {
-		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
-		queue_work(time_sync_wq, &etr_work);
-	}
-	return 0;
-}
-
-arch_initcall(etr_init);
-
-/*
- * Two sorts of ETR machine checks. The architecture reads:
- * "When a machine-check niterruption occurs and if a switch-to-local or
- *  ETR-sync-check interrupt request is pending but disabled, this pending
- *  disabled interruption request is indicated and is cleared".
- * Which means that we can get etr_switch_to_local events from the machine
- * check handler although the interruption condition is disabled. Lovely..
- */
-
-/*
- * Switch to local machine check. This is called when the last usable
- * ETR port goes inactive. After switch to local the clock is not in sync.
- */
-int etr_switch_to_local(void)
-{
-	if (!etr_eacr.sl)
-		return 0;
-	disable_sync_clock(NULL);
-	if (!test_and_set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events)) {
-		etr_eacr.es = etr_eacr.sl = 0;
-		etr_setr(&etr_eacr);
-		return 1;
-	}
-	return 0;
-}
-
-/*
- * ETR sync check machine check. This is called when the ETR OTE and the
- * local clock OTE are farther apart than the ETR sync check tolerance.
- * After a ETR sync check the clock is not in sync. The machine check
- * is broadcasted to all cpus at the same time.
- */
-int etr_sync_check(void)
-{
-	if (!etr_eacr.es)
-		return 0;
-	disable_sync_clock(NULL);
-	if (!test_and_set_bit(ETR_EVENT_SYNC_CHECK, &etr_events)) {
-		etr_eacr.es = 0;
-		etr_setr(&etr_eacr);
-		return 1;
-	}
-	return 0;
-}
-
-void etr_queue_work(void)
-{
-	queue_work(time_sync_wq, &etr_work);
-}
-
-/*
- * ETR timing alert. There are two causes:
- * 1) port state change, check the usability of the port
- * 2) port alert, one of the ETR-data-validity bits (v1-v2 bits of the
- *    sldr-status word) or ETR-data word 1 (edf1) or ETR-data word 3 (edf3)
- *    or ETR-data word 4 (edf4) has changed.
- */
-static void etr_timing_alert(struct etr_irq_parm *intparm)
-{
-	if (intparm->pc0)
-		/* ETR port 0 state change. */
-		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
-	if (intparm->pc1)
-		/* ETR port 1 state change. */
-		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
-	if (intparm->eai)
-		/*
-		 * ETR port alert on either port 0, 1 or both.
-		 * Both ports are not up-to-date now.
-		 */
-		set_bit(ETR_EVENT_PORT_ALERT, &etr_events);
-	queue_work(time_sync_wq, &etr_work);
-}
-
-static void etr_timeout(unsigned long dummy)
-{
-	set_bit(ETR_EVENT_UPDATE, &etr_events);
-	queue_work(time_sync_wq, &etr_work);
-}
-
-/*
- * Check if the etr mode is pss.
- */
-static inline int etr_mode_is_pps(struct etr_eacr eacr)
-{
-	return eacr.es && !eacr.sl;
-}
-
-/*
- * Check if the etr mode is etr.
- */
-static inline int etr_mode_is_etr(struct etr_eacr eacr)
-{
-	return eacr.es && eacr.sl;
-}
-
-/*
- * Check if the port can be used for TOD synchronization.
- * For PPS mode the port has to receive OTEs. For ETR mode
- * the port has to receive OTEs, the ETR stepping bit has to
- * be zero and the validity bits for data frame 1, 2, and 3
- * have to be 1.
- */
-static int etr_port_valid(struct etr_aib *aib, int port)
-{
-	unsigned int psc;
-
-	/* Check that this port is receiving OTEs. */
-	if (aib->tsp == 0)
-		return 0;
-
-	psc = port ? aib->esw.psc1 : aib->esw.psc0;
-	if (psc == etr_lpsc_pps_mode)
-		return 1;
-	if (psc == etr_lpsc_operational_step)
-		return !aib->esw.y && aib->slsw.v1 &&
-			aib->slsw.v2 && aib->slsw.v3;
-	return 0;
-}
-
-/*
- * Check if two ports are on the same network.
- */
-static int etr_compare_network(struct etr_aib *aib1, struct etr_aib *aib2)
-{
-	// FIXME: any other fields we have to compare?
-	return aib1->edf1.net_id == aib2->edf1.net_id;
-}
-
-/*
- * Wrapper for etr_stei that converts physical port states
- * to logical port states to be consistent with the output
- * of stetr (see etr_psc vs. etr_lpsc).
- */
-static void etr_steai_cv(struct etr_aib *aib, unsigned int func)
-{
-	BUG_ON(etr_steai(aib, func) != 0);
-	/* Convert port state to logical port state. */
-	if (aib->esw.psc0 == 1)
-		aib->esw.psc0 = 2;
-	else if (aib->esw.psc0 == 0 && aib->esw.p == 0)
-		aib->esw.psc0 = 1;
-	if (aib->esw.psc1 == 1)
-		aib->esw.psc1 = 2;
-	else if (aib->esw.psc1 == 0 && aib->esw.p == 1)
-		aib->esw.psc1 = 1;
-}
-
-/*
- * Check if the aib a2 is still connected to the same attachment as
- * aib a1, the etv values differ by one and a2 is valid.
- */
-static int etr_aib_follows(struct etr_aib *a1, struct etr_aib *a2, int p)
-{
-	int state_a1, state_a2;
-
-	/* Paranoia check: e0/e1 should better be the same. */
-	if (a1->esw.eacr.e0 != a2->esw.eacr.e0 ||
-	    a1->esw.eacr.e1 != a2->esw.eacr.e1)
-		return 0;
-
-	/* Still connected to the same etr ? */
-	state_a1 = p ? a1->esw.psc1 : a1->esw.psc0;
-	state_a2 = p ? a2->esw.psc1 : a2->esw.psc0;
-	if (state_a1 == etr_lpsc_operational_step) {
-		if (state_a2 != etr_lpsc_operational_step ||
-		    a1->edf1.net_id != a2->edf1.net_id ||
-		    a1->edf1.etr_id != a2->edf1.etr_id ||
-		    a1->edf1.etr_pn != a2->edf1.etr_pn)
-			return 0;
-	} else if (state_a2 != etr_lpsc_pps_mode)
-		return 0;
-
-	/* The ETV value of a2 needs to be ETV of a1 + 1. */
-	if (a1->edf2.etv + 1 != a2->edf2.etv)
-		return 0;
-
-	if (!etr_port_valid(a2, p))
-		return 0;
-
-	return 1;
-}
-
 struct clock_sync_data {
 	atomic_t cpus;
 	int in_sync;
@@ -748,688 +481,6 @@ static void clock_sync_cpu(struct clock_sync_data *sync)
 }
 
 /*
- * Sync the TOD clock using the port referred to by aibp. This port
- * has to be enabled and the other port has to be disabled. The
- * last eacr update has to be more than 1.6 seconds in the past.
- */
-static int etr_sync_clock(void *data)
-{
-	static int first;
-	unsigned long long clock, old_clock, clock_delta, delay, delta;
-	struct clock_sync_data *etr_sync;
-	struct etr_aib *sync_port, *aib;
-	int port;
-	int rc;
-
-	etr_sync = data;
-
-	if (xchg(&first, 1) == 1) {
-		/* Slave */
-		clock_sync_cpu(etr_sync);
-		return 0;
-	}
-
-	/* Wait until all other cpus entered the sync function. */
-	while (atomic_read(&etr_sync->cpus) != 0)
-		cpu_relax();
-
-	port = etr_sync->etr_port;
-	aib = etr_sync->etr_aib;
-	sync_port = (port == 0) ? &etr_port0 : &etr_port1;
-	enable_sync_clock();
-
-	/* Set clock to next OTE. */
-	__ctl_set_bit(14, 21);
-	__ctl_set_bit(0, 29);
-	clock = ((unsigned long long) (aib->edf2.etv + 1)) << 32;
-	old_clock = get_tod_clock();
-	if (set_tod_clock(clock) == 0) {
-		__udelay(1);	/* Wait for the clock to start. */
-		__ctl_clear_bit(0, 29);
-		__ctl_clear_bit(14, 21);
-		etr_stetr(aib);
-		/* Adjust Linux timing variables. */
-		delay = (unsigned long long)
-			(aib->edf2.etv - sync_port->edf2.etv) << 32;
-		delta = adjust_time(old_clock, clock, delay);
-		clock_delta = clock - old_clock;
-		atomic_notifier_call_chain(&s390_epoch_delta_notifier, 0,
-					   &clock_delta);
-		etr_sync->fixup_cc = delta;
-		fixup_clock_comparator(delta);
-		/* Verify that the clock is properly set. */
-		if (!etr_aib_follows(sync_port, aib, port)) {
-			/* Didn't work. */
-			disable_sync_clock(NULL);
-			etr_sync->in_sync = -EAGAIN;
-			rc = -EAGAIN;
-		} else {
-			etr_sync->in_sync = 1;
-			rc = 0;
-		}
-	} else {
-		/* Could not set the clock ?!? */
-		__ctl_clear_bit(0, 29);
-		__ctl_clear_bit(14, 21);
-		disable_sync_clock(NULL);
-		etr_sync->in_sync = -EAGAIN;
-		rc = -EAGAIN;
-	}
-	xchg(&first, 0);
-	return rc;
-}
-
-static int etr_sync_clock_stop(struct etr_aib *aib, int port)
-{
-	struct clock_sync_data etr_sync;
-	struct etr_aib *sync_port;
-	int follows;
-	int rc;
-
-	/* Check if the current aib is adjacent to the sync port aib. */
-	sync_port = (port == 0) ? &etr_port0 : &etr_port1;
-	follows = etr_aib_follows(sync_port, aib, port);
-	memcpy(sync_port, aib, sizeof(*aib));
-	if (!follows)
-		return -EAGAIN;
-	memset(&etr_sync, 0, sizeof(etr_sync));
-	etr_sync.etr_aib = aib;
-	etr_sync.etr_port = port;
-	get_online_cpus();
-	atomic_set(&etr_sync.cpus, num_online_cpus() - 1);
-	rc = stop_machine(etr_sync_clock, &etr_sync, cpu_online_mask);
-	put_online_cpus();
-	return rc;
-}
-
-/*
- * Handle the immediate effects of the different events.
- * The port change event is used for online/offline changes.
- */
-static struct etr_eacr etr_handle_events(struct etr_eacr eacr)
-{
-	if (test_and_clear_bit(ETR_EVENT_SYNC_CHECK, &etr_events))
-		eacr.es = 0;
-	if (test_and_clear_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events))
-		eacr.es = eacr.sl = 0;
-	if (test_and_clear_bit(ETR_EVENT_PORT_ALERT, &etr_events))
-		etr_port0_uptodate = etr_port1_uptodate = 0;
-
-	if (test_and_clear_bit(ETR_EVENT_PORT0_CHANGE, &etr_events)) {
-		if (eacr.e0)
-			/*
-			 * Port change of an enabled port. We have to
-			 * assume that this can have caused an stepping
-			 * port switch.
-			 */
-			etr_tolec = get_tod_clock();
-		eacr.p0 = etr_port0_online;
-		if (!eacr.p0)
-			eacr.e0 = 0;
-		etr_port0_uptodate = 0;
-	}
-	if (test_and_clear_bit(ETR_EVENT_PORT1_CHANGE, &etr_events)) {
-		if (eacr.e1)
-			/*
-			 * Port change of an enabled port. We have to
-			 * assume that this can have caused an stepping
-			 * port switch.
-			 */
-			etr_tolec = get_tod_clock();
-		eacr.p1 = etr_port1_online;
-		if (!eacr.p1)
-			eacr.e1 = 0;
-		etr_port1_uptodate = 0;
-	}
-	clear_bit(ETR_EVENT_UPDATE, &etr_events);
-	return eacr;
-}
-
-/*
- * Set up a timer that expires after the etr_tolec + 1.6 seconds if
- * one of the ports needs an update.
- */
-static void etr_set_tolec_timeout(unsigned long long now)
-{
-	unsigned long micros;
-
-	if ((!etr_eacr.p0 || etr_port0_uptodate) &&
-	    (!etr_eacr.p1 || etr_port1_uptodate))
-		return;
-	micros = (now > etr_tolec) ? ((now - etr_tolec) >> 12) : 0;
-	micros = (micros > 1600000) ? 0 : 1600000 - micros;
-	mod_timer(&etr_timer, jiffies + (micros * HZ) / 1000000 + 1);
-}
-
-/*
- * Set up a time that expires after 1/2 second.
- */
-static void etr_set_sync_timeout(void)
-{
-	mod_timer(&etr_timer, jiffies + HZ/2);
-}
-
-/*
- * Update the aib information for one or both ports.
- */
-static struct etr_eacr etr_handle_update(struct etr_aib *aib,
-					 struct etr_eacr eacr)
-{
-	/* With both ports disabled the aib information is useless. */
-	if (!eacr.e0 && !eacr.e1)
-		return eacr;
-
-	/* Update port0 or port1 with aib stored in etr_work_fn. */
-	if (aib->esw.q == 0) {
-		/* Information for port 0 stored. */
-		if (eacr.p0 && !etr_port0_uptodate) {
-			etr_port0 = *aib;
-			if (etr_port0_online)
-				etr_port0_uptodate = 1;
-		}
-	} else {
-		/* Information for port 1 stored. */
-		if (eacr.p1 && !etr_port1_uptodate) {
-			etr_port1 = *aib;
-			if (etr_port0_online)
-				etr_port1_uptodate = 1;
-		}
-	}
-
-	/*
-	 * Do not try to get the alternate port aib if the clock
-	 * is not in sync yet.
-	 */
-	if (!eacr.es || !check_sync_clock())
-		return eacr;
-
-	/*
-	 * If steai is available we can get the information about
-	 * the other port immediately. If only stetr is available the
-	 * data-port bit toggle has to be used.
-	 */
-	if (etr_steai_available) {
-		if (eacr.p0 && !etr_port0_uptodate) {
-			etr_steai_cv(&etr_port0, ETR_STEAI_PORT_0);
-			etr_port0_uptodate = 1;
-		}
-		if (eacr.p1 && !etr_port1_uptodate) {
-			etr_steai_cv(&etr_port1, ETR_STEAI_PORT_1);
-			etr_port1_uptodate = 1;
-		}
-	} else {
-		/*
-		 * One port was updated above, if the other
-		 * port is not uptodate toggle dp bit.
-		 */
-		if ((eacr.p0 && !etr_port0_uptodate) ||
-		    (eacr.p1 && !etr_port1_uptodate))
-			eacr.dp ^= 1;
-		else
-			eacr.dp = 0;
-	}
-	return eacr;
-}
-
-/*
- * Write new etr control register if it differs from the current one.
- * Return 1 if etr_tolec has been updated as well.
- */
-static void etr_update_eacr(struct etr_eacr eacr)
-{
-	int dp_changed;
-
-	if (memcmp(&etr_eacr, &eacr, sizeof(eacr)) == 0)
-		/* No change, return. */
-		return;
-	/*
-	 * The disable of an active port of the change of the data port
-	 * bit can/will cause a change in the data port.
-	 */
-	dp_changed = etr_eacr.e0 > eacr.e0 || etr_eacr.e1 > eacr.e1 ||
-		(etr_eacr.dp ^ eacr.dp) != 0;
-	etr_eacr = eacr;
-	etr_setr(&etr_eacr);
-	if (dp_changed)
-		etr_tolec = get_tod_clock();
-}
-
-/*
- * ETR work. In this function you'll find the main logic. In
- * particular this is the only function that calls etr_update_eacr(),
- * it "controls" the etr control register.
- */
-static void etr_work_fn(struct work_struct *work)
-{
-	unsigned long long now;
-	struct etr_eacr eacr;
-	struct etr_aib aib;
-	int sync_port;
-
-	/* prevent multiple execution. */
-	mutex_lock(&etr_work_mutex);
-
-	/* Create working copy of etr_eacr. */
-	eacr = etr_eacr;
-
-	/* Check for the different events and their immediate effects. */
-	eacr = etr_handle_events(eacr);
-
-	/* Check if ETR is supposed to be active. */
-	eacr.ea = eacr.p0 || eacr.p1;
-	if (!eacr.ea) {
-		/* Both ports offline. Reset everything. */
-		eacr.dp = eacr.es = eacr.sl = 0;
-		on_each_cpu(disable_sync_clock, NULL, 1);
-		del_timer_sync(&etr_timer);
-		etr_update_eacr(eacr);
-		goto out_unlock;
-	}
-
-	/* Store aib to get the current ETR status word. */
-	BUG_ON(etr_stetr(&aib) != 0);
-	etr_port0.esw = etr_port1.esw = aib.esw;	/* Copy status word. */
-	now = get_tod_clock();
-
-	/*
-	 * Update the port information if the last stepping port change
-	 * or data port change is older than 1.6 seconds.
-	 */
-	if (now >= etr_tolec + (1600000 << 12))
-		eacr = etr_handle_update(&aib, eacr);
-
-	/*
-	 * Select ports to enable. The preferred synchronization mode is PPS.
-	 * If a port can be enabled depends on a number of things:
-	 * 1) The port needs to be online and uptodate. A port is not
-	 *    disabled just because it is not uptodate, but it is only
-	 *    enabled if it is uptodate.
-	 * 2) The port needs to have the same mode (pps / etr).
-	 * 3) The port needs to be usable -> etr_port_valid() == 1
-	 * 4) To enable the second port the clock needs to be in sync.
-	 * 5) If both ports are useable and are ETR ports, the network id
-	 *    has to be the same.
-	 * The eacr.sl bit is used to indicate etr mode vs. pps mode.
-	 */
-	if (eacr.p0 && aib.esw.psc0 == etr_lpsc_pps_mode) {
-		eacr.sl = 0;
-		eacr.e0 = 1;
-		if (!etr_mode_is_pps(etr_eacr))
-			eacr.es = 0;
-		if (!eacr.es || !eacr.p1 || aib.esw.psc1 != etr_lpsc_pps_mode)
-			eacr.e1 = 0;
-		// FIXME: uptodate checks ?
-		else if (etr_port0_uptodate && etr_port1_uptodate)
-			eacr.e1 = 1;
-		sync_port = (etr_port0_uptodate &&
-			     etr_port_valid(&etr_port0, 0)) ? 0 : -1;
-	} else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_pps_mode) {
-		eacr.sl = 0;
-		eacr.e0 = 0;
-		eacr.e1 = 1;
-		if (!etr_mode_is_pps(etr_eacr))
-			eacr.es = 0;
-		sync_port = (etr_port1_uptodate &&
-			     etr_port_valid(&etr_port1, 1)) ? 1 : -1;
-	} else if (eacr.p0 && aib.esw.psc0 == etr_lpsc_operational_step) {
-		eacr.sl = 1;
-		eacr.e0 = 1;
-		if (!etr_mode_is_etr(etr_eacr))
-			eacr.es = 0;
-		if (!eacr.es || !eacr.p1 ||
-		    aib.esw.psc1 != etr_lpsc_operational_alt)
-			eacr.e1 = 0;
-		else if (etr_port0_uptodate && etr_port1_uptodate &&
-			 etr_compare_network(&etr_port0, &etr_port1))
-			eacr.e1 = 1;
-		sync_port = (etr_port0_uptodate &&
-			     etr_port_valid(&etr_port0, 0)) ? 0 : -1;
-	} else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_operational_step) {
-		eacr.sl = 1;
-		eacr.e0 = 0;
-		eacr.e1 = 1;
-		if (!etr_mode_is_etr(etr_eacr))
-			eacr.es = 0;
-		sync_port = (etr_port1_uptodate &&
-			     etr_port_valid(&etr_port1, 1)) ? 1 : -1;
-	} else {
-		/* Both ports not usable. */
-		eacr.es = eacr.sl = 0;
-		sync_port = -1;
-	}
-
-	/*
-	 * If the clock is in sync just update the eacr and return.
-	 * If there is no valid sync port wait for a port update.
-	 */
-	if ((eacr.es && check_sync_clock()) || sync_port < 0) {
-		etr_update_eacr(eacr);
-		etr_set_tolec_timeout(now);
-		goto out_unlock;
-	}
-
-	/*
-	 * Prepare control register for clock syncing
-	 * (reset data port bit, set sync check control.
-	 */
-	eacr.dp = 0;
-	eacr.es = 1;
-
-	/*
-	 * Update eacr and try to synchronize the clock. If the update
-	 * of eacr caused a stepping port switch (or if we have to
-	 * assume that a stepping port switch has occurred) or the
-	 * clock syncing failed, reset the sync check control bit
-	 * and set up a timer to try again after 0.5 seconds
-	 */
-	etr_update_eacr(eacr);
-	if (now < etr_tolec + (1600000 << 12) ||
-	    etr_sync_clock_stop(&aib, sync_port) != 0) {
-		/* Sync failed. Try again in 1/2 second. */
-		eacr.es = 0;
-		etr_update_eacr(eacr);
-		etr_set_sync_timeout();
-	} else
-		etr_set_tolec_timeout(now);
-out_unlock:
-	mutex_unlock(&etr_work_mutex);
-}
-
-/*
- * Sysfs interface functions
- */
-static struct bus_type etr_subsys = {
-	.name		= "etr",
-	.dev_name	= "etr",
-};
-
-static struct device etr_port0_dev = {
-	.id	= 0,
-	.bus	= &etr_subsys,
-};
-
-static struct device etr_port1_dev = {
-	.id	= 1,
-	.bus	= &etr_subsys,
-};
-
-/*
- * ETR subsys attributes
- */
-static ssize_t etr_stepping_port_show(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
-{
-	return sprintf(buf, "%i\n", etr_port0.esw.p);
-}
-
-static DEVICE_ATTR(stepping_port, 0400, etr_stepping_port_show, NULL);
-
-static ssize_t etr_stepping_mode_show(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
-{
-	char *mode_str;
-
-	if (etr_mode_is_pps(etr_eacr))
-		mode_str = "pps";
-	else if (etr_mode_is_etr(etr_eacr))
-		mode_str = "etr";
-	else
-		mode_str = "local";
-	return sprintf(buf, "%s\n", mode_str);
-}
-
-static DEVICE_ATTR(stepping_mode, 0400, etr_stepping_mode_show, NULL);
-
-/*
- * ETR port attributes
- */
-static inline struct etr_aib *etr_aib_from_dev(struct device *dev)
-{
-	if (dev == &etr_port0_dev)
-		return etr_port0_online ? &etr_port0 : NULL;
-	else
-		return etr_port1_online ? &etr_port1 : NULL;
-}
-
-static ssize_t etr_online_show(struct device *dev,
-				struct device_attribute *attr,
-				char *buf)
-{
-	unsigned int online;
-
-	online = (dev == &etr_port0_dev) ? etr_port0_online : etr_port1_online;
-	return sprintf(buf, "%i\n", online);
-}
-
-static ssize_t etr_online_store(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
-{
-	unsigned int value;
-
-	value = simple_strtoul(buf, NULL, 0);
-	if (value != 0 && value != 1)
-		return -EINVAL;
-	if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
-		return -EOPNOTSUPP;
-	mutex_lock(&clock_sync_mutex);
-	if (dev == &etr_port0_dev) {
-		if (etr_port0_online == value)
-			goto out;	/* Nothing to do. */
-		etr_port0_online = value;
-		if (etr_port0_online && etr_port1_online)
-			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
-		else
-			clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
-		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
-		queue_work(time_sync_wq, &etr_work);
-	} else {
-		if (etr_port1_online == value)
-			goto out;	/* Nothing to do. */
-		etr_port1_online = value;
-		if (etr_port0_online && etr_port1_online)
-			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
-		else
-			clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
-		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
-		queue_work(time_sync_wq, &etr_work);
-	}
-out:
-	mutex_unlock(&clock_sync_mutex);
-	return count;
-}
-
-static DEVICE_ATTR(online, 0600, etr_online_show, etr_online_store);
-
-static ssize_t etr_stepping_control_show(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
-{
-	return sprintf(buf, "%i\n", (dev == &etr_port0_dev) ?
-		       etr_eacr.e0 : etr_eacr.e1);
-}
-
-static DEVICE_ATTR(stepping_control, 0400, etr_stepping_control_show, NULL);
-
-static ssize_t etr_mode_code_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	if (!etr_port0_online && !etr_port1_online)
-		/* Status word is not uptodate if both ports are offline. */
-		return -ENODATA;
-	return sprintf(buf, "%i\n", (dev == &etr_port0_dev) ?
-		       etr_port0.esw.psc0 : etr_port0.esw.psc1);
-}
-
-static DEVICE_ATTR(state_code, 0400, etr_mode_code_show, NULL);
-
-static ssize_t etr_untuned_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct etr_aib *aib = etr_aib_from_dev(dev);
-
-	if (!aib || !aib->slsw.v1)
-		return -ENODATA;
-	return sprintf(buf, "%i\n", aib->edf1.u);
-}
-
-static DEVICE_ATTR(untuned, 0400, etr_untuned_show, NULL);
-
-static ssize_t etr_network_id_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct etr_aib *aib = etr_aib_from_dev(dev);
-
-	if (!aib || !aib->slsw.v1)
-		return -ENODATA;
-	return sprintf(buf, "%i\n", aib->edf1.net_id);
-}
-
-static DEVICE_ATTR(network, 0400, etr_network_id_show, NULL);
-
-static ssize_t etr_id_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct etr_aib *aib = etr_aib_from_dev(dev);
-
-	if (!aib || !aib->slsw.v1)
-		return -ENODATA;
-	return sprintf(buf, "%i\n", aib->edf1.etr_id);
-}
-
-static DEVICE_ATTR(id, 0400, etr_id_show, NULL);
-
-static ssize_t etr_port_number_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct etr_aib *aib = etr_aib_from_dev(dev);
-
-	if (!aib || !aib->slsw.v1)
-		return -ENODATA;
-	return sprintf(buf, "%i\n", aib->edf1.etr_pn);
-}
-
-static DEVICE_ATTR(port, 0400, etr_port_number_show, NULL);
-
-static ssize_t etr_coupled_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct etr_aib *aib = etr_aib_from_dev(dev);
-
-	if (!aib || !aib->slsw.v3)
-		return -ENODATA;
-	return sprintf(buf, "%i\n", aib->edf3.c);
-}
-
-static DEVICE_ATTR(coupled, 0400, etr_coupled_show, NULL);
-
-static ssize_t etr_local_time_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct etr_aib *aib = etr_aib_from_dev(dev);
-
-	if (!aib || !aib->slsw.v3)
-		return -ENODATA;
-	return sprintf(buf, "%i\n", aib->edf3.blto);
-}
-
-static DEVICE_ATTR(local_time, 0400, etr_local_time_show, NULL);
-
-static ssize_t etr_utc_offset_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct etr_aib *aib = etr_aib_from_dev(dev);
-
-	if (!aib || !aib->slsw.v3)
-		return -ENODATA;
-	return sprintf(buf, "%i\n", aib->edf3.buo);
-}
-
-static DEVICE_ATTR(utc_offset, 0400, etr_utc_offset_show, NULL);
-
-static struct device_attribute *etr_port_attributes[] = {
-	&dev_attr_online,
-	&dev_attr_stepping_control,
-	&dev_attr_state_code,
-	&dev_attr_untuned,
-	&dev_attr_network,
-	&dev_attr_id,
-	&dev_attr_port,
-	&dev_attr_coupled,
-	&dev_attr_local_time,
-	&dev_attr_utc_offset,
-	NULL
-};
-
-static int __init etr_register_port(struct device *dev)
-{
-	struct device_attribute **attr;
-	int rc;
-
-	rc = device_register(dev);
-	if (rc)
-		goto out;
-	for (attr = etr_port_attributes; *attr; attr++) {
-		rc = device_create_file(dev, *attr);
-		if (rc)
-			goto out_unreg;
-	}
-	return 0;
-out_unreg:
-	for (; attr >= etr_port_attributes; attr--)
-		device_remove_file(dev, *attr);
-	device_unregister(dev);
-out:
-	return rc;
-}
-
-static void __init etr_unregister_port(struct device *dev)
-{
-	struct device_attribute **attr;
-
-	for (attr = etr_port_attributes; *attr; attr++)
-		device_remove_file(dev, *attr);
-	device_unregister(dev);
-}
-
-static int __init etr_init_sysfs(void)
-{
-	int rc;
-
-	rc = subsys_system_register(&etr_subsys, NULL);
-	if (rc)
-		goto out;
-	rc = device_create_file(etr_subsys.dev_root, &dev_attr_stepping_port);
-	if (rc)
-		goto out_unreg_subsys;
-	rc = device_create_file(etr_subsys.dev_root, &dev_attr_stepping_mode);
-	if (rc)
-		goto out_remove_stepping_port;
-	rc = etr_register_port(&etr_port0_dev);
-	if (rc)
-		goto out_remove_stepping_mode;
-	rc = etr_register_port(&etr_port1_dev);
-	if (rc)
-		goto out_remove_port0;
-	return 0;
-
-out_remove_port0:
-	etr_unregister_port(&etr_port0_dev);
-out_remove_stepping_mode:
-	device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_mode);
-out_remove_stepping_port:
-	device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_port);
-out_unreg_subsys:
-	bus_unregister(&etr_subsys);
-out:
-	return rc;
-}
-
-device_initcall(etr_init_sysfs);
-
-/*
  * Server Time Protocol (STP) code.
  */
 static bool stp_online;
@@ -1455,7 +506,7 @@ static void __init stp_reset(void)
 	int rc;
 
 	stp_page = (void *) get_zeroed_page(GFP_ATOMIC);
-	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
+	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000, NULL);
 	if (rc == 0)
 		set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags);
 	else if (stp_online) {
@@ -1533,6 +584,7 @@ static int stp_sync_clock(void *data)
 	static int first;
 	unsigned long long old_clock, delta, new_clock, clock_delta;
 	struct clock_sync_data *stp_sync;
+	struct ptff_qto qto;
 	int rc;
 
 	stp_sync = data;
@@ -1554,11 +606,14 @@ static int stp_sync_clock(void *data)
 	    stp_info.todoff[2] || stp_info.todoff[3] ||
 	    stp_info.tmd != 2) {
 		old_clock = get_tod_clock();
-		rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0);
+		rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0, &clock_delta);
 		if (rc == 0) {
-			new_clock = get_tod_clock();
+			new_clock = old_clock + clock_delta;
 			delta = adjust_time(old_clock, new_clock, 0);
-			clock_delta = new_clock - old_clock;
+			if (ptff_query(PTFF_QTO) &&
+			    ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
+				/* Update LPAR offset */
+				lpar_offset = qto.tod_epoch_difference;
 			atomic_notifier_call_chain(&s390_epoch_delta_notifier,
 						   0, &clock_delta);
 			fixup_clock_comparator(delta);
@@ -1590,12 +645,12 @@ static void stp_work_fn(struct work_struct *work)
 	mutex_lock(&stp_work_mutex);
 
 	if (!stp_online) {
-		chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
+		chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000, NULL);
 		del_timer_sync(&stp_timer);
 		goto out_unlock;
 	}
 
-	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0);
+	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0, NULL);
 	if (rc)
 		goto out_unlock;
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 64298a867589..e959c02e0cac 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -46,6 +46,7 @@ static DECLARE_WORK(topology_work, topology_work_fn);
  */
 static struct mask_info socket_info;
 static struct mask_info book_info;
+static struct mask_info drawer_info;
 
 DEFINE_PER_CPU(struct cpu_topology_s390, cpu_topology);
 EXPORT_PER_CPU_SYMBOL_GPL(cpu_topology);
@@ -79,10 +80,10 @@ static cpumask_t cpu_thread_map(unsigned int cpu)
 	return mask;
 }
 
-static struct mask_info *add_cpus_to_mask(struct topology_core *tl_core,
-					  struct mask_info *book,
-					  struct mask_info *socket,
-					  int one_socket_per_cpu)
+static void add_cpus_to_mask(struct topology_core *tl_core,
+			     struct mask_info *drawer,
+			     struct mask_info *book,
+			     struct mask_info *socket)
 {
 	struct cpu_topology_s390 *topo;
 	unsigned int core;
@@ -97,21 +98,17 @@ static struct mask_info *add_cpus_to_mask(struct topology_core *tl_core,
 			continue;
 		for (i = 0; i <= smp_cpu_mtid; i++) {
 			topo = &per_cpu(cpu_topology, lcpu + i);
+			topo->drawer_id = drawer->id;
 			topo->book_id = book->id;
+			topo->socket_id = socket->id;
 			topo->core_id = rcore;
 			topo->thread_id = lcpu + i;
+			cpumask_set_cpu(lcpu + i, &drawer->mask);
 			cpumask_set_cpu(lcpu + i, &book->mask);
 			cpumask_set_cpu(lcpu + i, &socket->mask);
-			if (one_socket_per_cpu)
-				topo->socket_id = rcore;
-			else
-				topo->socket_id = socket->id;
 			smp_cpu_set_polarization(lcpu + i, tl_core->pp);
 		}
-		if (one_socket_per_cpu)
-			socket = socket->next;
 	}
-	return socket;
 }
 
 static void clear_masks(void)
@@ -128,6 +125,11 @@ static void clear_masks(void)
 		cpumask_clear(&info->mask);
 		info = info->next;
 	}
+	info = &drawer_info;
+	while (info) {
+		cpumask_clear(&info->mask);
+		info = info->next;
+	}
 }
 
 static union topology_entry *next_tle(union topology_entry *tle)
@@ -137,16 +139,22 @@ static union topology_entry *next_tle(union topology_entry *tle)
 	return (union topology_entry *)((struct topology_container *)tle + 1);
 }
 
-static void __tl_to_masks_generic(struct sysinfo_15_1_x *info)
+static void tl_to_masks(struct sysinfo_15_1_x *info)
 {
 	struct mask_info *socket = &socket_info;
 	struct mask_info *book = &book_info;
+	struct mask_info *drawer = &drawer_info;
 	union topology_entry *tle, *end;
 
+	clear_masks();
 	tle = info->tle;
 	end = (union topology_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
 		switch (tle->nl) {
+		case 3:
+			drawer = drawer->next;
+			drawer->id = tle->container.id;
+			break;
 		case 2:
 			book = book->next;
 			book->id = tle->container.id;
@@ -156,32 +164,7 @@ static void __tl_to_masks_generic(struct sysinfo_15_1_x *info)
 			socket->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_mask(&tle->cpu, book, socket, 0);
-			break;
-		default:
-			clear_masks();
-			return;
-		}
-		tle = next_tle(tle);
-	}
-}
-
-static void __tl_to_masks_z10(struct sysinfo_15_1_x *info)
-{
-	struct mask_info *socket = &socket_info;
-	struct mask_info *book = &book_info;
-	union topology_entry *tle, *end;
-
-	tle = info->tle;
-	end = (union topology_entry *)((unsigned long)info + info->length);
-	while (tle < end) {
-		switch (tle->nl) {
-		case 1:
-			book = book->next;
-			book->id = tle->container.id;
-			break;
-		case 0:
-			socket = add_cpus_to_mask(&tle->cpu, book, socket, 1);
+			add_cpus_to_mask(&tle->cpu, drawer, book, socket);
 			break;
 		default:
 			clear_masks();
@@ -191,22 +174,6 @@ static void __tl_to_masks_z10(struct sysinfo_15_1_x *info)
 	}
 }
 
-static void tl_to_masks(struct sysinfo_15_1_x *info)
-{
-	struct cpuid cpu_id;
-
-	get_cpu_id(&cpu_id);
-	clear_masks();
-	switch (cpu_id.machine) {
-	case 0x2097:
-	case 0x2098:
-		__tl_to_masks_z10(info);
-		break;
-	default:
-		__tl_to_masks_generic(info);
-	}
-}
-
 static void topology_update_polarization_simple(void)
 {
 	int cpu;
@@ -257,11 +224,13 @@ static void update_cpu_masks(void)
 		topo->thread_mask = cpu_thread_map(cpu);
 		topo->core_mask = cpu_group_map(&socket_info, cpu);
 		topo->book_mask = cpu_group_map(&book_info, cpu);
+		topo->drawer_mask = cpu_group_map(&drawer_info, cpu);
 		if (!MACHINE_HAS_TOPOLOGY) {
 			topo->thread_id = cpu;
 			topo->core_id = cpu;
 			topo->socket_id = cpu;
 			topo->book_id = cpu;
+			topo->drawer_id = cpu;
 		}
 	}
 	numa_update_cpu_topology();
@@ -269,10 +238,7 @@ static void update_cpu_masks(void)
 
 void store_topology(struct sysinfo_15_1_x *info)
 {
-	if (topology_max_mnest >= 3)
-		stsi(info, 15, 1, 3);
-	else
-		stsi(info, 15, 1, 2);
+	stsi(info, 15, 1, min(topology_max_mnest, 4));
 }
 
 int arch_update_cpu_topology(void)
@@ -442,6 +408,11 @@ static const struct cpumask *cpu_book_mask(int cpu)
 	return &per_cpu(cpu_topology, cpu).book_mask;
 }
 
+static const struct cpumask *cpu_drawer_mask(int cpu)
+{
+	return &per_cpu(cpu_topology, cpu).drawer_mask;
+}
+
 static int __init early_parse_topology(char *p)
 {
 	return kstrtobool(p, &topology_enabled);
@@ -452,6 +423,7 @@ static struct sched_domain_topology_level s390_topology[] = {
 	{ cpu_thread_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
 	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
+	{ cpu_drawer_mask, SD_INIT_NAME(DRAWER) },
 	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
 	{ NULL, },
 };
@@ -487,6 +459,7 @@ static int __init s390_topology_init(void)
 	printk(KERN_CONT " / %d\n", info->mnest);
 	alloc_masks(info, &socket_info, 1);
 	alloc_masks(info, &book_info, 2);
+	alloc_masks(info, &drawer_info, 3);
 	set_sched_topology(s390_topology);
 	return 0;
 }
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index f9c459586649..68145456fee2 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -1,5 +1,7 @@
 # List of files in the vdso, has to be asm only for now
 
+KCOV_INSTRUMENT := n
+
 obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o
 
 # Build rules
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 058659c1b8cf..0b0fd22c869a 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -1,5 +1,7 @@
 # List of files in the vdso, has to be asm only for now
 
+KCOV_INSTRUMENT := n
+
 obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o
 
 # Build rules
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 0f41a8286378..429bfd111961 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -4,6 +4,16 @@
 
 #include <asm/thread_info.h>
 #include <asm/page.h>
+
+/*
+ * Put .bss..swapper_pg_dir as the first thing in .bss. This will
+ * make sure it has 16k alignment.
+ */
+#define BSS_FIRST_SECTIONS *(.bss..swapper_pg_dir)
+
+/* Handle ro_after_init data on our own. */
+#define RO_AFTER_INIT_DATA
+
 #include <asm-generic/vmlinux.lds.h>
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
@@ -49,7 +59,14 @@ SECTIONS
 	_eshared = .;		/* End of shareable data */
 	_sdata = .;		/* Start of data section */
 
-	EXCEPTION_TABLE(16) :data
+	. = ALIGN(PAGE_SIZE);
+	__start_ro_after_init = .;
+	.data..ro_after_init : {
+		 *(.data..ro_after_init)
+	}
+	EXCEPTION_TABLE(16)
+	. = ALIGN(PAGE_SIZE);
+	__end_ro_after_init = .;
 
 	RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE)
 
@@ -81,7 +98,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
-	BSS_SECTION(0, 2, 0)
+	BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE)
 
 	_end = . ;
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 43f2a2b80490..6f5c344cd785 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -28,7 +28,7 @@
 #include <linux/vmalloc.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
-#include <asm/etr.h>
+#include <asm/stp.h>
 #include <asm/pgtable.h>
 #include <asm/gmap.h>
 #include <asm/nmi.h>
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index b647d5ff0ad9..e390bbb16443 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -236,6 +236,26 @@ char * strrchr(const char * s, int c)
 }
 EXPORT_SYMBOL(strrchr);
 
+static inline int clcle(const char *s1, unsigned long l1,
+			const char *s2, unsigned long l2,
+			int *diff)
+{
+	register unsigned long r2 asm("2") = (unsigned long) s1;
+	register unsigned long r3 asm("3") = (unsigned long) l2;
+	register unsigned long r4 asm("4") = (unsigned long) s2;
+	register unsigned long r5 asm("5") = (unsigned long) l2;
+	int cc;
+
+	asm volatile ("0: clcle %1,%3,0\n"
+		      "   jo    0b\n"
+		      "   ipm   %0\n"
+		      "   srl   %0,28"
+		      : "=&d" (cc), "+a" (r2), "+a" (r3),
+			"+a" (r4), "+a" (r5) : : "cc");
+	*diff = *(char *)r2 - *(char *)r4;
+	return cc;
+}
+
 /**
  * strstr - Find the first substring in a %NUL terminated string
  * @s1: The string to be searched
@@ -250,18 +270,9 @@ char * strstr(const char * s1,const char * s2)
 		return (char *) s1;
 	l1 = __strend(s1) - s1;
 	while (l1-- >= l2) {
-		register unsigned long r2 asm("2") = (unsigned long) s1;
-		register unsigned long r3 asm("3") = (unsigned long) l2;
-		register unsigned long r4 asm("4") = (unsigned long) s2;
-		register unsigned long r5 asm("5") = (unsigned long) l2;
-		int cc;
-
-		asm volatile ("0: clcle %1,%3,0\n"
-			      "   jo    0b\n"
-			      "   ipm   %0\n"
-			      "   srl   %0,28"
-			      : "=&d" (cc), "+a" (r2), "+a" (r3),
-			        "+a" (r4), "+a" (r5) : : "cc" );
+		int cc, dummy;
+
+		cc = clcle(s1, l1, s2, l2, &dummy);
 		if (!cc)
 			return (char *) s1;
 		s1++;
@@ -302,20 +313,11 @@ EXPORT_SYMBOL(memchr);
  */
 int memcmp(const void *cs, const void *ct, size_t n)
 {
-	register unsigned long r2 asm("2") = (unsigned long) cs;
-	register unsigned long r3 asm("3") = (unsigned long) n;
-	register unsigned long r4 asm("4") = (unsigned long) ct;
-	register unsigned long r5 asm("5") = (unsigned long) n;
-	int ret;
+	int ret, diff;
 
-	asm volatile ("0: clcle %1,%3,0\n"
-		      "   jo    0b\n"
-		      "   ipm   %0\n"
-		      "   srl   %0,28"
-		      : "=&d" (ret), "+a" (r2), "+a" (r3), "+a" (r4), "+a" (r5)
-		      : : "cc" );
+	ret = clcle(cs, n, ct, n, &diff);
 	if (ret)
-		ret = *(char *) r2 - *(char *) r4;
+		ret = diff;
 	return ret;
 }
 EXPORT_SYMBOL(memcmp);
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index ae4de559e3a0..d96596128e9f 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -49,7 +49,7 @@ static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr
 		"   jnm   5b\n"
 		"   ex    %4,0(%3)\n"
 		"   j     8f\n"
-		"7:slgr  %0,%0\n"
+		"7: slgr  %0,%0\n"
 		"8:\n"
 		EX_TABLE(0b,2b) EX_TABLE(3b,4b) EX_TABLE(9b,2b) EX_TABLE(10b,4b)
 		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
@@ -93,7 +93,7 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr,
 		"   jnm   6b\n"
 		"   ex    %4,0(%3)\n"
 		"   j     9f\n"
-		"8:slgr  %0,%0\n"
+		"8: slgr  %0,%0\n"
 		"9: sacf  768\n"
 		EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,5b)
 		EX_TABLE(10b,3b) EX_TABLE(11b,3b) EX_TABLE(12b,5b)
@@ -266,7 +266,7 @@ static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size
 		"3: .insn ss,0xc80000000000,0(%3,%1),0(%4),0\n"
 		"   slgr  %0,%3\n"
 		"   j	  5f\n"
-		"4:slgr  %0,%0\n"
+		"4: slgr  %0,%0\n"
 		"5:\n"
 		EX_TABLE(0b,2b) EX_TABLE(3b,5b)
 		: "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 8556d6be9b54..861880df12c7 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -157,7 +157,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st,
 		pud = pud_offset(pgd, addr);
 		if (!pud_none(*pud))
 			if (pud_large(*pud)) {
-				prot = pud_val(*pud) & _REGION3_ENTRY_RO;
+				prot = pud_val(*pud) & _REGION_ENTRY_PROTECT;
 				note_page(m, st, prot, 2);
 			} else
 				walk_pmd_level(m, st, pud, addr);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 6c47488745ae..25783dc3c813 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -624,7 +624,7 @@ void pfault_fini(void)
 	diag_stat_inc(DIAG_STAT_X258);
 	asm volatile(
 		"	diag	%0,0,0x258\n"
-		"0:\n"
+		"0:	nopr	%%r7\n"
 		EX_TABLE(0b,0b)
 		: : "a" (&refbk), "m" (refbk) : "cc");
 }
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index cace818d86eb..063c721ec0dc 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL_GPL(gmap_alloc);
 static void gmap_flush_tlb(struct gmap *gmap)
 {
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
+		__tlb_flush_idte(gmap->asce);
 	else
 		__tlb_flush_global();
 }
@@ -124,7 +124,7 @@ void gmap_free(struct gmap *gmap)
 
 	/* Flush tlb. */
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
+		__tlb_flush_idte(gmap->asce);
 	else
 		__tlb_flush_global();
 
@@ -430,6 +430,9 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	VM_BUG_ON(pgd_none(*pgd));
 	pud = pud_offset(pgd, vmaddr);
 	VM_BUG_ON(pud_none(*pud));
+	/* large puds cannot yet be handled */
+	if (pud_large(*pud))
+		return -EFAULT;
 	pmd = pmd_offset(pud, vmaddr);
 	VM_BUG_ON(pmd_none(*pmd));
 	/* large pmds cannot yet be handled */
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index a8a6765f1a51..adb0c34bf431 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -128,6 +128,44 @@ static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
 	return 1;
 }
 
+static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	struct page *head, *page;
+	unsigned long mask;
+	int refs;
+
+	mask = (write ? _REGION_ENTRY_PROTECT : 0) | _REGION_ENTRY_INVALID;
+	if ((pud_val(pud) & mask) != 0)
+		return 0;
+	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
+
+	refs = 0;
+	head = pud_page(pud);
+	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pud_val(pud) != pud_val(*pudp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	return 1;
+}
+
 static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
@@ -144,7 +182,12 @@ static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (!gup_pmd_range(pudp, pud, addr, next, write, pages, nr))
+		if (unlikely(pud_large(pud))) {
+			if (!gup_huge_pud(pudp, pud, addr, next, write, pages,
+					  nr))
+				return 0;
+		} else if (!gup_pmd_range(pudp, pud, addr, next, write, pages,
+					  nr))
 			return 0;
 	} while (pudp++, addr = next, addr != end);
 
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 1b5e8983f4f3..e19d853883be 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -1,19 +1,22 @@
 /*
  *  IBM System z Huge TLB Page Support for Kernel.
  *
- *    Copyright IBM Corp. 2007
+ *    Copyright IBM Corp. 2007,2016
  *    Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "hugetlb"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 
-static inline pmd_t __pte_to_pmd(pte_t pte)
+static inline unsigned long __pte_to_rste(pte_t pte)
 {
-	pmd_t pmd;
+	unsigned long rste;
 
 	/*
-	 * Convert encoding		  pte bits	   pmd bits
+	 * Convert encoding		  pte bits	pmd / pud bits
 	 *				lIR.uswrdy.p	dy..R...I...wr
 	 * empty			010.000000.0 -> 00..0...1...00
 	 * prot-none, clean, old	111.000000.1 -> 00..1...1...00
@@ -33,25 +36,31 @@ static inline pmd_t __pte_to_pmd(pte_t pte)
 	 *	    u unused, l large
 	 */
 	if (pte_present(pte)) {
-		pmd_val(pmd) = pte_val(pte) & PAGE_MASK;
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_READ) >> 4;
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_WRITE) >> 4;
-		pmd_val(pmd) |=	(pte_val(pte) & _PAGE_INVALID) >> 5;
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_PROTECT);
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_DIRTY) << 10;
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_YOUNG) << 10;
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_SOFT_DIRTY) << 13;
+		rste = pte_val(pte) & PAGE_MASK;
+		rste |= (pte_val(pte) & _PAGE_READ) >> 4;
+		rste |= (pte_val(pte) & _PAGE_WRITE) >> 4;
+		rste |= (pte_val(pte) & _PAGE_INVALID) >> 5;
+		rste |= (pte_val(pte) & _PAGE_PROTECT);
+		rste |= (pte_val(pte) & _PAGE_DIRTY) << 10;
+		rste |= (pte_val(pte) & _PAGE_YOUNG) << 10;
+		rste |= (pte_val(pte) & _PAGE_SOFT_DIRTY) << 13;
 	} else
-		pmd_val(pmd) = _SEGMENT_ENTRY_INVALID;
-	return pmd;
+		rste = _SEGMENT_ENTRY_INVALID;
+	return rste;
 }
 
-static inline pte_t __pmd_to_pte(pmd_t pmd)
+static inline pte_t __rste_to_pte(unsigned long rste)
 {
+	int present;
 	pte_t pte;
 
+	if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
+		present = pud_present(__pud(rste));
+	else
+		present = pmd_present(__pmd(rste));
+
 	/*
-	 * Convert encoding		   pmd bits	    pte bits
+	 * Convert encoding		pmd / pud bits	    pte bits
 	 *				dy..R...I...wr	  lIR.uswrdy.p
 	 * empty			00..0...1...00 -> 010.000000.0
 	 * prot-none, clean, old	00..1...1...00 -> 111.000000.1
@@ -70,16 +79,16 @@ static inline pte_t __pmd_to_pte(pmd_t pmd)
 	 * SW-bits: p present, y young, d dirty, r read, w write, s special,
 	 *	    u unused, l large
 	 */
-	if (pmd_present(pmd)) {
-		pte_val(pte) = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN_LARGE;
+	if (present) {
+		pte_val(pte) = rste & _SEGMENT_ENTRY_ORIGIN_LARGE;
 		pte_val(pte) |= _PAGE_LARGE | _PAGE_PRESENT;
-		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_READ) << 4;
-		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) << 4;
-		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) << 5;
-		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT);
-		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) >> 10;
-		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) >> 10;
-		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_SOFT_DIRTY) >> 13;
+		pte_val(pte) |= (rste & _SEGMENT_ENTRY_READ) << 4;
+		pte_val(pte) |= (rste & _SEGMENT_ENTRY_WRITE) << 4;
+		pte_val(pte) |= (rste & _SEGMENT_ENTRY_INVALID) << 5;
+		pte_val(pte) |= (rste & _SEGMENT_ENTRY_PROTECT);
+		pte_val(pte) |= (rste & _SEGMENT_ENTRY_DIRTY) >> 10;
+		pte_val(pte) |= (rste & _SEGMENT_ENTRY_YOUNG) >> 10;
+		pte_val(pte) |= (rste & _SEGMENT_ENTRY_SOFT_DIRTY) >> 13;
 	} else
 		pte_val(pte) = _PAGE_INVALID;
 	return pte;
@@ -88,27 +97,33 @@ static inline pte_t __pmd_to_pte(pmd_t pmd)
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte)
 {
-	pmd_t pmd = __pte_to_pmd(pte);
-
-	pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE;
-	*(pmd_t *) ptep = pmd;
+	unsigned long rste = __pte_to_rste(pte);
+
+	/* Set correct table type for 2G hugepages */
+	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
+		rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
+	else
+		rste |= _SEGMENT_ENTRY_LARGE;
+	pte_val(*ptep) = rste;
 }
 
 pte_t huge_ptep_get(pte_t *ptep)
 {
-	pmd_t pmd = *(pmd_t *) ptep;
-
-	return __pmd_to_pte(pmd);
+	return __rste_to_pte(pte_val(*ptep));
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
+	pte_t pte = huge_ptep_get(ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
-	pmd_t old;
+	pud_t *pudp = (pud_t *) ptep;
 
-	old = pmdp_xchg_direct(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
-	return __pmd_to_pte(old);
+	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
+		pudp_xchg_direct(mm, addr, pudp, __pud(_REGION3_ENTRY_EMPTY));
+	else
+		pmdp_xchg_direct(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
+	return pte;
 }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm,
@@ -120,8 +135,12 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 
 	pgdp = pgd_offset(mm, addr);
 	pudp = pud_alloc(mm, pgdp, addr);
-	if (pudp)
-		pmdp = pmd_alloc(mm, pudp, addr);
+	if (pudp) {
+		if (sz == PUD_SIZE)
+			return (pte_t *) pudp;
+		else if (sz == PMD_SIZE)
+			pmdp = pmd_alloc(mm, pudp, addr);
+	}
 	return (pte_t *) pmdp;
 }
 
@@ -134,8 +153,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	pgdp = pgd_offset(mm, addr);
 	if (pgd_present(*pgdp)) {
 		pudp = pud_offset(pgdp, addr);
-		if (pud_present(*pudp))
+		if (pud_present(*pudp)) {
+			if (pud_large(*pudp))
+				return (pte_t *) pudp;
 			pmdp = pmd_offset(pudp, addr);
+		}
 	}
 	return (pte_t *) pmdp;
 }
@@ -147,5 +169,34 @@ int pmd_huge(pmd_t pmd)
 
 int pud_huge(pud_t pud)
 {
-	return 0;
+	return pud_large(pud);
+}
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+		pud_t *pud, int flags)
+{
+	if (flags & FOLL_GET)
+		return NULL;
+
+	return pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
+}
+
+static __init int setup_hugepagesz(char *opt)
+{
+	unsigned long size;
+	char *string = opt;
+
+	size = memparse(opt, &opt);
+	if (MACHINE_HAS_EDAT1 && size == PMD_SIZE) {
+		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
+	} else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) {
+		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else {
+		pr_err("hugepagesz= specifies an unsupported page size %s\n",
+			string);
+		return 0;
+	}
+	return 1;
 }
+__setup("hugepagesz=", setup_hugepagesz);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 2489b2e917c8..f56a39bd8ba6 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -40,7 +40,7 @@
 #include <asm/ctl_reg.h>
 #include <asm/sclp.h>
 
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
 
 unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
@@ -111,17 +111,16 @@ void __init paging_init(void)
 
 void mark_rodata_ro(void)
 {
-	/* Text and rodata are already protected. Nothing to do here. */
-	pr_info("Write protecting the kernel read-only data: %luk\n",
-		((unsigned long)&_eshared - (unsigned long)&_stext) >> 10);
+	unsigned long size = __end_ro_after_init - __start_ro_after_init;
+
+	set_memory_ro((unsigned long)__start_ro_after_init, size >> PAGE_SHIFT);
+	pr_info("Write protected read-only-after-init data: %luk\n", size >> 10);
 }
 
 void __init mem_init(void)
 {
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
+	cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
 	cpumask_set_cpu(0, mm_cpumask(&init_mm));
-	atomic_set(&init_mm.context.attach_count, 1);
 
 	set_max_mapnr(max_low_pfn);
         high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e9dfb0..3330ea124eec 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -34,20 +34,25 @@ static int __init cmma(char *str)
 }
 __setup("cmma=", cmma);
 
-void __init cmma_init(void)
+static inline int cmma_test_essa(void)
 {
 	register unsigned long tmp asm("0") = 0;
 	register int rc asm("1") = -EOPNOTSUPP;
 
-	if (!cmma_flag)
-		return;
 	asm volatile(
 		"       .insn rrf,0xb9ab0000,%1,%1,0,0\n"
 		"0:     la      %0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
 		: "+&d" (rc), "+&d" (tmp));
-	if (rc)
+	return rc;
+}
+
+void __init cmma_init(void)
+{
+	if (!cmma_flag)
+		return;
+	if (cmma_test_essa())
 		cmma_flag = 0;
 }
 
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index f2a5c29a97e9..7104ffb5a67f 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -10,7 +10,6 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 
-#if PAGE_DEFAULT_KEY
 static inline unsigned long sske_frame(unsigned long addr, unsigned char skey)
 {
 	asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0"
@@ -22,6 +21,8 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 {
 	unsigned long boundary, size;
 
+	if (!PAGE_DEFAULT_KEY)
+		return;
 	while (start < end) {
 		if (MACHINE_HAS_EDAT1) {
 			/* set storage keys for a 1MB frame */
@@ -38,56 +39,254 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 		start += PAGE_SIZE;
 	}
 }
-#endif
 
-static pte_t *walk_page_table(unsigned long addr)
+#ifdef CONFIG_PROC_FS
+atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX];
+
+void arch_report_meminfo(struct seq_file *m)
 {
-	pgd_t *pgdp;
-	pud_t *pudp;
+	seq_printf(m, "DirectMap4k:    %8lu kB\n",
+		   atomic_long_read(&direct_pages_count[PG_DIRECT_MAP_4K]) << 2);
+	seq_printf(m, "DirectMap1M:    %8lu kB\n",
+		   atomic_long_read(&direct_pages_count[PG_DIRECT_MAP_1M]) << 10);
+	seq_printf(m, "DirectMap2G:    %8lu kB\n",
+		   atomic_long_read(&direct_pages_count[PG_DIRECT_MAP_2G]) << 21);
+}
+#endif /* CONFIG_PROC_FS */
+
+static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr,
+		    unsigned long dtt)
+{
+	unsigned long table, mask;
+
+	mask = 0;
+	if (MACHINE_HAS_EDAT2) {
+		switch (dtt) {
+		case CRDTE_DTT_REGION3:
+			mask = ~(PTRS_PER_PUD * sizeof(pud_t) - 1);
+			break;
+		case CRDTE_DTT_SEGMENT:
+			mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
+			break;
+		case CRDTE_DTT_PAGE:
+			mask = ~(PTRS_PER_PTE * sizeof(pte_t) - 1);
+			break;
+		}
+		table = (unsigned long)old & mask;
+		crdte(*old, new, table, dtt, addr, S390_lowcore.kernel_asce);
+	} else if (MACHINE_HAS_IDTE) {
+		cspg(old, *old, new);
+	} else {
+		csp((unsigned int *)old + 1, *old, new);
+	}
+}
+
+struct cpa {
+	unsigned int set_ro	: 1;
+	unsigned int clear_ro	: 1;
+};
+
+static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end,
+			  struct cpa cpa)
+{
+	pte_t *ptep, new;
+
+	ptep = pte_offset(pmdp, addr);
+	do {
+		if (pte_none(*ptep))
+			return -EINVAL;
+		if (cpa.set_ro)
+			new = pte_wrprotect(*ptep);
+		else if (cpa.clear_ro)
+			new = pte_mkwrite(pte_mkdirty(*ptep));
+		pgt_set((unsigned long *)ptep, pte_val(new), addr, CRDTE_DTT_PAGE);
+		ptep++;
+		addr += PAGE_SIZE;
+		cond_resched();
+	} while (addr < end);
+	return 0;
+}
+
+static int split_pmd_page(pmd_t *pmdp, unsigned long addr)
+{
+	unsigned long pte_addr, prot;
+	pte_t *pt_dir, *ptep;
+	pmd_t new;
+	int i, ro;
+
+	pt_dir = vmem_pte_alloc();
+	if (!pt_dir)
+		return -ENOMEM;
+	pte_addr = pmd_pfn(*pmdp) << PAGE_SHIFT;
+	ro = !!(pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT);
+	prot = pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL);
+	ptep = pt_dir;
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte_val(*ptep) = pte_addr | prot;
+		pte_addr += PAGE_SIZE;
+		ptep++;
+	}
+	pmd_val(new) = __pa(pt_dir) | _SEGMENT_ENTRY;
+	pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT);
+	update_page_count(PG_DIRECT_MAP_4K, PTRS_PER_PTE);
+	update_page_count(PG_DIRECT_MAP_1M, -1);
+	return 0;
+}
+
+static void modify_pmd_page(pmd_t *pmdp, unsigned long addr, struct cpa cpa)
+{
+	pmd_t new;
+
+	if (cpa.set_ro)
+		new = pmd_wrprotect(*pmdp);
+	else if (cpa.clear_ro)
+		new = pmd_mkwrite(pmd_mkdirty(*pmdp));
+	pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT);
+}
+
+static int walk_pmd_level(pud_t *pudp, unsigned long addr, unsigned long end,
+			  struct cpa cpa)
+{
+	unsigned long next;
 	pmd_t *pmdp;
-	pte_t *ptep;
+	int rc = 0;
 
-	pgdp = pgd_offset_k(addr);
-	if (pgd_none(*pgdp))
-		return NULL;
-	pudp = pud_offset(pgdp, addr);
-	if (pud_none(*pudp) || pud_large(*pudp))
-		return NULL;
 	pmdp = pmd_offset(pudp, addr);
-	if (pmd_none(*pmdp) || pmd_large(*pmdp))
-		return NULL;
-	ptep = pte_offset_kernel(pmdp, addr);
-	if (pte_none(*ptep))
-		return NULL;
-	return ptep;
+	do {
+		if (pmd_none(*pmdp))
+			return -EINVAL;
+		next = pmd_addr_end(addr, end);
+		if (pmd_large(*pmdp)) {
+			if (addr & ~PMD_MASK || addr + PMD_SIZE > next) {
+				rc = split_pmd_page(pmdp, addr);
+				if (rc)
+					return rc;
+				continue;
+			}
+			modify_pmd_page(pmdp, addr, cpa);
+		} else {
+			rc = walk_pte_level(pmdp, addr, next, cpa);
+			if (rc)
+				return rc;
+		}
+		pmdp++;
+		addr = next;
+		cond_resched();
+	} while (addr < end);
+	return rc;
 }
 
-static void change_page_attr(unsigned long addr, int numpages,
-			     pte_t (*set) (pte_t))
+static int split_pud_page(pud_t *pudp, unsigned long addr)
 {
-	pte_t *ptep;
-	int i;
+	unsigned long pmd_addr, prot;
+	pmd_t *pm_dir, *pmdp;
+	pud_t new;
+	int i, ro;
 
-	for (i = 0; i < numpages; i++) {
-		ptep = walk_page_table(addr);
-		if (WARN_ON_ONCE(!ptep))
-			break;
-		*ptep = set(*ptep);
-		addr += PAGE_SIZE;
+	pm_dir = vmem_pmd_alloc();
+	if (!pm_dir)
+		return -ENOMEM;
+	pmd_addr = pud_pfn(*pudp) << PAGE_SHIFT;
+	ro = !!(pud_val(*pudp) & _REGION_ENTRY_PROTECT);
+	prot = pgprot_val(ro ? SEGMENT_KERNEL_RO : SEGMENT_KERNEL);
+	pmdp = pm_dir;
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd_val(*pmdp) = pmd_addr | prot;
+		pmd_addr += PMD_SIZE;
+		pmdp++;
 	}
-	__tlb_flush_kernel();
+	pud_val(new) = __pa(pm_dir) | _REGION3_ENTRY;
+	pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3);
+	update_page_count(PG_DIRECT_MAP_1M, PTRS_PER_PMD);
+	update_page_count(PG_DIRECT_MAP_2G, -1);
+	return 0;
+}
+
+static void modify_pud_page(pud_t *pudp, unsigned long addr, struct cpa cpa)
+{
+	pud_t new;
+
+	if (cpa.set_ro)
+		new = pud_wrprotect(*pudp);
+	else if (cpa.clear_ro)
+		new = pud_mkwrite(pud_mkdirty(*pudp));
+	pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3);
+}
+
+static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end,
+			  struct cpa cpa)
+{
+	unsigned long next;
+	pud_t *pudp;
+	int rc = 0;
+
+	pudp = pud_offset(pgd, addr);
+	do {
+		if (pud_none(*pudp))
+			return -EINVAL;
+		next = pud_addr_end(addr, end);
+		if (pud_large(*pudp)) {
+			if (addr & ~PUD_MASK || addr + PUD_SIZE > next) {
+				rc = split_pud_page(pudp, addr);
+				if (rc)
+					break;
+				continue;
+			}
+			modify_pud_page(pudp, addr, cpa);
+		} else {
+			rc = walk_pmd_level(pudp, addr, next, cpa);
+		}
+		pudp++;
+		addr = next;
+		cond_resched();
+	} while (addr < end && !rc);
+	return rc;
+}
+
+static DEFINE_MUTEX(cpa_mutex);
+
+static int change_page_attr(unsigned long addr, unsigned long end,
+			    struct cpa cpa)
+{
+	unsigned long next;
+	int rc = -EINVAL;
+	pgd_t *pgdp;
+
+	if (end >= MODULES_END)
+		return -EINVAL;
+	mutex_lock(&cpa_mutex);
+	pgdp = pgd_offset_k(addr);
+	do {
+		if (pgd_none(*pgdp))
+			break;
+		next = pgd_addr_end(addr, end);
+		rc = walk_pud_level(pgdp, addr, next, cpa);
+		if (rc)
+			break;
+		cond_resched();
+	} while (pgdp++, addr = next, addr < end && !rc);
+	mutex_unlock(&cpa_mutex);
+	return rc;
 }
 
 int set_memory_ro(unsigned long addr, int numpages)
 {
-	change_page_attr(addr, numpages, pte_wrprotect);
-	return 0;
+	struct cpa cpa = {
+		.set_ro = 1,
+	};
+
+	addr &= PAGE_MASK;
+	return change_page_attr(addr, addr + numpages * PAGE_SIZE, cpa);
 }
 
 int set_memory_rw(unsigned long addr, int numpages)
 {
-	change_page_attr(addr, numpages, pte_mkwrite);
-	return 0;
+	struct cpa cpa = {
+		.clear_ro = 1,
+	};
+
+	addr &= PAGE_MASK;
+	return change_page_attr(addr, addr + numpages * PAGE_SIZE, cpa);
 }
 
 /* not possible */
@@ -138,7 +337,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 		nr = min(numpages - i, nr);
 		if (enable) {
 			for (j = 0; j < nr; j++) {
-				pte_val(*pte) = __pa(address);
+				pte_val(*pte) = address | pgprot_val(PAGE_KERNEL);
 				address += PAGE_SIZE;
 				pte++;
 			}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 9f0ce0e6eeb4..b98d1a152d46 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -27,40 +27,37 @@
 static inline pte_t ptep_flush_direct(struct mm_struct *mm,
 				      unsigned long addr, pte_t *ptep)
 {
-	int active, count;
 	pte_t old;
 
 	old = *ptep;
 	if (unlikely(pte_val(old) & _PAGE_INVALID))
 		return old;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+	atomic_inc(&mm->context.flush_count);
+	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		__ptep_ipte_local(addr, ptep);
 	else
 		__ptep_ipte(addr, ptep);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
 static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep)
 {
-	int active, count;
 	pte_t old;
 
 	old = *ptep;
 	if (unlikely(pte_val(old) & _PAGE_INVALID))
 		return old;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if ((count & 0xffff) <= active) {
+	atomic_inc(&mm->context.flush_count);
+	if (cpumask_equal(&mm->context.cpu_attach_mask,
+			  cpumask_of(smp_processor_id()))) {
 		pte_val(*ptep) |= _PAGE_INVALID;
 		mm->context.flush_mm = 1;
 	} else
 		__ptep_ipte(addr, ptep);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
@@ -70,7 +67,6 @@ static inline pgste_t pgste_get_lock(pte_t *ptep)
 #ifdef CONFIG_PGSTE
 	unsigned long old;
 
-	preempt_disable();
 	asm(
 		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
@@ -93,7 +89,6 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 		: "=Q" (ptep[PTRS_PER_PTE])
 		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
 		: "cc", "memory");
-	preempt_enable();
 #endif
 }
 
@@ -230,9 +225,11 @@ pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
 	pgste_t pgste;
 	pte_t old;
 
+	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	old = ptep_flush_direct(mm, addr, ptep);
 	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	preempt_enable();
 	return old;
 }
 EXPORT_SYMBOL(ptep_xchg_direct);
@@ -243,9 +240,11 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 	pgste_t pgste;
 	pte_t old;
 
+	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	old = ptep_flush_lazy(mm, addr, ptep);
 	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	preempt_enable();
 	return old;
 }
 EXPORT_SYMBOL(ptep_xchg_lazy);
@@ -256,6 +255,7 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
 	pgste_t pgste;
 	pte_t old;
 
+	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	old = ptep_flush_lazy(mm, addr, ptep);
 	if (mm_has_pgste(mm)) {
@@ -279,13 +279,13 @@ void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 	} else {
 		*ptep = pte;
 	}
+	preempt_enable();
 }
 EXPORT_SYMBOL(ptep_modify_prot_commit);
 
 static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp)
 {
-	int active, count;
 	pmd_t old;
 
 	old = *pmdp;
@@ -295,36 +295,34 @@ static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
 		__pmdp_csp(pmdp);
 		return old;
 	}
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+	atomic_inc(&mm->context.flush_count);
+	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		__pmdp_idte_local(addr, pmdp);
 	else
 		__pmdp_idte(addr, pmdp);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
 static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 				    unsigned long addr, pmd_t *pmdp)
 {
-	int active, count;
 	pmd_t old;
 
 	old = *pmdp;
 	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
 		return old;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if ((count & 0xffff) <= active) {
+	atomic_inc(&mm->context.flush_count);
+	if (cpumask_equal(&mm->context.cpu_attach_mask,
+			  cpumask_of(smp_processor_id()))) {
 		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
 		mm->context.flush_mm = 1;
 	} else if (MACHINE_HAS_IDTE)
 		__pmdp_idte(addr, pmdp);
 	else
 		__pmdp_csp(pmdp);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
@@ -333,8 +331,10 @@ pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
 {
 	pmd_t old;
 
+	preempt_disable();
 	old = pmdp_flush_direct(mm, addr, pmdp);
 	*pmdp = new;
+	preempt_enable();
 	return old;
 }
 EXPORT_SYMBOL(pmdp_xchg_direct);
@@ -344,12 +344,53 @@ pmd_t pmdp_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 {
 	pmd_t old;
 
+	preempt_disable();
 	old = pmdp_flush_lazy(mm, addr, pmdp);
 	*pmdp = new;
+	preempt_enable();
 	return old;
 }
 EXPORT_SYMBOL(pmdp_xchg_lazy);
 
+static inline pud_t pudp_flush_direct(struct mm_struct *mm,
+				      unsigned long addr, pud_t *pudp)
+{
+	pud_t old;
+
+	old = *pudp;
+	if (pud_val(old) & _REGION_ENTRY_INVALID)
+		return old;
+	if (!MACHINE_HAS_IDTE) {
+		/*
+		 * Invalid bit position is the same for pmd and pud, so we can
+		 * re-use _pmd_csp() here
+		 */
+		__pmdp_csp((pmd_t *) pudp);
+		return old;
+	}
+	atomic_inc(&mm->context.flush_count);
+	if (MACHINE_HAS_TLB_LC &&
+	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+		__pudp_idte_local(addr, pudp);
+	else
+		__pudp_idte(addr, pudp);
+	atomic_dec(&mm->context.flush_count);
+	return old;
+}
+
+pud_t pudp_xchg_direct(struct mm_struct *mm, unsigned long addr,
+		       pud_t *pudp, pud_t new)
+{
+	pud_t old;
+
+	preempt_disable();
+	old = pudp_flush_direct(mm, addr, pudp);
+	*pudp = new;
+	preempt_enable();
+	return old;
+}
+EXPORT_SYMBOL(pudp_xchg_direct);
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pgtable)
@@ -398,20 +439,24 @@ void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr,
 	pgste_t pgste;
 
 	/* the mm_has_pgste() check is done in set_pte_at() */
+	preempt_disable();
 	pgste = pgste_get_lock(ptep);
 	pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
 	pgste_set_key(ptep, pgste, entry, mm);
 	pgste = pgste_set_pte(ptep, pgste, entry);
 	pgste_set_unlock(ptep, pgste);
+	preempt_enable();
 }
 
 void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	pgste_t pgste;
 
+	preempt_disable();
 	pgste = pgste_get_lock(ptep);
 	pgste_val(pgste) |= PGSTE_IN_BIT;
 	pgste_set_unlock(ptep, pgste);
+	preempt_enable();
 }
 
 static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
@@ -434,6 +479,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 	pte_t pte;
 
 	/* Zap unused and logically-zero pages */
+	preempt_disable();
 	pgste = pgste_get_lock(ptep);
 	pgstev = pgste_val(pgste);
 	pte = *ptep;
@@ -446,6 +492,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 	if (reset)
 		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
 	pgste_set_unlock(ptep, pgste);
+	preempt_enable();
 }
 
 void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
@@ -454,6 +501,7 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	pgste_t pgste;
 
 	/* Clear storage key */
+	preempt_disable();
 	pgste = pgste_get_lock(ptep);
 	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
 			      PGSTE_GR_BIT | PGSTE_GC_BIT);
@@ -461,6 +509,7 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
 		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
 	pgste_set_unlock(ptep, pgste);
+	preempt_enable();
 }
 
 /*
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index d48cf25cfe99..1848292766ef 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -11,6 +11,7 @@
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
 #include <linux/memblock.h>
+#include <asm/cacheflush.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
@@ -29,9 +30,11 @@ static LIST_HEAD(mem_segs);
 
 static void __ref *vmem_alloc_pages(unsigned int order)
 {
+	unsigned long size = PAGE_SIZE << order;
+
 	if (slab_is_available())
 		return (void *)__get_free_pages(GFP_KERNEL, order);
-	return alloc_bootmem_pages((1 << order) * PAGE_SIZE);
+	return alloc_bootmem_align(size, size);
 }
 
 static inline pud_t *vmem_pud_alloc(void)
@@ -45,7 +48,7 @@ static inline pud_t *vmem_pud_alloc(void)
 	return pud;
 }
 
-static inline pmd_t *vmem_pmd_alloc(void)
+pmd_t *vmem_pmd_alloc(void)
 {
 	pmd_t *pmd = NULL;
 
@@ -56,7 +59,7 @@ static inline pmd_t *vmem_pmd_alloc(void)
 	return pmd;
 }
 
-static pte_t __ref *vmem_pte_alloc(void)
+pte_t __ref *vmem_pte_alloc(void)
 {
 	pte_t *pte;
 
@@ -75,8 +78,9 @@ static pte_t __ref *vmem_pte_alloc(void)
 /*
  * Add a physical memory range to the 1:1 mapping.
  */
-static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
+static int vmem_add_mem(unsigned long start, unsigned long size)
 {
+	unsigned long pages4k, pages1m, pages2g;
 	unsigned long end = start + size;
 	unsigned long address = start;
 	pgd_t *pg_dir;
@@ -85,6 +89,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 	pte_t *pt_dir;
 	int ret = -ENOMEM;
 
+	pages4k = pages1m = pages2g = 0;
 	while (address < end) {
 		pg_dir = pgd_offset_k(address);
 		if (pgd_none(*pg_dir)) {
@@ -97,10 +102,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
 		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
 		     !debug_pagealloc_enabled()) {
-			pud_val(*pu_dir) = __pa(address) |
-				_REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE |
-				(ro ? _REGION_ENTRY_PROTECT : 0);
+			pud_val(*pu_dir) = address | pgprot_val(REGION3_KERNEL);
 			address += PUD_SIZE;
+			pages2g++;
 			continue;
 		}
 		if (pud_none(*pu_dir)) {
@@ -113,11 +117,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
 		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end) &&
 		    !debug_pagealloc_enabled()) {
-			pmd_val(*pm_dir) = __pa(address) |
-				_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE |
-				_SEGMENT_ENTRY_YOUNG |
-				(ro ? _SEGMENT_ENTRY_PROTECT : 0);
+			pmd_val(*pm_dir) = address | pgprot_val(SEGMENT_KERNEL);
 			address += PMD_SIZE;
+			pages1m++;
 			continue;
 		}
 		if (pmd_none(*pm_dir)) {
@@ -128,12 +130,15 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		}
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
-		pte_val(*pt_dir) = __pa(address) |
-			pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL);
+		pte_val(*pt_dir) = address |  pgprot_val(PAGE_KERNEL);
 		address += PAGE_SIZE;
+		pages4k++;
 	}
 	ret = 0;
 out:
+	update_page_count(PG_DIRECT_MAP_4K, pages4k);
+	update_page_count(PG_DIRECT_MAP_1M, pages1m);
+	update_page_count(PG_DIRECT_MAP_2G, pages2g);
 	return ret;
 }
 
@@ -143,15 +148,15 @@ out:
  */
 static void vmem_remove_range(unsigned long start, unsigned long size)
 {
+	unsigned long pages4k, pages1m, pages2g;
 	unsigned long end = start + size;
 	unsigned long address = start;
 	pgd_t *pg_dir;
 	pud_t *pu_dir;
 	pmd_t *pm_dir;
 	pte_t *pt_dir;
-	pte_t  pte;
 
-	pte_val(pte) = _PAGE_INVALID;
+	pages4k = pages1m = pages2g = 0;
 	while (address < end) {
 		pg_dir = pgd_offset_k(address);
 		if (pgd_none(*pg_dir)) {
@@ -166,6 +171,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
 		if (pud_large(*pu_dir)) {
 			pud_clear(pu_dir);
 			address += PUD_SIZE;
+			pages2g++;
 			continue;
 		}
 		pm_dir = pmd_offset(pu_dir, address);
@@ -176,13 +182,18 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
 		if (pmd_large(*pm_dir)) {
 			pmd_clear(pm_dir);
 			address += PMD_SIZE;
+			pages1m++;
 			continue;
 		}
 		pt_dir = pte_offset_kernel(pm_dir, address);
-		*pt_dir = pte;
+		pte_clear(&init_mm, address, pt_dir);
 		address += PAGE_SIZE;
+		pages4k++;
 	}
 	flush_tlb_kernel_range(start, end);
+	update_page_count(PG_DIRECT_MAP_4K, -pages4k);
+	update_page_count(PG_DIRECT_MAP_1M, -pages1m);
+	update_page_count(PG_DIRECT_MAP_2G, -pages2g);
 }
 
 /*
@@ -341,7 +352,7 @@ int vmem_add_mapping(unsigned long start, unsigned long size)
 	if (ret)
 		goto out_free;
 
-	ret = vmem_add_mem(start, size, 0);
+	ret = vmem_add_mem(start, size);
 	if (ret)
 		goto out_remove;
 	goto out;
@@ -362,31 +373,13 @@ out:
  */
 void __init vmem_map_init(void)
 {
-	unsigned long ro_start, ro_end;
+	unsigned long size = _eshared - _stext;
 	struct memblock_region *reg;
-	phys_addr_t start, end;
 
-	ro_start = PFN_ALIGN((unsigned long)&_stext);
-	ro_end = (unsigned long)&_eshared & PAGE_MASK;
-	for_each_memblock(memory, reg) {
-		start = reg->base;
-		end = reg->base + reg->size;
-		if (start >= ro_end || end <= ro_start)
-			vmem_add_mem(start, end - start, 0);
-		else if (start >= ro_start && end <= ro_end)
-			vmem_add_mem(start, end - start, 1);
-		else if (start >= ro_start) {
-			vmem_add_mem(start, ro_end - start, 1);
-			vmem_add_mem(ro_end, end - ro_end, 0);
-		} else if (end < ro_end) {
-			vmem_add_mem(start, ro_start - start, 0);
-			vmem_add_mem(ro_start, end - ro_start, 1);
-		} else {
-			vmem_add_mem(start, ro_start - start, 0);
-			vmem_add_mem(ro_start, ro_end - ro_start, 1);
-			vmem_add_mem(ro_end, end - ro_end, 0);
-		}
-	}
+	for_each_memblock(memory, reg)
+		vmem_add_mem(reg->base, reg->size);
+	set_memory_ro((unsigned long)_stext, size >> PAGE_SHIFT);
+	pr_info("Write protected kernel read-only data: %luk\n", size >> 10);
 }
 
 /*
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
index 828d0695d0d4..fbc394e16b2c 100644
--- a/arch/s390/numa/mode_emu.c
+++ b/arch/s390/numa/mode_emu.c
@@ -34,7 +34,8 @@
 #define DIST_CORE	1
 #define DIST_MC		2
 #define DIST_BOOK	3
-#define DIST_MAX	4
+#define DIST_DRAWER	4
+#define DIST_MAX	5
 
 /* Node distance reported to common code */
 #define EMU_NODE_DIST	10
@@ -43,7 +44,7 @@
 #define NODE_ID_FREE	-1
 
 /* Different levels of toptree */
-enum toptree_level {CORE, MC, BOOK, NODE, TOPOLOGY};
+enum toptree_level {CORE, MC, BOOK, DRAWER, NODE, TOPOLOGY};
 
 /* The two toptree IDs */
 enum {TOPTREE_ID_PHYS, TOPTREE_ID_NUMA};
@@ -114,6 +115,14 @@ static int cores_free(struct toptree *tree)
  */
 static struct toptree *core_node(struct toptree *core)
 {
+	return core->parent->parent->parent->parent;
+}
+
+/*
+ * Return drawer of core
+ */
+static struct toptree *core_drawer(struct toptree *core)
+{
 	return core->parent->parent->parent;
 }
 
@@ -138,6 +147,8 @@ static struct toptree *core_mc(struct toptree *core)
  */
 static int dist_core_to_core(struct toptree *core1, struct toptree *core2)
 {
+	if (core_drawer(core1)->id != core_drawer(core2)->id)
+		return DIST_DRAWER;
 	if (core_book(core1)->id != core_book(core2)->id)
 		return DIST_BOOK;
 	if (core_mc(core1)->id != core_mc(core2)->id)
@@ -262,6 +273,8 @@ static void toptree_to_numa_first(struct toptree *numa, struct toptree *phys)
 	struct toptree *core;
 
 	/* Always try to move perfectly fitting structures first */
+	move_level_to_numa(numa, phys, DRAWER, true);
+	move_level_to_numa(numa, phys, DRAWER, false);
 	move_level_to_numa(numa, phys, BOOK, true);
 	move_level_to_numa(numa, phys, BOOK, false);
 	move_level_to_numa(numa, phys, MC, true);
@@ -335,7 +348,7 @@ static struct toptree *toptree_to_numa(struct toptree *phys)
  */
 static struct toptree *toptree_from_topology(void)
 {
-	struct toptree *phys, *node, *book, *mc, *core;
+	struct toptree *phys, *node, *drawer, *book, *mc, *core;
 	struct cpu_topology_s390 *top;
 	int cpu;
 
@@ -344,10 +357,11 @@ static struct toptree *toptree_from_topology(void)
 	for_each_online_cpu(cpu) {
 		top = &per_cpu(cpu_topology, cpu);
 		node = toptree_get_child(phys, 0);
-		book = toptree_get_child(node, top->book_id);
+		drawer = toptree_get_child(node, top->drawer_id);
+		book = toptree_get_child(drawer, top->book_id);
 		mc = toptree_get_child(book, top->socket_id);
 		core = toptree_get_child(mc, top->core_id);
-		if (!book || !mc || !core)
+		if (!drawer || !book || !mc || !core)
 			panic("NUMA emulation could not allocate memory");
 		cpumask_set_cpu(cpu, &core->mask);
 		toptree_update_mask(mc);
@@ -368,6 +382,7 @@ static void topology_add_core(struct toptree *core)
 		cpumask_copy(&top->thread_mask, &core->mask);
 		cpumask_copy(&top->core_mask, &core_mc(core)->mask);
 		cpumask_copy(&top->book_mask, &core_book(core)->mask);
+		cpumask_copy(&top->drawer_mask, &core_drawer(core)->mask);
 		cpumask_set_cpu(cpu, &node_to_cpumask_map[core_node(core)->id]);
 		top->node_id = core_node(core)->id;
 	}
diff --git a/arch/s390/oprofile/Makefile b/arch/s390/oprofile/Makefile
index 496e4a7ee00e..e9dd41b0b8d3 100644
--- a/arch/s390/oprofile/Makefile
+++ b/arch/s390/oprofile/Makefile
@@ -7,4 +7,3 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		timer_int.o )
 
 oprofile-y :=	$(DRIVER_OBJS) init.o
-oprofile-y +=	hwsampler.o
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
deleted file mode 100644
index ff9b4eb34589..000000000000
--- a/arch/s390/oprofile/hwsampler.c
+++ /dev/null
@@ -1,1178 +0,0 @@
-/*
- * Copyright IBM Corp. 2010
- * Author: Heinz Graalfs <graalfs@de.ibm.com>
- */
-
-#include <linux/kernel_stat.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/workqueue.h>
-#include <linux/interrupt.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/semaphore.h>
-#include <linux/oom.h>
-#include <linux/oprofile.h>
-
-#include <asm/facility.h>
-#include <asm/cpu_mf.h>
-#include <asm/irq.h>
-
-#include "hwsampler.h"
-#include "op_counter.h"
-
-#define MAX_NUM_SDB 511
-#define MIN_NUM_SDB 1
-
-DECLARE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
-
-struct hws_execute_parms {
-	void *buffer;
-	signed int rc;
-};
-
-DEFINE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
-EXPORT_PER_CPU_SYMBOL(sampler_cpu_buffer);
-
-static DEFINE_MUTEX(hws_sem);
-static DEFINE_MUTEX(hws_sem_oom);
-
-static unsigned char hws_flush_all;
-static unsigned int hws_oom;
-static unsigned int hws_alert;
-static struct workqueue_struct *hws_wq;
-
-static unsigned int hws_state;
-enum {
-	HWS_INIT = 1,
-	HWS_DEALLOCATED,
-	HWS_STOPPED,
-	HWS_STARTED,
-	HWS_STOPPING };
-
-/* set to 1 if called by kernel during memory allocation */
-static unsigned char oom_killer_was_active;
-/* size of SDBT and SDB as of allocate API */
-static unsigned long num_sdbt = 100;
-static unsigned long num_sdb = 511;
-/* sampling interval (machine cycles) */
-static unsigned long interval;
-
-static unsigned long min_sampler_rate;
-static unsigned long max_sampler_rate;
-
-static void execute_qsi(void *parms)
-{
-	struct hws_execute_parms *ep = parms;
-
-	ep->rc = qsi(ep->buffer);
-}
-
-static void execute_ssctl(void *parms)
-{
-	struct hws_execute_parms *ep = parms;
-
-	ep->rc = lsctl(ep->buffer);
-}
-
-static int smp_ctl_ssctl_stop(int cpu)
-{
-	int rc;
-	struct hws_execute_parms ep;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	cb->ssctl.es = 0;
-	cb->ssctl.cs = 0;
-
-	ep.buffer = &cb->ssctl;
-	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
-	rc = ep.rc;
-	if (rc) {
-		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
-		dump_stack();
-	}
-
-	ep.buffer = &cb->qsi;
-	smp_call_function_single(cpu, execute_qsi, &ep, 1);
-
-	if (cb->qsi.es || cb->qsi.cs) {
-		printk(KERN_EMERG "CPUMF sampling did not stop properly.\n");
-		dump_stack();
-	}
-
-	return rc;
-}
-
-static int smp_ctl_ssctl_deactivate(int cpu)
-{
-	int rc;
-	struct hws_execute_parms ep;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	cb->ssctl.es = 1;
-	cb->ssctl.cs = 0;
-
-	ep.buffer = &cb->ssctl;
-	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
-	rc = ep.rc;
-	if (rc)
-		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
-
-	ep.buffer = &cb->qsi;
-	smp_call_function_single(cpu, execute_qsi, &ep, 1);
-
-	if (cb->qsi.cs)
-		printk(KERN_EMERG "CPUMF sampling was not set inactive.\n");
-
-	return rc;
-}
-
-static int smp_ctl_ssctl_enable_activate(int cpu, unsigned long interval)
-{
-	int rc;
-	struct hws_execute_parms ep;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	cb->ssctl.h = 1;
-	cb->ssctl.tear = cb->first_sdbt;
-	cb->ssctl.dear = *(unsigned long *) cb->first_sdbt;
-	cb->ssctl.interval = interval;
-	cb->ssctl.es = 1;
-	cb->ssctl.cs = 1;
-
-	ep.buffer = &cb->ssctl;
-	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
-	rc = ep.rc;
-	if (rc)
-		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
-
-	ep.buffer = &cb->qsi;
-	smp_call_function_single(cpu, execute_qsi, &ep, 1);
-	if (ep.rc)
-		printk(KERN_ERR "hwsampler: CPU %d CPUMF QSI failed.\n", cpu);
-
-	return rc;
-}
-
-static int smp_ctl_qsi(int cpu)
-{
-	struct hws_execute_parms ep;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	ep.buffer = &cb->qsi;
-	smp_call_function_single(cpu, execute_qsi, &ep, 1);
-
-	return ep.rc;
-}
-
-static void hws_ext_handler(struct ext_code ext_code,
-			    unsigned int param32, unsigned long param64)
-{
-	struct hws_cpu_buffer *cb = this_cpu_ptr(&sampler_cpu_buffer);
-
-	if (!(param32 & CPU_MF_INT_SF_MASK))
-		return;
-
-	if (!hws_alert)
-		return;
-
-	inc_irq_stat(IRQEXT_CMS);
-	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
-
-	if (hws_wq)
-		queue_work(hws_wq, &cb->worker);
-}
-
-static void worker(struct work_struct *work);
-
-static void add_samples_to_oprofile(unsigned cpu, unsigned long *,
-				unsigned long *dear);
-
-static void init_all_cpu_buffers(void)
-{
-	int cpu;
-	struct hws_cpu_buffer *cb;
-
-	for_each_online_cpu(cpu) {
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-		memset(cb, 0, sizeof(struct hws_cpu_buffer));
-	}
-}
-
-static void prepare_cpu_buffers(void)
-{
-	struct hws_cpu_buffer *cb;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-		atomic_set(&cb->ext_params, 0);
-		cb->worker_entry = 0;
-		cb->sample_overflow = 0;
-		cb->req_alert = 0;
-		cb->incorrect_sdbt_entry = 0;
-		cb->invalid_entry_address = 0;
-		cb->loss_of_sample_data = 0;
-		cb->sample_auth_change_alert = 0;
-		cb->finish = 0;
-		cb->oom = 0;
-		cb->stop_mode = 0;
-	}
-}
-
-/*
- * allocate_sdbt() - allocate sampler memory
- * @cpu: the cpu for which sampler memory is allocated
- *
- * A 4K page is allocated for each requested SDBT.
- * A maximum of 511 4K pages are allocated for the SDBs in each of the SDBTs.
- * Set ALERT_REQ mask in each SDBs trailer.
- * Returns zero if successful, <0 otherwise.
- */
-static int allocate_sdbt(int cpu)
-{
-	int j, k, rc;
-	unsigned long *sdbt;
-	unsigned long  sdb;
-	unsigned long *tail;
-	unsigned long *trailer;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	if (cb->first_sdbt)
-		return -EINVAL;
-
-	sdbt = NULL;
-	tail = sdbt;
-
-	for (j = 0; j < num_sdbt; j++) {
-		sdbt = (unsigned long *)get_zeroed_page(GFP_KERNEL);
-
-		mutex_lock(&hws_sem_oom);
-		/* OOM killer might have been activated */
-		barrier();
-		if (oom_killer_was_active || !sdbt) {
-			if (sdbt)
-				free_page((unsigned long)sdbt);
-
-			goto allocate_sdbt_error;
-		}
-		if (cb->first_sdbt == 0)
-			cb->first_sdbt = (unsigned long)sdbt;
-
-		/* link current page to tail of chain */
-		if (tail)
-			*tail = (unsigned long)(void *)sdbt + 1;
-
-		mutex_unlock(&hws_sem_oom);
-
-		for (k = 0; k < num_sdb; k++) {
-			/* get and set SDB page */
-			sdb = get_zeroed_page(GFP_KERNEL);
-
-			mutex_lock(&hws_sem_oom);
-			/* OOM killer might have been activated */
-			barrier();
-			if (oom_killer_was_active || !sdb) {
-				if (sdb)
-					free_page(sdb);
-
-				goto allocate_sdbt_error;
-			}
-			*sdbt = sdb;
-			trailer = trailer_entry_ptr(*sdbt);
-			*trailer = SDB_TE_ALERT_REQ_MASK;
-			sdbt++;
-			mutex_unlock(&hws_sem_oom);
-		}
-		tail = sdbt;
-	}
-	mutex_lock(&hws_sem_oom);
-	if (oom_killer_was_active)
-		goto allocate_sdbt_error;
-
-	rc = 0;
-	if (tail)
-		*tail = (unsigned long)
-			((void *)cb->first_sdbt) + 1;
-
-allocate_sdbt_exit:
-	mutex_unlock(&hws_sem_oom);
-	return rc;
-
-allocate_sdbt_error:
-	rc = -ENOMEM;
-	goto allocate_sdbt_exit;
-}
-
-/*
- * deallocate_sdbt() - deallocate all sampler memory
- *
- * For each online CPU all SDBT trees are deallocated.
- * Returns the number of freed pages.
- */
-static int deallocate_sdbt(void)
-{
-	int cpu;
-	int counter;
-
-	counter = 0;
-
-	for_each_online_cpu(cpu) {
-		unsigned long start;
-		unsigned long sdbt;
-		unsigned long *curr;
-		struct hws_cpu_buffer *cb;
-
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-		if (!cb->first_sdbt)
-			continue;
-
-		sdbt = cb->first_sdbt;
-		curr = (unsigned long *) sdbt;
-		start = sdbt;
-
-		/* we'll free the SDBT after all SDBs are processed... */
-		while (1) {
-			if (!*curr || !sdbt)
-				break;
-
-			/* watch for link entry reset if found */
-			if (is_link_entry(curr)) {
-				curr = get_next_sdbt(curr);
-				if (sdbt)
-					free_page(sdbt);
-
-				/* we are done if we reach the start */
-				if ((unsigned long) curr == start)
-					break;
-				else
-					sdbt = (unsigned long) curr;
-			} else {
-				/* process SDB pointer */
-				if (*curr) {
-					free_page(*curr);
-					curr++;
-				}
-			}
-			counter++;
-		}
-		cb->first_sdbt = 0;
-	}
-	return counter;
-}
-
-static int start_sampling(int cpu)
-{
-	int rc;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-	rc = smp_ctl_ssctl_enable_activate(cpu, interval);
-	if (rc) {
-		printk(KERN_INFO "hwsampler: CPU %d ssctl failed.\n", cpu);
-		goto start_exit;
-	}
-
-	rc = -EINVAL;
-	if (!cb->qsi.es) {
-		printk(KERN_INFO "hwsampler: CPU %d ssctl not enabled.\n", cpu);
-		goto start_exit;
-	}
-
-	if (!cb->qsi.cs) {
-		printk(KERN_INFO "hwsampler: CPU %d ssctl not active.\n", cpu);
-		goto start_exit;
-	}
-
-	printk(KERN_INFO
-		"hwsampler: CPU %d, CPUMF Sampling started, interval %lu.\n",
-		cpu, interval);
-
-	rc = 0;
-
-start_exit:
-	return rc;
-}
-
-static int stop_sampling(int cpu)
-{
-	unsigned long v;
-	int rc;
-	struct hws_cpu_buffer *cb;
-
-	rc = smp_ctl_qsi(cpu);
-	WARN_ON(rc);
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-	if (!rc && !cb->qsi.es)
-		printk(KERN_INFO "hwsampler: CPU %d, already stopped.\n", cpu);
-
-	rc = smp_ctl_ssctl_stop(cpu);
-	if (rc) {
-		printk(KERN_INFO "hwsampler: CPU %d, ssctl stop error %d.\n",
-				cpu, rc);
-		goto stop_exit;
-	}
-
-	printk(KERN_INFO "hwsampler: CPU %d, CPUMF Sampling stopped.\n", cpu);
-
-stop_exit:
-	v = cb->req_alert;
-	if (v)
-		printk(KERN_ERR "hwsampler: CPU %d CPUMF Request alert,"
-				" count=%lu.\n", cpu, v);
-
-	v = cb->loss_of_sample_data;
-	if (v)
-		printk(KERN_ERR "hwsampler: CPU %d CPUMF Loss of sample data,"
-				" count=%lu.\n", cpu, v);
-
-	v = cb->invalid_entry_address;
-	if (v)
-		printk(KERN_ERR "hwsampler: CPU %d CPUMF Invalid entry address,"
-				" count=%lu.\n", cpu, v);
-
-	v = cb->incorrect_sdbt_entry;
-	if (v)
-		printk(KERN_ERR
-				"hwsampler: CPU %d CPUMF Incorrect SDBT address,"
-				" count=%lu.\n", cpu, v);
-
-	v = cb->sample_auth_change_alert;
-	if (v)
-		printk(KERN_ERR
-				"hwsampler: CPU %d CPUMF Sample authorization change,"
-				" count=%lu.\n", cpu, v);
-
-	return rc;
-}
-
-static int check_hardware_prerequisites(void)
-{
-	if (!test_facility(68))
-		return -EOPNOTSUPP;
-	return 0;
-}
-/*
- * hws_oom_callback() - the OOM callback function
- *
- * In case the callback is invoked during memory allocation for the
- *  hw sampler, all obtained memory is deallocated and a flag is set
- *  so main sampler memory allocation can exit with a failure code.
- * In case the callback is invoked during sampling the hw sampler
- *  is deactivated for all CPUs.
- */
-static int hws_oom_callback(struct notifier_block *nfb,
-	unsigned long dummy, void *parm)
-{
-	unsigned long *freed;
-	int cpu;
-	struct hws_cpu_buffer *cb;
-
-	freed = parm;
-
-	mutex_lock(&hws_sem_oom);
-
-	if (hws_state == HWS_DEALLOCATED) {
-		/* during memory allocation */
-		if (oom_killer_was_active == 0) {
-			oom_killer_was_active = 1;
-			*freed += deallocate_sdbt();
-		}
-	} else {
-		int i;
-		cpu = get_cpu();
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-		if (!cb->oom) {
-			for_each_online_cpu(i) {
-				smp_ctl_ssctl_deactivate(i);
-				cb->oom = 1;
-			}
-			cb->finish = 1;
-
-			printk(KERN_INFO
-				"hwsampler: CPU %d, OOM notify during CPUMF Sampling.\n",
-				cpu);
-		}
-	}
-
-	mutex_unlock(&hws_sem_oom);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block hws_oom_notifier = {
-	.notifier_call = hws_oom_callback
-};
-
-static int hws_cpu_callback(struct notifier_block *nfb,
-	unsigned long action, void *hcpu)
-{
-	/* We do not have sampler space available for all possible CPUs.
-	   All CPUs should be online when hw sampling is activated. */
-	return (hws_state <= HWS_DEALLOCATED) ? NOTIFY_OK : NOTIFY_BAD;
-}
-
-static struct notifier_block hws_cpu_notifier = {
-	.notifier_call = hws_cpu_callback
-};
-
-/**
- * hwsampler_deactivate() - set hardware sampling temporarily inactive
- * @cpu:  specifies the CPU to be set inactive.
- *
- * Returns 0 on success, !0 on failure.
- */
-int hwsampler_deactivate(unsigned int cpu)
-{
-	/*
-	 * Deactivate hw sampling temporarily and flush the buffer
-	 * by pushing all the pending samples to oprofile buffer.
-	 *
-	 * This function can be called under one of the following conditions:
-	 *     Memory unmap, task is exiting.
-	 */
-	int rc;
-	struct hws_cpu_buffer *cb;
-
-	rc = 0;
-	mutex_lock(&hws_sem);
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-	if (hws_state == HWS_STARTED) {
-		rc = smp_ctl_qsi(cpu);
-		WARN_ON(rc);
-		if (cb->qsi.cs) {
-			rc = smp_ctl_ssctl_deactivate(cpu);
-			if (rc) {
-				printk(KERN_INFO
-				"hwsampler: CPU %d, CPUMF Deactivation failed.\n", cpu);
-				cb->finish = 1;
-				hws_state = HWS_STOPPING;
-			} else  {
-				hws_flush_all = 1;
-				/* Add work to queue to read pending samples.*/
-				queue_work_on(cpu, hws_wq, &cb->worker);
-			}
-		}
-	}
-	mutex_unlock(&hws_sem);
-
-	if (hws_wq)
-		flush_workqueue(hws_wq);
-
-	return rc;
-}
-
-/**
- * hwsampler_activate() - activate/resume hardware sampling which was deactivated
- * @cpu:  specifies the CPU to be set active.
- *
- * Returns 0 on success, !0 on failure.
- */
-int hwsampler_activate(unsigned int cpu)
-{
-	/*
-	 * Re-activate hw sampling. This should be called in pair with
-	 * hwsampler_deactivate().
-	 */
-	int rc;
-	struct hws_cpu_buffer *cb;
-
-	rc = 0;
-	mutex_lock(&hws_sem);
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-	if (hws_state == HWS_STARTED) {
-		rc = smp_ctl_qsi(cpu);
-		WARN_ON(rc);
-		if (!cb->qsi.cs) {
-			hws_flush_all = 0;
-			rc = smp_ctl_ssctl_enable_activate(cpu, interval);
-			if (rc) {
-				printk(KERN_ERR
-				"CPU %d, CPUMF activate sampling failed.\n",
-					 cpu);
-			}
-		}
-	}
-
-	mutex_unlock(&hws_sem);
-
-	return rc;
-}
-
-static int check_qsi_on_setup(void)
-{
-	int rc;
-	unsigned int cpu;
-	struct hws_cpu_buffer *cb;
-
-	for_each_online_cpu(cpu) {
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-		rc = smp_ctl_qsi(cpu);
-		WARN_ON(rc);
-		if (rc)
-			return -EOPNOTSUPP;
-
-		if (!cb->qsi.as) {
-			printk(KERN_INFO "hwsampler: CPUMF sampling is not authorized.\n");
-			return -EINVAL;
-		}
-
-		if (cb->qsi.es) {
-			printk(KERN_WARNING "hwsampler: CPUMF is still enabled.\n");
-			rc = smp_ctl_ssctl_stop(cpu);
-			if (rc)
-				return -EINVAL;
-
-			printk(KERN_INFO
-				"CPU %d, CPUMF Sampling stopped now.\n", cpu);
-		}
-	}
-	return 0;
-}
-
-static int check_qsi_on_start(void)
-{
-	unsigned int cpu;
-	int rc;
-	struct hws_cpu_buffer *cb;
-
-	for_each_online_cpu(cpu) {
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-		rc = smp_ctl_qsi(cpu);
-		WARN_ON(rc);
-
-		if (!cb->qsi.as)
-			return -EINVAL;
-
-		if (cb->qsi.es)
-			return -EINVAL;
-
-		if (cb->qsi.cs)
-			return -EINVAL;
-	}
-	return 0;
-}
-
-static void worker_on_start(unsigned int cpu)
-{
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-	cb->worker_entry = cb->first_sdbt;
-}
-
-static int worker_check_error(unsigned int cpu, int ext_params)
-{
-	int rc;
-	unsigned long *sdbt;
-	struct hws_cpu_buffer *cb;
-
-	rc = 0;
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-	sdbt = (unsigned long *) cb->worker_entry;
-
-	if (!sdbt || !*sdbt)
-		return -EINVAL;
-
-	if (ext_params & CPU_MF_INT_SF_PRA)
-		cb->req_alert++;
-
-	if (ext_params & CPU_MF_INT_SF_LSDA)
-		cb->loss_of_sample_data++;
-
-	if (ext_params & CPU_MF_INT_SF_IAE) {
-		cb->invalid_entry_address++;
-		rc = -EINVAL;
-	}
-
-	if (ext_params & CPU_MF_INT_SF_ISE) {
-		cb->incorrect_sdbt_entry++;
-		rc = -EINVAL;
-	}
-
-	if (ext_params & CPU_MF_INT_SF_SACA) {
-		cb->sample_auth_change_alert++;
-		rc = -EINVAL;
-	}
-
-	return rc;
-}
-
-static void worker_on_finish(unsigned int cpu)
-{
-	int rc, i;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	if (cb->finish) {
-		rc = smp_ctl_qsi(cpu);
-		WARN_ON(rc);
-		if (cb->qsi.es) {
-			printk(KERN_INFO
-				"hwsampler: CPU %d, CPUMF Stop/Deactivate sampling.\n",
-				cpu);
-			rc = smp_ctl_ssctl_stop(cpu);
-			if (rc)
-				printk(KERN_INFO
-					"hwsampler: CPU %d, CPUMF Deactivation failed.\n",
-					cpu);
-
-			for_each_online_cpu(i) {
-				if (i == cpu)
-					continue;
-				if (!cb->finish) {
-					cb->finish = 1;
-					queue_work_on(i, hws_wq,
-						&cb->worker);
-				}
-			}
-		}
-	}
-}
-
-static void worker_on_interrupt(unsigned int cpu)
-{
-	unsigned long *sdbt;
-	unsigned char done;
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	sdbt = (unsigned long *) cb->worker_entry;
-
-	done = 0;
-	/* do not proceed if stop was entered,
-	 * forget the buffers not yet processed */
-	while (!done && !cb->stop_mode) {
-		unsigned long *trailer;
-		struct hws_trailer_entry *te;
-		unsigned long *dear = 0;
-
-		trailer = trailer_entry_ptr(*sdbt);
-		/* leave loop if no more work to do */
-		if (!(*trailer & SDB_TE_BUFFER_FULL_MASK)) {
-			done = 1;
-			if (!hws_flush_all)
-				continue;
-		}
-
-		te = (struct hws_trailer_entry *)trailer;
-		cb->sample_overflow += te->overflow;
-
-		add_samples_to_oprofile(cpu, sdbt, dear);
-
-		/* reset trailer */
-		xchg((unsigned char *) te, 0x40);
-
-		/* advance to next sdb slot in current sdbt */
-		sdbt++;
-		/* in case link bit is set use address w/o link bit */
-		if (is_link_entry(sdbt))
-			sdbt = get_next_sdbt(sdbt);
-
-		cb->worker_entry = (unsigned long)sdbt;
-	}
-}
-
-static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
-		unsigned long *dear)
-{
-	struct hws_basic_entry *sample_data_ptr;
-	unsigned long *trailer;
-
-	trailer = trailer_entry_ptr(*sdbt);
-	if (dear) {
-		if (dear > trailer)
-			return;
-		trailer = dear;
-	}
-
-	sample_data_ptr = (struct hws_basic_entry *)(*sdbt);
-
-	while ((unsigned long *)sample_data_ptr < trailer) {
-		struct pt_regs *regs = NULL;
-		struct task_struct *tsk = NULL;
-
-		/*
-		 * Check sampling mode, 1 indicates basic (=customer) sampling
-		 * mode.
-		 */
-		if (sample_data_ptr->def != 1) {
-			/* sample slot is not yet written */
-			break;
-		} else {
-			/* make sure we don't use it twice,
-			 * the next time the sampler will set it again */
-			sample_data_ptr->def = 0;
-		}
-
-		/* Get pt_regs. */
-		if (sample_data_ptr->P == 1) {
-			/* userspace sample */
-			unsigned int pid = sample_data_ptr->prim_asn;
-			if (!counter_config.user)
-				goto skip_sample;
-			rcu_read_lock();
-			tsk = pid_task(find_vpid(pid), PIDTYPE_PID);
-			if (tsk)
-				regs = task_pt_regs(tsk);
-			rcu_read_unlock();
-		} else {
-			/* kernelspace sample */
-			if (!counter_config.kernel)
-				goto skip_sample;
-			regs = task_pt_regs(current);
-		}
-
-		mutex_lock(&hws_sem);
-		oprofile_add_ext_hw_sample(sample_data_ptr->ia, regs, 0,
-				!sample_data_ptr->P, tsk);
-		mutex_unlock(&hws_sem);
-	skip_sample:
-		sample_data_ptr++;
-	}
-}
-
-static void worker(struct work_struct *work)
-{
-	unsigned int cpu;
-	int ext_params;
-	struct hws_cpu_buffer *cb;
-
-	cb = container_of(work, struct hws_cpu_buffer, worker);
-	cpu = smp_processor_id();
-	ext_params = atomic_xchg(&cb->ext_params, 0);
-
-	if (!cb->worker_entry)
-		worker_on_start(cpu);
-
-	if (worker_check_error(cpu, ext_params))
-		return;
-
-	if (!cb->finish)
-		worker_on_interrupt(cpu);
-
-	if (cb->finish)
-		worker_on_finish(cpu);
-}
-
-/**
- * hwsampler_allocate() - allocate memory for the hardware sampler
- * @sdbt:  number of SDBTs per online CPU (must be > 0)
- * @sdb:   number of SDBs per SDBT (minimum 1, maximum 511)
- *
- * Returns 0 on success, !0 on failure.
- */
-int hwsampler_allocate(unsigned long sdbt, unsigned long sdb)
-{
-	int cpu, rc;
-	mutex_lock(&hws_sem);
-
-	rc = -EINVAL;
-	if (hws_state != HWS_DEALLOCATED)
-		goto allocate_exit;
-
-	if (sdbt < 1)
-		goto allocate_exit;
-
-	if (sdb > MAX_NUM_SDB || sdb < MIN_NUM_SDB)
-		goto allocate_exit;
-
-	num_sdbt = sdbt;
-	num_sdb = sdb;
-
-	oom_killer_was_active = 0;
-	register_oom_notifier(&hws_oom_notifier);
-
-	for_each_online_cpu(cpu) {
-		if (allocate_sdbt(cpu)) {
-			unregister_oom_notifier(&hws_oom_notifier);
-			goto allocate_error;
-		}
-	}
-	unregister_oom_notifier(&hws_oom_notifier);
-	if (oom_killer_was_active)
-		goto allocate_error;
-
-	hws_state = HWS_STOPPED;
-	rc = 0;
-
-allocate_exit:
-	mutex_unlock(&hws_sem);
-	return rc;
-
-allocate_error:
-	rc = -ENOMEM;
-	printk(KERN_ERR "hwsampler: CPUMF Memory allocation failed.\n");
-	goto allocate_exit;
-}
-
-/**
- * hwsampler_deallocate() - deallocate hardware sampler memory
- *
- * Returns 0 on success, !0 on failure.
- */
-int hwsampler_deallocate(void)
-{
-	int rc;
-
-	mutex_lock(&hws_sem);
-
-	rc = -EINVAL;
-	if (hws_state != HWS_STOPPED)
-		goto deallocate_exit;
-
-	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
-	hws_alert = 0;
-	deallocate_sdbt();
-
-	hws_state = HWS_DEALLOCATED;
-	rc = 0;
-
-deallocate_exit:
-	mutex_unlock(&hws_sem);
-
-	return rc;
-}
-
-unsigned long hwsampler_query_min_interval(void)
-{
-	return min_sampler_rate;
-}
-
-unsigned long hwsampler_query_max_interval(void)
-{
-	return max_sampler_rate;
-}
-
-unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu)
-{
-	struct hws_cpu_buffer *cb;
-
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	return cb->sample_overflow;
-}
-
-int hwsampler_setup(void)
-{
-	int rc;
-	int cpu;
-	struct hws_cpu_buffer *cb;
-
-	mutex_lock(&hws_sem);
-
-	rc = -EINVAL;
-	if (hws_state)
-		goto setup_exit;
-
-	hws_state = HWS_INIT;
-
-	init_all_cpu_buffers();
-
-	rc = check_hardware_prerequisites();
-	if (rc)
-		goto setup_exit;
-
-	rc = check_qsi_on_setup();
-	if (rc)
-		goto setup_exit;
-
-	rc = -EINVAL;
-	hws_wq = create_workqueue("hwsampler");
-	if (!hws_wq)
-		goto setup_exit;
-
-	register_cpu_notifier(&hws_cpu_notifier);
-
-	for_each_online_cpu(cpu) {
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-		INIT_WORK(&cb->worker, worker);
-		rc = smp_ctl_qsi(cpu);
-		WARN_ON(rc);
-		if (min_sampler_rate != cb->qsi.min_sampl_rate) {
-			if (min_sampler_rate) {
-				printk(KERN_WARNING
-					"hwsampler: different min sampler rate values.\n");
-				if (min_sampler_rate < cb->qsi.min_sampl_rate)
-					min_sampler_rate =
-						cb->qsi.min_sampl_rate;
-			} else
-				min_sampler_rate = cb->qsi.min_sampl_rate;
-		}
-		if (max_sampler_rate != cb->qsi.max_sampl_rate) {
-			if (max_sampler_rate) {
-				printk(KERN_WARNING
-					"hwsampler: different max sampler rate values.\n");
-				if (max_sampler_rate > cb->qsi.max_sampl_rate)
-					max_sampler_rate =
-						cb->qsi.max_sampl_rate;
-			} else
-				max_sampler_rate = cb->qsi.max_sampl_rate;
-		}
-	}
-	register_external_irq(EXT_IRQ_MEASURE_ALERT, hws_ext_handler);
-
-	hws_state = HWS_DEALLOCATED;
-	rc = 0;
-
-setup_exit:
-	mutex_unlock(&hws_sem);
-	return rc;
-}
-
-int hwsampler_shutdown(void)
-{
-	int rc;
-
-	mutex_lock(&hws_sem);
-
-	rc = -EINVAL;
-	if (hws_state == HWS_DEALLOCATED || hws_state == HWS_STOPPED) {
-		mutex_unlock(&hws_sem);
-
-		if (hws_wq)
-			flush_workqueue(hws_wq);
-
-		mutex_lock(&hws_sem);
-
-		if (hws_state == HWS_STOPPED) {
-			irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
-			hws_alert = 0;
-			deallocate_sdbt();
-		}
-		if (hws_wq) {
-			destroy_workqueue(hws_wq);
-			hws_wq = NULL;
-		}
-
-		unregister_external_irq(EXT_IRQ_MEASURE_ALERT, hws_ext_handler);
-		hws_state = HWS_INIT;
-		rc = 0;
-	}
-	mutex_unlock(&hws_sem);
-
-	unregister_cpu_notifier(&hws_cpu_notifier);
-
-	return rc;
-}
-
-/**
- * hwsampler_start_all() - start hardware sampling on all online CPUs
- * @rate:  specifies the used interval when samples are taken
- *
- * Returns 0 on success, !0 on failure.
- */
-int hwsampler_start_all(unsigned long rate)
-{
-	int rc, cpu;
-
-	mutex_lock(&hws_sem);
-
-	hws_oom = 0;
-
-	rc = -EINVAL;
-	if (hws_state != HWS_STOPPED)
-		goto start_all_exit;
-
-	interval = rate;
-
-	/* fail if rate is not valid */
-	if (interval < min_sampler_rate || interval > max_sampler_rate)
-		goto start_all_exit;
-
-	rc = check_qsi_on_start();
-	if (rc)
-		goto start_all_exit;
-
-	prepare_cpu_buffers();
-
-	for_each_online_cpu(cpu) {
-		rc = start_sampling(cpu);
-		if (rc)
-			break;
-	}
-	if (rc) {
-		for_each_online_cpu(cpu) {
-			stop_sampling(cpu);
-		}
-		goto start_all_exit;
-	}
-	hws_state = HWS_STARTED;
-	rc = 0;
-
-start_all_exit:
-	mutex_unlock(&hws_sem);
-
-	if (rc)
-		return rc;
-
-	register_oom_notifier(&hws_oom_notifier);
-	hws_oom = 1;
-	hws_flush_all = 0;
-	/* now let them in, 1407 CPUMF external interrupts */
-	hws_alert = 1;
-	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
-
-	return 0;
-}
-
-/**
- * hwsampler_stop_all() - stop hardware sampling on all online CPUs
- *
- * Returns 0 on success, !0 on failure.
- */
-int hwsampler_stop_all(void)
-{
-	int tmp_rc, rc, cpu;
-	struct hws_cpu_buffer *cb;
-
-	mutex_lock(&hws_sem);
-
-	rc = 0;
-	if (hws_state == HWS_INIT) {
-		mutex_unlock(&hws_sem);
-		return 0;
-	}
-	hws_state = HWS_STOPPING;
-	mutex_unlock(&hws_sem);
-
-	for_each_online_cpu(cpu) {
-		cb = &per_cpu(sampler_cpu_buffer, cpu);
-		cb->stop_mode = 1;
-		tmp_rc = stop_sampling(cpu);
-		if (tmp_rc)
-			rc = tmp_rc;
-	}
-
-	if (hws_wq)
-		flush_workqueue(hws_wq);
-
-	mutex_lock(&hws_sem);
-	if (hws_oom) {
-		unregister_oom_notifier(&hws_oom_notifier);
-		hws_oom = 0;
-	}
-	hws_state = HWS_STOPPED;
-	mutex_unlock(&hws_sem);
-
-	return rc;
-}
diff --git a/arch/s390/oprofile/hwsampler.h b/arch/s390/oprofile/hwsampler.h
deleted file mode 100644
index a483d06f2fa7..000000000000
--- a/arch/s390/oprofile/hwsampler.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * CPUMF HW sampler functions and internal structures
- *
- *    Copyright IBM Corp. 2010
- *    Author(s): Heinz Graalfs <graalfs@de.ibm.com>
- */
-
-#ifndef HWSAMPLER_H_
-#define HWSAMPLER_H_
-
-#include <linux/workqueue.h>
-#include <asm/cpu_mf.h>
-
-struct hws_ssctl_request_block     /* SET SAMPLING CONTROLS req block   */
-{ /* bytes 0 - 7  Bit(s) */
-	unsigned int s:1;           /* 0: maximum buffer indicator       */
-	unsigned int h:1;           /* 1: part. level reserved for VM use*/
-	unsigned long b2_53:52;     /* 2-53: zeros                       */
-	unsigned int es:1;          /* 54: sampling enable control       */
-	unsigned int b55_61:7;      /* 55-61: - zeros                    */
-	unsigned int cs:1;          /* 62: sampling activation control   */
-	unsigned int b63:1;         /* 63: zero                          */
-	unsigned long interval;     /* 8-15: sampling interval           */
-	unsigned long tear;         /* 16-23: TEAR contents              */
-	unsigned long dear;         /* 24-31: DEAR contents              */
-	/* 32-63:                                                        */
-	unsigned long rsvrd1;       /* reserved                          */
-	unsigned long rsvrd2;       /* reserved                          */
-	unsigned long rsvrd3;       /* reserved                          */
-	unsigned long rsvrd4;       /* reserved                          */
-};
-
-struct hws_cpu_buffer {
-	unsigned long first_sdbt;       /* @ of 1st SDB-Table for this CP*/
-	unsigned long worker_entry;
-	unsigned long sample_overflow;  /* taken from SDB ...            */
-	struct hws_qsi_info_block qsi;
-	struct hws_ssctl_request_block ssctl;
-	struct work_struct worker;
-	atomic_t ext_params;
-	unsigned long req_alert;
-	unsigned long loss_of_sample_data;
-	unsigned long invalid_entry_address;
-	unsigned long incorrect_sdbt_entry;
-	unsigned long sample_auth_change_alert;
-	unsigned int finish:1;
-	unsigned int oom:1;
-	unsigned int stop_mode:1;
-};
-
-int hwsampler_setup(void);
-int hwsampler_shutdown(void);
-int hwsampler_allocate(unsigned long sdbt, unsigned long sdb);
-int hwsampler_deallocate(void);
-unsigned long hwsampler_query_min_interval(void);
-unsigned long hwsampler_query_max_interval(void);
-int hwsampler_start_all(unsigned long interval);
-int hwsampler_stop_all(void);
-int hwsampler_deactivate(unsigned int cpu);
-int hwsampler_activate(unsigned int cpu);
-unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu);
-
-#endif /*HWSAMPLER_H_*/
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 791935a65800..16f4c3960b87 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -10,488 +10,8 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/perf_event.h>
 #include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/module.h>
 #include <asm/processor.h>
-#include <asm/perf_event.h>
-
-#include "../../../drivers/oprofile/oprof.h"
-
-#include "hwsampler.h"
-#include "op_counter.h"
-
-#define DEFAULT_INTERVAL	4127518
-
-#define DEFAULT_SDBT_BLOCKS	1
-#define DEFAULT_SDB_BLOCKS	511
-
-static unsigned long oprofile_hw_interval = DEFAULT_INTERVAL;
-static unsigned long oprofile_min_interval;
-static unsigned long oprofile_max_interval;
-
-static unsigned long oprofile_sdbt_blocks = DEFAULT_SDBT_BLOCKS;
-static unsigned long oprofile_sdb_blocks = DEFAULT_SDB_BLOCKS;
-
-static int hwsampler_enabled;
-static int hwsampler_running;	/* start_mutex must be held to change */
-static int hwsampler_available;
-
-static struct oprofile_operations timer_ops;
-
-struct op_counter_config counter_config;
-
-enum __force_cpu_type {
-	reserved = 0,		/* do not force */
-	timer,
-};
-static int force_cpu_type;
-
-static int set_cpu_type(const char *str, struct kernel_param *kp)
-{
-	if (!strcmp(str, "timer")) {
-		force_cpu_type = timer;
-		printk(KERN_INFO "oprofile: forcing timer to be returned "
-		                 "as cpu type\n");
-	} else {
-		force_cpu_type = 0;
-	}
-
-	return 0;
-}
-module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
-MODULE_PARM_DESC(cpu_type, "Force legacy basic mode sampling"
-		           "(report cpu_type \"timer\"");
-
-static int __oprofile_hwsampler_start(void)
-{
-	int retval;
-
-	retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
-	if (retval)
-		return retval;
-
-	retval = hwsampler_start_all(oprofile_hw_interval);
-	if (retval)
-		hwsampler_deallocate();
-
-	return retval;
-}
-
-static int oprofile_hwsampler_start(void)
-{
-	int retval;
-
-	hwsampler_running = hwsampler_enabled;
-
-	if (!hwsampler_running)
-		return timer_ops.start();
-
-	retval = perf_reserve_sampling();
-	if (retval)
-		return retval;
-
-	retval = __oprofile_hwsampler_start();
-	if (retval)
-		perf_release_sampling();
-
-	return retval;
-}
-
-static void oprofile_hwsampler_stop(void)
-{
-	if (!hwsampler_running) {
-		timer_ops.stop();
-		return;
-	}
-
-	hwsampler_stop_all();
-	hwsampler_deallocate();
-	perf_release_sampling();
-	return;
-}
-
-/*
- * File ops used for:
- * /dev/oprofile/0/enabled
- * /dev/oprofile/hwsampling/hwsampler  (cpu_type = timer)
- */
-
-static ssize_t hwsampler_read(struct file *file, char __user *buf,
-		size_t count, loff_t *offset)
-{
-	return oprofilefs_ulong_to_user(hwsampler_enabled, buf, count, offset);
-}
-
-static ssize_t hwsampler_write(struct file *file, char const __user *buf,
-		size_t count, loff_t *offset)
-{
-	unsigned long val;
-	int retval;
-
-	if (*offset)
-		return -EINVAL;
-
-	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval <= 0)
-		return retval;
-
-	if (val != 0 && val != 1)
-		return -EINVAL;
-
-	if (oprofile_started)
-		/*
-		 * save to do without locking as we set
-		 * hwsampler_running in start() when start_mutex is
-		 * held
-		 */
-		return -EBUSY;
-
-	hwsampler_enabled = val;
-
-	return count;
-}
-
-static const struct file_operations hwsampler_fops = {
-	.read		= hwsampler_read,
-	.write		= hwsampler_write,
-};
-
-/*
- * File ops used for:
- * /dev/oprofile/0/count
- * /dev/oprofile/hwsampling/hw_interval  (cpu_type = timer)
- *
- * Make sure that the value is within the hardware range.
- */
-
-static ssize_t hw_interval_read(struct file *file, char __user *buf,
-				size_t count, loff_t *offset)
-{
-	return oprofilefs_ulong_to_user(oprofile_hw_interval, buf,
-					count, offset);
-}
-
-static ssize_t hw_interval_write(struct file *file, char const __user *buf,
-				 size_t count, loff_t *offset)
-{
-	unsigned long val;
-	int retval;
-
-	if (*offset)
-		return -EINVAL;
-	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval <= 0)
-		return retval;
-	if (val < oprofile_min_interval)
-		oprofile_hw_interval = oprofile_min_interval;
-	else if (val > oprofile_max_interval)
-		oprofile_hw_interval = oprofile_max_interval;
-	else
-		oprofile_hw_interval = val;
-
-	return count;
-}
-
-static const struct file_operations hw_interval_fops = {
-	.read		= hw_interval_read,
-	.write		= hw_interval_write,
-};
-
-/*
- * File ops used for:
- * /dev/oprofile/0/event
- * Only a single event with number 0 is supported with this counter.
- *
- * /dev/oprofile/0/unit_mask
- * This is a dummy file needed by the user space tools.
- * No value other than 0 is accepted or returned.
- */
-
-static ssize_t hwsampler_zero_read(struct file *file, char __user *buf,
-				    size_t count, loff_t *offset)
-{
-	return oprofilefs_ulong_to_user(0, buf, count, offset);
-}
-
-static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
-				     size_t count, loff_t *offset)
-{
-	unsigned long val;
-	int retval;
-
-	if (*offset)
-		return -EINVAL;
-
-	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval <= 0)
-		return retval;
-	if (val != 0)
-		return -EINVAL;
-	return count;
-}
-
-static const struct file_operations zero_fops = {
-	.read		= hwsampler_zero_read,
-	.write		= hwsampler_zero_write,
-};
-
-/* /dev/oprofile/0/kernel file ops.  */
-
-static ssize_t hwsampler_kernel_read(struct file *file, char __user *buf,
-				     size_t count, loff_t *offset)
-{
-	return oprofilefs_ulong_to_user(counter_config.kernel,
-					buf, count, offset);
-}
-
-static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
-				      size_t count, loff_t *offset)
-{
-	unsigned long val;
-	int retval;
-
-	if (*offset)
-		return -EINVAL;
-
-	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval <= 0)
-		return retval;
-
-	if (val != 0 && val != 1)
-		return -EINVAL;
-
-	counter_config.kernel = val;
-
-	return count;
-}
-
-static const struct file_operations kernel_fops = {
-	.read		= hwsampler_kernel_read,
-	.write		= hwsampler_kernel_write,
-};
-
-/* /dev/oprofile/0/user file ops. */
-
-static ssize_t hwsampler_user_read(struct file *file, char __user *buf,
-				   size_t count, loff_t *offset)
-{
-	return oprofilefs_ulong_to_user(counter_config.user,
-					buf, count, offset);
-}
-
-static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
-				    size_t count, loff_t *offset)
-{
-	unsigned long val;
-	int retval;
-
-	if (*offset)
-		return -EINVAL;
-
-	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval <= 0)
-		return retval;
-
-	if (val != 0 && val != 1)
-		return -EINVAL;
-
-	counter_config.user = val;
-
-	return count;
-}
-
-static const struct file_operations user_fops = {
-	.read		= hwsampler_user_read,
-	.write		= hwsampler_user_write,
-};
-
-
-/*
- * File ops used for: /dev/oprofile/timer/enabled
- * The value always has to be the inverted value of hwsampler_enabled. So
- * no separate variable is created. That way we do not need locking.
- */
-
-static ssize_t timer_enabled_read(struct file *file, char __user *buf,
-				  size_t count, loff_t *offset)
-{
-	return oprofilefs_ulong_to_user(!hwsampler_enabled, buf, count, offset);
-}
-
-static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
-				   size_t count, loff_t *offset)
-{
-	unsigned long val;
-	int retval;
-
-	if (*offset)
-		return -EINVAL;
-
-	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval <= 0)
-		return retval;
-
-	if (val != 0 && val != 1)
-		return -EINVAL;
-
-	/* Timer cannot be disabled without having hardware sampling.  */
-	if (val == 0 && !hwsampler_available)
-		return -EINVAL;
-
-	if (oprofile_started)
-		/*
-		 * save to do without locking as we set
-		 * hwsampler_running in start() when start_mutex is
-		 * held
-		 */
-		return -EBUSY;
-
-	hwsampler_enabled = !val;
-
-	return count;
-}
-
-static const struct file_operations timer_enabled_fops = {
-	.read		= timer_enabled_read,
-	.write		= timer_enabled_write,
-};
-
-
-static int oprofile_create_hwsampling_files(struct dentry *root)
-{
-	struct dentry *dir;
-
-	dir = oprofilefs_mkdir(root, "timer");
-	if (!dir)
-		return -EINVAL;
-
-	oprofilefs_create_file(dir, "enabled", &timer_enabled_fops);
-
-	if (!hwsampler_available)
-		return 0;
-
-	/* reinitialize default values */
-	hwsampler_enabled = 1;
-	counter_config.kernel = 1;
-	counter_config.user = 1;
-
-	if (!force_cpu_type) {
-		/*
-		 * Create the counter file system.  A single virtual
-		 * counter is created which can be used to
-		 * enable/disable hardware sampling dynamically from
-		 * user space.  The user space will configure a single
-		 * counter with a single event.  The value of 'event'
-		 * and 'unit_mask' are not evaluated by the kernel code
-		 * and can only be set to 0.
-		 */
-
-		dir = oprofilefs_mkdir(root, "0");
-		if (!dir)
-			return -EINVAL;
-
-		oprofilefs_create_file(dir, "enabled", &hwsampler_fops);
-		oprofilefs_create_file(dir, "event", &zero_fops);
-		oprofilefs_create_file(dir, "count", &hw_interval_fops);
-		oprofilefs_create_file(dir, "unit_mask", &zero_fops);
-		oprofilefs_create_file(dir, "kernel", &kernel_fops);
-		oprofilefs_create_file(dir, "user", &user_fops);
-		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
-					&oprofile_sdbt_blocks);
-
-	} else {
-		/*
-		 * Hardware sampling can be used but the cpu_type is
-		 * forced to timer in order to deal with legacy user
-		 * space tools.  The /dev/oprofile/hwsampling fs is
-		 * provided in that case.
-		 */
-		dir = oprofilefs_mkdir(root, "hwsampling");
-		if (!dir)
-			return -EINVAL;
-
-		oprofilefs_create_file(dir, "hwsampler",
-				       &hwsampler_fops);
-		oprofilefs_create_file(dir, "hw_interval",
-				       &hw_interval_fops);
-		oprofilefs_create_ro_ulong(dir, "hw_min_interval",
-					   &oprofile_min_interval);
-		oprofilefs_create_ro_ulong(dir, "hw_max_interval",
-					   &oprofile_max_interval);
-		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
-					&oprofile_sdbt_blocks);
-	}
-	return 0;
-}
-
-static int oprofile_hwsampler_init(struct oprofile_operations *ops)
-{
-	/*
-	 * Initialize the timer mode infrastructure as well in order
-	 * to be able to switch back dynamically.  oprofile_timer_init
-	 * is not supposed to fail.
-	 */
-	if (oprofile_timer_init(ops))
-		BUG();
-
-	memcpy(&timer_ops, ops, sizeof(timer_ops));
-	ops->create_files = oprofile_create_hwsampling_files;
-
-	/*
-	 * If the user space tools do not support newer cpu types,
-	 * the force_cpu_type module parameter
-	 * can be used to always return \"timer\" as cpu type.
-	 */
-	if (force_cpu_type != timer) {
-		struct cpuid id;
-
-		get_cpu_id (&id);
-
-		switch (id.machine) {
-		case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
-		case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
-		case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break;
-		case 0x2964: case 0x2965: ops->cpu_type = "s390/z13"; break;
-		default: return -ENODEV;
-		}
-	}
-
-	if (hwsampler_setup())
-		return -ENODEV;
-
-	/*
-	 * Query the range for the sampling interval from the
-	 * hardware.
-	 */
-	oprofile_min_interval = hwsampler_query_min_interval();
-	if (oprofile_min_interval == 0)
-		return -ENODEV;
-	oprofile_max_interval = hwsampler_query_max_interval();
-	if (oprofile_max_interval == 0)
-		return -ENODEV;
-
-	/* The initial value should be sane */
-	if (oprofile_hw_interval < oprofile_min_interval)
-		oprofile_hw_interval = oprofile_min_interval;
-	if (oprofile_hw_interval > oprofile_max_interval)
-		oprofile_hw_interval = oprofile_max_interval;
-
-	printk(KERN_INFO "oprofile: System z hardware sampling "
-	       "facility found.\n");
-
-	ops->start = oprofile_hwsampler_start;
-	ops->stop = oprofile_hwsampler_stop;
-
-	return 0;
-}
-
-static void oprofile_hwsampler_exit(void)
-{
-	hwsampler_shutdown();
-}
 
 static int __s390_backtrace(void *data, unsigned long address)
 {
@@ -514,18 +34,9 @@ static void s390_backtrace(struct pt_regs *regs, unsigned int depth)
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	ops->backtrace = s390_backtrace;
-
-	/*
-	 * -ENODEV is not reported to the caller.  The module itself
-         * will use the timer mode sampling as fallback and this is
-         * always available.
-	 */
-	hwsampler_available = oprofile_hwsampler_init(ops) == 0;
-
 	return 0;
 }
 
 void oprofile_arch_exit(void)
 {
-	oprofile_hwsampler_exit();
 }
diff --git a/arch/s390/oprofile/op_counter.h b/arch/s390/oprofile/op_counter.h
deleted file mode 100644
index 61b2531eef17..000000000000
--- a/arch/s390/oprofile/op_counter.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- *   Copyright IBM Corp. 2011
- *   Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
- *
- * @remark Copyright 2011 OProfile authors
- */
-
-#ifndef OP_COUNTER_H
-#define OP_COUNTER_H
-
-struct op_counter_config {
-	/* `enabled' maps to the hwsampler_file variable.  */
-	/* `count' maps to the oprofile_hw_interval variable.  */
-	/* `event' and `unit_mask' are unused. */
-	unsigned long kernel;
-	unsigned long user;
-};
-
-extern struct op_counter_config counter_config;
-
-#endif /* OP_COUNTER_H */
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 1ea8c07eab84..070f1ae5cfad 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -226,7 +226,8 @@ static unsigned long __dma_alloc_iommu(struct device *dev,
 	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
 			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
-				start, size, 0, boundary_size, 0);
+				start, size, zdev->start_dma >> PAGE_SHIFT,
+				boundary_size, 0);
 }
 
 static unsigned long dma_alloc_iommu(struct device *dev, int size)
@@ -469,6 +470,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 	 * Also set zdev->end_dma to the actual end address of the usable
 	 * range, instead of the theoretical maximum as reported by hardware.
 	 */
+	zdev->start_dma = PAGE_ALIGN(zdev->start_dma);
 	zdev->iommu_size = min3((u64) high_memory,
 				ZPCI_TABLE_SIZE_RT - zdev->start_dma,
 				zdev->end_dma - zdev->start_dma + 1);
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index fb2a9a560fdc..c2b27ad8e94d 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -145,8 +145,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	default:
 		break;
 	}
-	if (pdev)
-		pci_dev_put(pdev);
+	pci_dev_put(pdev);
 }
 
 void zpci_event_availability(void *data)
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 10ca15dcab11..fa8d7d4b9751 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -99,7 +99,7 @@ void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc)
 }
 
 /* PCI Load */
-static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
+static inline int ____pcilg(u64 *data, u64 req, u64 offset, u8 *status)
 {
 	register u64 __req asm("2") = req;
 	register u64 __offset asm("3") = offset;
@@ -116,6 +116,16 @@ static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
 		:  "d" (__offset)
 		: "cc");
 	*status = __req >> 24 & 0xff;
+	*data = __data;
+	return cc;
+}
+
+static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
+{
+	u64 __data;
+	int cc;
+
+	cc = ____pcilg(&__data, req, offset, status);
 	if (!cc)
 		*data = __data;
 
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index e803a836cb7c..0d5f3a9bb315 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -264,7 +264,6 @@ config CPU_SUBTYPE_SH7203
 	select CPU_HAS_FPU
 	select SYS_SUPPORTS_SH_CMT
 	select SYS_SUPPORTS_SH_MTU2
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select PINCTRL
 
 config CPU_SUBTYPE_SH7206
@@ -353,7 +352,6 @@ config CPU_SUBTYPE_SH7720
 	select CPU_SH3
 	select CPU_HAS_DSP
 	select SYS_SUPPORTS_SH_CMT
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select USB_OHCI_SH if USB_OHCI_HCD
 	select PINCTRL
 	help
@@ -419,7 +417,6 @@ config CPU_SUBTYPE_SH7723
 	select ARCH_SHMOBILE
 	select ARCH_SPARSEMEM_ENABLE
 	select SYS_SUPPORTS_SH_CMT
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select PINCTRL
 	help
 	  Select SH7723 if you have an SH-MobileR2 CPU.
@@ -431,7 +428,6 @@ config CPU_SUBTYPE_SH7724
 	select ARCH_SHMOBILE
 	select ARCH_SPARSEMEM_ENABLE
 	select SYS_SUPPORTS_SH_CMT
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select PINCTRL
 	help
 	  Select SH7724 if you have an SH-MobileR2R CPU.
@@ -440,7 +436,6 @@ config CPU_SUBTYPE_SH7734
 	bool "Support SH7734 processor"
 	select CPU_SH4A
 	select CPU_SHX2
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select PINCTRL
 	help
 	  Select SH7734 if you have a SH4A SH7734 CPU.
@@ -449,7 +444,6 @@ config CPU_SUBTYPE_SH7757
 	bool "Support SH7757 processor"
 	select CPU_SH4A
 	select CPU_SHX2
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select PINCTRL
 	help
 	  Select SH7757 if you have a SH4A SH7757 CPU.
@@ -475,7 +469,6 @@ config CPU_SUBTYPE_SH7785
 	select CPU_SHX2
 	select ARCH_SPARSEMEM_ENABLE
 	select SYS_SUPPORTS_NUMA
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select PINCTRL
 
 config CPU_SUBTYPE_SH7786
@@ -484,7 +477,6 @@ config CPU_SUBTYPE_SH7786
 	select CPU_SHX3
 	select CPU_HAS_PTEAEX
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select USB_OHCI_SH if USB_OHCI_HCD
 	select USB_EHCI_SH if USB_EHCI_HCD
 	select PINCTRL
@@ -494,7 +486,7 @@ config CPU_SUBTYPE_SHX3
 	select CPU_SH4A
 	select CPU_SHX3
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select PINCTRL
 
 # SH4AL-DSP Processor Support
@@ -513,7 +505,6 @@ config CPU_SUBTYPE_SH7722
 	select ARCH_SPARSEMEM_ENABLE
 	select SYS_SUPPORTS_NUMA
 	select SYS_SUPPORTS_SH_CMT
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select PINCTRL
 
 config CPU_SUBTYPE_SH7366
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index 5e52d5362292..e0db04664e2e 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -70,7 +70,7 @@ config SH_7724_SOLUTION_ENGINE
 	bool "SolutionEngine7724"
 	select SOLUTION_ENGINE
 	depends on CPU_SUBTYPE_SH7724
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select SND_SOC_AK4642 if SND_SIMPLE_CARD
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
@@ -174,7 +174,6 @@ config SH_SDK7786
 	depends on CPU_SUBTYPE_SH7786
 	select SYS_SUPPORTS_PCI
 	select NO_IOPORT_MAP if !PCI
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_SRAM_POOL
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
@@ -190,7 +189,7 @@ config SH_HIGHLANDER
 config SH_SH7757LCR
 	bool "SH7757LCR"
 	depends on CPU_SUBTYPE_SH7757
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config SH_SH7785LCR
@@ -217,14 +216,14 @@ config SH_SH7785LCR_PT
 config SH_URQUELL
 	bool "Urquell"
 	depends on CPU_SUBTYPE_SH7786
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select SYS_SUPPORTS_PCI
 	select NO_IOPORT_MAP if !PCI
 
 config SH_MIGOR
 	bool "Migo-R"
 	depends on CPU_SUBTYPE_SH7722
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
 	  Select Migo-R if configuring for the SH7722 Migo-R platform
@@ -233,7 +232,7 @@ config SH_MIGOR
 config SH_AP325RXA
 	bool "AP-325RXA"
 	depends on CPU_SUBTYPE_SH7723
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
 	  Renesas "AP-325RXA" support.
@@ -242,7 +241,7 @@ config SH_AP325RXA
 config SH_KFR2R09
 	bool "KFR2R09"
 	depends on CPU_SUBTYPE_SH7724
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
 	  "Kit For R2R for 2009" support.
@@ -250,7 +249,7 @@ config SH_KFR2R09
 config SH_ECOVEC
 	bool "EcoVec"
 	depends on CPU_SUBTYPE_SH7724
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select SND_SOC_DA7210 if SND_SIMPLE_CARD
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
@@ -327,7 +326,7 @@ config SH_X3PROTO
 config SH_MAGIC_PANEL_R2
 	bool "Magic Panel R2"
 	depends on CPU_SUBTYPE_SH7720
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
 	  Select Magic Panel R2 if configuring for Magic Panel R2.
diff --git a/arch/sh/boards/mach-highlander/Kconfig b/arch/sh/boards/mach-highlander/Kconfig
index def49cc0a7b9..42f5589b4bf3 100644
--- a/arch/sh/boards/mach-highlander/Kconfig
+++ b/arch/sh/boards/mach-highlander/Kconfig
@@ -18,7 +18,7 @@ config SH_R7780MP
 config SH_R7785RP
 	bool "R7785RP board support"
 	depends on CPU_SUBTYPE_SH7785
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 
 endchoice
 
diff --git a/arch/sh/boards/mach-rsk/Kconfig b/arch/sh/boards/mach-rsk/Kconfig
index 458a11ffd022..0b9b2c4952c1 100644
--- a/arch/sh/boards/mach-rsk/Kconfig
+++ b/arch/sh/boards/mach-rsk/Kconfig
@@ -10,17 +10,17 @@ config SH_RSK7201
 
 config SH_RSK7203
 	bool "RSK7203"
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	depends on CPU_SUBTYPE_SH7203
 
 config SH_RSK7264
 	bool "RSK2+SH7264"
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	depends on CPU_SUBTYPE_SH7264
 
 config SH_RSK7269
 	bool "RSK2+SH7269"
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	depends on CPU_SUBTYPE_SH7269
 
 endchoice
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 17e96dc29596..f3540270d096 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -801,6 +801,7 @@ static void ubd_device_release(struct device *dev)
 static int ubd_disk_register(int major, u64 size, int unit,
 			     struct gendisk **disk_out)
 {
+	struct device *parent = NULL;
 	struct gendisk *disk;
 
 	disk = alloc_disk(1 << UBD_SHIFT);
@@ -823,12 +824,12 @@ static int ubd_disk_register(int major, u64 size, int unit,
 		ubd_devs[unit].pdev.dev.release = ubd_device_release;
 		dev_set_drvdata(&ubd_devs[unit].pdev.dev, &ubd_devs[unit]);
 		platform_device_register(&ubd_devs[unit].pdev);
-		disk->driverfs_dev = &ubd_devs[unit].pdev.dev;
+		parent = &ubd_devs[unit].pdev.dev;
 	}
 
 	disk->private_data = &ubd_devs[unit];
 	disk->queue = ubd_devs[unit].queue;
-	add_disk(disk);
+	device_add_disk(parent, disk);
 
 	*disk_out = disk;
 	return 0;
@@ -1286,7 +1287,7 @@ static void do_ubd_request(struct request_queue *q)
 
 		req = dev->request;
 
-		if (req->cmd_flags & REQ_FLUSH) {
+		if (req_op(req) == REQ_OP_FLUSH) {
 			io_req = kmalloc(sizeof(struct io_thread_req),
 					 GFP_ATOMIC);
 			if (io_req == NULL) {
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index e5602ee9c610..0769066929c6 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -80,7 +80,7 @@ config ARCH_PUV3
 	select CPU_UCV2
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 
 # CONFIGs for ARCH_PUV3
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5977fea2c8b1..2fa55851d2a9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -22,6 +22,7 @@ config X86
 	select ANON_INODES
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_DISCARD_MEMBLOCK
+	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index b9b912a44d61..34b3fa2889d1 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -49,7 +49,9 @@ endif
 ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
-	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
+	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha1-mb/
+	obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb/
+	obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb/
 endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 5b7fa1471007..0ab5ee1c26af 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -59,17 +59,6 @@ struct aesni_rfc4106_gcm_ctx {
 	u8 nonce[4];
 };
 
-struct aesni_gcm_set_hash_subkey_result {
-	int err;
-	struct completion completion;
-};
-
-struct aesni_hash_subkey_req_data {
-	u8 iv[16];
-	struct aesni_gcm_set_hash_subkey_result result;
-	struct scatterlist sg;
-};
-
 struct aesni_lrw_ctx {
 	struct lrw_table_ctx lrw_table;
 	u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
@@ -809,71 +798,28 @@ static void rfc4106_exit(struct crypto_aead *aead)
 	cryptd_free_aead(*ctx);
 }
 
-static void
-rfc4106_set_hash_subkey_done(struct crypto_async_request *req, int err)
-{
-	struct aesni_gcm_set_hash_subkey_result *result = req->data;
-
-	if (err == -EINPROGRESS)
-		return;
-	result->err = err;
-	complete(&result->completion);
-}
-
 static int
 rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
 {
-	struct crypto_ablkcipher *ctr_tfm;
-	struct ablkcipher_request *req;
-	int ret = -EINVAL;
-	struct aesni_hash_subkey_req_data *req_data;
+	struct crypto_cipher *tfm;
+	int ret;
 
-	ctr_tfm = crypto_alloc_ablkcipher("ctr(aes)", 0, 0);
-	if (IS_ERR(ctr_tfm))
-		return PTR_ERR(ctr_tfm);
+	tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
 
-	ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len);
+	ret = crypto_cipher_setkey(tfm, key, key_len);
 	if (ret)
-		goto out_free_ablkcipher;
-
-	ret = -ENOMEM;
-	req = ablkcipher_request_alloc(ctr_tfm, GFP_KERNEL);
-	if (!req)
-		goto out_free_ablkcipher;
-
-	req_data = kmalloc(sizeof(*req_data), GFP_KERNEL);
-	if (!req_data)
-		goto out_free_request;
-
-	memset(req_data->iv, 0, sizeof(req_data->iv));
+		goto out_free_cipher;
 
 	/* Clear the data in the hash sub key container to zero.*/
 	/* We want to cipher all zeros to create the hash sub key. */
 	memset(hash_subkey, 0, RFC4106_HASH_SUBKEY_SIZE);
 
-	init_completion(&req_data->result.completion);
-	sg_init_one(&req_data->sg, hash_subkey, RFC4106_HASH_SUBKEY_SIZE);
-	ablkcipher_request_set_tfm(req, ctr_tfm);
-	ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP |
-					CRYPTO_TFM_REQ_MAY_BACKLOG,
-					rfc4106_set_hash_subkey_done,
-					&req_data->result);
-
-	ablkcipher_request_set_crypt(req, &req_data->sg,
-		&req_data->sg, RFC4106_HASH_SUBKEY_SIZE, req_data->iv);
-
-	ret = crypto_ablkcipher_encrypt(req);
-	if (ret == -EINPROGRESS || ret == -EBUSY) {
-		ret = wait_for_completion_interruptible
-			(&req_data->result.completion);
-		if (!ret)
-			ret = req_data->result.err;
-	}
-	kfree(req_data);
-out_free_request:
-	ablkcipher_request_free(req);
-out_free_ablkcipher:
-	crypto_free_ablkcipher(ctr_tfm);
+	crypto_cipher_encrypt_one(tfm, hash_subkey, hash_subkey);
+
+out_free_cipher:
+	crypto_free_cipher(tfm);
 	return ret;
 }
 
@@ -1098,9 +1044,12 @@ static int rfc4106_encrypt(struct aead_request *req)
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	aead_request_set_tfm(req, irq_fpu_usable() ?
-				  cryptd_aead_child(cryptd_tfm) :
-				  &cryptd_tfm->base);
+	tfm = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		tfm = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, tfm);
 
 	return crypto_aead_encrypt(req);
 }
@@ -1111,9 +1060,12 @@ static int rfc4106_decrypt(struct aead_request *req)
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	aead_request_set_tfm(req, irq_fpu_usable() ?
-				  cryptd_aead_child(cryptd_tfm) :
-				  &cryptd_tfm->base);
+	tfm = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		tfm = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, tfm);
 
 	return crypto_aead_decrypt(req);
 }
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 2d5c2e0bd939..f910d1d449f0 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -70,7 +70,7 @@ static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
 	struct blkcipher_walk walk;
 	int err;
 
-	if (!may_use_simd())
+	if (nbytes <= CHACHA20_BLOCK_SIZE || !may_use_simd())
 		return crypto_chacha20_crypt(desc, dst, src, nbytes);
 
 	state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN);
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index a69321a77783..0420bab19efb 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -168,30 +168,23 @@ static int ghash_async_init(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
-	if (!irq_fpu_usable()) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_init(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		desc->flags = req->base.flags;
-		return crypto_shash_init(desc);
-	}
+	desc->tfm = child;
+	desc->flags = req->base.flags;
+	return crypto_shash_init(desc);
 }
 
 static int ghash_async_update(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!irq_fpu_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_update(cryptd_req);
@@ -204,12 +197,12 @@ static int ghash_async_update(struct ahash_request *req)
 static int ghash_async_final(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!irq_fpu_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_final(cryptd_req);
@@ -249,7 +242,8 @@ static int ghash_async_digest(struct ahash_request *req)
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable()) {
+	if (!irq_fpu_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_digest(cryptd_req);
diff --git a/arch/x86/crypto/sha-mb/Makefile b/arch/x86/crypto/sha1-mb/Makefile
index 2f8756375df5..2f8756375df5 100644
--- a/arch/x86/crypto/sha-mb/Makefile
+++ b/arch/x86/crypto/sha1-mb/Makefile
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c
index 9c5af331a956..9e5b67127a09 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb.c
@@ -67,7 +67,7 @@
 #include <asm/byteorder.h>
 #include <linux/hardirq.h>
 #include <asm/fpu/api.h>
-#include "sha_mb_ctx.h"
+#include "sha1_mb_ctx.h"
 
 #define FLUSH_INTERVAL 1000 /* in usec */
 
@@ -77,30 +77,34 @@ struct sha1_mb_ctx {
 	struct mcryptd_ahash *mcryptd_tfm;
 };
 
-static inline struct mcryptd_hash_request_ctx *cast_hash_to_mcryptd_ctx(struct sha1_hash_ctx *hash_ctx)
+static inline struct mcryptd_hash_request_ctx
+		*cast_hash_to_mcryptd_ctx(struct sha1_hash_ctx *hash_ctx)
 {
-	struct shash_desc *desc;
+	struct ahash_request *areq;
 
-	desc = container_of((void *) hash_ctx, struct shash_desc, __ctx);
-	return container_of(desc, struct mcryptd_hash_request_ctx, desc);
+	areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
+	return container_of(areq, struct mcryptd_hash_request_ctx, areq);
 }
 
-static inline struct ahash_request *cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
+static inline struct ahash_request
+		*cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
 {
 	return container_of((void *) ctx, struct ahash_request, __ctx);
 }
 
 static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
-				struct shash_desc *desc)
+				struct ahash_request *areq)
 {
 	rctx->flag = HASH_UPDATE;
 }
 
 static asmlinkage void (*sha1_job_mgr_init)(struct sha1_mb_mgr *state);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)(struct sha1_mb_mgr *state,
-							  struct job_sha1 *job);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)(struct sha1_mb_mgr *state);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)(struct sha1_mb_mgr *state);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)
+			(struct sha1_mb_mgr *state, struct job_sha1 *job);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)
+						(struct sha1_mb_mgr *state);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)
+						(struct sha1_mb_mgr *state);
 
 static inline void sha1_init_digest(uint32_t *digest)
 {
@@ -131,7 +135,8 @@ static inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2],
 	return i >> SHA1_LOG2_BLOCK_SIZE;
 }
 
-static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr, struct sha1_hash_ctx *ctx)
+static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr,
+						struct sha1_hash_ctx *ctx)
 {
 	while (ctx) {
 		if (ctx->status & HASH_CTX_STS_COMPLETE) {
@@ -177,8 +182,8 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr, str
 
 				ctx->job.buffer = (uint8_t *) buffer;
 				ctx->job.len = len;
-				ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr,
-										  &ctx->job);
+				ctx = (struct sha1_hash_ctx *)sha1_job_mgr_submit(&mgr->mgr,
+										&ctx->job);
 				continue;
 			}
 		}
@@ -191,13 +196,15 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr, str
 		if (ctx->status & HASH_CTX_STS_LAST) {
 
 			uint8_t *buf = ctx->partial_block_buffer;
-			uint32_t n_extra_blocks = sha1_pad(buf, ctx->total_length);
+			uint32_t n_extra_blocks =
+					sha1_pad(buf, ctx->total_length);
 
 			ctx->status = (HASH_CTX_STS_PROCESSING |
 				       HASH_CTX_STS_COMPLETE);
 			ctx->job.buffer = buf;
 			ctx->job.len = (uint32_t) n_extra_blocks;
-			ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
+			ctx = (struct sha1_hash_ctx *)
+				sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
 			continue;
 		}
 
@@ -208,14 +215,17 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr, str
 	return NULL;
 }
 
-static struct sha1_hash_ctx *sha1_ctx_mgr_get_comp_ctx(struct sha1_ctx_mgr *mgr)
+static struct sha1_hash_ctx
+			*sha1_ctx_mgr_get_comp_ctx(struct sha1_ctx_mgr *mgr)
 {
 	/*
 	 * If get_comp_job returns NULL, there are no jobs complete.
-	 * If get_comp_job returns a job, verify that it is safe to return to the user.
+	 * If get_comp_job returns a job, verify that it is safe to return to
+	 * the user.
 	 * If it is not ready, resubmit the job to finish processing.
 	 * If sha1_ctx_mgr_resubmit returned a job, it is ready to be returned.
-	 * Otherwise, all jobs currently being managed by the hash_ctx_mgr still need processing.
+	 * Otherwise, all jobs currently being managed by the hash_ctx_mgr
+	 * still need processing.
 	 */
 	struct sha1_hash_ctx *ctx;
 
@@ -235,7 +245,10 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
 					  int flags)
 {
 	if (flags & (~HASH_ENTIRE)) {
-		/* User should not pass anything other than FIRST, UPDATE, or LAST */
+		/*
+		 * User should not pass anything other than FIRST, UPDATE, or
+		 * LAST
+		 */
 		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
 		return ctx;
 	}
@@ -264,14 +277,20 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
 		ctx->partial_block_buffer_length = 0;
 	}
 
-	/* If we made it here, there were no errors during this call to submit */
+	/*
+	 * If we made it here, there were no errors during this call to
+	 * submit
+	 */
 	ctx->error = HASH_CTX_ERROR_NONE;
 
 	/* Store buffer ptr info from user */
 	ctx->incoming_buffer = buffer;
 	ctx->incoming_buffer_length = len;
 
-	/* Store the user's request flags and mark this ctx as currently being processed. */
+	/*
+	 * Store the user's request flags and mark this ctx as currently
+	 * being processed.
+	 */
 	ctx->status = (flags & HASH_LAST) ?
 			(HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
 			HASH_CTX_STS_PROCESSING;
@@ -285,9 +304,13 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
 	 * Or if the user's buffer contains less than a whole block,
 	 * append as much as possible to the extra block.
 	 */
-	if ((ctx->partial_block_buffer_length) | (len < SHA1_BLOCK_SIZE)) {
-		/* Compute how many bytes to copy from user buffer into extra block */
-		uint32_t copy_len = SHA1_BLOCK_SIZE - ctx->partial_block_buffer_length;
+	if (ctx->partial_block_buffer_length || len < SHA1_BLOCK_SIZE) {
+		/*
+		 * Compute how many bytes to copy from user buffer into
+		 * extra block
+		 */
+		uint32_t copy_len = SHA1_BLOCK_SIZE -
+					ctx->partial_block_buffer_length;
 		if (len < copy_len)
 			copy_len = len;
 
@@ -297,20 +320,28 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
 				buffer, copy_len);
 
 			ctx->partial_block_buffer_length += copy_len;
-			ctx->incoming_buffer = (const void *)((const char *)buffer + copy_len);
+			ctx->incoming_buffer = (const void *)
+					((const char *)buffer + copy_len);
 			ctx->incoming_buffer_length = len - copy_len;
 		}
 
-		/* The extra block should never contain more than 1 block here */
+		/*
+		 * The extra block should never contain more than 1 block
+		 * here
+		 */
 		assert(ctx->partial_block_buffer_length <= SHA1_BLOCK_SIZE);
 
-		/* If the extra block buffer contains exactly 1 block, it can be hashed. */
+		/*
+		 * If the extra block buffer contains exactly 1 block, it can
+		 * be hashed.
+		 */
 		if (ctx->partial_block_buffer_length >= SHA1_BLOCK_SIZE) {
 			ctx->partial_block_buffer_length = 0;
 
 			ctx->job.buffer = ctx->partial_block_buffer;
 			ctx->job.len = 1;
-			ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
+			ctx = (struct sha1_hash_ctx *)
+				sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
 		}
 	}
 
@@ -329,23 +360,24 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_flush(struct sha1_ctx_mgr *mgr)
 			return NULL;
 
 		/*
-		 * If flush returned a job, resubmit the job to finish processing.
+		 * If flush returned a job, resubmit the job to finish
+		 * processing.
 		 */
 		ctx = sha1_ctx_mgr_resubmit(mgr, ctx);
 
 		/*
-		 * If sha1_ctx_mgr_resubmit returned a job, it is ready to be returned.
-		 * Otherwise, all jobs currently being managed by the sha1_ctx_mgr
-		 * still need processing. Loop.
+		 * If sha1_ctx_mgr_resubmit returned a job, it is ready to be
+		 * returned. Otherwise, all jobs currently being managed by the
+		 * sha1_ctx_mgr still need processing. Loop.
 		 */
 		if (ctx)
 			return ctx;
 	}
 }
 
-static int sha1_mb_init(struct shash_desc *desc)
+static int sha1_mb_init(struct ahash_request *areq)
 {
-	struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+	struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
 
 	hash_ctx_init(sctx);
 	sctx->job.result_digest[0] = SHA1_H0;
@@ -363,7 +395,7 @@ static int sha1_mb_init(struct shash_desc *desc)
 static int sha1_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
 {
 	int	i;
-	struct	sha1_hash_ctx *sctx = shash_desc_ctx(&rctx->desc);
+	struct	sha1_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
 	__be32	*dst = (__be32 *) rctx->out;
 
 	for (i = 0; i < 5; ++i)
@@ -394,9 +426,11 @@ static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
 				flag |= HASH_LAST;
 
 		}
-		sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(&rctx->desc);
+		sha_ctx = (struct sha1_hash_ctx *)
+						ahash_request_ctx(&rctx->areq);
 		kernel_fpu_begin();
-		sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, flag);
+		sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx,
+						rctx->walk.data, nbytes, flag);
 		if (!sha_ctx) {
 			if (flush)
 				sha_ctx = sha1_ctx_mgr_flush(cstate->mgr);
@@ -485,11 +519,10 @@ static void sha1_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
 	mcryptd_arm_flusher(cstate, delay);
 }
 
-static int sha1_mb_update(struct shash_desc *desc, const u8 *data,
-			  unsigned int len)
+static int sha1_mb_update(struct ahash_request *areq)
 {
 	struct mcryptd_hash_request_ctx *rctx =
-			container_of(desc, struct mcryptd_hash_request_ctx, desc);
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
 	struct mcryptd_alg_cstate *cstate =
 				this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
 
@@ -505,7 +538,7 @@ static int sha1_mb_update(struct shash_desc *desc, const u8 *data,
 	}
 
 	/* need to init context */
-	req_ctx_init(rctx, desc);
+	req_ctx_init(rctx, areq);
 
 	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
 
@@ -518,10 +551,11 @@ static int sha1_mb_update(struct shash_desc *desc, const u8 *data,
 		rctx->flag |= HASH_DONE;
 
 	/* submit */
-	sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+	sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
 	sha1_mb_add_list(rctx, cstate);
 	kernel_fpu_begin();
-	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, HASH_UPDATE);
+	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+							nbytes, HASH_UPDATE);
 	kernel_fpu_end();
 
 	/* check if anything is returned */
@@ -544,11 +578,10 @@ done:
 	return ret;
 }
 
-static int sha1_mb_finup(struct shash_desc *desc, const u8 *data,
-			     unsigned int len, u8 *out)
+static int sha1_mb_finup(struct ahash_request *areq)
 {
 	struct mcryptd_hash_request_ctx *rctx =
-			container_of(desc, struct mcryptd_hash_request_ctx, desc);
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
 	struct mcryptd_alg_cstate *cstate =
 				this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
 
@@ -563,7 +596,7 @@ static int sha1_mb_finup(struct shash_desc *desc, const u8 *data,
 	}
 
 	/* need to init context */
-	req_ctx_init(rctx, desc);
+	req_ctx_init(rctx, areq);
 
 	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
 
@@ -576,15 +609,15 @@ static int sha1_mb_finup(struct shash_desc *desc, const u8 *data,
 		rctx->flag |= HASH_DONE;
 		flag = HASH_LAST;
 	}
-	rctx->out = out;
 
 	/* submit */
 	rctx->flag |= HASH_FINAL;
-	sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+	sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
 	sha1_mb_add_list(rctx, cstate);
 
 	kernel_fpu_begin();
-	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, flag);
+	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+								nbytes, flag);
 	kernel_fpu_end();
 
 	/* check if anything is returned */
@@ -605,10 +638,10 @@ done:
 	return ret;
 }
 
-static int sha1_mb_final(struct shash_desc *desc, u8 *out)
+static int sha1_mb_final(struct ahash_request *areq)
 {
 	struct mcryptd_hash_request_ctx *rctx =
-			container_of(desc, struct mcryptd_hash_request_ctx, desc);
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
 	struct mcryptd_alg_cstate *cstate =
 				this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
 
@@ -623,16 +656,16 @@ static int sha1_mb_final(struct shash_desc *desc, u8 *out)
 	}
 
 	/* need to init context */
-	req_ctx_init(rctx, desc);
+	req_ctx_init(rctx, areq);
 
-	rctx->out = out;
 	rctx->flag |= HASH_DONE | HASH_FINAL;
 
-	sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+	sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
 	/* flag HASH_FINAL and 0 data size */
 	sha1_mb_add_list(rctx, cstate);
 	kernel_fpu_begin();
-	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0, HASH_LAST);
+	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
+								HASH_LAST);
 	kernel_fpu_end();
 
 	/* check if anything is returned */
@@ -654,48 +687,98 @@ done:
 	return ret;
 }
 
-static int sha1_mb_export(struct shash_desc *desc, void *out)
+static int sha1_mb_export(struct ahash_request *areq, void *out)
 {
-	struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+	struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
 
 	memcpy(out, sctx, sizeof(*sctx));
 
 	return 0;
 }
 
-static int sha1_mb_import(struct shash_desc *desc, const void *in)
+static int sha1_mb_import(struct ahash_request *areq, const void *in)
 {
-	struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+	struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
 
 	memcpy(sctx, in, sizeof(*sctx));
 
 	return 0;
 }
 
+static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct mcryptd_ahash *mcryptd_tfm;
+	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mcryptd_hash_ctx *mctx;
 
-static struct shash_alg sha1_mb_shash_alg = {
-	.digestsize	=	SHA1_DIGEST_SIZE,
+	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb",
+						CRYPTO_ALG_INTERNAL,
+						CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(mcryptd_tfm))
+		return PTR_ERR(mcryptd_tfm);
+	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
+	mctx->alg_state = &sha1_mb_alg_state;
+	ctx->mcryptd_tfm = mcryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				crypto_ahash_reqsize(&mcryptd_tfm->base));
+
+	return 0;
+}
+
+static void sha1_mb_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static int sha1_mb_areq_init_tfm(struct crypto_tfm *tfm)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				sizeof(struct sha1_hash_ctx));
+
+	return 0;
+}
+
+static void sha1_mb_areq_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static struct ahash_alg sha1_mb_areq_alg = {
 	.init		=	sha1_mb_init,
 	.update		=	sha1_mb_update,
 	.final		=	sha1_mb_final,
 	.finup		=	sha1_mb_finup,
 	.export		=	sha1_mb_export,
 	.import		=	sha1_mb_import,
-	.descsize	=	sizeof(struct sha1_hash_ctx),
-	.statesize	=	sizeof(struct sha1_hash_ctx),
-	.base		=	{
-		.cra_name	 = "__sha1-mb",
-		.cra_driver_name = "__intel_sha1-mb",
-		.cra_priority	 = 100,
-		/*
-		 * use ASYNC flag as some buffers in multi-buffer
-		 * algo may not have completed before hashing thread sleep
-		 */
-		.cra_flags	 = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_ASYNC |
-				   CRYPTO_ALG_INTERNAL,
-		.cra_blocksize	 = SHA1_BLOCK_SIZE,
-		.cra_module	 = THIS_MODULE,
-		.cra_list	 = LIST_HEAD_INIT(sha1_mb_shash_alg.base.cra_list),
+	.halg		=	{
+		.digestsize	=	SHA1_DIGEST_SIZE,
+		.statesize	=	sizeof(struct sha1_hash_ctx),
+		.base		=	{
+			.cra_name	 = "__sha1-mb",
+			.cra_driver_name = "__intel_sha1-mb",
+			.cra_priority	 = 100,
+			/*
+			 * use ASYNC flag as some buffers in multi-buffer
+			 * algo may not have completed before hashing thread
+			 * sleep
+			 */
+			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_INTERNAL,
+			.cra_blocksize	= SHA1_BLOCK_SIZE,
+			.cra_module	= THIS_MODULE,
+			.cra_list	= LIST_HEAD_INIT
+					(sha1_mb_areq_alg.halg.base.cra_list),
+			.cra_init	= sha1_mb_areq_init_tfm,
+			.cra_exit	= sha1_mb_areq_exit_tfm,
+			.cra_ctxsize	= sizeof(struct sha1_hash_ctx),
+		}
 	}
 };
 
@@ -780,46 +863,20 @@ static int sha1_mb_async_import(struct ahash_request *req, const void *in)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-	struct crypto_shash *child = mcryptd_ahash_child(mcryptd_tfm);
+	struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
 	struct mcryptd_hash_request_ctx *rctx;
-	struct shash_desc *desc;
+	struct ahash_request *areq;
 
 	memcpy(mcryptd_req, req, sizeof(*req));
 	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
 	rctx = ahash_request_ctx(mcryptd_req);
-	desc = &rctx->desc;
-	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	return crypto_ahash_import(mcryptd_req, in);
-}
-
-static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm)
-{
-	struct mcryptd_ahash *mcryptd_tfm;
-	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct mcryptd_hash_ctx *mctx;
+	areq = &rctx->areq;
 
-	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb",
-					  CRYPTO_ALG_INTERNAL,
-					  CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(mcryptd_tfm))
-		return PTR_ERR(mcryptd_tfm);
-	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
-	mctx->alg_state = &sha1_mb_alg_state;
-	ctx->mcryptd_tfm = mcryptd_tfm;
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct ahash_request) +
-				 crypto_ahash_reqsize(&mcryptd_tfm->base));
+	ahash_request_set_tfm(areq, child);
+	ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
+					rctx->complete, req);
 
-	return 0;
-}
-
-static void sha1_mb_async_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	mcryptd_free_ahash(ctx->mcryptd_tfm);
+	return crypto_ahash_import(mcryptd_req, in);
 }
 
 static struct ahash_alg sha1_mb_async_alg = {
@@ -866,7 +923,8 @@ static unsigned long sha1_mb_flusher(struct mcryptd_alg_cstate *cstate)
 		if (time_before(cur_time, rctx->tag.expire))
 			break;
 		kernel_fpu_begin();
-		sha_ctx = (struct sha1_hash_ctx *) sha1_ctx_mgr_flush(cstate->mgr);
+		sha_ctx = (struct sha1_hash_ctx *)
+					sha1_ctx_mgr_flush(cstate->mgr);
 		kernel_fpu_end();
 		if (!sha_ctx) {
 			pr_err("sha1_mb error: nothing got flushed for non-empty list\n");
@@ -927,7 +985,7 @@ static int __init sha1_mb_mod_init(void)
 	}
 	sha1_mb_alg_state.flusher = &sha1_mb_flusher;
 
-	err = crypto_register_shash(&sha1_mb_shash_alg);
+	err = crypto_register_ahash(&sha1_mb_areq_alg);
 	if (err)
 		goto err2;
 	err = crypto_register_ahash(&sha1_mb_async_alg);
@@ -937,7 +995,7 @@ static int __init sha1_mb_mod_init(void)
 
 	return 0;
 err1:
-	crypto_unregister_shash(&sha1_mb_shash_alg);
+	crypto_unregister_ahash(&sha1_mb_areq_alg);
 err2:
 	for_each_possible_cpu(cpu) {
 		cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
@@ -953,7 +1011,7 @@ static void __exit sha1_mb_mod_fini(void)
 	struct mcryptd_alg_cstate *cpu_state;
 
 	crypto_unregister_ahash(&sha1_mb_async_alg);
-	crypto_unregister_shash(&sha1_mb_shash_alg);
+	crypto_unregister_ahash(&sha1_mb_areq_alg);
 	for_each_possible_cpu(cpu) {
 		cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
 		kfree(cpu_state->mgr);
diff --git a/arch/x86/crypto/sha-mb/sha_mb_ctx.h b/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
index e36069d0c1bd..98a35bcc6f4a 100644
--- a/arch/x86/crypto/sha-mb/sha_mb_ctx.h
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
@@ -54,7 +54,7 @@
 #ifndef _SHA_MB_CTX_INTERNAL_H
 #define _SHA_MB_CTX_INTERNAL_H
 
-#include "sha_mb_mgr.h"
+#include "sha1_mb_mgr.h"
 
 #define HASH_UPDATE          0x00
 #define HASH_FIRST           0x01
diff --git a/arch/x86/crypto/sha-mb/sha_mb_mgr.h b/arch/x86/crypto/sha1-mb/sha1_mb_mgr.h
index 08ad1a9acfd7..08ad1a9acfd7 100644
--- a/arch/x86/crypto/sha-mb/sha_mb_mgr.h
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr.h
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S
index 86688c6e7a25..86688c6e7a25 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
index 96df6a39d7e2..96df6a39d7e2 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c
index 822acb5b464c..d2add0d35f43 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c
@@ -51,7 +51,7 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include "sha_mb_mgr.h"
+#include "sha1_mb_mgr.h"
 
 void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state)
 {
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S
index 63a0d9c8e31f..63a0d9c8e31f 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S
diff --git a/arch/x86/crypto/sha-mb/sha1_x8_avx2.S b/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S
index c9dae1cd2919..c9dae1cd2919 100644
--- a/arch/x86/crypto/sha-mb/sha1_x8_avx2.S
+++ b/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 1024e378a358..fc61739150e7 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -374,3 +374,9 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
 MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-ssse3");
+MODULE_ALIAS_CRYPTO("sha1-avx");
+MODULE_ALIAS_CRYPTO("sha1-avx2");
+#ifdef CONFIG_AS_SHA1_NI
+MODULE_ALIAS_CRYPTO("sha1-ni");
+#endif
diff --git a/arch/x86/crypto/sha256-mb/Makefile b/arch/x86/crypto/sha256-mb/Makefile
new file mode 100644
index 000000000000..41089e7c400c
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/Makefile
@@ -0,0 +1,11 @@
+#
+# Arch-specific CryptoAPI modules.
+#
+
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+                                $(comma)4)$(comma)%ymm2,yes,no)
+ifeq ($(avx2_supported),yes)
+	obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb.o
+	sha256-mb-y := sha256_mb.o sha256_mb_mgr_flush_avx2.o \
+	     sha256_mb_mgr_init_avx2.o sha256_mb_mgr_submit_avx2.o sha256_x8_avx2.o
+endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
new file mode 100644
index 000000000000..89fa85e8b10c
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -0,0 +1,1030 @@
+/*
+ * Multi buffer SHA256 algorithm Glue Code
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+#include <crypto/mcryptd.h>
+#include <crypto/crypto_wq.h>
+#include <asm/byteorder.h>
+#include <linux/hardirq.h>
+#include <asm/fpu/api.h>
+#include "sha256_mb_ctx.h"
+
+#define FLUSH_INTERVAL 1000 /* in usec */
+
+static struct mcryptd_alg_state sha256_mb_alg_state;
+
+struct sha256_mb_ctx {
+	struct mcryptd_ahash *mcryptd_tfm;
+};
+
+static inline struct mcryptd_hash_request_ctx
+		*cast_hash_to_mcryptd_ctx(struct sha256_hash_ctx *hash_ctx)
+{
+	struct ahash_request *areq;
+
+	areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
+	return container_of(areq, struct mcryptd_hash_request_ctx, areq);
+}
+
+static inline struct ahash_request
+		*cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
+{
+	return container_of((void *) ctx, struct ahash_request, __ctx);
+}
+
+static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
+				struct ahash_request *areq)
+{
+	rctx->flag = HASH_UPDATE;
+}
+
+static asmlinkage void (*sha256_job_mgr_init)(struct sha256_mb_mgr *state);
+static asmlinkage struct job_sha256* (*sha256_job_mgr_submit)
+			(struct sha256_mb_mgr *state, struct job_sha256 *job);
+static asmlinkage struct job_sha256* (*sha256_job_mgr_flush)
+			(struct sha256_mb_mgr *state);
+static asmlinkage struct job_sha256* (*sha256_job_mgr_get_comp_job)
+			(struct sha256_mb_mgr *state);
+
+inline void sha256_init_digest(uint32_t *digest)
+{
+	static const uint32_t initial_digest[SHA256_DIGEST_LENGTH] = {
+				SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+				SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7};
+	memcpy(digest, initial_digest, sizeof(initial_digest));
+}
+
+inline uint32_t sha256_pad(uint8_t padblock[SHA256_BLOCK_SIZE * 2],
+			 uint32_t total_len)
+{
+	uint32_t i = total_len & (SHA256_BLOCK_SIZE - 1);
+
+	memset(&padblock[i], 0, SHA256_BLOCK_SIZE);
+	padblock[i] = 0x80;
+
+	i += ((SHA256_BLOCK_SIZE - 1) &
+	      (0 - (total_len + SHA256_PADLENGTHFIELD_SIZE + 1)))
+	     + 1 + SHA256_PADLENGTHFIELD_SIZE;
+
+#if SHA256_PADLENGTHFIELD_SIZE == 16
+	*((uint64_t *) &padblock[i - 16]) = 0;
+#endif
+
+	*((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
+
+	/* Number of extra blocks to hash */
+	return i >> SHA256_LOG2_BLOCK_SIZE;
+}
+
+static struct sha256_hash_ctx
+		*sha256_ctx_mgr_resubmit(struct sha256_ctx_mgr *mgr,
+					struct sha256_hash_ctx *ctx)
+{
+	while (ctx) {
+		if (ctx->status & HASH_CTX_STS_COMPLETE) {
+			/* Clear PROCESSING bit */
+			ctx->status = HASH_CTX_STS_COMPLETE;
+			return ctx;
+		}
+
+		/*
+		 * If the extra blocks are empty, begin hashing what remains
+		 * in the user's buffer.
+		 */
+		if (ctx->partial_block_buffer_length == 0 &&
+		    ctx->incoming_buffer_length) {
+
+			const void *buffer = ctx->incoming_buffer;
+			uint32_t len = ctx->incoming_buffer_length;
+			uint32_t copy_len;
+
+			/*
+			 * Only entire blocks can be hashed.
+			 * Copy remainder to extra blocks buffer.
+			 */
+			copy_len = len & (SHA256_BLOCK_SIZE-1);
+
+			if (copy_len) {
+				len -= copy_len;
+				memcpy(ctx->partial_block_buffer,
+				       ((const char *) buffer + len),
+				       copy_len);
+				ctx->partial_block_buffer_length = copy_len;
+			}
+
+			ctx->incoming_buffer_length = 0;
+
+			/* len should be a multiple of the block size now */
+			assert((len % SHA256_BLOCK_SIZE) == 0);
+
+			/* Set len to the number of blocks to be hashed */
+			len >>= SHA256_LOG2_BLOCK_SIZE;
+
+			if (len) {
+
+				ctx->job.buffer = (uint8_t *) buffer;
+				ctx->job.len = len;
+				ctx = (struct sha256_hash_ctx *)
+				sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
+				continue;
+			}
+		}
+
+		/*
+		 * If the extra blocks are not empty, then we are
+		 * either on the last block(s) or we need more
+		 * user input before continuing.
+		 */
+		if (ctx->status & HASH_CTX_STS_LAST) {
+
+			uint8_t *buf = ctx->partial_block_buffer;
+			uint32_t n_extra_blocks =
+				sha256_pad(buf, ctx->total_length);
+
+			ctx->status = (HASH_CTX_STS_PROCESSING |
+				       HASH_CTX_STS_COMPLETE);
+			ctx->job.buffer = buf;
+			ctx->job.len = (uint32_t) n_extra_blocks;
+			ctx = (struct sha256_hash_ctx *)
+				sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
+			continue;
+		}
+
+		ctx->status = HASH_CTX_STS_IDLE;
+		return ctx;
+	}
+
+	return NULL;
+}
+
+static struct sha256_hash_ctx
+		*sha256_ctx_mgr_get_comp_ctx(struct sha256_ctx_mgr *mgr)
+{
+	/*
+	 * If get_comp_job returns NULL, there are no jobs complete.
+	 * If get_comp_job returns a job, verify that it is safe to return to
+	 * the user. If it is not ready, resubmit the job to finish processing.
+	 * If sha256_ctx_mgr_resubmit returned a job, it is ready to be
+	 * returned. Otherwise, all jobs currently being managed by the
+	 * hash_ctx_mgr still need processing.
+	 */
+	struct sha256_hash_ctx *ctx;
+
+	ctx = (struct sha256_hash_ctx *) sha256_job_mgr_get_comp_job(&mgr->mgr);
+	return sha256_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static void sha256_ctx_mgr_init(struct sha256_ctx_mgr *mgr)
+{
+	sha256_job_mgr_init(&mgr->mgr);
+}
+
+static struct sha256_hash_ctx *sha256_ctx_mgr_submit(struct sha256_ctx_mgr *mgr,
+					  struct sha256_hash_ctx *ctx,
+					  const void *buffer,
+					  uint32_t len,
+					  int flags)
+{
+	if (flags & (~HASH_ENTIRE)) {
+		/* User should not pass anything other than FIRST, UPDATE
+		 * or LAST
+		 */
+		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
+		return ctx;
+	}
+
+	if (ctx->status & HASH_CTX_STS_PROCESSING) {
+		/* Cannot submit to a currently processing job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
+		return ctx;
+	}
+
+	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+		/* Cannot update a finished job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
+		return ctx;
+	}
+
+	if (flags & HASH_FIRST) {
+		/* Init digest */
+		sha256_init_digest(ctx->job.result_digest);
+
+		/* Reset byte counter */
+		ctx->total_length = 0;
+
+		/* Clear extra blocks */
+		ctx->partial_block_buffer_length = 0;
+	}
+
+	/* If we made it here, there was no error during this call to submit */
+	ctx->error = HASH_CTX_ERROR_NONE;
+
+	/* Store buffer ptr info from user */
+	ctx->incoming_buffer = buffer;
+	ctx->incoming_buffer_length = len;
+
+	/*
+	 * Store the user's request flags and mark this ctx as currently
+	 * being processed.
+	 */
+	ctx->status = (flags & HASH_LAST) ?
+			(HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
+			HASH_CTX_STS_PROCESSING;
+
+	/* Advance byte counter */
+	ctx->total_length += len;
+
+	/*
+	 * If there is anything currently buffered in the extra blocks,
+	 * append to it until it contains a whole block.
+	 * Or if the user's buffer contains less than a whole block,
+	 * append as much as possible to the extra block.
+	 */
+	if (ctx->partial_block_buffer_length || len < SHA256_BLOCK_SIZE) {
+		/*
+		 * Compute how many bytes to copy from user buffer into
+		 * extra block
+		 */
+		uint32_t copy_len = SHA256_BLOCK_SIZE -
+					ctx->partial_block_buffer_length;
+		if (len < copy_len)
+			copy_len = len;
+
+		if (copy_len) {
+			/* Copy and update relevant pointers and counters */
+			memcpy(
+		&ctx->partial_block_buffer[ctx->partial_block_buffer_length],
+				buffer, copy_len);
+
+			ctx->partial_block_buffer_length += copy_len;
+			ctx->incoming_buffer = (const void *)
+					((const char *)buffer + copy_len);
+			ctx->incoming_buffer_length = len - copy_len;
+		}
+
+		/* The extra block should never contain more than 1 block */
+		assert(ctx->partial_block_buffer_length <= SHA256_BLOCK_SIZE);
+
+		/*
+		 * If the extra block buffer contains exactly 1 block,
+		 * it can be hashed.
+		 */
+		if (ctx->partial_block_buffer_length >= SHA256_BLOCK_SIZE) {
+			ctx->partial_block_buffer_length = 0;
+
+			ctx->job.buffer = ctx->partial_block_buffer;
+			ctx->job.len = 1;
+			ctx = (struct sha256_hash_ctx *)
+				sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
+		}
+	}
+
+	return sha256_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static struct sha256_hash_ctx *sha256_ctx_mgr_flush(struct sha256_ctx_mgr *mgr)
+{
+	struct sha256_hash_ctx *ctx;
+
+	while (1) {
+		ctx = (struct sha256_hash_ctx *)
+					sha256_job_mgr_flush(&mgr->mgr);
+
+		/* If flush returned 0, there are no more jobs in flight. */
+		if (!ctx)
+			return NULL;
+
+		/*
+		 * If flush returned a job, resubmit the job to finish
+		 * processing.
+		 */
+		ctx = sha256_ctx_mgr_resubmit(mgr, ctx);
+
+		/*
+		 * If sha256_ctx_mgr_resubmit returned a job, it is ready to
+		 * be returned. Otherwise, all jobs currently being managed by
+		 * the sha256_ctx_mgr still need processing. Loop.
+		 */
+		if (ctx)
+			return ctx;
+	}
+}
+
+static int sha256_mb_init(struct ahash_request *areq)
+{
+	struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	hash_ctx_init(sctx);
+	sctx->job.result_digest[0] = SHA256_H0;
+	sctx->job.result_digest[1] = SHA256_H1;
+	sctx->job.result_digest[2] = SHA256_H2;
+	sctx->job.result_digest[3] = SHA256_H3;
+	sctx->job.result_digest[4] = SHA256_H4;
+	sctx->job.result_digest[5] = SHA256_H5;
+	sctx->job.result_digest[6] = SHA256_H6;
+	sctx->job.result_digest[7] = SHA256_H7;
+	sctx->total_length = 0;
+	sctx->partial_block_buffer_length = 0;
+	sctx->status = HASH_CTX_STS_IDLE;
+
+	return 0;
+}
+
+static int sha256_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
+{
+	int	i;
+	struct	sha256_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
+	__be32	*dst = (__be32 *) rctx->out;
+
+	for (i = 0; i < 8; ++i)
+		dst[i] = cpu_to_be32(sctx->job.result_digest[i]);
+
+	return 0;
+}
+
+static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
+			struct mcryptd_alg_cstate *cstate, bool flush)
+{
+	int	flag = HASH_UPDATE;
+	int	nbytes, err = 0;
+	struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
+	struct sha256_hash_ctx *sha_ctx;
+
+	/* more work ? */
+	while (!(rctx->flag & HASH_DONE)) {
+		nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
+		if (nbytes < 0) {
+			err = nbytes;
+			goto out;
+		}
+		/* check if the walk is done */
+		if (crypto_ahash_walk_last(&rctx->walk)) {
+			rctx->flag |= HASH_DONE;
+			if (rctx->flag & HASH_FINAL)
+				flag |= HASH_LAST;
+
+		}
+		sha_ctx = (struct sha256_hash_ctx *)
+						ahash_request_ctx(&rctx->areq);
+		kernel_fpu_begin();
+		sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx,
+						rctx->walk.data, nbytes, flag);
+		if (!sha_ctx) {
+			if (flush)
+				sha_ctx = sha256_ctx_mgr_flush(cstate->mgr);
+		}
+		kernel_fpu_end();
+		if (sha_ctx)
+			rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		else {
+			rctx = NULL;
+			goto out;
+		}
+	}
+
+	/* copy the results */
+	if (rctx->flag & HASH_FINAL)
+		sha256_mb_set_results(rctx);
+
+out:
+	*ret_rctx = rctx;
+	return err;
+}
+
+static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
+			    struct mcryptd_alg_cstate *cstate,
+			    int err)
+{
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha256_hash_ctx *sha_ctx;
+	struct mcryptd_hash_request_ctx *req_ctx;
+	int ret;
+
+	/* remove from work list */
+	spin_lock(&cstate->work_lock);
+	list_del(&rctx->waiter);
+	spin_unlock(&cstate->work_lock);
+
+	if (irqs_disabled())
+		rctx->complete(&req->base, err);
+	else {
+		local_bh_disable();
+		rctx->complete(&req->base, err);
+		local_bh_enable();
+	}
+
+	/* check to see if there are other jobs that are done */
+	sha_ctx = sha256_ctx_mgr_get_comp_ctx(cstate->mgr);
+	while (sha_ctx) {
+		req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		ret = sha_finish_walk(&req_ctx, cstate, false);
+		if (req_ctx) {
+			spin_lock(&cstate->work_lock);
+			list_del(&req_ctx->waiter);
+			spin_unlock(&cstate->work_lock);
+
+			req = cast_mcryptd_ctx_to_req(req_ctx);
+			if (irqs_disabled())
+				rctx->complete(&req->base, ret);
+			else {
+				local_bh_disable();
+				rctx->complete(&req->base, ret);
+				local_bh_enable();
+			}
+		}
+		sha_ctx = sha256_ctx_mgr_get_comp_ctx(cstate->mgr);
+	}
+
+	return 0;
+}
+
+static void sha256_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
+			     struct mcryptd_alg_cstate *cstate)
+{
+	unsigned long next_flush;
+	unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
+
+	/* initialize tag */
+	rctx->tag.arrival = jiffies;    /* tag the arrival time */
+	rctx->tag.seq_num = cstate->next_seq_num++;
+	next_flush = rctx->tag.arrival + delay;
+	rctx->tag.expire = next_flush;
+
+	spin_lock(&cstate->work_lock);
+	list_add_tail(&rctx->waiter, &cstate->work_list);
+	spin_unlock(&cstate->work_lock);
+
+	mcryptd_arm_flusher(cstate, delay);
+}
+
+static int sha256_mb_update(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha256_hash_ctx *sha_ctx;
+	int ret = 0, nbytes;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk))
+		rctx->flag |= HASH_DONE;
+
+	/* submit */
+	sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
+	sha256_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+							nbytes, HASH_UPDATE);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha256_mb_finup(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha256_hash_ctx *sha_ctx;
+	int ret = 0, flag = HASH_UPDATE, nbytes;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk)) {
+		rctx->flag |= HASH_DONE;
+		flag = HASH_LAST;
+	}
+
+	/* submit */
+	rctx->flag |= HASH_FINAL;
+	sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
+	sha256_mb_add_list(rctx, cstate);
+
+	kernel_fpu_begin();
+	sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+								nbytes, flag);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha256_mb_final(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+			areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
+
+	struct sha256_hash_ctx *sha_ctx;
+	int ret = 0;
+	u8 data;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	rctx->flag |= HASH_DONE | HASH_FINAL;
+
+	sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
+	/* flag HASH_FINAL and 0 data size */
+	sha256_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
+								HASH_LAST);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha256_mb_export(struct ahash_request *areq, void *out)
+{
+	struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha256_mb_import(struct ahash_request *areq, const void *in)
+{
+	struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha256_mb_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct mcryptd_ahash *mcryptd_tfm;
+	struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mcryptd_hash_ctx *mctx;
+
+	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha256-mb",
+						CRYPTO_ALG_INTERNAL,
+						CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(mcryptd_tfm))
+		return PTR_ERR(mcryptd_tfm);
+	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
+	mctx->alg_state = &sha256_mb_alg_state;
+	ctx->mcryptd_tfm = mcryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				crypto_ahash_reqsize(&mcryptd_tfm->base));
+
+	return 0;
+}
+
+static void sha256_mb_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static int sha256_mb_areq_init_tfm(struct crypto_tfm *tfm)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				sizeof(struct sha256_hash_ctx));
+
+	return 0;
+}
+
+static void sha256_mb_areq_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static struct ahash_alg sha256_mb_areq_alg = {
+	.init		=	sha256_mb_init,
+	.update		=	sha256_mb_update,
+	.final		=	sha256_mb_final,
+	.finup		=	sha256_mb_finup,
+	.export		=	sha256_mb_export,
+	.import		=	sha256_mb_import,
+	.halg		=	{
+	.digestsize	=	SHA256_DIGEST_SIZE,
+	.statesize	=	sizeof(struct sha256_hash_ctx),
+		.base		=	{
+			.cra_name	 = "__sha256-mb",
+			.cra_driver_name = "__intel_sha256-mb",
+			.cra_priority	 = 100,
+			/*
+			 * use ASYNC flag as some buffers in multi-buffer
+			 * algo may not have completed before hashing thread
+			 * sleep
+			 */
+			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_INTERNAL,
+			.cra_blocksize	= SHA256_BLOCK_SIZE,
+			.cra_module	= THIS_MODULE,
+			.cra_list	= LIST_HEAD_INIT
+					(sha256_mb_areq_alg.halg.base.cra_list),
+			.cra_init	= sha256_mb_areq_init_tfm,
+			.cra_exit	= sha256_mb_areq_exit_tfm,
+			.cra_ctxsize	= sizeof(struct sha256_hash_ctx),
+		}
+	}
+};
+
+static int sha256_mb_async_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_init(mcryptd_req);
+}
+
+static int sha256_mb_async_update(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_update(mcryptd_req);
+}
+
+static int sha256_mb_async_finup(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_finup(mcryptd_req);
+}
+
+static int sha256_mb_async_final(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_final(mcryptd_req);
+}
+
+static int sha256_mb_async_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_digest(mcryptd_req);
+}
+
+static int sha256_mb_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_export(mcryptd_req, out);
+}
+
+static int sha256_mb_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+	struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
+	struct mcryptd_hash_request_ctx *rctx;
+	struct ahash_request *areq;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	rctx = ahash_request_ctx(mcryptd_req);
+	areq = &rctx->areq;
+
+	ahash_request_set_tfm(areq, child);
+	ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
+					rctx->complete, req);
+
+	return crypto_ahash_import(mcryptd_req, in);
+}
+
+static struct ahash_alg sha256_mb_async_alg = {
+	.init           = sha256_mb_async_init,
+	.update         = sha256_mb_async_update,
+	.final          = sha256_mb_async_final,
+	.finup          = sha256_mb_async_finup,
+	.export         = sha256_mb_async_export,
+	.import         = sha256_mb_async_import,
+	.digest         = sha256_mb_async_digest,
+	.halg = {
+		.digestsize     = SHA256_DIGEST_SIZE,
+		.statesize      = sizeof(struct sha256_hash_ctx),
+		.base = {
+			.cra_name               = "sha256",
+			.cra_driver_name        = "sha256_mb",
+			.cra_priority           = 200,
+			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
+							CRYPTO_ALG_ASYNC,
+			.cra_blocksize          = SHA256_BLOCK_SIZE,
+			.cra_type               = &crypto_ahash_type,
+			.cra_module             = THIS_MODULE,
+			.cra_list               = LIST_HEAD_INIT
+				(sha256_mb_async_alg.halg.base.cra_list),
+			.cra_init               = sha256_mb_async_init_tfm,
+			.cra_exit               = sha256_mb_async_exit_tfm,
+			.cra_ctxsize		= sizeof(struct sha256_mb_ctx),
+			.cra_alignmask		= 0,
+		},
+	},
+};
+
+static unsigned long sha256_mb_flusher(struct mcryptd_alg_cstate *cstate)
+{
+	struct mcryptd_hash_request_ctx *rctx;
+	unsigned long cur_time;
+	unsigned long next_flush = 0;
+	struct sha256_hash_ctx *sha_ctx;
+
+
+	cur_time = jiffies;
+
+	while (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		if (time_before(cur_time, rctx->tag.expire))
+			break;
+		kernel_fpu_begin();
+		sha_ctx = (struct sha256_hash_ctx *)
+					sha256_ctx_mgr_flush(cstate->mgr);
+		kernel_fpu_end();
+		if (!sha_ctx) {
+			pr_err("sha256_mb error: nothing got"
+					" flushed for non-empty list\n");
+			break;
+		}
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		sha_finish_walk(&rctx, cstate, true);
+		sha_complete_job(rctx, cstate, 0);
+	}
+
+	if (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		/* get the hash context and then flush time */
+		next_flush = rctx->tag.expire;
+		mcryptd_arm_flusher(cstate, get_delay(next_flush));
+	}
+	return next_flush;
+}
+
+static int __init sha256_mb_mod_init(void)
+{
+
+	int cpu;
+	int err;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	/* check for dependent cpu features */
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_BMI2))
+		return -ENODEV;
+
+	/* initialize multibuffer structures */
+	sha256_mb_alg_state.alg_cstate = alloc_percpu
+						(struct mcryptd_alg_cstate);
+
+	sha256_job_mgr_init = sha256_mb_mgr_init_avx2;
+	sha256_job_mgr_submit = sha256_mb_mgr_submit_avx2;
+	sha256_job_mgr_flush = sha256_mb_mgr_flush_avx2;
+	sha256_job_mgr_get_comp_job = sha256_mb_mgr_get_comp_job_avx2;
+
+	if (!sha256_mb_alg_state.alg_cstate)
+		return -ENOMEM;
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
+		cpu_state->next_flush = 0;
+		cpu_state->next_seq_num = 0;
+		cpu_state->flusher_engaged = false;
+		INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
+		cpu_state->cpu = cpu;
+		cpu_state->alg_state = &sha256_mb_alg_state;
+		cpu_state->mgr = kzalloc(sizeof(struct sha256_ctx_mgr),
+					GFP_KERNEL);
+		if (!cpu_state->mgr)
+			goto err2;
+		sha256_ctx_mgr_init(cpu_state->mgr);
+		INIT_LIST_HEAD(&cpu_state->work_list);
+		spin_lock_init(&cpu_state->work_lock);
+	}
+	sha256_mb_alg_state.flusher = &sha256_mb_flusher;
+
+	err = crypto_register_ahash(&sha256_mb_areq_alg);
+	if (err)
+		goto err2;
+	err = crypto_register_ahash(&sha256_mb_async_alg);
+	if (err)
+		goto err1;
+
+
+	return 0;
+err1:
+	crypto_unregister_ahash(&sha256_mb_areq_alg);
+err2:
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha256_mb_alg_state.alg_cstate);
+	return -ENODEV;
+}
+
+static void __exit sha256_mb_mod_fini(void)
+{
+	int cpu;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	crypto_unregister_ahash(&sha256_mb_async_alg);
+	crypto_unregister_ahash(&sha256_mb_areq_alg);
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha256_mb_alg_state.alg_cstate);
+}
+
+module_init(sha256_mb_mod_init);
+module_exit(sha256_mb_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, multi buffer accelerated");
+
+MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h b/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
new file mode 100644
index 000000000000..edd252b73206
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
@@ -0,0 +1,136 @@
+/*
+ * Header file for multi buffer SHA256 context
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _SHA_MB_CTX_INTERNAL_H
+#define _SHA_MB_CTX_INTERNAL_H
+
+#include "sha256_mb_mgr.h"
+
+#define HASH_UPDATE          0x00
+#define HASH_FIRST           0x01
+#define HASH_LAST            0x02
+#define HASH_ENTIRE          0x03
+#define HASH_DONE	     0x04
+#define HASH_FINAL	     0x08
+
+#define HASH_CTX_STS_IDLE       0x00
+#define HASH_CTX_STS_PROCESSING 0x01
+#define HASH_CTX_STS_LAST       0x02
+#define HASH_CTX_STS_COMPLETE   0x04
+
+enum hash_ctx_error {
+	HASH_CTX_ERROR_NONE               =  0,
+	HASH_CTX_ERROR_INVALID_FLAGS      = -1,
+	HASH_CTX_ERROR_ALREADY_PROCESSING = -2,
+	HASH_CTX_ERROR_ALREADY_COMPLETED  = -3,
+
+#ifdef HASH_CTX_DEBUG
+	HASH_CTX_ERROR_DEBUG_DIGEST_MISMATCH = -4,
+#endif
+};
+
+
+#define hash_ctx_user_data(ctx)  ((ctx)->user_data)
+#define hash_ctx_digest(ctx)     ((ctx)->job.result_digest)
+#define hash_ctx_processing(ctx) ((ctx)->status & HASH_CTX_STS_PROCESSING)
+#define hash_ctx_complete(ctx)   ((ctx)->status == HASH_CTX_STS_COMPLETE)
+#define hash_ctx_status(ctx)     ((ctx)->status)
+#define hash_ctx_error(ctx)      ((ctx)->error)
+#define hash_ctx_init(ctx) \
+	do { \
+		(ctx)->error = HASH_CTX_ERROR_NONE; \
+		(ctx)->status = HASH_CTX_STS_COMPLETE; \
+	} while (0)
+
+
+/* Hash Constants and Typedefs */
+#define SHA256_DIGEST_LENGTH        8
+#define SHA256_LOG2_BLOCK_SIZE        6
+
+#define SHA256_PADLENGTHFIELD_SIZE    8
+
+#ifdef SHA_MB_DEBUG
+#define assert(expr) \
+do { \
+	if (unlikely(!(expr))) { \
+		printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \
+		#expr, __FILE__, __func__, __LINE__); \
+	} \
+} while (0)
+#else
+#define assert(expr) do {} while (0)
+#endif
+
+struct sha256_ctx_mgr {
+	struct sha256_mb_mgr mgr;
+};
+
+/* typedef struct sha256_ctx_mgr sha256_ctx_mgr; */
+
+struct sha256_hash_ctx {
+	/* Must be at struct offset 0 */
+	struct job_sha256       job;
+	/* status flag */
+	int status;
+	/* error flag */
+	int error;
+
+	uint32_t	total_length;
+	const void	*incoming_buffer;
+	uint32_t	incoming_buffer_length;
+	uint8_t		partial_block_buffer[SHA256_BLOCK_SIZE * 2];
+	uint32_t	partial_block_buffer_length;
+	void		*user_data;
+};
+
+#endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h b/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h
new file mode 100644
index 000000000000..b01ae408c56d
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h
@@ -0,0 +1,108 @@
+/*
+ * Header file for multi buffer SHA256 algorithm manager
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef __SHA_MB_MGR_H
+#define __SHA_MB_MGR_H
+
+#include <linux/types.h>
+
+#define NUM_SHA256_DIGEST_WORDS 8
+
+enum job_sts {	STS_UNKNOWN = 0,
+		STS_BEING_PROCESSED = 1,
+		STS_COMPLETED = 2,
+		STS_INTERNAL_ERROR = 3,
+		STS_ERROR = 4
+};
+
+struct job_sha256 {
+	u8	*buffer;
+	u32	len;
+	u32	result_digest[NUM_SHA256_DIGEST_WORDS] __aligned(32);
+	enum	job_sts status;
+	void	*user_data;
+};
+
+/* SHA256 out-of-order scheduler */
+
+/* typedef uint32_t sha8_digest_array[8][8]; */
+
+struct sha256_args_x8 {
+	uint32_t	digest[8][8];
+	uint8_t		*data_ptr[8];
+};
+
+struct sha256_lane_data {
+	struct job_sha256 *job_in_lane;
+};
+
+struct sha256_mb_mgr {
+	struct sha256_args_x8 args;
+
+	uint32_t lens[8];
+
+	/* each byte is index (0...7) of unused lanes */
+	uint64_t unused_lanes;
+	/* byte 4 is set to FF as a flag */
+	struct sha256_lane_data ldata[8];
+};
+
+
+#define SHA256_MB_MGR_NUM_LANES_AVX2 8
+
+void sha256_mb_mgr_init_avx2(struct sha256_mb_mgr *state);
+struct job_sha256 *sha256_mb_mgr_submit_avx2(struct sha256_mb_mgr *state,
+					 struct job_sha256 *job);
+struct job_sha256 *sha256_mb_mgr_flush_avx2(struct sha256_mb_mgr *state);
+struct job_sha256 *sha256_mb_mgr_get_comp_job_avx2(struct sha256_mb_mgr *state);
+
+#endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S
new file mode 100644
index 000000000000..5c377bac21d0
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S
@@ -0,0 +1,304 @@
+/*
+ * Header file for multi buffer SHA256 algorithm data structure
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+# Macros for defining data structures
+
+# Usage example
+
+#START_FIELDS	# JOB_AES
+###	name		size	align
+#FIELD	_plaintext,	8,	8	# pointer to plaintext
+#FIELD	_ciphertext,	8,	8	# pointer to ciphertext
+#FIELD	_IV,		16,	8	# IV
+#FIELD	_keys,		8,	8	# pointer to keys
+#FIELD	_len,		4,	4	# length in bytes
+#FIELD	_status,	4,	4	# status enumeration
+#FIELD	_user_data,	8,	8	# pointer to user data
+#UNION  _union,         size1,  align1, \
+#	                size2,  align2, \
+#	                size3,  align3, \
+#	                ...
+#END_FIELDS
+#%assign _JOB_AES_size	_FIELD_OFFSET
+#%assign _JOB_AES_align	_STRUCT_ALIGN
+
+#########################################################################
+
+# Alternate "struc-like" syntax:
+#	STRUCT job_aes2
+#	RES_Q	.plaintext,	1
+#	RES_Q	.ciphertext, 	1
+#	RES_DQ	.IV,		1
+#	RES_B	.nested,	_JOB_AES_SIZE, _JOB_AES_ALIGN
+#	RES_U	.union,		size1, align1, \
+#				size2, align2, \
+#				...
+#	ENDSTRUCT
+#	# Following only needed if nesting
+#	%assign job_aes2_size	_FIELD_OFFSET
+#	%assign job_aes2_align	_STRUCT_ALIGN
+#
+# RES_* macros take a name, a count and an optional alignment.
+# The count in in terms of the base size of the macro, and the
+# default alignment is the base size.
+# The macros are:
+# Macro    Base size
+# RES_B	    1
+# RES_W	    2
+# RES_D     4
+# RES_Q     8
+# RES_DQ   16
+# RES_Y    32
+# RES_Z    64
+#
+# RES_U defines a union. It's arguments are a name and two or more
+# pairs of "size, alignment"
+#
+# The two assigns are only needed if this structure is being nested
+# within another. Even if the assigns are not done, one can still use
+# STRUCT_NAME_size as the size of the structure.
+#
+# Note that for nesting, you still need to assign to STRUCT_NAME_size.
+#
+# The differences between this and using "struc" directly are that each
+# type is implicitly aligned to its natural length (although this can be
+# over-ridden with an explicit third parameter), and that the structure
+# is padded at the end to its overall alignment.
+#
+
+#########################################################################
+
+#ifndef _DATASTRUCT_ASM_
+#define _DATASTRUCT_ASM_
+
+#define SZ8			8*SHA256_DIGEST_WORD_SIZE
+#define ROUNDS			64*SZ8
+#define PTR_SZ                  8
+#define SHA256_DIGEST_WORD_SIZE 4
+#define MAX_SHA256_LANES        8
+#define SHA256_DIGEST_WORDS 8
+#define SHA256_DIGEST_ROW_SIZE  (MAX_SHA256_LANES * SHA256_DIGEST_WORD_SIZE)
+#define SHA256_DIGEST_SIZE      (SHA256_DIGEST_ROW_SIZE * SHA256_DIGEST_WORDS)
+#define SHA256_BLK_SZ           64
+
+# START_FIELDS
+.macro START_FIELDS
+ _FIELD_OFFSET = 0
+ _STRUCT_ALIGN = 0
+.endm
+
+# FIELD name size align
+.macro FIELD name size align
+ _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
+ \name	= _FIELD_OFFSET
+ _FIELD_OFFSET = _FIELD_OFFSET + (\size)
+.if (\align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = \align
+.endif
+.endm
+
+# END_FIELDS
+.macro END_FIELDS
+ _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
+.endm
+
+########################################################################
+
+.macro STRUCT p1
+START_FIELDS
+.struc \p1
+.endm
+
+.macro ENDSTRUCT
+ tmp = _FIELD_OFFSET
+ END_FIELDS
+ tmp = (_FIELD_OFFSET - %%tmp)
+.if (tmp > 0)
+	.lcomm	tmp
+.endif
+.endstruc
+.endm
+
+## RES_int name size align
+.macro RES_int p1 p2 p3
+ name = \p1
+ size = \p2
+ align = .\p3
+
+ _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
+.align align
+.lcomm name size
+ _FIELD_OFFSET = _FIELD_OFFSET + (size)
+.if (align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = align
+.endif
+.endm
+
+# macro RES_B name, size [, align]
+.macro RES_B _name, _size, _align=1
+RES_int _name _size _align
+.endm
+
+# macro RES_W name, size [, align]
+.macro RES_W _name, _size, _align=2
+RES_int _name 2*(_size) _align
+.endm
+
+# macro RES_D name, size [, align]
+.macro RES_D _name, _size, _align=4
+RES_int _name 4*(_size) _align
+.endm
+
+# macro RES_Q name, size [, align]
+.macro RES_Q _name, _size, _align=8
+RES_int _name 8*(_size) _align
+.endm
+
+# macro RES_DQ name, size [, align]
+.macro RES_DQ _name, _size, _align=16
+RES_int _name 16*(_size) _align
+.endm
+
+# macro RES_Y name, size [, align]
+.macro RES_Y _name, _size, _align=32
+RES_int _name 32*(_size) _align
+.endm
+
+# macro RES_Z name, size [, align]
+.macro RES_Z _name, _size, _align=64
+RES_int _name 64*(_size) _align
+.endm
+
+#endif
+
+
+########################################################################
+#### Define SHA256 Out Of Order Data Structures
+########################################################################
+
+START_FIELDS    # LANE_DATA
+###     name            size    align
+FIELD   _job_in_lane,   8,      8       # pointer to job object
+END_FIELDS
+
+ _LANE_DATA_size = _FIELD_OFFSET
+ _LANE_DATA_align = _STRUCT_ALIGN
+
+########################################################################
+
+START_FIELDS    # SHA256_ARGS_X4
+###     name            size    align
+FIELD   _digest,        4*8*8,  4       # transposed digest
+FIELD   _data_ptr,      8*8,    8       # array of pointers to data
+END_FIELDS
+
+ _SHA256_ARGS_X4_size  =  _FIELD_OFFSET
+ _SHA256_ARGS_X4_align = _STRUCT_ALIGN
+ _SHA256_ARGS_X8_size  =	_FIELD_OFFSET
+ _SHA256_ARGS_X8_align =	_STRUCT_ALIGN
+
+#######################################################################
+
+START_FIELDS    # MB_MGR
+###     name            size    align
+FIELD   _args,          _SHA256_ARGS_X4_size, _SHA256_ARGS_X4_align
+FIELD   _lens,          4*8,    8
+FIELD   _unused_lanes,  8,      8
+FIELD   _ldata,         _LANE_DATA_size*8, _LANE_DATA_align
+END_FIELDS
+
+ _MB_MGR_size  =  _FIELD_OFFSET
+ _MB_MGR_align =  _STRUCT_ALIGN
+
+_args_digest   =     _args + _digest
+_args_data_ptr =     _args + _data_ptr
+
+#######################################################################
+
+START_FIELDS    #STACK_FRAME
+###     name            size    align
+FIELD   _data,		16*SZ8,   1       # transposed digest
+FIELD   _digest,         8*SZ8,   1       # array of pointers to data
+FIELD   _ytmp,           4*SZ8,   1
+FIELD   _rsp,            8,       1
+END_FIELDS
+
+ _STACK_FRAME_size  =  _FIELD_OFFSET
+ _STACK_FRAME_align =  _STRUCT_ALIGN
+
+#######################################################################
+
+########################################################################
+#### Define constants
+########################################################################
+
+#define STS_UNKNOWN             0
+#define STS_BEING_PROCESSED     1
+#define STS_COMPLETED           2
+
+########################################################################
+#### Define JOB_SHA256 structure
+########################################################################
+
+START_FIELDS    # JOB_SHA256
+
+###     name                            size    align
+FIELD   _buffer,                        8,      8       # pointer to buffer
+FIELD   _len,                           8,      8       # length in bytes
+FIELD   _result_digest,                 8*4,    32      # Digest (output)
+FIELD   _status,                        4,      4
+FIELD   _user_data,                     8,      8
+END_FIELDS
+
+ _JOB_SHA256_size = _FIELD_OFFSET
+ _JOB_SHA256_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
new file mode 100644
index 000000000000..b691da981cd9
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -0,0 +1,304 @@
+/*
+ * Flush routine for SHA256 multibuffer
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha256_mb_mgr_datastruct.S"
+
+.extern sha256_x8_avx2
+
+#LINUX register definitions
+#define arg1	%rdi
+#define arg2	%rsi
+
+# Common register definitions
+#define state	arg1
+#define job	arg2
+#define len2	arg2
+
+# idx must be a register not clobberred by sha1_mult
+#define idx		%r8
+#define DWORD_idx	%r8d
+
+#define unused_lanes	%rbx
+#define lane_data	%rbx
+#define tmp2		%rbx
+#define tmp2_w		%ebx
+
+#define job_rax		%rax
+#define tmp1		%rax
+#define size_offset	%rax
+#define tmp		%rax
+#define start_offset	%rax
+
+#define tmp3		%arg1
+
+#define extra_blocks	%arg2
+#define p		%arg2
+
+.macro LABEL prefix n
+\prefix\n\():
+.endm
+
+.macro JNE_SKIP i
+jne     skip_\i
+.endm
+
+.altmacro
+.macro SET_OFFSET _offset
+offset = \_offset
+.endm
+.noaltmacro
+
+# JOB_SHA256* sha256_mb_mgr_flush_avx2(MB_MGR *state)
+# arg 1 : rcx : state
+ENTRY(sha256_mb_mgr_flush_avx2)
+	FRAME_BEGIN
+        push    %rbx
+
+	# If bit (32+3) is set, then all lanes are empty
+	mov	_unused_lanes(state), unused_lanes
+	bt	$32+3, unused_lanes
+	jc	return_null
+
+	# find a lane with a non-null job
+	xor	idx, idx
+	offset = (_ldata + 1 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	one(%rip), idx
+	offset = (_ldata + 2 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	two(%rip), idx
+	offset = (_ldata + 3 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	three(%rip), idx
+	offset = (_ldata + 4 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	four(%rip), idx
+	offset = (_ldata + 5 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	five(%rip), idx
+	offset = (_ldata + 6 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	six(%rip), idx
+	offset = (_ldata + 7 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	seven(%rip), idx
+
+	# copy idx to empty lanes
+copy_lane_data:
+	offset =  (_args + _data_ptr)
+	mov	offset(state,idx,8), tmp
+
+	I = 0
+.rep 8
+	offset = (_ldata + I * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+.altmacro
+	JNE_SKIP %I
+	offset =  (_args + _data_ptr + 8*I)
+	mov	tmp, offset(state)
+	offset =  (_lens + 4*I)
+	movl	$0xFFFFFFFF, offset(state)
+LABEL skip_ %I
+	I = (I+1)
+.noaltmacro
+.endr
+
+	# Find min length
+	vmovdqa _lens+0*16(state), %xmm0
+	vmovdqa _lens+1*16(state), %xmm1
+
+	vpminud %xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
+	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
+	vpminud %xmm3, %xmm2, %xmm2		# xmm2 has {x,x,E,F}
+	vpalignr $4, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,x,E}
+	vpminud %xmm3, %xmm2, %xmm2		# xmm2 has min val in low dword
+
+	vmovd	%xmm2, DWORD_idx
+	mov	idx, len2
+	and	$0xF, idx
+	shr	$4, len2
+	jz	len_is_0
+
+	vpand	clear_low_nibble(%rip), %xmm2, %xmm2
+	vpshufd	$0, %xmm2, %xmm2
+
+	vpsubd	%xmm2, %xmm0, %xmm0
+	vpsubd	%xmm2, %xmm1, %xmm1
+
+	vmovdqa	%xmm0, _lens+0*16(state)
+	vmovdqa	%xmm1, _lens+1*16(state)
+
+	# "state" and "args" are the same address, arg1
+	# len is arg2
+	call	sha256_x8_avx2
+	# state and idx are intact
+
+len_is_0:
+	# process completed job "idx"
+	imul	$_LANE_DATA_size, idx, lane_data
+	lea	_ldata(state, lane_data), lane_data
+
+	mov	_job_in_lane(lane_data), job_rax
+	movq	$0, _job_in_lane(lane_data)
+	movl	$STS_COMPLETED, _status(job_rax)
+	mov	_unused_lanes(state), unused_lanes
+	shl	$4, unused_lanes
+	or	idx, unused_lanes
+
+	mov	unused_lanes, _unused_lanes(state)
+	movl	$0xFFFFFFFF, _lens(state,idx,4)
+
+	vmovd	_args_digest(state , idx, 4) , %xmm0
+	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
+	vmovd	_args_digest+4*32(state, idx, 4), %xmm1
+	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
+
+	vmovdqu	%xmm0, _result_digest(job_rax)
+	offset =  (_result_digest + 1*16)
+	vmovdqu	%xmm1, offset(job_rax)
+
+return:
+	pop     %rbx
+	FRAME_END
+	ret
+
+return_null:
+	xor	job_rax, job_rax
+	jmp	return
+ENDPROC(sha256_mb_mgr_flush_avx2)
+
+##############################################################################
+
+.align 16
+ENTRY(sha256_mb_mgr_get_comp_job_avx2)
+	push	%rbx
+
+	## if bit 32+3 is set, then all lanes are empty
+	mov	_unused_lanes(state), unused_lanes
+	bt	$(32+3), unused_lanes
+	jc	.return_null
+
+	# Find min length
+	vmovdqa	_lens(state), %xmm0
+	vmovdqa	_lens+1*16(state), %xmm1
+
+	vpminud	%xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
+	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has {x,x,E,F}
+	vpalignr $4, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,x,E}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has min val in low dword
+
+	vmovd	%xmm2, DWORD_idx
+	test	$~0xF, idx
+	jnz	.return_null
+
+	# process completed job "idx"
+	imul	$_LANE_DATA_size, idx, lane_data
+	lea	_ldata(state, lane_data), lane_data
+
+	mov	_job_in_lane(lane_data), job_rax
+	movq	$0,  _job_in_lane(lane_data)
+	movl	$STS_COMPLETED, _status(job_rax)
+	mov	_unused_lanes(state), unused_lanes
+	shl	$4, unused_lanes
+	or	idx, unused_lanes
+	mov	unused_lanes, _unused_lanes(state)
+
+	movl	$0xFFFFFFFF, _lens(state,  idx, 4)
+
+	vmovd	_args_digest(state, idx, 4), %xmm0
+	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
+	movl	_args_digest+4*32(state, idx, 4), tmp2_w
+	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
+
+	vmovdqu	%xmm0, _result_digest(job_rax)
+	movl	tmp2_w, _result_digest+1*16(job_rax)
+
+	pop	%rbx
+
+	ret
+
+.return_null:
+	xor	job_rax, job_rax
+	pop	%rbx
+	ret
+ENDPROC(sha256_mb_mgr_get_comp_job_avx2)
+
+.data
+
+.align 16
+clear_low_nibble:
+.octa	0x000000000000000000000000FFFFFFF0
+one:
+.quad	1
+two:
+.quad	2
+three:
+.quad	3
+four:
+.quad	4
+five:
+.quad	5
+six:
+.quad	6
+seven:
+.quad  7
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c
new file mode 100644
index 000000000000..b0c498371e67
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c
@@ -0,0 +1,65 @@
+/*
+ * Initialization code for multi buffer SHA256 algorithm for AVX2
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "sha256_mb_mgr.h"
+
+void sha256_mb_mgr_init_avx2(struct sha256_mb_mgr *state)
+{
+	unsigned int j;
+
+	state->unused_lanes = 0xF76543210ULL;
+	for (j = 0; j < 8; j++) {
+		state->lens[j] = 0xFFFFFFFF;
+		state->ldata[j].job_in_lane = NULL;
+	}
+}
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S
new file mode 100644
index 000000000000..7ea670e25acc
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S
@@ -0,0 +1,215 @@
+/*
+ * Buffer submit code for multi buffer SHA256 algorithm
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha256_mb_mgr_datastruct.S"
+
+.extern sha256_x8_avx2
+
+# LINUX register definitions
+arg1		= %rdi
+arg2		= %rsi
+size_offset	= %rcx
+tmp2		= %rcx
+extra_blocks	= %rdx
+
+# Common definitions
+#define state	arg1
+#define job	%rsi
+#define len2	arg2
+#define p2	arg2
+
+# idx must be a register not clobberred by sha1_x8_avx2
+idx		= %r8
+DWORD_idx	= %r8d
+last_len	= %r8
+
+p		= %r11
+start_offset	= %r11
+
+unused_lanes	= %rbx
+BYTE_unused_lanes = %bl
+
+job_rax		= %rax
+len		= %rax
+DWORD_len	= %eax
+
+lane		= %r12
+tmp3		= %r12
+
+tmp		= %r9
+DWORD_tmp	= %r9d
+
+lane_data	= %r10
+
+# JOB* sha256_mb_mgr_submit_avx2(MB_MGR *state, JOB_SHA256 *job)
+# arg 1 : rcx : state
+# arg 2 : rdx : job
+ENTRY(sha256_mb_mgr_submit_avx2)
+	FRAME_BEGIN
+	push	%rbx
+	push	%r12
+
+	mov	_unused_lanes(state), unused_lanes
+	mov	unused_lanes, lane
+	and	$0xF, lane
+	shr	$4, unused_lanes
+	imul	$_LANE_DATA_size, lane, lane_data
+	movl	$STS_BEING_PROCESSED, _status(job)
+	lea	_ldata(state, lane_data), lane_data
+	mov	unused_lanes, _unused_lanes(state)
+	movl	_len(job),  DWORD_len
+
+	mov	job, _job_in_lane(lane_data)
+	shl	$4, len
+	or	lane, len
+
+	movl	DWORD_len,  _lens(state , lane, 4)
+
+	# Load digest words from result_digest
+	vmovdqu	_result_digest(job), %xmm0
+	vmovdqu	_result_digest+1*16(job), %xmm1
+	vmovd	%xmm0, _args_digest(state, lane, 4)
+	vpextrd	$1, %xmm0, _args_digest+1*32(state , lane, 4)
+	vpextrd	$2, %xmm0, _args_digest+2*32(state , lane, 4)
+	vpextrd	$3, %xmm0, _args_digest+3*32(state , lane, 4)
+	vmovd	%xmm1, _args_digest+4*32(state , lane, 4)
+
+	vpextrd	$1, %xmm1, _args_digest+5*32(state , lane, 4)
+	vpextrd	$2, %xmm1, _args_digest+6*32(state , lane, 4)
+	vpextrd	$3, %xmm1, _args_digest+7*32(state , lane, 4)
+
+	mov	_buffer(job), p
+	mov	p, _args_data_ptr(state, lane, 8)
+
+	cmp	$0xF, unused_lanes
+	jne	return_null
+
+start_loop:
+	# Find min length
+	vmovdqa	_lens(state), %xmm0
+	vmovdqa	_lens+1*16(state), %xmm1
+
+	vpminud	%xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
+	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has {x,x,E,F}
+	vpalignr $4, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,x,E}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has min val in low dword
+
+	vmovd	%xmm2, DWORD_idx
+	mov	idx, len2
+	and	$0xF, idx
+	shr	$4, len2
+	jz	len_is_0
+
+	vpand	clear_low_nibble(%rip), %xmm2, %xmm2
+	vpshufd	$0, %xmm2, %xmm2
+
+	vpsubd	%xmm2, %xmm0, %xmm0
+	vpsubd	%xmm2, %xmm1, %xmm1
+
+	vmovdqa	%xmm0, _lens + 0*16(state)
+	vmovdqa	%xmm1, _lens + 1*16(state)
+
+	# "state" and "args" are the same address, arg1
+	# len is arg2
+	call	sha256_x8_avx2
+
+	# state and idx are intact
+
+len_is_0:
+	# process completed job "idx"
+	imul	$_LANE_DATA_size, idx, lane_data
+	lea	_ldata(state, lane_data), lane_data
+
+	mov	_job_in_lane(lane_data), job_rax
+	mov	_unused_lanes(state), unused_lanes
+	movq	$0, _job_in_lane(lane_data)
+	movl	$STS_COMPLETED, _status(job_rax)
+	shl	$4, unused_lanes
+	or	idx, unused_lanes
+	mov	unused_lanes, _unused_lanes(state)
+
+	movl	$0xFFFFFFFF, _lens(state,idx,4)
+
+	vmovd	_args_digest(state, idx, 4), %xmm0
+	vpinsrd	$1, _args_digest+1*32(state , idx, 4), %xmm0, %xmm0
+	vpinsrd	$2, _args_digest+2*32(state , idx, 4), %xmm0, %xmm0
+	vpinsrd	$3, _args_digest+3*32(state , idx, 4), %xmm0, %xmm0
+	vmovd	_args_digest+4*32(state, idx, 4), %xmm1
+
+	vpinsrd	$1, _args_digest+5*32(state , idx, 4), %xmm1, %xmm1
+	vpinsrd	$2, _args_digest+6*32(state , idx, 4), %xmm1, %xmm1
+	vpinsrd	$3, _args_digest+7*32(state , idx, 4), %xmm1, %xmm1
+
+	vmovdqu	%xmm0, _result_digest(job_rax)
+	vmovdqu	%xmm1, _result_digest+1*16(job_rax)
+
+return:
+	pop     %r12
+        pop     %rbx
+        FRAME_END
+	ret
+
+return_null:
+	xor	job_rax, job_rax
+	jmp	return
+
+ENDPROC(sha256_mb_mgr_submit_avx2)
+
+.data
+
+.align 16
+clear_low_nibble:
+	.octa	0x000000000000000000000000FFFFFFF0
diff --git a/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S b/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S
new file mode 100644
index 000000000000..aa21aea4c722
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S
@@ -0,0 +1,593 @@
+/*
+ * Multi-buffer SHA256 algorithm hash compute routine
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include "sha256_mb_mgr_datastruct.S"
+
+## code to compute oct SHA256 using SSE-256
+## outer calling routine takes care of save and restore of XMM registers
+## Logic designed/laid out by JDG
+
+## Function clobbers: rax, rcx, rdx,   rbx, rsi, rdi, r9-r15; %ymm0-15
+## Linux clobbers:    rax rbx rcx rdx rsi            r9 r10 r11 r12 r13 r14 r15
+## Linux preserves:                       rdi rbp r8
+##
+## clobbers %ymm0-15
+
+arg1 = %rdi
+arg2 = %rsi
+reg3 = %rcx
+reg4 = %rdx
+
+# Common definitions
+STATE = arg1
+INP_SIZE = arg2
+
+IDX = %rax
+ROUND = %rbx
+TBL = reg3
+
+inp0 = %r9
+inp1 = %r10
+inp2 = %r11
+inp3 = %r12
+inp4 = %r13
+inp5 = %r14
+inp6 = %r15
+inp7 = reg4
+
+a = %ymm0
+b = %ymm1
+c = %ymm2
+d = %ymm3
+e = %ymm4
+f = %ymm5
+g = %ymm6
+h = %ymm7
+
+T1 = %ymm8
+
+a0 = %ymm12
+a1 = %ymm13
+a2 = %ymm14
+TMP = %ymm15
+TMP0 = %ymm6
+TMP1 = %ymm7
+
+TT0 = %ymm8
+TT1 = %ymm9
+TT2 = %ymm10
+TT3 = %ymm11
+TT4 = %ymm12
+TT5 = %ymm13
+TT6 = %ymm14
+TT7 = %ymm15
+
+# Define stack usage
+
+# Assume stack aligned to 32 bytes before call
+# Therefore FRAMESZ mod 32 must be 32-8 = 24
+
+#define FRAMESZ	0x388
+
+#define VMOVPS	vmovups
+
+# TRANSPOSE8 r0, r1, r2, r3, r4, r5, r6, r7, t0, t1
+# "transpose" data in {r0...r7} using temps {t0...t1}
+# Input looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
+# r0 = {a7 a6 a5 a4   a3 a2 a1 a0}
+# r1 = {b7 b6 b5 b4   b3 b2 b1 b0}
+# r2 = {c7 c6 c5 c4   c3 c2 c1 c0}
+# r3 = {d7 d6 d5 d4   d3 d2 d1 d0}
+# r4 = {e7 e6 e5 e4   e3 e2 e1 e0}
+# r5 = {f7 f6 f5 f4   f3 f2 f1 f0}
+# r6 = {g7 g6 g5 g4   g3 g2 g1 g0}
+# r7 = {h7 h6 h5 h4   h3 h2 h1 h0}
+#
+# Output looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
+# r0 = {h0 g0 f0 e0   d0 c0 b0 a0}
+# r1 = {h1 g1 f1 e1   d1 c1 b1 a1}
+# r2 = {h2 g2 f2 e2   d2 c2 b2 a2}
+# r3 = {h3 g3 f3 e3   d3 c3 b3 a3}
+# r4 = {h4 g4 f4 e4   d4 c4 b4 a4}
+# r5 = {h5 g5 f5 e5   d5 c5 b5 a5}
+# r6 = {h6 g6 f6 e6   d6 c6 b6 a6}
+# r7 = {h7 g7 f7 e7   d7 c7 b7 a7}
+#
+
+.macro TRANSPOSE8 r0 r1 r2 r3 r4 r5 r6 r7 t0 t1
+	# process top half (r0..r3) {a...d}
+	vshufps	$0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4   b1 b0 a1 a0}
+	vshufps	$0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6   b3 b2 a3 a2}
+	vshufps	$0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4   d1 d0 c1 c0}
+	vshufps	$0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6   d3 d2 c3 c2}
+	vshufps	$0xDD, \t1, \t0, \r3 # r3 = {d5 c5 b5 a5   d1 c1 b1 a1}
+	vshufps	$0x88, \r2, \r0, \r1 # r1 = {d6 c6 b6 a6   d2 c2 b2 a2}
+	vshufps	$0xDD, \r2, \r0, \r0 # r0 = {d7 c7 b7 a7   d3 c3 b3 a3}
+	vshufps	$0x88, \t1, \t0, \t0 # t0 = {d4 c4 b4 a4   d0 c0 b0 a0}
+
+	# use r2 in place of t0
+	# process bottom half (r4..r7) {e...h}
+	vshufps	$0x44, \r5, \r4, \r2 # r2 = {f5 f4 e5 e4   f1 f0 e1 e0}
+	vshufps	$0xEE, \r5, \r4, \r4 # r4 = {f7 f6 e7 e6   f3 f2 e3 e2}
+	vshufps	$0x44, \r7, \r6, \t1 # t1 = {h5 h4 g5 g4   h1 h0 g1 g0}
+	vshufps	$0xEE, \r7, \r6, \r6 # r6 = {h7 h6 g7 g6   h3 h2 g3 g2}
+	vshufps	$0xDD, \t1, \r2, \r7 # r7 = {h5 g5 f5 e5   h1 g1 f1 e1}
+	vshufps	$0x88, \r6, \r4, \r5 # r5 = {h6 g6 f6 e6   h2 g2 f2 e2}
+	vshufps	$0xDD, \r6, \r4, \r4 # r4 = {h7 g7 f7 e7   h3 g3 f3 e3}
+	vshufps	$0x88, \t1, \r2, \t1 # t1 = {h4 g4 f4 e4   h0 g0 f0 e0}
+
+	vperm2f128	$0x13, \r1, \r5, \r6  # h6...a6
+	vperm2f128	$0x02, \r1, \r5, \r2  # h2...a2
+	vperm2f128	$0x13, \r3, \r7, \r5  # h5...a5
+	vperm2f128	$0x02, \r3, \r7, \r1  # h1...a1
+	vperm2f128	$0x13, \r0, \r4, \r7  # h7...a7
+	vperm2f128	$0x02, \r0, \r4, \r3  # h3...a3
+	vperm2f128	$0x13, \t0, \t1, \r4  # h4...a4
+	vperm2f128	$0x02, \t0, \t1, \r0  # h0...a0
+
+.endm
+
+.macro ROTATE_ARGS
+TMP_ = h
+h = g
+g = f
+f = e
+e = d
+d = c
+c = b
+b = a
+a = TMP_
+.endm
+
+.macro _PRORD reg imm tmp
+	vpslld	$(32-\imm),\reg,\tmp
+	vpsrld	$\imm,\reg, \reg
+	vpor	\tmp,\reg, \reg
+.endm
+
+# PRORD_nd reg, imm, tmp, src
+.macro _PRORD_nd reg imm tmp src
+	vpslld	$(32-\imm), \src, \tmp
+	vpsrld	$\imm, \src, \reg
+	vpor	\tmp, \reg, \reg
+.endm
+
+# PRORD dst/src, amt
+.macro PRORD reg imm
+	_PRORD	\reg,\imm,TMP
+.endm
+
+# PRORD_nd dst, src, amt
+.macro PRORD_nd reg tmp imm
+	_PRORD_nd	\reg, \imm, TMP, \tmp
+.endm
+
+# arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_00_15 _T1 i
+	PRORD_nd	a0,e,5	# sig1: a0 = (e >> 5)
+
+	vpxor	g, f, a2	# ch: a2 = f^g
+	vpand	e,a2, a2	# ch: a2 = (f^g)&e
+	vpxor	g, a2, a2	# a2 = ch
+
+	PRORD_nd	a1,e,25	# sig1: a1 = (e >> 25)
+
+	vmovdqu	\_T1,(SZ8*(\i & 0xf))(%rsp)
+	vpaddd	(TBL,ROUND,1), \_T1, \_T1	# T1 = W + K
+	vpxor	e,a0, a0	# sig1: a0 = e ^ (e >> 5)
+	PRORD	a0, 6		# sig1: a0 = (e >> 6) ^ (e >> 11)
+	vpaddd	a2, h, h	# h = h + ch
+	PRORD_nd	a2,a,11	# sig0: a2 = (a >> 11)
+	vpaddd	\_T1,h, h 	# h = h + ch + W + K
+	vpxor	a1, a0, a0	# a0 = sigma1
+	PRORD_nd	a1,a,22	# sig0: a1 = (a >> 22)
+	vpxor	c, a, \_T1	# maj: T1 = a^c
+	add	$SZ8, ROUND	# ROUND++
+	vpand	b, \_T1, \_T1	# maj: T1 = (a^c)&b
+	vpaddd	a0, h, h
+	vpaddd	h, d, d
+	vpxor	a, a2, a2	# sig0: a2 = a ^ (a >> 11)
+	PRORD	a2,2		# sig0: a2 = (a >> 2) ^ (a >> 13)
+	vpxor	a1, a2, a2	# a2 = sig0
+	vpand	c, a, a1	# maj: a1 = a&c
+	vpor	\_T1, a1, a1 	# a1 = maj
+	vpaddd	a1, h, h	# h = h + ch + W + K + maj
+	vpaddd	a2, h, h	# h = h + ch + W + K + maj + sigma0
+	ROTATE_ARGS
+.endm
+
+# arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_16_XX _T1 i
+	vmovdqu	(SZ8*((\i-15)&0xf))(%rsp), \_T1
+	vmovdqu	(SZ8*((\i-2)&0xf))(%rsp), a1
+	vmovdqu	\_T1, a0
+	PRORD	\_T1,11
+	vmovdqu	a1, a2
+	PRORD	a1,2
+	vpxor	a0, \_T1, \_T1
+	PRORD	\_T1, 7
+	vpxor	a2, a1, a1
+	PRORD	a1, 17
+	vpsrld	$3, a0, a0
+	vpxor	a0, \_T1, \_T1
+	vpsrld	$10, a2, a2
+	vpxor	a2, a1, a1
+	vpaddd	(SZ8*((\i-16)&0xf))(%rsp), \_T1, \_T1
+	vpaddd	(SZ8*((\i-7)&0xf))(%rsp), a1, a1
+	vpaddd	a1, \_T1, \_T1
+
+	ROUND_00_15 \_T1,\i
+.endm
+
+# SHA256_ARGS:
+#   UINT128 digest[8];  // transposed digests
+#   UINT8  *data_ptr[4];
+
+# void sha256_x8_avx2(SHA256_ARGS *args, UINT64 bytes);
+# arg 1 : STATE : pointer to array of pointers to input data
+# arg 2 : INP_SIZE  : size of input in blocks
+	# general registers preserved in outer calling routine
+	# outer calling routine saves all the XMM registers
+	# save rsp, allocate 32-byte aligned for local variables
+ENTRY(sha256_x8_avx2)
+
+	# save callee-saved clobbered registers to comply with C function ABI
+	push    %r12
+	push    %r13
+	push    %r14
+	push    %r15
+
+	mov	%rsp, IDX
+	sub	$FRAMESZ, %rsp
+	and	$~0x1F, %rsp
+	mov	IDX, _rsp(%rsp)
+
+	# Load the pre-transposed incoming digest.
+	vmovdqu	0*SHA256_DIGEST_ROW_SIZE(STATE),a
+	vmovdqu	1*SHA256_DIGEST_ROW_SIZE(STATE),b
+	vmovdqu	2*SHA256_DIGEST_ROW_SIZE(STATE),c
+	vmovdqu	3*SHA256_DIGEST_ROW_SIZE(STATE),d
+	vmovdqu	4*SHA256_DIGEST_ROW_SIZE(STATE),e
+	vmovdqu	5*SHA256_DIGEST_ROW_SIZE(STATE),f
+	vmovdqu	6*SHA256_DIGEST_ROW_SIZE(STATE),g
+	vmovdqu	7*SHA256_DIGEST_ROW_SIZE(STATE),h
+
+	lea	K256_8(%rip),TBL
+
+	# load the address of each of the 4 message lanes
+	# getting ready to transpose input onto stack
+	mov	_args_data_ptr+0*PTR_SZ(STATE),inp0
+	mov	_args_data_ptr+1*PTR_SZ(STATE),inp1
+	mov	_args_data_ptr+2*PTR_SZ(STATE),inp2
+	mov	_args_data_ptr+3*PTR_SZ(STATE),inp3
+	mov	_args_data_ptr+4*PTR_SZ(STATE),inp4
+	mov	_args_data_ptr+5*PTR_SZ(STATE),inp5
+	mov	_args_data_ptr+6*PTR_SZ(STATE),inp6
+	mov	_args_data_ptr+7*PTR_SZ(STATE),inp7
+
+	xor	IDX, IDX
+lloop:
+	xor	ROUND, ROUND
+
+	# save old digest
+	vmovdqu	a, _digest(%rsp)
+	vmovdqu	b, _digest+1*SZ8(%rsp)
+	vmovdqu	c, _digest+2*SZ8(%rsp)
+	vmovdqu	d, _digest+3*SZ8(%rsp)
+	vmovdqu	e, _digest+4*SZ8(%rsp)
+	vmovdqu	f, _digest+5*SZ8(%rsp)
+	vmovdqu	g, _digest+6*SZ8(%rsp)
+	vmovdqu	h, _digest+7*SZ8(%rsp)
+	i = 0
+.rep 2
+	VMOVPS	i*32(inp0, IDX), TT0
+	VMOVPS	i*32(inp1, IDX), TT1
+	VMOVPS	i*32(inp2, IDX), TT2
+	VMOVPS	i*32(inp3, IDX), TT3
+	VMOVPS	i*32(inp4, IDX), TT4
+	VMOVPS	i*32(inp5, IDX), TT5
+	VMOVPS	i*32(inp6, IDX), TT6
+	VMOVPS	i*32(inp7, IDX), TT7
+	vmovdqu	g, _ytmp(%rsp)
+	vmovdqu	h, _ytmp+1*SZ8(%rsp)
+	TRANSPOSE8	TT0, TT1, TT2, TT3, TT4, TT5, TT6, TT7,   TMP0, TMP1
+	vmovdqu	PSHUFFLE_BYTE_FLIP_MASK(%rip), TMP1
+	vmovdqu	_ytmp(%rsp), g
+	vpshufb	TMP1, TT0, TT0
+	vpshufb	TMP1, TT1, TT1
+	vpshufb	TMP1, TT2, TT2
+	vpshufb	TMP1, TT3, TT3
+	vpshufb	TMP1, TT4, TT4
+	vpshufb	TMP1, TT5, TT5
+	vpshufb	TMP1, TT6, TT6
+	vpshufb	TMP1, TT7, TT7
+	vmovdqu	_ytmp+1*SZ8(%rsp), h
+	vmovdqu	TT4, _ytmp(%rsp)
+	vmovdqu	TT5, _ytmp+1*SZ8(%rsp)
+	vmovdqu	TT6, _ytmp+2*SZ8(%rsp)
+	vmovdqu	TT7, _ytmp+3*SZ8(%rsp)
+	ROUND_00_15	TT0,(i*8+0)
+	vmovdqu	_ytmp(%rsp), TT0
+	ROUND_00_15	TT1,(i*8+1)
+	vmovdqu	_ytmp+1*SZ8(%rsp), TT1
+	ROUND_00_15	TT2,(i*8+2)
+	vmovdqu	_ytmp+2*SZ8(%rsp), TT2
+	ROUND_00_15	TT3,(i*8+3)
+	vmovdqu	_ytmp+3*SZ8(%rsp), TT3
+	ROUND_00_15	TT0,(i*8+4)
+	ROUND_00_15	TT1,(i*8+5)
+	ROUND_00_15	TT2,(i*8+6)
+	ROUND_00_15	TT3,(i*8+7)
+	i = (i+1)
+.endr
+	add	$64, IDX
+	i = (i*8)
+
+	jmp	Lrounds_16_xx
+.align 16
+Lrounds_16_xx:
+.rep 16
+	ROUND_16_XX	T1, i
+	i = (i+1)
+.endr
+
+	cmp	$ROUNDS,ROUND
+	jb	Lrounds_16_xx
+
+	# add old digest
+	vpaddd	_digest+0*SZ8(%rsp), a, a
+	vpaddd	_digest+1*SZ8(%rsp), b, b
+	vpaddd	_digest+2*SZ8(%rsp), c, c
+	vpaddd	_digest+3*SZ8(%rsp), d, d
+	vpaddd	_digest+4*SZ8(%rsp), e, e
+	vpaddd	_digest+5*SZ8(%rsp), f, f
+	vpaddd	_digest+6*SZ8(%rsp), g, g
+	vpaddd	_digest+7*SZ8(%rsp), h, h
+
+	sub	$1, INP_SIZE  # unit is blocks
+	jne	lloop
+
+	# write back to memory (state object) the transposed digest
+	vmovdqu	a, 0*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	b, 1*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	c, 2*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	d, 3*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	e, 4*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	f, 5*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	g, 6*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	h, 7*SHA256_DIGEST_ROW_SIZE(STATE)
+
+	# update input pointers
+	add	IDX, inp0
+	mov	inp0, _args_data_ptr+0*8(STATE)
+	add	IDX, inp1
+	mov	inp1, _args_data_ptr+1*8(STATE)
+	add	IDX, inp2
+	mov	inp2, _args_data_ptr+2*8(STATE)
+	add	IDX, inp3
+	mov	inp3, _args_data_ptr+3*8(STATE)
+	add	IDX, inp4
+	mov	inp4, _args_data_ptr+4*8(STATE)
+	add	IDX, inp5
+	mov	inp5, _args_data_ptr+5*8(STATE)
+	add	IDX, inp6
+	mov	inp6, _args_data_ptr+6*8(STATE)
+	add	IDX, inp7
+	mov	inp7, _args_data_ptr+7*8(STATE)
+
+	# Postamble
+	mov	_rsp(%rsp), %rsp
+
+	# restore callee-saved clobbered registers
+	pop     %r15
+	pop     %r14
+	pop     %r13
+	pop     %r12
+
+	ret
+ENDPROC(sha256_x8_avx2)
+.data
+.align 64
+K256_8:
+	.octa	0x428a2f98428a2f98428a2f98428a2f98
+	.octa	0x428a2f98428a2f98428a2f98428a2f98
+	.octa	0x71374491713744917137449171374491
+	.octa	0x71374491713744917137449171374491
+	.octa	0xb5c0fbcfb5c0fbcfb5c0fbcfb5c0fbcf
+	.octa	0xb5c0fbcfb5c0fbcfb5c0fbcfb5c0fbcf
+	.octa	0xe9b5dba5e9b5dba5e9b5dba5e9b5dba5
+	.octa	0xe9b5dba5e9b5dba5e9b5dba5e9b5dba5
+	.octa	0x3956c25b3956c25b3956c25b3956c25b
+	.octa	0x3956c25b3956c25b3956c25b3956c25b
+	.octa	0x59f111f159f111f159f111f159f111f1
+	.octa	0x59f111f159f111f159f111f159f111f1
+	.octa	0x923f82a4923f82a4923f82a4923f82a4
+	.octa	0x923f82a4923f82a4923f82a4923f82a4
+	.octa	0xab1c5ed5ab1c5ed5ab1c5ed5ab1c5ed5
+	.octa	0xab1c5ed5ab1c5ed5ab1c5ed5ab1c5ed5
+	.octa	0xd807aa98d807aa98d807aa98d807aa98
+	.octa	0xd807aa98d807aa98d807aa98d807aa98
+	.octa	0x12835b0112835b0112835b0112835b01
+	.octa	0x12835b0112835b0112835b0112835b01
+	.octa	0x243185be243185be243185be243185be
+	.octa	0x243185be243185be243185be243185be
+	.octa	0x550c7dc3550c7dc3550c7dc3550c7dc3
+	.octa	0x550c7dc3550c7dc3550c7dc3550c7dc3
+	.octa	0x72be5d7472be5d7472be5d7472be5d74
+	.octa	0x72be5d7472be5d7472be5d7472be5d74
+	.octa	0x80deb1fe80deb1fe80deb1fe80deb1fe
+	.octa	0x80deb1fe80deb1fe80deb1fe80deb1fe
+	.octa	0x9bdc06a79bdc06a79bdc06a79bdc06a7
+	.octa	0x9bdc06a79bdc06a79bdc06a79bdc06a7
+	.octa	0xc19bf174c19bf174c19bf174c19bf174
+	.octa	0xc19bf174c19bf174c19bf174c19bf174
+	.octa	0xe49b69c1e49b69c1e49b69c1e49b69c1
+	.octa	0xe49b69c1e49b69c1e49b69c1e49b69c1
+	.octa	0xefbe4786efbe4786efbe4786efbe4786
+	.octa	0xefbe4786efbe4786efbe4786efbe4786
+	.octa	0x0fc19dc60fc19dc60fc19dc60fc19dc6
+	.octa	0x0fc19dc60fc19dc60fc19dc60fc19dc6
+	.octa	0x240ca1cc240ca1cc240ca1cc240ca1cc
+	.octa	0x240ca1cc240ca1cc240ca1cc240ca1cc
+	.octa	0x2de92c6f2de92c6f2de92c6f2de92c6f
+	.octa	0x2de92c6f2de92c6f2de92c6f2de92c6f
+	.octa	0x4a7484aa4a7484aa4a7484aa4a7484aa
+	.octa	0x4a7484aa4a7484aa4a7484aa4a7484aa
+	.octa	0x5cb0a9dc5cb0a9dc5cb0a9dc5cb0a9dc
+	.octa	0x5cb0a9dc5cb0a9dc5cb0a9dc5cb0a9dc
+	.octa	0x76f988da76f988da76f988da76f988da
+	.octa	0x76f988da76f988da76f988da76f988da
+	.octa	0x983e5152983e5152983e5152983e5152
+	.octa	0x983e5152983e5152983e5152983e5152
+	.octa	0xa831c66da831c66da831c66da831c66d
+	.octa	0xa831c66da831c66da831c66da831c66d
+	.octa	0xb00327c8b00327c8b00327c8b00327c8
+	.octa	0xb00327c8b00327c8b00327c8b00327c8
+	.octa	0xbf597fc7bf597fc7bf597fc7bf597fc7
+	.octa	0xbf597fc7bf597fc7bf597fc7bf597fc7
+	.octa	0xc6e00bf3c6e00bf3c6e00bf3c6e00bf3
+	.octa	0xc6e00bf3c6e00bf3c6e00bf3c6e00bf3
+	.octa	0xd5a79147d5a79147d5a79147d5a79147
+	.octa	0xd5a79147d5a79147d5a79147d5a79147
+	.octa	0x06ca635106ca635106ca635106ca6351
+	.octa	0x06ca635106ca635106ca635106ca6351
+	.octa	0x14292967142929671429296714292967
+	.octa	0x14292967142929671429296714292967
+	.octa	0x27b70a8527b70a8527b70a8527b70a85
+	.octa	0x27b70a8527b70a8527b70a8527b70a85
+	.octa	0x2e1b21382e1b21382e1b21382e1b2138
+	.octa	0x2e1b21382e1b21382e1b21382e1b2138
+	.octa	0x4d2c6dfc4d2c6dfc4d2c6dfc4d2c6dfc
+	.octa	0x4d2c6dfc4d2c6dfc4d2c6dfc4d2c6dfc
+	.octa	0x53380d1353380d1353380d1353380d13
+	.octa	0x53380d1353380d1353380d1353380d13
+	.octa	0x650a7354650a7354650a7354650a7354
+	.octa	0x650a7354650a7354650a7354650a7354
+	.octa	0x766a0abb766a0abb766a0abb766a0abb
+	.octa	0x766a0abb766a0abb766a0abb766a0abb
+	.octa	0x81c2c92e81c2c92e81c2c92e81c2c92e
+	.octa	0x81c2c92e81c2c92e81c2c92e81c2c92e
+	.octa	0x92722c8592722c8592722c8592722c85
+	.octa	0x92722c8592722c8592722c8592722c85
+	.octa	0xa2bfe8a1a2bfe8a1a2bfe8a1a2bfe8a1
+	.octa	0xa2bfe8a1a2bfe8a1a2bfe8a1a2bfe8a1
+	.octa	0xa81a664ba81a664ba81a664ba81a664b
+	.octa	0xa81a664ba81a664ba81a664ba81a664b
+	.octa	0xc24b8b70c24b8b70c24b8b70c24b8b70
+	.octa	0xc24b8b70c24b8b70c24b8b70c24b8b70
+	.octa	0xc76c51a3c76c51a3c76c51a3c76c51a3
+	.octa	0xc76c51a3c76c51a3c76c51a3c76c51a3
+	.octa	0xd192e819d192e819d192e819d192e819
+	.octa	0xd192e819d192e819d192e819d192e819
+	.octa	0xd6990624d6990624d6990624d6990624
+	.octa	0xd6990624d6990624d6990624d6990624
+	.octa	0xf40e3585f40e3585f40e3585f40e3585
+	.octa	0xf40e3585f40e3585f40e3585f40e3585
+	.octa	0x106aa070106aa070106aa070106aa070
+	.octa	0x106aa070106aa070106aa070106aa070
+	.octa	0x19a4c11619a4c11619a4c11619a4c116
+	.octa	0x19a4c11619a4c11619a4c11619a4c116
+	.octa	0x1e376c081e376c081e376c081e376c08
+	.octa	0x1e376c081e376c081e376c081e376c08
+	.octa	0x2748774c2748774c2748774c2748774c
+	.octa	0x2748774c2748774c2748774c2748774c
+	.octa	0x34b0bcb534b0bcb534b0bcb534b0bcb5
+	.octa	0x34b0bcb534b0bcb534b0bcb534b0bcb5
+	.octa	0x391c0cb3391c0cb3391c0cb3391c0cb3
+	.octa	0x391c0cb3391c0cb3391c0cb3391c0cb3
+	.octa	0x4ed8aa4a4ed8aa4a4ed8aa4a4ed8aa4a
+	.octa	0x4ed8aa4a4ed8aa4a4ed8aa4a4ed8aa4a
+	.octa	0x5b9cca4f5b9cca4f5b9cca4f5b9cca4f
+	.octa	0x5b9cca4f5b9cca4f5b9cca4f5b9cca4f
+	.octa	0x682e6ff3682e6ff3682e6ff3682e6ff3
+	.octa	0x682e6ff3682e6ff3682e6ff3682e6ff3
+	.octa	0x748f82ee748f82ee748f82ee748f82ee
+	.octa	0x748f82ee748f82ee748f82ee748f82ee
+	.octa	0x78a5636f78a5636f78a5636f78a5636f
+	.octa	0x78a5636f78a5636f78a5636f78a5636f
+	.octa	0x84c8781484c8781484c8781484c87814
+	.octa	0x84c8781484c8781484c8781484c87814
+	.octa	0x8cc702088cc702088cc702088cc70208
+	.octa	0x8cc702088cc702088cc702088cc70208
+	.octa	0x90befffa90befffa90befffa90befffa
+	.octa	0x90befffa90befffa90befffa90befffa
+	.octa	0xa4506ceba4506ceba4506ceba4506ceb
+	.octa	0xa4506ceba4506ceba4506ceba4506ceb
+	.octa	0xbef9a3f7bef9a3f7bef9a3f7bef9a3f7
+	.octa	0xbef9a3f7bef9a3f7bef9a3f7bef9a3f7
+	.octa	0xc67178f2c67178f2c67178f2c67178f2
+	.octa	0xc67178f2c67178f2c67178f2c67178f2
+PSHUFFLE_BYTE_FLIP_MASK:
+.octa 0x0c0d0e0f08090a0b0405060700010203
+.octa 0x0c0d0e0f08090a0b0405060700010203
+
+.align 64
+.global K256
+K256:
+	.int	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.int	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.int	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.int	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.int	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.int	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.int	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.int	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.int	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.int	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.int	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.int	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.int	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.int	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.int	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.int	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 3ae0f43ebd37..9e79baf03a4b 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -427,4 +427,14 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
 MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha256-ssse3");
+MODULE_ALIAS_CRYPTO("sha256-avx");
+MODULE_ALIAS_CRYPTO("sha256-avx2");
 MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha224-ssse3");
+MODULE_ALIAS_CRYPTO("sha224-avx");
+MODULE_ALIAS_CRYPTO("sha224-avx2");
+#ifdef CONFIG_AS_SHA256_NI
+MODULE_ALIAS_CRYPTO("sha256-ni");
+MODULE_ALIAS_CRYPTO("sha224-ni");
+#endif
diff --git a/arch/x86/crypto/sha512-mb/Makefile b/arch/x86/crypto/sha512-mb/Makefile
new file mode 100644
index 000000000000..0a57e2103980
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/Makefile
@@ -0,0 +1,11 @@
+#
+# Arch-specific CryptoAPI modules.
+#
+
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+                                $(comma)4)$(comma)%ymm2,yes,no)
+ifeq ($(avx2_supported),yes)
+	obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb.o
+	sha512-mb-y := sha512_mb.o sha512_mb_mgr_flush_avx2.o \
+	     sha512_mb_mgr_init_avx2.o sha512_mb_mgr_submit_avx2.o sha512_x4_avx2.o
+endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
new file mode 100644
index 000000000000..f4cf5b78fd36
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -0,0 +1,1046 @@
+/*
+ * Multi buffer SHA512 algorithm Glue Code
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+#include <crypto/mcryptd.h>
+#include <crypto/crypto_wq.h>
+#include <asm/byteorder.h>
+#include <linux/hardirq.h>
+#include <asm/fpu/api.h>
+#include "sha512_mb_ctx.h"
+
+#define FLUSH_INTERVAL 1000 /* in usec */
+
+static struct mcryptd_alg_state sha512_mb_alg_state;
+
+struct sha512_mb_ctx {
+	struct mcryptd_ahash *mcryptd_tfm;
+};
+
+static inline struct mcryptd_hash_request_ctx
+		*cast_hash_to_mcryptd_ctx(struct sha512_hash_ctx *hash_ctx)
+{
+	struct ahash_request *areq;
+
+	areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
+	return container_of(areq, struct mcryptd_hash_request_ctx, areq);
+}
+
+static inline struct ahash_request
+		*cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
+{
+	return container_of((void *) ctx, struct ahash_request, __ctx);
+}
+
+static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
+				struct ahash_request *areq)
+{
+	rctx->flag = HASH_UPDATE;
+}
+
+static asmlinkage void (*sha512_job_mgr_init)(struct sha512_mb_mgr *state);
+static asmlinkage struct job_sha512* (*sha512_job_mgr_submit)
+						(struct sha512_mb_mgr *state,
+						struct job_sha512 *job);
+static asmlinkage struct job_sha512* (*sha512_job_mgr_flush)
+						(struct sha512_mb_mgr *state);
+static asmlinkage struct job_sha512* (*sha512_job_mgr_get_comp_job)
+						(struct sha512_mb_mgr *state);
+
+inline void sha512_init_digest(uint64_t *digest)
+{
+	static const uint64_t initial_digest[SHA512_DIGEST_LENGTH] = {
+					SHA512_H0, SHA512_H1, SHA512_H2,
+					SHA512_H3, SHA512_H4, SHA512_H5,
+					SHA512_H6, SHA512_H7 };
+	memcpy(digest, initial_digest, sizeof(initial_digest));
+}
+
+inline uint32_t sha512_pad(uint8_t padblock[SHA512_BLOCK_SIZE * 2],
+			 uint32_t total_len)
+{
+	uint32_t i = total_len & (SHA512_BLOCK_SIZE - 1);
+
+	memset(&padblock[i], 0, SHA512_BLOCK_SIZE);
+	padblock[i] = 0x80;
+
+	i += ((SHA512_BLOCK_SIZE - 1) &
+	      (0 - (total_len + SHA512_PADLENGTHFIELD_SIZE + 1)))
+	     + 1 + SHA512_PADLENGTHFIELD_SIZE;
+
+#if SHA512_PADLENGTHFIELD_SIZE == 16
+	*((uint64_t *) &padblock[i - 16]) = 0;
+#endif
+
+	*((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
+
+	/* Number of extra blocks to hash */
+	return i >> SHA512_LOG2_BLOCK_SIZE;
+}
+
+static struct sha512_hash_ctx *sha512_ctx_mgr_resubmit
+		(struct sha512_ctx_mgr *mgr, struct sha512_hash_ctx *ctx)
+{
+	while (ctx) {
+		if (ctx->status & HASH_CTX_STS_COMPLETE) {
+			/* Clear PROCESSING bit */
+			ctx->status = HASH_CTX_STS_COMPLETE;
+			return ctx;
+		}
+
+		/*
+		 * If the extra blocks are empty, begin hashing what remains
+		 * in the user's buffer.
+		 */
+		if (ctx->partial_block_buffer_length == 0 &&
+		    ctx->incoming_buffer_length) {
+
+			const void *buffer = ctx->incoming_buffer;
+			uint32_t len = ctx->incoming_buffer_length;
+			uint32_t copy_len;
+
+			/*
+			 * Only entire blocks can be hashed.
+			 * Copy remainder to extra blocks buffer.
+			 */
+			copy_len = len & (SHA512_BLOCK_SIZE-1);
+
+			if (copy_len) {
+				len -= copy_len;
+				memcpy(ctx->partial_block_buffer,
+				       ((const char *) buffer + len),
+				       copy_len);
+				ctx->partial_block_buffer_length = copy_len;
+			}
+
+			ctx->incoming_buffer_length = 0;
+
+			/* len should be a multiple of the block size now */
+			assert((len % SHA512_BLOCK_SIZE) == 0);
+
+			/* Set len to the number of blocks to be hashed */
+			len >>= SHA512_LOG2_BLOCK_SIZE;
+
+			if (len) {
+
+				ctx->job.buffer = (uint8_t *) buffer;
+				ctx->job.len = len;
+				ctx = (struct sha512_hash_ctx *)
+					sha512_job_mgr_submit(&mgr->mgr,
+					&ctx->job);
+				continue;
+			}
+		}
+
+		/*
+		 * If the extra blocks are not empty, then we are
+		 * either on the last block(s) or we need more
+		 * user input before continuing.
+		 */
+		if (ctx->status & HASH_CTX_STS_LAST) {
+
+			uint8_t *buf = ctx->partial_block_buffer;
+			uint32_t n_extra_blocks =
+					sha512_pad(buf, ctx->total_length);
+
+			ctx->status = (HASH_CTX_STS_PROCESSING |
+				       HASH_CTX_STS_COMPLETE);
+			ctx->job.buffer = buf;
+			ctx->job.len = (uint32_t) n_extra_blocks;
+			ctx = (struct sha512_hash_ctx *)
+				sha512_job_mgr_submit(&mgr->mgr, &ctx->job);
+			continue;
+		}
+
+		if (ctx)
+			ctx->status = HASH_CTX_STS_IDLE;
+		return ctx;
+	}
+
+	return NULL;
+}
+
+static struct sha512_hash_ctx
+		*sha512_ctx_mgr_get_comp_ctx(struct sha512_ctx_mgr *mgr)
+{
+	/*
+	 * If get_comp_job returns NULL, there are no jobs complete.
+	 * If get_comp_job returns a job, verify that it is safe to return to
+	 * the user.
+	 * If it is not ready, resubmit the job to finish processing.
+	 * If sha512_ctx_mgr_resubmit returned a job, it is ready to be
+	 * returned.
+	 * Otherwise, all jobs currently being managed by the hash_ctx_mgr
+	 * still need processing.
+	 */
+	struct sha512_hash_ctx *ctx;
+
+	ctx = (struct sha512_hash_ctx *)
+				sha512_job_mgr_get_comp_job(&mgr->mgr);
+	return sha512_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static void sha512_ctx_mgr_init(struct sha512_ctx_mgr *mgr)
+{
+	sha512_job_mgr_init(&mgr->mgr);
+}
+
+static struct sha512_hash_ctx
+			*sha512_ctx_mgr_submit(struct sha512_ctx_mgr *mgr,
+					  struct sha512_hash_ctx *ctx,
+					  const void *buffer,
+					  uint32_t len,
+					  int flags)
+{
+	if (flags & (~HASH_ENTIRE)) {
+		/*
+		 * User should not pass anything other than FIRST, UPDATE, or
+		 * LAST
+		 */
+		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
+		return ctx;
+	}
+
+	if (ctx->status & HASH_CTX_STS_PROCESSING) {
+		/* Cannot submit to a currently processing job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
+		return ctx;
+	}
+
+	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+		/* Cannot update a finished job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
+		return ctx;
+	}
+
+
+	if (flags & HASH_FIRST) {
+		/* Init digest */
+		sha512_init_digest(ctx->job.result_digest);
+
+		/* Reset byte counter */
+		ctx->total_length = 0;
+
+		/* Clear extra blocks */
+		ctx->partial_block_buffer_length = 0;
+	}
+
+	/*
+	 * If we made it here, there were no errors during this call to
+	 * submit
+	 */
+	ctx->error = HASH_CTX_ERROR_NONE;
+
+	/* Store buffer ptr info from user */
+	ctx->incoming_buffer = buffer;
+	ctx->incoming_buffer_length = len;
+
+	/*
+	 * Store the user's request flags and mark this ctx as currently being
+	 * processed.
+	 */
+	ctx->status = (flags & HASH_LAST) ?
+			(HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
+			HASH_CTX_STS_PROCESSING;
+
+	/* Advance byte counter */
+	ctx->total_length += len;
+
+	/*
+	 * If there is anything currently buffered in the extra blocks,
+	 * append to it until it contains a whole block.
+	 * Or if the user's buffer contains less than a whole block,
+	 * append as much as possible to the extra block.
+	 */
+	if (ctx->partial_block_buffer_length || len < SHA512_BLOCK_SIZE) {
+		/* Compute how many bytes to copy from user buffer into extra
+		 * block
+		 */
+		uint32_t copy_len = SHA512_BLOCK_SIZE -
+					ctx->partial_block_buffer_length;
+		if (len < copy_len)
+			copy_len = len;
+
+		if (copy_len) {
+			/* Copy and update relevant pointers and counters */
+			memcpy
+		(&ctx->partial_block_buffer[ctx->partial_block_buffer_length],
+				buffer, copy_len);
+
+			ctx->partial_block_buffer_length += copy_len;
+			ctx->incoming_buffer = (const void *)
+					((const char *)buffer + copy_len);
+			ctx->incoming_buffer_length = len - copy_len;
+		}
+
+		/* The extra block should never contain more than 1 block
+		 * here
+		 */
+		assert(ctx->partial_block_buffer_length <= SHA512_BLOCK_SIZE);
+
+		/* If the extra block buffer contains exactly 1 block, it can
+		 * be hashed.
+		 */
+		if (ctx->partial_block_buffer_length >= SHA512_BLOCK_SIZE) {
+			ctx->partial_block_buffer_length = 0;
+
+			ctx->job.buffer = ctx->partial_block_buffer;
+			ctx->job.len = 1;
+			ctx = (struct sha512_hash_ctx *)
+				sha512_job_mgr_submit(&mgr->mgr, &ctx->job);
+		}
+	}
+
+	return sha512_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static struct sha512_hash_ctx *sha512_ctx_mgr_flush(struct sha512_ctx_mgr *mgr)
+{
+	struct sha512_hash_ctx *ctx;
+
+	while (1) {
+		ctx = (struct sha512_hash_ctx *)
+					sha512_job_mgr_flush(&mgr->mgr);
+
+		/* If flush returned 0, there are no more jobs in flight. */
+		if (!ctx)
+			return NULL;
+
+		/*
+		 * If flush returned a job, resubmit the job to finish
+		 * processing.
+		 */
+		ctx = sha512_ctx_mgr_resubmit(mgr, ctx);
+
+		/*
+		 * If sha512_ctx_mgr_resubmit returned a job, it is ready to
+		 * be returned. Otherwise, all jobs currently being managed by
+		 * the sha512_ctx_mgr still need processing. Loop.
+		 */
+		if (ctx)
+			return ctx;
+	}
+}
+
+static int sha512_mb_init(struct ahash_request *areq)
+{
+	struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	hash_ctx_init(sctx);
+	sctx->job.result_digest[0] = SHA512_H0;
+	sctx->job.result_digest[1] = SHA512_H1;
+	sctx->job.result_digest[2] = SHA512_H2;
+	sctx->job.result_digest[3] = SHA512_H3;
+	sctx->job.result_digest[4] = SHA512_H4;
+	sctx->job.result_digest[5] = SHA512_H5;
+	sctx->job.result_digest[6] = SHA512_H6;
+	sctx->job.result_digest[7] = SHA512_H7;
+	sctx->total_length = 0;
+	sctx->partial_block_buffer_length = 0;
+	sctx->status = HASH_CTX_STS_IDLE;
+
+	return 0;
+}
+
+static int sha512_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
+{
+	int	i;
+	struct	sha512_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
+	__be64	*dst = (__be64 *) rctx->out;
+
+	for (i = 0; i < 8; ++i)
+		dst[i] = cpu_to_be64(sctx->job.result_digest[i]);
+
+	return 0;
+}
+
+static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
+			struct mcryptd_alg_cstate *cstate, bool flush)
+{
+	int	flag = HASH_UPDATE;
+	int	nbytes, err = 0;
+	struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
+	struct sha512_hash_ctx *sha_ctx;
+
+	/* more work ? */
+	while (!(rctx->flag & HASH_DONE)) {
+		nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
+		if (nbytes < 0) {
+			err = nbytes;
+			goto out;
+		}
+		/* check if the walk is done */
+		if (crypto_ahash_walk_last(&rctx->walk)) {
+			rctx->flag |= HASH_DONE;
+			if (rctx->flag & HASH_FINAL)
+				flag |= HASH_LAST;
+
+		}
+		sha_ctx = (struct sha512_hash_ctx *)
+						ahash_request_ctx(&rctx->areq);
+		kernel_fpu_begin();
+		sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx,
+						rctx->walk.data, nbytes, flag);
+		if (!sha_ctx) {
+			if (flush)
+				sha_ctx = sha512_ctx_mgr_flush(cstate->mgr);
+		}
+		kernel_fpu_end();
+		if (sha_ctx)
+			rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		else {
+			rctx = NULL;
+			goto out;
+		}
+	}
+
+	/* copy the results */
+	if (rctx->flag & HASH_FINAL)
+		sha512_mb_set_results(rctx);
+
+out:
+	*ret_rctx = rctx;
+	return err;
+}
+
+static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
+			    struct mcryptd_alg_cstate *cstate,
+			    int err)
+{
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha512_hash_ctx *sha_ctx;
+	struct mcryptd_hash_request_ctx *req_ctx;
+	int ret;
+
+	/* remove from work list */
+	spin_lock(&cstate->work_lock);
+	list_del(&rctx->waiter);
+	spin_unlock(&cstate->work_lock);
+
+	if (irqs_disabled())
+		rctx->complete(&req->base, err);
+	else {
+		local_bh_disable();
+		rctx->complete(&req->base, err);
+		local_bh_enable();
+	}
+
+	/* check to see if there are other jobs that are done */
+	sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate->mgr);
+	while (sha_ctx) {
+		req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		ret = sha_finish_walk(&req_ctx, cstate, false);
+		if (req_ctx) {
+			spin_lock(&cstate->work_lock);
+			list_del(&req_ctx->waiter);
+			spin_unlock(&cstate->work_lock);
+
+			req = cast_mcryptd_ctx_to_req(req_ctx);
+			if (irqs_disabled())
+				rctx->complete(&req->base, ret);
+			else {
+				local_bh_disable();
+				rctx->complete(&req->base, ret);
+				local_bh_enable();
+			}
+		}
+		sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate->mgr);
+	}
+
+	return 0;
+}
+
+static void sha512_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
+			     struct mcryptd_alg_cstate *cstate)
+{
+	unsigned long next_flush;
+	unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
+
+	/* initialize tag */
+	rctx->tag.arrival = jiffies;    /* tag the arrival time */
+	rctx->tag.seq_num = cstate->next_seq_num++;
+	next_flush = rctx->tag.arrival + delay;
+	rctx->tag.expire = next_flush;
+
+	spin_lock(&cstate->work_lock);
+	list_add_tail(&rctx->waiter, &cstate->work_list);
+	spin_unlock(&cstate->work_lock);
+
+	mcryptd_arm_flusher(cstate, delay);
+}
+
+static int sha512_mb_update(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+									areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha512_hash_ctx *sha_ctx;
+	int ret = 0, nbytes;
+
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk))
+		rctx->flag |= HASH_DONE;
+
+	/* submit */
+	sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
+	sha512_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+							nbytes, HASH_UPDATE);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha512_mb_finup(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+									areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha512_hash_ctx *sha_ctx;
+	int ret = 0, flag = HASH_UPDATE, nbytes;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk)) {
+		rctx->flag |= HASH_DONE;
+		flag = HASH_LAST;
+	}
+
+	/* submit */
+	rctx->flag |= HASH_FINAL;
+	sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
+	sha512_mb_add_list(rctx, cstate);
+
+	kernel_fpu_begin();
+	sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+								nbytes, flag);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha512_mb_final(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+									areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
+
+	struct sha512_hash_ctx *sha_ctx;
+	int ret = 0;
+	u8 data;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	rctx->flag |= HASH_DONE | HASH_FINAL;
+
+	sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
+	/* flag HASH_FINAL and 0 data size */
+	sha512_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
+								HASH_LAST);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha512_mb_export(struct ahash_request *areq, void *out)
+{
+	struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_mb_import(struct ahash_request *areq, const void *in)
+{
+	struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_mb_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct mcryptd_ahash *mcryptd_tfm;
+	struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mcryptd_hash_ctx *mctx;
+
+	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha512-mb",
+						CRYPTO_ALG_INTERNAL,
+						CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(mcryptd_tfm))
+		return PTR_ERR(mcryptd_tfm);
+	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
+	mctx->alg_state = &sha512_mb_alg_state;
+	ctx->mcryptd_tfm = mcryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				crypto_ahash_reqsize(&mcryptd_tfm->base));
+
+	return 0;
+}
+
+static void sha512_mb_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static int sha512_mb_areq_init_tfm(struct crypto_tfm *tfm)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				sizeof(struct sha512_hash_ctx));
+
+	return 0;
+}
+
+static void sha512_mb_areq_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static struct ahash_alg sha512_mb_areq_alg = {
+	.init		=	sha512_mb_init,
+	.update		=	sha512_mb_update,
+	.final		=	sha512_mb_final,
+	.finup		=	sha512_mb_finup,
+	.export		=	sha512_mb_export,
+	.import		=	sha512_mb_import,
+	.halg		=	{
+	.digestsize	=	SHA512_DIGEST_SIZE,
+	.statesize	=	sizeof(struct sha512_hash_ctx),
+	.base		=	{
+			.cra_name	 = "__sha512-mb",
+			.cra_driver_name = "__intel_sha512-mb",
+			.cra_priority	 = 100,
+			/*
+			 * use ASYNC flag as some buffers in multi-buffer
+			 * algo may not have completed before hashing thread
+			 * sleep
+			 */
+			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_INTERNAL,
+			.cra_blocksize	= SHA512_BLOCK_SIZE,
+			.cra_module	= THIS_MODULE,
+			.cra_list	= LIST_HEAD_INIT
+					(sha512_mb_areq_alg.halg.base.cra_list),
+			.cra_init	= sha512_mb_areq_init_tfm,
+			.cra_exit	= sha512_mb_areq_exit_tfm,
+			.cra_ctxsize	= sizeof(struct sha512_hash_ctx),
+		}
+	}
+};
+
+static int sha512_mb_async_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_init(mcryptd_req);
+}
+
+static int sha512_mb_async_update(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_update(mcryptd_req);
+}
+
+static int sha512_mb_async_finup(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_finup(mcryptd_req);
+}
+
+static int sha512_mb_async_final(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_final(mcryptd_req);
+}
+
+static int sha512_mb_async_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_digest(mcryptd_req);
+}
+
+static int sha512_mb_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_export(mcryptd_req, out);
+}
+
+static int sha512_mb_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+	struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
+	struct mcryptd_hash_request_ctx *rctx;
+	struct ahash_request *areq;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	rctx = ahash_request_ctx(mcryptd_req);
+
+	areq = &rctx->areq;
+
+	ahash_request_set_tfm(areq, child);
+	ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
+					rctx->complete, req);
+
+	return crypto_ahash_import(mcryptd_req, in);
+}
+
+static struct ahash_alg sha512_mb_async_alg = {
+	.init           = sha512_mb_async_init,
+	.update         = sha512_mb_async_update,
+	.final          = sha512_mb_async_final,
+	.finup          = sha512_mb_async_finup,
+	.digest         = sha512_mb_async_digest,
+	.export		= sha512_mb_async_export,
+	.import		= sha512_mb_async_import,
+	.halg = {
+		.digestsize     = SHA512_DIGEST_SIZE,
+		.statesize      = sizeof(struct sha512_hash_ctx),
+		.base = {
+			.cra_name               = "sha512",
+			.cra_driver_name        = "sha512_mb",
+			.cra_priority           = 200,
+			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
+							CRYPTO_ALG_ASYNC,
+			.cra_blocksize          = SHA512_BLOCK_SIZE,
+			.cra_type               = &crypto_ahash_type,
+			.cra_module             = THIS_MODULE,
+			.cra_list               = LIST_HEAD_INIT
+				(sha512_mb_async_alg.halg.base.cra_list),
+			.cra_init               = sha512_mb_async_init_tfm,
+			.cra_exit               = sha512_mb_async_exit_tfm,
+			.cra_ctxsize		= sizeof(struct sha512_mb_ctx),
+			.cra_alignmask		= 0,
+		},
+	},
+};
+
+static unsigned long sha512_mb_flusher(struct mcryptd_alg_cstate *cstate)
+{
+	struct mcryptd_hash_request_ctx *rctx;
+	unsigned long cur_time;
+	unsigned long next_flush = 0;
+	struct sha512_hash_ctx *sha_ctx;
+
+
+	cur_time = jiffies;
+
+	while (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		if time_before(cur_time, rctx->tag.expire)
+			break;
+		kernel_fpu_begin();
+		sha_ctx = (struct sha512_hash_ctx *)
+					sha512_ctx_mgr_flush(cstate->mgr);
+		kernel_fpu_end();
+		if (!sha_ctx) {
+			pr_err("sha512_mb error: nothing got flushed for"
+							" non-empty list\n");
+			break;
+		}
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		sha_finish_walk(&rctx, cstate, true);
+		sha_complete_job(rctx, cstate, 0);
+	}
+
+	if (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		/* get the hash context and then flush time */
+		next_flush = rctx->tag.expire;
+		mcryptd_arm_flusher(cstate, get_delay(next_flush));
+	}
+	return next_flush;
+}
+
+static int __init sha512_mb_mod_init(void)
+{
+
+	int cpu;
+	int err;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	/* check for dependent cpu features */
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_BMI2))
+		return -ENODEV;
+
+	/* initialize multibuffer structures */
+	sha512_mb_alg_state.alg_cstate =
+				alloc_percpu(struct mcryptd_alg_cstate);
+
+	sha512_job_mgr_init = sha512_mb_mgr_init_avx2;
+	sha512_job_mgr_submit = sha512_mb_mgr_submit_avx2;
+	sha512_job_mgr_flush = sha512_mb_mgr_flush_avx2;
+	sha512_job_mgr_get_comp_job = sha512_mb_mgr_get_comp_job_avx2;
+
+	if (!sha512_mb_alg_state.alg_cstate)
+		return -ENOMEM;
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
+		cpu_state->next_flush = 0;
+		cpu_state->next_seq_num = 0;
+		cpu_state->flusher_engaged = false;
+		INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
+		cpu_state->cpu = cpu;
+		cpu_state->alg_state = &sha512_mb_alg_state;
+		cpu_state->mgr = kzalloc(sizeof(struct sha512_ctx_mgr),
+								GFP_KERNEL);
+		if (!cpu_state->mgr)
+			goto err2;
+		sha512_ctx_mgr_init(cpu_state->mgr);
+		INIT_LIST_HEAD(&cpu_state->work_list);
+		spin_lock_init(&cpu_state->work_lock);
+	}
+	sha512_mb_alg_state.flusher = &sha512_mb_flusher;
+
+	err = crypto_register_ahash(&sha512_mb_areq_alg);
+	if (err)
+		goto err2;
+	err = crypto_register_ahash(&sha512_mb_async_alg);
+	if (err)
+		goto err1;
+
+
+	return 0;
+err1:
+	crypto_unregister_ahash(&sha512_mb_areq_alg);
+err2:
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha512_mb_alg_state.alg_cstate);
+	return -ENODEV;
+}
+
+static void __exit sha512_mb_mod_fini(void)
+{
+	int cpu;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	crypto_unregister_ahash(&sha512_mb_async_alg);
+	crypto_unregister_ahash(&sha512_mb_areq_alg);
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha512_mb_alg_state.alg_cstate);
+}
+
+module_init(sha512_mb_mod_init);
+module_exit(sha512_mb_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, multi buffer accelerated");
+
+MODULE_ALIAS("sha512");
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h b/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
new file mode 100644
index 000000000000..9d4b2c8208d5
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
@@ -0,0 +1,130 @@
+/*
+ * Header file for multi buffer SHA512 context
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _SHA_MB_CTX_INTERNAL_H
+#define _SHA_MB_CTX_INTERNAL_H
+
+#include "sha512_mb_mgr.h"
+
+#define HASH_UPDATE          0x00
+#define HASH_FIRST           0x01
+#define HASH_LAST            0x02
+#define HASH_ENTIRE          0x03
+#define HASH_DONE            0x04
+#define HASH_FINAL           0x08
+
+#define HASH_CTX_STS_IDLE       0x00
+#define HASH_CTX_STS_PROCESSING 0x01
+#define HASH_CTX_STS_LAST       0x02
+#define HASH_CTX_STS_COMPLETE   0x04
+
+enum hash_ctx_error {
+	HASH_CTX_ERROR_NONE               =  0,
+	HASH_CTX_ERROR_INVALID_FLAGS      = -1,
+	HASH_CTX_ERROR_ALREADY_PROCESSING = -2,
+	HASH_CTX_ERROR_ALREADY_COMPLETED  = -3,
+};
+
+#define hash_ctx_user_data(ctx)  ((ctx)->user_data)
+#define hash_ctx_digest(ctx)     ((ctx)->job.result_digest)
+#define hash_ctx_processing(ctx) ((ctx)->status & HASH_CTX_STS_PROCESSING)
+#define hash_ctx_complete(ctx)   ((ctx)->status == HASH_CTX_STS_COMPLETE)
+#define hash_ctx_status(ctx)     ((ctx)->status)
+#define hash_ctx_error(ctx)      ((ctx)->error)
+#define hash_ctx_init(ctx) \
+	do { \
+		(ctx)->error = HASH_CTX_ERROR_NONE; \
+		(ctx)->status = HASH_CTX_STS_COMPLETE; \
+	} while (0)
+
+/* Hash Constants and Typedefs */
+#define SHA512_DIGEST_LENGTH          8
+#define SHA512_LOG2_BLOCK_SIZE        7
+
+#define SHA512_PADLENGTHFIELD_SIZE    16
+
+#ifdef SHA_MB_DEBUG
+#define assert(expr) \
+do { \
+	if (unlikely(!(expr))) { \
+		printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \
+		#expr, __FILE__, __func__, __LINE__); \
+	} \
+} while (0)
+#else
+#define assert(expr) do {} while (0)
+#endif
+
+struct sha512_ctx_mgr {
+	struct sha512_mb_mgr mgr;
+};
+
+/* typedef struct sha512_ctx_mgr sha512_ctx_mgr; */
+
+struct sha512_hash_ctx {
+	/* Must be at struct offset 0 */
+	struct job_sha512       job;
+	/* status flag */
+	int status;
+	/* error flag */
+	int error;
+
+	uint32_t        total_length;
+	const void      *incoming_buffer;
+	uint32_t        incoming_buffer_length;
+	uint8_t         partial_block_buffer[SHA512_BLOCK_SIZE * 2];
+	uint32_t        partial_block_buffer_length;
+	void            *user_data;
+};
+
+#endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h b/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h
new file mode 100644
index 000000000000..178f17eef382
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h
@@ -0,0 +1,104 @@
+/*
+ * Header file for multi buffer SHA512 algorithm manager
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __SHA_MB_MGR_H
+#define __SHA_MB_MGR_H
+
+#include <linux/types.h>
+
+#define NUM_SHA512_DIGEST_WORDS 8
+
+enum job_sts {STS_UNKNOWN = 0,
+	STS_BEING_PROCESSED = 1,
+	STS_COMPLETED =       2,
+	STS_INTERNAL_ERROR = 3,
+	STS_ERROR = 4
+};
+
+struct job_sha512 {
+	u8  *buffer;
+	u64  len;
+	u64  result_digest[NUM_SHA512_DIGEST_WORDS] __aligned(32);
+	enum job_sts status;
+	void   *user_data;
+};
+
+struct sha512_args_x4 {
+	uint64_t        digest[8][4];
+	uint8_t         *data_ptr[4];
+};
+
+struct sha512_lane_data {
+	struct job_sha512 *job_in_lane;
+};
+
+struct sha512_mb_mgr {
+	struct sha512_args_x4 args;
+
+	uint64_t lens[4];
+
+	/* each byte is index (0...7) of unused lanes */
+	uint64_t unused_lanes;
+	/* byte 4 is set to FF as a flag */
+	struct sha512_lane_data ldata[4];
+};
+
+#define SHA512_MB_MGR_NUM_LANES_AVX2 4
+
+void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state);
+struct job_sha512 *sha512_mb_mgr_submit_avx2(struct sha512_mb_mgr *state,
+						struct job_sha512 *job);
+struct job_sha512 *sha512_mb_mgr_flush_avx2(struct sha512_mb_mgr *state);
+struct job_sha512 *sha512_mb_mgr_get_comp_job_avx2(struct sha512_mb_mgr *state);
+
+#endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S
new file mode 100644
index 000000000000..cf2636d4c9ba
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S
@@ -0,0 +1,281 @@
+/*
+ * Header file for multi buffer SHA256 algorithm data structure
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+# Macros for defining data structures
+
+# Usage example
+
+#START_FIELDS   # JOB_AES
+###     name            size    align
+#FIELD  _plaintext,     8,      8       # pointer to plaintext
+#FIELD  _ciphertext,    8,      8       # pointer to ciphertext
+#FIELD  _IV,            16,     8       # IV
+#FIELD  _keys,          8,      8       # pointer to keys
+#FIELD  _len,           4,      4       # length in bytes
+#FIELD  _status,        4,      4       # status enumeration
+#FIELD  _user_data,     8,      8       # pointer to user data
+#UNION  _union,         size1,  align1, \
+#                       size2,  align2, \
+#                       size3,  align3, \
+#                       ...
+#END_FIELDS
+#%assign _JOB_AES_size  _FIELD_OFFSET
+#%assign _JOB_AES_align _STRUCT_ALIGN
+
+#########################################################################
+
+# Alternate "struc-like" syntax:
+#       STRUCT job_aes2
+#       RES_Q   .plaintext,     1
+#       RES_Q   .ciphertext,    1
+#       RES_DQ  .IV,            1
+#       RES_B   .nested,        _JOB_AES_SIZE, _JOB_AES_ALIGN
+#       RES_U   .union,         size1, align1, \
+#                               size2, align2, \
+#                               ...
+#       ENDSTRUCT
+#       # Following only needed if nesting
+#       %assign job_aes2_size   _FIELD_OFFSET
+#       %assign job_aes2_align  _STRUCT_ALIGN
+#
+# RES_* macros take a name, a count and an optional alignment.
+# The count in in terms of the base size of the macro, and the
+# default alignment is the base size.
+# The macros are:
+# Macro    Base size
+# RES_B     1
+# RES_W     2
+# RES_D     4
+# RES_Q     8
+# RES_DQ   16
+# RES_Y    32
+# RES_Z    64
+#
+# RES_U defines a union. It's arguments are a name and two or more
+# pairs of "size, alignment"
+#
+# The two assigns are only needed if this structure is being nested
+# within another. Even if the assigns are not done, one can still use
+# STRUCT_NAME_size as the size of the structure.
+#
+# Note that for nesting, you still need to assign to STRUCT_NAME_size.
+#
+# The differences between this and using "struc" directly are that each
+# type is implicitly aligned to its natural length (although this can be
+# over-ridden with an explicit third parameter), and that the structure
+# is padded at the end to its overall alignment.
+#
+
+#########################################################################
+
+#ifndef _DATASTRUCT_ASM_
+#define _DATASTRUCT_ASM_
+
+#define PTR_SZ                  8
+#define SHA512_DIGEST_WORD_SIZE 8
+#define SHA512_MB_MGR_NUM_LANES_AVX2 4
+#define NUM_SHA512_DIGEST_WORDS 8
+#define SZ4                     4*SHA512_DIGEST_WORD_SIZE
+#define ROUNDS                  80*SZ4
+#define SHA512_DIGEST_ROW_SIZE  (SHA512_MB_MGR_NUM_LANES_AVX2 * 8)
+
+# START_FIELDS
+.macro START_FIELDS
+ _FIELD_OFFSET = 0
+ _STRUCT_ALIGN = 0
+.endm
+
+# FIELD name size align
+.macro FIELD name size align
+ _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
+ \name  = _FIELD_OFFSET
+ _FIELD_OFFSET = _FIELD_OFFSET + (\size)
+.if (\align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = \align
+.endif
+.endm
+
+# END_FIELDS
+.macro END_FIELDS
+ _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
+.endm
+
+.macro STRUCT p1
+START_FIELDS
+.struc \p1
+.endm
+
+.macro ENDSTRUCT
+ tmp = _FIELD_OFFSET
+ END_FIELDS
+ tmp = (_FIELD_OFFSET - ##tmp)
+.if (tmp > 0)
+        .lcomm  tmp
+.endm
+
+## RES_int name size align
+.macro RES_int p1 p2 p3
+ name = \p1
+ size = \p2
+ align = .\p3
+
+ _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
+.align align
+.lcomm name size
+ _FIELD_OFFSET = _FIELD_OFFSET + (size)
+.if (align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = align
+.endif
+.endm
+
+# macro RES_B name, size [, align]
+.macro RES_B _name, _size, _align=1
+RES_int _name _size _align
+.endm
+
+# macro RES_W name, size [, align]
+.macro RES_W _name, _size, _align=2
+RES_int _name 2*(_size) _align
+.endm
+
+# macro RES_D name, size [, align]
+.macro RES_D _name, _size, _align=4
+RES_int _name 4*(_size) _align
+.endm
+
+# macro RES_Q name, size [, align]
+.macro RES_Q _name, _size, _align=8
+RES_int _name 8*(_size) _align
+.endm
+
+# macro RES_DQ name, size [, align]
+.macro RES_DQ _name, _size, _align=16
+RES_int _name 16*(_size) _align
+.endm
+
+# macro RES_Y name, size [, align]
+.macro RES_Y _name, _size, _align=32
+RES_int _name 32*(_size) _align
+.endm
+
+# macro RES_Z name, size [, align]
+.macro RES_Z _name, _size, _align=64
+RES_int _name 64*(_size) _align
+.endm
+
+#endif
+
+###################################################################
+### Define SHA512 Out Of Order Data Structures
+###################################################################
+
+START_FIELDS    # LANE_DATA
+###     name            size    align
+FIELD   _job_in_lane,   8,      8       # pointer to job object
+END_FIELDS
+
+ _LANE_DATA_size = _FIELD_OFFSET
+ _LANE_DATA_align = _STRUCT_ALIGN
+
+####################################################################
+
+START_FIELDS    # SHA512_ARGS_X4
+###     name            size    align
+FIELD   _digest,        8*8*4,  4      # transposed digest
+FIELD   _data_ptr,      8*4,    8       # array of pointers to data
+END_FIELDS
+
+ _SHA512_ARGS_X4_size  =  _FIELD_OFFSET
+ _SHA512_ARGS_X4_align =  _STRUCT_ALIGN
+
+#####################################################################
+
+START_FIELDS    # MB_MGR
+###     name            size    align
+FIELD   _args,          _SHA512_ARGS_X4_size, _SHA512_ARGS_X4_align
+FIELD   _lens,          8*4,    8
+FIELD   _unused_lanes,  8,      8
+FIELD   _ldata,         _LANE_DATA_size*4, _LANE_DATA_align
+END_FIELDS
+
+ _MB_MGR_size  =  _FIELD_OFFSET
+ _MB_MGR_align =  _STRUCT_ALIGN
+
+_args_digest = _args + _digest
+_args_data_ptr = _args + _data_ptr
+
+#######################################################################
+
+#######################################################################
+#### Define constants
+#######################################################################
+
+#define STS_UNKNOWN             0
+#define STS_BEING_PROCESSED     1
+#define STS_COMPLETED           2
+
+#######################################################################
+#### Define JOB_SHA512 structure
+#######################################################################
+
+START_FIELDS    # JOB_SHA512
+###     name                            size    align
+FIELD   _buffer,                        8,      8       # pointer to buffer
+FIELD   _len,                           8,      8       # length in bytes
+FIELD   _result_digest,                 8*8,    32      # Digest (output)
+FIELD   _status,                        4,      4
+FIELD   _user_data,                     8,      8
+END_FIELDS
+
+ _JOB_SHA512_size = _FIELD_OFFSET
+ _JOB_SHA512_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S
new file mode 100644
index 000000000000..3ddba19a0db6
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S
@@ -0,0 +1,291 @@
+/*
+ * Flush routine for SHA512 multibuffer
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha512_mb_mgr_datastruct.S"
+
+.extern sha512_x4_avx2
+
+# LINUX register definitions
+#define arg1    %rdi
+#define arg2    %rsi
+
+# idx needs to be other than arg1, arg2, rbx, r12
+#define idx     %rdx
+
+# Common definitions
+#define state   arg1
+#define job     arg2
+#define len2    arg2
+
+#define unused_lanes    %rbx
+#define lane_data       %rbx
+#define tmp2            %rbx
+
+#define job_rax         %rax
+#define tmp1            %rax
+#define size_offset     %rax
+#define tmp             %rax
+#define start_offset    %rax
+
+#define tmp3            arg1
+
+#define extra_blocks    arg2
+#define p               arg2
+
+#define tmp4            %r8
+#define lens0           %r8
+
+#define lens1           %r9
+#define lens2           %r10
+#define lens3           %r11
+
+.macro LABEL prefix n
+\prefix\n\():
+.endm
+
+.macro JNE_SKIP i
+jne     skip_\i
+.endm
+
+.altmacro
+.macro SET_OFFSET _offset
+offset = \_offset
+.endm
+.noaltmacro
+
+# JOB* sha512_mb_mgr_flush_avx2(MB_MGR *state)
+# arg 1 : rcx : state
+ENTRY(sha512_mb_mgr_flush_avx2)
+	FRAME_BEGIN
+	push	%rbx
+
+	# If bit (32+3) is set, then all lanes are empty
+	mov     _unused_lanes(state), unused_lanes
+        bt      $32+7, unused_lanes
+        jc      return_null
+
+        # find a lane with a non-null job
+	xor     idx, idx
+        offset = (_ldata + 1*_LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+        cmovne  one(%rip), idx
+        offset = (_ldata + 2*_LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+        cmovne  two(%rip), idx
+        offset = (_ldata + 3*_LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+        cmovne  three(%rip), idx
+
+        # copy idx to empty lanes
+copy_lane_data:
+	offset =  (_args + _data_ptr)
+        mov     offset(state,idx,8), tmp
+
+        I = 0
+.rep 4
+	offset =  (_ldata + I * _LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+.altmacro
+        JNE_SKIP %I
+        offset =  (_args + _data_ptr + 8*I)
+        mov     tmp, offset(state)
+        offset =  (_lens + 8*I +4)
+        movl    $0xFFFFFFFF, offset(state)
+LABEL skip_ %I
+        I = (I+1)
+.noaltmacro
+.endr
+
+        # Find min length
+        mov     _lens + 0*8(state),lens0
+        mov     lens0,idx
+        mov     _lens + 1*8(state),lens1
+        cmp     idx,lens1
+        cmovb   lens1,idx
+        mov     _lens + 2*8(state),lens2
+        cmp     idx,lens2
+        cmovb   lens2,idx
+        mov     _lens + 3*8(state),lens3
+        cmp     idx,lens3
+        cmovb   lens3,idx
+        mov     idx,len2
+        and     $0xF,idx
+        and     $~0xFF,len2
+	jz      len_is_0
+
+        sub     len2, lens0
+        sub     len2, lens1
+        sub     len2, lens2
+        sub     len2, lens3
+        shr     $32,len2
+        mov     lens0, _lens + 0*8(state)
+        mov     lens1, _lens + 1*8(state)
+        mov     lens2, _lens + 2*8(state)
+        mov     lens3, _lens + 3*8(state)
+
+        # "state" and "args" are the same address, arg1
+        # len is arg2
+        call    sha512_x4_avx2
+        # state and idx are intact
+
+len_is_0:
+        # process completed job "idx"
+	imul    $_LANE_DATA_size, idx, lane_data
+        lea     _ldata(state, lane_data), lane_data
+
+        mov     _job_in_lane(lane_data), job_rax
+        movq    $0,  _job_in_lane(lane_data)
+        movl    $STS_COMPLETED, _status(job_rax)
+        mov     _unused_lanes(state), unused_lanes
+        shl     $8, unused_lanes
+        or      idx, unused_lanes
+        mov     unused_lanes, _unused_lanes(state)
+
+	movl    $0xFFFFFFFF, _lens+4(state,  idx, 8)
+
+	vmovq _args_digest+0*32(state, idx, 8), %xmm0
+        vpinsrq $1, _args_digest+1*32(state, idx, 8), %xmm0, %xmm0
+	vmovq _args_digest+2*32(state, idx, 8), %xmm1
+        vpinsrq $1, _args_digest+3*32(state, idx, 8), %xmm1, %xmm1
+	vmovq _args_digest+4*32(state, idx, 8), %xmm2
+        vpinsrq $1, _args_digest+5*32(state, idx, 8), %xmm2, %xmm2
+	vmovq _args_digest+6*32(state, idx, 8), %xmm3
+	vpinsrq $1, _args_digest+7*32(state, idx, 8), %xmm3, %xmm3
+
+	vmovdqu %xmm0, _result_digest(job_rax)
+	vmovdqu %xmm1, _result_digest+1*16(job_rax)
+	vmovdqu %xmm2, _result_digest+2*16(job_rax)
+	vmovdqu %xmm3, _result_digest+3*16(job_rax)
+
+return:
+	pop	%rbx
+	FRAME_END
+        ret
+
+return_null:
+        xor     job_rax, job_rax
+        jmp     return
+ENDPROC(sha512_mb_mgr_flush_avx2)
+.align 16
+
+ENTRY(sha512_mb_mgr_get_comp_job_avx2)
+        push    %rbx
+
+	mov     _unused_lanes(state), unused_lanes
+        bt      $(32+7), unused_lanes
+        jc      .return_null
+
+        # Find min length
+        mov     _lens(state),lens0
+        mov     lens0,idx
+        mov     _lens+1*8(state),lens1
+        cmp     idx,lens1
+        cmovb   lens1,idx
+        mov     _lens+2*8(state),lens2
+        cmp     idx,lens2
+        cmovb   lens2,idx
+        mov     _lens+3*8(state),lens3
+        cmp     idx,lens3
+        cmovb   lens3,idx
+        test    $~0xF,idx
+        jnz     .return_null
+        and     $0xF,idx
+
+        #process completed job "idx"
+	imul    $_LANE_DATA_size, idx, lane_data
+        lea     _ldata(state, lane_data), lane_data
+
+        mov     _job_in_lane(lane_data), job_rax
+        movq    $0,  _job_in_lane(lane_data)
+        movl    $STS_COMPLETED, _status(job_rax)
+        mov     _unused_lanes(state), unused_lanes
+        shl     $8, unused_lanes
+        or      idx, unused_lanes
+        mov     unused_lanes, _unused_lanes(state)
+
+        movl    $0xFFFFFFFF, _lens+4(state,  idx, 8)
+
+	vmovq   _args_digest(state, idx, 8), %xmm0
+        vpinsrq $1, _args_digest+1*32(state, idx, 8), %xmm0, %xmm0
+	vmovq    _args_digest+2*32(state, idx, 8), %xmm1
+        vpinsrq $1, _args_digest+3*32(state, idx, 8), %xmm1, %xmm1
+	vmovq    _args_digest+4*32(state, idx, 8), %xmm2
+        vpinsrq $1, _args_digest+5*32(state, idx, 8), %xmm2, %xmm2
+        vmovq    _args_digest+6*32(state, idx, 8), %xmm3
+        vpinsrq $1, _args_digest+7*32(state, idx, 8), %xmm3, %xmm3
+
+	vmovdqu %xmm0, _result_digest+0*16(job_rax)
+	vmovdqu %xmm1, _result_digest+1*16(job_rax)
+	vmovdqu %xmm2, _result_digest+2*16(job_rax)
+	vmovdqu %xmm3, _result_digest+3*16(job_rax)
+
+	pop     %rbx
+
+        ret
+
+.return_null:
+        xor     job_rax, job_rax
+	pop     %rbx
+        ret
+ENDPROC(sha512_mb_mgr_get_comp_job_avx2)
+.data
+
+.align 16
+one:
+.quad  1
+two:
+.quad  2
+three:
+.quad  3
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
new file mode 100644
index 000000000000..36870b26067a
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
@@ -0,0 +1,67 @@
+/*
+ * Initialization code for multi buffer SHA256 algorithm for AVX2
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "sha512_mb_mgr.h"
+
+void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state)
+{
+	unsigned int j;
+
+	state->lens[0] = 0;
+	state->lens[1] = 1;
+	state->lens[2] = 2;
+	state->lens[3] = 3;
+	state->unused_lanes = 0xFF03020100;
+	for (j = 0; j < 4; j++)
+		state->ldata[j].job_in_lane = NULL;
+}
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S
new file mode 100644
index 000000000000..815f07bdd1f8
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S
@@ -0,0 +1,222 @@
+/*
+ * Buffer submit code for multi buffer SHA512 algorithm
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha512_mb_mgr_datastruct.S"
+
+.extern sha512_x4_avx2
+
+#define arg1    %rdi
+#define arg2    %rsi
+
+#define idx             %rdx
+#define last_len        %rdx
+
+#define size_offset     %rcx
+#define tmp2            %rcx
+
+# Common definitions
+#define state   arg1
+#define job     arg2
+#define len2    arg2
+#define p2      arg2
+
+#define p               %r11
+#define start_offset    %r11
+
+#define unused_lanes    %rbx
+
+#define job_rax         %rax
+#define len             %rax
+
+#define lane            %r12
+#define tmp3            %r12
+#define lens3           %r12
+
+#define extra_blocks    %r8
+#define lens0           %r8
+
+#define tmp             %r9
+#define lens1           %r9
+
+#define lane_data       %r10
+#define lens2           %r10
+
+#define DWORD_len %eax
+
+# JOB* sha512_mb_mgr_submit_avx2(MB_MGR *state, JOB *job)
+# arg 1 : rcx : state
+# arg 2 : rdx : job
+ENTRY(sha512_mb_mgr_submit_avx2)
+	FRAME_BEGIN
+	push	%rbx
+	push	%r12
+
+        mov     _unused_lanes(state), unused_lanes
+        movzb     %bl,lane
+        shr     $8, unused_lanes
+        imul    $_LANE_DATA_size, lane,lane_data
+        movl    $STS_BEING_PROCESSED, _status(job)
+	lea     _ldata(state, lane_data), lane_data
+        mov     unused_lanes, _unused_lanes(state)
+        movl    _len(job),  DWORD_len
+
+	mov     job, _job_in_lane(lane_data)
+        movl    DWORD_len,_lens+4(state , lane, 8)
+
+	# Load digest words from result_digest
+	vmovdqu	_result_digest+0*16(job), %xmm0
+	vmovdqu _result_digest+1*16(job), %xmm1
+	vmovdqu	_result_digest+2*16(job), %xmm2
+        vmovdqu	_result_digest+3*16(job), %xmm3
+
+	vmovq    %xmm0, _args_digest(state, lane, 8)
+	vpextrq  $1, %xmm0, _args_digest+1*32(state , lane, 8)
+	vmovq    %xmm1, _args_digest+2*32(state , lane, 8)
+	vpextrq  $1, %xmm1, _args_digest+3*32(state , lane, 8)
+	vmovq    %xmm2, _args_digest+4*32(state , lane, 8)
+	vpextrq  $1, %xmm2, _args_digest+5*32(state , lane, 8)
+	vmovq    %xmm3, _args_digest+6*32(state , lane, 8)
+	vpextrq  $1, %xmm3, _args_digest+7*32(state , lane, 8)
+
+	mov     _buffer(job), p
+	mov     p, _args_data_ptr(state, lane, 8)
+
+	cmp     $0xFF, unused_lanes
+	jne     return_null
+
+start_loop:
+
+	# Find min length
+	mov     _lens+0*8(state),lens0
+	mov     lens0,idx
+	mov     _lens+1*8(state),lens1
+	cmp     idx,lens1
+	cmovb   lens1, idx
+	mov     _lens+2*8(state),lens2
+	cmp     idx,lens2
+	cmovb   lens2,idx
+	mov     _lens+3*8(state),lens3
+	cmp     idx,lens3
+	cmovb   lens3,idx
+	mov     idx,len2
+	and     $0xF,idx
+	and     $~0xFF,len2
+	jz      len_is_0
+
+	sub     len2,lens0
+	sub     len2,lens1
+	sub     len2,lens2
+	sub     len2,lens3
+	shr     $32,len2
+	mov     lens0, _lens + 0*8(state)
+	mov     lens1, _lens + 1*8(state)
+	mov     lens2, _lens + 2*8(state)
+	mov     lens3, _lens + 3*8(state)
+
+	# "state" and "args" are the same address, arg1
+	# len is arg2
+	call    sha512_x4_avx2
+	# state and idx are intact
+
+len_is_0:
+
+	# process completed job "idx"
+	imul    $_LANE_DATA_size, idx, lane_data
+	lea     _ldata(state, lane_data), lane_data
+
+	mov     _job_in_lane(lane_data), job_rax
+	mov     _unused_lanes(state), unused_lanes
+	movq    $0, _job_in_lane(lane_data)
+	movl    $STS_COMPLETED, _status(job_rax)
+	shl     $8, unused_lanes
+	or      idx, unused_lanes
+	mov     unused_lanes, _unused_lanes(state)
+
+	movl	$0xFFFFFFFF,_lens+4(state,idx,8)
+	vmovq    _args_digest+0*32(state , idx, 8), %xmm0
+	vpinsrq  $1, _args_digest+1*32(state , idx, 8), %xmm0, %xmm0
+	vmovq    _args_digest+2*32(state , idx, 8), %xmm1
+	vpinsrq  $1, _args_digest+3*32(state , idx, 8), %xmm1, %xmm1
+	vmovq    _args_digest+4*32(state , idx, 8), %xmm2
+	vpinsrq  $1, _args_digest+5*32(state , idx, 8), %xmm2, %xmm2
+	vmovq    _args_digest+6*32(state , idx, 8), %xmm3
+	vpinsrq  $1, _args_digest+7*32(state , idx, 8), %xmm3, %xmm3
+
+	vmovdqu  %xmm0, _result_digest + 0*16(job_rax)
+	vmovdqu  %xmm1, _result_digest + 1*16(job_rax)
+	vmovdqu  %xmm2, _result_digest + 2*16(job_rax)
+	vmovdqu  %xmm3, _result_digest + 3*16(job_rax)
+
+return:
+	pop	%r12
+	pop	%rbx
+	FRAME_END
+	ret
+
+return_null:
+	xor     job_rax, job_rax
+	jmp     return
+ENDPROC(sha512_mb_mgr_submit_avx2)
+.data
+
+.align 16
+H0:     .int  0x6a09e667
+H1:     .int  0xbb67ae85
+H2:     .int  0x3c6ef372
+H3:     .int  0xa54ff53a
+H4:     .int  0x510e527f
+H5:     .int  0x9b05688c
+H6:     .int  0x1f83d9ab
+H7:     .int  0x5be0cd19
diff --git a/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S b/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S
new file mode 100644
index 000000000000..31ab1eff6413
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S
@@ -0,0 +1,529 @@
+/*
+ * Multi-buffer SHA512 algorithm hash compute routine
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+# code to compute quad SHA512 using AVX2
+# use YMMs to tackle the larger digest size
+# outer calling routine takes care of save and restore of XMM registers
+# Logic designed/laid out by JDG
+
+# Function clobbers: rax, rcx, rdx, rbx, rsi, rdi, r9-r15; ymm0-15
+# Stack must be aligned to 32 bytes before call
+# Linux clobbers: rax rbx rcx rsi r8 r9 r10 r11 r12
+# Linux preserves: rcx rdx rdi rbp r13 r14 r15
+# clobbers ymm0-15
+
+#include <linux/linkage.h>
+#include "sha512_mb_mgr_datastruct.S"
+
+arg1 = %rdi
+arg2 = %rsi
+
+# Common definitions
+STATE = arg1
+INP_SIZE = arg2
+
+IDX = %rax
+ROUND = %rbx
+TBL = %r8
+
+inp0 = %r9
+inp1 = %r10
+inp2 = %r11
+inp3 = %r12
+
+a = %ymm0
+b = %ymm1
+c = %ymm2
+d = %ymm3
+e = %ymm4
+f = %ymm5
+g = %ymm6
+h = %ymm7
+
+a0 = %ymm8
+a1 = %ymm9
+a2 = %ymm10
+
+TT0 = %ymm14
+TT1 = %ymm13
+TT2 = %ymm12
+TT3 = %ymm11
+TT4 = %ymm10
+TT5 = %ymm9
+
+T1 = %ymm14
+TMP = %ymm15
+
+# Define stack usage
+STACK_SPACE1 = SZ4*16 + NUM_SHA512_DIGEST_WORDS*SZ4 + 24
+
+#define VMOVPD	vmovupd
+_digest = SZ4*16
+
+# transpose r0, r1, r2, r3, t0, t1
+# "transpose" data in {r0..r3} using temps {t0..t3}
+# Input looks like: {r0 r1 r2 r3}
+# r0 = {a7 a6 a5 a4 a3 a2 a1 a0}
+# r1 = {b7 b6 b5 b4 b3 b2 b1 b0}
+# r2 = {c7 c6 c5 c4 c3 c2 c1 c0}
+# r3 = {d7 d6 d5 d4 d3 d2 d1 d0}
+#
+# output looks like: {t0 r1 r0 r3}
+# t0 = {d1 d0 c1 c0 b1 b0 a1 a0}
+# r1 = {d3 d2 c3 c2 b3 b2 a3 a2}
+# r0 = {d5 d4 c5 c4 b5 b4 a5 a4}
+# r3 = {d7 d6 c7 c6 b7 b6 a7 a6}
+
+.macro TRANSPOSE r0 r1 r2 r3 t0 t1
+	vshufps  $0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4   b1 b0 a1 a0}
+        vshufps  $0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6   b3 b2 a3 a2}
+        vshufps  $0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4   d1 d0 c1 c0}
+        vshufps  $0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6   d3 d2 c3 c2}
+
+	vperm2f128      $0x20, \r2, \r0, \r1  # h6...a6
+        vperm2f128      $0x31, \r2, \r0, \r3  # h2...a2
+        vperm2f128      $0x31, \t1, \t0, \r0  # h5...a5
+        vperm2f128      $0x20, \t1, \t0, \t0  # h1...a1
+.endm
+
+.macro ROTATE_ARGS
+TMP_ = h
+h = g
+g = f
+f = e
+e = d
+d = c
+c = b
+b = a
+a = TMP_
+.endm
+
+# PRORQ reg, imm, tmp
+# packed-rotate-right-double
+# does a rotate by doing two shifts and an or
+.macro _PRORQ reg imm tmp
+	vpsllq	$(64-\imm),\reg,\tmp
+	vpsrlq	$\imm,\reg, \reg
+	vpor	\tmp,\reg, \reg
+.endm
+
+# non-destructive
+# PRORQ_nd reg, imm, tmp, src
+.macro _PRORQ_nd reg imm tmp src
+	vpsllq	$(64-\imm), \src, \tmp
+	vpsrlq	$\imm, \src, \reg
+	vpor	\tmp, \reg, \reg
+.endm
+
+# PRORQ dst/src, amt
+.macro PRORQ reg imm
+	_PRORQ	\reg, \imm, TMP
+.endm
+
+# PRORQ_nd dst, src, amt
+.macro PRORQ_nd reg tmp imm
+	_PRORQ_nd	\reg, \imm, TMP, \tmp
+.endm
+
+#; arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_00_15 _T1 i
+	PRORQ_nd a0, e, (18-14)	# sig1: a0 = (e >> 4)
+
+	vpxor   g, f, a2        # ch: a2 = f^g
+        vpand   e,a2, a2                # ch: a2 = (f^g)&e
+        vpxor   g, a2, a2               # a2 = ch
+
+        PRORQ_nd        a1,e,41         # sig1: a1 = (e >> 25)
+
+        offset = SZ4*(\i & 0xf)
+        vmovdqu \_T1,offset(%rsp)
+        vpaddq  (TBL,ROUND,1), \_T1, \_T1       # T1 = W + K
+        vpxor   e,a0, a0        # sig1: a0 = e ^ (e >> 5)
+        PRORQ   a0, 14           # sig1: a0 = (e >> 6) ^ (e >> 11)
+        vpaddq  a2, h, h        # h = h + ch
+        PRORQ_nd        a2,a,6  # sig0: a2 = (a >> 11)
+        vpaddq  \_T1,h, h       # h = h + ch + W + K
+        vpxor   a1, a0, a0      # a0 = sigma1
+	vmovdqu a,\_T1
+        PRORQ_nd        a1,a,39 # sig0: a1 = (a >> 22)
+        vpxor   c, \_T1, \_T1      # maj: T1 = a^c
+        add     $SZ4, ROUND     # ROUND++
+        vpand   b, \_T1, \_T1   # maj: T1 = (a^c)&b
+        vpaddq  a0, h, h
+        vpaddq  h, d, d
+        vpxor   a, a2, a2       # sig0: a2 = a ^ (a >> 11)
+        PRORQ   a2,28            # sig0: a2 = (a >> 2) ^ (a >> 13)
+        vpxor   a1, a2, a2      # a2 = sig0
+        vpand   c, a, a1        # maj: a1 = a&c
+        vpor    \_T1, a1, a1    # a1 = maj
+        vpaddq  a1, h, h        # h = h + ch + W + K + maj
+        vpaddq  a2, h, h        # h = h + ch + W + K + maj + sigma0
+        ROTATE_ARGS
+.endm
+
+
+#; arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_16_XX _T1 i
+	vmovdqu SZ4*((\i-15)&0xf)(%rsp), \_T1
+        vmovdqu SZ4*((\i-2)&0xf)(%rsp), a1
+        vmovdqu \_T1, a0
+        PRORQ   \_T1,7
+        vmovdqu a1, a2
+        PRORQ   a1,42
+        vpxor   a0, \_T1, \_T1
+        PRORQ   \_T1, 1
+        vpxor   a2, a1, a1
+        PRORQ   a1, 19
+        vpsrlq  $7, a0, a0
+        vpxor   a0, \_T1, \_T1
+        vpsrlq  $6, a2, a2
+        vpxor   a2, a1, a1
+        vpaddq  SZ4*((\i-16)&0xf)(%rsp), \_T1, \_T1
+        vpaddq  SZ4*((\i-7)&0xf)(%rsp), a1, a1
+        vpaddq  a1, \_T1, \_T1
+
+        ROUND_00_15 \_T1,\i
+.endm
+
+
+# void sha512_x4_avx2(void *STATE, const int INP_SIZE)
+# arg 1 : STATE    : pointer to input data
+# arg 2 : INP_SIZE : size of data in blocks (assumed >= 1)
+ENTRY(sha512_x4_avx2)
+	# general registers preserved in outer calling routine
+	# outer calling routine saves all the XMM registers
+	# save callee-saved clobbered registers to comply with C function ABI
+	push    %r12
+	push    %r13
+	push    %r14
+	push    %r15
+
+	sub     $STACK_SPACE1, %rsp
+
+        # Load the pre-transposed incoming digest.
+        vmovdqu 0*SHA512_DIGEST_ROW_SIZE(STATE),a
+        vmovdqu 1*SHA512_DIGEST_ROW_SIZE(STATE),b
+        vmovdqu 2*SHA512_DIGEST_ROW_SIZE(STATE),c
+        vmovdqu 3*SHA512_DIGEST_ROW_SIZE(STATE),d
+        vmovdqu 4*SHA512_DIGEST_ROW_SIZE(STATE),e
+        vmovdqu 5*SHA512_DIGEST_ROW_SIZE(STATE),f
+        vmovdqu 6*SHA512_DIGEST_ROW_SIZE(STATE),g
+        vmovdqu 7*SHA512_DIGEST_ROW_SIZE(STATE),h
+
+        lea     K512_4(%rip),TBL
+
+        # load the address of each of the 4 message lanes
+        # getting ready to transpose input onto stack
+        mov     _data_ptr+0*PTR_SZ(STATE),inp0
+        mov     _data_ptr+1*PTR_SZ(STATE),inp1
+        mov     _data_ptr+2*PTR_SZ(STATE),inp2
+        mov     _data_ptr+3*PTR_SZ(STATE),inp3
+
+        xor     IDX, IDX
+lloop:
+        xor     ROUND, ROUND
+
+	# save old digest
+        vmovdqu a, _digest(%rsp)
+        vmovdqu b, _digest+1*SZ4(%rsp)
+        vmovdqu c, _digest+2*SZ4(%rsp)
+        vmovdqu d, _digest+3*SZ4(%rsp)
+        vmovdqu e, _digest+4*SZ4(%rsp)
+        vmovdqu f, _digest+5*SZ4(%rsp)
+        vmovdqu g, _digest+6*SZ4(%rsp)
+        vmovdqu h, _digest+7*SZ4(%rsp)
+        i = 0
+.rep 4
+	vmovdqu PSHUFFLE_BYTE_FLIP_MASK(%rip), TMP
+        VMOVPD  i*32(inp0, IDX), TT2
+        VMOVPD  i*32(inp1, IDX), TT1
+        VMOVPD  i*32(inp2, IDX), TT4
+        VMOVPD  i*32(inp3, IDX), TT3
+	TRANSPOSE	TT2, TT1, TT4, TT3, TT0, TT5
+	vpshufb	TMP, TT0, TT0
+	vpshufb	TMP, TT1, TT1
+	vpshufb	TMP, TT2, TT2
+	vpshufb	TMP, TT3, TT3
+	ROUND_00_15	TT0,(i*4+0)
+	ROUND_00_15	TT1,(i*4+1)
+	ROUND_00_15	TT2,(i*4+2)
+	ROUND_00_15	TT3,(i*4+3)
+	i = (i+1)
+.endr
+        add     $128, IDX
+
+        i = (i*4)
+
+        jmp     Lrounds_16_xx
+.align 16
+Lrounds_16_xx:
+.rep 16
+        ROUND_16_XX     T1, i
+        i = (i+1)
+.endr
+        cmp     $0xa00,ROUND
+        jb      Lrounds_16_xx
+
+	# add old digest
+        vpaddq  _digest(%rsp), a, a
+        vpaddq  _digest+1*SZ4(%rsp), b, b
+        vpaddq  _digest+2*SZ4(%rsp), c, c
+        vpaddq  _digest+3*SZ4(%rsp), d, d
+        vpaddq  _digest+4*SZ4(%rsp), e, e
+        vpaddq  _digest+5*SZ4(%rsp), f, f
+        vpaddq  _digest+6*SZ4(%rsp), g, g
+        vpaddq  _digest+7*SZ4(%rsp), h, h
+
+        sub     $1, INP_SIZE  # unit is blocks
+        jne     lloop
+
+        # write back to memory (state object) the transposed digest
+        vmovdqu a, 0*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu b, 1*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu c, 2*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu d, 3*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu e, 4*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu f, 5*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu g, 6*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu h, 7*SHA512_DIGEST_ROW_SIZE(STATE)
+
+	# update input data pointers
+	add     IDX, inp0
+        mov     inp0, _data_ptr+0*PTR_SZ(STATE)
+        add     IDX, inp1
+        mov     inp1, _data_ptr+1*PTR_SZ(STATE)
+        add     IDX, inp2
+        mov     inp2, _data_ptr+2*PTR_SZ(STATE)
+        add     IDX, inp3
+        mov     inp3, _data_ptr+3*PTR_SZ(STATE)
+
+	#;;;;;;;;;;;;;;;
+	#; Postamble
+	add $STACK_SPACE1, %rsp
+	# restore callee-saved clobbered registers
+
+	pop     %r15
+	pop     %r14
+	pop     %r13
+	pop     %r12
+
+	# outer calling routine restores XMM and other GP registers
+	ret
+ENDPROC(sha512_x4_avx2)
+
+.data
+.align 64
+K512_4:
+	.octa 0x428a2f98d728ae22428a2f98d728ae22,\
+		0x428a2f98d728ae22428a2f98d728ae22
+	.octa 0x7137449123ef65cd7137449123ef65cd,\
+		0x7137449123ef65cd7137449123ef65cd
+	.octa 0xb5c0fbcfec4d3b2fb5c0fbcfec4d3b2f,\
+		0xb5c0fbcfec4d3b2fb5c0fbcfec4d3b2f
+	.octa 0xe9b5dba58189dbbce9b5dba58189dbbc,\
+		0xe9b5dba58189dbbce9b5dba58189dbbc
+	.octa 0x3956c25bf348b5383956c25bf348b538,\
+		0x3956c25bf348b5383956c25bf348b538
+	.octa 0x59f111f1b605d01959f111f1b605d019,\
+		0x59f111f1b605d01959f111f1b605d019
+	.octa 0x923f82a4af194f9b923f82a4af194f9b,\
+		0x923f82a4af194f9b923f82a4af194f9b
+	.octa 0xab1c5ed5da6d8118ab1c5ed5da6d8118,\
+		0xab1c5ed5da6d8118ab1c5ed5da6d8118
+	.octa 0xd807aa98a3030242d807aa98a3030242,\
+		0xd807aa98a3030242d807aa98a3030242
+	.octa 0x12835b0145706fbe12835b0145706fbe,\
+		0x12835b0145706fbe12835b0145706fbe
+	.octa 0x243185be4ee4b28c243185be4ee4b28c,\
+		0x243185be4ee4b28c243185be4ee4b28c
+	.octa 0x550c7dc3d5ffb4e2550c7dc3d5ffb4e2,\
+		0x550c7dc3d5ffb4e2550c7dc3d5ffb4e2
+	.octa 0x72be5d74f27b896f72be5d74f27b896f,\
+		0x72be5d74f27b896f72be5d74f27b896f
+	.octa 0x80deb1fe3b1696b180deb1fe3b1696b1,\
+		0x80deb1fe3b1696b180deb1fe3b1696b1
+	.octa 0x9bdc06a725c712359bdc06a725c71235,\
+		0x9bdc06a725c712359bdc06a725c71235
+	.octa 0xc19bf174cf692694c19bf174cf692694,\
+		0xc19bf174cf692694c19bf174cf692694
+	.octa 0xe49b69c19ef14ad2e49b69c19ef14ad2,\
+		0xe49b69c19ef14ad2e49b69c19ef14ad2
+	.octa 0xefbe4786384f25e3efbe4786384f25e3,\
+		0xefbe4786384f25e3efbe4786384f25e3
+	.octa 0x0fc19dc68b8cd5b50fc19dc68b8cd5b5,\
+		0x0fc19dc68b8cd5b50fc19dc68b8cd5b5
+	.octa 0x240ca1cc77ac9c65240ca1cc77ac9c65,\
+		0x240ca1cc77ac9c65240ca1cc77ac9c65
+	.octa 0x2de92c6f592b02752de92c6f592b0275,\
+		0x2de92c6f592b02752de92c6f592b0275
+	.octa 0x4a7484aa6ea6e4834a7484aa6ea6e483,\
+		0x4a7484aa6ea6e4834a7484aa6ea6e483
+	.octa 0x5cb0a9dcbd41fbd45cb0a9dcbd41fbd4,\
+		0x5cb0a9dcbd41fbd45cb0a9dcbd41fbd4
+	.octa 0x76f988da831153b576f988da831153b5,\
+		0x76f988da831153b576f988da831153b5
+	.octa 0x983e5152ee66dfab983e5152ee66dfab,\
+		0x983e5152ee66dfab983e5152ee66dfab
+	.octa 0xa831c66d2db43210a831c66d2db43210,\
+		0xa831c66d2db43210a831c66d2db43210
+	.octa 0xb00327c898fb213fb00327c898fb213f,\
+		0xb00327c898fb213fb00327c898fb213f
+	.octa 0xbf597fc7beef0ee4bf597fc7beef0ee4,\
+		0xbf597fc7beef0ee4bf597fc7beef0ee4
+	.octa 0xc6e00bf33da88fc2c6e00bf33da88fc2,\
+		0xc6e00bf33da88fc2c6e00bf33da88fc2
+	.octa 0xd5a79147930aa725d5a79147930aa725,\
+		0xd5a79147930aa725d5a79147930aa725
+	.octa 0x06ca6351e003826f06ca6351e003826f,\
+		0x06ca6351e003826f06ca6351e003826f
+	.octa 0x142929670a0e6e70142929670a0e6e70,\
+		0x142929670a0e6e70142929670a0e6e70
+	.octa 0x27b70a8546d22ffc27b70a8546d22ffc,\
+		0x27b70a8546d22ffc27b70a8546d22ffc
+	.octa 0x2e1b21385c26c9262e1b21385c26c926,\
+		0x2e1b21385c26c9262e1b21385c26c926
+	.octa 0x4d2c6dfc5ac42aed4d2c6dfc5ac42aed,\
+		0x4d2c6dfc5ac42aed4d2c6dfc5ac42aed
+	.octa 0x53380d139d95b3df53380d139d95b3df,\
+		0x53380d139d95b3df53380d139d95b3df
+	.octa 0x650a73548baf63de650a73548baf63de,\
+		0x650a73548baf63de650a73548baf63de
+	.octa 0x766a0abb3c77b2a8766a0abb3c77b2a8,\
+		0x766a0abb3c77b2a8766a0abb3c77b2a8
+	.octa 0x81c2c92e47edaee681c2c92e47edaee6,\
+		0x81c2c92e47edaee681c2c92e47edaee6
+	.octa 0x92722c851482353b92722c851482353b,\
+		0x92722c851482353b92722c851482353b
+	.octa 0xa2bfe8a14cf10364a2bfe8a14cf10364,\
+		0xa2bfe8a14cf10364a2bfe8a14cf10364
+	.octa 0xa81a664bbc423001a81a664bbc423001,\
+		0xa81a664bbc423001a81a664bbc423001
+	.octa 0xc24b8b70d0f89791c24b8b70d0f89791,\
+		0xc24b8b70d0f89791c24b8b70d0f89791
+	.octa 0xc76c51a30654be30c76c51a30654be30,\
+		0xc76c51a30654be30c76c51a30654be30
+	.octa 0xd192e819d6ef5218d192e819d6ef5218,\
+		0xd192e819d6ef5218d192e819d6ef5218
+	.octa 0xd69906245565a910d69906245565a910,\
+		0xd69906245565a910d69906245565a910
+	.octa 0xf40e35855771202af40e35855771202a,\
+		0xf40e35855771202af40e35855771202a
+	.octa 0x106aa07032bbd1b8106aa07032bbd1b8,\
+		0x106aa07032bbd1b8106aa07032bbd1b8
+	.octa 0x19a4c116b8d2d0c819a4c116b8d2d0c8,\
+		0x19a4c116b8d2d0c819a4c116b8d2d0c8
+	.octa 0x1e376c085141ab531e376c085141ab53,\
+		0x1e376c085141ab531e376c085141ab53
+	.octa 0x2748774cdf8eeb992748774cdf8eeb99,\
+		0x2748774cdf8eeb992748774cdf8eeb99
+	.octa 0x34b0bcb5e19b48a834b0bcb5e19b48a8,\
+		0x34b0bcb5e19b48a834b0bcb5e19b48a8
+	.octa 0x391c0cb3c5c95a63391c0cb3c5c95a63,\
+		0x391c0cb3c5c95a63391c0cb3c5c95a63
+	.octa 0x4ed8aa4ae3418acb4ed8aa4ae3418acb,\
+		0x4ed8aa4ae3418acb4ed8aa4ae3418acb
+	.octa 0x5b9cca4f7763e3735b9cca4f7763e373,\
+		0x5b9cca4f7763e3735b9cca4f7763e373
+	.octa 0x682e6ff3d6b2b8a3682e6ff3d6b2b8a3,\
+		0x682e6ff3d6b2b8a3682e6ff3d6b2b8a3
+	.octa 0x748f82ee5defb2fc748f82ee5defb2fc,\
+		0x748f82ee5defb2fc748f82ee5defb2fc
+	.octa 0x78a5636f43172f6078a5636f43172f60,\
+		0x78a5636f43172f6078a5636f43172f60
+	.octa 0x84c87814a1f0ab7284c87814a1f0ab72,\
+		0x84c87814a1f0ab7284c87814a1f0ab72
+	.octa 0x8cc702081a6439ec8cc702081a6439ec,\
+		0x8cc702081a6439ec8cc702081a6439ec
+	.octa 0x90befffa23631e2890befffa23631e28,\
+		0x90befffa23631e2890befffa23631e28
+	.octa 0xa4506cebde82bde9a4506cebde82bde9,\
+		0xa4506cebde82bde9a4506cebde82bde9
+	.octa 0xbef9a3f7b2c67915bef9a3f7b2c67915,\
+		0xbef9a3f7b2c67915bef9a3f7b2c67915
+	.octa 0xc67178f2e372532bc67178f2e372532b,\
+		0xc67178f2e372532bc67178f2e372532b
+	.octa 0xca273eceea26619cca273eceea26619c,\
+		0xca273eceea26619cca273eceea26619c
+	.octa 0xd186b8c721c0c207d186b8c721c0c207,\
+		0xd186b8c721c0c207d186b8c721c0c207
+	.octa 0xeada7dd6cde0eb1eeada7dd6cde0eb1e,\
+		0xeada7dd6cde0eb1eeada7dd6cde0eb1e
+	.octa 0xf57d4f7fee6ed178f57d4f7fee6ed178,\
+		0xf57d4f7fee6ed178f57d4f7fee6ed178
+	.octa 0x06f067aa72176fba06f067aa72176fba,\
+		0x06f067aa72176fba06f067aa72176fba
+	.octa 0x0a637dc5a2c898a60a637dc5a2c898a6,\
+		0x0a637dc5a2c898a60a637dc5a2c898a6
+	.octa 0x113f9804bef90dae113f9804bef90dae,\
+		0x113f9804bef90dae113f9804bef90dae
+	.octa 0x1b710b35131c471b1b710b35131c471b,\
+		0x1b710b35131c471b1b710b35131c471b
+	.octa 0x28db77f523047d8428db77f523047d84,\
+		0x28db77f523047d8428db77f523047d84
+	.octa 0x32caab7b40c7249332caab7b40c72493,\
+		0x32caab7b40c7249332caab7b40c72493
+	.octa 0x3c9ebe0a15c9bebc3c9ebe0a15c9bebc,\
+		0x3c9ebe0a15c9bebc3c9ebe0a15c9bebc
+	.octa 0x431d67c49c100d4c431d67c49c100d4c,\
+		0x431d67c49c100d4c431d67c49c100d4c
+	.octa 0x4cc5d4becb3e42b64cc5d4becb3e42b6,\
+		0x4cc5d4becb3e42b64cc5d4becb3e42b6
+	.octa 0x597f299cfc657e2a597f299cfc657e2a,\
+		0x597f299cfc657e2a597f299cfc657e2a
+	.octa 0x5fcb6fab3ad6faec5fcb6fab3ad6faec,\
+		0x5fcb6fab3ad6faec5fcb6fab3ad6faec
+	.octa 0x6c44198c4a4758176c44198c4a475817,\
+		0x6c44198c4a4758176c44198c4a475817
+
+PSHUFFLE_BYTE_FLIP_MASK: .octa 0x08090a0b0c0d0e0f0001020304050607
+                         .octa 0x18191a1b1c1d1e1f1011121314151617
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 0b17c83d027d..2b0e2a6825f3 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -346,4 +346,10 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
 MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha512-ssse3");
+MODULE_ALIAS_CRYPTO("sha512-avx");
+MODULE_ALIAS_CRYPTO("sha512-avx2");
 MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha384-ssse3");
+MODULE_ALIAS_CRYPTO("sha384-avx");
+MODULE_ALIAS_CRYPTO("sha384-avx2");
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 68b63fddc209..6ba89a1ab0e5 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -55,7 +55,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 94c18ebfd68c..5391b0ae7cc3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -145,7 +145,6 @@ static inline void disable_acpi(void) { }
 #define ARCH_HAS_POWER_INIT	1
 
 #ifdef CONFIG_ACPI_NUMA
-extern int acpi_numa;
 extern int x86_acpi_numa_init(void);
 #endif /* CONFIG_ACPI_NUMA */
 
@@ -170,4 +169,6 @@ static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
 }
 #endif
 
+#define ACPI_TABLE_UPGRADE_MAX_PHYS (max_low_pfn_mapped << PAGE_SHIFT)
+
 #endif /* _ASM_X86_ACPI_H */
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 74a2e312e8a2..02aff0867211 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -89,6 +90,7 @@
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
 	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)
@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-	return attr & INAT_VEXONLY;
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
 }
 #endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index e7814b74caf8..b3e32b010ab1 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
 #define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
 #define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
 #define X86_VEX2_M	1			/* VEX2.M always 1 */
 #define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
 	return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
 		return X86_VEX2_M;
-	else
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
 		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 5a73a9c62c39..56f4c6676b29 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -64,8 +64,6 @@
 
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
-#define MSR_NHM_TURBO_RATIO_LIMIT	0x000001ad
-#define MSR_IVT_TURBO_RATIO_LIMIT	0x000001ae
 #define MSR_TURBO_RATIO_LIMIT		0x000001ad
 #define MSR_TURBO_RATIO_LIMIT1		0x000001ae
 #define MSR_TURBO_RATIO_LIMIT2		0x000001af
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 0576b6157f3a..c9734dc76257 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -135,6 +135,7 @@ int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_disable(void);
 int common_cpu_die(unsigned int cpu);
 void native_cpu_die(unsigned int cpu);
+void hlt_play_dead(void);
 void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a2616584b6e9..6cb2b02fcc87 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -400,10 +400,6 @@ static void __init reserve_initrd(void)
 	memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
 }
 
-static void __init early_initrd_acpi_init(void)
-{
-	early_acpi_table_init((void *)initrd_start, initrd_end - initrd_start);
-}
 #else
 static void __init early_reserve_initrd(void)
 {
@@ -411,9 +407,6 @@ static void __init early_reserve_initrd(void)
 static void __init reserve_initrd(void)
 {
 }
-static void __init early_initrd_acpi_init(void)
-{
-}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
 static void __init parse_setup_data(void)
@@ -1149,7 +1142,7 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_initrd();
 
-	early_initrd_acpi_init();
+	acpi_table_upgrade();
 
 	vsmp_init();
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index d0a51939c150..c93609c97406 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1644,7 +1644,7 @@ static inline void mwait_play_dead(void)
 	}
 }
 
-static inline void hlt_play_dead(void)
+void hlt_play_dead(void)
 {
 	if (__this_cpu_read(cpu_info.x86) >= 4)
 		wbinvd();
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index c146f3c262c3..0149ac59c273 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -539,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter)
 
 	iter->fixed = false;
 	iter->start_max = iter->start;
+	iter->range = NULL;
 	iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
 
 	__mtrr_lookup_var_next(iter);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 64a79f271276..7758680db20b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4979,6 +4979,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	if (vmx_xsaves_supported())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
+	if (enable_pml) {
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	return 0;
 }
 
@@ -7937,22 +7943,6 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
-static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
-{
-	struct page *pml_pg;
-
-	pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!pml_pg)
-		return -ENOMEM;
-
-	vmx->pml_pg = pml_pg;
-
-	vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-
-	return 0;
-}
-
 static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
 {
 	if (vmx->pml_pg) {
@@ -8224,6 +8214,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
+			exit_reason != EXIT_REASON_PML_FULL &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8854,6 +8845,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       int r;
+
+       r = vcpu_load(vcpu);
+       BUG_ON(r);
+       vmx_load_vmcs01(vcpu);
+       free_nested(vmx);
+       vcpu_put(vcpu);
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8862,8 +8869,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 		vmx_destroy_pml_buffer(vmx);
 	free_vpid(vmx->vpid);
 	leave_guest_mode(vcpu);
-	vmx_load_vmcs01(vcpu);
-	free_nested(vmx);
+	vmx_free_vcpu_nested(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
@@ -8885,14 +8891,26 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	err = -ENOMEM;
+
+	/*
+	 * If PML is turned on, failure on enabling PML just results in failure
+	 * of creating the vcpu, therefore we can simplify PML logic (by
+	 * avoiding dealing with cases, such as enabling PML partially on vcpus
+	 * for the guest, etc.
+	 */
+	if (enable_pml) {
+		vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!vmx->pml_pg)
+			goto uninit_vcpu;
+	}
+
 	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
 		     > PAGE_SIZE);
 
-	err = -ENOMEM;
-	if (!vmx->guest_msrs) {
-		goto uninit_vcpu;
-	}
+	if (!vmx->guest_msrs)
+		goto free_pml;
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
 	vmx->loaded_vmcs->vmcs = alloc_vmcs();
@@ -8936,18 +8954,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx->nested.current_vmptr = -1ull;
 	vmx->nested.current_vmcs12 = NULL;
 
-	/*
-	 * If PML is turned on, failure on enabling PML just results in failure
-	 * of creating the vcpu, therefore we can simplify PML logic (by
-	 * avoiding dealing with cases, such as enabling PML partially on vcpus
-	 * for the guest, etc.
-	 */
-	if (enable_pml) {
-		err = vmx_create_pml_buffer(vmx);
-		if (err)
-			goto free_vmcs;
-	}
-
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -8955,6 +8961,8 @@ free_vmcs:
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
+free_pml:
+	vmx_destroy_pml_buffer(vmx);
 uninit_vcpu:
 	kvm_vcpu_uninit(&vmx->vcpu);
 free_vcpu:
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 1a416935bac9..1088eb8f3a5f 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -155,14 +155,24 @@ found:
 			/*
 			 * In 32-bits mode, if the [7:6] bits (mod bits of
 			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES.
+			 * LDS or LES or BOUND.
 			 */
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
 		insn->vex_prefix.bytes[0] = b;
 		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_vex3_prefix(attr)) {
+		if (inat_is_evex_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+			insn->vex_prefix.bytes[3] = b2;
+			insn->vex_prefix.nbytes = 4;
+			insn->next_byte += 4;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else if (inat_is_vex3_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
 			insn->vex_prefix.bytes[2] = b2;
 			insn->vex_prefix.nbytes = 3;
@@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn)
 		m = insn_vex_m_bits(insn);
 		p = insn_vex_p_bits(insn);
 		insn->attr = inat_get_avx_attribute(op, m, p);
-		if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+		    (!inat_accept_vex(insn->attr) &&
+		     !inat_is_group(insn->attr)))
 			insn->attr = 0;	/* This instruction is bad */
 		goto end;	/* VEX has only 1 byte for opcode */
 	}
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index d388de72eaca..ec378cd7b71e 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -13,12 +13,17 @@
 # opcode: escape # escaped-name
 # EndTable
 #
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
 #<group maps>
 # GrpTable: GrpXXX
 # reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
 # EndTable
 #
 # AVX Superscripts
+#  (ev): this opcode requires EVEX prefix.
+#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
 #  (v): this opcode requires VEX prefix.
 #  (v1): this opcode only supports 128bit VEX.
 #
@@ -137,7 +142,7 @@ AVXcode:
 # 0x60 - 0x6f
 60: PUSHA/PUSHAD (i64)
 61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
 64: SEG=FS (Prefix)
 65: SEG=GS (Prefix)
@@ -399,17 +404,17 @@ AVXcode: 1
 3f:
 # 0x0f 0x40-0x4f
 40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev
-42: CMOVB/C/NAE Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
 43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev
-45: CMOVNE/NZ Gv,Ev
-46: CMOVBE/NA Gv,Ev
-47: CMOVA/NBE Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
 48: CMOVS Gv,Ev
 49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev
-4b: CMOVNP/PO Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
 4c: CMOVL/NGE Gv,Ev
 4d: CMOVNL/GE Gv,Ev
 4e: CMOVLE/NG Gv,Ev
@@ -426,7 +431,7 @@ AVXcode: 1
 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
@@ -447,7 +452,7 @@ AVXcode: 1
 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
 # 0x0f 0x70-0x7f
 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
 71: Grp12 (1A)
@@ -458,14 +463,14 @@ AVXcode: 1
 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
 # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
 77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy
-79: VMWRITE Gy,Ey
-7a:
-7b:
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
 80: JO Jz (f64)
@@ -485,16 +490,16 @@ AVXcode: 1
 8e: JLE/JNG Jz (f64)
 8f: JNLE/JG Jz (f64)
 # 0x0f 0x90-0x9f
-90: SETO Eb
-91: SETNO Eb
-92: SETB/C/NAE Eb
-93: SETAE/NB/NC Eb
+90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
+91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
 94: SETE/Z Eb
 95: SETNE/NZ Eb
 96: SETBE/NA Eb
 97: SETA/NBE Eb
-98: SETS Eb
-99: SETNS Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
 9a: SETP/PE Eb
 9b: SETNP/PO Eb
 9c: SETL/NGE Eb
@@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
 d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
 d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
 da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
 dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
 dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
 de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xe0-0xef
 e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
 e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
@@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
 e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
 e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
 e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
 e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
 e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
 e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
 ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
 ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
 ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
 ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xf0-0xff
 f0: vlddqu Vx,Mx (F2)
 f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
@@ -626,81 +631,105 @@ AVXcode: 2
 0e: vtestps Vx,Wx (66),(v)
 0f: vtestpd Vx,Wx (66),(v)
 # 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66)
-11:
-12:
-13: vcvtph2ps Vx,Wx,Ib (66),(v)
-14: blendvps Vdq,Wdq (66)
-15: blendvpd Vdq,Wdq (66)
-16: vpermps Vqq,Hqq,Wqq (66),(v)
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
 17: vptest Vx,Wx (66)
 18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v)
-1a: vbroadcastf128 Vqq,Mdq (66),(v)
-1b:
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f:
+1f: vpabsq Vx,Wx (66),(ev)
 # 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1)
-21: vpmovsxbd Vx,Ux/Md (66),(v1)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1)
-24: vpmovsxwq Vx,Ux/Md (66),(v1)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1)
-26:
-27:
-28: vpmuldq Vx,Hx,Wx (66),(v1)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1)
-2a: vmovntdqa Vx,Mx (66),(v1)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
 2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
 2e: vmaskmovps Mx,Hx,Vx (66),(v)
 2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1)
-31: vpmovzxbd Vx,Ux/Md (66),(v1)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1)
-34: vpmovzxwq Vx,Ux/Md (66),(v1)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1)
-36: vpermd Vqq,Hqq,Wqq (66),(v)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
 37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1)
-39: vpminsd Vx,Hx,Wx (66),(v1)
-3a: vpminuw Vx,Hx,Wx (66),(v1)
-3b: vpminud Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
 3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
 3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1)
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
 41: vphminposuw Vdq,Wdq (66),(v1)
-42:
-43:
-44:
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
 45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
 47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x57
+# Skip 0x48-0x4b
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+# Skip 0x50-0x57
 58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v)
-5a: vbroadcasti128 Vqq,Mdq (66),(v)
-# Skip 0x5b-0x77
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+# Skip 0x5c-0x63
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+# Skip 0x67-0x74
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
 78: vpbroadcastb Vx,Wx (66),(v)
 79: vpbroadcastw Vx,Wx (66),(v)
-# Skip 0x7a-0x7f
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
 81: INVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
 # 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v)
-91: vgatherqd/q Vx,Hx,Wx (66),(v)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
 92: vgatherdps/d Vx,Hx,Wx (66),(v)
 93: vgatherqps/d Vx,Hx,Wx (66),(v)
 94:
@@ -715,6 +744,10 @@ AVXcode: 2
 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
 a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
 a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
 a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
@@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
 af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
 b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
 b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
 b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
-c8: sha1nexte Vdq,Wdq
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
 c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq
-cb: sha256rnds2 Vdq,Wdq
-cc: sha256msg1 Vdq,Wdq
-cd: sha256msg2 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -763,15 +801,15 @@ AVXcode: 3
 00: vpermq Vqq,Wqq,Ib (66),(v)
 01: vpermpd Vqq,Wqq,Ib (66),(v)
 02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03:
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
 04: vpermilps Vx,Wx,Ib (66),(v)
 05: vpermilpd Vx,Wx,Ib (66),(v)
 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
 07:
-08: vroundps Vx,Wx,Ib (66)
-09: vroundpd Vx,Wx,Ib (66)
-0a: vroundss Vss,Wss,Ib (66),(v1)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
 0c: vblendps Vx,Hx,Wx,Ib (66)
 0d: vblendpd Vx,Hx,Wx,Ib (66)
 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
@@ -780,26 +818,51 @@ AVXcode: 3
 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
 16: vpextrd/q Ey,Vdq,Ib (66),(v1)
 17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
-19: vextractf128 Wdq,Vqq,Ib (66),(v)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
 1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
-39: vextracti128 Wdq,Vqq,Ib (66),(v)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
 40: vdpps Vx,Hx,Wx,Ib (66)
 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
 4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
@@ -927,8 +990,10 @@ GrpTable: Grp12
 EndTable
 
 GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 
@@ -963,6 +1028,20 @@ GrpTable: Grp17
 3: BLSI By,Ey (v)
 EndTable
 
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 9c086c57105c..968ac028c34e 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -1,4 +1,5 @@
 /* Common code for 32 and 64-bit NUMA */
+#include <linux/acpi.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/string.h>
@@ -15,7 +16,6 @@
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
-#include <asm/acpi.h>
 #include <asm/amd_nb.h>
 
 #include "numa_internal.h"
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index b5f821881465..b1ecff460a46 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -15,8 +15,6 @@
 #include <linux/bitmap.h>
 #include <linux/module.h>
 #include <linux/topology.h>
-#include <linux/bootmem.h>
-#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
@@ -24,51 +22,6 @@
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
 
-int acpi_numa __initdata;
-
-static __init int setup_node(int pxm)
-{
-	return acpi_map_pxm_to_node(pxm);
-}
-
-static __init void bad_srat(void)
-{
-	printk(KERN_ERR "SRAT: SRAT not used.\n");
-	acpi_numa = -1;
-}
-
-static __init inline int srat_disabled(void)
-{
-	return acpi_numa < 0;
-}
-
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
-{
-	int i, j;
-
-	for (i = 0; i < slit->locality_count; i++) {
-		const int from_node = pxm_to_node(i);
-
-		if (from_node == NUMA_NO_NODE)
-			continue;
-
-		for (j = 0; j < slit->locality_count; j++) {
-			const int to_node = pxm_to_node(j);
-
-			if (to_node == NUMA_NO_NODE)
-				continue;
-
-			numa_set_distance(from_node, to_node,
-				slit->entry[slit->locality_count * i + j]);
-		}
-	}
-}
-
 /* Callback for Proximity Domain -> x2APIC mapping */
 void __init
 acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
@@ -91,7 +44,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 			 pxm, apic_id);
 		return;
 	}
-	node = setup_node(pxm);
+	node = acpi_map_pxm_to_node(pxm);
 	if (node < 0) {
 		printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
 		bad_srat();
@@ -104,7 +57,6 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 	}
 	set_apicid_to_node(apic_id, node);
 	node_set(node, numa_nodes_parsed);
-	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
 	       pxm, apic_id, node);
 }
@@ -127,7 +79,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	pxm = pa->proximity_domain_lo;
 	if (acpi_srat_revision >= 2)
 		pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
-	node = setup_node(pxm);
+	node = acpi_map_pxm_to_node(pxm);
 	if (node < 0) {
 		printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
 		bad_srat();
@@ -146,74 +98,10 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 
 	set_apicid_to_node(apic_id, node);
 	node_set(node, numa_nodes_parsed);
-	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
 	       pxm, apic_id, node);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-static inline int save_add_info(void) {return 1;}
-#else
-static inline int save_add_info(void) {return 0;}
-#endif
-
-/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
-int __init
-acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
-{
-	u64 start, end;
-	u32 hotpluggable;
-	int node, pxm;
-
-	if (srat_disabled())
-		goto out_err;
-	if (ma->header.length != sizeof(struct acpi_srat_mem_affinity))
-		goto out_err_bad_srat;
-	if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
-		goto out_err;
-	hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
-	if (hotpluggable && !save_add_info())
-		goto out_err;
-
-	start = ma->base_address;
-	end = start + ma->length;
-	pxm = ma->proximity_domain;
-	if (acpi_srat_revision <= 1)
-		pxm &= 0xff;
-
-	node = setup_node(pxm);
-	if (node < 0) {
-		printk(KERN_ERR "SRAT: Too many proximity domains.\n");
-		goto out_err_bad_srat;
-	}
-
-	if (numa_add_memblk(node, start, end) < 0)
-		goto out_err_bad_srat;
-
-	node_set(node, numa_nodes_parsed);
-
-	pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n",
-		node, pxm,
-		(unsigned long long) start, (unsigned long long) end - 1,
-		hotpluggable ? " hotplug" : "",
-		ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : "");
-
-	/* Mark hotplug range in memblock. */
-	if (hotpluggable && memblock_mark_hotplug(start, ma->length))
-		pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
-			(unsigned long long)start, (unsigned long long)end - 1);
-
-	max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
-
-	return 0;
-out_err_bad_srat:
-	bad_srat();
-out_err:
-	return -1;
-}
-
-void __init acpi_numa_arch_fixup(void) {}
-
 int __init x86_acpi_numa_init(void)
 {
 	int ret;
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index d5f64996394a..b12c26e2e309 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -12,6 +12,7 @@
 #include <linux/export.h>
 #include <linux/smp.h>
 #include <linux/perf_event.h>
+#include <linux/tboot.h>
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
@@ -266,6 +267,35 @@ void notrace restore_processor_state(void)
 EXPORT_SYMBOL(restore_processor_state);
 #endif
 
+#if defined(CONFIG_HIBERNATION) && defined(CONFIG_HOTPLUG_CPU)
+static void resume_play_dead(void)
+{
+	play_dead_common();
+	tboot_shutdown(TB_SHUTDOWN_WFS);
+	hlt_play_dead();
+}
+
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	void (*play_dead)(void) = smp_ops.play_dead;
+	int ret;
+
+	/*
+	 * Ensure that MONITOR/MWAIT will not be used in the "play dead" loop
+	 * during hibernate image restoration, because it is likely that the
+	 * monitored address will be actually written to at that time and then
+	 * the "dead" CPU will attempt to execute instructions again, but the
+	 * address in its instruction pointer may not be possible to resolve
+	 * any more at that point (the page tables used by it previously may
+	 * have been overwritten by hibernate image data).
+	 */
+	smp_ops.play_dead = resume_play_dead;
+	ret = disable_nonboot_cpus();
+	smp_ops.play_dead = play_dead;
+	return ret;
+}
+#endif
+
 /*
  * When bsp_check() is called in hibernate and suspend, cpu hotplug
  * is disabled already. So it's unnessary to handle race condition between
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 093a892026f9..a3d2c62fd805 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -72,12 +72,14 @@ BEGIN {
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
-	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
 	# accepts VEX prefix
-	vexok_opcode_expr = "^v.*"
+	vexok_opcode_expr = "^[vk].*"
 	vexok_expr = "\\(v1\\)"
 	# All opcodes with (v) superscript supports *only* VEX prefix
 	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
 	clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			flags = add_flags(flags, "INAT_MODRM")
 
 		# check VEX codes
-		if (match(ext, vexonly_expr))
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
 			flags = add_flags(flags, "INAT_VEXOK")
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 711e4d8de6fa..f70cc3bdfd01 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -26,6 +26,7 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include <linux/slab.h>
+#include "blk.h"
 
 #define BIP_INLINE_VECS	4
 
@@ -53,7 +54,6 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 {
 	struct bio_integrity_payload *bip;
 	struct bio_set *bs = bio->bi_pool;
-	unsigned long idx = BIO_POOL_NONE;
 	unsigned inline_vecs;
 
 	if (!bs || !bs->bio_integrity_pool) {
@@ -71,17 +71,19 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	memset(bip, 0, sizeof(*bip));
 
 	if (nr_vecs > inline_vecs) {
+		unsigned long idx = 0;
+
 		bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
 					  bs->bvec_integrity_pool);
 		if (!bip->bip_vec)
 			goto err;
 		bip->bip_max_vcnt = bvec_nr_vecs(idx);
+		bip->bip_slab = idx;
 	} else {
 		bip->bip_vec = bip->bip_inline_vecs;
 		bip->bip_max_vcnt = inline_vecs;
 	}
 
-	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
 	bio->bi_rw |= REQ_INTEGRITY;
@@ -110,9 +112,7 @@ void bio_integrity_free(struct bio *bio)
 		      bip->bip_vec->bv_offset);
 
 	if (bs && bs->bio_integrity_pool) {
-		if (bip->bip_slab != BIO_POOL_NONE)
-			bvec_free(bs->bvec_integrity_pool, bip->bip_vec,
-				  bip->bip_slab);
+		bvec_free(bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
 
 		mempool_free(bip, bs->bio_integrity_pool);
 	} else {
diff --git a/block/bio.c b/block/bio.c
index 0e4aa42bc30d..54ee3846c3a5 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -43,7 +43,7 @@
  * unsigned short
  */
 #define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
-static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
+static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = {
 	BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
 };
 #undef BV
@@ -160,11 +160,15 @@ unsigned int bvec_nr_vecs(unsigned short idx)
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
 {
-	BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);
+	if (!idx)
+		return;
+	idx--;
+
+	BIO_BUG_ON(idx >= BVEC_POOL_NR);
 
-	if (idx == BIOVEC_MAX_IDX)
+	if (idx == BVEC_POOL_MAX) {
 		mempool_free(bv, pool);
-	else {
+	} else {
 		struct biovec_slab *bvs = bvec_slabs + idx;
 
 		kmem_cache_free(bvs->slab, bv);
@@ -206,7 +210,7 @@ struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
 	 * idx now points to the pool we want to allocate from. only the
 	 * 1-vec entry pool is mempool backed.
 	 */
-	if (*idx == BIOVEC_MAX_IDX) {
+	if (*idx == BVEC_POOL_MAX) {
 fallback:
 		bvl = mempool_alloc(pool, gfp_mask);
 	} else {
@@ -226,11 +230,12 @@ fallback:
 		 */
 		bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
 		if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) {
-			*idx = BIOVEC_MAX_IDX;
+			*idx = BVEC_POOL_MAX;
 			goto fallback;
 		}
 	}
 
+	(*idx)++;
 	return bvl;
 }
 
@@ -250,8 +255,7 @@ static void bio_free(struct bio *bio)
 	__bio_free(bio);
 
 	if (bs) {
-		if (bio_flagged(bio, BIO_OWNS_VEC))
-			bvec_free(bs->bvec_pool, bio->bi_io_vec, BIO_POOL_IDX(bio));
+		bvec_free(bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
 
 		/*
 		 * If we have front padding, adjust the bio pointer before freeing
@@ -420,7 +424,6 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 	gfp_t saved_gfp = gfp_mask;
 	unsigned front_pad;
 	unsigned inline_vecs;
-	unsigned long idx = BIO_POOL_NONE;
 	struct bio_vec *bvl = NULL;
 	struct bio *bio;
 	void *p;
@@ -480,6 +483,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 	bio_init(bio);
 
 	if (nr_iovecs > inline_vecs) {
+		unsigned long idx = 0;
+
 		bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
 		if (!bvl && gfp_mask != saved_gfp) {
 			punt_bios_to_rescuer(bs);
@@ -490,13 +495,12 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		if (unlikely(!bvl))
 			goto err_free;
 
-		bio_set_flag(bio, BIO_OWNS_VEC);
+		bio->bi_flags |= idx << BVEC_POOL_OFFSET;
 	} else if (nr_iovecs) {
 		bvl = bio->bi_inline_vecs;
 	}
 
 	bio->bi_pool = bs;
-	bio->bi_flags |= idx << BIO_POOL_OFFSET;
 	bio->bi_max_vecs = nr_iovecs;
 	bio->bi_io_vec = bvl;
 	return bio;
@@ -568,7 +572,7 @@ EXPORT_SYMBOL(bio_phys_segments);
  */
 void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 {
-	BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE);
+	BUG_ON(bio->bi_pool && BVEC_POOL_IDX(bio));
 
 	/*
 	 * most users will be overriding ->bi_bdev with a new target,
@@ -656,16 +660,15 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
 	if (!bio)
 		return NULL;
-
 	bio->bi_bdev		= bio_src->bi_bdev;
 	bio->bi_rw		= bio_src->bi_rw;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		goto integrity_clone;
 
-	if (bio->bi_rw & REQ_WRITE_SAME) {
+	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
 		goto integrity_clone;
 	}
@@ -854,21 +857,20 @@ static void submit_bio_wait_endio(struct bio *bio)
 
 /**
  * submit_bio_wait - submit a bio, and wait until it completes
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
  * @bio: The &struct bio which describes the I/O
  *
  * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
  * bio_endio() on failure.
  */
-int submit_bio_wait(int rw, struct bio *bio)
+int submit_bio_wait(struct bio *bio)
 {
 	struct submit_bio_ret ret;
 
-	rw |= REQ_SYNC;
 	init_completion(&ret.event);
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
-	submit_bio(rw, bio);
+	bio->bi_rw |= REQ_SYNC;
+	submit_bio(bio);
 	wait_for_completion_io(&ret.event);
 
 	return ret.error;
@@ -1099,7 +1101,6 @@ int bio_uncopy_user(struct bio *bio)
 	bio_put(bio);
 	return ret;
 }
-EXPORT_SYMBOL(bio_uncopy_user);
 
 /**
  *	bio_copy_user_iov	-	copy user data to bio
@@ -1167,7 +1168,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 		goto out_bmd;
 
 	if (iter->type & WRITE)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	ret = 0;
 
@@ -1337,7 +1338,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	 * set data direction, and check if mapped pages need bouncing
 	 */
 	if (iter->type & WRITE)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	bio_set_flag(bio, BIO_USER_MAPPED);
 
@@ -1394,7 +1395,6 @@ void bio_unmap_user(struct bio *bio)
 	__bio_unmap_user(bio);
 	bio_put(bio);
 }
-EXPORT_SYMBOL(bio_unmap_user);
 
 static void bio_map_kern_endio(struct bio *bio)
 {
@@ -1530,7 +1530,7 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 		bio->bi_private = data;
 	} else {
 		bio->bi_end_io = bio_copy_kern_endio;
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	}
 
 	return bio;
@@ -1540,7 +1540,6 @@ cleanup:
 	bio_put(bio);
 	return ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL(bio_copy_kern);
 
 /*
  * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
@@ -1785,7 +1784,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	 * Discards need a mutable bio_vec to accommodate the payload
 	 * required by the DSM TRIM and UNMAP commands.
 	 */
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		split = bio_clone_bioset(bio, gfp, bs);
 	else
 		split = bio_clone_fast(bio, gfp, bs);
@@ -1834,7 +1833,7 @@ EXPORT_SYMBOL_GPL(bio_trim);
  */
 mempool_t *biovec_create_pool(int pool_entries)
 {
-	struct biovec_slab *bp = bvec_slabs + BIOVEC_MAX_IDX;
+	struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX;
 
 	return mempool_create_slab_pool(pool_entries, bp->slab);
 }
@@ -2011,7 +2010,7 @@ static void __init biovec_init_slabs(void)
 {
 	int i;
 
-	for (i = 0; i < BIOVEC_NR_POOLS; i++) {
+	for (i = 0; i < BVEC_POOL_NR; i++) {
 		int size;
 		struct biovec_slab *bvs = bvec_slabs + i;
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 66e6f1aae02e..dd38e5ced4a3 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -905,7 +905,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 	return 0;
 }
 
-struct cftype blkcg_files[] = {
+static struct cftype blkcg_files[] = {
 	{
 		.name = "stat",
 		.flags = CFTYPE_NOT_ON_ROOT,
@@ -914,7 +914,7 @@ struct cftype blkcg_files[] = {
 	{ }	/* terminate */
 };
 
-struct cftype blkcg_legacy_files[] = {
+static struct cftype blkcg_legacy_files[] = {
 	{
 		.name = "reset_stats",
 		.write_u64 = blkcg_reset_stats,
diff --git a/block/blk-core.c b/block/blk-core.c
index 2475b1c72773..a687e9cc16c2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -959,10 +959,10 @@ static void __freed_request(struct request_list *rl, int sync)
  * A request has just been released.  Account for it, update the full and
  * congestion status, wake up any waiters.   Called under q->queue_lock.
  */
-static void freed_request(struct request_list *rl, unsigned int flags)
+static void freed_request(struct request_list *rl, int op, unsigned int flags)
 {
 	struct request_queue *q = rl->q;
-	int sync = rw_is_sync(flags);
+	int sync = rw_is_sync(op, flags);
 
 	q->nr_rqs[sync]--;
 	rl->count[sync]--;
@@ -1029,7 +1029,7 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 	 * Flush requests do not use the elevator so skip initialization.
 	 * This allows a request to share the flush and elevator data.
 	 */
-	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
+	if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA))
 		return false;
 
 	return true;
@@ -1054,7 +1054,8 @@ static struct io_context *rq_ioc(struct bio *bio)
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
- * @rw_flags: RW and SYNC flags
+ * @op: REQ_OP_READ/REQ_OP_WRITE
+ * @op_flags: rq_flag_bits
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1065,21 +1066,22 @@ static struct io_context *rq_ioc(struct bio *bio)
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *__get_request(struct request_list *rl, int rw_flags,
-				     struct bio *bio, gfp_t gfp_mask)
+static struct request *__get_request(struct request_list *rl, int op,
+				     int op_flags, struct bio *bio,
+				     gfp_t gfp_mask)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
 	struct elevator_type *et = q->elevator->type;
 	struct io_context *ioc = rq_ioc(bio);
 	struct io_cq *icq = NULL;
-	const bool is_sync = rw_is_sync(rw_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	int may_queue;
 
 	if (unlikely(blk_queue_dying(q)))
 		return ERR_PTR(-ENODEV);
 
-	may_queue = elv_may_queue(q, rw_flags);
+	may_queue = elv_may_queue(q, op, op_flags);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
@@ -1123,7 +1125,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 
 	/*
 	 * Decide whether the new request will be managed by elevator.  If
-	 * so, mark @rw_flags and increment elvpriv.  Non-zero elvpriv will
+	 * so, mark @op_flags and increment elvpriv.  Non-zero elvpriv will
 	 * prevent the current elevator from being destroyed until the new
 	 * request is freed.  This guarantees icq's won't be destroyed and
 	 * makes creating new ones safe.
@@ -1132,14 +1134,14 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	 * it will be created after releasing queue_lock.
 	 */
 	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
-		rw_flags |= REQ_ELVPRIV;
+		op_flags |= REQ_ELVPRIV;
 		q->nr_rqs_elvpriv++;
 		if (et->icq_cache && ioc)
 			icq = ioc_lookup_icq(ioc, q);
 	}
 
 	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		op_flags |= REQ_IO_STAT;
 	spin_unlock_irq(q->queue_lock);
 
 	/* allocate and init request */
@@ -1149,10 +1151,10 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 
 	blk_rq_init(q, rq);
 	blk_rq_set_rl(rq, rl);
-	rq->cmd_flags = rw_flags | REQ_ALLOCED;
+	req_set_op_attrs(rq, op, op_flags | REQ_ALLOCED);
 
 	/* init elvpriv */
-	if (rw_flags & REQ_ELVPRIV) {
+	if (op_flags & REQ_ELVPRIV) {
 		if (unlikely(et->icq_cache && !icq)) {
 			if (ioc)
 				icq = ioc_create_icq(ioc, q, gfp_mask);
@@ -1178,7 +1180,7 @@ out:
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	trace_block_getrq(q, bio, rw_flags & 1);
+	trace_block_getrq(q, bio, op);
 	return rq;
 
 fail_elvpriv:
@@ -1208,7 +1210,7 @@ fail_alloc:
 	 * queue, but this is pretty rare.
 	 */
 	spin_lock_irq(q->queue_lock);
-	freed_request(rl, rw_flags);
+	freed_request(rl, op, op_flags);
 
 	/*
 	 * in the very unlikely event that allocation failed and no
@@ -1226,7 +1228,8 @@ rq_starved:
 /**
  * get_request - get a free request
  * @q: request_queue to allocate request from
- * @rw_flags: RW and SYNC flags
+ * @op: REQ_OP_READ/REQ_OP_WRITE
+ * @op_flags: rq_flag_bits
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1237,17 +1240,18 @@ rq_starved:
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *get_request(struct request_queue *q, int rw_flags,
-				   struct bio *bio, gfp_t gfp_mask)
+static struct request *get_request(struct request_queue *q, int op,
+				   int op_flags, struct bio *bio,
+				   gfp_t gfp_mask)
 {
-	const bool is_sync = rw_is_sync(rw_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	DEFINE_WAIT(wait);
 	struct request_list *rl;
 	struct request *rq;
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, rw_flags, bio, gfp_mask);
+	rq = __get_request(rl, op, op_flags, bio, gfp_mask);
 	if (!IS_ERR(rq))
 		return rq;
 
@@ -1260,7 +1264,7 @@ retry:
 	prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
 				  TASK_UNINTERRUPTIBLE);
 
-	trace_block_sleeprq(q, bio, rw_flags & 1);
+	trace_block_sleeprq(q, bio, op);
 
 	spin_unlock_irq(q->queue_lock);
 	io_schedule();
@@ -1289,11 +1293,16 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 	create_io_context(gfp_mask, q->node);
 
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, rw, NULL, gfp_mask);
-	if (IS_ERR(rq))
+	rq = get_request(q, rw, 0, NULL, gfp_mask);
+	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
-	/* q->queue_lock is unlocked at this point */
+		return rq;
+	}
 
+	/* q->queue_lock is unlocked at this point */
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
 	return rq;
 }
 
@@ -1309,63 +1318,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 EXPORT_SYMBOL(blk_get_request);
 
 /**
- * blk_make_request - given a bio, allocate a corresponding struct request.
- * @q: target request queue
- * @bio:  The bio describing the memory mappings that will be submitted for IO.
- *        It may be a chained-bio properly constructed by block/bio layer.
- * @gfp_mask: gfp flags to be used for memory allocation
- *
- * blk_make_request is the parallel of generic_make_request for BLOCK_PC
- * type commands. Where the struct request needs to be farther initialized by
- * the caller. It is passed a &struct bio, which describes the memory info of
- * the I/O transfer.
- *
- * The caller of blk_make_request must make sure that bi_io_vec
- * are set to describe the memory buffers. That bio_data_dir() will return
- * the needed direction of the request. (And all bio's in the passed bio-chain
- * are properly set accordingly)
- *
- * If called under none-sleepable conditions, mapped bio buffers must not
- * need bouncing, by calling the appropriate masked or flagged allocator,
- * suitable for the target device. Otherwise the call to blk_queue_bounce will
- * BUG.
- *
- * WARNING: When allocating/cloning a bio-chain, careful consideration should be
- * given to how you allocate bios. In particular, you cannot use
- * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise
- * you risk waiting for IO completion of a bio that hasn't been submitted yet,
- * thus resulting in a deadlock. Alternatively bios should be allocated using
- * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock.
- * If possible a big IO should be split into smaller parts when allocation
- * fails. Partial allocation should not be an error, or you risk a live-lock.
- */
-struct request *blk_make_request(struct request_queue *q, struct bio *bio,
-				 gfp_t gfp_mask)
-{
-	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
-
-	if (IS_ERR(rq))
-		return rq;
-
-	blk_rq_set_block_pc(rq);
-
-	for_each_bio(bio) {
-		struct bio *bounce_bio = bio;
-		int ret;
-
-		blk_queue_bounce(q, &bounce_bio);
-		ret = blk_rq_append_bio(q, rq, bounce_bio);
-		if (unlikely(ret)) {
-			blk_put_request(rq);
-			return ERR_PTR(ret);
-		}
-	}
-
-	return rq;
-}
-EXPORT_SYMBOL(blk_make_request);
-
-/**
  * blk_rq_set_block_pc - initialize a request to type BLOCK_PC
  * @rq:		request to be initialized
  *
@@ -1373,9 +1325,6 @@ EXPORT_SYMBOL(blk_make_request);
 void blk_rq_set_block_pc(struct request *rq)
 {
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->__data_len = 0;
-	rq->__sector = (sector_t) -1;
-	rq->bio = rq->biotail = NULL;
 	memset(rq->__cmd, 0, sizeof(rq->__cmd));
 }
 EXPORT_SYMBOL(blk_rq_set_block_pc);
@@ -1491,13 +1440,14 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	 */
 	if (req->cmd_flags & REQ_ALLOCED) {
 		unsigned int flags = req->cmd_flags;
+		int op = req_op(req);
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
-		freed_request(rl, flags);
+		freed_request(rl, op, flags);
 		blk_put_rl(rl);
 	}
 }
@@ -1712,7 +1662,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
 	struct blk_plug *plug;
-	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
+	int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
 	unsigned int request_count = 0;
 
@@ -1731,7 +1681,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+	if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
@@ -1772,15 +1722,19 @@ get_rq:
 	 * but we need to set it earlier to expose the sync flag to the
 	 * rq allocator and io schedulers.
 	 */
-	rw_flags = bio_data_dir(bio);
 	if (sync)
 		rw_flags |= REQ_SYNC;
 
 	/*
+	 * Add in META/PRIO flags, if set, before we get to the IO scheduler
+	 */
+	rw_flags |= (bio->bi_rw & (REQ_META | REQ_PRIO));
+
+	/*
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
-	req = get_request(q, rw_flags, bio, GFP_NOIO);
+	req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
 		bio->bi_error = PTR_ERR(req);
 		bio_endio(bio);
@@ -1849,7 +1803,7 @@ static void handle_bad_sector(struct bio *bio)
 	char b[BDEVNAME_SIZE];
 
 	printk(KERN_INFO "attempt to access beyond end of device\n");
-	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
+	printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n",
 			bdevname(bio->bi_bdev, b),
 			bio->bi_rw,
 			(unsigned long long)bio_end_sector(bio),
@@ -1964,25 +1918,30 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) &&
+	if ((bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
-		bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+		bio->bi_rw &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
 			err = 0;
 			goto end_io;
 		}
 	}
 
-	if ((bio->bi_rw & REQ_DISCARD) &&
-	    (!blk_queue_discard(q) ||
-	     ((bio->bi_rw & REQ_SECURE) && !blk_queue_secdiscard(q)))) {
-		err = -EOPNOTSUPP;
-		goto end_io;
-	}
-
-	if (bio->bi_rw & REQ_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
-		err = -EOPNOTSUPP;
-		goto end_io;
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+		if (!blk_queue_discard(q))
+			goto not_supported;
+		break;
+	case REQ_OP_SECURE_ERASE:
+		if (!blk_queue_secure_erase(q))
+			goto not_supported;
+		break;
+	case REQ_OP_WRITE_SAME:
+		if (!bdev_write_same(bio->bi_bdev))
+			goto not_supported;
+		break;
+	default:
+		break;
 	}
 
 	/*
@@ -1999,6 +1958,8 @@ generic_make_request_checks(struct bio *bio)
 	trace_block_bio_queue(q, bio);
 	return true;
 
+not_supported:
+	err = -EOPNOTSUPP;
 end_io:
 	bio->bi_error = err;
 	bio_endio(bio);
@@ -2094,7 +2055,6 @@ EXPORT_SYMBOL(generic_make_request);
 
 /**
  * submit_bio - submit a bio to the block device layer for I/O
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
  * @bio: The &struct bio which describes the I/O
  *
  * submit_bio() is very similar in purpose to generic_make_request(), and
@@ -2102,10 +2062,8 @@ EXPORT_SYMBOL(generic_make_request);
  * interfaces; @bio must be presetup and ready for I/O.
  *
  */
-blk_qc_t submit_bio(int rw, struct bio *bio)
+blk_qc_t submit_bio(struct bio *bio)
 {
-	bio->bi_rw |= rw;
-
 	/*
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.
@@ -2113,12 +2071,12 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 	if (bio_has_data(bio)) {
 		unsigned int count;
 
-		if (unlikely(rw & REQ_WRITE_SAME))
+		if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
 			count = bdev_logical_block_size(bio->bi_bdev) >> 9;
 		else
 			count = bio_sectors(bio);
 
-		if (rw & WRITE) {
+		if (op_is_write(bio_op(bio))) {
 			count_vm_events(PGPGOUT, count);
 		} else {
 			task_io_account_read(bio->bi_iter.bi_size);
@@ -2129,7 +2087,7 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 			char b[BDEVNAME_SIZE];
 			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
 			current->comm, task_pid_nr(current),
-				(rw & WRITE) ? "WRITE" : "READ",
+				op_is_write(bio_op(bio)) ? "WRITE" : "READ",
 				(unsigned long long)bio->bi_iter.bi_sector,
 				bdevname(bio->bi_bdev, b),
 				count);
@@ -2160,7 +2118,7 @@ EXPORT_SYMBOL(submit_bio);
 static int blk_cloned_rq_check_limits(struct request_queue *q,
 				      struct request *rq)
 {
-	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
+	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
 	}
@@ -2216,7 +2174,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
+	if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
 		where = ELEVATOR_INSERT_FLUSH;
 
 	add_acct_request(q, rq, where);
@@ -2979,8 +2937,7 @@ EXPORT_SYMBOL_GPL(__blk_end_request_err);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
-	rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
+	req_set_op(rq, bio_op(bio));
 
 	if (bio_has_data(bio))
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
@@ -3065,7 +3022,8 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+	req_set_op_attrs(dst, req_op(src),
+			 (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE);
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
@@ -3310,7 +3268,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA))
+		if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
 			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
 		else
 			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
@@ -3377,6 +3335,7 @@ bool blk_poll(struct request_queue *q, blk_qc_t cookie)
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(blk_poll);
 
 #ifdef CONFIG_PM
 /**
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 3fec8a29d0fa..7ea04325d02f 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -62,7 +62,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	/*
 	 * don't check dying flag for MQ because the request won't
-	 * be resued after dying flag is set
+	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
 		blk_mq_insert_request(rq, at_head, true, false);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index b1c91d229e5e..d308def812db 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -10,8 +10,8 @@
  * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
  * properties and hardware capability.
  *
- * If a request doesn't have data, only REQ_FLUSH makes sense, which
- * indicates a simple flush request.  If there is data, REQ_FLUSH indicates
+ * If a request doesn't have data, only REQ_PREFLUSH makes sense, which
+ * indicates a simple flush request.  If there is data, REQ_PREFLUSH indicates
  * that the device cache should be flushed before the data is executed, and
  * REQ_FUA means that the data must be on non-volatile media on request
  * completion.
@@ -20,16 +20,16 @@
  * difference.  The requests are either completed immediately if there's no
  * data or executed as normal requests otherwise.
  *
- * If the device has writeback cache and supports FUA, REQ_FLUSH is
+ * If the device has writeback cache and supports FUA, REQ_PREFLUSH is
  * translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
  *
- * If the device has writeback cache and doesn't support FUA, REQ_FLUSH is
- * translated to PREFLUSH and REQ_FUA to POSTFLUSH.
+ * If the device has writeback cache and doesn't support FUA, REQ_PREFLUSH
+ * is translated to PREFLUSH and REQ_FUA to POSTFLUSH.
  *
  * The actual execution of flush is double buffered.  Whenever a request
  * needs to execute PRE or POSTFLUSH, it queues at
  * fq->flush_queue[fq->flush_pending_idx].  Once certain criteria are met, a
- * flush is issued and the pending_idx is toggled.  When the flush
+ * REQ_OP_FLUSH is issued and the pending_idx is toggled.  When the flush
  * completes, all the requests which were pending are proceeded to the next
  * step.  This allows arbitrary merging of different types of FLUSH/FUA
  * requests.
@@ -103,7 +103,7 @@ static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
 		policy |= REQ_FSEQ_DATA;
 
 	if (fflags & (1UL << QUEUE_FLAG_WC)) {
-		if (rq->cmd_flags & REQ_FLUSH)
+		if (rq->cmd_flags & REQ_PREFLUSH)
 			policy |= REQ_FSEQ_PREFLUSH;
 		if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
 		    (rq->cmd_flags & REQ_FUA))
@@ -330,7 +330,7 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
-	flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ);
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
 
@@ -391,9 +391,9 @@ void blk_insert_flush(struct request *rq)
 
 	/*
 	 * @policy now records what operations need to be done.  Adjust
-	 * REQ_FLUSH and FUA for the driver.
+	 * REQ_PREFLUSH and FUA for the driver.
 	 */
-	rq->cmd_flags &= ~REQ_FLUSH;
+	rq->cmd_flags &= ~REQ_PREFLUSH;
 	if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
 		rq->cmd_flags &= ~REQ_FUA;
 
@@ -485,8 +485,9 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 
 	bio = bio_alloc(gfp_mask, 0);
 	bio->bi_bdev = bdev;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
 
-	ret = submit_bio_wait(WRITE_FLUSH, bio);
+	ret = submit_bio_wait(bio);
 
 	/*
 	 * The driver must store the error location in ->bi_sector, if
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9e29dc351695..083e56f72308 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -9,33 +9,46 @@
 
 #include "blk.h"
 
-static struct bio *next_bio(struct bio *bio, int rw, unsigned int nr_pages,
+static struct bio *next_bio(struct bio *bio, unsigned int nr_pages,
 		gfp_t gfp)
 {
 	struct bio *new = bio_alloc(gfp, nr_pages);
 
 	if (bio) {
 		bio_chain(bio, new);
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	}
 
 	return new;
 }
 
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop)
+		sector_t nr_sects, gfp_t gfp_mask, int flags,
+		struct bio **biop)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
 	unsigned int granularity;
+	enum req_op op;
 	int alignment;
 
 	if (!q)
 		return -ENXIO;
-	if (!blk_queue_discard(q))
-		return -EOPNOTSUPP;
-	if ((type & REQ_SECURE) && !blk_queue_secdiscard(q))
-		return -EOPNOTSUPP;
+
+	if (flags & BLKDEV_DISCARD_SECURE) {
+		if (flags & BLKDEV_DISCARD_ZERO)
+			return -EOPNOTSUPP;
+		if (!blk_queue_secure_erase(q))
+			return -EOPNOTSUPP;
+		op = REQ_OP_SECURE_ERASE;
+	} else {
+		if (!blk_queue_discard(q))
+			return -EOPNOTSUPP;
+		if ((flags & BLKDEV_DISCARD_ZERO) &&
+		    !q->limits.discard_zeroes_data)
+			return -EOPNOTSUPP;
+		op = REQ_OP_DISCARD;
+	}
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
@@ -62,9 +75,10 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			req_sects = end_sect - sector;
 		}
 
-		bio = next_bio(bio, type, 1, gfp_mask);
+		bio = next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
+		bio_set_op_attrs(bio, op, 0);
 
 		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
@@ -98,20 +112,16 @@ EXPORT_SYMBOL(__blkdev_issue_discard);
 int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
 {
-	int type = REQ_WRITE | REQ_DISCARD;
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 	int ret;
 
-	if (flags & BLKDEV_DISCARD_SECURE)
-		type |= REQ_SECURE;
-
 	blk_start_plug(&plug);
-	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, type,
+	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
 			&bio);
 	if (!ret && bio) {
-		ret = submit_bio_wait(type, bio);
-		if (ret == -EOPNOTSUPP)
+		ret = submit_bio_wait(bio);
+		if (ret == -EOPNOTSUPP && !(flags & BLKDEV_DISCARD_ZERO))
 			ret = 0;
 		bio_put(bio);
 	}
@@ -148,13 +158,14 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	max_write_same_sectors = UINT_MAX >> 9;
 
 	while (nr_sects) {
-		bio = next_bio(bio, REQ_WRITE | REQ_WRITE_SAME, 1, gfp_mask);
+		bio = next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
 		bio->bi_vcnt = 1;
 		bio->bi_io_vec->bv_page = page;
 		bio->bi_io_vec->bv_offset = 0;
 		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
+		bio_set_op_attrs(bio, REQ_OP_WRITE_SAME, 0);
 
 		if (nr_sects > max_write_same_sectors) {
 			bio->bi_iter.bi_size = max_write_same_sectors << 9;
@@ -167,10 +178,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	}
 
 	if (bio) {
-		ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio);
+		ret = submit_bio_wait(bio);
 		bio_put(bio);
 	}
-	return ret != -EOPNOTSUPP ? ret : 0;
+	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
 
@@ -193,11 +204,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	unsigned int sz;
 
 	while (nr_sects != 0) {
-		bio = next_bio(bio, WRITE,
-				min(nr_sects, (sector_t)BIO_MAX_PAGES),
+		bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES),
 				gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev   = bdev;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
@@ -210,7 +221,7 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	}
 
 	if (bio) {
-		ret = submit_bio_wait(WRITE, bio);
+		ret = submit_bio_wait(bio);
 		bio_put(bio);
 		return ret;
 	}
@@ -241,11 +252,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data &&
-	    blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0) == 0)
-		return 0;
+	if (discard) {
+		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
+				BLKDEV_DISCARD_ZERO))
+			return 0;
+	}
 
 	if (bdev_write_same(bdev) &&
 	    blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
diff --git a/block/blk-map.c b/block/blk-map.c
index b9f88b7751fb..b8657fa8dc9a 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -9,21 +9,26 @@
 
 #include "blk.h"
 
-int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-		      struct bio *bio)
+/*
+ * Append a bio to a passthrough request.  Only works can be merged into
+ * the request based on the driver constraints.
+ */
+int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
-	if (!rq->bio)
-		blk_rq_bio_prep(q, rq, bio);
-	else if (!ll_back_merge_fn(q, rq, bio))
-		return -EINVAL;
-	else {
+	if (!rq->bio) {
+		blk_rq_bio_prep(rq->q, rq, bio);
+	} else {
+		if (!ll_back_merge_fn(rq->q, rq, bio))
+			return -EINVAL;
+
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
-
 		rq->__data_len += bio->bi_iter.bi_size;
 	}
+
 	return 0;
 }
+EXPORT_SYMBOL(blk_rq_append_bio);
 
 static int __blk_rq_unmap_user(struct bio *bio)
 {
@@ -71,7 +76,7 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	 */
 	bio_get(bio);
 
-	ret = blk_rq_append_bio(q, rq, bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (ret) {
 		bio_endio(bio);
 		__blk_rq_unmap_user(orig_bio);
@@ -224,12 +229,12 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		return PTR_ERR(bio);
 
 	if (!reading)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
 
-	ret = blk_rq_append_bio(q, rq, bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (unlikely(ret)) {
 		/* request is too big */
 		bio_put(bio);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 261353166dcf..41cbd4878958 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -172,9 +172,9 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 	struct bio *split, *res;
 	unsigned nsegs;
 
-	if ((*bio)->bi_rw & REQ_DISCARD)
+	if (bio_op(*bio) == REQ_OP_DISCARD)
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
-	else if ((*bio)->bi_rw & REQ_WRITE_SAME)
+	else if (bio_op(*bio) == REQ_OP_WRITE_SAME)
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
 	else
 		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
@@ -213,10 +213,10 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	 * This should probably be returning 0, but blk_add_request_payload()
 	 * (Christoph!!!!)
 	 */
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		return 1;
 
-	if (bio->bi_rw & REQ_WRITE_SAME)
+	if (bio_op(bio) == REQ_OP_WRITE_SAME)
 		return 1;
 
 	fbio = bio;
@@ -385,7 +385,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	if (bio->bi_rw & REQ_DISCARD) {
+	if (bio_op(bio) == REQ_OP_DISCARD) {
 		/*
 		 * This is a hack - drivers should be neither modifying the
 		 * biovec, nor relying on bi_vcnt - but because of
@@ -400,7 +400,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 		return 0;
 	}
 
-	if (bio->bi_rw & REQ_WRITE_SAME) {
+	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
 single_segment:
 		*sg = sglist;
 		bvec = bio_iovec(bio);
@@ -439,7 +439,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	}
 
 	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
-		if (rq->cmd_flags & REQ_WRITE)
+		if (op_is_write(req_op(rq)))
 			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
 
 		sg_unmark_end(sg);
@@ -500,7 +500,7 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 	    integrity_req_gap_back_merge(req, bio))
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
-	    blk_rq_get_max_sectors(req)) {
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -524,7 +524,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	    integrity_req_gap_front_merge(req, bio))
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
-	    blk_rq_get_max_sectors(req)) {
+	    blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -570,7 +570,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	 * Will it become too large?
 	 */
 	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
-	    blk_rq_get_max_sectors(req))
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
@@ -649,7 +649,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (!rq_mergeable(req) || !rq_mergeable(next))
 		return 0;
 
-	if (!blk_check_merge_flags(req->cmd_flags, next->cmd_flags))
+	if (req_op(req) != req_op(next))
 		return 0;
 
 	/*
@@ -663,7 +663,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	    || req_no_special_merge(next))
 		return 0;
 
-	if (req->cmd_flags & REQ_WRITE_SAME &&
+	if (req_op(req) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(req->bio, next->bio))
 		return 0;
 
@@ -743,6 +743,12 @@ int attempt_front_merge(struct request_queue *q, struct request *rq)
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 			  struct request *next)
 {
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.elevator_allow_rq_merge_fn)
+		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+			return 0;
+
 	return attempt_merge(q, rq, next);
 }
 
@@ -751,7 +757,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
-	if (!blk_check_merge_flags(rq->cmd_flags, bio->bi_rw))
+	if (req_op(rq) != bio_op(bio))
 		return false;
 
 	/* different data direction or already started, don't merge */
@@ -767,7 +773,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 		return false;
 
 	/* must be using the same buffer */
-	if (rq->cmd_flags & REQ_WRITE_SAME &&
+	if (req_op(rq) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 56a0c37a3d06..729bac3a673b 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -485,6 +485,32 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
+int blk_mq_reinit_tagset(struct blk_mq_tag_set *set)
+{
+	int i, j, ret = 0;
+
+	if (!set->ops->reinit_request)
+		goto out;
+
+	for (i = 0; i < set->nr_hw_queues; i++) {
+		struct blk_mq_tags *tags = set->tags[i];
+
+		for (j = 0; j < tags->nr_tags; j++) {
+			if (!tags->rqs[j])
+				continue;
+
+			ret = set->ops->reinit_request(set->driver_data,
+						tags->rqs[j]);
+			if (ret)
+				goto out;
+		}
+	}
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blk_mq_reinit_tagset);
+
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f9b9049b1284..576e7112f807 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -159,16 +159,17 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 EXPORT_SYMBOL(blk_mq_can_queue);
 
 static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, unsigned int rw_flags)
+			       struct request *rq, int op,
+			       unsigned int op_flags)
 {
 	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		op_flags |= REQ_IO_STAT;
 
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
 	rq->q = q;
 	rq->mq_ctx = ctx;
-	rq->cmd_flags |= rw_flags;
+	req_set_op_attrs(rq, op, op_flags);
 	/* do not touch atomic flags, it needs atomic ops against the timer */
 	rq->cpu = -1;
 	INIT_HLIST_NODE(&rq->hash);
@@ -203,11 +204,11 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
-	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
+	ctx->rq_dispatched[rw_is_sync(op, op_flags)]++;
 }
 
 static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
+__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -222,7 +223,7 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
 		}
 
 		rq->tag = tag;
-		blk_mq_rq_ctx_init(data->q, data->ctx, rq, rw);
+		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags);
 		return rq;
 	}
 
@@ -246,7 +247,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
 
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
+	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
 	if (!rq && !(flags & BLK_MQ_REQ_NOWAIT)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
@@ -254,7 +255,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
 		blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-		rq =  __blk_mq_alloc_request(&alloc_data, rw);
+		rq =  __blk_mq_alloc_request(&alloc_data, rw, 0);
 		ctx = alloc_data.ctx;
 	}
 	blk_mq_put_ctx(ctx);
@@ -262,10 +263,53 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		blk_queue_exit(q);
 		return ERR_PTR(-EWOULDBLOCK);
 	}
+
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
 	return rq;
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
+		unsigned int flags, unsigned int hctx_idx)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	struct request *rq;
+	struct blk_mq_alloc_data alloc_data;
+	int ret;
+
+	/*
+	 * If the tag allocator sleeps we could get an allocation for a
+	 * different hardware context.  No need to complicate the low level
+	 * allocator for this for the rare use case of a command tied to
+	 * a specific queue.
+	 */
+	if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)))
+		return ERR_PTR(-EINVAL);
+
+	if (hctx_idx >= q->nr_hw_queues)
+		return ERR_PTR(-EIO);
+
+	ret = blk_queue_enter(q, true);
+	if (ret)
+		return ERR_PTR(ret);
+
+	hctx = q->queue_hw_ctx[hctx_idx];
+	ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
+
+	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
+	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
+	if (!rq) {
+		blk_queue_exit(q);
+		return ERR_PTR(-EWOULDBLOCK);
+	}
+
+	return rq;
+}
+EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
+
 static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 				  struct blk_mq_ctx *ctx, struct request *rq)
 {
@@ -784,7 +828,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
 			queued++;
-			continue;
+			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
 			list_add(&rq->queuelist, &rq_list);
 			__blk_mq_requeue_request(rq);
@@ -1169,28 +1213,29 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct request *rq;
-	int rw = bio_data_dir(bio);
+	int op = bio_data_dir(bio);
+	int op_flags = 0;
 	struct blk_mq_alloc_data alloc_data;
 
 	blk_queue_enter_live(q);
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rw_is_sync(bio->bi_rw))
-		rw |= REQ_SYNC;
+	if (rw_is_sync(bio_op(bio), bio->bi_rw))
+		op_flags |= REQ_SYNC;
 
-	trace_block_getrq(q, bio, rw);
+	trace_block_getrq(q, bio, op);
 	blk_mq_set_alloc_data(&alloc_data, q, BLK_MQ_REQ_NOWAIT, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
+	rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
 	if (unlikely(!rq)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
-		trace_block_sleeprq(q, bio, rw);
+		trace_block_sleeprq(q, bio, op);
 
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
 		blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
-		rq = __blk_mq_alloc_request(&alloc_data, rw);
+		rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
 		ctx = alloc_data.ctx;
 		hctx = alloc_data.hctx;
 	}
@@ -1244,8 +1289,8 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
  */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
+	const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
 	unsigned int request_count = 0;
@@ -1338,8 +1383,8 @@ done:
  */
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
+	const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
 	struct blk_map_ctx data;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 99205965f559..f87a7e747d36 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -379,6 +379,11 @@ static ssize_t queue_wc_store(struct request_queue *q, const char *page,
 	return count;
 }
 
+static ssize_t queue_dax_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_dax(q), page);
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -516,6 +521,11 @@ static struct queue_sysfs_entry queue_wc_entry = {
 	.store = queue_wc_store,
 };
 
+static struct queue_sysfs_entry queue_dax_entry = {
+	.attr = {.name = "dax", .mode = S_IRUGO },
+	.show = queue_dax_show,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -542,6 +552,7 @@ static struct attribute *default_attrs[] = {
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
+	&queue_dax_entry.attr,
 	NULL,
 };
 
diff --git a/block/blk.h b/block/blk.h
index 70e4aee9cdcb..c37492f5edaa 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -64,8 +64,6 @@ void blk_exit_rl(struct request_list *rl);
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
-int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-		      struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
 void blk_queue_bypass_end(struct request_queue *q);
 void blk_dequeue_request(struct request *rq);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 4a349787bc62..acabba198de9 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
-#include <linux/jiffies.h>
+#include <linux/ktime.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 #include <linux/blktrace_api.h>
@@ -22,28 +22,28 @@
  */
 /* max queue in one round of service */
 static const int cfq_quantum = 8;
-static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
+static const u64 cfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
 /* maximum backwards seek, in KiB */
 static const int cfq_back_max = 16 * 1024;
 /* penalty of a backwards seek */
 static const int cfq_back_penalty = 2;
-static const int cfq_slice_sync = HZ / 10;
-static int cfq_slice_async = HZ / 25;
+static const u64 cfq_slice_sync = NSEC_PER_SEC / 10;
+static u64 cfq_slice_async = NSEC_PER_SEC / 25;
 static const int cfq_slice_async_rq = 2;
-static int cfq_slice_idle = HZ / 125;
-static int cfq_group_idle = HZ / 125;
-static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
+static u64 cfq_slice_idle = NSEC_PER_SEC / 125;
+static u64 cfq_group_idle = NSEC_PER_SEC / 125;
+static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
 /*
  * offset from end of service tree
  */
-#define CFQ_IDLE_DELAY		(HZ / 5)
+#define CFQ_IDLE_DELAY		(NSEC_PER_SEC / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
  */
-#define CFQ_MIN_TT		(2)
+#define CFQ_MIN_TT		(2 * NSEC_PER_SEC / HZ)
 
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_HW_QUEUE_MIN	(5)
@@ -73,11 +73,11 @@ static struct kmem_cache *cfq_pool;
 #define CFQ_WEIGHT_LEGACY_MAX	1000
 
 struct cfq_ttime {
-	unsigned long last_end_request;
+	u64 last_end_request;
 
-	unsigned long ttime_total;
+	u64 ttime_total;
+	u64 ttime_mean;
 	unsigned long ttime_samples;
-	unsigned long ttime_mean;
 };
 
 /*
@@ -94,7 +94,7 @@ struct cfq_rb_root {
 	struct cfq_ttime ttime;
 };
 #define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, \
-			.ttime = {.last_end_request = jiffies,},}
+			.ttime = {.last_end_request = ktime_get_ns(),},}
 
 /*
  * Per process-grouping structure
@@ -109,7 +109,7 @@ struct cfq_queue {
 	/* service_tree member */
 	struct rb_node rb_node;
 	/* service_tree key */
-	unsigned long rb_key;
+	u64 rb_key;
 	/* prio tree member */
 	struct rb_node p_node;
 	/* prio tree root we belong to, if any */
@@ -126,13 +126,13 @@ struct cfq_queue {
 	struct list_head fifo;
 
 	/* time when queue got scheduled in to dispatch first request. */
-	unsigned long dispatch_start;
-	unsigned int allocated_slice;
-	unsigned int slice_dispatch;
+	u64 dispatch_start;
+	u64 allocated_slice;
+	u64 slice_dispatch;
 	/* time when first request from queue completed and slice started. */
-	unsigned long slice_start;
-	unsigned long slice_end;
-	long slice_resid;
+	u64 slice_start;
+	u64 slice_end;
+	s64 slice_resid;
 
 	/* pending priority requests */
 	int prio_pending;
@@ -141,7 +141,7 @@ struct cfq_queue {
 
 	/* io prio of this group */
 	unsigned short ioprio, org_ioprio;
-	unsigned short ioprio_class;
+	unsigned short ioprio_class, org_ioprio_class;
 
 	pid_t pid;
 
@@ -290,7 +290,7 @@ struct cfq_group {
 	struct cfq_rb_root service_trees[2][3];
 	struct cfq_rb_root service_tree_idle;
 
-	unsigned long saved_wl_slice;
+	u64 saved_wl_slice;
 	enum wl_type_t saved_wl_type;
 	enum wl_class_t saved_wl_class;
 
@@ -329,7 +329,7 @@ struct cfq_data {
 	 */
 	enum wl_class_t serving_wl_class;
 	enum wl_type_t serving_wl_type;
-	unsigned long workload_expires;
+	u64 workload_expires;
 	struct cfq_group *serving_group;
 
 	/*
@@ -362,7 +362,7 @@ struct cfq_data {
 	/*
 	 * idle window management
 	 */
-	struct timer_list idle_slice_timer;
+	struct hrtimer idle_slice_timer;
 	struct work_struct unplug_work;
 
 	struct cfq_queue *active_queue;
@@ -374,22 +374,22 @@ struct cfq_data {
 	 * tunables, see top of file
 	 */
 	unsigned int cfq_quantum;
-	unsigned int cfq_fifo_expire[2];
 	unsigned int cfq_back_penalty;
 	unsigned int cfq_back_max;
-	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
-	unsigned int cfq_slice_idle;
-	unsigned int cfq_group_idle;
 	unsigned int cfq_latency;
-	unsigned int cfq_target_latency;
+	u64 cfq_fifo_expire[2];
+	u64 cfq_slice[2];
+	u64 cfq_slice_idle;
+	u64 cfq_group_idle;
+	u64 cfq_target_latency;
 
 	/*
 	 * Fallback dummy cfqq for extreme OOM conditions
 	 */
 	struct cfq_queue oom_cfqq;
 
-	unsigned long last_delayed_sync;
+	u64 last_delayed_sync;
 };
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
@@ -667,15 +667,16 @@ static inline void cfqg_put(struct cfq_group *cfqg)
 } while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-					    struct cfq_group *curr_cfqg, int rw)
+					    struct cfq_group *curr_cfqg, int op,
+					    int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, rw, 1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, 1);
 	cfqg_stats_end_empty_time(&cfqg->stats);
 	cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg);
 }
 
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
-			unsigned long time, unsigned long unaccounted_time)
+			uint64_t time, unsigned long unaccounted_time)
 {
 	blkg_stat_add(&cfqg->stats.time, time);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
@@ -683,26 +684,30 @@ static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
 #endif
 }
 
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw)
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
+					       int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, rw, -1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, -1);
 }
 
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw)
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
+					       int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.merged, rw, 1);
+	blkg_rwstat_add(&cfqg->stats.merged, op, op_flags, 1);
 }
 
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw)
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags)
 {
 	struct cfqg_stats *stats = &cfqg->stats;
 	unsigned long long now = sched_clock();
 
 	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, rw, now - io_start_time);
+		blkg_rwstat_add(&stats->service_time, op, op_flags,
+				now - io_start_time);
 	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, rw,
+		blkg_rwstat_add(&stats->wait_time, op, op_flags,
 				io_start_time - start_time);
 }
 
@@ -781,13 +786,16 @@ static inline void cfqg_put(struct cfq_group *cfqg) { }
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-			struct cfq_group *curr_cfqg, int rw) { }
+			struct cfq_group *curr_cfqg, int op, int op_flags) { }
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
-			unsigned long time, unsigned long unaccounted_time) { }
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw) { }
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw) { }
+			uint64_t time, unsigned long unaccounted_time) { }
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
+			int op_flags) { }
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
+			int op_flags) { }
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw) { }
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags) { }
 
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 
@@ -807,7 +815,7 @@ static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
 static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
 	struct cfq_ttime *ttime, bool group_idle)
 {
-	unsigned long slice;
+	u64 slice;
 	if (!sample_valid(ttime->ttime_samples))
 		return false;
 	if (group_idle)
@@ -930,17 +938,18 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
  * if a queue is marked sync and has sync io queued. A sync queue with async
  * io only, should not get full sync slice length.
  */
-static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
+static inline u64 cfq_prio_slice(struct cfq_data *cfqd, bool sync,
 				 unsigned short prio)
 {
-	const int base_slice = cfqd->cfq_slice[sync];
+	u64 base_slice = cfqd->cfq_slice[sync];
+	u64 slice = div_u64(base_slice, CFQ_SLICE_SCALE);
 
 	WARN_ON(prio >= IOPRIO_BE_NR);
 
-	return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
+	return base_slice + (slice * (4 - prio));
 }
 
-static inline int
+static inline u64
 cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
@@ -958,15 +967,14 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  *
  * The result is also in fixed point w/ CFQ_SERVICE_SHIFT.
  */
-static inline u64 cfqg_scale_charge(unsigned long charge,
+static inline u64 cfqg_scale_charge(u64 charge,
 				    unsigned int vfraction)
 {
 	u64 c = charge << CFQ_SERVICE_SHIFT;	/* make it fixed point */
 
 	/* charge / vfraction */
 	c <<= CFQ_SERVICE_SHIFT;
-	do_div(c, vfraction);
-	return c;
+	return div_u64(c, vfraction);
 }
 
 static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
@@ -1019,16 +1027,16 @@ static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
 	return cfqg->busy_queues_avg[rt];
 }
 
-static inline unsigned
+static inline u64
 cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	return cfqd->cfq_target_latency * cfqg->vfraction >> CFQ_SERVICE_SHIFT;
 }
 
-static inline unsigned
+static inline u64
 cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
+	u64 slice = cfq_prio_to_slice(cfqd, cfqq);
 	if (cfqd->cfq_latency) {
 		/*
 		 * interested queues (we consider only the ones with the same
@@ -1036,20 +1044,22 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		 */
 		unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
 						cfq_class_rt(cfqq));
-		unsigned sync_slice = cfqd->cfq_slice[1];
-		unsigned expect_latency = sync_slice * iq;
-		unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
+		u64 sync_slice = cfqd->cfq_slice[1];
+		u64 expect_latency = sync_slice * iq;
+		u64 group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
 
 		if (expect_latency > group_slice) {
-			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
+			u64 base_low_slice = 2 * cfqd->cfq_slice_idle;
+			u64 low_slice;
+
 			/* scale low_slice according to IO priority
 			 * and sync vs async */
-			unsigned low_slice =
-				min(slice, base_low_slice * slice / sync_slice);
+			low_slice = div64_u64(base_low_slice*slice, sync_slice);
+			low_slice = min(slice, low_slice);
 			/* the adapted slice value is scaled to fit all iqs
 			 * into the target latency */
-			slice = max(slice * group_slice / expect_latency,
-				    low_slice);
+			slice = div64_u64(slice*group_slice, expect_latency);
+			slice = max(slice, low_slice);
 		}
 	}
 	return slice;
@@ -1058,12 +1068,13 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+	u64 slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+	u64 now = ktime_get_ns();
 
-	cfqq->slice_start = jiffies;
-	cfqq->slice_end = jiffies + slice;
+	cfqq->slice_start = now;
+	cfqq->slice_end = now + slice;
 	cfqq->allocated_slice = slice;
-	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
+	cfq_log_cfqq(cfqd, cfqq, "set_slice=%llu", cfqq->slice_end - now);
 }
 
 /*
@@ -1075,7 +1086,7 @@ static inline bool cfq_slice_used(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_slice_new(cfqq))
 		return false;
-	if (time_before(jiffies, cfqq->slice_end))
+	if (ktime_get_ns() < cfqq->slice_end)
 		return false;
 
 	return true;
@@ -1241,8 +1252,8 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
 }
 
-static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
-				      struct cfq_queue *cfqq)
+static u64 cfq_slice_offset(struct cfq_data *cfqd,
+			    struct cfq_queue *cfqq)
 {
 	/*
 	 * just an approximation, should be ok.
@@ -1435,31 +1446,32 @@ cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	cfqg_stats_update_dequeue(cfqg);
 }
 
-static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
-						unsigned int *unaccounted_time)
+static inline u64 cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
+				       u64 *unaccounted_time)
 {
-	unsigned int slice_used;
+	u64 slice_used;
+	u64 now = ktime_get_ns();
 
 	/*
 	 * Queue got expired before even a single request completed or
 	 * got expired immediately after first request completion.
 	 */
-	if (!cfqq->slice_start || cfqq->slice_start == jiffies) {
+	if (!cfqq->slice_start || cfqq->slice_start == now) {
 		/*
 		 * Also charge the seek time incurred to the group, otherwise
 		 * if there are mutiple queues in the group, each can dispatch
 		 * a single request on seeky media and cause lots of seek time
 		 * and group will never know it.
 		 */
-		slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start),
-					1);
+		slice_used = max_t(u64, (now - cfqq->dispatch_start),
+					jiffies_to_nsecs(1));
 	} else {
-		slice_used = jiffies - cfqq->slice_start;
+		slice_used = now - cfqq->slice_start;
 		if (slice_used > cfqq->allocated_slice) {
 			*unaccounted_time = slice_used - cfqq->allocated_slice;
 			slice_used = cfqq->allocated_slice;
 		}
-		if (time_after(cfqq->slice_start, cfqq->dispatch_start))
+		if (cfqq->slice_start > cfqq->dispatch_start)
 			*unaccounted_time += cfqq->slice_start -
 					cfqq->dispatch_start;
 	}
@@ -1471,10 +1483,11 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl, charge, unaccounted_sl = 0;
+	u64 used_sl, charge, unaccounted_sl = 0;
 	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
 			- cfqg->service_tree_idle.count;
 	unsigned int vfr;
+	u64 now = ktime_get_ns();
 
 	BUG_ON(nr_sync < 0);
 	used_sl = charge = cfq_cfqq_slice_usage(cfqq, &unaccounted_sl);
@@ -1496,9 +1509,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
-	if (time_after(cfqd->workload_expires, jiffies)) {
-		cfqg->saved_wl_slice = cfqd->workload_expires
-						- jiffies;
+	if (cfqd->workload_expires > now) {
+		cfqg->saved_wl_slice = cfqd->workload_expires - now;
 		cfqg->saved_wl_type = cfqd->serving_wl_type;
 		cfqg->saved_wl_class = cfqd->serving_wl_class;
 	} else
@@ -1507,7 +1519,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
 					st->min_vdisktime);
 	cfq_log_cfqq(cfqq->cfqd, cfqq,
-		     "sl_used=%u disp=%u charge=%u iops=%u sect=%lu",
+		     "sl_used=%llu disp=%llu charge=%llu iops=%u sect=%lu",
 		     used_sl, cfqq->slice_dispatch, charge,
 		     iops_mode(cfqd), cfqq->nr_sectors);
 	cfqg_stats_update_timeslice_used(cfqg, used_sl, unaccounted_sl);
@@ -1530,7 +1542,7 @@ static void cfq_init_cfqg_base(struct cfq_group *cfqg)
 		*st = CFQ_RB_ROOT;
 	RB_CLEAR_NODE(&cfqg->rb_node);
 
-	cfqg->ttime.last_end_request = jiffies;
+	cfqg->ttime.last_end_request = ktime_get_ns();
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
@@ -2213,10 +2225,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 {
 	struct rb_node **p, *parent;
 	struct cfq_queue *__cfqq;
-	unsigned long rb_key;
+	u64 rb_key;
 	struct cfq_rb_root *st;
 	int left;
 	int new_cfqq = 1;
+	u64 now = ktime_get_ns();
 
 	st = st_for(cfqq->cfqg, cfqq_class(cfqq), cfqq_type(cfqq));
 	if (cfq_class_idle(cfqq)) {
@@ -2226,7 +2239,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
 			rb_key += __cfqq->rb_key;
 		} else
-			rb_key += jiffies;
+			rb_key += now;
 	} else if (!add_front) {
 		/*
 		 * Get our rb key offset. Subtract any residual slice
@@ -2234,13 +2247,13 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * count indicates slice overrun, and this should position
 		 * the next service time further away in the tree.
 		 */
-		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
+		rb_key = cfq_slice_offset(cfqd, cfqq) + now;
 		rb_key -= cfqq->slice_resid;
 		cfqq->slice_resid = 0;
 	} else {
-		rb_key = -HZ;
+		rb_key = -NSEC_PER_SEC;
 		__cfqq = cfq_rb_first(st);
-		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+		rb_key += __cfqq ? __cfqq->rb_key : now;
 	}
 
 	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
@@ -2266,7 +2279,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * sort by key, that represents service time.
 		 */
-		if (time_before(rb_key, __cfqq->rb_key))
+		if (rb_key < __cfqq->rb_key)
 			p = &parent->rb_left;
 		else {
 			p = &parent->rb_right;
@@ -2461,10 +2474,10 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
 {
 	elv_rb_del(&cfqq->sort_list, rq);
 	cfqq->queued[rq_is_sync(rq)]--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
 	cfq_add_rq_rb(rq);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group,
-				 rq->cmd_flags);
+				 req_op(rq), rq->cmd_flags);
 }
 
 static struct request *
@@ -2517,7 +2530,7 @@ static void cfq_remove_request(struct request *rq)
 	cfq_del_rq_rb(rq);
 
 	cfqq->cfqd->rq_queued--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
 	if (rq->cmd_flags & REQ_PRIO) {
 		WARN_ON(!cfqq->prio_pending);
 		cfqq->prio_pending--;
@@ -2531,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req,
 	struct request *__rq;
 
 	__rq = cfq_find_rq_fmerge(cfqd, bio);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_FRONT_MERGE;
 	}
@@ -2552,7 +2565,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req,
 static void cfq_bio_merged(struct request_queue *q, struct request *req,
 				struct bio *bio)
 {
-	cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_rw);
+	cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_rw);
 }
 
 static void
@@ -2566,7 +2579,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(next->fifo_time, rq->fifo_time) &&
+	    next->fifo_time < rq->fifo_time &&
 	    cfqq == RQ_CFQQ(next)) {
 		list_move(&rq->queuelist, &next->queuelist);
 		rq->fifo_time = next->fifo_time;
@@ -2575,7 +2588,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	if (cfqq->next_rq == next)
 		cfqq->next_rq = rq;
 	cfq_remove_request(next);
-	cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags);
+	cfqg_stats_update_io_merged(RQ_CFQG(rq), req_op(next), next->cmd_flags);
 
 	cfqq = RQ_CFQQ(next);
 	/*
@@ -2588,8 +2601,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 		cfq_del_cfqq_rr(cfqd, cfqq);
 }
 
-static int cfq_allow_merge(struct request_queue *q, struct request *rq,
-			   struct bio *bio)
+static int cfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+			       struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_io_cq *cic;
@@ -2613,9 +2626,15 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	return cfqq == RQ_CFQQ(rq);
 }
 
+static int cfq_allow_rq_merge(struct request_queue *q, struct request *rq,
+			      struct request *next)
+{
+	return RQ_CFQQ(rq) == RQ_CFQQ(next);
+}
+
 static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	del_timer(&cfqd->idle_slice_timer);
+	hrtimer_try_to_cancel(&cfqd->idle_slice_timer);
 	cfqg_stats_update_idle_time(cfqq->cfqg);
 }
 
@@ -2627,7 +2646,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				cfqd->serving_wl_class, cfqd->serving_wl_type);
 		cfqg_stats_update_avg_queue_size(cfqq->cfqg);
 		cfqq->slice_start = 0;
-		cfqq->dispatch_start = jiffies;
+		cfqq->dispatch_start = ktime_get_ns();
 		cfqq->allocated_slice = 0;
 		cfqq->slice_end = 0;
 		cfqq->slice_dispatch = 0;
@@ -2676,8 +2695,8 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (cfq_cfqq_slice_new(cfqq))
 			cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
 		else
-			cfqq->slice_resid = cfqq->slice_end - jiffies;
-		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+			cfqq->slice_resid = cfqq->slice_end - ktime_get_ns();
+		cfq_log_cfqq(cfqd, cfqq, "resid=%lld", cfqq->slice_resid);
 	}
 
 	cfq_group_served(cfqd, cfqq->cfqg, cfqq);
@@ -2911,7 +2930,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq = cfqd->active_queue;
 	struct cfq_rb_root *st = cfqq->service_tree;
 	struct cfq_io_cq *cic;
-	unsigned long sl, group_idle = 0;
+	u64 sl, group_idle = 0;
+	u64 now = ktime_get_ns();
 
 	/*
 	 * SSD device without seek penalty, disable idling. But only do so
@@ -2954,8 +2974,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 * time slice.
 	 */
 	if (sample_valid(cic->ttime.ttime_samples) &&
-	    (cfqq->slice_end - jiffies < cic->ttime.ttime_mean)) {
-		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu",
+	    (cfqq->slice_end - now < cic->ttime.ttime_mean)) {
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%llu",
 			     cic->ttime.ttime_mean);
 		return;
 	}
@@ -2976,9 +2996,10 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	else
 		sl = cfqd->cfq_slice_idle;
 
-	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	hrtimer_start(&cfqd->idle_slice_timer, ns_to_ktime(sl),
+		      HRTIMER_MODE_REL);
 	cfqg_stats_set_start_idle_time(cfqq->cfqg);
-	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %llu group_idle: %d", sl,
 			group_idle ? 1 : 0);
 }
 
@@ -3018,7 +3039,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 		return NULL;
 
 	rq = rq_entry_fifo(cfqq->fifo.next);
-	if (time_before(jiffies, rq->fifo_time))
+	if (ktime_get_ns() < rq->fifo_time)
 		rq = NULL;
 
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
@@ -3096,14 +3117,14 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
 	struct cfq_queue *queue;
 	int i;
 	bool key_valid = false;
-	unsigned long lowest_key = 0;
+	u64 lowest_key = 0;
 	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
 
 	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
 		/* select the one with lowest rb_key */
 		queue = cfq_rb_first(st_for(cfqg, wl_class, i));
 		if (queue &&
-		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
+		    (!key_valid || queue->rb_key < lowest_key)) {
 			lowest_key = queue->rb_key;
 			cur_best = i;
 			key_valid = true;
@@ -3116,11 +3137,12 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
 static void
 choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
-	unsigned slice;
+	u64 slice;
 	unsigned count;
 	struct cfq_rb_root *st;
-	unsigned group_slice;
+	u64 group_slice;
 	enum wl_class_t original_class = cfqd->serving_wl_class;
+	u64 now = ktime_get_ns();
 
 	/* Choose next priority. RT > BE > IDLE */
 	if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
@@ -3129,7 +3151,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		cfqd->serving_wl_class = BE_WORKLOAD;
 	else {
 		cfqd->serving_wl_class = IDLE_WORKLOAD;
-		cfqd->workload_expires = jiffies + 1;
+		cfqd->workload_expires = now + jiffies_to_nsecs(1);
 		return;
 	}
 
@@ -3147,7 +3169,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	/*
 	 * check workload expiration, and that we still have other queues ready
 	 */
-	if (count && !time_after(jiffies, cfqd->workload_expires))
+	if (count && !(now > cfqd->workload_expires))
 		return;
 
 new_workload:
@@ -3164,13 +3186,13 @@ new_workload:
 	 */
 	group_slice = cfq_group_slice(cfqd, cfqg);
 
-	slice = group_slice * count /
+	slice = div_u64(group_slice * count,
 		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_wl_class],
 		      cfq_group_busy_queues_wl(cfqd->serving_wl_class, cfqd,
-					cfqg));
+					cfqg)));
 
 	if (cfqd->serving_wl_type == ASYNC_WORKLOAD) {
-		unsigned int tmp;
+		u64 tmp;
 
 		/*
 		 * Async queues are currently system wide. Just taking
@@ -3181,19 +3203,19 @@ new_workload:
 		 */
 		tmp = cfqd->cfq_target_latency *
 			cfqg_busy_async_queues(cfqd, cfqg);
-		tmp = tmp/cfqd->busy_queues;
-		slice = min_t(unsigned, slice, tmp);
+		tmp = div_u64(tmp, cfqd->busy_queues);
+		slice = min_t(u64, slice, tmp);
 
 		/* async workload slice is scaled down according to
 		 * the sync/async slice ratio. */
-		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
+		slice = div64_u64(slice*cfqd->cfq_slice[0], cfqd->cfq_slice[1]);
 	} else
 		/* sync workload slice is at least 2 * cfq_slice_idle */
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
-	slice = max_t(unsigned, slice, CFQ_MIN_TT);
-	cfq_log(cfqd, "workload slice:%d", slice);
-	cfqd->workload_expires = jiffies + slice;
+	slice = max_t(u64, slice, CFQ_MIN_TT);
+	cfq_log(cfqd, "workload slice:%llu", slice);
+	cfqd->workload_expires = now + slice;
 }
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
@@ -3211,16 +3233,17 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
 static void cfq_choose_cfqg(struct cfq_data *cfqd)
 {
 	struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd);
+	u64 now = ktime_get_ns();
 
 	cfqd->serving_group = cfqg;
 
 	/* Restore the workload type data */
 	if (cfqg->saved_wl_slice) {
-		cfqd->workload_expires = jiffies + cfqg->saved_wl_slice;
+		cfqd->workload_expires = now + cfqg->saved_wl_slice;
 		cfqd->serving_wl_type = cfqg->saved_wl_type;
 		cfqd->serving_wl_class = cfqg->saved_wl_class;
 	} else
-		cfqd->workload_expires = jiffies - 1;
+		cfqd->workload_expires = now - 1;
 
 	choose_wl_class_and_type(cfqd, cfqg);
 }
@@ -3232,6 +3255,7 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd)
 static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq, *new_cfqq = NULL;
+	u64 now = ktime_get_ns();
 
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
@@ -3292,7 +3316,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 * flight or is idling for a new request, allow either of these
 	 * conditions to happen (or time out) before selecting a new queue.
 	 */
-	if (timer_pending(&cfqd->idle_slice_timer)) {
+	if (hrtimer_active(&cfqd->idle_slice_timer)) {
 		cfqq = NULL;
 		goto keep_queue;
 	}
@@ -3303,7 +3327,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 **/
 	if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
 	    (cfq_cfqq_slice_new(cfqq) ||
-	    (cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) {
+	    (cfqq->slice_end - now > now - cfqq->slice_start))) {
 		cfq_clear_cfqq_deep(cfqq);
 		cfq_clear_cfqq_idle_window(cfqq);
 	}
@@ -3381,11 +3405,12 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
 	struct cfq_queue *cfqq)
 {
+	u64 now = ktime_get_ns();
+
 	/* the queue hasn't finished any request, can't estimate */
 	if (cfq_cfqq_slice_new(cfqq))
 		return true;
-	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
-		cfqq->slice_end))
+	if (now + cfqd->cfq_slice_idle * cfqq->dispatched > cfqq->slice_end)
 		return true;
 
 	return false;
@@ -3460,10 +3485,10 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * based on the last sync IO we serviced
 	 */
 	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
-		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
+		u64 last_sync = ktime_get_ns() - cfqd->last_delayed_sync;
 		unsigned int depth;
 
-		depth = last_sync / cfqd->cfq_slice[1];
+		depth = div64_u64(last_sync, cfqd->cfq_slice[1]);
 		if (!depth && !cfqq->dispatched)
 			depth = 1;
 		if (depth < max_dispatch)
@@ -3546,7 +3571,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
 	    cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
 	    cfq_class_idle(cfqq))) {
-		cfqq->slice_end = jiffies + 1;
+		cfqq->slice_end = ktime_get_ns() + 1;
 		cfq_slice_expired(cfqd, 0);
 	}
 
@@ -3624,7 +3649,7 @@ static void cfq_init_icq(struct io_cq *icq)
 {
 	struct cfq_io_cq *cic = icq_to_cic(icq);
 
-	cic->ttime.last_end_request = jiffies;
+	cic->ttime.last_end_request = ktime_get_ns();
 }
 
 static void cfq_exit_icq(struct io_cq *icq)
@@ -3682,6 +3707,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
 	 * elevate the priority of this queue
 	 */
 	cfqq->org_ioprio = cfqq->ioprio;
+	cfqq->org_ioprio_class = cfqq->ioprio_class;
 	cfq_clear_cfqq_prio_changed(cfqq);
 }
 
@@ -3845,14 +3871,15 @@ out:
 }
 
 static void
-__cfq_update_io_thinktime(struct cfq_ttime *ttime, unsigned long slice_idle)
+__cfq_update_io_thinktime(struct cfq_ttime *ttime, u64 slice_idle)
 {
-	unsigned long elapsed = jiffies - ttime->last_end_request;
+	u64 elapsed = ktime_get_ns() - ttime->last_end_request;
 	elapsed = min(elapsed, 2UL * slice_idle);
 
 	ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
-	ttime->ttime_total = (7*ttime->ttime_total + 256*elapsed) / 8;
-	ttime->ttime_mean = (ttime->ttime_total + 128) / ttime->ttime_samples;
+	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
+	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+				     ttime->ttime_samples);
 }
 
 static void
@@ -4105,10 +4132,10 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq));
 
-	rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
+	rq->fifo_time = ktime_get_ns() + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
-	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group,
+	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq),
 				 rq->cmd_flags);
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
@@ -4153,6 +4180,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct cfq_io_cq *cic = cfqd->active_cic;
+	u64 now = ktime_get_ns();
 
 	/* If the queue already has requests, don't wait */
 	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
@@ -4171,7 +4199,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	/* if slice left is less than think time, wait busy */
 	if (cic && sample_valid(cic->ttime.ttime_samples)
-	    && (cfqq->slice_end - jiffies < cic->ttime.ttime_mean))
+	    && (cfqq->slice_end - now < cic->ttime.ttime_mean))
 		return true;
 
 	/*
@@ -4181,7 +4209,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * case where think time is less than a jiffy, mark the queue wait
 	 * busy if only 1 jiffy is left in the slice.
 	 */
-	if (cfqq->slice_end - jiffies == 1)
+	if (cfqq->slice_end - now <= jiffies_to_nsecs(1))
 		return true;
 
 	return false;
@@ -4192,9 +4220,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 	struct cfq_data *cfqd = cfqq->cfqd;
 	const int sync = rq_is_sync(rq);
-	unsigned long now;
+	u64 now = ktime_get_ns();
 
-	now = jiffies;
 	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d",
 		     !!(rq->cmd_flags & REQ_NOIDLE));
 
@@ -4206,7 +4233,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	cfqq->dispatched--;
 	(RQ_CFQG(rq))->dispatched--;
 	cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq), rq->cmd_flags);
+				     rq_io_start_time_ns(rq), req_op(rq),
+				     rq->cmd_flags);
 
 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
@@ -4222,7 +4250,16 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 					cfqq_type(cfqq));
 
 		st->ttime.last_end_request = now;
-		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+		/*
+		 * We have to do this check in jiffies since start_time is in
+		 * jiffies and it is not trivial to convert to ns. If
+		 * cfq_fifo_expire[1] ever comes close to 1 jiffie, this test
+		 * will become problematic but so far we are fine (the default
+		 * is 128 ms).
+		 */
+		if (!time_after(rq->start_time +
+				  nsecs_to_jiffies(cfqd->cfq_fifo_expire[1]),
+				jiffies))
 			cfqd->last_delayed_sync = now;
 	}
 
@@ -4247,10 +4284,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		 * the queue.
 		 */
 		if (cfq_should_wait_busy(cfqd, cfqq)) {
-			unsigned long extend_sl = cfqd->cfq_slice_idle;
+			u64 extend_sl = cfqd->cfq_slice_idle;
 			if (!cfqd->cfq_slice_idle)
 				extend_sl = cfqd->cfq_group_idle;
-			cfqq->slice_end = jiffies + extend_sl;
+			cfqq->slice_end = now + extend_sl;
 			cfq_mark_cfqq_wait_busy(cfqq);
 			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
@@ -4275,6 +4312,24 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		cfq_schedule_dispatch(cfqd);
 }
 
+static void cfqq_boost_on_prio(struct cfq_queue *cfqq, int op_flags)
+{
+	/*
+	 * If REQ_PRIO is set, boost class and prio level, if it's below
+	 * BE/NORM. If prio is not set, restore the potentially boosted
+	 * class/prio level.
+	 */
+	if (!(op_flags & REQ_PRIO)) {
+		cfqq->ioprio_class = cfqq->org_ioprio_class;
+		cfqq->ioprio = cfqq->org_ioprio;
+	} else {
+		if (cfq_class_idle(cfqq))
+			cfqq->ioprio_class = IOPRIO_CLASS_BE;
+		if (cfqq->ioprio > IOPRIO_NORM)
+			cfqq->ioprio = IOPRIO_NORM;
+	}
+}
+
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
@@ -4285,7 +4340,7 @@ static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 	return ELV_MQUEUE_MAY;
 }
 
-static int cfq_may_queue(struct request_queue *q, int rw)
+static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
@@ -4302,9 +4357,10 @@ static int cfq_may_queue(struct request_queue *q, int rw)
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw_is_sync(rw));
+	cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic);
+		cfqq_boost_on_prio(cfqq, op_flags);
 
 		return __cfq_may_queue(cfqq);
 	}
@@ -4435,9 +4491,10 @@ static void cfq_kick_queue(struct work_struct *work)
 /*
  * Timer running if the active_queue is currently idling inside its time slice
  */
-static void cfq_idle_slice_timer(unsigned long data)
+static enum hrtimer_restart cfq_idle_slice_timer(struct hrtimer *timer)
 {
-	struct cfq_data *cfqd = (struct cfq_data *) data;
+	struct cfq_data *cfqd = container_of(timer, struct cfq_data,
+					     idle_slice_timer);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 	int timed_out = 1;
@@ -4486,11 +4543,12 @@ out_kick:
 	cfq_schedule_dispatch(cfqd);
 out_cont:
 	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+	return HRTIMER_NORESTART;
 }
 
 static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
 {
-	del_timer_sync(&cfqd->idle_slice_timer);
+	hrtimer_cancel(&cfqd->idle_slice_timer);
 	cancel_work_sync(&cfqd->unplug_work);
 }
 
@@ -4586,9 +4644,9 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	cfqg_put(cfqd->root_group);
 	spin_unlock_irq(q->queue_lock);
 
-	init_timer(&cfqd->idle_slice_timer);
+	hrtimer_init(&cfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
 	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
-	cfqd->idle_slice_timer.data = (unsigned long) cfqd;
 
 	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
 
@@ -4609,7 +4667,7 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	 * we optimistically start assuming sync ops weren't delayed in last
 	 * second, in order to have larger depth for async operations.
 	 */
-	cfqd->last_delayed_sync = jiffies - HZ;
+	cfqd->last_delayed_sync = ktime_get_ns() - NSEC_PER_SEC;
 	return 0;
 
 out_free:
@@ -4652,9 +4710,9 @@ cfq_var_store(unsigned int *var, const char *page, size_t count)
 static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data = __VAR;					\
+	u64 __data = __VAR;						\
 	if (__CONV)							\
-		__data = jiffies_to_msecs(__data);			\
+		__data = div_u64(__data, NSEC_PER_MSEC);			\
 	return cfq_var_show(__data, (page));				\
 }
 SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
@@ -4671,6 +4729,21 @@ SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
 SHOW_FUNCTION(cfq_target_latency_show, cfqd->cfq_target_latency, 1);
 #undef SHOW_FUNCTION
 
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	__data = div_u64(__data, NSEC_PER_USEC);			\
+	return cfq_var_show(__data, (page));				\
+}
+USEC_SHOW_FUNCTION(cfq_slice_idle_us_show, cfqd->cfq_slice_idle);
+USEC_SHOW_FUNCTION(cfq_group_idle_us_show, cfqd->cfq_group_idle);
+USEC_SHOW_FUNCTION(cfq_slice_sync_us_show, cfqd->cfq_slice[1]);
+USEC_SHOW_FUNCTION(cfq_slice_async_us_show, cfqd->cfq_slice[0]);
+USEC_SHOW_FUNCTION(cfq_target_latency_us_show, cfqd->cfq_target_latency);
+#undef USEC_SHOW_FUNCTION
+
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
@@ -4682,7 +4755,7 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)
 	else if (__data > (MAX))					\
 		__data = (MAX);						\
 	if (__CONV)							\
-		*(__PTR) = msecs_to_jiffies(__data);			\
+		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
 		*(__PTR) = __data;					\
 	return ret;							\
@@ -4705,6 +4778,26 @@ STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
 STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX, 1);
 #undef STORE_FUNCTION
 
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	unsigned int __data;						\
+	int ret = cfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
+	return ret;							\
+}
+USEC_STORE_FUNCTION(cfq_slice_idle_us_store, &cfqd->cfq_slice_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_group_idle_us_store, &cfqd->cfq_group_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_sync_us_store, &cfqd->cfq_slice[1], 1, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_async_us_store, &cfqd->cfq_slice[0], 1, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_target_latency_us_store, &cfqd->cfq_target_latency, 1, UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
 #define CFQ_ATTR(name) \
 	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
 
@@ -4715,12 +4808,17 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(back_seek_max),
 	CFQ_ATTR(back_seek_penalty),
 	CFQ_ATTR(slice_sync),
+	CFQ_ATTR(slice_sync_us),
 	CFQ_ATTR(slice_async),
+	CFQ_ATTR(slice_async_us),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(slice_idle_us),
 	CFQ_ATTR(group_idle),
+	CFQ_ATTR(group_idle_us),
 	CFQ_ATTR(low_latency),
 	CFQ_ATTR(target_latency),
+	CFQ_ATTR(target_latency_us),
 	__ATTR_NULL
 };
 
@@ -4729,7 +4827,8 @@ static struct elevator_type iosched_cfq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
-		.elevator_allow_merge_fn =	cfq_allow_merge,
+		.elevator_allow_bio_merge_fn =	cfq_allow_bio_merge,
+		.elevator_allow_rq_merge_fn =	cfq_allow_rq_merge,
 		.elevator_bio_merged_fn =	cfq_bio_merged,
 		.elevator_dispatch_fn =		cfq_dispatch_requests,
 		.elevator_add_req_fn =		cfq_insert_request,
@@ -4776,18 +4875,7 @@ static int __init cfq_init(void)
 {
 	int ret;
 
-	/*
-	 * could be 0 on HZ < 1000 setups
-	 */
-	if (!cfq_slice_async)
-		cfq_slice_async = 1;
-	if (!cfq_slice_idle)
-		cfq_slice_idle = 1;
-
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-	if (!cfq_group_idle)
-		cfq_group_idle = 1;
-
 	ret = blkcg_policy_register(&blkcg_policy_cfq);
 	if (ret)
 		return ret;
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index d0dd7882d8c7..55e0bb6d7da7 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -137,7 +137,7 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		if (__rq) {
 			BUG_ON(sector != blk_rq_pos(__rq));
 
-			if (elv_rq_merge_ok(__rq, bio)) {
+			if (elv_bio_merge_ok(__rq, bio)) {
 				ret = ELEVATOR_FRONT_MERGE;
 				goto out;
 			}
@@ -173,7 +173,8 @@ deadline_merged_requests(struct request_queue *q, struct request *req,
 	 * and move into next position (next will be deleted) in fifo
 	 */
 	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
-		if (time_before(next->fifo_time, req->fifo_time)) {
+		if (time_before((unsigned long)next->fifo_time,
+				(unsigned long)req->fifo_time)) {
 			list_move(&req->queuelist, &next->queuelist);
 			req->fifo_time = next->fifo_time;
 		}
@@ -227,7 +228,7 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	/*
 	 * rq is expired!
 	 */
-	if (time_after_eq(jiffies, rq->fifo_time))
+	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
 		return 1;
 
 	return 0;
diff --git a/block/elevator.c b/block/elevator.c
index c3555c9c672f..7096c22041e7 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -53,13 +53,13 @@ static LIST_HEAD(elv_list);
  * Query io scheduler to see if the current process issuing bio may be
  * merged with rq.
  */
-static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
+static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 {
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_merge_fn)
-		return e->type->ops.elevator_allow_merge_fn(q, rq, bio);
+	if (e->type->ops.elevator_allow_bio_merge_fn)
+		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
 }
@@ -67,17 +67,17 @@ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
 /*
  * can we safely merge with this request?
  */
-bool elv_rq_merge_ok(struct request *rq, struct bio *bio)
+bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
 {
 	if (!blk_rq_merge_ok(rq, bio))
-		return 0;
+		return false;
 
-	if (!elv_iosched_allow_merge(rq, bio))
-		return 0;
+	if (!elv_iosched_allow_bio_merge(rq, bio))
+		return false;
 
-	return 1;
+	return true;
 }
-EXPORT_SYMBOL(elv_rq_merge_ok);
+EXPORT_SYMBOL(elv_bio_merge_ok);
 
 static struct elevator_type *elevator_find(const char *name)
 {
@@ -366,8 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
-		if ((rq->cmd_flags & REQ_DISCARD) !=
-		    (pos->cmd_flags & REQ_DISCARD))
+		if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;
@@ -426,7 +425,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	/*
 	 * First try one-hit cache.
 	 */
-	if (q->last_merge && elv_rq_merge_ok(q->last_merge, bio)) {
+	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
 		ret = blk_try_merge(q->last_merge, bio);
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
@@ -441,7 +440,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * See if our hash lookup can find a potential backmerge.
 	 */
 	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_BACK_MERGE;
 	}
@@ -717,12 +716,12 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 		e->type->ops.elevator_put_req_fn(rq);
 }
 
-int elv_may_queue(struct request_queue *q, int rw)
+int elv_may_queue(struct request_queue *q, int op, int op_flags)
 {
 	struct elevator_queue *e = q->elevator;
 
 	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, rw);
+		return e->type->ops.elevator_may_queue_fn(q, op, op_flags);
 
 	return ELV_MQUEUE_MAY;
 }
diff --git a/block/genhd.c b/block/genhd.c
index f06d7f3b075b..3c9dede4e04f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -506,7 +506,7 @@ static int exact_lock(dev_t devt, void *data)
 	return 0;
 }
 
-static void register_disk(struct gendisk *disk)
+static void register_disk(struct device *parent, struct gendisk *disk)
 {
 	struct device *ddev = disk_to_dev(disk);
 	struct block_device *bdev;
@@ -514,7 +514,7 @@ static void register_disk(struct gendisk *disk)
 	struct hd_struct *part;
 	int err;
 
-	ddev->parent = disk->driverfs_dev;
+	ddev->parent = parent;
 
 	dev_set_name(ddev, "%s", disk->disk_name);
 
@@ -573,7 +573,8 @@ exit:
 }
 
 /**
- * add_disk - add partitioning information to kernel list
+ * device_add_disk - add partitioning information to kernel list
+ * @parent: parent device for the disk
  * @disk: per-device partitioning information
  *
  * This function registers the partitioning information in @disk
@@ -581,7 +582,7 @@ exit:
  *
  * FIXME: error handling
  */
-void add_disk(struct gendisk *disk)
+void device_add_disk(struct device *parent, struct gendisk *disk)
 {
 	struct backing_dev_info *bdi;
 	dev_t devt;
@@ -617,7 +618,7 @@ void add_disk(struct gendisk *disk)
 
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
 			    exact_match, exact_lock, disk);
-	register_disk(disk);
+	register_disk(parent, disk);
 	blk_register_queue(disk);
 
 	/*
@@ -633,7 +634,7 @@ void add_disk(struct gendisk *disk)
 	disk_add_events(disk);
 	blk_integrity_add(disk);
 }
-EXPORT_SYMBOL(add_disk);
+EXPORT_SYMBOL(device_add_disk);
 
 void del_gendisk(struct gendisk *disk)
 {
@@ -799,10 +800,9 @@ void __init printk_all_partitions(void)
 			       , disk_name(disk, part->partno, name_buf),
 			       part->info ? part->info->uuid : "");
 			if (is_part0) {
-				if (disk->driverfs_dev != NULL &&
-				    disk->driverfs_dev->driver != NULL)
+				if (dev->parent && dev->parent->driver)
 					printk(" driver: %s\n",
-					      disk->driverfs_dev->driver->name);
+					      dev->parent->driver->name);
 				else
 					printk(" (driver?)\n");
 			} else
diff --git a/block/partition-generic.c b/block/partition-generic.c
index d7eb77e1e3a8..71d9ed9df8da 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -495,7 +495,6 @@ rescan:
 	/* add partitions */
 	for (p = 1; p < state->limit; p++) {
 		sector_t size, from;
-		struct partition_meta_info *info = NULL;
 
 		size = state->parts[p].size;
 		if (!size)
@@ -530,8 +529,6 @@ rescan:
 			}
 		}
 
-		if (state->parts[p].has_info)
-			info = &state->parts[p].info;
 		part = add_partition(disk, p, from, size,
 				     state->parts[p].flags,
 				     &state->parts[p].info);
diff --git a/block/partitions/atari.c b/block/partitions/atari.c
index 9875b05e80a2..ff1fb93712c1 100644
--- a/block/partitions/atari.c
+++ b/block/partitions/atari.c
@@ -42,6 +42,13 @@ int atari_partition(struct parsed_partitions *state)
 	int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */
 #endif
 
+	/*
+	 * ATARI partition scheme supports 512 lba only.  If this is not
+	 * the case, bail early to avoid miscalculating hd_size.
+	 */
+	if (bdev_logical_block_size(state->bdev) != 512)
+		return 0;
+
 	rs = read_part_sector(state, 0, &sect);
 	if (!rs)
 		return -1;
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 1d33beb6a1ae..a9377bef25e3 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -93,6 +93,15 @@ config CRYPTO_AKCIPHER
 	select CRYPTO_AKCIPHER2
 	select CRYPTO_ALGAPI
 
+config CRYPTO_KPP2
+	tristate
+	select CRYPTO_ALGAPI2
+
+config CRYPTO_KPP
+	tristate
+	select CRYPTO_ALGAPI
+	select CRYPTO_KPP2
+
 config CRYPTO_RSA
 	tristate "RSA algorithm"
 	select CRYPTO_AKCIPHER
@@ -102,6 +111,19 @@ config CRYPTO_RSA
 	help
 	  Generic implementation of the RSA public key algorithm.
 
+config CRYPTO_DH
+	tristate "Diffie-Hellman algorithm"
+	select CRYPTO_KPP
+	select MPILIB
+	help
+	  Generic implementation of the Diffie-Hellman algorithm.
+
+config CRYPTO_ECDH
+	tristate "ECDH algorithm"
+	select CRYTPO_KPP
+	help
+	  Generic implementation of the ECDH algorithm
+
 config CRYPTO_MANAGER
 	tristate "Cryptographic algorithm manager"
 	select CRYPTO_MANAGER2
@@ -115,6 +137,7 @@ config CRYPTO_MANAGER2
 	select CRYPTO_HASH2
 	select CRYPTO_BLKCIPHER2
 	select CRYPTO_AKCIPHER2
+	select CRYPTO_KPP2
 
 config CRYPTO_USER
 	tristate "Userspace cryptographic algorithm configuration"
@@ -414,6 +437,17 @@ config CRYPTO_CRC32C_INTEL
 	  gain performance compared with software implementation.
 	  Module will be crc32c-intel.
 
+config CRYPT_CRC32C_VPMSUM
+	tristate "CRC32c CRC algorithm (powerpc64)"
+	depends on PPC64
+	select CRYPTO_HASH
+	select CRC32
+	help
+	  CRC32c algorithm implemented using vector polynomial multiply-sum
+	  (vpmsum) instructions, introduced in POWER8. Enable on POWER8
+	  and newer processors for improved performance.
+
+
 config CRYPTO_CRC32C_SPARC64
 	tristate "CRC32c CRC algorithm (SPARC64)"
 	depends on SPARC64
@@ -681,6 +715,38 @@ config CRYPTO_SHA1_MB
 	  lanes remain unfilled, a flush operation will be initiated to
 	  process the crypto jobs, adding a slight latency.
 
+config CRYPTO_SHA256_MB
+	tristate "SHA256 digest algorithm (x86_64 Multi-Buffer, Experimental)"
+	depends on X86 && 64BIT
+	select CRYPTO_SHA256
+	select CRYPTO_HASH
+	select CRYPTO_MCRYPTD
+	help
+	  SHA-256 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
+	  using multi-buffer technique.  This algorithm computes on
+	  multiple data lanes concurrently with SIMD instructions for
+	  better throughput.  It should not be enabled by default but
+	  used when there is significant amount of work to keep the keep
+	  the data lanes filled to get performance benefit.  If the data
+	  lanes remain unfilled, a flush operation will be initiated to
+	  process the crypto jobs, adding a slight latency.
+
+config CRYPTO_SHA512_MB
+        tristate "SHA512 digest algorithm (x86_64 Multi-Buffer, Experimental)"
+        depends on X86 && 64BIT
+        select CRYPTO_SHA512
+        select CRYPTO_HASH
+        select CRYPTO_MCRYPTD
+        help
+          SHA-512 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
+          using multi-buffer technique.  This algorithm computes on
+          multiple data lanes concurrently with SIMD instructions for
+          better throughput.  It should not be enabled by default but
+          used when there is significant amount of work to keep the keep
+          the data lanes filled to get performance benefit.  If the data
+          lanes remain unfilled, a flush operation will be initiated to
+          process the crypto jobs, adding a slight latency.
+
 config CRYPTO_SHA256
 	tristate "SHA224 and SHA256 digest algorithm"
 	select CRYPTO_HASH
@@ -750,6 +816,16 @@ config CRYPTO_SHA512_SPARC64
 	  SHA-512 secure hash standard (DFIPS 180-2) implemented
 	  using sparc64 crypto instructions, when available.
 
+config CRYPTO_SHA3
+	tristate "SHA3 digest algorithm"
+	select CRYPTO_HASH
+	help
+	  SHA-3 secure hash standard (DFIPS 202). It's based on
+	  cryptographic sponge function family called Keccak.
+
+	  References:
+	  http://keccak.noekeon.org/
+
 config CRYPTO_TGR192
 	tristate "Tiger digest algorithms"
 	select CRYPTO_HASH
@@ -1567,6 +1643,7 @@ config CRYPTO_DRBG_HASH
 config CRYPTO_DRBG_CTR
 	bool "Enable CTR DRBG"
 	select CRYPTO_AES
+	depends on CRYPTO_CTR
 	help
 	  Enable the CTR DRBG variant as defined in NIST SP800-90A.
 
diff --git a/crypto/Makefile b/crypto/Makefile
index 4f4ef7eaae3f..99cc64ac70ef 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -20,8 +20,6 @@ crypto_blkcipher-y := ablkcipher.o
 crypto_blkcipher-y += blkcipher.o
 crypto_blkcipher-y += skcipher.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += crypto_blkcipher.o
-obj-$(CONFIG_CRYPTO_BLKCIPHER2) += chainiv.o
-obj-$(CONFIG_CRYPTO_BLKCIPHER2) += eseqiv.o
 obj-$(CONFIG_CRYPTO_SEQIV) += seqiv.o
 obj-$(CONFIG_CRYPTO_ECHAINIV) += echainiv.o
 
@@ -30,6 +28,15 @@ crypto_hash-y += shash.o
 obj-$(CONFIG_CRYPTO_HASH2) += crypto_hash.o
 
 obj-$(CONFIG_CRYPTO_AKCIPHER2) += akcipher.o
+obj-$(CONFIG_CRYPTO_KPP2) += kpp.o
+
+dh_generic-y := dh.o
+dh_generic-y += dh_helper.o
+obj-$(CONFIG_CRYPTO_DH) += dh_generic.o
+ecdh_generic-y := ecc.o
+ecdh_generic-y += ecdh.o
+ecdh_generic-y += ecdh_helper.o
+obj-$(CONFIG_CRYPTO_ECDH) += ecdh_generic.o
 
 $(obj)/rsapubkey-asn1.o: $(obj)/rsapubkey-asn1.c $(obj)/rsapubkey-asn1.h
 $(obj)/rsaprivkey-asn1.o: $(obj)/rsaprivkey-asn1.c $(obj)/rsaprivkey-asn1.h
@@ -61,6 +68,7 @@ obj-$(CONFIG_CRYPTO_RMD320) += rmd320.o
 obj-$(CONFIG_CRYPTO_SHA1) += sha1_generic.o
 obj-$(CONFIG_CRYPTO_SHA256) += sha256_generic.o
 obj-$(CONFIG_CRYPTO_SHA512) += sha512_generic.o
+obj-$(CONFIG_CRYPTO_SHA3) += sha3_generic.o
 obj-$(CONFIG_CRYPTO_WP512) += wp512.o
 obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
index e1fcf53bb931..1441f07d0a19 100644
--- a/crypto/ablk_helper.c
+++ b/crypto/ablk_helper.c
@@ -71,7 +71,8 @@ int ablk_encrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ablkcipher_queued(ctx->cryptd_tfm))) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 
@@ -90,7 +91,8 @@ int ablk_decrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ablkcipher_queued(ctx->cryptd_tfm))) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 
diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index e5b5721809e2..d676fc59521a 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -14,11 +14,8 @@
  */
 
 #include <crypto/internal/skcipher.h>
-#include <linux/cpumask.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
-#include <linux/rtnetlink.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/cryptouser.h>
@@ -349,16 +346,6 @@ static unsigned int crypto_ablkcipher_ctxsize(struct crypto_alg *alg, u32 type,
 	return alg->cra_ctxsize;
 }
 
-int skcipher_null_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	return crypto_ablkcipher_encrypt(&req->creq);
-}
-
-int skcipher_null_givdecrypt(struct skcipher_givcrypt_request *req)
-{
-	return crypto_ablkcipher_decrypt(&req->creq);
-}
-
 static int crypto_init_ablkcipher_ops(struct crypto_tfm *tfm, u32 type,
 				      u32 mask)
 {
@@ -371,10 +358,6 @@ static int crypto_init_ablkcipher_ops(struct crypto_tfm *tfm, u32 type,
 	crt->setkey = setkey;
 	crt->encrypt = alg->encrypt;
 	crt->decrypt = alg->decrypt;
-	if (!alg->ivsize) {
-		crt->givencrypt = skcipher_null_givencrypt;
-		crt->givdecrypt = skcipher_null_givdecrypt;
-	}
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
 
@@ -436,11 +419,6 @@ const struct crypto_type crypto_ablkcipher_type = {
 };
 EXPORT_SYMBOL_GPL(crypto_ablkcipher_type);
 
-static int no_givdecrypt(struct skcipher_givcrypt_request *req)
-{
-	return -ENOSYS;
-}
-
 static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
 				      u32 mask)
 {
@@ -454,8 +432,6 @@ static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
 		      alg->setkey : setkey;
 	crt->encrypt = alg->encrypt;
 	crt->decrypt = alg->decrypt;
-	crt->givencrypt = alg->givencrypt ?: no_givdecrypt;
-	crt->givdecrypt = alg->givdecrypt ?: no_givdecrypt;
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
 
@@ -516,202 +492,3 @@ const struct crypto_type crypto_givcipher_type = {
 	.report = crypto_givcipher_report,
 };
 EXPORT_SYMBOL_GPL(crypto_givcipher_type);
-
-const char *crypto_default_geniv(const struct crypto_alg *alg)
-{
-	if (((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	     CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
-					 alg->cra_ablkcipher.ivsize) !=
-	    alg->cra_blocksize)
-		return "chainiv";
-
-	return "eseqiv";
-}
-
-static int crypto_givcipher_default(struct crypto_alg *alg, u32 type, u32 mask)
-{
-	struct rtattr *tb[3];
-	struct {
-		struct rtattr attr;
-		struct crypto_attr_type data;
-	} ptype;
-	struct {
-		struct rtattr attr;
-		struct crypto_attr_alg data;
-	} palg;
-	struct crypto_template *tmpl;
-	struct crypto_instance *inst;
-	struct crypto_alg *larval;
-	const char *geniv;
-	int err;
-
-	larval = crypto_larval_lookup(alg->cra_driver_name,
-				      (type & ~CRYPTO_ALG_TYPE_MASK) |
-				      CRYPTO_ALG_TYPE_GIVCIPHER,
-				      mask | CRYPTO_ALG_TYPE_MASK);
-	err = PTR_ERR(larval);
-	if (IS_ERR(larval))
-		goto out;
-
-	err = -EAGAIN;
-	if (!crypto_is_larval(larval))
-		goto drop_larval;
-
-	ptype.attr.rta_len = sizeof(ptype);
-	ptype.attr.rta_type = CRYPTOA_TYPE;
-	ptype.data.type = type | CRYPTO_ALG_GENIV;
-	/* GENIV tells the template that we're making a default geniv. */
-	ptype.data.mask = mask | CRYPTO_ALG_GENIV;
-	tb[0] = &ptype.attr;
-
-	palg.attr.rta_len = sizeof(palg);
-	palg.attr.rta_type = CRYPTOA_ALG;
-	/* Must use the exact name to locate ourselves. */
-	memcpy(palg.data.name, alg->cra_driver_name, CRYPTO_MAX_ALG_NAME);
-	tb[1] = &palg.attr;
-
-	tb[2] = NULL;
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		geniv = alg->cra_blkcipher.geniv;
-	else
-		geniv = alg->cra_ablkcipher.geniv;
-
-	if (!geniv)
-		geniv = crypto_default_geniv(alg);
-
-	tmpl = crypto_lookup_template(geniv);
-	err = -ENOENT;
-	if (!tmpl)
-		goto kill_larval;
-
-	if (tmpl->create) {
-		err = tmpl->create(tmpl, tb);
-		if (err)
-			goto put_tmpl;
-		goto ok;
-	}
-
-	inst = tmpl->alloc(tb);
-	err = PTR_ERR(inst);
-	if (IS_ERR(inst))
-		goto put_tmpl;
-
-	err = crypto_register_instance(tmpl, inst);
-	if (err) {
-		tmpl->free(inst);
-		goto put_tmpl;
-	}
-
-ok:
-	/* Redo the lookup to use the instance we just registered. */
-	err = -EAGAIN;
-
-put_tmpl:
-	crypto_tmpl_put(tmpl);
-kill_larval:
-	crypto_larval_kill(larval);
-drop_larval:
-	crypto_mod_put(larval);
-out:
-	crypto_mod_put(alg);
-	return err;
-}
-
-struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask)
-{
-	struct crypto_alg *alg;
-
-	alg = crypto_alg_mod_lookup(name, type, mask);
-	if (IS_ERR(alg))
-		return alg;
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_GIVCIPHER)
-		return alg;
-
-	if (!((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	      CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
-					  alg->cra_ablkcipher.ivsize))
-		return alg;
-
-	crypto_mod_put(alg);
-	alg = crypto_alg_mod_lookup(name, type | CRYPTO_ALG_TESTED,
-				    mask & ~CRYPTO_ALG_TESTED);
-	if (IS_ERR(alg))
-		return alg;
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_GIVCIPHER) {
-		if (~alg->cra_flags & (type ^ ~mask) & CRYPTO_ALG_TESTED) {
-			crypto_mod_put(alg);
-			alg = ERR_PTR(-ENOENT);
-		}
-		return alg;
-	}
-
-	BUG_ON(!((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-		 CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
-					     alg->cra_ablkcipher.ivsize));
-
-	return ERR_PTR(crypto_givcipher_default(alg, type, mask));
-}
-EXPORT_SYMBOL_GPL(crypto_lookup_skcipher);
-
-int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name,
-			 u32 type, u32 mask)
-{
-	struct crypto_alg *alg;
-	int err;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask);
-
-	alg = crypto_lookup_skcipher(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
-
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
-	return err;
-}
-EXPORT_SYMBOL_GPL(crypto_grab_skcipher);
-
-struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name,
-						  u32 type, u32 mask)
-{
-	struct crypto_tfm *tfm;
-	int err;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask);
-
-	for (;;) {
-		struct crypto_alg *alg;
-
-		alg = crypto_lookup_skcipher(alg_name, type, mask);
-		if (IS_ERR(alg)) {
-			err = PTR_ERR(alg);
-			goto err;
-		}
-
-		tfm = __crypto_alloc_tfm(alg, type, mask);
-		if (!IS_ERR(tfm))
-			return __crypto_ablkcipher_cast(tfm);
-
-		crypto_mod_put(alg);
-		err = PTR_ERR(tfm);
-
-err:
-		if (err != -EAGAIN)
-			break;
-		if (fatal_signal_pending(current)) {
-			err = -EINTR;
-			break;
-		}
-	}
-
-	return ERR_PTR(err);
-}
-EXPORT_SYMBOL_GPL(crypto_alloc_ablkcipher);
diff --git a/crypto/aead.c b/crypto/aead.c
index 9b18a1e40d6a..3f5c5ff004ab 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -294,9 +294,9 @@ int aead_init_geniv(struct crypto_aead *aead)
 	if (err)
 		goto out;
 
-	ctx->null = crypto_get_default_null_skcipher();
-	err = PTR_ERR(ctx->null);
-	if (IS_ERR(ctx->null))
+	ctx->sknull = crypto_get_default_null_skcipher2();
+	err = PTR_ERR(ctx->sknull);
+	if (IS_ERR(ctx->sknull))
 		goto out;
 
 	child = crypto_spawn_aead(aead_instance_ctx(inst));
@@ -314,7 +314,7 @@ out:
 	return err;
 
 drop_null:
-	crypto_put_default_null_skcipher();
+	crypto_put_default_null_skcipher2();
 	goto out;
 }
 EXPORT_SYMBOL_GPL(aead_init_geniv);
@@ -324,7 +324,7 @@ void aead_exit_geniv(struct crypto_aead *tfm)
 	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_put_default_null_skcipher();
+	crypto_put_default_null_skcipher2();
 }
 EXPORT_SYMBOL_GPL(aead_exit_geniv);
 
@@ -346,9 +346,13 @@ static int aead_prepare_alg(struct aead_alg *alg)
 {
 	struct crypto_alg *base = &alg->base;
 
-	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
+	if (max3(alg->maxauthsize, alg->ivsize, alg->chunksize) >
+	    PAGE_SIZE / 8)
 		return -EINVAL;
 
+	if (!alg->chunksize)
+		alg->chunksize = base->cra_blocksize;
+
 	base->cra_type = &crypto_aead_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_AEAD;
diff --git a/crypto/ahash.c b/crypto/ahash.c
index 3887a98abcc3..2ce8bcb9049c 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -461,10 +461,10 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 
 static unsigned int crypto_ahash_extsize(struct crypto_alg *alg)
 {
-	if (alg->cra_type == &crypto_ahash_type)
-		return alg->cra_ctxsize;
+	if (alg->cra_type != &crypto_ahash_type)
+		return sizeof(struct crypto_shash *);
 
-	return sizeof(struct crypto_shash *);
+	return crypto_alg_extsize(alg);
 }
 
 #ifdef CONFIG_NET
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 731255a6104f..df939b54b09f 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -811,6 +811,21 @@ int crypto_attr_u32(struct rtattr *rta, u32 *num)
 }
 EXPORT_SYMBOL_GPL(crypto_attr_u32);
 
+int crypto_inst_setname(struct crypto_instance *inst, const char *name,
+			struct crypto_alg *alg)
+{
+	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", name,
+		     alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
+		     name, alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_inst_setname);
+
 void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg,
 			     unsigned int head)
 {
@@ -825,13 +840,8 @@ void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg,
 
 	inst = (void *)(p + head);
 
-	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", name,
-		     alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
-		goto err_free_inst;
-
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
-		     name, alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+	err = crypto_inst_setname(inst, name, alg);
+	if (err)
 		goto err_free_inst;
 
 	return p;
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 55a354d57251..a7e1ac786c5d 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -32,8 +32,8 @@ struct authenc_instance_ctx {
 
 struct crypto_authenc_ctx {
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 };
 
 struct authenc_request_ctx {
@@ -83,7 +83,7 @@ static int crypto_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 {
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
 	struct crypto_ahash *auth = ctx->auth;
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct crypto_skcipher *enc = ctx->enc;
 	struct crypto_authenc_keys keys;
 	int err = -EINVAL;
 
@@ -100,11 +100,11 @@ static int crypto_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	if (err)
 		goto out;
 
-	crypto_ablkcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(enc, crypto_aead_get_flags(authenc) &
-					 CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(enc, keys.enckey, keys.enckeylen);
-	crypto_aead_set_flags(authenc, crypto_ablkcipher_get_flags(enc) &
+	crypto_skcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(enc, crypto_aead_get_flags(authenc) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(enc, keys.enckey, keys.enckeylen);
+	crypto_aead_set_flags(authenc, crypto_skcipher_get_flags(enc) &
 				       CRYPTO_TFM_RES_MASK);
 
 out:
@@ -184,12 +184,15 @@ static int crypto_authenc_copy_assoc(struct aead_request *req)
 {
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct blkcipher_desc desc = {
-		.tfm = ctx->null,
-	};
+	SKCIPHER_REQUEST_ON_STACK(skreq, ctx->null);
 
-	return crypto_blkcipher_encrypt(&desc, req->dst, req->src,
-					req->assoclen);
+	skcipher_request_set_tfm(skreq, ctx->null);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      NULL, NULL);
+	skcipher_request_set_crypt(skreq, req->src, req->dst, req->assoclen,
+				   NULL);
+
+	return crypto_skcipher_encrypt(skreq);
 }
 
 static int crypto_authenc_encrypt(struct aead_request *req)
@@ -199,14 +202,13 @@ static int crypto_authenc_encrypt(struct aead_request *req)
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
 	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct crypto_skcipher *enc = ctx->enc;
 	unsigned int cryptlen = req->cryptlen;
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail +
-						    ictx->reqoff);
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ictx->reqoff);
 	struct scatterlist *src, *dst;
 	int err;
 
-	sg_init_table(areq_ctx->src, 2);
 	src = scatterwalk_ffwd(areq_ctx->src, req->src, req->assoclen);
 	dst = src;
 
@@ -215,16 +217,15 @@ static int crypto_authenc_encrypt(struct aead_request *req)
 		if (err)
 			return err;
 
-		sg_init_table(areq_ctx->dst, 2);
 		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, req->assoclen);
 	}
 
-	ablkcipher_request_set_tfm(abreq, enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					crypto_authenc_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, src, dst, cryptlen, req->iv);
+	skcipher_request_set_tfm(skreq, enc);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      crypto_authenc_encrypt_done, req);
+	skcipher_request_set_crypt(skreq, src, dst, cryptlen, req->iv);
 
-	err = crypto_ablkcipher_encrypt(abreq);
+	err = crypto_skcipher_encrypt(skreq);
 	if (err)
 		return err;
 
@@ -240,8 +241,8 @@ static int crypto_authenc_decrypt_tail(struct aead_request *req,
 	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
 	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff);
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail +
-						    ictx->reqoff);
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ictx->reqoff);
 	unsigned int authsize = crypto_aead_authsize(authenc);
 	u8 *ihash = ahreq->result + authsize;
 	struct scatterlist *src, *dst;
@@ -251,22 +252,19 @@ static int crypto_authenc_decrypt_tail(struct aead_request *req,
 	if (crypto_memneq(ihash, ahreq->result, authsize))
 		return -EBADMSG;
 
-	sg_init_table(areq_ctx->src, 2);
 	src = scatterwalk_ffwd(areq_ctx->src, req->src, req->assoclen);
 	dst = src;
 
-	if (req->src != req->dst) {
-		sg_init_table(areq_ctx->dst, 2);
+	if (req->src != req->dst)
 		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, req->assoclen);
-	}
 
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, src, dst,
-				     req->cryptlen - authsize, req->iv);
+	skcipher_request_set_tfm(skreq, ctx->enc);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      req->base.complete, req->base.data);
+	skcipher_request_set_crypt(skreq, src, dst,
+				   req->cryptlen - authsize, req->iv);
 
-	return crypto_ablkcipher_decrypt(abreq);
+	return crypto_skcipher_decrypt(skreq);
 }
 
 static void authenc_verify_ahash_done(struct crypto_async_request *areq,
@@ -318,20 +316,20 @@ static int crypto_authenc_init_tfm(struct crypto_aead *tfm)
 	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 	int err;
 
 	auth = crypto_spawn_ahash(&ictx->auth);
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
-	enc = crypto_spawn_skcipher(&ictx->enc);
+	enc = crypto_spawn_skcipher2(&ictx->enc);
 	err = PTR_ERR(enc);
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
-	null = crypto_get_default_null_skcipher();
+	null = crypto_get_default_null_skcipher2();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_skcipher;
@@ -347,13 +345,13 @@ static int crypto_authenc_init_tfm(struct crypto_aead *tfm)
 		max_t(unsigned int,
 		      crypto_ahash_reqsize(auth) +
 		      sizeof(struct ahash_request),
-		      sizeof(struct ablkcipher_request) +
-		      crypto_ablkcipher_reqsize(enc)));
+		      sizeof(struct skcipher_request) +
+		      crypto_skcipher_reqsize(enc)));
 
 	return 0;
 
 err_free_skcipher:
-	crypto_free_ablkcipher(enc);
+	crypto_free_skcipher(enc);
 err_free_ahash:
 	crypto_free_ahash(auth);
 	return err;
@@ -364,8 +362,8 @@ static void crypto_authenc_exit_tfm(struct crypto_aead *tfm)
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->auth);
-	crypto_free_ablkcipher(ctx->enc);
-	crypto_put_default_null_skcipher();
+	crypto_free_skcipher(ctx->enc);
+	crypto_put_default_null_skcipher2();
 }
 
 static void crypto_authenc_free(struct aead_instance *inst)
@@ -384,7 +382,7 @@ static int crypto_authenc_create(struct crypto_template *tmpl,
 	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
-	struct crypto_alg *enc;
+	struct skcipher_alg *enc;
 	struct authenc_instance_ctx *ctx;
 	const char *enc_name;
 	int err;
@@ -397,7 +395,8 @@ static int crypto_authenc_create(struct crypto_template *tmpl,
 		return -EINVAL;
 
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
-			       CRYPTO_ALG_TYPE_AHASH_MASK);
+			      CRYPTO_ALG_TYPE_AHASH_MASK |
+			      crypto_requires_sync(algt->type, algt->mask));
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
@@ -421,37 +420,40 @@ static int crypto_authenc_create(struct crypto_template *tmpl,
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->enc, enc_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_auth;
 
-	enc = crypto_skcipher_spawn_alg(&ctx->enc);
+	enc = crypto_spawn_skcipher_alg(&ctx->enc);
 
 	ctx->reqoff = ALIGN(2 * auth->digestsize + auth_base->cra_alignmask,
 			    auth_base->cra_alignmask + 1);
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "authenc(%s,%s)", auth_base->cra_name, enc->cra_name) >=
+		     "authenc(%s,%s)", auth_base->cra_name,
+		     enc->base.cra_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "authenc(%s,%s)", auth_base->cra_driver_name,
-		     enc->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		     enc->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	inst->alg.base.cra_flags = enc->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.base.cra_priority = enc->cra_priority * 10 +
+	inst->alg.base.cra_flags = (auth_base->cra_flags |
+				    enc->base.cra_flags) & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = enc->base.cra_priority * 10 +
 				      auth_base->cra_priority;
-	inst->alg.base.cra_blocksize = enc->cra_blocksize;
+	inst->alg.base.cra_blocksize = enc->base.cra_blocksize;
 	inst->alg.base.cra_alignmask = auth_base->cra_alignmask |
-				       enc->cra_alignmask;
+				       enc->base.cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_authenc_ctx);
 
-	inst->alg.ivsize = enc->cra_ablkcipher.ivsize;
+	inst->alg.ivsize = crypto_skcipher_alg_ivsize(enc);
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(enc);
 	inst->alg.maxauthsize = auth->digestsize;
 
 	inst->alg.init = crypto_authenc_init_tfm;
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 0c0468869e25..121010ac9962 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -35,8 +35,8 @@ struct authenc_esn_instance_ctx {
 struct crypto_authenc_esn_ctx {
 	unsigned int reqoff;
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 };
 
 struct authenc_esn_request_ctx {
@@ -65,7 +65,7 @@ static int crypto_authenc_esn_setkey(struct crypto_aead *authenc_esn, const u8 *
 {
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
 	struct crypto_ahash *auth = ctx->auth;
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct crypto_skcipher *enc = ctx->enc;
 	struct crypto_authenc_keys keys;
 	int err = -EINVAL;
 
@@ -82,11 +82,11 @@ static int crypto_authenc_esn_setkey(struct crypto_aead *authenc_esn, const u8 *
 	if (err)
 		goto out;
 
-	crypto_ablkcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(enc, crypto_aead_get_flags(authenc_esn) &
+	crypto_skcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(enc, crypto_aead_get_flags(authenc_esn) &
 					 CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(enc, keys.enckey, keys.enckeylen);
-	crypto_aead_set_flags(authenc_esn, crypto_ablkcipher_get_flags(enc) &
+	err = crypto_skcipher_setkey(enc, keys.enckey, keys.enckeylen);
+	crypto_aead_set_flags(authenc_esn, crypto_skcipher_get_flags(enc) &
 					   CRYPTO_TFM_RES_MASK);
 
 out:
@@ -182,11 +182,14 @@ static int crypto_authenc_esn_copy(struct aead_request *req, unsigned int len)
 {
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct blkcipher_desc desc = {
-		.tfm = ctx->null,
-	};
+	SKCIPHER_REQUEST_ON_STACK(skreq, ctx->null);
 
-	return crypto_blkcipher_encrypt(&desc, req->dst, req->src, len);
+	skcipher_request_set_tfm(skreq, ctx->null);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      NULL, NULL);
+	skcipher_request_set_crypt(skreq, req->src, req->dst, len, NULL);
+
+	return crypto_skcipher_encrypt(skreq);
 }
 
 static int crypto_authenc_esn_encrypt(struct aead_request *req)
@@ -194,9 +197,9 @@ static int crypto_authenc_esn_encrypt(struct aead_request *req)
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
-						    + ctx->reqoff);
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ctx->reqoff);
+	struct crypto_skcipher *enc = ctx->enc;
 	unsigned int assoclen = req->assoclen;
 	unsigned int cryptlen = req->cryptlen;
 	struct scatterlist *src, *dst;
@@ -215,12 +218,12 @@ static int crypto_authenc_esn_encrypt(struct aead_request *req)
 		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, assoclen);
 	}
 
-	ablkcipher_request_set_tfm(abreq, enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					crypto_authenc_esn_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, src, dst, cryptlen, req->iv);
+	skcipher_request_set_tfm(skreq, enc);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      crypto_authenc_esn_encrypt_done, req);
+	skcipher_request_set_crypt(skreq, src, dst, cryptlen, req->iv);
 
-	err = crypto_ablkcipher_encrypt(abreq);
+	err = crypto_skcipher_encrypt(skreq);
 	if (err)
 		return err;
 
@@ -234,8 +237,8 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req,
 	unsigned int authsize = crypto_aead_authsize(authenc_esn);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
-						    + ctx->reqoff);
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ctx->reqoff);
 	struct crypto_ahash *auth = ctx->auth;
 	u8 *ohash = PTR_ALIGN((u8 *)areq_ctx->tail,
 			      crypto_ahash_alignmask(auth) + 1);
@@ -256,12 +259,12 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req,
 	sg_init_table(areq_ctx->dst, 2);
 	dst = scatterwalk_ffwd(areq_ctx->dst, dst, assoclen);
 
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, flags,
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, dst, dst, cryptlen, req->iv);
+	skcipher_request_set_tfm(skreq, ctx->enc);
+	skcipher_request_set_callback(skreq, flags,
+				      req->base.complete, req->base.data);
+	skcipher_request_set_crypt(skreq, dst, dst, cryptlen, req->iv);
 
-	return crypto_ablkcipher_decrypt(abreq);
+	return crypto_skcipher_decrypt(skreq);
 }
 
 static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq,
@@ -331,20 +334,20 @@ static int crypto_authenc_esn_init_tfm(struct crypto_aead *tfm)
 	struct authenc_esn_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 	int err;
 
 	auth = crypto_spawn_ahash(&ictx->auth);
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
-	enc = crypto_spawn_skcipher(&ictx->enc);
+	enc = crypto_spawn_skcipher2(&ictx->enc);
 	err = PTR_ERR(enc);
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
-	null = crypto_get_default_null_skcipher();
+	null = crypto_get_default_null_skcipher2();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_skcipher;
@@ -361,15 +364,15 @@ static int crypto_authenc_esn_init_tfm(struct crypto_aead *tfm)
 		sizeof(struct authenc_esn_request_ctx) +
 		ctx->reqoff +
 		max_t(unsigned int,
-			crypto_ahash_reqsize(auth) +
-			sizeof(struct ahash_request),
-			sizeof(struct skcipher_givcrypt_request) +
-			crypto_ablkcipher_reqsize(enc)));
+		      crypto_ahash_reqsize(auth) +
+		      sizeof(struct ahash_request),
+		      sizeof(struct skcipher_request) +
+		      crypto_skcipher_reqsize(enc)));
 
 	return 0;
 
 err_free_skcipher:
-	crypto_free_ablkcipher(enc);
+	crypto_free_skcipher(enc);
 err_free_ahash:
 	crypto_free_ahash(auth);
 	return err;
@@ -380,8 +383,8 @@ static void crypto_authenc_esn_exit_tfm(struct crypto_aead *tfm)
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->auth);
-	crypto_free_ablkcipher(ctx->enc);
-	crypto_put_default_null_skcipher();
+	crypto_free_skcipher(ctx->enc);
+	crypto_put_default_null_skcipher2();
 }
 
 static void crypto_authenc_esn_free(struct aead_instance *inst)
@@ -400,7 +403,7 @@ static int crypto_authenc_esn_create(struct crypto_template *tmpl,
 	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
-	struct crypto_alg *enc;
+	struct skcipher_alg *enc;
 	struct authenc_esn_instance_ctx *ctx;
 	const char *enc_name;
 	int err;
@@ -413,7 +416,8 @@ static int crypto_authenc_esn_create(struct crypto_template *tmpl,
 		return -EINVAL;
 
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
-			       CRYPTO_ALG_TYPE_AHASH_MASK);
+			      CRYPTO_ALG_TYPE_AHASH_MASK |
+			      crypto_requires_sync(algt->type, algt->mask));
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
@@ -437,34 +441,36 @@ static int crypto_authenc_esn_create(struct crypto_template *tmpl,
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->enc, enc_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_auth;
 
-	enc = crypto_skcipher_spawn_alg(&ctx->enc);
+	enc = crypto_spawn_skcipher_alg(&ctx->enc);
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
 		     "authencesn(%s,%s)", auth_base->cra_name,
-		     enc->cra_name) >= CRYPTO_MAX_ALG_NAME)
+		     enc->base.cra_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "authencesn(%s,%s)", auth_base->cra_driver_name,
-		     enc->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		     enc->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	inst->alg.base.cra_flags = enc->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.base.cra_priority = enc->cra_priority * 10 +
+	inst->alg.base.cra_flags = (auth_base->cra_flags |
+				    enc->base.cra_flags) & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = enc->base.cra_priority * 10 +
 				      auth_base->cra_priority;
-	inst->alg.base.cra_blocksize = enc->cra_blocksize;
+	inst->alg.base.cra_blocksize = enc->base.cra_blocksize;
 	inst->alg.base.cra_alignmask = auth_base->cra_alignmask |
-				       enc->cra_alignmask;
+				       enc->base.cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_authenc_esn_ctx);
 
-	inst->alg.ivsize = enc->cra_ablkcipher.ivsize;
+	inst->alg.ivsize = crypto_skcipher_alg_ivsize(enc);
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(enc);
 	inst->alg.maxauthsize = auth->digestsize;
 
 	inst->alg.init = crypto_authenc_esn_init_tfm;
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 8cc1622b2ee0..369999530108 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -21,7 +21,6 @@
 #include <linux/hardirq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/scatterlist.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -466,10 +465,6 @@ static int crypto_init_blkcipher_ops_async(struct crypto_tfm *tfm)
 	crt->setkey = async_setkey;
 	crt->encrypt = async_encrypt;
 	crt->decrypt = async_decrypt;
-	if (!alg->ivsize) {
-		crt->givencrypt = skcipher_null_givencrypt;
-		crt->givdecrypt = skcipher_null_givdecrypt;
-	}
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
 
@@ -560,185 +555,5 @@ const struct crypto_type crypto_blkcipher_type = {
 };
 EXPORT_SYMBOL_GPL(crypto_blkcipher_type);
 
-static int crypto_grab_nivcipher(struct crypto_skcipher_spawn *spawn,
-				const char *name, u32 type, u32 mask)
-{
-	struct crypto_alg *alg;
-	int err;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask)| CRYPTO_ALG_GENIV;
-
-	alg = crypto_alg_mod_lookup(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
-
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
-	return err;
-}
-
-struct crypto_instance *skcipher_geniv_alloc(struct crypto_template *tmpl,
-					     struct rtattr **tb, u32 type,
-					     u32 mask)
-{
-	struct {
-		int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key,
-			      unsigned int keylen);
-		int (*encrypt)(struct ablkcipher_request *req);
-		int (*decrypt)(struct ablkcipher_request *req);
-
-		unsigned int min_keysize;
-		unsigned int max_keysize;
-		unsigned int ivsize;
-
-		const char *geniv;
-	} balg;
-	const char *name;
-	struct crypto_skcipher_spawn *spawn;
-	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
-	int err;
-
-	algt = crypto_get_attr_type(tb);
-	if (IS_ERR(algt))
-		return ERR_CAST(algt);
-
-	if ((algt->type ^ (CRYPTO_ALG_TYPE_GIVCIPHER | CRYPTO_ALG_GENIV)) &
-	    algt->mask)
-		return ERR_PTR(-EINVAL);
-
-	name = crypto_attr_alg_name(tb[1]);
-	if (IS_ERR(name))
-		return ERR_CAST(name);
-
-	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
-	if (!inst)
-		return ERR_PTR(-ENOMEM);
-
-	spawn = crypto_instance_ctx(inst);
-
-	/* Ignore async algorithms if necessary. */
-	mask |= crypto_requires_sync(algt->type, algt->mask);
-
-	crypto_set_skcipher_spawn(spawn, inst);
-	err = crypto_grab_nivcipher(spawn, name, type, mask);
-	if (err)
-		goto err_free_inst;
-
-	alg = crypto_skcipher_spawn_alg(spawn);
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER) {
-		balg.ivsize = alg->cra_blkcipher.ivsize;
-		balg.min_keysize = alg->cra_blkcipher.min_keysize;
-		balg.max_keysize = alg->cra_blkcipher.max_keysize;
-
-		balg.setkey = async_setkey;
-		balg.encrypt = async_encrypt;
-		balg.decrypt = async_decrypt;
-
-		balg.geniv = alg->cra_blkcipher.geniv;
-	} else {
-		balg.ivsize = alg->cra_ablkcipher.ivsize;
-		balg.min_keysize = alg->cra_ablkcipher.min_keysize;
-		balg.max_keysize = alg->cra_ablkcipher.max_keysize;
-
-		balg.setkey = alg->cra_ablkcipher.setkey;
-		balg.encrypt = alg->cra_ablkcipher.encrypt;
-		balg.decrypt = alg->cra_ablkcipher.decrypt;
-
-		balg.geniv = alg->cra_ablkcipher.geniv;
-	}
-
-	err = -EINVAL;
-	if (!balg.ivsize)
-		goto err_drop_alg;
-
-	/*
-	 * This is only true if we're constructing an algorithm with its
-	 * default IV generator.  For the default generator we elide the
-	 * template name and double-check the IV generator.
-	 */
-	if (algt->mask & CRYPTO_ALG_GENIV) {
-		if (!balg.geniv)
-			balg.geniv = crypto_default_geniv(alg);
-		err = -EAGAIN;
-		if (strcmp(tmpl->name, balg.geniv))
-			goto err_drop_alg;
-
-		memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
-		memcpy(inst->alg.cra_driver_name, alg->cra_driver_name,
-		       CRYPTO_MAX_ALG_NAME);
-	} else {
-		err = -ENAMETOOLONG;
-		if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
-		if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_driver_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
-	}
-
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_GIVCIPHER | CRYPTO_ALG_GENIV;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_givcipher_type;
-
-	inst->alg.cra_ablkcipher.ivsize = balg.ivsize;
-	inst->alg.cra_ablkcipher.min_keysize = balg.min_keysize;
-	inst->alg.cra_ablkcipher.max_keysize = balg.max_keysize;
-	inst->alg.cra_ablkcipher.geniv = balg.geniv;
-
-	inst->alg.cra_ablkcipher.setkey = balg.setkey;
-	inst->alg.cra_ablkcipher.encrypt = balg.encrypt;
-	inst->alg.cra_ablkcipher.decrypt = balg.decrypt;
-
-out:
-	return inst;
-
-err_drop_alg:
-	crypto_drop_skcipher(spawn);
-err_free_inst:
-	kfree(inst);
-	inst = ERR_PTR(err);
-	goto out;
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_alloc);
-
-void skcipher_geniv_free(struct crypto_instance *inst)
-{
-	crypto_drop_skcipher(crypto_instance_ctx(inst));
-	kfree(inst);
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_free);
-
-int skcipher_geniv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_ablkcipher *cipher;
-
-	cipher = crypto_spawn_skcipher(crypto_instance_ctx(inst));
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	tfm->crt_ablkcipher.base = cipher;
-	tfm->crt_ablkcipher.reqsize += crypto_ablkcipher_reqsize(cipher);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_init);
-
-void skcipher_geniv_exit(struct crypto_tfm *tfm)
-{
-	crypto_free_ablkcipher(tfm->crt_ablkcipher.base);
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_exit);
-
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Generic block chaining cipher type");
diff --git a/crypto/ccm.c b/crypto/ccm.c
index cc31ea4335bf..006d8575ef5c 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -28,7 +28,7 @@ struct ccm_instance_ctx {
 
 struct crypto_ccm_ctx {
 	struct crypto_cipher *cipher;
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 };
 
 struct crypto_rfc4309_ctx {
@@ -50,7 +50,7 @@ struct crypto_ccm_req_priv_ctx {
 	u32 flags;
 	struct scatterlist src[3];
 	struct scatterlist dst[3];
-	struct ablkcipher_request abreq;
+	struct skcipher_request skreq;
 };
 
 static inline struct crypto_ccm_req_priv_ctx *crypto_ccm_reqctx(
@@ -83,15 +83,15 @@ static int crypto_ccm_setkey(struct crypto_aead *aead, const u8 *key,
 			     unsigned int keylen)
 {
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead);
-	struct crypto_ablkcipher *ctr = ctx->ctr;
+	struct crypto_skcipher *ctr = ctx->ctr;
 	struct crypto_cipher *tfm = ctx->cipher;
 	int err = 0;
 
-	crypto_ablkcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
-				    CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(ctr, key, keylen);
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
+	crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(ctr, key, keylen);
+	crypto_aead_set_flags(aead, crypto_skcipher_get_flags(ctr) &
 			      CRYPTO_TFM_RES_MASK);
 	if (err)
 		goto out;
@@ -347,7 +347,7 @@ static int crypto_ccm_encrypt(struct aead_request *req)
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->abreq;
+	struct skcipher_request *skreq = &pctx->skreq;
 	struct scatterlist *dst;
 	unsigned int cryptlen = req->cryptlen;
 	u8 *odata = pctx->odata;
@@ -366,11 +366,11 @@ static int crypto_ccm_encrypt(struct aead_request *req)
 	if (req->src != req->dst)
 		dst = pctx->dst;
 
-	ablkcipher_request_set_tfm(abreq, ctx->ctr);
-	ablkcipher_request_set_callback(abreq, pctx->flags,
-					crypto_ccm_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, pctx->src, dst, cryptlen + 16, iv);
-	err = crypto_ablkcipher_encrypt(abreq);
+	skcipher_request_set_tfm(skreq, ctx->ctr);
+	skcipher_request_set_callback(skreq, pctx->flags,
+				      crypto_ccm_encrypt_done, req);
+	skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv);
+	err = crypto_skcipher_encrypt(skreq);
 	if (err)
 		return err;
 
@@ -407,7 +407,7 @@ static int crypto_ccm_decrypt(struct aead_request *req)
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->abreq;
+	struct skcipher_request *skreq = &pctx->skreq;
 	struct scatterlist *dst;
 	unsigned int authsize = crypto_aead_authsize(aead);
 	unsigned int cryptlen = req->cryptlen;
@@ -429,11 +429,11 @@ static int crypto_ccm_decrypt(struct aead_request *req)
 	if (req->src != req->dst)
 		dst = pctx->dst;
 
-	ablkcipher_request_set_tfm(abreq, ctx->ctr);
-	ablkcipher_request_set_callback(abreq, pctx->flags,
-					crypto_ccm_decrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, pctx->src, dst, cryptlen + 16, iv);
-	err = crypto_ablkcipher_decrypt(abreq);
+	skcipher_request_set_tfm(skreq, ctx->ctr);
+	skcipher_request_set_callback(skreq, pctx->flags,
+				      crypto_ccm_decrypt_done, req);
+	skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv);
+	err = crypto_skcipher_decrypt(skreq);
 	if (err)
 		return err;
 
@@ -454,7 +454,7 @@ static int crypto_ccm_init_tfm(struct crypto_aead *tfm)
 	struct ccm_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_cipher *cipher;
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 	unsigned long align;
 	int err;
 
@@ -462,7 +462,7 @@ static int crypto_ccm_init_tfm(struct crypto_aead *tfm)
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	ctr = crypto_spawn_skcipher(&ictx->ctr);
+	ctr = crypto_spawn_skcipher2(&ictx->ctr);
 	err = PTR_ERR(ctr);
 	if (IS_ERR(ctr))
 		goto err_free_cipher;
@@ -475,7 +475,7 @@ static int crypto_ccm_init_tfm(struct crypto_aead *tfm)
 	crypto_aead_set_reqsize(
 		tfm,
 		align + sizeof(struct crypto_ccm_req_priv_ctx) +
-		crypto_ablkcipher_reqsize(ctr));
+		crypto_skcipher_reqsize(ctr));
 
 	return 0;
 
@@ -489,7 +489,7 @@ static void crypto_ccm_exit_tfm(struct crypto_aead *tfm)
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_cipher(ctx->cipher);
-	crypto_free_ablkcipher(ctx->ctr);
+	crypto_free_skcipher(ctx->ctr);
 }
 
 static void crypto_ccm_free(struct aead_instance *inst)
@@ -509,7 +509,7 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 {
 	struct crypto_attr_type *algt;
 	struct aead_instance *inst;
-	struct crypto_alg *ctr;
+	struct skcipher_alg *ctr;
 	struct crypto_alg *cipher;
 	struct ccm_instance_ctx *ictx;
 	int err;
@@ -544,39 +544,40 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ictx->ctr, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ictx->ctr, ctr_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ictx->ctr, ctr_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_cipher;
 
-	ctr = crypto_skcipher_spawn_alg(&ictx->ctr);
+	ctr = crypto_spawn_skcipher_alg(&ictx->ctr);
 
 	/* Not a stream cipher? */
 	err = -EINVAL;
-	if (ctr->cra_blocksize != 1)
+	if (ctr->base.cra_blocksize != 1)
 		goto err_drop_ctr;
 
 	/* We want the real thing! */
-	if (ctr->cra_ablkcipher.ivsize != 16)
+	if (crypto_skcipher_alg_ivsize(ctr) != 16)
 		goto err_drop_ctr;
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "ccm_base(%s,%s)", ctr->cra_driver_name,
+		     "ccm_base(%s,%s)", ctr->base.cra_driver_name,
 		     cipher->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_ctr;
 
 	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
 
-	inst->alg.base.cra_flags = ctr->cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_flags = ctr->base.cra_flags & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (cipher->cra_priority +
-				       ctr->cra_priority) / 2;
+				       ctr->base.cra_priority) / 2;
 	inst->alg.base.cra_blocksize = 1;
 	inst->alg.base.cra_alignmask = cipher->cra_alignmask |
-				       ctr->cra_alignmask |
+				       ctr->base.cra_alignmask |
 				       (__alignof__(u32) - 1);
 	inst->alg.ivsize = 16;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(ctr);
 	inst->alg.maxauthsize = 16;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_ccm_ctx);
 	inst->alg.init = crypto_ccm_init_tfm;
@@ -863,6 +864,7 @@ static int crypto_rfc4309_create(struct crypto_template *tmpl,
 	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
 	inst->alg.ivsize = 8;
+	inst->alg.chunksize = crypto_aead_alg_chunksize(alg);
 	inst->alg.maxauthsize = 16;
 
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4309_ctx);
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index 7b6b935cef23..e899ef51dc8e 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -31,7 +31,7 @@ struct chachapoly_instance_ctx {
 };
 
 struct chachapoly_ctx {
-	struct crypto_ablkcipher *chacha;
+	struct crypto_skcipher *chacha;
 	struct crypto_ahash *poly;
 	/* key bytes we use for the ChaCha20 IV */
 	unsigned int saltlen;
@@ -53,7 +53,7 @@ struct poly_req {
 struct chacha_req {
 	u8 iv[CHACHA20_IV_SIZE];
 	struct scatterlist src[1];
-	struct ablkcipher_request req; /* must be last member */
+	struct skcipher_request req; /* must be last member */
 };
 
 struct chachapoly_req_ctx {
@@ -144,12 +144,12 @@ static int chacha_decrypt(struct aead_request *req)
 		dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);
 	}
 
-	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
-					chacha_decrypt_done, req);
-	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, src, dst,
-				     rctx->cryptlen, creq->iv);
-	err = crypto_ablkcipher_decrypt(&creq->req);
+	skcipher_request_set_callback(&creq->req, aead_request_flags(req),
+				      chacha_decrypt_done, req);
+	skcipher_request_set_tfm(&creq->req, ctx->chacha);
+	skcipher_request_set_crypt(&creq->req, src, dst,
+				   rctx->cryptlen, creq->iv);
+	err = crypto_skcipher_decrypt(&creq->req);
 	if (err)
 		return err;
 
@@ -393,13 +393,13 @@ static int poly_genkey(struct aead_request *req)
 
 	chacha_iv(creq->iv, req, 0);
 
-	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
-					poly_genkey_done, req);
-	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, creq->src, creq->src,
-				     POLY1305_KEY_SIZE, creq->iv);
+	skcipher_request_set_callback(&creq->req, aead_request_flags(req),
+				      poly_genkey_done, req);
+	skcipher_request_set_tfm(&creq->req, ctx->chacha);
+	skcipher_request_set_crypt(&creq->req, creq->src, creq->src,
+				   POLY1305_KEY_SIZE, creq->iv);
 
-	err = crypto_ablkcipher_decrypt(&creq->req);
+	err = crypto_skcipher_decrypt(&creq->req);
 	if (err)
 		return err;
 
@@ -433,12 +433,12 @@ static int chacha_encrypt(struct aead_request *req)
 		dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);
 	}
 
-	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
-					chacha_encrypt_done, req);
-	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, src, dst,
-				     req->cryptlen, creq->iv);
-	err = crypto_ablkcipher_encrypt(&creq->req);
+	skcipher_request_set_callback(&creq->req, aead_request_flags(req),
+				      chacha_encrypt_done, req);
+	skcipher_request_set_tfm(&creq->req, ctx->chacha);
+	skcipher_request_set_crypt(&creq->req, src, dst,
+				   req->cryptlen, creq->iv);
+	err = crypto_skcipher_encrypt(&creq->req);
 	if (err)
 		return err;
 
@@ -500,13 +500,13 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key,
 	keylen -= ctx->saltlen;
 	memcpy(ctx->salt, key + keylen, ctx->saltlen);
 
-	crypto_ablkcipher_clear_flags(ctx->chacha, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(ctx->chacha, crypto_aead_get_flags(aead) &
-				    CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(ctx->chacha, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctx->chacha, crypto_aead_get_flags(aead) &
+					       CRYPTO_TFM_REQ_MASK);
 
-	err = crypto_ablkcipher_setkey(ctx->chacha, key, keylen);
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctx->chacha) &
-			      CRYPTO_TFM_RES_MASK);
+	err = crypto_skcipher_setkey(ctx->chacha, key, keylen);
+	crypto_aead_set_flags(aead, crypto_skcipher_get_flags(ctx->chacha) &
+				    CRYPTO_TFM_RES_MASK);
 	return err;
 }
 
@@ -524,7 +524,7 @@ static int chachapoly_init(struct crypto_aead *tfm)
 	struct aead_instance *inst = aead_alg_instance(tfm);
 	struct chachapoly_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
-	struct crypto_ablkcipher *chacha;
+	struct crypto_skcipher *chacha;
 	struct crypto_ahash *poly;
 	unsigned long align;
 
@@ -532,7 +532,7 @@ static int chachapoly_init(struct crypto_aead *tfm)
 	if (IS_ERR(poly))
 		return PTR_ERR(poly);
 
-	chacha = crypto_spawn_skcipher(&ictx->chacha);
+	chacha = crypto_spawn_skcipher2(&ictx->chacha);
 	if (IS_ERR(chacha)) {
 		crypto_free_ahash(poly);
 		return PTR_ERR(chacha);
@@ -548,8 +548,8 @@ static int chachapoly_init(struct crypto_aead *tfm)
 		tfm,
 		align + offsetof(struct chachapoly_req_ctx, u) +
 		max(offsetof(struct chacha_req, req) +
-		    sizeof(struct ablkcipher_request) +
-		    crypto_ablkcipher_reqsize(chacha),
+		    sizeof(struct skcipher_request) +
+		    crypto_skcipher_reqsize(chacha),
 		    offsetof(struct poly_req, req) +
 		    sizeof(struct ahash_request) +
 		    crypto_ahash_reqsize(poly)));
@@ -562,7 +562,7 @@ static void chachapoly_exit(struct crypto_aead *tfm)
 	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->poly);
-	crypto_free_ablkcipher(ctx->chacha);
+	crypto_free_skcipher(ctx->chacha);
 }
 
 static void chachapoly_free(struct aead_instance *inst)
@@ -579,7 +579,7 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 {
 	struct crypto_attr_type *algt;
 	struct aead_instance *inst;
-	struct crypto_alg *chacha;
+	struct skcipher_alg *chacha;
 	struct crypto_alg *poly;
 	struct hash_alg_common *poly_hash;
 	struct chachapoly_instance_ctx *ctx;
@@ -605,7 +605,9 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 
 	poly = crypto_find_alg(poly_name, &crypto_ahash_type,
 			       CRYPTO_ALG_TYPE_HASH,
-			       CRYPTO_ALG_TYPE_AHASH_MASK);
+			       CRYPTO_ALG_TYPE_AHASH_MASK |
+			       crypto_requires_sync(algt->type,
+						    algt->mask));
 	if (IS_ERR(poly))
 		return PTR_ERR(poly);
 
@@ -623,20 +625,20 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ctx->chacha, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->chacha, chacha_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->chacha, chacha_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_poly;
 
-	chacha = crypto_skcipher_spawn_alg(&ctx->chacha);
+	chacha = crypto_spawn_skcipher_alg(&ctx->chacha);
 
 	err = -EINVAL;
 	/* Need 16-byte IV size, including Initial Block Counter value */
-	if (chacha->cra_ablkcipher.ivsize != CHACHA20_IV_SIZE)
+	if (crypto_skcipher_alg_ivsize(chacha) != CHACHA20_IV_SIZE)
 		goto out_drop_chacha;
 	/* Not a stream cipher? */
-	if (chacha->cra_blocksize != 1)
+	if (chacha->base.cra_blocksize != 1)
 		goto out_drop_chacha;
 
 	err = -ENAMETOOLONG;
@@ -645,20 +647,21 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 		     poly_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "%s(%s,%s)", name, chacha->cra_driver_name,
+		     "%s(%s,%s)", name, chacha->base.cra_driver_name,
 		     poly->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
 
-	inst->alg.base.cra_flags = (chacha->cra_flags | poly->cra_flags) &
+	inst->alg.base.cra_flags = (chacha->base.cra_flags | poly->cra_flags) &
 				   CRYPTO_ALG_ASYNC;
-	inst->alg.base.cra_priority = (chacha->cra_priority +
+	inst->alg.base.cra_priority = (chacha->base.cra_priority +
 				       poly->cra_priority) / 2;
 	inst->alg.base.cra_blocksize = 1;
-	inst->alg.base.cra_alignmask = chacha->cra_alignmask |
+	inst->alg.base.cra_alignmask = chacha->base.cra_alignmask |
 				       poly->cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct chachapoly_ctx) +
 				     ctx->saltlen;
 	inst->alg.ivsize = ivsize;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(chacha);
 	inst->alg.maxauthsize = POLY1305_DIGEST_SIZE;
 	inst->alg.init = chachapoly_init;
 	inst->alg.exit = chachapoly_exit;
diff --git a/crypto/chainiv.c b/crypto/chainiv.c
deleted file mode 100644
index b4340018c8d4..000000000000
--- a/crypto/chainiv.c
+++ /dev/null
@@ -1,317 +0,0 @@
-/*
- * chainiv: Chain IV Generator
- *
- * Generate IVs simply be using the last block of the previous encryption.
- * This is mainly useful for CBC with a synchronous algorithm.
- *
- * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/skcipher.h>
-#include <crypto/rng.h>
-#include <crypto/crypto_wq.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/workqueue.h>
-
-enum {
-	CHAINIV_STATE_INUSE = 0,
-};
-
-struct chainiv_ctx {
-	spinlock_t lock;
-	char iv[];
-};
-
-struct async_chainiv_ctx {
-	unsigned long state;
-
-	spinlock_t lock;
-	int err;
-
-	struct crypto_queue queue;
-	struct work_struct postponed;
-
-	char iv[];
-};
-
-static int chainiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	unsigned int ivsize;
-	int err;
-
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags &
-						~CRYPTO_TFM_REQ_MAY_SLEEP,
-					req->creq.base.complete,
-					req->creq.base.data);
-	ablkcipher_request_set_crypt(subreq, req->creq.src, req->creq.dst,
-				     req->creq.nbytes, req->creq.info);
-
-	spin_lock_bh(&ctx->lock);
-
-	ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	memcpy(req->giv, ctx->iv, ivsize);
-	memcpy(subreq->info, ctx->iv, ivsize);
-
-	err = crypto_ablkcipher_encrypt(subreq);
-	if (err)
-		goto unlock;
-
-	memcpy(ctx->iv, subreq->info, ivsize);
-
-unlock:
-	spin_unlock_bh(&ctx->lock);
-
-	return err;
-}
-
-static int chainiv_init_common(struct crypto_tfm *tfm, char iv[])
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	int err = 0;
-
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
-
-	if (iv) {
-		err = crypto_rng_get_bytes(crypto_default_rng, iv,
-					   crypto_ablkcipher_ivsize(geniv));
-		crypto_put_default_rng();
-	}
-
-	return err ?: skcipher_geniv_init(tfm);
-}
-
-static int chainiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
-	char *iv;
-
-	spin_lock_init(&ctx->lock);
-
-	iv = NULL;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt = chainiv_givencrypt;
-		iv = ctx->iv;
-	}
-
-	return chainiv_init_common(tfm, iv);
-}
-
-static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx)
-{
-	int queued;
-	int err = ctx->err;
-
-	if (!ctx->queue.qlen) {
-		smp_mb__before_atomic();
-		clear_bit(CHAINIV_STATE_INUSE, &ctx->state);
-
-		if (!ctx->queue.qlen ||
-		    test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-			goto out;
-	}
-
-	queued = queue_work(kcrypto_wq, &ctx->postponed);
-	BUG_ON(!queued);
-
-out:
-	return err;
-}
-
-static int async_chainiv_postpone_request(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err;
-
-	spin_lock_bh(&ctx->lock);
-	err = skcipher_enqueue_givcrypt(&ctx->queue, req);
-	spin_unlock_bh(&ctx->lock);
-
-	if (test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-		return err;
-
-	ctx->err = err;
-	return async_chainiv_schedule_work(ctx);
-}
-
-static int async_chainiv_givencrypt_tail(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	unsigned int ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	memcpy(req->giv, ctx->iv, ivsize);
-	memcpy(subreq->info, ctx->iv, ivsize);
-
-	ctx->err = crypto_ablkcipher_encrypt(subreq);
-	if (ctx->err)
-		goto out;
-
-	memcpy(ctx->iv, subreq->info, ivsize);
-
-out:
-	return async_chainiv_schedule_work(ctx);
-}
-
-static int async_chainiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags,
-					req->creq.base.complete,
-					req->creq.base.data);
-	ablkcipher_request_set_crypt(subreq, req->creq.src, req->creq.dst,
-				     req->creq.nbytes, req->creq.info);
-
-	if (test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-		goto postpone;
-
-	if (ctx->queue.qlen) {
-		clear_bit(CHAINIV_STATE_INUSE, &ctx->state);
-		goto postpone;
-	}
-
-	return async_chainiv_givencrypt_tail(req);
-
-postpone:
-	return async_chainiv_postpone_request(req);
-}
-
-static void async_chainiv_do_postponed(struct work_struct *work)
-{
-	struct async_chainiv_ctx *ctx = container_of(work,
-						     struct async_chainiv_ctx,
-						     postponed);
-	struct skcipher_givcrypt_request *req;
-	struct ablkcipher_request *subreq;
-	int err;
-
-	/* Only handle one request at a time to avoid hogging keventd. */
-	spin_lock_bh(&ctx->lock);
-	req = skcipher_dequeue_givcrypt(&ctx->queue);
-	spin_unlock_bh(&ctx->lock);
-
-	if (!req) {
-		async_chainiv_schedule_work(ctx);
-		return;
-	}
-
-	subreq = skcipher_givcrypt_reqctx(req);
-	subreq->base.flags |= CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	err = async_chainiv_givencrypt_tail(req);
-
-	local_bh_disable();
-	skcipher_givcrypt_complete(req, err);
-	local_bh_enable();
-}
-
-static int async_chainiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct async_chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
-	char *iv;
-
-	spin_lock_init(&ctx->lock);
-
-	crypto_init_queue(&ctx->queue, 100);
-	INIT_WORK(&ctx->postponed, async_chainiv_do_postponed);
-
-	iv = NULL;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt =
-			async_chainiv_givencrypt;
-		iv = ctx->iv;
-	}
-
-	return chainiv_init_common(tfm, iv);
-}
-
-static void async_chainiv_exit(struct crypto_tfm *tfm)
-{
-	struct async_chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	BUG_ON(test_bit(CHAINIV_STATE_INUSE, &ctx->state) || ctx->queue.qlen);
-
-	skcipher_geniv_exit(tfm);
-}
-
-static struct crypto_template chainiv_tmpl;
-
-static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
-{
-	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-
-	algt = crypto_get_attr_type(tb);
-	if (IS_ERR(algt))
-		return ERR_CAST(algt);
-
-	inst = skcipher_geniv_alloc(&chainiv_tmpl, tb, 0, 0);
-	if (IS_ERR(inst))
-		goto out;
-
-	inst->alg.cra_init = chainiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
-
-	inst->alg.cra_ctxsize = sizeof(struct chainiv_ctx);
-
-	if (!crypto_requires_sync(algt->type, algt->mask)) {
-		inst->alg.cra_flags |= CRYPTO_ALG_ASYNC;
-
-		inst->alg.cra_init = async_chainiv_init;
-		inst->alg.cra_exit = async_chainiv_exit;
-
-		inst->alg.cra_ctxsize = sizeof(struct async_chainiv_ctx);
-	}
-
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
-
-out:
-	return inst;
-}
-
-static struct crypto_template chainiv_tmpl = {
-	.name = "chainiv",
-	.alloc = chainiv_alloc,
-	.free = skcipher_geniv_free,
-	.module = THIS_MODULE,
-};
-
-static int __init chainiv_module_init(void)
-{
-	return crypto_register_template(&chainiv_tmpl);
-}
-
-static void chainiv_module_exit(void)
-{
-	crypto_unregister_template(&chainiv_tmpl);
-}
-
-module_init(chainiv_module_init);
-module_exit(chainiv_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Chain IV Generator");
-MODULE_ALIAS_CRYPTO("chainiv");
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 7921251cdb13..cf8037a87b2d 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -22,6 +22,7 @@
 #include <crypto/internal/aead.h>
 #include <crypto/cryptd.h>
 #include <crypto/crypto_wq.h>
+#include <linux/atomic.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -31,7 +32,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 
-#define CRYPTD_MAX_CPU_QLEN 100
+#define CRYPTD_MAX_CPU_QLEN 1000
 
 struct cryptd_cpu_queue {
 	struct crypto_queue queue;
@@ -58,6 +59,7 @@ struct aead_instance_ctx {
 };
 
 struct cryptd_blkcipher_ctx {
+	atomic_t refcnt;
 	struct crypto_blkcipher *child;
 };
 
@@ -66,6 +68,7 @@ struct cryptd_blkcipher_request_ctx {
 };
 
 struct cryptd_hash_ctx {
+	atomic_t refcnt;
 	struct crypto_shash *child;
 };
 
@@ -75,6 +78,7 @@ struct cryptd_hash_request_ctx {
 };
 
 struct cryptd_aead_ctx {
+	atomic_t refcnt;
 	struct crypto_aead *child;
 };
 
@@ -118,11 +122,29 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue,
 {
 	int cpu, err;
 	struct cryptd_cpu_queue *cpu_queue;
+	struct crypto_tfm *tfm;
+	atomic_t *refcnt;
+	bool may_backlog;
 
 	cpu = get_cpu();
 	cpu_queue = this_cpu_ptr(queue->cpu_queue);
 	err = crypto_enqueue_request(&cpu_queue->queue, request);
+
+	refcnt = crypto_tfm_ctx(request->tfm);
+	may_backlog = request->flags & CRYPTO_TFM_REQ_MAY_BACKLOG;
+
+	if (err == -EBUSY && !may_backlog)
+		goto out_put_cpu;
+
 	queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
+
+	if (!atomic_read(refcnt))
+		goto out_put_cpu;
+
+	tfm = request->tfm;
+	atomic_inc(refcnt);
+
+out_put_cpu:
 	put_cpu();
 
 	return err;
@@ -206,7 +228,10 @@ static void cryptd_blkcipher_crypt(struct ablkcipher_request *req,
 						unsigned int len))
 {
 	struct cryptd_blkcipher_request_ctx *rctx;
+	struct cryptd_blkcipher_ctx *ctx;
+	struct crypto_ablkcipher *tfm;
 	struct blkcipher_desc desc;
+	int refcnt;
 
 	rctx = ablkcipher_request_ctx(req);
 
@@ -222,9 +247,16 @@ static void cryptd_blkcipher_crypt(struct ablkcipher_request *req,
 	req->base.complete = rctx->complete;
 
 out:
+	tfm = crypto_ablkcipher_reqtfm(req);
+	ctx = crypto_ablkcipher_ctx(tfm);
+	refcnt = atomic_read(&ctx->refcnt);
+
 	local_bh_disable();
 	rctx->complete(&req->base, err);
 	local_bh_enable();
+
+	if (err != -EINPROGRESS && refcnt && atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ablkcipher(tfm);
 }
 
 static void cryptd_blkcipher_encrypt(struct crypto_async_request *req, int err)
@@ -456,6 +488,21 @@ static int cryptd_hash_enqueue(struct ahash_request *req,
 	return cryptd_enqueue_request(queue, &req->base);
 }
 
+static void cryptd_hash_complete(struct ahash_request *req, int err)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	int refcnt = atomic_read(&ctx->refcnt);
+
+	local_bh_disable();
+	rctx->complete(&req->base, err);
+	local_bh_enable();
+
+	if (err != -EINPROGRESS && refcnt && atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ahash(tfm);
+}
+
 static void cryptd_hash_init(struct crypto_async_request *req_async, int err)
 {
 	struct cryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
@@ -475,9 +522,7 @@ static void cryptd_hash_init(struct crypto_async_request *req_async, int err)
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_init_enqueue(struct ahash_request *req)
@@ -500,9 +545,7 @@ static void cryptd_hash_update(struct crypto_async_request *req_async, int err)
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_update_enqueue(struct ahash_request *req)
@@ -523,9 +566,7 @@ static void cryptd_hash_final(struct crypto_async_request *req_async, int err)
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_final_enqueue(struct ahash_request *req)
@@ -546,9 +587,7 @@ static void cryptd_hash_finup(struct crypto_async_request *req_async, int err)
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_finup_enqueue(struct ahash_request *req)
@@ -575,9 +614,7 @@ static void cryptd_hash_digest(struct crypto_async_request *req_async, int err)
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_digest_enqueue(struct ahash_request *req)
@@ -688,7 +725,10 @@ static void cryptd_aead_crypt(struct aead_request *req,
 			int (*crypt)(struct aead_request *req))
 {
 	struct cryptd_aead_request_ctx *rctx;
+	struct cryptd_aead_ctx *ctx;
 	crypto_completion_t compl;
+	struct crypto_aead *tfm;
+	int refcnt;
 
 	rctx = aead_request_ctx(req);
 	compl = rctx->complete;
@@ -697,10 +737,18 @@ static void cryptd_aead_crypt(struct aead_request *req,
 		goto out;
 	aead_request_set_tfm(req, child);
 	err = crypt( req );
+
 out:
+	tfm = crypto_aead_reqtfm(req);
+	ctx = crypto_aead_ctx(tfm);
+	refcnt = atomic_read(&ctx->refcnt);
+
 	local_bh_disable();
 	compl(&req->base, err);
 	local_bh_enable();
+
+	if (err != -EINPROGRESS && refcnt && atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_aead(tfm);
 }
 
 static void cryptd_aead_encrypt(struct crypto_async_request *areq, int err)
@@ -883,6 +931,7 @@ struct cryptd_ablkcipher *cryptd_alloc_ablkcipher(const char *alg_name,
 						  u32 type, u32 mask)
 {
 	char cryptd_alg_name[CRYPTO_MAX_ALG_NAME];
+	struct cryptd_blkcipher_ctx *ctx;
 	struct crypto_tfm *tfm;
 
 	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
@@ -899,6 +948,9 @@ struct cryptd_ablkcipher *cryptd_alloc_ablkcipher(const char *alg_name,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ctx = crypto_tfm_ctx(tfm);
+	atomic_set(&ctx->refcnt, 1);
+
 	return __cryptd_ablkcipher_cast(__crypto_ablkcipher_cast(tfm));
 }
 EXPORT_SYMBOL_GPL(cryptd_alloc_ablkcipher);
@@ -910,9 +962,20 @@ struct crypto_blkcipher *cryptd_ablkcipher_child(struct cryptd_ablkcipher *tfm)
 }
 EXPORT_SYMBOL_GPL(cryptd_ablkcipher_child);
 
+bool cryptd_ablkcipher_queued(struct cryptd_ablkcipher *tfm)
+{
+	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(&tfm->base);
+
+	return atomic_read(&ctx->refcnt) - 1;
+}
+EXPORT_SYMBOL_GPL(cryptd_ablkcipher_queued);
+
 void cryptd_free_ablkcipher(struct cryptd_ablkcipher *tfm)
 {
-	crypto_free_ablkcipher(&tfm->base);
+	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(&tfm->base);
+
+	if (atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ablkcipher(&tfm->base);
 }
 EXPORT_SYMBOL_GPL(cryptd_free_ablkcipher);
 
@@ -920,6 +983,7 @@ struct cryptd_ahash *cryptd_alloc_ahash(const char *alg_name,
 					u32 type, u32 mask)
 {
 	char cryptd_alg_name[CRYPTO_MAX_ALG_NAME];
+	struct cryptd_hash_ctx *ctx;
 	struct crypto_ahash *tfm;
 
 	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
@@ -933,6 +997,9 @@ struct cryptd_ahash *cryptd_alloc_ahash(const char *alg_name,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ctx = crypto_ahash_ctx(tfm);
+	atomic_set(&ctx->refcnt, 1);
+
 	return __cryptd_ahash_cast(tfm);
 }
 EXPORT_SYMBOL_GPL(cryptd_alloc_ahash);
@@ -952,9 +1019,20 @@ struct shash_desc *cryptd_shash_desc(struct ahash_request *req)
 }
 EXPORT_SYMBOL_GPL(cryptd_shash_desc);
 
+bool cryptd_ahash_queued(struct cryptd_ahash *tfm)
+{
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
+
+	return atomic_read(&ctx->refcnt) - 1;
+}
+EXPORT_SYMBOL_GPL(cryptd_ahash_queued);
+
 void cryptd_free_ahash(struct cryptd_ahash *tfm)
 {
-	crypto_free_ahash(&tfm->base);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
+
+	if (atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ahash(&tfm->base);
 }
 EXPORT_SYMBOL_GPL(cryptd_free_ahash);
 
@@ -962,6 +1040,7 @@ struct cryptd_aead *cryptd_alloc_aead(const char *alg_name,
 						  u32 type, u32 mask)
 {
 	char cryptd_alg_name[CRYPTO_MAX_ALG_NAME];
+	struct cryptd_aead_ctx *ctx;
 	struct crypto_aead *tfm;
 
 	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
@@ -974,6 +1053,10 @@ struct cryptd_aead *cryptd_alloc_aead(const char *alg_name,
 		crypto_free_aead(tfm);
 		return ERR_PTR(-EINVAL);
 	}
+
+	ctx = crypto_aead_ctx(tfm);
+	atomic_set(&ctx->refcnt, 1);
+
 	return __cryptd_aead_cast(tfm);
 }
 EXPORT_SYMBOL_GPL(cryptd_alloc_aead);
@@ -986,9 +1069,20 @@ struct crypto_aead *cryptd_aead_child(struct cryptd_aead *tfm)
 }
 EXPORT_SYMBOL_GPL(cryptd_aead_child);
 
+bool cryptd_aead_queued(struct cryptd_aead *tfm)
+{
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(&tfm->base);
+
+	return atomic_read(&ctx->refcnt) - 1;
+}
+EXPORT_SYMBOL_GPL(cryptd_aead_queued);
+
 void cryptd_free_aead(struct cryptd_aead *tfm)
 {
-	crypto_free_aead(&tfm->base);
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(&tfm->base);
+
+	if (atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_aead(&tfm->base);
 }
 EXPORT_SYMBOL_GPL(cryptd_free_aead);
 
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index 941c9a434d50..20ff2c746e0b 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -26,7 +26,7 @@
 #include <linux/string.h>
 
 static DEFINE_MUTEX(crypto_default_null_skcipher_lock);
-static struct crypto_blkcipher *crypto_default_null_skcipher;
+static struct crypto_skcipher *crypto_default_null_skcipher;
 static int crypto_default_null_skcipher_refcnt;
 
 static int null_compress(struct crypto_tfm *tfm, const u8 *src,
@@ -153,15 +153,16 @@ MODULE_ALIAS_CRYPTO("compress_null");
 MODULE_ALIAS_CRYPTO("digest_null");
 MODULE_ALIAS_CRYPTO("cipher_null");
 
-struct crypto_blkcipher *crypto_get_default_null_skcipher(void)
+struct crypto_skcipher *crypto_get_default_null_skcipher(void)
 {
-	struct crypto_blkcipher *tfm;
+	struct crypto_skcipher *tfm;
 
 	mutex_lock(&crypto_default_null_skcipher_lock);
 	tfm = crypto_default_null_skcipher;
 
 	if (!tfm) {
-		tfm = crypto_alloc_blkcipher("ecb(cipher_null)", 0, 0);
+		tfm = crypto_alloc_skcipher("ecb(cipher_null)",
+					    0, CRYPTO_ALG_ASYNC);
 		if (IS_ERR(tfm))
 			goto unlock;
 
@@ -181,7 +182,7 @@ void crypto_put_default_null_skcipher(void)
 {
 	mutex_lock(&crypto_default_null_skcipher_lock);
 	if (!--crypto_default_null_skcipher_refcnt) {
-		crypto_free_blkcipher(crypto_default_null_skcipher);
+		crypto_free_skcipher(crypto_default_null_skcipher);
 		crypto_default_null_skcipher = NULL;
 	}
 	mutex_unlock(&crypto_default_null_skcipher_lock);
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 7097a3395b25..1c5705481c69 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -28,6 +28,7 @@
 #include <crypto/internal/skcipher.h>
 #include <crypto/internal/rng.h>
 #include <crypto/akcipher.h>
+#include <crypto/kpp.h>
 
 #include "internal.h"
 
@@ -126,6 +127,21 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_kpp rkpp;
+
+	strncpy(rkpp.type, "kpp", sizeof(rkpp.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_KPP,
+		    sizeof(struct crypto_report_kpp), &rkpp))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int crypto_report_one(struct crypto_alg *alg,
 			     struct crypto_user_alg *ualg, struct sk_buff *skb)
 {
@@ -176,6 +192,10 @@ static int crypto_report_one(struct crypto_alg *alg,
 			goto nla_put_failure;
 
 		break;
+	case CRYPTO_ALG_TYPE_KPP:
+		if (crypto_report_kpp(skb, alg))
+			goto nla_put_failure;
+		break;
 	}
 
 out:
@@ -358,32 +378,6 @@ drop_alg:
 	return err;
 }
 
-static struct crypto_alg *crypto_user_skcipher_alg(const char *name, u32 type,
-						   u32 mask)
-{
-	int err;
-	struct crypto_alg *alg;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask);
-
-	for (;;) {
-		alg = crypto_lookup_skcipher(name,  type, mask);
-		if (!IS_ERR(alg))
-			return alg;
-
-		err = PTR_ERR(alg);
-		if (err != -EAGAIN)
-			break;
-		if (fatal_signal_pending(current)) {
-			err = -EINTR;
-			break;
-		}
-	}
-
-	return ERR_PTR(err);
-}
-
 static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct nlattr **attrs)
 {
@@ -416,16 +410,7 @@ static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	else
 		name = p->cru_name;
 
-	switch (p->cru_type & p->cru_mask & CRYPTO_ALG_TYPE_MASK) {
-	case CRYPTO_ALG_TYPE_GIVCIPHER:
-	case CRYPTO_ALG_TYPE_BLKCIPHER:
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		alg = crypto_user_skcipher_alg(name, p->cru_type, p->cru_mask);
-		break;
-	default:
-		alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask);
-	}
-
+	alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask);
 	if (IS_ERR(alg))
 		return PTR_ERR(alg);
 
diff --git a/crypto/ctr.c b/crypto/ctr.c
index 2386f7313952..ff4d21eddb83 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -26,13 +26,13 @@ struct crypto_ctr_ctx {
 };
 
 struct crypto_rfc3686_ctx {
-	struct crypto_ablkcipher *child;
+	struct crypto_skcipher *child;
 	u8 nonce[CTR_RFC3686_NONCE_SIZE];
 };
 
 struct crypto_rfc3686_req_ctx {
 	u8 iv[CTR_RFC3686_BLOCK_SIZE];
-	struct ablkcipher_request subreq CRYPTO_MINALIGN_ATTR;
+	struct skcipher_request subreq CRYPTO_MINALIGN_ATTR;
 };
 
 static int crypto_ctr_setkey(struct crypto_tfm *parent, const u8 *key,
@@ -249,11 +249,11 @@ static struct crypto_template crypto_ctr_tmpl = {
 	.module = THIS_MODULE,
 };
 
-static int crypto_rfc3686_setkey(struct crypto_ablkcipher *parent,
+static int crypto_rfc3686_setkey(struct crypto_skcipher *parent,
 				 const u8 *key, unsigned int keylen)
 {
-	struct crypto_rfc3686_ctx *ctx = crypto_ablkcipher_ctx(parent);
-	struct crypto_ablkcipher *child = ctx->child;
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(parent);
+	struct crypto_skcipher *child = ctx->child;
 	int err;
 
 	/* the nonce is stored in bytes at end of key */
@@ -265,173 +265,178 @@ static int crypto_rfc3686_setkey(struct crypto_ablkcipher *parent,
 
 	keylen -= CTR_RFC3686_NONCE_SIZE;
 
-	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(parent) &
-				    CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(child, key, keylen);
-	crypto_ablkcipher_set_flags(parent, crypto_ablkcipher_get_flags(child) &
-				    CRYPTO_TFM_RES_MASK);
+	crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
+					 CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(child, key, keylen);
+	crypto_skcipher_set_flags(parent, crypto_skcipher_get_flags(child) &
+					  CRYPTO_TFM_RES_MASK);
 
 	return err;
 }
 
-static int crypto_rfc3686_crypt(struct ablkcipher_request *req)
+static int crypto_rfc3686_crypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct crypto_rfc3686_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct crypto_ablkcipher *child = ctx->child;
-	unsigned long align = crypto_ablkcipher_alignmask(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *child = ctx->child;
+	unsigned long align = crypto_skcipher_alignmask(tfm);
 	struct crypto_rfc3686_req_ctx *rctx =
-		(void *)PTR_ALIGN((u8 *)ablkcipher_request_ctx(req), align + 1);
-	struct ablkcipher_request *subreq = &rctx->subreq;
+		(void *)PTR_ALIGN((u8 *)skcipher_request_ctx(req), align + 1);
+	struct skcipher_request *subreq = &rctx->subreq;
 	u8 *iv = rctx->iv;
 
 	/* set up counter block */
 	memcpy(iv, ctx->nonce, CTR_RFC3686_NONCE_SIZE);
-	memcpy(iv + CTR_RFC3686_NONCE_SIZE, req->info, CTR_RFC3686_IV_SIZE);
+	memcpy(iv + CTR_RFC3686_NONCE_SIZE, req->iv, CTR_RFC3686_IV_SIZE);
 
 	/* initialize counter portion of counter block */
 	*(__be32 *)(iv + CTR_RFC3686_NONCE_SIZE + CTR_RFC3686_IV_SIZE) =
 		cpu_to_be32(1);
 
-	ablkcipher_request_set_tfm(subreq, child);
-	ablkcipher_request_set_callback(subreq, req->base.flags,
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(subreq, req->src, req->dst, req->nbytes,
-				     iv);
+	skcipher_request_set_tfm(subreq, child);
+	skcipher_request_set_callback(subreq, req->base.flags,
+				      req->base.complete, req->base.data);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   req->cryptlen, iv);
 
-	return crypto_ablkcipher_encrypt(subreq);
+	return crypto_skcipher_encrypt(subreq);
 }
 
-static int crypto_rfc3686_init_tfm(struct crypto_tfm *tfm)
+static int crypto_rfc3686_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_skcipher_spawn *spawn = crypto_instance_ctx(inst);
-	struct crypto_rfc3686_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_ablkcipher *cipher;
+	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
+	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *cipher;
 	unsigned long align;
+	unsigned int reqsize;
 
-	cipher = crypto_spawn_skcipher(spawn);
+	cipher = crypto_spawn_skcipher2(spawn);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
 	ctx->child = cipher;
 
-	align = crypto_tfm_alg_alignmask(tfm);
+	align = crypto_skcipher_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_ablkcipher.reqsize = align +
-		sizeof(struct crypto_rfc3686_req_ctx) +
-		crypto_ablkcipher_reqsize(cipher);
+	reqsize = align + sizeof(struct crypto_rfc3686_req_ctx) +
+		  crypto_skcipher_reqsize(cipher);
+	crypto_skcipher_set_reqsize(tfm, reqsize);
 
 	return 0;
 }
 
-static void crypto_rfc3686_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_rfc3686_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_rfc3686_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_skcipher(ctx->child);
+}
 
-	crypto_free_ablkcipher(ctx->child);
+static void crypto_rfc3686_free(struct skcipher_instance *inst)
+{
+	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);
+
+	crypto_drop_skcipher(spawn);
+	kfree(inst);
 }
 
-static struct crypto_instance *crypto_rfc3686_alloc(struct rtattr **tb)
+static int crypto_rfc3686_create(struct crypto_template *tmpl,
+				 struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	struct skcipher_instance *inst;
+	struct skcipher_alg *alg;
 	struct crypto_skcipher_spawn *spawn;
 	const char *cipher_name;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
-	if ((algt->type ^ CRYPTO_ALG_TYPE_BLKCIPHER) & algt->mask)
-		return ERR_PTR(-EINVAL);
+	if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
+		return -EINVAL;
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
-		return ERR_CAST(cipher_name);
+		return PTR_ERR(cipher_name);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
 	if (!inst)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	spawn = crypto_instance_ctx(inst);
+	spawn = skcipher_instance_ctx(inst);
 
-	crypto_set_skcipher_spawn(spawn, inst);
-	err = crypto_grab_skcipher(spawn, cipher_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
+	err = crypto_grab_skcipher2(spawn, cipher_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_free_inst;
 
-	alg = crypto_skcipher_spawn_alg(spawn);
+	alg = crypto_spawn_skcipher_alg(spawn);
 
 	/* We only support 16-byte blocks. */
 	err = -EINVAL;
-	if (alg->cra_ablkcipher.ivsize != CTR_RFC3686_BLOCK_SIZE)
+	if (crypto_skcipher_alg_ivsize(alg) != CTR_RFC3686_BLOCK_SIZE)
 		goto err_drop_spawn;
 
 	/* Not a stream cipher? */
-	if (alg->cra_blocksize != 1)
+	if (alg->base.cra_blocksize != 1)
 		goto err_drop_spawn;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, "rfc3686(%s)",
-		     alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc3686(%s)", alg->base.cra_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_spawn;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc3686(%s)", alg->cra_driver_name) >=
-			CRYPTO_MAX_ALG_NAME)
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc3686(%s)", alg->base.cra_driver_name) >=
+	    CRYPTO_MAX_ALG_NAME)
 		goto err_drop_spawn;
 
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-			      (alg->cra_flags & CRYPTO_ALG_ASYNC);
-	inst->alg.cra_type = &crypto_ablkcipher_type;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
 
-	inst->alg.cra_ablkcipher.ivsize = CTR_RFC3686_IV_SIZE;
-	inst->alg.cra_ablkcipher.min_keysize =
-		alg->cra_ablkcipher.min_keysize + CTR_RFC3686_NONCE_SIZE;
-	inst->alg.cra_ablkcipher.max_keysize =
-		alg->cra_ablkcipher.max_keysize + CTR_RFC3686_NONCE_SIZE;
+	inst->alg.ivsize = CTR_RFC3686_IV_SIZE;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(alg);
+	inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(alg) +
+				CTR_RFC3686_NONCE_SIZE;
+	inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(alg) +
+				CTR_RFC3686_NONCE_SIZE;
 
-	inst->alg.cra_ablkcipher.geniv = "seqiv";
+	inst->alg.setkey = crypto_rfc3686_setkey;
+	inst->alg.encrypt = crypto_rfc3686_crypt;
+	inst->alg.decrypt = crypto_rfc3686_crypt;
 
-	inst->alg.cra_ablkcipher.setkey = crypto_rfc3686_setkey;
-	inst->alg.cra_ablkcipher.encrypt = crypto_rfc3686_crypt;
-	inst->alg.cra_ablkcipher.decrypt = crypto_rfc3686_crypt;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc3686_ctx);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc3686_ctx);
+	inst->alg.init = crypto_rfc3686_init_tfm;
+	inst->alg.exit = crypto_rfc3686_exit_tfm;
 
-	inst->alg.cra_init = crypto_rfc3686_init_tfm;
-	inst->alg.cra_exit = crypto_rfc3686_exit_tfm;
+	inst->free = crypto_rfc3686_free;
 
-	return inst;
+	err = skcipher_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_spawn;
+
+out:
+	return err;
 
 err_drop_spawn:
 	crypto_drop_skcipher(spawn);
 err_free_inst:
 	kfree(inst);
-	return ERR_PTR(err);
-}
-
-static void crypto_rfc3686_free(struct crypto_instance *inst)
-{
-	struct crypto_skcipher_spawn *spawn = crypto_instance_ctx(inst);
-
-	crypto_drop_skcipher(spawn);
-	kfree(inst);
+	goto out;
 }
 
 static struct crypto_template crypto_rfc3686_tmpl = {
 	.name = "rfc3686",
-	.alloc = crypto_rfc3686_alloc,
-	.free = crypto_rfc3686_free,
+	.create = crypto_rfc3686_create,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/cts.c b/crypto/cts.c
index e467ec0acf9f..51976187b2bf 100644
--- a/crypto/cts.c
+++ b/crypto/cts.c
@@ -40,7 +40,7 @@
  * rfc3962 includes errata information in its Appendix A.
  */
 
-#include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -51,289 +51,364 @@
 #include <linux/slab.h>
 
 struct crypto_cts_ctx {
-	struct crypto_blkcipher *child;
+	struct crypto_skcipher *child;
 };
 
-static int crypto_cts_setkey(struct crypto_tfm *parent, const u8 *key,
-			     unsigned int keylen)
+struct crypto_cts_reqctx {
+	struct scatterlist sg[2];
+	unsigned offset;
+	struct skcipher_request subreq;
+};
+
+static inline u8 *crypto_cts_reqctx_space(struct skcipher_request *req)
 {
-	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(parent);
-	struct crypto_blkcipher *child = ctx->child;
-	int err;
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *child = ctx->child;
 
-	crypto_blkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_blkcipher_set_flags(child, crypto_tfm_get_flags(parent) &
-				       CRYPTO_TFM_REQ_MASK);
-	err = crypto_blkcipher_setkey(child, key, keylen);
-	crypto_tfm_set_flags(parent, crypto_blkcipher_get_flags(child) &
-				     CRYPTO_TFM_RES_MASK);
-	return err;
+	return PTR_ALIGN((u8 *)(rctx + 1) + crypto_skcipher_reqsize(child),
+			 crypto_skcipher_alignmask(tfm) + 1);
 }
 
-static int cts_cbc_encrypt(struct crypto_cts_ctx *ctx,
-			   struct blkcipher_desc *desc,
-			   struct scatterlist *dst,
-			   struct scatterlist *src,
-			   unsigned int offset,
-			   unsigned int nbytes)
+static int crypto_cts_setkey(struct crypto_skcipher *parent, const u8 *key,
+			     unsigned int keylen)
 {
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	u8 tmp[bsize], tmp2[bsize];
-	struct blkcipher_desc lcldesc;
-	struct scatterlist sgsrc[1], sgdst[1];
-	int lastn = nbytes - bsize;
-	u8 iv[bsize];
-	u8 s[bsize * 2], d[bsize * 2];
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(parent);
+	struct crypto_skcipher *child = ctx->child;
 	int err;
 
-	if (lastn < 0)
-		return -EINVAL;
+	crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
+					 CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(child, key, keylen);
+	crypto_skcipher_set_flags(parent, crypto_skcipher_get_flags(child) &
+					  CRYPTO_TFM_RES_MASK);
+	return err;
+}
 
-	sg_init_table(sgsrc, 1);
-	sg_init_table(sgdst, 1);
+static void cts_cbc_crypt_done(struct crypto_async_request *areq, int err)
+{
+	struct skcipher_request *req = areq->data;
 
-	memset(s, 0, sizeof(s));
-	scatterwalk_map_and_copy(s, src, offset, nbytes, 0);
+	if (err == -EINPROGRESS)
+		return;
 
-	memcpy(iv, desc->info, bsize);
+	skcipher_request_complete(req, err);
+}
 
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = iv;
-	lcldesc.flags = desc->flags;
+static int cts_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	u8 d[bsize * 2] __attribute__ ((aligned(__alignof__(u32))));
+	struct scatterlist *sg;
+	unsigned int offset;
+	int lastn;
+
+	offset = rctx->offset;
+	lastn = req->cryptlen - offset;
+
+	sg = scatterwalk_ffwd(rctx->sg, req->dst, offset - bsize);
+	scatterwalk_map_and_copy(d + bsize, sg, 0, bsize, 0);
+
+	memset(d, 0, bsize);
+	scatterwalk_map_and_copy(d, req->src, offset, lastn, 0);
+
+	scatterwalk_map_and_copy(d, sg, 0, bsize + lastn, 1);
+	memzero_explicit(d, sizeof(d));
+
+	skcipher_request_set_callback(subreq, req->base.flags &
+					      CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      cts_cbc_crypt_done, req);
+	skcipher_request_set_crypt(subreq, sg, sg, bsize, req->iv);
+	return crypto_skcipher_encrypt(subreq);
+}
 
-	sg_set_buf(&sgsrc[0], s, bsize);
-	sg_set_buf(&sgdst[0], tmp, bsize);
-	err = crypto_blkcipher_encrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
+static void crypto_cts_encrypt_done(struct crypto_async_request *areq, int err)
+{
+	struct skcipher_request *req = areq->data;
 
-	memcpy(d + bsize, tmp, lastn);
+	if (err)
+		goto out;
 
-	lcldesc.info = tmp;
+	err = cts_cbc_encrypt(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
+		return;
 
-	sg_set_buf(&sgsrc[0], s + bsize, bsize);
-	sg_set_buf(&sgdst[0], tmp2, bsize);
-	err = crypto_blkcipher_encrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
+out:
+	skcipher_request_complete(req, err);
+}
 
-	memcpy(d, tmp2, bsize);
+static int crypto_cts_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	unsigned int nbytes = req->cryptlen;
+	int cbc_blocks = (nbytes + bsize - 1) / bsize - 1;
+	unsigned int offset;
+
+	skcipher_request_set_tfm(subreq, ctx->child);
+
+	if (cbc_blocks <= 0) {
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      req->base.complete,
+					      req->base.data);
+		skcipher_request_set_crypt(subreq, req->src, req->dst, nbytes,
+					   req->iv);
+		return crypto_skcipher_encrypt(subreq);
+	}
 
-	scatterwalk_map_and_copy(d, dst, offset, nbytes, 1);
+	offset = cbc_blocks * bsize;
+	rctx->offset = offset;
 
-	memcpy(desc->info, tmp2, bsize);
+	skcipher_request_set_callback(subreq, req->base.flags,
+				      crypto_cts_encrypt_done, req);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   offset, req->iv);
 
-	return err;
+	return crypto_skcipher_encrypt(subreq) ?:
+	       cts_cbc_encrypt(req);
 }
 
-static int crypto_cts_encrypt(struct blkcipher_desc *desc,
-			      struct scatterlist *dst, struct scatterlist *src,
-			      unsigned int nbytes)
+static int cts_cbc_decrypt(struct skcipher_request *req)
 {
-	struct crypto_cts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	int tot_blocks = (nbytes + bsize - 1) / bsize;
-	int cbc_blocks = tot_blocks > 2 ? tot_blocks - 2 : 0;
-	struct blkcipher_desc lcldesc;
-	int err;
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	u8 d[bsize * 2] __attribute__ ((aligned(__alignof__(u32))));
+	struct scatterlist *sg;
+	unsigned int offset;
+	u8 *space;
+	int lastn;
+
+	offset = rctx->offset;
+	lastn = req->cryptlen - offset;
+
+	sg = scatterwalk_ffwd(rctx->sg, req->dst, offset - bsize);
+
+	/* 1. Decrypt Cn-1 (s) to create Dn */
+	scatterwalk_map_and_copy(d + bsize, sg, 0, bsize, 0);
+	space = crypto_cts_reqctx_space(req);
+	crypto_xor(d + bsize, space, bsize);
+	/* 2. Pad Cn with zeros at the end to create C of length BB */
+	memset(d, 0, bsize);
+	scatterwalk_map_and_copy(d, req->src, offset, lastn, 0);
+	/* 3. Exclusive-or Dn with C to create Xn */
+	/* 4. Select the first Ln bytes of Xn to create Pn */
+	crypto_xor(d + bsize, d, lastn);
+
+	/* 5. Append the tail (BB - Ln) bytes of Xn to Cn to create En */
+	memcpy(d + lastn, d + bsize + lastn, bsize - lastn);
+	/* 6. Decrypt En to create Pn-1 */
 
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = desc->info;
-	lcldesc.flags = desc->flags;
-
-	if (tot_blocks == 1) {
-		err = crypto_blkcipher_encrypt_iv(&lcldesc, dst, src, bsize);
-	} else if (nbytes <= bsize * 2) {
-		err = cts_cbc_encrypt(ctx, desc, dst, src, 0, nbytes);
-	} else {
-		/* do normal function for tot_blocks - 2 */
-		err = crypto_blkcipher_encrypt_iv(&lcldesc, dst, src,
-							cbc_blocks * bsize);
-		if (err == 0) {
-			/* do cts for final two blocks */
-			err = cts_cbc_encrypt(ctx, desc, dst, src,
-						cbc_blocks * bsize,
-						nbytes - (cbc_blocks * bsize));
-		}
-	}
+	scatterwalk_map_and_copy(d, sg, 0, bsize + lastn, 1);
+	memzero_explicit(d, sizeof(d));
 
-	return err;
+	skcipher_request_set_callback(subreq, req->base.flags &
+					      CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      cts_cbc_crypt_done, req);
+
+	skcipher_request_set_crypt(subreq, sg, sg, bsize, space);
+	return crypto_skcipher_decrypt(subreq);
 }
 
-static int cts_cbc_decrypt(struct crypto_cts_ctx *ctx,
-			   struct blkcipher_desc *desc,
-			   struct scatterlist *dst,
-			   struct scatterlist *src,
-			   unsigned int offset,
-			   unsigned int nbytes)
+static void crypto_cts_decrypt_done(struct crypto_async_request *areq, int err)
 {
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	u8 tmp[bsize];
-	struct blkcipher_desc lcldesc;
-	struct scatterlist sgsrc[1], sgdst[1];
-	int lastn = nbytes - bsize;
-	u8 iv[bsize];
-	u8 s[bsize * 2], d[bsize * 2];
-	int err;
-
-	if (lastn < 0)
-		return -EINVAL;
+	struct skcipher_request *req = areq->data;
 
-	sg_init_table(sgsrc, 1);
-	sg_init_table(sgdst, 1);
+	if (err)
+		goto out;
 
-	scatterwalk_map_and_copy(s, src, offset, nbytes, 0);
+	err = cts_cbc_decrypt(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
+		return;
 
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = iv;
-	lcldesc.flags = desc->flags;
+out:
+	skcipher_request_complete(req, err);
+}
 
-	/* 1. Decrypt Cn-1 (s) to create Dn (tmp)*/
-	memset(iv, 0, sizeof(iv));
-	sg_set_buf(&sgsrc[0], s, bsize);
-	sg_set_buf(&sgdst[0], tmp, bsize);
-	err = crypto_blkcipher_decrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
-	if (err)
-		return err;
-	/* 2. Pad Cn with zeros at the end to create C of length BB */
-	memset(iv, 0, sizeof(iv));
-	memcpy(iv, s + bsize, lastn);
-	/* 3. Exclusive-or Dn (tmp) with C (iv) to create Xn (tmp) */
-	crypto_xor(tmp, iv, bsize);
-	/* 4. Select the first Ln bytes of Xn (tmp) to create Pn */
-	memcpy(d + bsize, tmp, lastn);
-
-	/* 5. Append the tail (BB - Ln) bytes of Xn (tmp) to Cn to create En */
-	memcpy(s + bsize + lastn, tmp + lastn, bsize - lastn);
-	/* 6. Decrypt En to create Pn-1 */
-	memzero_explicit(iv, sizeof(iv));
+static int crypto_cts_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	unsigned int nbytes = req->cryptlen;
+	int cbc_blocks = (nbytes + bsize - 1) / bsize - 1;
+	unsigned int offset;
+	u8 *space;
+
+	skcipher_request_set_tfm(subreq, ctx->child);
+
+	if (cbc_blocks <= 0) {
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      req->base.complete,
+					      req->base.data);
+		skcipher_request_set_crypt(subreq, req->src, req->dst, nbytes,
+					   req->iv);
+		return crypto_skcipher_decrypt(subreq);
+	}
 
-	sg_set_buf(&sgsrc[0], s + bsize, bsize);
-	sg_set_buf(&sgdst[0], d, bsize);
-	err = crypto_blkcipher_decrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
+	skcipher_request_set_callback(subreq, req->base.flags,
+				      crypto_cts_decrypt_done, req);
 
-	/* XOR with previous block */
-	crypto_xor(d, desc->info, bsize);
+	space = crypto_cts_reqctx_space(req);
 
-	scatterwalk_map_and_copy(d, dst, offset, nbytes, 1);
+	offset = cbc_blocks * bsize;
+	rctx->offset = offset;
 
-	memcpy(desc->info, s, bsize);
-	return err;
-}
+	if (cbc_blocks <= 1)
+		memcpy(space, req->iv, bsize);
+	else
+		scatterwalk_map_and_copy(space, req->src, offset - 2 * bsize,
+					 bsize, 0);
 
-static int crypto_cts_decrypt(struct blkcipher_desc *desc,
-			      struct scatterlist *dst, struct scatterlist *src,
-			      unsigned int nbytes)
-{
-	struct crypto_cts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	int tot_blocks = (nbytes + bsize - 1) / bsize;
-	int cbc_blocks = tot_blocks > 2 ? tot_blocks - 2 : 0;
-	struct blkcipher_desc lcldesc;
-	int err;
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   offset, req->iv);
 
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = desc->info;
-	lcldesc.flags = desc->flags;
-
-	if (tot_blocks == 1) {
-		err = crypto_blkcipher_decrypt_iv(&lcldesc, dst, src, bsize);
-	} else if (nbytes <= bsize * 2) {
-		err = cts_cbc_decrypt(ctx, desc, dst, src, 0, nbytes);
-	} else {
-		/* do normal function for tot_blocks - 2 */
-		err = crypto_blkcipher_decrypt_iv(&lcldesc, dst, src,
-							cbc_blocks * bsize);
-		if (err == 0) {
-			/* do cts for final two blocks */
-			err = cts_cbc_decrypt(ctx, desc, dst, src,
-						cbc_blocks * bsize,
-						nbytes - (cbc_blocks * bsize));
-		}
-	}
-	return err;
+	return crypto_skcipher_decrypt(subreq) ?:
+	       cts_cbc_decrypt(req);
 }
 
-static int crypto_cts_init_tfm(struct crypto_tfm *tfm)
+static int crypto_cts_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
-	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_blkcipher *cipher;
-
-	cipher = crypto_spawn_blkcipher(spawn);
+	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
+	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *cipher;
+	unsigned reqsize;
+	unsigned bsize;
+	unsigned align;
+
+	cipher = crypto_spawn_skcipher2(spawn);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
 	ctx->child = cipher;
+
+	align = crypto_skcipher_alignmask(tfm);
+	bsize = crypto_skcipher_blocksize(cipher);
+	reqsize = ALIGN(sizeof(struct crypto_cts_reqctx) +
+			crypto_skcipher_reqsize(cipher),
+			crypto_tfm_ctx_alignment()) +
+		  (align & ~(crypto_tfm_ctx_alignment() - 1)) + bsize;
+
+	crypto_skcipher_set_reqsize(tfm, reqsize);
+
 	return 0;
 }
 
-static void crypto_cts_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_cts_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(tfm);
-	crypto_free_blkcipher(ctx->child);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_skcipher(ctx->child);
 }
 
-static struct crypto_instance *crypto_cts_alloc(struct rtattr **tb)
+static void crypto_cts_free(struct skcipher_instance *inst)
 {
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	crypto_drop_skcipher(skcipher_instance_ctx(inst));
+	kfree(inst);
+}
+
+static int crypto_cts_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct crypto_skcipher_spawn *spawn;
+	struct skcipher_instance *inst;
+	struct crypto_attr_type *algt;
+	struct skcipher_alg *alg;
+	const char *cipher_name;
 	int err;
 
-	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER);
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return PTR_ERR(algt);
+
+	if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
+		return -EINVAL;
+
+	cipher_name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(cipher_name))
+		return PTR_ERR(cipher_name);
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	spawn = skcipher_instance_ctx(inst);
+
+	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
+	err = crypto_grab_skcipher2(spawn, cipher_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
-		return ERR_PTR(err);
+		goto err_free_inst;
 
-	alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_BLKCIPHER,
-				  CRYPTO_ALG_TYPE_MASK);
-	if (IS_ERR(alg))
-		return ERR_CAST(alg);
+	alg = crypto_spawn_skcipher_alg(spawn);
 
-	inst = ERR_PTR(-EINVAL);
-	if (!is_power_of_2(alg->cra_blocksize))
-		goto out_put_alg;
+	err = -EINVAL;
+	if (crypto_skcipher_alg_ivsize(alg) != alg->base.cra_blocksize)
+		goto err_drop_spawn;
 
-	if (strncmp(alg->cra_name, "cbc(", 4))
-		goto out_put_alg;
+	if (strncmp(alg->base.cra_name, "cbc(", 4))
+		goto err_drop_spawn;
 
-	inst = crypto_alloc_instance("cts", alg);
-	if (IS_ERR(inst))
-		goto out_put_alg;
+	err = crypto_inst_setname(skcipher_crypto_instance(inst), "cts",
+				  &alg->base);
+	if (err)
+		goto err_drop_spawn;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_blkcipher_type;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
 	/* We access the data as u32s when xoring. */
-	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
 
-	inst->alg.cra_blkcipher.ivsize = alg->cra_blocksize;
-	inst->alg.cra_blkcipher.min_keysize = alg->cra_blkcipher.min_keysize;
-	inst->alg.cra_blkcipher.max_keysize = alg->cra_blkcipher.max_keysize;
+	inst->alg.ivsize = alg->base.cra_blocksize;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(alg);
+	inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(alg);
+	inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(alg);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_cts_ctx);
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_cts_ctx);
 
-	inst->alg.cra_init = crypto_cts_init_tfm;
-	inst->alg.cra_exit = crypto_cts_exit_tfm;
+	inst->alg.init = crypto_cts_init_tfm;
+	inst->alg.exit = crypto_cts_exit_tfm;
 
-	inst->alg.cra_blkcipher.setkey = crypto_cts_setkey;
-	inst->alg.cra_blkcipher.encrypt = crypto_cts_encrypt;
-	inst->alg.cra_blkcipher.decrypt = crypto_cts_decrypt;
+	inst->alg.setkey = crypto_cts_setkey;
+	inst->alg.encrypt = crypto_cts_encrypt;
+	inst->alg.decrypt = crypto_cts_decrypt;
 
-out_put_alg:
-	crypto_mod_put(alg);
-	return inst;
-}
+	inst->free = crypto_cts_free;
 
-static void crypto_cts_free(struct crypto_instance *inst)
-{
-	crypto_drop_spawn(crypto_instance_ctx(inst));
+	err = skcipher_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_spawn;
+
+out:
+	return err;
+
+err_drop_spawn:
+	crypto_drop_skcipher(spawn);
+err_free_inst:
 	kfree(inst);
+	goto out;
 }
 
 static struct crypto_template crypto_cts_tmpl = {
 	.name = "cts",
-	.alloc = crypto_cts_alloc,
-	.free = crypto_cts_free,
+	.create = crypto_cts_create,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/dh.c b/crypto/dh.c
new file mode 100644
index 000000000000..9d19360e7189
--- /dev/null
+++ b/crypto/dh.c
@@ -0,0 +1,189 @@
+/*  Diffie-Hellman Key Agreement Method [RFC2631]
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/kpp.h>
+#include <crypto/dh.h>
+#include <linux/mpi.h>
+
+struct dh_ctx {
+	MPI p;
+	MPI g;
+	MPI xa;
+};
+
+static inline void dh_clear_params(struct dh_ctx *ctx)
+{
+	mpi_free(ctx->p);
+	mpi_free(ctx->g);
+	ctx->p = NULL;
+	ctx->g = NULL;
+}
+
+static void dh_free_ctx(struct dh_ctx *ctx)
+{
+	dh_clear_params(ctx);
+	mpi_free(ctx->xa);
+	ctx->xa = NULL;
+}
+
+/*
+ * If base is g we compute the public key
+ *	ya = g^xa mod p; [RFC2631 sec 2.1.1]
+ * else if base if the counterpart public key we compute the shared secret
+ *	ZZ = yb^xa mod p; [RFC2631 sec 2.1.1]
+ */
+static int _compute_val(const struct dh_ctx *ctx, MPI base, MPI val)
+{
+	/* val = base^xa mod p */
+	return mpi_powm(val, base, ctx->xa, ctx->p);
+}
+
+static inline struct dh_ctx *dh_get_ctx(struct crypto_kpp *tfm)
+{
+	return kpp_tfm_ctx(tfm);
+}
+
+static int dh_check_params_length(unsigned int p_len)
+{
+	return (p_len < 1536) ? -EINVAL : 0;
+}
+
+static int dh_set_params(struct dh_ctx *ctx, struct dh *params)
+{
+	if (unlikely(!params->p || !params->g))
+		return -EINVAL;
+
+	if (dh_check_params_length(params->p_size << 3))
+		return -EINVAL;
+
+	ctx->p = mpi_read_raw_data(params->p, params->p_size);
+	if (!ctx->p)
+		return -EINVAL;
+
+	ctx->g = mpi_read_raw_data(params->g, params->g_size);
+	if (!ctx->g) {
+		mpi_free(ctx->p);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dh_set_secret(struct crypto_kpp *tfm, void *buf, unsigned int len)
+{
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+	struct dh params;
+
+	if (crypto_dh_decode_key(buf, len, &params) < 0)
+		return -EINVAL;
+
+	if (dh_set_params(ctx, &params) < 0)
+		return -EINVAL;
+
+	ctx->xa = mpi_read_raw_data(params.key, params.key_size);
+	if (!ctx->xa) {
+		dh_clear_params(ctx);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dh_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+	MPI base, val = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!val)
+		return -ENOMEM;
+
+	if (unlikely(!ctx->xa)) {
+		ret = -EINVAL;
+		goto err_free_val;
+	}
+
+	if (req->src) {
+		base = mpi_read_raw_from_sgl(req->src, req->src_len);
+		if (!base) {
+			ret = EINVAL;
+			goto err_free_val;
+		}
+	} else {
+		base = ctx->g;
+	}
+
+	ret = _compute_val(ctx, base, val);
+	if (ret)
+		goto err_free_base;
+
+	ret = mpi_write_to_sgl(val, req->dst, req->dst_len, &sign);
+	if (ret)
+		goto err_free_base;
+
+	if (sign < 0)
+		ret = -EBADMSG;
+err_free_base:
+	if (req->src)
+		mpi_free(base);
+err_free_val:
+	mpi_free(val);
+	return ret;
+}
+
+static int dh_max_size(struct crypto_kpp *tfm)
+{
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+
+	return mpi_get_size(ctx->p);
+}
+
+static void dh_exit_tfm(struct crypto_kpp *tfm)
+{
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+
+	dh_free_ctx(ctx);
+}
+
+static struct kpp_alg dh = {
+	.set_secret = dh_set_secret,
+	.generate_public_key = dh_compute_value,
+	.compute_shared_secret = dh_compute_value,
+	.max_size = dh_max_size,
+	.exit = dh_exit_tfm,
+	.base = {
+		.cra_name = "dh",
+		.cra_driver_name = "dh-generic",
+		.cra_priority = 100,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct dh_ctx),
+	},
+};
+
+static int dh_init(void)
+{
+	return crypto_register_kpp(&dh);
+}
+
+static void dh_exit(void)
+{
+	crypto_unregister_kpp(&dh);
+}
+
+module_init(dh_init);
+module_exit(dh_exit);
+MODULE_ALIAS_CRYPTO("dh");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("DH generic algorithm");
diff --git a/crypto/dh_helper.c b/crypto/dh_helper.c
new file mode 100644
index 000000000000..02db76b20d00
--- /dev/null
+++ b/crypto/dh_helper.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <crypto/dh.h>
+#include <crypto/kpp.h>
+
+#define DH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 3 * sizeof(int))
+
+static inline u8 *dh_pack_data(void *dst, const void *src, size_t size)
+{
+	memcpy(dst, src, size);
+	return dst + size;
+}
+
+static inline const u8 *dh_unpack_data(void *dst, const void *src, size_t size)
+{
+	memcpy(dst, src, size);
+	return src + size;
+}
+
+static inline int dh_data_size(const struct dh *p)
+{
+	return p->key_size + p->p_size + p->g_size;
+}
+
+int crypto_dh_key_len(const struct dh *p)
+{
+	return DH_KPP_SECRET_MIN_SIZE + dh_data_size(p);
+}
+EXPORT_SYMBOL_GPL(crypto_dh_key_len);
+
+int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params)
+{
+	u8 *ptr = buf;
+	struct kpp_secret secret = {
+		.type = CRYPTO_KPP_SECRET_TYPE_DH,
+		.len = len
+	};
+
+	if (unlikely(!buf))
+		return -EINVAL;
+
+	if (len != crypto_dh_key_len(params))
+		return -EINVAL;
+
+	ptr = dh_pack_data(ptr, &secret, sizeof(secret));
+	ptr = dh_pack_data(ptr, &params->key_size, sizeof(params->key_size));
+	ptr = dh_pack_data(ptr, &params->p_size, sizeof(params->p_size));
+	ptr = dh_pack_data(ptr, &params->g_size, sizeof(params->g_size));
+	ptr = dh_pack_data(ptr, params->key, params->key_size);
+	ptr = dh_pack_data(ptr, params->p, params->p_size);
+	dh_pack_data(ptr, params->g, params->g_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_dh_encode_key);
+
+int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params)
+{
+	const u8 *ptr = buf;
+	struct kpp_secret secret;
+
+	if (unlikely(!buf || len < DH_KPP_SECRET_MIN_SIZE))
+		return -EINVAL;
+
+	ptr = dh_unpack_data(&secret, ptr, sizeof(secret));
+	if (secret.type != CRYPTO_KPP_SECRET_TYPE_DH)
+		return -EINVAL;
+
+	ptr = dh_unpack_data(&params->key_size, ptr, sizeof(params->key_size));
+	ptr = dh_unpack_data(&params->p_size, ptr, sizeof(params->p_size));
+	ptr = dh_unpack_data(&params->g_size, ptr, sizeof(params->g_size));
+	if (secret.len != crypto_dh_key_len(params))
+		return -EINVAL;
+
+	/* Don't allocate memory. Set pointers to data within
+	 * the given buffer
+	 */
+	params->key = (void *)ptr;
+	params->p = (void *)(ptr + params->key_size);
+	params->g = (void *)(ptr + params->key_size + params->p_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_dh_decode_key);
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 0a3538f6cf22..f752da3a7c75 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -252,10 +252,16 @@ MODULE_ALIAS_CRYPTO("drbg_nopr_ctr_aes192");
 MODULE_ALIAS_CRYPTO("drbg_pr_ctr_aes128");
 MODULE_ALIAS_CRYPTO("drbg_nopr_ctr_aes128");
 
-static int drbg_kcapi_sym(struct drbg_state *drbg, const unsigned char *key,
-			  unsigned char *outval, const struct drbg_string *in);
+static void drbg_kcapi_symsetkey(struct drbg_state *drbg,
+				 const unsigned char *key);
+static int drbg_kcapi_sym(struct drbg_state *drbg, unsigned char *outval,
+			  const struct drbg_string *in);
 static int drbg_init_sym_kernel(struct drbg_state *drbg);
 static int drbg_fini_sym_kernel(struct drbg_state *drbg);
+static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
+			      u8 *inbuf, u32 inbuflen,
+			      u8 *outbuf, u32 outlen);
+#define DRBG_CTR_NULL_LEN 128
 
 /* BCC function for CTR DRBG as defined in 10.4.3 */
 static int drbg_ctr_bcc(struct drbg_state *drbg,
@@ -270,6 +276,7 @@ static int drbg_ctr_bcc(struct drbg_state *drbg,
 	drbg_string_fill(&data, out, drbg_blocklen(drbg));
 
 	/* 10.4.3 step 2 / 4 */
+	drbg_kcapi_symsetkey(drbg, key);
 	list_for_each_entry(curr, in, list) {
 		const unsigned char *pos = curr->buf;
 		size_t len = curr->len;
@@ -278,7 +285,7 @@ static int drbg_ctr_bcc(struct drbg_state *drbg,
 			/* 10.4.3 step 4.2 */
 			if (drbg_blocklen(drbg) == cnt) {
 				cnt = 0;
-				ret = drbg_kcapi_sym(drbg, key, out, &data);
+				ret = drbg_kcapi_sym(drbg, out, &data);
 				if (ret)
 					return ret;
 			}
@@ -290,7 +297,7 @@ static int drbg_ctr_bcc(struct drbg_state *drbg,
 	}
 	/* 10.4.3 step 4.2 for last block */
 	if (cnt)
-		ret = drbg_kcapi_sym(drbg, key, out, &data);
+		ret = drbg_kcapi_sym(drbg, out, &data);
 
 	return ret;
 }
@@ -425,6 +432,7 @@ static int drbg_ctr_df(struct drbg_state *drbg,
 	/* 10.4.2 step 12: overwriting of outval is implemented in next step */
 
 	/* 10.4.2 step 13 */
+	drbg_kcapi_symsetkey(drbg, temp);
 	while (generated_len < bytes_to_return) {
 		short blocklen = 0;
 		/*
@@ -432,7 +440,7 @@ static int drbg_ctr_df(struct drbg_state *drbg,
 		 * implicit as the key is only drbg_blocklen in size based on
 		 * the implementation of the cipher function callback
 		 */
-		ret = drbg_kcapi_sym(drbg, temp, X, &cipherin);
+		ret = drbg_kcapi_sym(drbg, X, &cipherin);
 		if (ret)
 			goto out;
 		blocklen = (drbg_blocklen(drbg) <
@@ -476,49 +484,47 @@ static int drbg_ctr_update(struct drbg_state *drbg, struct list_head *seed,
 	unsigned char *temp = drbg->scratchpad;
 	unsigned char *df_data = drbg->scratchpad + drbg_statelen(drbg) +
 				 drbg_blocklen(drbg);
-	unsigned char *temp_p, *df_data_p; /* pointer to iterate over buffers */
-	unsigned int len = 0;
-	struct drbg_string cipherin;
 
 	if (3 > reseed)
 		memset(df_data, 0, drbg_statelen(drbg));
 
-	/* 10.2.1.3.2 step 2 and 10.2.1.4.2 step 2 */
-	if (seed) {
-		ret = drbg_ctr_df(drbg, df_data, drbg_statelen(drbg), seed);
+	if (!reseed) {
+		/*
+		 * The DRBG uses the CTR mode of the underlying AES cipher. The
+		 * CTR mode increments the counter value after the AES operation
+		 * but SP800-90A requires that the counter is incremented before
+		 * the AES operation. Hence, we increment it at the time we set
+		 * it by one.
+		 */
+		crypto_inc(drbg->V, drbg_blocklen(drbg));
+
+		ret = crypto_skcipher_setkey(drbg->ctr_handle, drbg->C,
+					     drbg_keylen(drbg));
 		if (ret)
 			goto out;
 	}
 
-	drbg_string_fill(&cipherin, drbg->V, drbg_blocklen(drbg));
-	/*
-	 * 10.2.1.3.2 steps 2 and 3 are already covered as the allocation
-	 * zeroizes all memory during initialization
-	 */
-	while (len < (drbg_statelen(drbg))) {
-		/* 10.2.1.2 step 2.1 */
-		crypto_inc(drbg->V, drbg_blocklen(drbg));
-		/*
-		 * 10.2.1.2 step 2.2 */
-		ret = drbg_kcapi_sym(drbg, drbg->C, temp + len, &cipherin);
+	/* 10.2.1.3.2 step 2 and 10.2.1.4.2 step 2 */
+	if (seed) {
+		ret = drbg_ctr_df(drbg, df_data, drbg_statelen(drbg), seed);
 		if (ret)
 			goto out;
-		/* 10.2.1.2 step 2.3 and 3 */
-		len += drbg_blocklen(drbg);
 	}
 
-	/* 10.2.1.2 step 4 */
-	temp_p = temp;
-	df_data_p = df_data;
-	for (len = 0; len < drbg_statelen(drbg); len++) {
-		*temp_p ^= *df_data_p;
-		df_data_p++; temp_p++;
-	}
+	ret = drbg_kcapi_sym_ctr(drbg, df_data, drbg_statelen(drbg),
+				 temp, drbg_statelen(drbg));
+	if (ret)
+		return ret;
 
 	/* 10.2.1.2 step 5 */
-	memcpy(drbg->C, temp, drbg_keylen(drbg));
+	ret = crypto_skcipher_setkey(drbg->ctr_handle, temp,
+				     drbg_keylen(drbg));
+	if (ret)
+		goto out;
 	/* 10.2.1.2 step 6 */
 	memcpy(drbg->V, temp + drbg_keylen(drbg), drbg_blocklen(drbg));
+	/* See above: increment counter by one to compensate timing of CTR op */
+	crypto_inc(drbg->V, drbg_blocklen(drbg));
 	ret = 0;
 
 out:
@@ -537,9 +543,8 @@ static int drbg_ctr_generate(struct drbg_state *drbg,
 			     unsigned char *buf, unsigned int buflen,
 			     struct list_head *addtl)
 {
-	int len = 0;
-	int ret = 0;
-	struct drbg_string data;
+	int ret;
+	int len = min_t(int, buflen, INT_MAX);
 
 	/* 10.2.1.5.2 step 2 */
 	if (addtl && !list_empty(addtl)) {
@@ -549,33 +554,16 @@ static int drbg_ctr_generate(struct drbg_state *drbg,
 	}
 
 	/* 10.2.1.5.2 step 4.1 */
-	crypto_inc(drbg->V, drbg_blocklen(drbg));
-	drbg_string_fill(&data, drbg->V, drbg_blocklen(drbg));
-	while (len < buflen) {
-		int outlen = 0;
-		/* 10.2.1.5.2 step 4.2 */
-		ret = drbg_kcapi_sym(drbg, drbg->C, drbg->scratchpad, &data);
-		if (ret) {
-			len = ret;
-			goto out;
-		}
-		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
-			  drbg_blocklen(drbg) : (buflen - len);
-		/* 10.2.1.5.2 step 4.3 */
-		memcpy(buf + len, drbg->scratchpad, outlen);
-		len += outlen;
-		/* 10.2.1.5.2 step 6 */
-		if (len < buflen)
-			crypto_inc(drbg->V, drbg_blocklen(drbg));
-	}
+	ret = drbg_kcapi_sym_ctr(drbg, drbg->ctr_null_value, DRBG_CTR_NULL_LEN,
+				 buf, len);
+	if (ret)
+		return ret;
 
 	/* 10.2.1.5.2 step 6 */
 	ret = drbg_ctr_update(drbg, NULL, 3);
 	if (ret)
 		len = ret;
 
-out:
-	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
 	return len;
 }
 
@@ -1145,11 +1133,11 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg)
 	if (!drbg)
 		return;
 	kzfree(drbg->V);
-	drbg->V = NULL;
+	drbg->Vbuf = NULL;
 	kzfree(drbg->C);
-	drbg->C = NULL;
-	kzfree(drbg->scratchpad);
-	drbg->scratchpad = NULL;
+	drbg->Cbuf = NULL;
+	kzfree(drbg->scratchpadbuf);
+	drbg->scratchpadbuf = NULL;
 	drbg->reseed_ctr = 0;
 	drbg->d_ops = NULL;
 	drbg->core = NULL;
@@ -1185,12 +1173,18 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 		goto err;
 	}
 
-	drbg->V = kmalloc(drbg_statelen(drbg), GFP_KERNEL);
-	if (!drbg->V)
-		goto err;
-	drbg->C = kmalloc(drbg_statelen(drbg), GFP_KERNEL);
-	if (!drbg->C)
+	ret = drbg->d_ops->crypto_init(drbg);
+	if (ret < 0)
 		goto err;
+
+	drbg->Vbuf = kmalloc(drbg_statelen(drbg) + ret, GFP_KERNEL);
+	if (!drbg->Vbuf)
+		goto fini;
+	drbg->V = PTR_ALIGN(drbg->Vbuf, ret + 1);
+	drbg->Cbuf = kmalloc(drbg_statelen(drbg) + ret, GFP_KERNEL);
+	if (!drbg->Cbuf)
+		goto fini;
+	drbg->C = PTR_ALIGN(drbg->Cbuf, ret + 1);
 	/* scratchpad is only generated for CTR and Hash */
 	if (drbg->core->flags & DRBG_HMAC)
 		sb_size = 0;
@@ -1204,13 +1198,16 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 		sb_size = drbg_statelen(drbg) + drbg_blocklen(drbg);
 
 	if (0 < sb_size) {
-		drbg->scratchpad = kzalloc(sb_size, GFP_KERNEL);
-		if (!drbg->scratchpad)
-			goto err;
+		drbg->scratchpadbuf = kzalloc(sb_size + ret, GFP_KERNEL);
+		if (!drbg->scratchpadbuf)
+			goto fini;
+		drbg->scratchpad = PTR_ALIGN(drbg->scratchpadbuf, ret + 1);
 	}
 
 	return 0;
 
+fini:
+	drbg->d_ops->crypto_fini(drbg);
 err:
 	drbg_dealloc_state(drbg);
 	return ret;
@@ -1478,10 +1475,6 @@ static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers,
 		if (ret)
 			goto unlock;
 
-		ret = -EFAULT;
-		if (drbg->d_ops->crypto_init(drbg))
-			goto err;
-
 		ret = drbg_prepare_hrng(drbg);
 		if (ret)
 			goto free_everything;
@@ -1505,8 +1498,6 @@ static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers,
 	mutex_unlock(&drbg->drbg_mutex);
 	return ret;
 
-err:
-	drbg_dealloc_state(drbg);
 unlock:
 	mutex_unlock(&drbg->drbg_mutex);
 	return ret;
@@ -1591,7 +1582,8 @@ static int drbg_init_hash_kernel(struct drbg_state *drbg)
 	sdesc->shash.tfm = tfm;
 	sdesc->shash.flags = 0;
 	drbg->priv_data = sdesc;
-	return 0;
+
+	return crypto_shash_alignmask(tfm);
 }
 
 static int drbg_fini_hash_kernel(struct drbg_state *drbg)
@@ -1627,10 +1619,45 @@ static int drbg_kcapi_hash(struct drbg_state *drbg, unsigned char *outval,
 #endif /* (CONFIG_CRYPTO_DRBG_HASH || CONFIG_CRYPTO_DRBG_HMAC) */
 
 #ifdef CONFIG_CRYPTO_DRBG_CTR
+static int drbg_fini_sym_kernel(struct drbg_state *drbg)
+{
+	struct crypto_cipher *tfm =
+		(struct crypto_cipher *)drbg->priv_data;
+	if (tfm)
+		crypto_free_cipher(tfm);
+	drbg->priv_data = NULL;
+
+	if (drbg->ctr_handle)
+		crypto_free_skcipher(drbg->ctr_handle);
+	drbg->ctr_handle = NULL;
+
+	if (drbg->ctr_req)
+		skcipher_request_free(drbg->ctr_req);
+	drbg->ctr_req = NULL;
+
+	kfree(drbg->ctr_null_value_buf);
+	drbg->ctr_null_value = NULL;
+
+	return 0;
+}
+
+static void drbg_skcipher_cb(struct crypto_async_request *req, int error)
+{
+	struct drbg_state *drbg = req->data;
+
+	if (error == -EINPROGRESS)
+		return;
+	drbg->ctr_async_err = error;
+	complete(&drbg->ctr_completion);
+}
+
 static int drbg_init_sym_kernel(struct drbg_state *drbg)
 {
-	int ret = 0;
 	struct crypto_cipher *tfm;
+	struct crypto_skcipher *sk_tfm;
+	struct skcipher_request *req;
+	unsigned int alignmask;
+	char ctr_name[CRYPTO_MAX_ALG_NAME];
 
 	tfm = crypto_alloc_cipher(drbg->core->backend_cra_name, 0, 0);
 	if (IS_ERR(tfm)) {
@@ -1640,31 +1667,103 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg)
 	}
 	BUG_ON(drbg_blocklen(drbg) != crypto_cipher_blocksize(tfm));
 	drbg->priv_data = tfm;
-	return ret;
+
+	if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)",
+	    drbg->core->backend_cra_name) >= CRYPTO_MAX_ALG_NAME) {
+		drbg_fini_sym_kernel(drbg);
+		return -EINVAL;
+	}
+	sk_tfm = crypto_alloc_skcipher(ctr_name, 0, 0);
+	if (IS_ERR(sk_tfm)) {
+		pr_info("DRBG: could not allocate CTR cipher TFM handle: %s\n",
+				ctr_name);
+		drbg_fini_sym_kernel(drbg);
+		return PTR_ERR(sk_tfm);
+	}
+	drbg->ctr_handle = sk_tfm;
+
+	req = skcipher_request_alloc(sk_tfm, GFP_KERNEL);
+	if (!req) {
+		pr_info("DRBG: could not allocate request queue\n");
+		drbg_fini_sym_kernel(drbg);
+		return -ENOMEM;
+	}
+	drbg->ctr_req = req;
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					drbg_skcipher_cb, drbg);
+
+	alignmask = crypto_skcipher_alignmask(sk_tfm);
+	drbg->ctr_null_value_buf = kzalloc(DRBG_CTR_NULL_LEN + alignmask,
+					   GFP_KERNEL);
+	if (!drbg->ctr_null_value_buf) {
+		drbg_fini_sym_kernel(drbg);
+		return -ENOMEM;
+	}
+	drbg->ctr_null_value = (u8 *)PTR_ALIGN(drbg->ctr_null_value_buf,
+					       alignmask + 1);
+
+	return alignmask;
 }
 
-static int drbg_fini_sym_kernel(struct drbg_state *drbg)
+static void drbg_kcapi_symsetkey(struct drbg_state *drbg,
+				 const unsigned char *key)
 {
 	struct crypto_cipher *tfm =
 		(struct crypto_cipher *)drbg->priv_data;
-	if (tfm)
-		crypto_free_cipher(tfm);
-	drbg->priv_data = NULL;
-	return 0;
+
+	crypto_cipher_setkey(tfm, key, (drbg_keylen(drbg)));
 }
 
-static int drbg_kcapi_sym(struct drbg_state *drbg, const unsigned char *key,
-			  unsigned char *outval, const struct drbg_string *in)
+static int drbg_kcapi_sym(struct drbg_state *drbg, unsigned char *outval,
+			  const struct drbg_string *in)
 {
 	struct crypto_cipher *tfm =
 		(struct crypto_cipher *)drbg->priv_data;
 
-	crypto_cipher_setkey(tfm, key, (drbg_keylen(drbg)));
 	/* there is only component in *in */
 	BUG_ON(in->len < drbg_blocklen(drbg));
 	crypto_cipher_encrypt_one(tfm, outval, in->buf);
 	return 0;
 }
+
+static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
+			      u8 *inbuf, u32 inlen,
+			      u8 *outbuf, u32 outlen)
+{
+	struct scatterlist sg_in;
+
+	sg_init_one(&sg_in, inbuf, inlen);
+
+	while (outlen) {
+		u32 cryptlen = min_t(u32, inlen, outlen);
+		struct scatterlist sg_out;
+		int ret;
+
+		sg_init_one(&sg_out, outbuf, cryptlen);
+		skcipher_request_set_crypt(drbg->ctr_req, &sg_in, &sg_out,
+					   cryptlen, drbg->V);
+		ret = crypto_skcipher_encrypt(drbg->ctr_req);
+		switch (ret) {
+		case 0:
+			break;
+		case -EINPROGRESS:
+		case -EBUSY:
+			ret = wait_for_completion_interruptible(
+				&drbg->ctr_completion);
+			if (!ret && !drbg->ctr_async_err) {
+				reinit_completion(&drbg->ctr_completion);
+				break;
+			}
+		default:
+			return ret;
+		}
+		init_completion(&drbg->ctr_completion);
+
+		outlen -= cryptlen;
+	}
+
+	return 0;
+}
 #endif /* CONFIG_CRYPTO_DRBG_CTR */
 
 /***************************************************************
diff --git a/crypto/ecc.c b/crypto/ecc.c
new file mode 100644
index 000000000000..414c78a9c214
--- /dev/null
+++ b/crypto/ecc.c
@@ -0,0 +1,1018 @@
+/*
+ * Copyright (c) 2013, Kenneth MacKay
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *  * Redistributions of source code must retain the above copyright
+ *   notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/swab.h>
+#include <linux/fips.h>
+#include <crypto/ecdh.h>
+
+#include "ecc.h"
+#include "ecc_curve_defs.h"
+
+typedef struct {
+	u64 m_low;
+	u64 m_high;
+} uint128_t;
+
+static inline const struct ecc_curve *ecc_get_curve(unsigned int curve_id)
+{
+	switch (curve_id) {
+	/* In FIPS mode only allow P256 and higher */
+	case ECC_CURVE_NIST_P192:
+		return fips_enabled ? NULL : &nist_p192;
+	case ECC_CURVE_NIST_P256:
+		return &nist_p256;
+	default:
+		return NULL;
+	}
+}
+
+static u64 *ecc_alloc_digits_space(unsigned int ndigits)
+{
+	size_t len = ndigits * sizeof(u64);
+
+	if (!len)
+		return NULL;
+
+	return kmalloc(len, GFP_KERNEL);
+}
+
+static void ecc_free_digits_space(u64 *space)
+{
+	kzfree(space);
+}
+
+static struct ecc_point *ecc_alloc_point(unsigned int ndigits)
+{
+	struct ecc_point *p = kmalloc(sizeof(*p), GFP_KERNEL);
+
+	if (!p)
+		return NULL;
+
+	p->x = ecc_alloc_digits_space(ndigits);
+	if (!p->x)
+		goto err_alloc_x;
+
+	p->y = ecc_alloc_digits_space(ndigits);
+	if (!p->y)
+		goto err_alloc_y;
+
+	p->ndigits = ndigits;
+
+	return p;
+
+err_alloc_y:
+	ecc_free_digits_space(p->x);
+err_alloc_x:
+	kfree(p);
+	return NULL;
+}
+
+static void ecc_free_point(struct ecc_point *p)
+{
+	if (!p)
+		return;
+
+	kzfree(p->x);
+	kzfree(p->y);
+	kzfree(p);
+}
+
+static void vli_clear(u64 *vli, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		vli[i] = 0;
+}
+
+/* Returns true if vli == 0, false otherwise. */
+static bool vli_is_zero(const u64 *vli, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		if (vli[i])
+			return false;
+	}
+
+	return true;
+}
+
+/* Returns nonzero if bit bit of vli is set. */
+static u64 vli_test_bit(const u64 *vli, unsigned int bit)
+{
+	return (vli[bit / 64] & ((u64)1 << (bit % 64)));
+}
+
+/* Counts the number of 64-bit "digits" in vli. */
+static unsigned int vli_num_digits(const u64 *vli, unsigned int ndigits)
+{
+	int i;
+
+	/* Search from the end until we find a non-zero digit.
+	 * We do it in reverse because we expect that most digits will
+	 * be nonzero.
+	 */
+	for (i = ndigits - 1; i >= 0 && vli[i] == 0; i--);
+
+	return (i + 1);
+}
+
+/* Counts the number of bits required for vli. */
+static unsigned int vli_num_bits(const u64 *vli, unsigned int ndigits)
+{
+	unsigned int i, num_digits;
+	u64 digit;
+
+	num_digits = vli_num_digits(vli, ndigits);
+	if (num_digits == 0)
+		return 0;
+
+	digit = vli[num_digits - 1];
+	for (i = 0; digit; i++)
+		digit >>= 1;
+
+	return ((num_digits - 1) * 64 + i);
+}
+
+/* Sets dest = src. */
+static void vli_set(u64 *dest, const u64 *src, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		dest[i] = src[i];
+}
+
+/* Returns sign of left - right. */
+static int vli_cmp(const u64 *left, const u64 *right, unsigned int ndigits)
+{
+	int i;
+
+	for (i = ndigits - 1; i >= 0; i--) {
+		if (left[i] > right[i])
+			return 1;
+		else if (left[i] < right[i])
+			return -1;
+	}
+
+	return 0;
+}
+
+/* Computes result = in << c, returning carry. Can modify in place
+ * (if result == in). 0 < shift < 64.
+ */
+static u64 vli_lshift(u64 *result, const u64 *in, unsigned int shift,
+		      unsigned int ndigits)
+{
+	u64 carry = 0;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 temp = in[i];
+
+		result[i] = (temp << shift) | carry;
+		carry = temp >> (64 - shift);
+	}
+
+	return carry;
+}
+
+/* Computes vli = vli >> 1. */
+static void vli_rshift1(u64 *vli, unsigned int ndigits)
+{
+	u64 *end = vli;
+	u64 carry = 0;
+
+	vli += ndigits;
+
+	while (vli-- > end) {
+		u64 temp = *vli;
+		*vli = (temp >> 1) | carry;
+		carry = temp << 63;
+	}
+}
+
+/* Computes result = left + right, returning carry. Can modify in place. */
+static u64 vli_add(u64 *result, const u64 *left, const u64 *right,
+		   unsigned int ndigits)
+{
+	u64 carry = 0;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 sum;
+
+		sum = left[i] + right[i] + carry;
+		if (sum != left[i])
+			carry = (sum < left[i]);
+
+		result[i] = sum;
+	}
+
+	return carry;
+}
+
+/* Computes result = left - right, returning borrow. Can modify in place. */
+static u64 vli_sub(u64 *result, const u64 *left, const u64 *right,
+		   unsigned int ndigits)
+{
+	u64 borrow = 0;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 diff;
+
+		diff = left[i] - right[i] - borrow;
+		if (diff != left[i])
+			borrow = (diff > left[i]);
+
+		result[i] = diff;
+	}
+
+	return borrow;
+}
+
+static uint128_t mul_64_64(u64 left, u64 right)
+{
+	u64 a0 = left & 0xffffffffull;
+	u64 a1 = left >> 32;
+	u64 b0 = right & 0xffffffffull;
+	u64 b1 = right >> 32;
+	u64 m0 = a0 * b0;
+	u64 m1 = a0 * b1;
+	u64 m2 = a1 * b0;
+	u64 m3 = a1 * b1;
+	uint128_t result;
+
+	m2 += (m0 >> 32);
+	m2 += m1;
+
+	/* Overflow */
+	if (m2 < m1)
+		m3 += 0x100000000ull;
+
+	result.m_low = (m0 & 0xffffffffull) | (m2 << 32);
+	result.m_high = m3 + (m2 >> 32);
+
+	return result;
+}
+
+static uint128_t add_128_128(uint128_t a, uint128_t b)
+{
+	uint128_t result;
+
+	result.m_low = a.m_low + b.m_low;
+	result.m_high = a.m_high + b.m_high + (result.m_low < a.m_low);
+
+	return result;
+}
+
+static void vli_mult(u64 *result, const u64 *left, const u64 *right,
+		     unsigned int ndigits)
+{
+	uint128_t r01 = { 0, 0 };
+	u64 r2 = 0;
+	unsigned int i, k;
+
+	/* Compute each digit of result in sequence, maintaining the
+	 * carries.
+	 */
+	for (k = 0; k < ndigits * 2 - 1; k++) {
+		unsigned int min;
+
+		if (k < ndigits)
+			min = 0;
+		else
+			min = (k + 1) - ndigits;
+
+		for (i = min; i <= k && i < ndigits; i++) {
+			uint128_t product;
+
+			product = mul_64_64(left[i], right[k - i]);
+
+			r01 = add_128_128(r01, product);
+			r2 += (r01.m_high < product.m_high);
+		}
+
+		result[k] = r01.m_low;
+		r01.m_low = r01.m_high;
+		r01.m_high = r2;
+		r2 = 0;
+	}
+
+	result[ndigits * 2 - 1] = r01.m_low;
+}
+
+static void vli_square(u64 *result, const u64 *left, unsigned int ndigits)
+{
+	uint128_t r01 = { 0, 0 };
+	u64 r2 = 0;
+	int i, k;
+
+	for (k = 0; k < ndigits * 2 - 1; k++) {
+		unsigned int min;
+
+		if (k < ndigits)
+			min = 0;
+		else
+			min = (k + 1) - ndigits;
+
+		for (i = min; i <= k && i <= k - i; i++) {
+			uint128_t product;
+
+			product = mul_64_64(left[i], left[k - i]);
+
+			if (i < k - i) {
+				r2 += product.m_high >> 63;
+				product.m_high = (product.m_high << 1) |
+						 (product.m_low >> 63);
+				product.m_low <<= 1;
+			}
+
+			r01 = add_128_128(r01, product);
+			r2 += (r01.m_high < product.m_high);
+		}
+
+		result[k] = r01.m_low;
+		r01.m_low = r01.m_high;
+		r01.m_high = r2;
+		r2 = 0;
+	}
+
+	result[ndigits * 2 - 1] = r01.m_low;
+}
+
+/* Computes result = (left + right) % mod.
+ * Assumes that left < mod and right < mod, result != mod.
+ */
+static void vli_mod_add(u64 *result, const u64 *left, const u64 *right,
+			const u64 *mod, unsigned int ndigits)
+{
+	u64 carry;
+
+	carry = vli_add(result, left, right, ndigits);
+
+	/* result > mod (result = mod + remainder), so subtract mod to
+	 * get remainder.
+	 */
+	if (carry || vli_cmp(result, mod, ndigits) >= 0)
+		vli_sub(result, result, mod, ndigits);
+}
+
+/* Computes result = (left - right) % mod.
+ * Assumes that left < mod and right < mod, result != mod.
+ */
+static void vli_mod_sub(u64 *result, const u64 *left, const u64 *right,
+			const u64 *mod, unsigned int ndigits)
+{
+	u64 borrow = vli_sub(result, left, right, ndigits);
+
+	/* In this case, p_result == -diff == (max int) - diff.
+	 * Since -x % d == d - x, we can get the correct result from
+	 * result + mod (with overflow).
+	 */
+	if (borrow)
+		vli_add(result, result, mod, ndigits);
+}
+
+/* Computes p_result = p_product % curve_p.
+ * See algorithm 5 and 6 from
+ * http://www.isys.uni-klu.ac.at/PDF/2001-0126-MT.pdf
+ */
+static void vli_mmod_fast_192(u64 *result, const u64 *product,
+			      const u64 *curve_prime, u64 *tmp)
+{
+	const unsigned int ndigits = 3;
+	int carry;
+
+	vli_set(result, product, ndigits);
+
+	vli_set(tmp, &product[3], ndigits);
+	carry = vli_add(result, result, tmp, ndigits);
+
+	tmp[0] = 0;
+	tmp[1] = product[3];
+	tmp[2] = product[4];
+	carry += vli_add(result, result, tmp, ndigits);
+
+	tmp[0] = tmp[1] = product[5];
+	tmp[2] = 0;
+	carry += vli_add(result, result, tmp, ndigits);
+
+	while (carry || vli_cmp(curve_prime, result, ndigits) != 1)
+		carry -= vli_sub(result, result, curve_prime, ndigits);
+}
+
+/* Computes result = product % curve_prime
+ * from http://www.nsa.gov/ia/_files/nist-routines.pdf
+ */
+static void vli_mmod_fast_256(u64 *result, const u64 *product,
+			      const u64 *curve_prime, u64 *tmp)
+{
+	int carry;
+	const unsigned int ndigits = 4;
+
+	/* t */
+	vli_set(result, product, ndigits);
+
+	/* s1 */
+	tmp[0] = 0;
+	tmp[1] = product[5] & 0xffffffff00000000ull;
+	tmp[2] = product[6];
+	tmp[3] = product[7];
+	carry = vli_lshift(tmp, tmp, 1, ndigits);
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s2 */
+	tmp[1] = product[6] << 32;
+	tmp[2] = (product[6] >> 32) | (product[7] << 32);
+	tmp[3] = product[7] >> 32;
+	carry += vli_lshift(tmp, tmp, 1, ndigits);
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s3 */
+	tmp[0] = product[4];
+	tmp[1] = product[5] & 0xffffffff;
+	tmp[2] = 0;
+	tmp[3] = product[7];
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s4 */
+	tmp[0] = (product[4] >> 32) | (product[5] << 32);
+	tmp[1] = (product[5] >> 32) | (product[6] & 0xffffffff00000000ull);
+	tmp[2] = product[7];
+	tmp[3] = (product[6] >> 32) | (product[4] << 32);
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* d1 */
+	tmp[0] = (product[5] >> 32) | (product[6] << 32);
+	tmp[1] = (product[6] >> 32);
+	tmp[2] = 0;
+	tmp[3] = (product[4] & 0xffffffff) | (product[5] << 32);
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d2 */
+	tmp[0] = product[6];
+	tmp[1] = product[7];
+	tmp[2] = 0;
+	tmp[3] = (product[4] >> 32) | (product[5] & 0xffffffff00000000ull);
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d3 */
+	tmp[0] = (product[6] >> 32) | (product[7] << 32);
+	tmp[1] = (product[7] >> 32) | (product[4] << 32);
+	tmp[2] = (product[4] >> 32) | (product[5] << 32);
+	tmp[3] = (product[6] << 32);
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d4 */
+	tmp[0] = product[7];
+	tmp[1] = product[4] & 0xffffffff00000000ull;
+	tmp[2] = product[5];
+	tmp[3] = product[6] & 0xffffffff00000000ull;
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	if (carry < 0) {
+		do {
+			carry += vli_add(result, result, curve_prime, ndigits);
+		} while (carry < 0);
+	} else {
+		while (carry || vli_cmp(curve_prime, result, ndigits) != 1)
+			carry -= vli_sub(result, result, curve_prime, ndigits);
+	}
+}
+
+/* Computes result = product % curve_prime
+ *  from http://www.nsa.gov/ia/_files/nist-routines.pdf
+*/
+static bool vli_mmod_fast(u64 *result, u64 *product,
+			  const u64 *curve_prime, unsigned int ndigits)
+{
+	u64 tmp[2 * ndigits];
+
+	switch (ndigits) {
+	case 3:
+		vli_mmod_fast_192(result, product, curve_prime, tmp);
+		break;
+	case 4:
+		vli_mmod_fast_256(result, product, curve_prime, tmp);
+		break;
+	default:
+		pr_err("unsupports digits size!\n");
+		return false;
+	}
+
+	return true;
+}
+
+/* Computes result = (left * right) % curve_prime. */
+static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right,
+			      const u64 *curve_prime, unsigned int ndigits)
+{
+	u64 product[2 * ndigits];
+
+	vli_mult(product, left, right, ndigits);
+	vli_mmod_fast(result, product, curve_prime, ndigits);
+}
+
+/* Computes result = left^2 % curve_prime. */
+static void vli_mod_square_fast(u64 *result, const u64 *left,
+				const u64 *curve_prime, unsigned int ndigits)
+{
+	u64 product[2 * ndigits];
+
+	vli_square(product, left, ndigits);
+	vli_mmod_fast(result, product, curve_prime, ndigits);
+}
+
+#define EVEN(vli) (!(vli[0] & 1))
+/* Computes result = (1 / p_input) % mod. All VLIs are the same size.
+ * See "From Euclid's GCD to Montgomery Multiplication to the Great Divide"
+ * https://labs.oracle.com/techrep/2001/smli_tr-2001-95.pdf
+ */
+static void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod,
+			unsigned int ndigits)
+{
+	u64 a[ndigits], b[ndigits];
+	u64 u[ndigits], v[ndigits];
+	u64 carry;
+	int cmp_result;
+
+	if (vli_is_zero(input, ndigits)) {
+		vli_clear(result, ndigits);
+		return;
+	}
+
+	vli_set(a, input, ndigits);
+	vli_set(b, mod, ndigits);
+	vli_clear(u, ndigits);
+	u[0] = 1;
+	vli_clear(v, ndigits);
+
+	while ((cmp_result = vli_cmp(a, b, ndigits)) != 0) {
+		carry = 0;
+
+		if (EVEN(a)) {
+			vli_rshift1(a, ndigits);
+
+			if (!EVEN(u))
+				carry = vli_add(u, u, mod, ndigits);
+
+			vli_rshift1(u, ndigits);
+			if (carry)
+				u[ndigits - 1] |= 0x8000000000000000ull;
+		} else if (EVEN(b)) {
+			vli_rshift1(b, ndigits);
+
+			if (!EVEN(v))
+				carry = vli_add(v, v, mod, ndigits);
+
+			vli_rshift1(v, ndigits);
+			if (carry)
+				v[ndigits - 1] |= 0x8000000000000000ull;
+		} else if (cmp_result > 0) {
+			vli_sub(a, a, b, ndigits);
+			vli_rshift1(a, ndigits);
+
+			if (vli_cmp(u, v, ndigits) < 0)
+				vli_add(u, u, mod, ndigits);
+
+			vli_sub(u, u, v, ndigits);
+			if (!EVEN(u))
+				carry = vli_add(u, u, mod, ndigits);
+
+			vli_rshift1(u, ndigits);
+			if (carry)
+				u[ndigits - 1] |= 0x8000000000000000ull;
+		} else {
+			vli_sub(b, b, a, ndigits);
+			vli_rshift1(b, ndigits);
+
+			if (vli_cmp(v, u, ndigits) < 0)
+				vli_add(v, v, mod, ndigits);
+
+			vli_sub(v, v, u, ndigits);
+			if (!EVEN(v))
+				carry = vli_add(v, v, mod, ndigits);
+
+			vli_rshift1(v, ndigits);
+			if (carry)
+				v[ndigits - 1] |= 0x8000000000000000ull;
+		}
+	}
+
+	vli_set(result, u, ndigits);
+}
+
+/* ------ Point operations ------ */
+
+/* Returns true if p_point is the point at infinity, false otherwise. */
+static bool ecc_point_is_zero(const struct ecc_point *point)
+{
+	return (vli_is_zero(point->x, point->ndigits) &&
+		vli_is_zero(point->y, point->ndigits));
+}
+
+/* Point multiplication algorithm using Montgomery's ladder with co-Z
+ * coordinates. From http://eprint.iacr.org/2011/338.pdf
+ */
+
+/* Double in place */
+static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
+				      u64 *curve_prime, unsigned int ndigits)
+{
+	/* t1 = x, t2 = y, t3 = z */
+	u64 t4[ndigits];
+	u64 t5[ndigits];
+
+	if (vli_is_zero(z1, ndigits))
+		return;
+
+	/* t4 = y1^2 */
+	vli_mod_square_fast(t4, y1, curve_prime, ndigits);
+	/* t5 = x1*y1^2 = A */
+	vli_mod_mult_fast(t5, x1, t4, curve_prime, ndigits);
+	/* t4 = y1^4 */
+	vli_mod_square_fast(t4, t4, curve_prime, ndigits);
+	/* t2 = y1*z1 = z3 */
+	vli_mod_mult_fast(y1, y1, z1, curve_prime, ndigits);
+	/* t3 = z1^2 */
+	vli_mod_square_fast(z1, z1, curve_prime, ndigits);
+
+	/* t1 = x1 + z1^2 */
+	vli_mod_add(x1, x1, z1, curve_prime, ndigits);
+	/* t3 = 2*z1^2 */
+	vli_mod_add(z1, z1, z1, curve_prime, ndigits);
+	/* t3 = x1 - z1^2 */
+	vli_mod_sub(z1, x1, z1, curve_prime, ndigits);
+	/* t1 = x1^2 - z1^4 */
+	vli_mod_mult_fast(x1, x1, z1, curve_prime, ndigits);
+
+	/* t3 = 2*(x1^2 - z1^4) */
+	vli_mod_add(z1, x1, x1, curve_prime, ndigits);
+	/* t1 = 3*(x1^2 - z1^4) */
+	vli_mod_add(x1, x1, z1, curve_prime, ndigits);
+	if (vli_test_bit(x1, 0)) {
+		u64 carry = vli_add(x1, x1, curve_prime, ndigits);
+
+		vli_rshift1(x1, ndigits);
+		x1[ndigits - 1] |= carry << 63;
+	} else {
+		vli_rshift1(x1, ndigits);
+	}
+	/* t1 = 3/2*(x1^2 - z1^4) = B */
+
+	/* t3 = B^2 */
+	vli_mod_square_fast(z1, x1, curve_prime, ndigits);
+	/* t3 = B^2 - A */
+	vli_mod_sub(z1, z1, t5, curve_prime, ndigits);
+	/* t3 = B^2 - 2A = x3 */
+	vli_mod_sub(z1, z1, t5, curve_prime, ndigits);
+	/* t5 = A - x3 */
+	vli_mod_sub(t5, t5, z1, curve_prime, ndigits);
+	/* t1 = B * (A - x3) */
+	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	/* t4 = B * (A - x3) - y1^4 = y3 */
+	vli_mod_sub(t4, x1, t4, curve_prime, ndigits);
+
+	vli_set(x1, z1, ndigits);
+	vli_set(z1, y1, ndigits);
+	vli_set(y1, t4, ndigits);
+}
+
+/* Modify (x1, y1) => (x1 * z^2, y1 * z^3) */
+static void apply_z(u64 *x1, u64 *y1, u64 *z, u64 *curve_prime,
+		    unsigned int ndigits)
+{
+	u64 t1[ndigits];
+
+	vli_mod_square_fast(t1, z, curve_prime, ndigits);    /* z^2 */
+	vli_mod_mult_fast(x1, x1, t1, curve_prime, ndigits); /* x1 * z^2 */
+	vli_mod_mult_fast(t1, t1, z, curve_prime, ndigits);  /* z^3 */
+	vli_mod_mult_fast(y1, y1, t1, curve_prime, ndigits); /* y1 * z^3 */
+}
+
+/* P = (x1, y1) => 2P, (x2, y2) => P' */
+static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
+				u64 *p_initial_z, u64 *curve_prime,
+				unsigned int ndigits)
+{
+	u64 z[ndigits];
+
+	vli_set(x2, x1, ndigits);
+	vli_set(y2, y1, ndigits);
+
+	vli_clear(z, ndigits);
+	z[0] = 1;
+
+	if (p_initial_z)
+		vli_set(z, p_initial_z, ndigits);
+
+	apply_z(x1, y1, z, curve_prime, ndigits);
+
+	ecc_point_double_jacobian(x1, y1, z, curve_prime, ndigits);
+
+	apply_z(x2, y2, z, curve_prime, ndigits);
+}
+
+/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
+ * Output P' = (x1', y1', Z3), P + Q = (x3, y3, Z3)
+ * or P => P', Q => P + Q
+ */
+static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
+		     unsigned int ndigits)
+{
+	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
+	u64 t5[ndigits];
+
+	/* t5 = x2 - x1 */
+	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
+	/* t5 = (x2 - x1)^2 = A */
+	vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+	/* t1 = x1*A = B */
+	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	/* t3 = x2*A = C */
+	vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+	/* t4 = y2 - y1 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+	/* t5 = (y2 - y1)^2 = D */
+	vli_mod_square_fast(t5, y2, curve_prime, ndigits);
+
+	/* t5 = D - B */
+	vli_mod_sub(t5, t5, x1, curve_prime, ndigits);
+	/* t5 = D - B - C = x3 */
+	vli_mod_sub(t5, t5, x2, curve_prime, ndigits);
+	/* t3 = C - B */
+	vli_mod_sub(x2, x2, x1, curve_prime, ndigits);
+	/* t2 = y1*(C - B) */
+	vli_mod_mult_fast(y1, y1, x2, curve_prime, ndigits);
+	/* t3 = B - x3 */
+	vli_mod_sub(x2, x1, t5, curve_prime, ndigits);
+	/* t4 = (y2 - y1)*(B - x3) */
+	vli_mod_mult_fast(y2, y2, x2, curve_prime, ndigits);
+	/* t4 = y3 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+
+	vli_set(x2, t5, ndigits);
+}
+
+/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
+ * Output P + Q = (x3, y3, Z3), P - Q = (x3', y3', Z3)
+ * or P => P - Q, Q => P + Q
+ */
+static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
+		       unsigned int ndigits)
+{
+	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
+	u64 t5[ndigits];
+	u64 t6[ndigits];
+	u64 t7[ndigits];
+
+	/* t5 = x2 - x1 */
+	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
+	/* t5 = (x2 - x1)^2 = A */
+	vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+	/* t1 = x1*A = B */
+	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	/* t3 = x2*A = C */
+	vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+	/* t4 = y2 + y1 */
+	vli_mod_add(t5, y2, y1, curve_prime, ndigits);
+	/* t4 = y2 - y1 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+
+	/* t6 = C - B */
+	vli_mod_sub(t6, x2, x1, curve_prime, ndigits);
+	/* t2 = y1 * (C - B) */
+	vli_mod_mult_fast(y1, y1, t6, curve_prime, ndigits);
+	/* t6 = B + C */
+	vli_mod_add(t6, x1, x2, curve_prime, ndigits);
+	/* t3 = (y2 - y1)^2 */
+	vli_mod_square_fast(x2, y2, curve_prime, ndigits);
+	/* t3 = x3 */
+	vli_mod_sub(x2, x2, t6, curve_prime, ndigits);
+
+	/* t7 = B - x3 */
+	vli_mod_sub(t7, x1, x2, curve_prime, ndigits);
+	/* t4 = (y2 - y1)*(B - x3) */
+	vli_mod_mult_fast(y2, y2, t7, curve_prime, ndigits);
+	/* t4 = y3 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+
+	/* t7 = (y2 + y1)^2 = F */
+	vli_mod_square_fast(t7, t5, curve_prime, ndigits);
+	/* t7 = x3' */
+	vli_mod_sub(t7, t7, t6, curve_prime, ndigits);
+	/* t6 = x3' - B */
+	vli_mod_sub(t6, t7, x1, curve_prime, ndigits);
+	/* t6 = (y2 + y1)*(x3' - B) */
+	vli_mod_mult_fast(t6, t6, t5, curve_prime, ndigits);
+	/* t2 = y3' */
+	vli_mod_sub(y1, t6, y1, curve_prime, ndigits);
+
+	vli_set(x1, t7, ndigits);
+}
+
+static void ecc_point_mult(struct ecc_point *result,
+			   const struct ecc_point *point, const u64 *scalar,
+			   u64 *initial_z, u64 *curve_prime,
+			   unsigned int ndigits)
+{
+	/* R0 and R1 */
+	u64 rx[2][ndigits];
+	u64 ry[2][ndigits];
+	u64 z[ndigits];
+	int i, nb;
+	int num_bits = vli_num_bits(scalar, ndigits);
+
+	vli_set(rx[1], point->x, ndigits);
+	vli_set(ry[1], point->y, ndigits);
+
+	xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve_prime,
+			    ndigits);
+
+	for (i = num_bits - 2; i > 0; i--) {
+		nb = !vli_test_bit(scalar, i);
+		xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
+			   ndigits);
+		xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime,
+			 ndigits);
+	}
+
+	nb = !vli_test_bit(scalar, 0);
+	xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
+		   ndigits);
+
+	/* Find final 1/Z value. */
+	/* X1 - X0 */
+	vli_mod_sub(z, rx[1], rx[0], curve_prime, ndigits);
+	/* Yb * (X1 - X0) */
+	vli_mod_mult_fast(z, z, ry[1 - nb], curve_prime, ndigits);
+	/* xP * Yb * (X1 - X0) */
+	vli_mod_mult_fast(z, z, point->x, curve_prime, ndigits);
+
+	/* 1 / (xP * Yb * (X1 - X0)) */
+	vli_mod_inv(z, z, curve_prime, point->ndigits);
+
+	/* yP / (xP * Yb * (X1 - X0)) */
+	vli_mod_mult_fast(z, z, point->y, curve_prime, ndigits);
+	/* Xb * yP / (xP * Yb * (X1 - X0)) */
+	vli_mod_mult_fast(z, z, rx[1 - nb], curve_prime, ndigits);
+	/* End 1/Z calculation */
+
+	xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime, ndigits);
+
+	apply_z(rx[0], ry[0], z, curve_prime, ndigits);
+
+	vli_set(result->x, rx[0], ndigits);
+	vli_set(result->y, ry[0], ndigits);
+}
+
+static inline void ecc_swap_digits(const u64 *in, u64 *out,
+				   unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		out[i] = __swab64(in[ndigits - 1 - i]);
+}
+
+int ecc_is_key_valid(unsigned int curve_id, unsigned int ndigits,
+		     const u8 *private_key, unsigned int private_key_len)
+{
+	int nbytes;
+	const struct ecc_curve *curve = ecc_get_curve(curve_id);
+
+	if (!private_key)
+		return -EINVAL;
+
+	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	if (private_key_len != nbytes)
+		return -EINVAL;
+
+	if (vli_is_zero((const u64 *)&private_key[0], ndigits))
+		return -EINVAL;
+
+	/* Make sure the private key is in the range [1, n-1]. */
+	if (vli_cmp(curve->n, (const u64 *)&private_key[0], ndigits) != 1)
+		return -EINVAL;
+
+	return 0;
+}
+
+int ecdh_make_pub_key(unsigned int curve_id, unsigned int ndigits,
+		      const u8 *private_key, unsigned int private_key_len,
+		      u8 *public_key, unsigned int public_key_len)
+{
+	int ret = 0;
+	struct ecc_point *pk;
+	u64 priv[ndigits];
+	unsigned int nbytes;
+	const struct ecc_curve *curve = ecc_get_curve(curve_id);
+
+	if (!private_key || !curve) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ecc_swap_digits((const u64 *)private_key, priv, ndigits);
+
+	pk = ecc_alloc_point(ndigits);
+	if (!pk) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ecc_point_mult(pk, &curve->g, priv, NULL, curve->p, ndigits);
+	if (ecc_point_is_zero(pk)) {
+		ret = -EAGAIN;
+		goto err_free_point;
+	}
+
+	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+	ecc_swap_digits(pk->x, (u64 *)public_key, ndigits);
+	ecc_swap_digits(pk->y, (u64 *)&public_key[nbytes], ndigits);
+
+err_free_point:
+	ecc_free_point(pk);
+out:
+	return ret;
+}
+
+int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
+		       const u8 *private_key, unsigned int private_key_len,
+		       const u8 *public_key, unsigned int public_key_len,
+		       u8 *secret, unsigned int secret_len)
+{
+	int ret = 0;
+	struct ecc_point *product, *pk;
+	u64 priv[ndigits];
+	u64 rand_z[ndigits];
+	unsigned int nbytes;
+	const struct ecc_curve *curve = ecc_get_curve(curve_id);
+
+	if (!private_key || !public_key || !curve) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	get_random_bytes(rand_z, nbytes);
+
+	pk = ecc_alloc_point(ndigits);
+	if (!pk) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	product = ecc_alloc_point(ndigits);
+	if (!product) {
+		ret = -ENOMEM;
+		goto err_alloc_product;
+	}
+
+	ecc_swap_digits((const u64 *)public_key, pk->x, ndigits);
+	ecc_swap_digits((const u64 *)&public_key[nbytes], pk->y, ndigits);
+	ecc_swap_digits((const u64 *)private_key, priv, ndigits);
+
+	ecc_point_mult(product, pk, priv, rand_z, curve->p, ndigits);
+
+	ecc_swap_digits(product->x, (u64 *)secret, ndigits);
+
+	if (ecc_point_is_zero(product))
+		ret = -EFAULT;
+
+	ecc_free_point(product);
+err_alloc_product:
+	ecc_free_point(pk);
+out:
+	return ret;
+}
diff --git a/crypto/ecc.h b/crypto/ecc.h
new file mode 100644
index 000000000000..663d598c7406
--- /dev/null
+++ b/crypto/ecc.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (c) 2013, Kenneth MacKay
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *  * Redistributions of source code must retain the above copyright
+ *   notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _CRYPTO_ECC_H
+#define _CRYPTO_ECC_H
+
+#define ECC_MAX_DIGITS	4 /* 256 */
+
+#define ECC_DIGITS_TO_BYTES_SHIFT 3
+
+/**
+ * ecc_is_key_valid() - Validate a given ECDH private key
+ *
+ * @curve_id:		id representing the curve to use
+ * @ndigits:		curve number of digits
+ * @private_key:	private key to be used for the given curve
+ * @private_key_len:	private key len
+ *
+ * Returns 0 if the key is acceptable, a negative value otherwise
+ */
+int ecc_is_key_valid(unsigned int curve_id, unsigned int ndigits,
+		     const u8 *private_key, unsigned int private_key_len);
+
+/**
+ * ecdh_make_pub_key() - Compute an ECC public key
+ *
+ * @curve_id:		id representing the curve to use
+ * @private_key:	pregenerated private key for the given curve
+ * @private_key_len:	length of private_key
+ * @public_key:		buffer for storing the public key generated
+ * @public_key_len:	length of the public_key buffer
+ *
+ * Returns 0 if the public key was generated successfully, a negative value
+ * if an error occurred.
+ */
+int ecdh_make_pub_key(const unsigned int curve_id, unsigned int ndigits,
+		      const u8 *private_key, unsigned int private_key_len,
+		      u8 *public_key, unsigned int public_key_len);
+
+/**
+ * crypto_ecdh_shared_secret() - Compute a shared secret
+ *
+ * @curve_id:		id representing the curve to use
+ * @private_key:	private key of part A
+ * @private_key_len:	length of private_key
+ * @public_key:		public key of counterpart B
+ * @public_key_len:	length of public_key
+ * @secret:		buffer for storing the calculated shared secret
+ * @secret_len:		length of the secret buffer
+ *
+ * Note: It is recommended that you hash the result of crypto_ecdh_shared_secret
+ * before using it for symmetric encryption or HMAC.
+ *
+ * Returns 0 if the shared secret was generated successfully, a negative value
+ * if an error occurred.
+ */
+int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
+		       const u8 *private_key, unsigned int private_key_len,
+		       const u8 *public_key, unsigned int public_key_len,
+		       u8 *secret, unsigned int secret_len);
+#endif
diff --git a/crypto/ecc_curve_defs.h b/crypto/ecc_curve_defs.h
new file mode 100644
index 000000000000..03ae5f714028
--- /dev/null
+++ b/crypto/ecc_curve_defs.h
@@ -0,0 +1,57 @@
+#ifndef _CRYTO_ECC_CURVE_DEFS_H
+#define _CRYTO_ECC_CURVE_DEFS_H
+
+struct ecc_point {
+	u64 *x;
+	u64 *y;
+	u8 ndigits;
+};
+
+struct ecc_curve {
+	char *name;
+	struct ecc_point g;
+	u64 *p;
+	u64 *n;
+};
+
+/* NIST P-192 */
+static u64 nist_p192_g_x[] = { 0xF4FF0AFD82FF1012ull, 0x7CBF20EB43A18800ull,
+				0x188DA80EB03090F6ull };
+static u64 nist_p192_g_y[] = { 0x73F977A11E794811ull, 0x631011ED6B24CDD5ull,
+				0x07192B95FFC8DA78ull };
+static u64 nist_p192_p[] = { 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFEull,
+				0xFFFFFFFFFFFFFFFFull };
+static u64 nist_p192_n[] = { 0x146BC9B1B4D22831ull, 0xFFFFFFFF99DEF836ull,
+				0xFFFFFFFFFFFFFFFFull };
+static struct ecc_curve nist_p192 = {
+	.name = "nist_192",
+	.g = {
+		.x = nist_p192_g_x,
+		.y = nist_p192_g_y,
+		.ndigits = 3,
+	},
+	.p = nist_p192_p,
+	.n = nist_p192_n
+};
+
+/* NIST P-256 */
+static u64 nist_p256_g_x[] = { 0xF4A13945D898C296ull, 0x77037D812DEB33A0ull,
+				0xF8BCE6E563A440F2ull, 0x6B17D1F2E12C4247ull };
+static u64 nist_p256_g_y[] = { 0xCBB6406837BF51F5ull, 0x2BCE33576B315ECEull,
+				0x8EE7EB4A7C0F9E16ull, 0x4FE342E2FE1A7F9Bull };
+static u64 nist_p256_p[] = { 0xFFFFFFFFFFFFFFFFull, 0x00000000FFFFFFFFull,
+				0x0000000000000000ull, 0xFFFFFFFF00000001ull };
+static u64 nist_p256_n[] = { 0xF3B9CAC2FC632551ull, 0xBCE6FAADA7179E84ull,
+				0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFF00000000ull };
+static struct ecc_curve nist_p256 = {
+	.name = "nist_256",
+	.g = {
+		.x = nist_p256_g_x,
+		.y = nist_p256_g_y,
+		.ndigits = 4,
+	},
+	.p = nist_p256_p,
+	.n = nist_p256_n
+};
+
+#endif
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
new file mode 100644
index 000000000000..3de289806d67
--- /dev/null
+++ b/crypto/ecdh.c
@@ -0,0 +1,151 @@
+/* ECDH key-agreement protocol
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvator Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/kpp.h>
+#include <crypto/ecdh.h>
+#include <linux/scatterlist.h>
+#include "ecc.h"
+
+struct ecdh_ctx {
+	unsigned int curve_id;
+	unsigned int ndigits;
+	u64 private_key[ECC_MAX_DIGITS];
+	u64 public_key[2 * ECC_MAX_DIGITS];
+	u64 shared_secret[ECC_MAX_DIGITS];
+};
+
+static inline struct ecdh_ctx *ecdh_get_ctx(struct crypto_kpp *tfm)
+{
+	return kpp_tfm_ctx(tfm);
+}
+
+static unsigned int ecdh_supported_curve(unsigned int curve_id)
+{
+	switch (curve_id) {
+	case ECC_CURVE_NIST_P192: return 3;
+	case ECC_CURVE_NIST_P256: return 4;
+	default: return 0;
+	}
+}
+
+static int ecdh_set_secret(struct crypto_kpp *tfm, void *buf, unsigned int len)
+{
+	struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+	struct ecdh params;
+	unsigned int ndigits;
+
+	if (crypto_ecdh_decode_key(buf, len, &params) < 0)
+		return -EINVAL;
+
+	ndigits = ecdh_supported_curve(params.curve_id);
+	if (!ndigits)
+		return -EINVAL;
+
+	ctx->curve_id = params.curve_id;
+	ctx->ndigits = ndigits;
+
+	if (ecc_is_key_valid(ctx->curve_id, ctx->ndigits,
+			     (const u8 *)params.key, params.key_size) < 0)
+		return -EINVAL;
+
+	memcpy(ctx->private_key, params.key, params.key_size);
+
+	return 0;
+}
+
+static int ecdh_compute_value(struct kpp_request *req)
+{
+	int ret = 0;
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+	size_t copied, nbytes;
+	void *buf;
+
+	nbytes = ctx->ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	if (req->src) {
+		copied = sg_copy_to_buffer(req->src, 1, ctx->public_key,
+					   2 * nbytes);
+		if (copied != 2 * nbytes)
+			return -EINVAL;
+
+		ret = crypto_ecdh_shared_secret(ctx->curve_id, ctx->ndigits,
+					 (const u8 *)ctx->private_key, nbytes,
+					 (const u8 *)ctx->public_key, 2 * nbytes,
+					 (u8 *)ctx->shared_secret, nbytes);
+
+		buf = ctx->shared_secret;
+	} else {
+		ret = ecdh_make_pub_key(ctx->curve_id, ctx->ndigits,
+					(const u8 *)ctx->private_key, nbytes,
+					(u8 *)ctx->public_key,
+					sizeof(ctx->public_key));
+		buf = ctx->public_key;
+		/* Public part is a point thus it has both coordinates */
+		nbytes *= 2;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	copied = sg_copy_from_buffer(req->dst, 1, buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+
+	return ret;
+}
+
+static int ecdh_max_size(struct crypto_kpp *tfm)
+{
+	struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+	int nbytes = ctx->ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	/* Public key is made of two coordinates */
+	return 2 * nbytes;
+}
+
+static void no_exit_tfm(struct crypto_kpp *tfm)
+{
+	return;
+}
+
+static struct kpp_alg ecdh = {
+	.set_secret = ecdh_set_secret,
+	.generate_public_key = ecdh_compute_value,
+	.compute_shared_secret = ecdh_compute_value,
+	.max_size = ecdh_max_size,
+	.exit = no_exit_tfm,
+	.base = {
+		.cra_name = "ecdh",
+		.cra_driver_name = "ecdh-generic",
+		.cra_priority = 100,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct ecdh_ctx),
+	},
+};
+
+static int ecdh_init(void)
+{
+	return crypto_register_kpp(&ecdh);
+}
+
+static void ecdh_exit(void)
+{
+	crypto_unregister_kpp(&ecdh);
+}
+
+module_init(ecdh_init);
+module_exit(ecdh_exit);
+MODULE_ALIAS_CRYPTO("ecdh");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ECDH generic algorithm");
diff --git a/crypto/ecdh_helper.c b/crypto/ecdh_helper.c
new file mode 100644
index 000000000000..3cd8a2414e60
--- /dev/null
+++ b/crypto/ecdh_helper.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <crypto/ecdh.h>
+#include <crypto/kpp.h>
+
+#define ECDH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 2 * sizeof(short))
+
+static inline u8 *ecdh_pack_data(void *dst, const void *src, size_t sz)
+{
+	memcpy(dst, src, sz);
+	return dst + sz;
+}
+
+static inline const u8 *ecdh_unpack_data(void *dst, const void *src, size_t sz)
+{
+	memcpy(dst, src, sz);
+	return src + sz;
+}
+
+int crypto_ecdh_key_len(const struct ecdh *params)
+{
+	return ECDH_KPP_SECRET_MIN_SIZE + params->key_size;
+}
+EXPORT_SYMBOL_GPL(crypto_ecdh_key_len);
+
+int crypto_ecdh_encode_key(char *buf, unsigned int len,
+			   const struct ecdh *params)
+{
+	u8 *ptr = buf;
+	struct kpp_secret secret = {
+		.type = CRYPTO_KPP_SECRET_TYPE_ECDH,
+		.len = len
+	};
+
+	if (unlikely(!buf))
+		return -EINVAL;
+
+	if (len != crypto_ecdh_key_len(params))
+		return -EINVAL;
+
+	ptr = ecdh_pack_data(ptr, &secret, sizeof(secret));
+	ptr = ecdh_pack_data(ptr, &params->curve_id, sizeof(params->curve_id));
+	ptr = ecdh_pack_data(ptr, &params->key_size, sizeof(params->key_size));
+	ecdh_pack_data(ptr, params->key, params->key_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_ecdh_encode_key);
+
+int crypto_ecdh_decode_key(const char *buf, unsigned int len,
+			   struct ecdh *params)
+{
+	const u8 *ptr = buf;
+	struct kpp_secret secret;
+
+	if (unlikely(!buf || len < ECDH_KPP_SECRET_MIN_SIZE))
+		return -EINVAL;
+
+	ptr = ecdh_unpack_data(&secret, ptr, sizeof(secret));
+	if (secret.type != CRYPTO_KPP_SECRET_TYPE_ECDH)
+		return -EINVAL;
+
+	ptr = ecdh_unpack_data(&params->curve_id, ptr, sizeof(params->curve_id));
+	ptr = ecdh_unpack_data(&params->key_size, ptr, sizeof(params->key_size));
+	if (secret.len != crypto_ecdh_key_len(params))
+		return -EINVAL;
+
+	/* Don't allocate memory. Set pointer to data
+	 * within the given buffer
+	 */
+	params->key = (void *)ptr;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_ecdh_decode_key);
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
index b96a84560b67..1b01fe98e91f 100644
--- a/crypto/echainiv.c
+++ b/crypto/echainiv.c
@@ -20,6 +20,7 @@
 
 #include <crypto/internal/geniv.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -112,13 +113,16 @@ static int echainiv_encrypt(struct aead_request *req)
 	info = req->iv;
 
 	if (req->src != req->dst) {
-		struct blkcipher_desc desc = {
-			.tfm = ctx->null,
-		};
+		SKCIPHER_REQUEST_ON_STACK(nreq, ctx->sknull);
 
-		err = crypto_blkcipher_encrypt(
-			&desc, req->dst, req->src,
-			req->assoclen + req->cryptlen);
+		skcipher_request_set_tfm(nreq, ctx->sknull);
+		skcipher_request_set_callback(nreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(nreq, req->src, req->dst,
+					   req->assoclen + req->cryptlen,
+					   NULL);
+
+		err = crypto_skcipher_encrypt(nreq);
 		if (err)
 			return err;
 	}
diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c
deleted file mode 100644
index 16dda72fc4f8..000000000000
--- a/crypto/eseqiv.c
+++ /dev/null
@@ -1,242 +0,0 @@
-/*
- * eseqiv: Encrypted Sequence Number IV Generator
- *
- * This generator generates an IV based on a sequence number by xoring it
- * with a salt and then encrypting it with the same key as used to encrypt
- * the plain text.  This algorithm requires that the block size be equal
- * to the IV size.  It is mainly useful for CBC.
- *
- * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/skcipher.h>
-#include <crypto/rng.h>
-#include <crypto/scatterwalk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-
-struct eseqiv_request_ctx {
-	struct scatterlist src[2];
-	struct scatterlist dst[2];
-	char tail[];
-};
-
-struct eseqiv_ctx {
-	spinlock_t lock;
-	unsigned int reqoff;
-	char salt[];
-};
-
-static void eseqiv_complete2(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct eseqiv_request_ctx *reqctx = skcipher_givcrypt_reqctx(req);
-
-	memcpy(req->giv, PTR_ALIGN((u8 *)reqctx->tail,
-			 crypto_ablkcipher_alignmask(geniv) + 1),
-	       crypto_ablkcipher_ivsize(geniv));
-}
-
-static void eseqiv_complete(struct crypto_async_request *base, int err)
-{
-	struct skcipher_givcrypt_request *req = base->data;
-
-	if (err)
-		goto out;
-
-	eseqiv_complete2(req);
-
-out:
-	skcipher_givcrypt_complete(req, err);
-}
-
-static int eseqiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct eseqiv_request_ctx *reqctx = skcipher_givcrypt_reqctx(req);
-	struct ablkcipher_request *subreq;
-	crypto_completion_t compl;
-	void *data;
-	struct scatterlist *osrc, *odst;
-	struct scatterlist *dst;
-	struct page *srcp;
-	struct page *dstp;
-	u8 *giv;
-	u8 *vsrc;
-	u8 *vdst;
-	__be64 seq;
-	unsigned int ivsize;
-	unsigned int len;
-	int err;
-
-	subreq = (void *)(reqctx->tail + ctx->reqoff);
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-
-	giv = req->giv;
-	compl = req->creq.base.complete;
-	data = req->creq.base.data;
-
-	osrc = req->creq.src;
-	odst = req->creq.dst;
-	srcp = sg_page(osrc);
-	dstp = sg_page(odst);
-	vsrc = PageHighMem(srcp) ? NULL : page_address(srcp) + osrc->offset;
-	vdst = PageHighMem(dstp) ? NULL : page_address(dstp) + odst->offset;
-
-	ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	if (vsrc != giv + ivsize && vdst != giv + ivsize) {
-		giv = PTR_ALIGN((u8 *)reqctx->tail,
-				crypto_ablkcipher_alignmask(geniv) + 1);
-		compl = eseqiv_complete;
-		data = req;
-	}
-
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags, compl,
-					data);
-
-	sg_init_table(reqctx->src, 2);
-	sg_set_buf(reqctx->src, giv, ivsize);
-	scatterwalk_crypto_chain(reqctx->src, osrc, vsrc == giv + ivsize, 2);
-
-	dst = reqctx->src;
-	if (osrc != odst) {
-		sg_init_table(reqctx->dst, 2);
-		sg_set_buf(reqctx->dst, giv, ivsize);
-		scatterwalk_crypto_chain(reqctx->dst, odst, vdst == giv + ivsize, 2);
-
-		dst = reqctx->dst;
-	}
-
-	ablkcipher_request_set_crypt(subreq, reqctx->src, dst,
-				     req->creq.nbytes + ivsize,
-				     req->creq.info);
-
-	memcpy(req->creq.info, ctx->salt, ivsize);
-
-	len = ivsize;
-	if (ivsize > sizeof(u64)) {
-		memset(req->giv, 0, ivsize - sizeof(u64));
-		len = sizeof(u64);
-	}
-	seq = cpu_to_be64(req->seq);
-	memcpy(req->giv + ivsize - len, &seq, len);
-
-	err = crypto_ablkcipher_encrypt(subreq);
-	if (err)
-		goto out;
-
-	if (giv != req->giv)
-		eseqiv_complete2(req);
-
-out:
-	return err;
-}
-
-static int eseqiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	unsigned long alignmask;
-	unsigned int reqsize;
-	int err;
-
-	spin_lock_init(&ctx->lock);
-
-	alignmask = crypto_tfm_ctx_alignment() - 1;
-	reqsize = sizeof(struct eseqiv_request_ctx);
-
-	if (alignmask & reqsize) {
-		alignmask &= reqsize;
-		alignmask--;
-	}
-
-	alignmask = ~alignmask;
-	alignmask &= crypto_ablkcipher_alignmask(geniv);
-
-	reqsize += alignmask;
-	reqsize += crypto_ablkcipher_ivsize(geniv);
-	reqsize = ALIGN(reqsize, crypto_tfm_ctx_alignment());
-
-	ctx->reqoff = reqsize - sizeof(struct eseqiv_request_ctx);
-
-	tfm->crt_ablkcipher.reqsize = reqsize +
-				      sizeof(struct ablkcipher_request);
-
-	err = 0;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt = eseqiv_givencrypt;
-		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-					   crypto_ablkcipher_ivsize(geniv));
-		crypto_put_default_rng();
-	}
-
-	return err ?: skcipher_geniv_init(tfm);
-}
-
-static struct crypto_template eseqiv_tmpl;
-
-static struct crypto_instance *eseqiv_alloc(struct rtattr **tb)
-{
-	struct crypto_instance *inst;
-	int err;
-
-	inst = skcipher_geniv_alloc(&eseqiv_tmpl, tb, 0, 0);
-	if (IS_ERR(inst))
-		goto out;
-
-	err = -EINVAL;
-	if (inst->alg.cra_ablkcipher.ivsize != inst->alg.cra_blocksize)
-		goto free_inst;
-
-	inst->alg.cra_init = eseqiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
-
-	inst->alg.cra_ctxsize = sizeof(struct eseqiv_ctx);
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
-
-out:
-	return inst;
-
-free_inst:
-	skcipher_geniv_free(inst);
-	inst = ERR_PTR(err);
-	goto out;
-}
-
-static struct crypto_template eseqiv_tmpl = {
-	.name = "eseqiv",
-	.alloc = eseqiv_alloc,
-	.free = skcipher_geniv_free,
-	.module = THIS_MODULE,
-};
-
-static int __init eseqiv_module_init(void)
-{
-	return crypto_register_template(&eseqiv_tmpl);
-}
-
-static void __exit eseqiv_module_exit(void)
-{
-	crypto_unregister_template(&eseqiv_tmpl);
-}
-
-module_init(eseqiv_module_init);
-module_exit(eseqiv_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Encrypted Sequence Number IV Generator");
-MODULE_ALIAS_CRYPTO("eseqiv");
diff --git a/crypto/gcm.c b/crypto/gcm.c
index bec329b3de8d..70a892e87ccb 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -29,7 +29,7 @@ struct gcm_instance_ctx {
 };
 
 struct crypto_gcm_ctx {
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 	struct crypto_ahash *ghash;
 };
 
@@ -50,7 +50,7 @@ struct crypto_rfc4543_instance_ctx {
 
 struct crypto_rfc4543_ctx {
 	struct crypto_aead *child;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *null;
 	u8 nonce[4];
 };
 
@@ -74,7 +74,7 @@ struct crypto_gcm_req_priv_ctx {
 	struct crypto_gcm_ghash_ctx ghash_ctx;
 	union {
 		struct ahash_request ahreq;
-		struct ablkcipher_request abreq;
+		struct skcipher_request skreq;
 	} u;
 };
 
@@ -114,7 +114,7 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 {
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_ahash *ghash = ctx->ghash;
-	struct crypto_ablkcipher *ctr = ctx->ctr;
+	struct crypto_skcipher *ctr = ctx->ctr;
 	struct {
 		be128 hash;
 		u8 iv[8];
@@ -122,35 +122,35 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 		struct crypto_gcm_setkey_result result;
 
 		struct scatterlist sg[1];
-		struct ablkcipher_request req;
+		struct skcipher_request req;
 	} *data;
 	int err;
 
-	crypto_ablkcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
-					 CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(ctr, key, keylen);
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
+	crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(ctr, key, keylen);
+	crypto_aead_set_flags(aead, crypto_skcipher_get_flags(ctr) &
 				    CRYPTO_TFM_RES_MASK);
 	if (err)
 		return err;
 
-	data = kzalloc(sizeof(*data) + crypto_ablkcipher_reqsize(ctr),
+	data = kzalloc(sizeof(*data) + crypto_skcipher_reqsize(ctr),
 		       GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
 	init_completion(&data->result.completion);
 	sg_init_one(data->sg, &data->hash, sizeof(data->hash));
-	ablkcipher_request_set_tfm(&data->req, ctr);
-	ablkcipher_request_set_callback(&data->req, CRYPTO_TFM_REQ_MAY_SLEEP |
-						    CRYPTO_TFM_REQ_MAY_BACKLOG,
-					crypto_gcm_setkey_done,
-					&data->result);
-	ablkcipher_request_set_crypt(&data->req, data->sg, data->sg,
-				     sizeof(data->hash), data->iv);
-
-	err = crypto_ablkcipher_encrypt(&data->req);
+	skcipher_request_set_tfm(&data->req, ctr);
+	skcipher_request_set_callback(&data->req, CRYPTO_TFM_REQ_MAY_SLEEP |
+						  CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      crypto_gcm_setkey_done,
+				      &data->result);
+	skcipher_request_set_crypt(&data->req, data->sg, data->sg,
+				   sizeof(data->hash), data->iv);
+
+	err = crypto_skcipher_encrypt(&data->req);
 	if (err == -EINPROGRESS || err == -EBUSY) {
 		err = wait_for_completion_interruptible(
 			&data->result.completion);
@@ -223,13 +223,13 @@ static void crypto_gcm_init_crypt(struct aead_request *req,
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *ablk_req = &pctx->u.abreq;
+	struct skcipher_request *skreq = &pctx->u.skreq;
 	struct scatterlist *dst;
 
 	dst = req->src == req->dst ? pctx->src : pctx->dst;
 
-	ablkcipher_request_set_tfm(ablk_req, ctx->ctr);
-	ablkcipher_request_set_crypt(ablk_req, pctx->src, dst,
+	skcipher_request_set_tfm(skreq, ctx->ctr);
+	skcipher_request_set_crypt(skreq, pctx->src, dst,
 				     cryptlen + sizeof(pctx->auth_tag),
 				     pctx->iv);
 }
@@ -494,14 +494,14 @@ out:
 static int crypto_gcm_encrypt(struct aead_request *req)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->u.abreq;
+	struct skcipher_request *skreq = &pctx->u.skreq;
 	u32 flags = aead_request_flags(req);
 
 	crypto_gcm_init_common(req);
 	crypto_gcm_init_crypt(req, req->cryptlen);
-	ablkcipher_request_set_callback(abreq, flags, gcm_encrypt_done, req);
+	skcipher_request_set_callback(skreq, flags, gcm_encrypt_done, req);
 
-	return crypto_ablkcipher_encrypt(abreq) ?:
+	return crypto_skcipher_encrypt(skreq) ?:
 	       gcm_encrypt_continue(req, flags);
 }
 
@@ -533,12 +533,12 @@ static void gcm_decrypt_done(struct crypto_async_request *areq, int err)
 static int gcm_dec_hash_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->u.abreq;
+	struct skcipher_request *skreq = &pctx->u.skreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
 	crypto_gcm_init_crypt(req, gctx->cryptlen);
-	ablkcipher_request_set_callback(abreq, flags, gcm_decrypt_done, req);
-	return crypto_ablkcipher_decrypt(abreq) ?: crypto_gcm_verify(req);
+	skcipher_request_set_callback(skreq, flags, gcm_decrypt_done, req);
+	return crypto_skcipher_decrypt(skreq) ?: crypto_gcm_verify(req);
 }
 
 static int crypto_gcm_decrypt(struct aead_request *req)
@@ -566,7 +566,7 @@ static int crypto_gcm_init_tfm(struct crypto_aead *tfm)
 	struct aead_instance *inst = aead_alg_instance(tfm);
 	struct gcm_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 	struct crypto_ahash *ghash;
 	unsigned long align;
 	int err;
@@ -575,7 +575,7 @@ static int crypto_gcm_init_tfm(struct crypto_aead *tfm)
 	if (IS_ERR(ghash))
 		return PTR_ERR(ghash);
 
-	ctr = crypto_spawn_skcipher(&ictx->ctr);
+	ctr = crypto_spawn_skcipher2(&ictx->ctr);
 	err = PTR_ERR(ctr);
 	if (IS_ERR(ctr))
 		goto err_free_hash;
@@ -587,8 +587,8 @@ static int crypto_gcm_init_tfm(struct crypto_aead *tfm)
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
 	crypto_aead_set_reqsize(tfm,
 		align + offsetof(struct crypto_gcm_req_priv_ctx, u) +
-		max(sizeof(struct ablkcipher_request) +
-		    crypto_ablkcipher_reqsize(ctr),
+		max(sizeof(struct skcipher_request) +
+		    crypto_skcipher_reqsize(ctr),
 		    sizeof(struct ahash_request) +
 		    crypto_ahash_reqsize(ghash)));
 
@@ -604,7 +604,7 @@ static void crypto_gcm_exit_tfm(struct crypto_aead *tfm)
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->ghash);
-	crypto_free_ablkcipher(ctx->ctr);
+	crypto_free_skcipher(ctx->ctr);
 }
 
 static void crypto_gcm_free(struct aead_instance *inst)
@@ -624,7 +624,7 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 {
 	struct crypto_attr_type *algt;
 	struct aead_instance *inst;
-	struct crypto_alg *ctr;
+	struct skcipher_alg *ctr;
 	struct crypto_alg *ghash_alg;
 	struct hash_alg_common *ghash;
 	struct gcm_instance_ctx *ctx;
@@ -639,7 +639,9 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 
 	ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type,
 				    CRYPTO_ALG_TYPE_HASH,
-				    CRYPTO_ALG_TYPE_AHASH_MASK);
+				    CRYPTO_ALG_TYPE_AHASH_MASK |
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (IS_ERR(ghash_alg))
 		return PTR_ERR(ghash_alg);
 
@@ -661,41 +663,42 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 		goto err_drop_ghash;
 
 	crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->ctr, ctr_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->ctr, ctr_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_ghash;
 
-	ctr = crypto_skcipher_spawn_alg(&ctx->ctr);
+	ctr = crypto_spawn_skcipher_alg(&ctx->ctr);
 
 	/* We only support 16-byte blocks. */
-	if (ctr->cra_ablkcipher.ivsize != 16)
+	if (crypto_skcipher_alg_ivsize(ctr) != 16)
 		goto out_put_ctr;
 
 	/* Not a stream cipher? */
 	err = -EINVAL;
-	if (ctr->cra_blocksize != 1)
+	if (ctr->base.cra_blocksize != 1)
 		goto out_put_ctr;
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "gcm_base(%s,%s)", ctr->cra_driver_name,
+		     "gcm_base(%s,%s)", ctr->base.cra_driver_name,
 		     ghash_alg->cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_put_ctr;
 
 	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
 
-	inst->alg.base.cra_flags = (ghash->base.cra_flags | ctr->cra_flags) &
-				   CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_flags = (ghash->base.cra_flags |
+				    ctr->base.cra_flags) & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (ghash->base.cra_priority +
-				       ctr->cra_priority) / 2;
+				       ctr->base.cra_priority) / 2;
 	inst->alg.base.cra_blocksize = 1;
 	inst->alg.base.cra_alignmask = ghash->base.cra_alignmask |
-				       ctr->cra_alignmask;
+				       ctr->base.cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_gcm_ctx);
 	inst->alg.ivsize = 12;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(ctr);
 	inst->alg.maxauthsize = 16;
 	inst->alg.init = crypto_gcm_init_tfm;
 	inst->alg.exit = crypto_gcm_exit_tfm;
@@ -980,6 +983,7 @@ static int crypto_rfc4106_create(struct crypto_template *tmpl,
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4106_ctx);
 
 	inst->alg.ivsize = 8;
+	inst->alg.chunksize = crypto_aead_alg_chunksize(alg);
 	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
 	inst->alg.init = crypto_rfc4106_init_tfm;
@@ -1084,11 +1088,13 @@ static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc)
 	unsigned int authsize = crypto_aead_authsize(aead);
 	unsigned int nbytes = req->assoclen + req->cryptlen -
 			      (enc ? 0 : authsize);
-	struct blkcipher_desc desc = {
-		.tfm = ctx->null,
-	};
+	SKCIPHER_REQUEST_ON_STACK(nreq, ctx->null);
 
-	return crypto_blkcipher_encrypt(&desc, req->dst, req->src, nbytes);
+	skcipher_request_set_tfm(nreq, ctx->null);
+	skcipher_request_set_callback(nreq, req->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(nreq, req->src, req->dst, nbytes, NULL);
+
+	return crypto_skcipher_encrypt(nreq);
 }
 
 static int crypto_rfc4543_encrypt(struct aead_request *req)
@@ -1108,7 +1114,7 @@ static int crypto_rfc4543_init_tfm(struct crypto_aead *tfm)
 	struct crypto_aead_spawn *spawn = &ictx->aead;
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *aead;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *null;
 	unsigned long align;
 	int err = 0;
 
@@ -1116,7 +1122,7 @@ static int crypto_rfc4543_init_tfm(struct crypto_aead *tfm)
 	if (IS_ERR(aead))
 		return PTR_ERR(aead);
 
-	null = crypto_get_default_null_skcipher();
+	null = crypto_get_default_null_skcipher2();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_aead;
@@ -1144,7 +1150,7 @@ static void crypto_rfc4543_exit_tfm(struct crypto_aead *tfm)
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_put_default_null_skcipher();
+	crypto_put_default_null_skcipher2();
 }
 
 static void crypto_rfc4543_free(struct aead_instance *inst)
@@ -1219,6 +1225,7 @@ static int crypto_rfc4543_create(struct crypto_template *tmpl,
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4543_ctx);
 
 	inst->alg.ivsize = 8;
+	inst->alg.chunksize = crypto_aead_alg_chunksize(alg);
 	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
 	inst->alg.init = crypto_rfc4543_init_tfm;
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index 597cedd3531c..c4938497eedb 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -87,24 +87,28 @@ void jent_memcpy(void *dest, const void *src, unsigned int n)
 	memcpy(dest, src, n);
 }
 
+/*
+ * Obtain a high-resolution time stamp value. The time stamp is used to measure
+ * the execution time of a given code path and its variations. Hence, the time
+ * stamp must have a sufficiently high resolution.
+ *
+ * Note, if the function returns zero because a given architecture does not
+ * implement a high-resolution time stamp, the RNG code's runtime test
+ * will detect it and will not produce output.
+ */
 void jent_get_nstime(__u64 *out)
 {
-	struct timespec ts;
 	__u64 tmp = 0;
 
 	tmp = random_get_entropy();
 
 	/*
-	 * If random_get_entropy does not return a value (which is possible on,
-	 * for example, MIPS), invoke __getnstimeofday
+	 * If random_get_entropy does not return a value, i.e. it is not
+	 * implemented for a given architecture, use a clock source.
 	 * hoping that there are timers we can work with.
 	 */
-	if ((0 == tmp) &&
-	   (0 == __getnstimeofday(&ts))) {
-		tmp = ts.tv_sec;
-		tmp = tmp << 32;
-		tmp = tmp | ts.tv_nsec;
-	}
+	if (tmp == 0)
+		tmp = ktime_get_ns();
 
 	*out = tmp;
 }
diff --git a/crypto/kpp.c b/crypto/kpp.c
new file mode 100644
index 000000000000..d36ce05eee43
--- /dev/null
+++ b/crypto/kpp.c
@@ -0,0 +1,123 @@
+/*
+ * Key-agreement Protocol Primitives (KPP)
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
+#include <linux/cryptouser.h>
+#include <net/netlink.h>
+#include <crypto/kpp.h>
+#include <crypto/internal/kpp.h>
+#include "internal.h"
+
+#ifdef CONFIG_NET
+static int crypto_kpp_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_kpp rkpp;
+
+	strncpy(rkpp.type, "kpp", sizeof(rkpp.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_KPP,
+		    sizeof(struct crypto_report_kpp), &rkpp))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
+static int crypto_kpp_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
+static void crypto_kpp_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+
+static void crypto_kpp_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	seq_puts(m, "type         : kpp\n");
+}
+
+static void crypto_kpp_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_kpp *kpp = __crypto_kpp_tfm(tfm);
+	struct kpp_alg *alg = crypto_kpp_alg(kpp);
+
+	alg->exit(kpp);
+}
+
+static int crypto_kpp_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_kpp *kpp = __crypto_kpp_tfm(tfm);
+	struct kpp_alg *alg = crypto_kpp_alg(kpp);
+
+	if (alg->exit)
+		kpp->base.exit = crypto_kpp_exit_tfm;
+
+	if (alg->init)
+		return alg->init(kpp);
+
+	return 0;
+}
+
+static const struct crypto_type crypto_kpp_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_kpp_init_tfm,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_kpp_show,
+#endif
+	.report = crypto_kpp_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_KPP,
+	.tfmsize = offsetof(struct crypto_kpp, base),
+};
+
+struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_kpp_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_kpp);
+
+static void kpp_prepare_alg(struct kpp_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	base->cra_type = &crypto_kpp_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_KPP;
+}
+
+int crypto_register_kpp(struct kpp_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	kpp_prepare_alg(alg);
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_kpp);
+
+void crypto_unregister_kpp(struct kpp_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_kpp);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Key-agreement Protocol Primitives");
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index c4eb9da49d4f..86fb59b109a9 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -41,7 +41,7 @@ struct mcryptd_flush_list {
 static struct mcryptd_flush_list __percpu *mcryptd_flist;
 
 struct hashd_instance_ctx {
-	struct crypto_shash_spawn spawn;
+	struct crypto_ahash_spawn spawn;
 	struct mcryptd_queue *queue;
 };
 
@@ -272,18 +272,18 @@ static int mcryptd_hash_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
 	struct hashd_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_shash_spawn *spawn = &ictx->spawn;
+	struct crypto_ahash_spawn *spawn = &ictx->spawn;
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_shash *hash;
+	struct crypto_ahash *hash;
 
-	hash = crypto_spawn_shash(spawn);
+	hash = crypto_spawn_ahash(spawn);
 	if (IS_ERR(hash))
 		return PTR_ERR(hash);
 
 	ctx->child = hash;
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct mcryptd_hash_request_ctx) +
-				 crypto_shash_descsize(hash));
+				 crypto_ahash_reqsize(hash));
 	return 0;
 }
 
@@ -291,21 +291,21 @@ static void mcryptd_hash_exit_tfm(struct crypto_tfm *tfm)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_shash(ctx->child);
+	crypto_free_ahash(ctx->child);
 }
 
 static int mcryptd_hash_setkey(struct crypto_ahash *parent,
 				   const u8 *key, unsigned int keylen)
 {
 	struct mcryptd_hash_ctx *ctx   = crypto_ahash_ctx(parent);
-	struct crypto_shash *child = ctx->child;
+	struct crypto_ahash *child = ctx->child;
 	int err;
 
-	crypto_shash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_shash_set_flags(child, crypto_ahash_get_flags(parent) &
+	crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_ahash_set_flags(child, crypto_ahash_get_flags(parent) &
 				      CRYPTO_TFM_REQ_MASK);
-	err = crypto_shash_setkey(child, key, keylen);
-	crypto_ahash_set_flags(parent, crypto_shash_get_flags(child) &
+	err = crypto_ahash_setkey(child, key, keylen);
+	crypto_ahash_set_flags(parent, crypto_ahash_get_flags(child) &
 				       CRYPTO_TFM_RES_MASK);
 	return err;
 }
@@ -331,20 +331,20 @@ static int mcryptd_hash_enqueue(struct ahash_request *req,
 static void mcryptd_hash_init(struct crypto_async_request *req_async, int err)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
-	struct crypto_shash *child = ctx->child;
+	struct crypto_ahash *child = ctx->child;
 	struct ahash_request *req = ahash_request_cast(req_async);
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
-	struct shash_desc *desc = &rctx->desc;
+	struct ahash_request *desc = &rctx->areq;
 
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	ahash_request_set_tfm(desc, child);
+	ahash_request_set_callback(desc, CRYPTO_TFM_REQ_MAY_SLEEP,
+						rctx->complete, req_async);
 
-	err = crypto_shash_init(desc);
-
-	req->base.complete = rctx->complete;
+	rctx->out = req->result;
+	err = crypto_ahash_init(desc);
 
 out:
 	local_bh_disable();
@@ -365,7 +365,8 @@ static void mcryptd_hash_update(struct crypto_async_request *req_async, int err)
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	err = shash_ahash_mcryptd_update(req, &rctx->desc);
+	rctx->out = req->result;
+	err = ahash_mcryptd_update(&rctx->areq);
 	if (err) {
 		req->base.complete = rctx->complete;
 		goto out;
@@ -391,7 +392,8 @@ static void mcryptd_hash_final(struct crypto_async_request *req_async, int err)
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	err = shash_ahash_mcryptd_final(req, &rctx->desc);
+	rctx->out = req->result;
+	err = ahash_mcryptd_final(&rctx->areq);
 	if (err) {
 		req->base.complete = rctx->complete;
 		goto out;
@@ -416,8 +418,8 @@ static void mcryptd_hash_finup(struct crypto_async_request *req_async, int err)
 
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
-
-	err = shash_ahash_mcryptd_finup(req, &rctx->desc);
+	rctx->out = req->result;
+	err = ahash_mcryptd_finup(&rctx->areq);
 
 	if (err) {
 		req->base.complete = rctx->complete;
@@ -439,25 +441,21 @@ static int mcryptd_hash_finup_enqueue(struct ahash_request *req)
 static void mcryptd_hash_digest(struct crypto_async_request *req_async, int err)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
-	struct crypto_shash *child = ctx->child;
+	struct crypto_ahash *child = ctx->child;
 	struct ahash_request *req = ahash_request_cast(req_async);
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
-	struct shash_desc *desc = &rctx->desc;
+	struct ahash_request *desc = &rctx->areq;
 
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;  /* check this again */
-
-	err = shash_ahash_mcryptd_digest(req, desc);
+	ahash_request_set_tfm(desc, child);
+	ahash_request_set_callback(desc, CRYPTO_TFM_REQ_MAY_SLEEP,
+						rctx->complete, req_async);
 
-	if (err) {
-		req->base.complete = rctx->complete;
-		goto out;
-	}
+	rctx->out = req->result;
+	err = ahash_mcryptd_digest(desc);
 
-	return;
 out:
 	local_bh_disable();
 	rctx->complete(&req->base, err);
@@ -473,14 +471,14 @@ static int mcryptd_hash_export(struct ahash_request *req, void *out)
 {
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
 
-	return crypto_shash_export(&rctx->desc, out);
+	return crypto_ahash_export(&rctx->areq, out);
 }
 
 static int mcryptd_hash_import(struct ahash_request *req, const void *in)
 {
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
 
-	return crypto_shash_import(&rctx->desc, in);
+	return crypto_ahash_import(&rctx->areq, in);
 }
 
 static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
@@ -488,7 +486,7 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 {
 	struct hashd_instance_ctx *ctx;
 	struct ahash_instance *inst;
-	struct shash_alg *salg;
+	struct hash_alg_common *halg;
 	struct crypto_alg *alg;
 	u32 type = 0;
 	u32 mask = 0;
@@ -496,11 +494,11 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 
 	mcryptd_check_internal(tb, &type, &mask);
 
-	salg = shash_attr_alg(tb[1], type, mask);
-	if (IS_ERR(salg))
-		return PTR_ERR(salg);
+	halg = ahash_attr_alg(tb[1], type, mask);
+	if (IS_ERR(halg))
+		return PTR_ERR(halg);
 
-	alg = &salg->base;
+	alg = &halg->base;
 	pr_debug("crypto: mcryptd hash alg: %s\n", alg->cra_name);
 	inst = mcryptd_alloc_instance(alg, ahash_instance_headroom(),
 					sizeof(*ctx));
@@ -511,7 +509,7 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	ctx = ahash_instance_ctx(inst);
 	ctx->queue = queue;
 
-	err = crypto_init_shash_spawn(&ctx->spawn, salg,
+	err = crypto_init_ahash_spawn(&ctx->spawn, halg,
 				      ahash_crypto_instance(inst));
 	if (err)
 		goto out_free_inst;
@@ -521,8 +519,8 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 		type |= CRYPTO_ALG_INTERNAL;
 	inst->alg.halg.base.cra_flags = type;
 
-	inst->alg.halg.digestsize = salg->digestsize;
-	inst->alg.halg.statesize = salg->statesize;
+	inst->alg.halg.digestsize = halg->digestsize;
+	inst->alg.halg.statesize = halg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct mcryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = mcryptd_hash_init_tfm;
@@ -539,7 +537,7 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 
 	err = ahash_register_instance(tmpl, inst);
 	if (err) {
-		crypto_drop_shash(&ctx->spawn);
+		crypto_drop_ahash(&ctx->spawn);
 out_free_inst:
 		kfree(inst);
 	}
@@ -575,7 +573,7 @@ static void mcryptd_free(struct crypto_instance *inst)
 
 	switch (inst->alg.cra_flags & CRYPTO_ALG_TYPE_MASK) {
 	case CRYPTO_ALG_TYPE_AHASH:
-		crypto_drop_shash(&hctx->spawn);
+		crypto_drop_ahash(&hctx->spawn);
 		kfree(ahash_instance(inst));
 		return;
 	default:
@@ -612,55 +610,38 @@ struct mcryptd_ahash *mcryptd_alloc_ahash(const char *alg_name,
 }
 EXPORT_SYMBOL_GPL(mcryptd_alloc_ahash);
 
-int shash_ahash_mcryptd_digest(struct ahash_request *req,
-			       struct shash_desc *desc)
+int ahash_mcryptd_digest(struct ahash_request *desc)
 {
 	int err;
 
-	err = crypto_shash_init(desc) ?:
-	      shash_ahash_mcryptd_finup(req, desc);
+	err = crypto_ahash_init(desc) ?:
+	      ahash_mcryptd_finup(desc);
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_digest);
 
-int shash_ahash_mcryptd_update(struct ahash_request *req,
-			       struct shash_desc *desc)
+int ahash_mcryptd_update(struct ahash_request *desc)
 {
-	struct crypto_shash *tfm = desc->tfm;
-	struct shash_alg *shash = crypto_shash_alg(tfm);
-
 	/* alignment is to be done by multi-buffer crypto algorithm if needed */
 
-	return shash->update(desc, NULL, 0);
+	return crypto_ahash_update(desc);
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_update);
 
-int shash_ahash_mcryptd_finup(struct ahash_request *req,
-			      struct shash_desc *desc)
+int ahash_mcryptd_finup(struct ahash_request *desc)
 {
-	struct crypto_shash *tfm = desc->tfm;
-	struct shash_alg *shash = crypto_shash_alg(tfm);
-
 	/* alignment is to be done by multi-buffer crypto algorithm if needed */
 
-	return shash->finup(desc, NULL, 0, req->result);
+	return crypto_ahash_finup(desc);
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_finup);
 
-int shash_ahash_mcryptd_final(struct ahash_request *req,
-			      struct shash_desc *desc)
+int ahash_mcryptd_final(struct ahash_request *desc)
 {
-	struct crypto_shash *tfm = desc->tfm;
-	struct shash_alg *shash = crypto_shash_alg(tfm);
-
 	/* alignment is to be done by multi-buffer crypto algorithm if needed */
 
-	return shash->final(desc, req->result);
+	return crypto_ahash_final(desc);
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_final);
 
-struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm)
+struct crypto_ahash *mcryptd_ahash_child(struct mcryptd_ahash *tfm)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
 
@@ -668,12 +649,12 @@ struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm)
 }
 EXPORT_SYMBOL_GPL(mcryptd_ahash_child);
 
-struct shash_desc *mcryptd_shash_desc(struct ahash_request *req)
+struct ahash_request *mcryptd_ahash_desc(struct ahash_request *req)
 {
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
-	return &rctx->desc;
+	return &rctx->areq;
 }
-EXPORT_SYMBOL_GPL(mcryptd_shash_desc);
+EXPORT_SYMBOL_GPL(mcryptd_ahash_desc);
 
 void mcryptd_free_ahash(struct mcryptd_ahash *tfm)
 {
@@ -681,7 +662,6 @@ void mcryptd_free_ahash(struct mcryptd_ahash *tfm)
 }
 EXPORT_SYMBOL_GPL(mcryptd_free_ahash);
 
-
 static int __init mcryptd_init(void)
 {
 	int err, cpu;
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index 8ba426635b1b..877019a6d3ea 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -92,19 +92,17 @@ static const struct rsa_asn1_template *rsa_lookup_asn1(const char *name)
 
 struct pkcs1pad_ctx {
 	struct crypto_akcipher *child;
-	const char *hash_name;
 	unsigned int key_size;
 };
 
 struct pkcs1pad_inst_ctx {
 	struct crypto_akcipher_spawn spawn;
-	const char *hash_name;
+	const struct rsa_asn1_template *digest_info;
 };
 
 struct pkcs1pad_request {
-	struct scatterlist in_sg[3], out_sg[2];
+	struct scatterlist in_sg[2], out_sg[1];
 	uint8_t *in_buf, *out_buf;
-
 	struct akcipher_request child_req;
 };
 
@@ -112,40 +110,48 @@ static int pkcs1pad_set_pub_key(struct crypto_akcipher *tfm, const void *key,
 		unsigned int keylen)
 {
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
-	int err, size;
+	int err;
+
+	ctx->key_size = 0;
 
 	err = crypto_akcipher_set_pub_key(ctx->child, key, keylen);
+	if (err)
+		return err;
 
-	if (!err) {
-		/* Find out new modulus size from rsa implementation */
-		size = crypto_akcipher_maxsize(ctx->child);
+	/* Find out new modulus size from rsa implementation */
+	err = crypto_akcipher_maxsize(ctx->child);
+	if (err < 0)
+		return err;
 
-		ctx->key_size = size > 0 ? size : 0;
-		if (size <= 0)
-			err = size;
-	}
+	if (err > PAGE_SIZE)
+		return -ENOTSUPP;
 
-	return err;
+	ctx->key_size = err;
+	return 0;
 }
 
 static int pkcs1pad_set_priv_key(struct crypto_akcipher *tfm, const void *key,
 		unsigned int keylen)
 {
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
-	int err, size;
+	int err;
+
+	ctx->key_size = 0;
 
 	err = crypto_akcipher_set_priv_key(ctx->child, key, keylen);
+	if (err)
+		return err;
 
-	if (!err) {
-		/* Find out new modulus size from rsa implementation */
-		size = crypto_akcipher_maxsize(ctx->child);
+	/* Find out new modulus size from rsa implementation */
+	err = crypto_akcipher_maxsize(ctx->child);
+	if (err < 0)
+		return err;
 
-		ctx->key_size = size > 0 ? size : 0;
-		if (size <= 0)
-			err = size;
-	}
+	if (err > PAGE_SIZE)
+		return -ENOTSUPP;
 
-	return err;
+	ctx->key_size = err;
+	return 0;
 }
 
 static int pkcs1pad_get_max_size(struct crypto_akcipher *tfm)
@@ -164,19 +170,10 @@ static int pkcs1pad_get_max_size(struct crypto_akcipher *tfm)
 static void pkcs1pad_sg_set_buf(struct scatterlist *sg, void *buf, size_t len,
 		struct scatterlist *next)
 {
-	int nsegs = next ? 1 : 0;
-
-	if (offset_in_page(buf) + len <= PAGE_SIZE) {
-		nsegs += 1;
-		sg_init_table(sg, nsegs);
-		sg_set_buf(sg, buf, len);
-	} else {
-		nsegs += 2;
-		sg_init_table(sg, nsegs);
-		sg_set_buf(sg + 0, buf, PAGE_SIZE - offset_in_page(buf));
-		sg_set_buf(sg + 1, buf + PAGE_SIZE - offset_in_page(buf),
-				offset_in_page(buf) + len - PAGE_SIZE);
-	}
+	int nsegs = next ? 2 : 1;
+
+	sg_init_table(sg, nsegs);
+	sg_set_buf(sg, buf, len);
 
 	if (next)
 		sg_chain(sg, nsegs, next);
@@ -187,37 +184,36 @@ static int pkcs1pad_encrypt_sign_complete(struct akcipher_request *req, int err)
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
-	size_t pad_len = ctx->key_size - req_ctx->child_req.dst_len;
-	size_t chunk_len, pad_left;
-	struct sg_mapping_iter miter;
-
-	if (!err) {
-		if (pad_len) {
-			sg_miter_start(&miter, req->dst,
-					sg_nents_for_len(req->dst, pad_len),
-					SG_MITER_ATOMIC | SG_MITER_TO_SG);
-
-			pad_left = pad_len;
-			while (pad_left) {
-				sg_miter_next(&miter);
-
-				chunk_len = min(miter.length, pad_left);
-				memset(miter.addr, 0, chunk_len);
-				pad_left -= chunk_len;
-			}
-
-			sg_miter_stop(&miter);
-		}
-
-		sg_pcopy_from_buffer(req->dst,
-				sg_nents_for_len(req->dst, ctx->key_size),
-				req_ctx->out_buf, req_ctx->child_req.dst_len,
-				pad_len);
-	}
+	unsigned int pad_len;
+	unsigned int len;
+	u8 *out_buf;
+
+	if (err)
+		goto out;
+
+	len = req_ctx->child_req.dst_len;
+	pad_len = ctx->key_size - len;
+
+	/* Four billion to one */
+	if (likely(!pad_len))
+		goto out;
+
+	out_buf = kzalloc(ctx->key_size, GFP_ATOMIC);
+	err = -ENOMEM;
+	if (!out_buf)
+		goto out;
+
+	sg_copy_to_buffer(req->dst, sg_nents_for_len(req->dst, len),
+			  out_buf + pad_len, len);
+	sg_copy_from_buffer(req->dst,
+			    sg_nents_for_len(req->dst, ctx->key_size),
+			    out_buf, ctx->key_size);
+	kzfree(out_buf);
+
+out:
 	req->dst_len = ctx->key_size;
 
 	kfree(req_ctx->in_buf);
-	kzfree(req_ctx->out_buf);
 
 	return err;
 }
@@ -257,21 +253,8 @@ static int pkcs1pad_encrypt(struct akcipher_request *req)
 		return -EOVERFLOW;
 	}
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/*
-	 * Replace both input and output to add the padding in the input and
-	 * the potential missing leading zeros in the output.
-	 */
-	req_ctx->child_req.src = req_ctx->in_sg;
-	req_ctx->child_req.src_len = ctx->key_size - 1;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
 	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!req_ctx->in_buf)
 		return -ENOMEM;
 
@@ -284,9 +267,7 @@ static int pkcs1pad_encrypt(struct akcipher_request *req)
 	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
 			ctx->key_size - 1 - req->src_len, req->src);
 
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf) {
 		kfree(req_ctx->in_buf);
 		return -ENOMEM;
@@ -299,6 +280,10 @@ static int pkcs1pad_encrypt(struct akcipher_request *req)
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_encrypt_sign_complete_cb, req);
 
+	/* Reuse output buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req_ctx->in_sg,
+				   req->dst, ctx->key_size - 1, req->dst_len);
+
 	err = crypto_akcipher_encrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -380,18 +365,7 @@ static int pkcs1pad_decrypt(struct akcipher_request *req)
 	if (!ctx->key_size || req->src_len != ctx->key_size)
 		return -EINVAL;
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/* Reuse input buffer, output to a new buffer */
-	req_ctx->child_req.src = req->src;
-	req_ctx->child_req.src_len = req->src_len;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size ;
-
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
 
@@ -402,6 +376,11 @@ static int pkcs1pad_decrypt(struct akcipher_request *req)
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_decrypt_complete_cb, req);
 
+	/* Reuse input buffer, output to a new buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req->src,
+				   req_ctx->out_sg, req->src_len,
+				   ctx->key_size);
+
 	err = crypto_akcipher_decrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -416,20 +395,16 @@ static int pkcs1pad_sign(struct akcipher_request *req)
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
-	const struct rsa_asn1_template *digest_info = NULL;
+	struct akcipher_instance *inst = akcipher_alg_instance(tfm);
+	struct pkcs1pad_inst_ctx *ictx = akcipher_instance_ctx(inst);
+	const struct rsa_asn1_template *digest_info = ictx->digest_info;
 	int err;
 	unsigned int ps_end, digest_size = 0;
 
 	if (!ctx->key_size)
 		return -EINVAL;
 
-	if (ctx->hash_name) {
-		digest_info = rsa_lookup_asn1(ctx->hash_name);
-		if (!digest_info)
-			return -EINVAL;
-
-		digest_size = digest_info->size;
-	}
+	digest_size = digest_info->size;
 
 	if (req->src_len + digest_size > ctx->key_size - 11)
 		return -EOVERFLOW;
@@ -439,21 +414,8 @@ static int pkcs1pad_sign(struct akcipher_request *req)
 		return -EOVERFLOW;
 	}
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/*
-	 * Replace both input and output to add the padding in the input and
-	 * the potential missing leading zeros in the output.
-	 */
-	req_ctx->child_req.src = req_ctx->in_sg;
-	req_ctx->child_req.src_len = ctx->key_size - 1;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
 	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!req_ctx->in_buf)
 		return -ENOMEM;
 
@@ -462,29 +424,20 @@ static int pkcs1pad_sign(struct akcipher_request *req)
 	memset(req_ctx->in_buf + 1, 0xff, ps_end - 1);
 	req_ctx->in_buf[ps_end] = 0x00;
 
-	if (digest_info) {
-		memcpy(req_ctx->in_buf + ps_end + 1, digest_info->data,
-		       digest_info->size);
-	}
+	memcpy(req_ctx->in_buf + ps_end + 1, digest_info->data,
+	       digest_info->size);
 
 	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
 			ctx->key_size - 1 - req->src_len, req->src);
 
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
-	if (!req_ctx->out_buf) {
-		kfree(req_ctx->in_buf);
-		return -ENOMEM;
-	}
-
-	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
-			ctx->key_size, NULL);
-
 	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_encrypt_sign_complete_cb, req);
 
+	/* Reuse output buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req_ctx->in_sg,
+				   req->dst, ctx->key_size - 1, req->dst_len);
+
 	err = crypto_akcipher_sign(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -499,56 +452,58 @@ static int pkcs1pad_verify_complete(struct akcipher_request *req, int err)
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
-	const struct rsa_asn1_template *digest_info;
+	struct akcipher_instance *inst = akcipher_alg_instance(tfm);
+	struct pkcs1pad_inst_ctx *ictx = akcipher_instance_ctx(inst);
+	const struct rsa_asn1_template *digest_info = ictx->digest_info;
+	unsigned int dst_len;
 	unsigned int pos;
-
-	if (err == -EOVERFLOW)
-		/* Decrypted value had no leading 0 byte */
-		err = -EINVAL;
+	u8 *out_buf;
 
 	if (err)
 		goto done;
 
-	if (req_ctx->child_req.dst_len != ctx->key_size - 1) {
-		err = -EINVAL;
+	err = -EINVAL;
+	dst_len = req_ctx->child_req.dst_len;
+	if (dst_len < ctx->key_size - 1)
 		goto done;
+
+	out_buf = req_ctx->out_buf;
+	if (dst_len == ctx->key_size) {
+		if (out_buf[0] != 0x00)
+			/* Decrypted value had no leading 0 byte */
+			goto done;
+
+		dst_len--;
+		out_buf++;
 	}
 
 	err = -EBADMSG;
-	if (req_ctx->out_buf[0] != 0x01)
+	if (out_buf[0] != 0x01)
 		goto done;
 
-	for (pos = 1; pos < req_ctx->child_req.dst_len; pos++)
-		if (req_ctx->out_buf[pos] != 0xff)
+	for (pos = 1; pos < dst_len; pos++)
+		if (out_buf[pos] != 0xff)
 			break;
 
-	if (pos < 9 || pos == req_ctx->child_req.dst_len ||
-	    req_ctx->out_buf[pos] != 0x00)
+	if (pos < 9 || pos == dst_len || out_buf[pos] != 0x00)
 		goto done;
 	pos++;
 
-	if (ctx->hash_name) {
-		digest_info = rsa_lookup_asn1(ctx->hash_name);
-		if (!digest_info)
-			goto done;
-
-		if (memcmp(req_ctx->out_buf + pos, digest_info->data,
-			   digest_info->size))
-			goto done;
+	if (memcmp(out_buf + pos, digest_info->data, digest_info->size))
+		goto done;
 
-		pos += digest_info->size;
-	}
+	pos += digest_info->size;
 
 	err = 0;
 
-	if (req->dst_len < req_ctx->child_req.dst_len - pos)
+	if (req->dst_len < dst_len - pos)
 		err = -EOVERFLOW;
-	req->dst_len = req_ctx->child_req.dst_len - pos;
+	req->dst_len = dst_len - pos;
 
 	if (!err)
 		sg_copy_from_buffer(req->dst,
 				sg_nents_for_len(req->dst, req->dst_len),
-				req_ctx->out_buf + pos, req->dst_len);
+				out_buf + pos, req->dst_len);
 done:
 	kzfree(req_ctx->out_buf);
 
@@ -588,18 +543,7 @@ static int pkcs1pad_verify(struct akcipher_request *req)
 	if (!ctx->key_size || req->src_len < ctx->key_size)
 		return -EINVAL;
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/* Reuse input buffer, output to a new buffer */
-	req_ctx->child_req.src = req->src;
-	req_ctx->child_req.src_len = req->src_len;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
 
@@ -610,6 +554,11 @@ static int pkcs1pad_verify(struct akcipher_request *req)
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_verify_complete_cb, req);
 
+	/* Reuse input buffer, output to a new buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req->src,
+				   req_ctx->out_sg, req->src_len,
+				   ctx->key_size);
+
 	err = crypto_akcipher_verify(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -626,12 +575,11 @@ static int pkcs1pad_init_tfm(struct crypto_akcipher *tfm)
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct crypto_akcipher *child_tfm;
 
-	child_tfm = crypto_spawn_akcipher(akcipher_instance_ctx(inst));
+	child_tfm = crypto_spawn_akcipher(&ictx->spawn);
 	if (IS_ERR(child_tfm))
 		return PTR_ERR(child_tfm);
 
 	ctx->child = child_tfm;
-	ctx->hash_name = ictx->hash_name;
 	return 0;
 }
 
@@ -648,12 +596,12 @@ static void pkcs1pad_free(struct akcipher_instance *inst)
 	struct crypto_akcipher_spawn *spawn = &ctx->spawn;
 
 	crypto_drop_akcipher(spawn);
-	kfree(ctx->hash_name);
 	kfree(inst);
 }
 
 static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
+	const struct rsa_asn1_template *digest_info;
 	struct crypto_attr_type *algt;
 	struct akcipher_instance *inst;
 	struct pkcs1pad_inst_ctx *ctx;
@@ -676,7 +624,11 @@ static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	hash_name = crypto_attr_alg_name(tb[2]);
 	if (IS_ERR(hash_name))
-		hash_name = NULL;
+		return PTR_ERR(hash_name);
+
+	digest_info = rsa_lookup_asn1(hash_name);
+	if (!digest_info)
+		return -EINVAL;
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
 	if (!inst)
@@ -684,7 +636,7 @@ static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	ctx = akcipher_instance_ctx(inst);
 	spawn = &ctx->spawn;
-	ctx->hash_name = hash_name ? kstrdup(hash_name, GFP_KERNEL) : NULL;
+	ctx->digest_info = digest_info;
 
 	crypto_set_spawn(&spawn->base, akcipher_crypto_instance(inst));
 	err = crypto_grab_akcipher(spawn, rsa_alg_name, 0,
@@ -696,27 +648,14 @@ static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	err = -ENAMETOOLONG;
 
-	if (!hash_name) {
-		if (snprintf(inst->alg.base.cra_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)",
-			     rsa_alg->base.cra_name) >=
-					CRYPTO_MAX_ALG_NAME ||
-		    snprintf(inst->alg.base.cra_driver_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)",
-			     rsa_alg->base.cra_driver_name) >=
-					CRYPTO_MAX_ALG_NAME)
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "pkcs1pad(%s,%s)", rsa_alg->base.cra_name, hash_name) >=
+	    CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "pkcs1pad(%s,%s)",
+		     rsa_alg->base.cra_driver_name, hash_name) >=
+	    CRYPTO_MAX_ALG_NAME)
 		goto out_drop_alg;
-	} else {
-		if (snprintf(inst->alg.base.cra_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s,%s)",
-			     rsa_alg->base.cra_name, hash_name) >=
-				CRYPTO_MAX_ALG_NAME ||
-		    snprintf(inst->alg.base.cra_driver_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s,%s)",
-			     rsa_alg->base.cra_driver_name, hash_name) >=
-					CRYPTO_MAX_ALG_NAME)
-		goto out_free_hash;
-	}
 
 	inst->alg.base.cra_flags = rsa_alg->base.cra_flags & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = rsa_alg->base.cra_priority;
@@ -738,12 +677,10 @@ static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	err = akcipher_register_instance(tmpl, inst);
 	if (err)
-		goto out_free_hash;
+		goto out_drop_alg;
 
 	return 0;
 
-out_free_hash:
-	kfree(ctx->hash_name);
 out_drop_alg:
 	crypto_drop_akcipher(spawn);
 out_free_inst:
diff --git a/crypto/rsa.c b/crypto/rsa.c
index 77d737f52147..4c280b6a3ea9 100644
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -10,16 +10,23 @@
  */
 
 #include <linux/module.h>
+#include <linux/mpi.h>
 #include <crypto/internal/rsa.h>
 #include <crypto/internal/akcipher.h>
 #include <crypto/akcipher.h>
 #include <crypto/algapi.h>
 
+struct rsa_mpi_key {
+	MPI n;
+	MPI e;
+	MPI d;
+};
+
 /*
  * RSAEP function [RFC3447 sec 5.1.1]
  * c = m^e mod n;
  */
-static int _rsa_enc(const struct rsa_key *key, MPI c, MPI m)
+static int _rsa_enc(const struct rsa_mpi_key *key, MPI c, MPI m)
 {
 	/* (1) Validate 0 <= m < n */
 	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
@@ -33,7 +40,7 @@ static int _rsa_enc(const struct rsa_key *key, MPI c, MPI m)
  * RSADP function [RFC3447 sec 5.1.2]
  * m = c^d mod n;
  */
-static int _rsa_dec(const struct rsa_key *key, MPI m, MPI c)
+static int _rsa_dec(const struct rsa_mpi_key *key, MPI m, MPI c)
 {
 	/* (1) Validate 0 <= c < n */
 	if (mpi_cmp_ui(c, 0) < 0 || mpi_cmp(c, key->n) >= 0)
@@ -47,7 +54,7 @@ static int _rsa_dec(const struct rsa_key *key, MPI m, MPI c)
  * RSASP1 function [RFC3447 sec 5.2.1]
  * s = m^d mod n
  */
-static int _rsa_sign(const struct rsa_key *key, MPI s, MPI m)
+static int _rsa_sign(const struct rsa_mpi_key *key, MPI s, MPI m)
 {
 	/* (1) Validate 0 <= m < n */
 	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
@@ -61,7 +68,7 @@ static int _rsa_sign(const struct rsa_key *key, MPI s, MPI m)
  * RSAVP1 function [RFC3447 sec 5.2.2]
  * m = s^e mod n;
  */
-static int _rsa_verify(const struct rsa_key *key, MPI m, MPI s)
+static int _rsa_verify(const struct rsa_mpi_key *key, MPI m, MPI s)
 {
 	/* (1) Validate 0 <= s < n */
 	if (mpi_cmp_ui(s, 0) < 0 || mpi_cmp(s, key->n) >= 0)
@@ -71,7 +78,7 @@ static int _rsa_verify(const struct rsa_key *key, MPI m, MPI s)
 	return mpi_powm(m, s, key->e, key->n);
 }
 
-static inline struct rsa_key *rsa_get_key(struct crypto_akcipher *tfm)
+static inline struct rsa_mpi_key *rsa_get_key(struct crypto_akcipher *tfm)
 {
 	return akcipher_tfm_ctx(tfm);
 }
@@ -79,7 +86,7 @@ static inline struct rsa_key *rsa_get_key(struct crypto_akcipher *tfm)
 static int rsa_enc(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI m, c = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -101,7 +108,7 @@ static int rsa_enc(struct akcipher_request *req)
 	if (ret)
 		goto err_free_m;
 
-	ret = mpi_write_to_sgl(c, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(c, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_m;
 
@@ -118,7 +125,7 @@ err_free_c:
 static int rsa_dec(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI c, m = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -140,7 +147,7 @@ static int rsa_dec(struct akcipher_request *req)
 	if (ret)
 		goto err_free_c;
 
-	ret = mpi_write_to_sgl(m, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(m, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_c;
 
@@ -156,7 +163,7 @@ err_free_m:
 static int rsa_sign(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI m, s = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -178,7 +185,7 @@ static int rsa_sign(struct akcipher_request *req)
 	if (ret)
 		goto err_free_m;
 
-	ret = mpi_write_to_sgl(s, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(s, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_m;
 
@@ -195,7 +202,7 @@ err_free_s:
 static int rsa_verify(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI s, m = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -219,7 +226,7 @@ static int rsa_verify(struct akcipher_request *req)
 	if (ret)
 		goto err_free_s;
 
-	ret = mpi_write_to_sgl(m, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(m, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_s;
 
@@ -233,6 +240,16 @@ err_free_m:
 	return ret;
 }
 
+static void rsa_free_mpi_key(struct rsa_mpi_key *key)
+{
+	mpi_free(key->d);
+	mpi_free(key->e);
+	mpi_free(key->n);
+	key->d = NULL;
+	key->e = NULL;
+	key->n = NULL;
+}
+
 static int rsa_check_key_length(unsigned int len)
 {
 	switch (len) {
@@ -251,49 +268,87 @@ static int rsa_check_key_length(unsigned int len)
 static int rsa_set_pub_key(struct crypto_akcipher *tfm, const void *key,
 			   unsigned int keylen)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *mpi_key = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
 	int ret;
 
-	ret = rsa_parse_pub_key(pkey, key, keylen);
+	/* Free the old MPI key if any */
+	rsa_free_mpi_key(mpi_key);
+
+	ret = rsa_parse_pub_key(&raw_key, key, keylen);
 	if (ret)
 		return ret;
 
-	if (rsa_check_key_length(mpi_get_size(pkey->n) << 3)) {
-		rsa_free_key(pkey);
-		ret = -EINVAL;
+	mpi_key->e = mpi_read_raw_data(raw_key.e, raw_key.e_sz);
+	if (!mpi_key->e)
+		goto err;
+
+	mpi_key->n = mpi_read_raw_data(raw_key.n, raw_key.n_sz);
+	if (!mpi_key->n)
+		goto err;
+
+	if (rsa_check_key_length(mpi_get_size(mpi_key->n) << 3)) {
+		rsa_free_mpi_key(mpi_key);
+		return -EINVAL;
 	}
-	return ret;
+
+	return 0;
+
+err:
+	rsa_free_mpi_key(mpi_key);
+	return -ENOMEM;
 }
 
 static int rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key,
 			    unsigned int keylen)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *mpi_key = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
 	int ret;
 
-	ret = rsa_parse_priv_key(pkey, key, keylen);
+	/* Free the old MPI key if any */
+	rsa_free_mpi_key(mpi_key);
+
+	ret = rsa_parse_priv_key(&raw_key, key, keylen);
 	if (ret)
 		return ret;
 
-	if (rsa_check_key_length(mpi_get_size(pkey->n) << 3)) {
-		rsa_free_key(pkey);
-		ret = -EINVAL;
+	mpi_key->d = mpi_read_raw_data(raw_key.d, raw_key.d_sz);
+	if (!mpi_key->d)
+		goto err;
+
+	mpi_key->e = mpi_read_raw_data(raw_key.e, raw_key.e_sz);
+	if (!mpi_key->e)
+		goto err;
+
+	mpi_key->n = mpi_read_raw_data(raw_key.n, raw_key.n_sz);
+	if (!mpi_key->n)
+		goto err;
+
+	if (rsa_check_key_length(mpi_get_size(mpi_key->n) << 3)) {
+		rsa_free_mpi_key(mpi_key);
+		return -EINVAL;
 	}
-	return ret;
+
+	return 0;
+
+err:
+	rsa_free_mpi_key(mpi_key);
+	return -ENOMEM;
 }
 
 static int rsa_max_size(struct crypto_akcipher *tfm)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *pkey = akcipher_tfm_ctx(tfm);
 
 	return pkey->n ? mpi_get_size(pkey->n) : -EINVAL;
 }
 
 static void rsa_exit_tfm(struct crypto_akcipher *tfm)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *pkey = akcipher_tfm_ctx(tfm);
 
-	rsa_free_key(pkey);
+	rsa_free_mpi_key(pkey);
 }
 
 static struct akcipher_alg rsa = {
@@ -310,7 +365,7 @@ static struct akcipher_alg rsa = {
 		.cra_driver_name = "rsa-generic",
 		.cra_priority = 100,
 		.cra_module = THIS_MODULE,
-		.cra_ctxsize = sizeof(struct rsa_key),
+		.cra_ctxsize = sizeof(struct rsa_mpi_key),
 	},
 };
 
diff --git a/crypto/rsa_helper.c b/crypto/rsa_helper.c
index d226f48d0907..4df6451e7543 100644
--- a/crypto/rsa_helper.c
+++ b/crypto/rsa_helper.c
@@ -22,20 +22,29 @@ int rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
 	      const void *value, size_t vlen)
 {
 	struct rsa_key *key = context;
+	const u8 *ptr = value;
+	size_t n_sz = vlen;
 
-	key->n = mpi_read_raw_data(value, vlen);
-
-	if (!key->n)
-		return -ENOMEM;
-
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (mpi_get_size(key->n) != 256 &&
-			     mpi_get_size(key->n) != 384)) {
-		pr_err("RSA: key size not allowed in FIPS mode\n");
-		mpi_free(key->n);
-		key->n = NULL;
+	/* invalid key provided */
+	if (!value || !vlen)
 		return -EINVAL;
+
+	if (fips_enabled) {
+		while (!*ptr && n_sz) {
+			ptr++;
+			n_sz--;
+		}
+
+		/* In FIPS mode only allow key size 2K & 3K */
+		if (n_sz != 256 && n_sz != 384) {
+			pr_err("RSA: key size not allowed in FIPS mode\n");
+			return -EINVAL;
+		}
 	}
+
+	key->n = value;
+	key->n_sz = vlen;
+
 	return 0;
 }
 
@@ -44,10 +53,12 @@ int rsa_get_e(void *context, size_t hdrlen, unsigned char tag,
 {
 	struct rsa_key *key = context;
 
-	key->e = mpi_read_raw_data(value, vlen);
+	/* invalid key provided */
+	if (!value || !key->n_sz || !vlen || vlen > key->n_sz)
+		return -EINVAL;
 
-	if (!key->e)
-		return -ENOMEM;
+	key->e = value;
+	key->e_sz = vlen;
 
 	return 0;
 }
@@ -57,46 +68,95 @@ int rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
 {
 	struct rsa_key *key = context;
 
-	key->d = mpi_read_raw_data(value, vlen);
+	/* invalid key provided */
+	if (!value || !key->n_sz || !vlen || vlen > key->n_sz)
+		return -EINVAL;
 
-	if (!key->d)
-		return -ENOMEM;
+	key->d = value;
+	key->d_sz = vlen;
 
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (mpi_get_size(key->d) != 256 &&
-			     mpi_get_size(key->d) != 384)) {
-		pr_err("RSA: key size not allowed in FIPS mode\n");
-		mpi_free(key->d);
-		key->d = NULL;
+	return 0;
+}
+
+int rsa_get_p(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
 		return -EINVAL;
-	}
+
+	key->p = value;
+	key->p_sz = vlen;
+
 	return 0;
 }
 
-static void free_mpis(struct rsa_key *key)
+int rsa_get_q(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
 {
-	mpi_free(key->n);
-	mpi_free(key->e);
-	mpi_free(key->d);
-	key->n = NULL;
-	key->e = NULL;
-	key->d = NULL;
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->q = value;
+	key->q_sz = vlen;
+
+	return 0;
 }
 
-/**
- * rsa_free_key() - frees rsa key allocated by rsa_parse_key()
- *
- * @rsa_key:	struct rsa_key key representation
- */
-void rsa_free_key(struct rsa_key *key)
+int rsa_get_dp(void *context, size_t hdrlen, unsigned char tag,
+	       const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->dp = value;
+	key->dp_sz = vlen;
+
+	return 0;
+}
+
+int rsa_get_dq(void *context, size_t hdrlen, unsigned char tag,
+	       const void *value, size_t vlen)
 {
-	free_mpis(key);
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->dq = value;
+	key->dq_sz = vlen;
+
+	return 0;
+}
+
+int rsa_get_qinv(void *context, size_t hdrlen, unsigned char tag,
+		 const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->qinv = value;
+	key->qinv_sz = vlen;
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(rsa_free_key);
 
 /**
- * rsa_parse_pub_key() - extracts an rsa public key from BER encoded buffer
- *			 and stores it in the provided struct rsa_key
+ * rsa_parse_pub_key() - decodes the BER encoded buffer and stores in the
+ *                       provided struct rsa_key, pointers to the raw key as is,
+ *                       so that the caller can copy it or MPI parse it, etc.
  *
  * @rsa_key:	struct rsa_key key representation
  * @key:	key in BER format
@@ -107,23 +167,15 @@ EXPORT_SYMBOL_GPL(rsa_free_key);
 int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key,
 		      unsigned int key_len)
 {
-	int ret;
-
-	free_mpis(rsa_key);
-	ret = asn1_ber_decoder(&rsapubkey_decoder, rsa_key, key, key_len);
-	if (ret < 0)
-		goto error;
-
-	return 0;
-error:
-	free_mpis(rsa_key);
-	return ret;
+	return asn1_ber_decoder(&rsapubkey_decoder, rsa_key, key, key_len);
 }
 EXPORT_SYMBOL_GPL(rsa_parse_pub_key);
 
 /**
- * rsa_parse_pub_key() - extracts an rsa private key from BER encoded buffer
- *			 and stores it in the provided struct rsa_key
+ * rsa_parse_priv_key() - decodes the BER encoded buffer and stores in the
+ *                        provided struct rsa_key, pointers to the raw key
+ *                        as is, so that the caller can copy it or MPI parse it,
+ *                        etc.
  *
  * @rsa_key:	struct rsa_key key representation
  * @key:	key in BER format
@@ -134,16 +186,6 @@ EXPORT_SYMBOL_GPL(rsa_parse_pub_key);
 int rsa_parse_priv_key(struct rsa_key *rsa_key, const void *key,
 		       unsigned int key_len)
 {
-	int ret;
-
-	free_mpis(rsa_key);
-	ret = asn1_ber_decoder(&rsaprivkey_decoder, rsa_key, key, key_len);
-	if (ret < 0)
-		goto error;
-
-	return 0;
-error:
-	free_mpis(rsa_key);
-	return ret;
+	return asn1_ber_decoder(&rsaprivkey_decoder, rsa_key, key, key_len);
 }
 EXPORT_SYMBOL_GPL(rsa_parse_priv_key);
diff --git a/crypto/rsaprivkey.asn1 b/crypto/rsaprivkey.asn1
index 731aea5edb0c..4ce06758e8af 100644
--- a/crypto/rsaprivkey.asn1
+++ b/crypto/rsaprivkey.asn1
@@ -3,9 +3,9 @@ RsaPrivKey ::= SEQUENCE {
 	n		INTEGER ({ rsa_get_n }),
 	e		INTEGER ({ rsa_get_e }),
 	d		INTEGER ({ rsa_get_d }),
-	prime1		INTEGER,
-	prime2		INTEGER,
-	exponent1	INTEGER,
-	exponent2	INTEGER,
-	coefficient	INTEGER
+	prime1		INTEGER ({ rsa_get_p }),
+	prime2		INTEGER ({ rsa_get_q }),
+	exponent1	INTEGER ({ rsa_get_dp }),
+	exponent2	INTEGER ({ rsa_get_dq }),
+	coefficient	INTEGER ({ rsa_get_qinv })
 }
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index ea5815c5e128..52ce17a3dd63 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -18,8 +18,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/pagemap.h>
-#include <linux/highmem.h>
 #include <linux/scatterlist.h>
 
 static inline void memcpy_dir(void *buf, void *sgdata, size_t nbytes, int out)
@@ -30,53 +28,6 @@ static inline void memcpy_dir(void *buf, void *sgdata, size_t nbytes, int out)
 	memcpy(dst, src, nbytes);
 }
 
-void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg)
-{
-	walk->sg = sg;
-
-	BUG_ON(!sg->length);
-
-	walk->offset = sg->offset;
-}
-EXPORT_SYMBOL_GPL(scatterwalk_start);
-
-void *scatterwalk_map(struct scatter_walk *walk)
-{
-	return kmap_atomic(scatterwalk_page(walk)) +
-	       offset_in_page(walk->offset);
-}
-EXPORT_SYMBOL_GPL(scatterwalk_map);
-
-static void scatterwalk_pagedone(struct scatter_walk *walk, int out,
-				 unsigned int more)
-{
-	if (out) {
-		struct page *page;
-
-		page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT);
-		/* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as
-		 * PageSlab cannot be optimised away per se due to
-		 * use of volatile pointer.
-		 */
-		if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page))
-			flush_dcache_page(page);
-	}
-
-	if (more) {
-		walk->offset += PAGE_SIZE - 1;
-		walk->offset &= PAGE_MASK;
-		if (walk->offset >= walk->sg->offset + walk->sg->length)
-			scatterwalk_start(walk, sg_next(walk->sg));
-	}
-}
-
-void scatterwalk_done(struct scatter_walk *walk, int out, int more)
-{
-	if (!(scatterwalk_pagelen(walk) & (PAGE_SIZE - 1)) || !more)
-		scatterwalk_pagedone(walk, out, more);
-}
-EXPORT_SYMBOL_GPL(scatterwalk_done);
-
 void scatterwalk_copychunks(void *buf, struct scatter_walk *walk,
 			    size_t nbytes, int out)
 {
@@ -87,9 +38,11 @@ void scatterwalk_copychunks(void *buf, struct scatter_walk *walk,
 		if (len_this_page > nbytes)
 			len_this_page = nbytes;
 
-		vaddr = scatterwalk_map(walk);
-		memcpy_dir(buf, vaddr, len_this_page, out);
-		scatterwalk_unmap(vaddr);
+		if (out != 2) {
+			vaddr = scatterwalk_map(walk);
+			memcpy_dir(buf, vaddr, len_this_page, out);
+			scatterwalk_unmap(vaddr);
+		}
 
 		scatterwalk_advance(walk, len_this_page);
 
@@ -99,7 +52,7 @@ void scatterwalk_copychunks(void *buf, struct scatter_walk *walk,
 		buf += len_this_page;
 		nbytes -= len_this_page;
 
-		scatterwalk_pagedone(walk, out, 1);
+		scatterwalk_pagedone(walk, out & 1, 1);
 	}
 }
 EXPORT_SYMBOL_GPL(scatterwalk_copychunks);
@@ -125,28 +78,6 @@ void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 }
 EXPORT_SYMBOL_GPL(scatterwalk_map_and_copy);
 
-int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes)
-{
-	int offset = 0, n = 0;
-
-	/* num_bytes is too small */
-	if (num_bytes < sg->length)
-		return -1;
-
-	do {
-		offset += sg->length;
-		n++;
-		sg = sg_next(sg);
-
-		/* num_bytes is too large */
-		if (unlikely(!sg && (num_bytes < offset)))
-			return -1;
-	} while (sg && (num_bytes > offset));
-
-	return n;
-}
-EXPORT_SYMBOL_GPL(scatterwalk_bytes_sglen);
-
 struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
 				     struct scatterlist *src,
 				     unsigned int len)
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index 15a749a5cab7..c7049231861f 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -14,50 +14,17 @@
  */
 
 #include <crypto/internal/geniv.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/rng.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/string.h>
 
-struct seqiv_ctx {
-	spinlock_t lock;
-	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
-};
-
 static void seqiv_free(struct crypto_instance *inst);
 
-static void seqiv_complete2(struct skcipher_givcrypt_request *req, int err)
-{
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	struct crypto_ablkcipher *geniv;
-
-	if (err == -EINPROGRESS)
-		return;
-
-	if (err)
-		goto out;
-
-	geniv = skcipher_givcrypt_reqtfm(req);
-	memcpy(req->creq.info, subreq->info, crypto_ablkcipher_ivsize(geniv));
-
-out:
-	kfree(subreq->info);
-}
-
-static void seqiv_complete(struct crypto_async_request *base, int err)
-{
-	struct skcipher_givcrypt_request *req = base->data;
-
-	seqiv_complete2(req, err);
-	skcipher_givcrypt_complete(req, err);
-}
-
 static void seqiv_aead_encrypt_complete2(struct aead_request *req, int err)
 {
 	struct aead_request *subreq = aead_request_ctx(req);
@@ -85,65 +52,6 @@ static void seqiv_aead_encrypt_complete(struct crypto_async_request *base,
 	aead_request_complete(req, err);
 }
 
-static void seqiv_geniv(struct seqiv_ctx *ctx, u8 *info, u64 seq,
-			unsigned int ivsize)
-{
-	unsigned int len = ivsize;
-
-	if (ivsize > sizeof(u64)) {
-		memset(info, 0, ivsize - sizeof(u64));
-		len = sizeof(u64);
-	}
-	seq = cpu_to_be64(seq);
-	memcpy(info + ivsize - len, &seq, len);
-	crypto_xor(info, ctx->salt, ivsize);
-}
-
-static int seqiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	crypto_completion_t compl;
-	void *data;
-	u8 *info;
-	unsigned int ivsize;
-	int err;
-
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-
-	compl = req->creq.base.complete;
-	data = req->creq.base.data;
-	info = req->creq.info;
-
-	ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	if (unlikely(!IS_ALIGNED((unsigned long)info,
-				 crypto_ablkcipher_alignmask(geniv) + 1))) {
-		info = kmalloc(ivsize, req->creq.base.flags &
-				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
-								  GFP_ATOMIC);
-		if (!info)
-			return -ENOMEM;
-
-		compl = seqiv_complete;
-		data = req;
-	}
-
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags, compl,
-					data);
-	ablkcipher_request_set_crypt(subreq, req->creq.src, req->creq.dst,
-				     req->creq.nbytes, info);
-
-	seqiv_geniv(ctx, info, req->seq, ivsize);
-	memcpy(req->giv, info, ivsize);
-
-	err = crypto_ablkcipher_encrypt(subreq);
-	if (unlikely(info != req->creq.info))
-		seqiv_complete2(req, err);
-	return err;
-}
-
 static int seqiv_aead_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
@@ -165,12 +73,16 @@ static int seqiv_aead_encrypt(struct aead_request *req)
 	info = req->iv;
 
 	if (req->src != req->dst) {
-		struct blkcipher_desc desc = {
-			.tfm = ctx->null,
-		};
+		SKCIPHER_REQUEST_ON_STACK(nreq, ctx->sknull);
+
+		skcipher_request_set_tfm(nreq, ctx->sknull);
+		skcipher_request_set_callback(nreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(nreq, req->src, req->dst,
+					   req->assoclen + req->cryptlen,
+					   NULL);
 
-		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
-					       req->assoclen + req->cryptlen);
+		err = crypto_skcipher_encrypt(nreq);
 		if (err)
 			return err;
 	}
@@ -229,62 +141,6 @@ static int seqiv_aead_decrypt(struct aead_request *req)
 	return crypto_aead_decrypt(subreq);
 }
 
-static int seqiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err;
-
-	spin_lock_init(&ctx->lock);
-
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
-
-	err = 0;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt = seqiv_givencrypt;
-		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-					   crypto_ablkcipher_ivsize(geniv));
-		crypto_put_default_rng();
-	}
-
-	return err ?: skcipher_geniv_init(tfm);
-}
-
-static int seqiv_ablkcipher_create(struct crypto_template *tmpl,
-				   struct rtattr **tb)
-{
-	struct crypto_instance *inst;
-	int err;
-
-	inst = skcipher_geniv_alloc(tmpl, tb, 0, 0);
-
-	if (IS_ERR(inst))
-		return PTR_ERR(inst);
-
-	err = -EINVAL;
-	if (inst->alg.cra_ablkcipher.ivsize < sizeof(u64))
-		goto free_inst;
-
-	inst->alg.cra_init = seqiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
-
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
-	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
-
-	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
-
-	err = crypto_register_instance(tmpl, inst);
-	if (err)
-		goto free_inst;
-
-out:
-	return err;
-
-free_inst:
-	skcipher_geniv_free(inst);
-	goto out;
-}
-
 static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct aead_instance *inst;
@@ -330,26 +186,20 @@ free_inst:
 static int seqiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
 		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
-		err = seqiv_ablkcipher_create(tmpl, tb);
-	else
-		err = seqiv_aead_create(tmpl, tb);
+		return -EINVAL;
 
-	return err;
+	return seqiv_aead_create(tmpl, tb);
 }
 
 static void seqiv_free(struct crypto_instance *inst)
 {
-	if ((inst->alg.cra_flags ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
-		skcipher_geniv_free(inst);
-	else
-		aead_geniv_free(aead_instance(inst));
+	aead_geniv_free(aead_instance(inst));
 }
 
 static struct crypto_template seqiv_tmpl = {
diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
new file mode 100644
index 000000000000..62264397a2d2
--- /dev/null
+++ b/crypto/sha3_generic.c
@@ -0,0 +1,300 @@
+/*
+ * Cryptographic API.
+ *
+ * SHA-3, as specified in
+ * http://nvlpubs.nist.gov/nistpubs/FIPS/NIST.FIPS.202.pdf
+ *
+ * SHA-3 code by Jeff Garzik <jeff@garzik.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)•
+ * any later version.
+ *
+ */
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/sha3.h>
+#include <asm/byteorder.h>
+
+#define KECCAK_ROUNDS 24
+
+#define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y))))
+
+static const u64 keccakf_rndc[24] = {
+	0x0000000000000001, 0x0000000000008082, 0x800000000000808a,
+	0x8000000080008000, 0x000000000000808b, 0x0000000080000001,
+	0x8000000080008081, 0x8000000000008009, 0x000000000000008a,
+	0x0000000000000088, 0x0000000080008009, 0x000000008000000a,
+	0x000000008000808b, 0x800000000000008b, 0x8000000000008089,
+	0x8000000000008003, 0x8000000000008002, 0x8000000000000080,
+	0x000000000000800a, 0x800000008000000a, 0x8000000080008081,
+	0x8000000000008080, 0x0000000080000001, 0x8000000080008008
+};
+
+static const int keccakf_rotc[24] = {
+	1,  3,  6,  10, 15, 21, 28, 36, 45, 55, 2,  14,
+	27, 41, 56, 8,  25, 43, 62, 18, 39, 61, 20, 44
+};
+
+static const int keccakf_piln[24] = {
+	10, 7,  11, 17, 18, 3, 5,  16, 8,  21, 24, 4,
+	15, 23, 19, 13, 12, 2, 20, 14, 22, 9,  6,  1
+};
+
+/* update the state with given number of rounds */
+
+static void keccakf(u64 st[25])
+{
+	int i, j, round;
+	u64 t, bc[5];
+
+	for (round = 0; round < KECCAK_ROUNDS; round++) {
+
+		/* Theta */
+		for (i = 0; i < 5; i++)
+			bc[i] = st[i] ^ st[i + 5] ^ st[i + 10] ^ st[i + 15]
+				^ st[i + 20];
+
+		for (i = 0; i < 5; i++) {
+			t = bc[(i + 4) % 5] ^ ROTL64(bc[(i + 1) % 5], 1);
+			for (j = 0; j < 25; j += 5)
+				st[j + i] ^= t;
+		}
+
+		/* Rho Pi */
+		t = st[1];
+		for (i = 0; i < 24; i++) {
+			j = keccakf_piln[i];
+			bc[0] = st[j];
+			st[j] = ROTL64(t, keccakf_rotc[i]);
+			t = bc[0];
+		}
+
+		/* Chi */
+		for (j = 0; j < 25; j += 5) {
+			for (i = 0; i < 5; i++)
+				bc[i] = st[j + i];
+			for (i = 0; i < 5; i++)
+				st[j + i] ^= (~bc[(i + 1) % 5]) &
+					     bc[(i + 2) % 5];
+		}
+
+		/* Iota */
+		st[0] ^= keccakf_rndc[round];
+	}
+}
+
+static void sha3_init(struct sha3_state *sctx, unsigned int digest_sz)
+{
+	memset(sctx, 0, sizeof(*sctx));
+	sctx->md_len = digest_sz;
+	sctx->rsiz = 200 - 2 * digest_sz;
+	sctx->rsizw = sctx->rsiz / 8;
+}
+
+static int sha3_224_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_224_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_256_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_256_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_384_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_384_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_512_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_512_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int done;
+	const u8 *src;
+
+	done = 0;
+	src = data;
+
+	if ((sctx->partial + len) > (sctx->rsiz - 1)) {
+		if (sctx->partial) {
+			done = -sctx->partial;
+			memcpy(sctx->buf + sctx->partial, data,
+			       done + sctx->rsiz);
+			src = sctx->buf;
+		}
+
+		do {
+			unsigned int i;
+
+			for (i = 0; i < sctx->rsizw; i++)
+				sctx->st[i] ^= ((u64 *) src)[i];
+			keccakf(sctx->st);
+
+			done += sctx->rsiz;
+			src = data + done;
+		} while (done + (sctx->rsiz - 1) < len);
+
+		sctx->partial = 0;
+	}
+	memcpy(sctx->buf + sctx->partial, src, len - done);
+	sctx->partial += (len - done);
+
+	return 0;
+}
+
+static int sha3_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, inlen = sctx->partial;
+
+	sctx->buf[inlen++] = 0x06;
+	memset(sctx->buf + inlen, 0, sctx->rsiz - inlen);
+	sctx->buf[sctx->rsiz - 1] |= 0x80;
+
+	for (i = 0; i < sctx->rsizw; i++)
+		sctx->st[i] ^= ((u64 *) sctx->buf)[i];
+
+	keccakf(sctx->st);
+
+	for (i = 0; i < sctx->rsizw; i++)
+		sctx->st[i] = cpu_to_le64(sctx->st[i]);
+
+	memcpy(out, sctx->st, sctx->md_len);
+
+	memset(sctx, 0, sizeof(*sctx));
+	return 0;
+}
+
+static struct shash_alg sha3_224 = {
+	.digestsize	=	SHA3_224_DIGEST_SIZE,
+	.init		=	sha3_224_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-224",
+		.cra_driver_name =	"sha3-224-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_224_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static struct shash_alg sha3_256 = {
+	.digestsize	=	SHA3_256_DIGEST_SIZE,
+	.init		=	sha3_256_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-256",
+		.cra_driver_name =	"sha3-256-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_256_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static struct shash_alg sha3_384 = {
+	.digestsize	=	SHA3_384_DIGEST_SIZE,
+	.init		=	sha3_384_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-384",
+		.cra_driver_name =	"sha3-384-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_384_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static struct shash_alg sha3_512 = {
+	.digestsize	=	SHA3_512_DIGEST_SIZE,
+	.init		=	sha3_512_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-512",
+		.cra_driver_name =	"sha3-512-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_512_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static int __init sha3_generic_mod_init(void)
+{
+	int ret;
+
+	ret = crypto_register_shash(&sha3_224);
+	if (ret < 0)
+		goto err_out;
+	ret = crypto_register_shash(&sha3_256);
+	if (ret < 0)
+		goto err_out_224;
+	ret = crypto_register_shash(&sha3_384);
+	if (ret < 0)
+		goto err_out_256;
+	ret = crypto_register_shash(&sha3_512);
+	if (ret < 0)
+		goto err_out_384;
+
+	return 0;
+
+err_out_384:
+	crypto_unregister_shash(&sha3_384);
+err_out_256:
+	crypto_unregister_shash(&sha3_256);
+err_out_224:
+	crypto_unregister_shash(&sha3_224);
+err_out:
+	return ret;
+}
+
+static void __exit sha3_generic_mod_fini(void)
+{
+	crypto_unregister_shash(&sha3_224);
+	crypto_unregister_shash(&sha3_256);
+	crypto_unregister_shash(&sha3_384);
+	crypto_unregister_shash(&sha3_512);
+}
+
+module_init(sha3_generic_mod_init);
+module_exit(sha3_generic_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-3 Secure Hash Algorithm");
+
+MODULE_ALIAS_CRYPTO("sha3-224");
+MODULE_ALIAS_CRYPTO("sha3-224-generic");
+MODULE_ALIAS_CRYPTO("sha3-256");
+MODULE_ALIAS_CRYPTO("sha3-256-generic");
+MODULE_ALIAS_CRYPTO("sha3-384");
+MODULE_ALIAS_CRYPTO("sha3-384-generic");
+MODULE_ALIAS_CRYPTO("sha3-512");
+MODULE_ALIAS_CRYPTO("sha3-512-generic");
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 69230e9d4ac9..f7d0018dcaee 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -16,7 +16,11 @@
 
 #include <crypto/internal/skcipher.h>
 #include <linux/bug.h>
+#include <linux/cryptouser.h>
 #include <linux/module.h>
+#include <linux/rtnetlink.h>
+#include <linux/seq_file.h>
+#include <net/netlink.h>
 
 #include "internal.h"
 
@@ -25,10 +29,11 @@ static unsigned int crypto_skcipher_extsize(struct crypto_alg *alg)
 	if (alg->cra_type == &crypto_blkcipher_type)
 		return sizeof(struct crypto_blkcipher *);
 
-	BUG_ON(alg->cra_type != &crypto_ablkcipher_type &&
-	       alg->cra_type != &crypto_givcipher_type);
+	if (alg->cra_type == &crypto_ablkcipher_type ||
+	    alg->cra_type == &crypto_givcipher_type)
+		return sizeof(struct crypto_ablkcipher *);
 
-	return sizeof(struct crypto_ablkcipher *);
+	return crypto_alg_extsize(alg);
 }
 
 static int skcipher_setkey_blkcipher(struct crypto_skcipher *tfm,
@@ -216,26 +221,118 @@ static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
 	return 0;
 }
 
+static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(skcipher);
+
+	alg->exit(skcipher);
+}
+
 static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 {
+	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(skcipher);
+
 	if (tfm->__crt_alg->cra_type == &crypto_blkcipher_type)
 		return crypto_init_skcipher_ops_blkcipher(tfm);
 
-	BUG_ON(tfm->__crt_alg->cra_type != &crypto_ablkcipher_type &&
-	       tfm->__crt_alg->cra_type != &crypto_givcipher_type);
+	if (tfm->__crt_alg->cra_type == &crypto_ablkcipher_type ||
+	    tfm->__crt_alg->cra_type == &crypto_givcipher_type)
+		return crypto_init_skcipher_ops_ablkcipher(tfm);
+
+	skcipher->setkey = alg->setkey;
+	skcipher->encrypt = alg->encrypt;
+	skcipher->decrypt = alg->decrypt;
+	skcipher->ivsize = alg->ivsize;
+	skcipher->keysize = alg->max_keysize;
+
+	if (alg->exit)
+		skcipher->base.exit = crypto_skcipher_exit_tfm;
 
-	return crypto_init_skcipher_ops_ablkcipher(tfm);
+	if (alg->init)
+		return alg->init(skcipher);
+
+	return 0;
+}
+
+static void crypto_skcipher_free_instance(struct crypto_instance *inst)
+{
+	struct skcipher_instance *skcipher =
+		container_of(inst, struct skcipher_instance, s.base);
+
+	skcipher->free(skcipher);
+}
+
+static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	struct skcipher_alg *skcipher = container_of(alg, struct skcipher_alg,
+						     base);
+
+	seq_printf(m, "type         : skcipher\n");
+	seq_printf(m, "async        : %s\n",
+		   alg->cra_flags & CRYPTO_ALG_ASYNC ?  "yes" : "no");
+	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
+	seq_printf(m, "min keysize  : %u\n", skcipher->min_keysize);
+	seq_printf(m, "max keysize  : %u\n", skcipher->max_keysize);
+	seq_printf(m, "ivsize       : %u\n", skcipher->ivsize);
+	seq_printf(m, "chunksize    : %u\n", skcipher->chunksize);
 }
 
+#ifdef CONFIG_NET
+static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_blkcipher rblkcipher;
+	struct skcipher_alg *skcipher = container_of(alg, struct skcipher_alg,
+						     base);
+
+	strncpy(rblkcipher.type, "skcipher", sizeof(rblkcipher.type));
+	strncpy(rblkcipher.geniv, "<none>", sizeof(rblkcipher.geniv));
+
+	rblkcipher.blocksize = alg->cra_blocksize;
+	rblkcipher.min_keysize = skcipher->min_keysize;
+	rblkcipher.max_keysize = skcipher->max_keysize;
+	rblkcipher.ivsize = skcipher->ivsize;
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER,
+		    sizeof(struct crypto_report_blkcipher), &rblkcipher))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
+static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
 static const struct crypto_type crypto_skcipher_type2 = {
 	.extsize = crypto_skcipher_extsize,
 	.init_tfm = crypto_skcipher_init_tfm,
+	.free = crypto_skcipher_free_instance,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_skcipher_show,
+#endif
+	.report = crypto_skcipher_report,
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_BLKCIPHER_MASK,
-	.type = CRYPTO_ALG_TYPE_BLKCIPHER,
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
 	.tfmsize = offsetof(struct crypto_skcipher, base),
 };
 
+int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn,
+			  const char *name, u32 type, u32 mask)
+{
+	spawn->base.frontend = &crypto_skcipher_type2;
+	return crypto_grab_spawn(&spawn->base, name, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_grab_skcipher);
+
 struct crypto_skcipher *crypto_alloc_skcipher(const char *alg_name,
 					      u32 type, u32 mask)
 {
@@ -243,5 +340,90 @@ struct crypto_skcipher *crypto_alloc_skcipher(const char *alg_name,
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_skcipher);
 
+int crypto_has_skcipher2(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_type_has_alg(alg_name, &crypto_skcipher_type2,
+				   type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_has_skcipher2);
+
+static int skcipher_prepare_alg(struct skcipher_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8)
+		return -EINVAL;
+
+	if (!alg->chunksize)
+		alg->chunksize = base->cra_blocksize;
+
+	base->cra_type = &crypto_skcipher_type2;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_SKCIPHER;
+
+	return 0;
+}
+
+int crypto_register_skcipher(struct skcipher_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+	int err;
+
+	err = skcipher_prepare_alg(alg);
+	if (err)
+		return err;
+
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_skcipher);
+
+void crypto_unregister_skcipher(struct skcipher_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_skcipher);
+
+int crypto_register_skciphers(struct skcipher_alg *algs, int count)
+{
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_skcipher(&algs[i]);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (--i; i >= 0; --i)
+		crypto_unregister_skcipher(&algs[i]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_register_skciphers);
+
+void crypto_unregister_skciphers(struct skcipher_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_skcipher(&algs[i]);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_skciphers);
+
+int skcipher_register_instance(struct crypto_template *tmpl,
+			   struct skcipher_instance *inst)
+{
+	int err;
+
+	err = skcipher_prepare_alg(&inst->alg);
+	if (err)
+		return err;
+
+	return crypto_register_instance(tmpl, skcipher_crypto_instance(inst));
+}
+EXPORT_SYMBOL_GPL(skcipher_register_instance);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Symmetric key cipher type");
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 579dce071463..ae22f05d5936 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -24,6 +24,7 @@
 
 #include <crypto/aead.h>
 #include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/fips.h>
 #include <linux/init.h>
@@ -72,7 +73,8 @@ static char *check[] = {
 	"cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea",
 	"khazad", "wp512", "wp384", "wp256", "tnepres", "xeta",  "fcrypt",
 	"camellia", "seed", "salsa20", "rmd128", "rmd160", "rmd256", "rmd320",
-	"lzo", "cts", "zlib", NULL
+	"lzo", "cts", "zlib", "sha3-224", "sha3-256", "sha3-384", "sha3-512",
+	NULL
 };
 
 struct tcrypt_result {
@@ -91,76 +93,6 @@ static void tcrypt_complete(struct crypto_async_request *req, int err)
 	complete(&res->completion);
 }
 
-static int test_cipher_jiffies(struct blkcipher_desc *desc, int enc,
-			       struct scatterlist *sg, int blen, int secs)
-{
-	unsigned long start, end;
-	int bcount;
-	int ret;
-
-	for (start = jiffies, end = start + secs * HZ, bcount = 0;
-	     time_before(jiffies, end); bcount++) {
-		if (enc)
-			ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
-		else
-			ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
-
-		if (ret)
-			return ret;
-	}
-
-	printk("%d operations in %d seconds (%ld bytes)\n",
-	       bcount, secs, (long)bcount * blen);
-	return 0;
-}
-
-static int test_cipher_cycles(struct blkcipher_desc *desc, int enc,
-			      struct scatterlist *sg, int blen)
-{
-	unsigned long cycles = 0;
-	int ret = 0;
-	int i;
-
-	local_irq_disable();
-
-	/* Warm-up run. */
-	for (i = 0; i < 4; i++) {
-		if (enc)
-			ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
-		else
-			ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
-
-		if (ret)
-			goto out;
-	}
-
-	/* The real thing. */
-	for (i = 0; i < 8; i++) {
-		cycles_t start, end;
-
-		start = get_cycles();
-		if (enc)
-			ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
-		else
-			ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
-		end = get_cycles();
-
-		if (ret)
-			goto out;
-
-		cycles += end - start;
-	}
-
-out:
-	local_irq_enable();
-
-	if (ret == 0)
-		printk("1 operation in %lu cycles (%d bytes)\n",
-		       (cycles + 4) / 8, blen);
-
-	return ret;
-}
-
 static inline int do_one_aead_op(struct aead_request *req, int ret)
 {
 	if (ret == -EINPROGRESS || ret == -EBUSY) {
@@ -454,127 +386,148 @@ out_noxbuf:
 	return;
 }
 
-static void test_cipher_speed(const char *algo, int enc, unsigned int secs,
-			      struct cipher_speed_template *template,
-			      unsigned int tcount, u8 *keysize)
+static void test_hash_sg_init(struct scatterlist *sg)
 {
-	unsigned int ret, i, j, iv_len;
-	const char *key;
-	char iv[128];
-	struct crypto_blkcipher *tfm;
-	struct blkcipher_desc desc;
-	const char *e;
-	u32 *b_size;
+	int i;
 
-	if (enc == ENCRYPT)
-	        e = "encryption";
-	else
-		e = "decryption";
+	sg_init_table(sg, TVMEMSIZE);
+	for (i = 0; i < TVMEMSIZE; i++) {
+		sg_set_buf(sg + i, tvmem[i], PAGE_SIZE);
+		memset(tvmem[i], 0xff, PAGE_SIZE);
+	}
+}
 
-	tfm = crypto_alloc_blkcipher(algo, 0, CRYPTO_ALG_ASYNC);
+static inline int do_one_ahash_op(struct ahash_request *req, int ret)
+{
+	if (ret == -EINPROGRESS || ret == -EBUSY) {
+		struct tcrypt_result *tr = req->base.data;
 
-	if (IS_ERR(tfm)) {
-		printk("failed to load transform for %s: %ld\n", algo,
-		       PTR_ERR(tfm));
+		wait_for_completion(&tr->completion);
+		reinit_completion(&tr->completion);
+		ret = tr->err;
+	}
+	return ret;
+}
+
+struct test_mb_ahash_data {
+	struct scatterlist sg[TVMEMSIZE];
+	char result[64];
+	struct ahash_request *req;
+	struct tcrypt_result tresult;
+	char *xbuf[XBUFSIZE];
+};
+
+static void test_mb_ahash_speed(const char *algo, unsigned int sec,
+				struct hash_speed *speed)
+{
+	struct test_mb_ahash_data *data;
+	struct crypto_ahash *tfm;
+	unsigned long start, end;
+	unsigned long cycles;
+	unsigned int i, j, k;
+	int ret;
+
+	data = kzalloc(sizeof(*data) * 8, GFP_KERNEL);
+	if (!data)
 		return;
+
+	tfm = crypto_alloc_ahash(algo, 0, 0);
+	if (IS_ERR(tfm)) {
+		pr_err("failed to load transform for %s: %ld\n",
+			algo, PTR_ERR(tfm));
+		goto free_data;
 	}
-	desc.tfm = tfm;
-	desc.flags = 0;
 
-	printk(KERN_INFO "\ntesting speed of %s (%s) %s\n", algo,
-			get_driver_name(crypto_blkcipher, tfm), e);
+	for (i = 0; i < 8; ++i) {
+		if (testmgr_alloc_buf(data[i].xbuf))
+			goto out;
 
-	i = 0;
-	do {
+		init_completion(&data[i].tresult.completion);
 
-		b_size = block_sizes;
-		do {
-			struct scatterlist sg[TVMEMSIZE];
+		data[i].req = ahash_request_alloc(tfm, GFP_KERNEL);
+		if (!data[i].req) {
+			pr_err("alg: hash: Failed to allocate request for %s\n",
+			       algo);
+			goto out;
+		}
 
-			if ((*keysize + *b_size) > TVMEMSIZE * PAGE_SIZE) {
-				printk("template (%u) too big for "
-				       "tvmem (%lu)\n", *keysize + *b_size,
-				       TVMEMSIZE * PAGE_SIZE);
-				goto out;
-			}
+		ahash_request_set_callback(data[i].req, 0,
+					   tcrypt_complete, &data[i].tresult);
+		test_hash_sg_init(data[i].sg);
+	}
 
-			printk("test %u (%d bit key, %d byte blocks): ", i,
-					*keysize * 8, *b_size);
+	pr_info("\ntesting speed of multibuffer %s (%s)\n", algo,
+		get_driver_name(crypto_ahash, tfm));
 
-			memset(tvmem[0], 0xff, PAGE_SIZE);
+	for (i = 0; speed[i].blen != 0; i++) {
+		/* For some reason this only tests digests. */
+		if (speed[i].blen != speed[i].plen)
+			continue;
 
-			/* set key, plain text and IV */
-			key = tvmem[0];
-			for (j = 0; j < tcount; j++) {
-				if (template[j].klen == *keysize) {
-					key = template[j].key;
-					break;
-				}
-			}
+		if (speed[i].blen > TVMEMSIZE * PAGE_SIZE) {
+			pr_err("template (%u) too big for tvmem (%lu)\n",
+			       speed[i].blen, TVMEMSIZE * PAGE_SIZE);
+			goto out;
+		}
 
-			ret = crypto_blkcipher_setkey(tfm, key, *keysize);
-			if (ret) {
-				printk("setkey() failed flags=%x\n",
-						crypto_blkcipher_get_flags(tfm));
-				goto out;
-			}
+		if (speed[i].klen)
+			crypto_ahash_setkey(tfm, tvmem[0], speed[i].klen);
 
-			sg_init_table(sg, TVMEMSIZE);
-			sg_set_buf(sg, tvmem[0] + *keysize,
-				   PAGE_SIZE - *keysize);
-			for (j = 1; j < TVMEMSIZE; j++) {
-				sg_set_buf(sg + j, tvmem[j], PAGE_SIZE);
-				memset (tvmem[j], 0xff, PAGE_SIZE);
-			}
+		for (k = 0; k < 8; k++)
+			ahash_request_set_crypt(data[k].req, data[k].sg,
+						data[k].result, speed[i].blen);
 
-			iv_len = crypto_blkcipher_ivsize(tfm);
-			if (iv_len) {
-				memset(&iv, 0xff, iv_len);
-				crypto_blkcipher_set_iv(tfm, iv, iv_len);
-			}
+		pr_info("test%3u "
+			"(%5u byte blocks,%5u bytes per update,%4u updates): ",
+			i, speed[i].blen, speed[i].plen,
+			speed[i].blen / speed[i].plen);
 
-			if (secs)
-				ret = test_cipher_jiffies(&desc, enc, sg,
-							  *b_size, secs);
-			else
-				ret = test_cipher_cycles(&desc, enc, sg,
-							 *b_size);
+		start = get_cycles();
 
-			if (ret) {
-				printk("%s() failed flags=%x\n", e, desc.flags);
-				break;
+		for (k = 0; k < 8; k++) {
+			ret = crypto_ahash_digest(data[k].req);
+			if (ret == -EINPROGRESS) {
+				ret = 0;
+				continue;
 			}
-			b_size++;
-			i++;
-		} while (*b_size);
-		keysize++;
-	} while (*keysize);
 
-out:
-	crypto_free_blkcipher(tfm);
-}
+			if (ret)
+				break;
 
-static void test_hash_sg_init(struct scatterlist *sg)
-{
-	int i;
+			complete(&data[k].tresult.completion);
+			data[k].tresult.err = 0;
+		}
 
-	sg_init_table(sg, TVMEMSIZE);
-	for (i = 0; i < TVMEMSIZE; i++) {
-		sg_set_buf(sg + i, tvmem[i], PAGE_SIZE);
-		memset(tvmem[i], 0xff, PAGE_SIZE);
-	}
-}
+		for (j = 0; j < k; j++) {
+			struct tcrypt_result *tr = &data[j].tresult;
 
-static inline int do_one_ahash_op(struct ahash_request *req, int ret)
-{
-	if (ret == -EINPROGRESS || ret == -EBUSY) {
-		struct tcrypt_result *tr = req->base.data;
+			wait_for_completion(&tr->completion);
+			if (tr->err)
+				ret = tr->err;
+		}
 
-		wait_for_completion(&tr->completion);
-		reinit_completion(&tr->completion);
-		ret = tr->err;
+		end = get_cycles();
+		cycles = end - start;
+		pr_cont("%6lu cycles/operation, %4lu cycles/byte\n",
+			cycles, cycles / (8 * speed[i].blen));
+
+		if (ret) {
+			pr_err("At least one hashing failed ret=%d\n", ret);
+			break;
+		}
 	}
-	return ret;
+
+out:
+	for (k = 0; k < 8; ++k)
+		ahash_request_free(data[k].req);
+
+	for (k = 0; k < 8; ++k)
+		testmgr_free_buf(data[k].xbuf);
+
+	crypto_free_ahash(tfm);
+
+free_data:
+	kfree(data);
 }
 
 static int test_ahash_jiffies_digest(struct ahash_request *req, int blen,
@@ -812,7 +765,7 @@ static void test_hash_speed(const char *algo, unsigned int secs,
 	return test_ahash_speed_common(algo, secs, speed, CRYPTO_ALG_ASYNC);
 }
 
-static inline int do_one_acipher_op(struct ablkcipher_request *req, int ret)
+static inline int do_one_acipher_op(struct skcipher_request *req, int ret)
 {
 	if (ret == -EINPROGRESS || ret == -EBUSY) {
 		struct tcrypt_result *tr = req->base.data;
@@ -825,7 +778,7 @@ static inline int do_one_acipher_op(struct ablkcipher_request *req, int ret)
 	return ret;
 }
 
-static int test_acipher_jiffies(struct ablkcipher_request *req, int enc,
+static int test_acipher_jiffies(struct skcipher_request *req, int enc,
 				int blen, int secs)
 {
 	unsigned long start, end;
@@ -836,10 +789,10 @@ static int test_acipher_jiffies(struct ablkcipher_request *req, int enc,
 	     time_before(jiffies, end); bcount++) {
 		if (enc)
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_encrypt(req));
+						crypto_skcipher_encrypt(req));
 		else
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_decrypt(req));
+						crypto_skcipher_decrypt(req));
 
 		if (ret)
 			return ret;
@@ -850,7 +803,7 @@ static int test_acipher_jiffies(struct ablkcipher_request *req, int enc,
 	return 0;
 }
 
-static int test_acipher_cycles(struct ablkcipher_request *req, int enc,
+static int test_acipher_cycles(struct skcipher_request *req, int enc,
 			       int blen)
 {
 	unsigned long cycles = 0;
@@ -861,10 +814,10 @@ static int test_acipher_cycles(struct ablkcipher_request *req, int enc,
 	for (i = 0; i < 4; i++) {
 		if (enc)
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_encrypt(req));
+						crypto_skcipher_encrypt(req));
 		else
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_decrypt(req));
+						crypto_skcipher_decrypt(req));
 
 		if (ret)
 			goto out;
@@ -877,10 +830,10 @@ static int test_acipher_cycles(struct ablkcipher_request *req, int enc,
 		start = get_cycles();
 		if (enc)
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_encrypt(req));
+						crypto_skcipher_encrypt(req));
 		else
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_decrypt(req));
+						crypto_skcipher_decrypt(req));
 		end = get_cycles();
 
 		if (ret)
@@ -897,16 +850,16 @@ out:
 	return ret;
 }
 
-static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
-			       struct cipher_speed_template *template,
-			       unsigned int tcount, u8 *keysize)
+static void test_skcipher_speed(const char *algo, int enc, unsigned int secs,
+				struct cipher_speed_template *template,
+				unsigned int tcount, u8 *keysize, bool async)
 {
 	unsigned int ret, i, j, k, iv_len;
 	struct tcrypt_result tresult;
 	const char *key;
 	char iv[128];
-	struct ablkcipher_request *req;
-	struct crypto_ablkcipher *tfm;
+	struct skcipher_request *req;
+	struct crypto_skcipher *tfm;
 	const char *e;
 	u32 *b_size;
 
@@ -917,7 +870,7 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
 
 	init_completion(&tresult.completion);
 
-	tfm = crypto_alloc_ablkcipher(algo, 0, 0);
+	tfm = crypto_alloc_skcipher(algo, 0, async ? 0 : CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm)) {
 		pr_err("failed to load transform for %s: %ld\n", algo,
@@ -926,17 +879,17 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
 	}
 
 	pr_info("\ntesting speed of async %s (%s) %s\n", algo,
-			get_driver_name(crypto_ablkcipher, tfm), e);
+			get_driver_name(crypto_skcipher, tfm), e);
 
-	req = ablkcipher_request_alloc(tfm, GFP_KERNEL);
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
 	if (!req) {
 		pr_err("tcrypt: skcipher: Failed to allocate request for %s\n",
 		       algo);
 		goto out;
 	}
 
-	ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-					tcrypt_complete, &tresult);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      tcrypt_complete, &tresult);
 
 	i = 0;
 	do {
@@ -966,12 +919,12 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
 				}
 			}
 
-			crypto_ablkcipher_clear_flags(tfm, ~0);
+			crypto_skcipher_clear_flags(tfm, ~0);
 
-			ret = crypto_ablkcipher_setkey(tfm, key, *keysize);
+			ret = crypto_skcipher_setkey(tfm, key, *keysize);
 			if (ret) {
 				pr_err("setkey() failed flags=%x\n",
-					crypto_ablkcipher_get_flags(tfm));
+					crypto_skcipher_get_flags(tfm));
 				goto out_free_req;
 			}
 
@@ -995,11 +948,11 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
 				sg_set_buf(sg, tvmem[0] + *keysize, *b_size);
 			}
 
-			iv_len = crypto_ablkcipher_ivsize(tfm);
+			iv_len = crypto_skcipher_ivsize(tfm);
 			if (iv_len)
 				memset(&iv, 0xff, iv_len);
 
-			ablkcipher_request_set_crypt(req, sg, sg, *b_size, iv);
+			skcipher_request_set_crypt(req, sg, sg, *b_size, iv);
 
 			if (secs)
 				ret = test_acipher_jiffies(req, enc,
@@ -1010,7 +963,7 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
 
 			if (ret) {
 				pr_err("%s() failed flags=%x\n", e,
-					crypto_ablkcipher_get_flags(tfm));
+				       crypto_skcipher_get_flags(tfm));
 				break;
 			}
 			b_size++;
@@ -1020,9 +973,25 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
 	} while (*keysize);
 
 out_free_req:
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 out:
-	crypto_free_ablkcipher(tfm);
+	crypto_free_skcipher(tfm);
+}
+
+static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
+			       struct cipher_speed_template *template,
+			       unsigned int tcount, u8 *keysize)
+{
+	return test_skcipher_speed(algo, enc, secs, template, tcount, keysize,
+				   true);
+}
+
+static void test_cipher_speed(const char *algo, int enc, unsigned int secs,
+			      struct cipher_speed_template *template,
+			      unsigned int tcount, u8 *keysize)
+{
+	return test_skcipher_speed(algo, enc, secs, template, tcount, keysize,
+				   false);
 }
 
 static void test_available(void)
@@ -1284,6 +1253,22 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		ret += tcrypt_test("crct10dif");
 		break;
 
+	case 48:
+		ret += tcrypt_test("sha3-224");
+		break;
+
+	case 49:
+		ret += tcrypt_test("sha3-256");
+		break;
+
+	case 50:
+		ret += tcrypt_test("sha3-384");
+		break;
+
+	case 51:
+		ret += tcrypt_test("sha3-512");
+		break;
+
 	case 100:
 		ret += tcrypt_test("hmac(md5)");
 		break;
@@ -1328,6 +1313,22 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		ret += tcrypt_test("hmac(crc32)");
 		break;
 
+	case 111:
+		ret += tcrypt_test("hmac(sha3-224)");
+		break;
+
+	case 112:
+		ret += tcrypt_test("hmac(sha3-256)");
+		break;
+
+	case 113:
+		ret += tcrypt_test("hmac(sha3-384)");
+		break;
+
+	case 114:
+		ret += tcrypt_test("hmac(sha3-512)");
+		break;
+
 	case 150:
 		ret += tcrypt_test("ansi_cprng");
 		break;
@@ -1406,6 +1407,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 				speed_template_32_48_64);
 		test_cipher_speed("xts(aes)", DECRYPT, sec, NULL, 0,
 				speed_template_32_48_64);
+		test_cipher_speed("cts(cbc(aes))", ENCRYPT, sec, NULL, 0,
+				speed_template_16_24_32);
+		test_cipher_speed("cts(cbc(aes))", DECRYPT, sec, NULL, 0,
+				speed_template_16_24_32);
 		test_cipher_speed("ctr(aes)", ENCRYPT, sec, NULL, 0,
 				speed_template_16_24_32);
 		test_cipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
@@ -1691,6 +1696,22 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		test_hash_speed("poly1305", sec, poly1305_speed_template);
 		if (mode > 300 && mode < 400) break;
 
+	case 322:
+		test_hash_speed("sha3-224", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
+	case 323:
+		test_hash_speed("sha3-256", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
+	case 324:
+		test_hash_speed("sha3-384", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
+	case 325:
+		test_hash_speed("sha3-512", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
 	case 399:
 		break;
 
@@ -1770,6 +1791,35 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 		test_ahash_speed("rmd320", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
 
+	case 418:
+		test_ahash_speed("sha3-224", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 419:
+		test_ahash_speed("sha3-256", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 420:
+		test_ahash_speed("sha3-384", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+
+	case 421:
+		test_ahash_speed("sha3-512", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 422:
+		test_mb_ahash_speed("sha1", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 423:
+		test_mb_ahash_speed("sha256", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 424:
+		test_mb_ahash_speed("sha512", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
 	case 499:
 		break;
 
@@ -1790,6 +1840,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 				   speed_template_32_48_64);
 		test_acipher_speed("xts(aes)", DECRYPT, sec, NULL, 0,
 				   speed_template_32_48_64);
+		test_acipher_speed("cts(cbc(aes))", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("cts(cbc(aes))", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
 		test_acipher_speed("ctr(aes)", ENCRYPT, sec, NULL, 0,
 				   speed_template_16_24_32);
 		test_acipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index c727fb0cb021..5c9d5a5e7b65 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -32,6 +32,7 @@
 #include <crypto/rng.h>
 #include <crypto/drbg.h>
 #include <crypto/akcipher.h>
+#include <crypto/kpp.h>
 
 #include "internal.h"
 
@@ -120,6 +121,11 @@ struct akcipher_test_suite {
 	unsigned int count;
 };
 
+struct kpp_test_suite {
+	struct kpp_testvec *vecs;
+	unsigned int count;
+};
+
 struct alg_test_desc {
 	const char *alg;
 	int (*test)(const struct alg_test_desc *desc, const char *driver,
@@ -134,6 +140,7 @@ struct alg_test_desc {
 		struct cprng_test_suite cprng;
 		struct drbg_test_suite drbg;
 		struct akcipher_test_suite akcipher;
+		struct kpp_test_suite kpp;
 	} suite;
 };
 
@@ -1777,8 +1784,135 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver,
 
 }
 
-static int do_test_rsa(struct crypto_akcipher *tfm,
-		       struct akcipher_testvec *vecs)
+static int do_test_kpp(struct crypto_kpp *tfm, struct kpp_testvec *vec,
+		       const char *alg)
+{
+	struct kpp_request *req;
+	void *input_buf = NULL;
+	void *output_buf = NULL;
+	struct tcrypt_result result;
+	unsigned int out_len_max;
+	int err = -ENOMEM;
+	struct scatterlist src, dst;
+
+	req = kpp_request_alloc(tfm, GFP_KERNEL);
+	if (!req)
+		return err;
+
+	init_completion(&result.completion);
+
+	err = crypto_kpp_set_secret(tfm, vec->secret, vec->secret_size);
+	if (err < 0)
+		goto free_req;
+
+	out_len_max = crypto_kpp_maxsize(tfm);
+	output_buf = kzalloc(out_len_max, GFP_KERNEL);
+	if (!output_buf) {
+		err = -ENOMEM;
+		goto free_req;
+	}
+
+	/* Use appropriate parameter as base */
+	kpp_request_set_input(req, NULL, 0);
+	sg_init_one(&dst, output_buf, out_len_max);
+	kpp_request_set_output(req, &dst, out_len_max);
+	kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				 tcrypt_complete, &result);
+
+	/* Compute public key */
+	err = wait_async_op(&result, crypto_kpp_generate_public_key(req));
+	if (err) {
+		pr_err("alg: %s: generate public key test failed. err %d\n",
+		       alg, err);
+		goto free_output;
+	}
+	/* Verify calculated public key */
+	if (memcmp(vec->expected_a_public, sg_virt(req->dst),
+		   vec->expected_a_public_size)) {
+		pr_err("alg: %s: generate public key test failed. Invalid output\n",
+		       alg);
+		err = -EINVAL;
+		goto free_output;
+	}
+
+	/* Calculate shared secret key by using counter part (b) public key. */
+	input_buf = kzalloc(vec->b_public_size, GFP_KERNEL);
+	if (!input_buf) {
+		err = -ENOMEM;
+		goto free_output;
+	}
+
+	memcpy(input_buf, vec->b_public, vec->b_public_size);
+	sg_init_one(&src, input_buf, vec->b_public_size);
+	sg_init_one(&dst, output_buf, out_len_max);
+	kpp_request_set_input(req, &src, vec->b_public_size);
+	kpp_request_set_output(req, &dst, out_len_max);
+	kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				 tcrypt_complete, &result);
+	err = wait_async_op(&result, crypto_kpp_compute_shared_secret(req));
+	if (err) {
+		pr_err("alg: %s: compute shard secret test failed. err %d\n",
+		       alg, err);
+		goto free_all;
+	}
+	/*
+	 * verify shared secret from which the user will derive
+	 * secret key by executing whatever hash it has chosen
+	 */
+	if (memcmp(vec->expected_ss, sg_virt(req->dst),
+		   vec->expected_ss_size)) {
+		pr_err("alg: %s: compute shared secret test failed. Invalid output\n",
+		       alg);
+		err = -EINVAL;
+	}
+
+free_all:
+	kfree(input_buf);
+free_output:
+	kfree(output_buf);
+free_req:
+	kpp_request_free(req);
+	return err;
+}
+
+static int test_kpp(struct crypto_kpp *tfm, const char *alg,
+		    struct kpp_testvec *vecs, unsigned int tcount)
+{
+	int ret, i;
+
+	for (i = 0; i < tcount; i++) {
+		ret = do_test_kpp(tfm, vecs++, alg);
+		if (ret) {
+			pr_err("alg: %s: test failed on vector %d, err=%d\n",
+			       alg, i + 1, ret);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static int alg_test_kpp(const struct alg_test_desc *desc, const char *driver,
+			u32 type, u32 mask)
+{
+	struct crypto_kpp *tfm;
+	int err = 0;
+
+	tfm = crypto_alloc_kpp(driver, type | CRYPTO_ALG_INTERNAL, mask);
+	if (IS_ERR(tfm)) {
+		pr_err("alg: kpp: Failed to load tfm for %s: %ld\n",
+		       driver, PTR_ERR(tfm));
+		return PTR_ERR(tfm);
+	}
+	if (desc->suite.kpp.vecs)
+		err = test_kpp(tfm, desc->alg, desc->suite.kpp.vecs,
+			       desc->suite.kpp.count);
+
+	crypto_free_kpp(tfm);
+	return err;
+}
+
+static int test_akcipher_one(struct crypto_akcipher *tfm,
+			     struct akcipher_testvec *vecs)
 {
 	char *xbuf[XBUFSIZE];
 	struct akcipher_request *req;
@@ -1807,6 +1941,7 @@ static int do_test_rsa(struct crypto_akcipher *tfm,
 	if (err)
 		goto free_req;
 
+	err = -ENOMEM;
 	out_len_max = crypto_akcipher_maxsize(tfm);
 	outbuf_enc = kzalloc(out_len_max, GFP_KERNEL);
 	if (!outbuf_enc)
@@ -1829,17 +1964,18 @@ static int do_test_rsa(struct crypto_akcipher *tfm,
 	/* Run RSA encrypt - c = m^e mod n;*/
 	err = wait_async_op(&result, crypto_akcipher_encrypt(req));
 	if (err) {
-		pr_err("alg: rsa: encrypt test failed. err %d\n", err);
+		pr_err("alg: akcipher: encrypt test failed. err %d\n", err);
 		goto free_all;
 	}
 	if (req->dst_len != vecs->c_size) {
-		pr_err("alg: rsa: encrypt test failed. Invalid output len\n");
+		pr_err("alg: akcipher: encrypt test failed. Invalid output len\n");
 		err = -EINVAL;
 		goto free_all;
 	}
 	/* verify that encrypted message is equal to expected */
 	if (memcmp(vecs->c, outbuf_enc, vecs->c_size)) {
-		pr_err("alg: rsa: encrypt test failed. Invalid output\n");
+		pr_err("alg: akcipher: encrypt test failed. Invalid output\n");
+		hexdump(outbuf_enc, vecs->c_size);
 		err = -EINVAL;
 		goto free_all;
 	}
@@ -1867,18 +2003,22 @@ static int do_test_rsa(struct crypto_akcipher *tfm,
 	/* Run RSA decrypt - m = c^d mod n;*/
 	err = wait_async_op(&result, crypto_akcipher_decrypt(req));
 	if (err) {
-		pr_err("alg: rsa: decrypt test failed. err %d\n", err);
+		pr_err("alg: akcipher: decrypt test failed. err %d\n", err);
 		goto free_all;
 	}
 	out_len = req->dst_len;
-	if (out_len != vecs->m_size) {
-		pr_err("alg: rsa: decrypt test failed. Invalid output len\n");
+	if (out_len < vecs->m_size) {
+		pr_err("alg: akcipher: decrypt test failed. "
+		       "Invalid output len %u\n", out_len);
 		err = -EINVAL;
 		goto free_all;
 	}
 	/* verify that decrypted message is equal to the original msg */
-	if (memcmp(vecs->m, outbuf_dec, vecs->m_size)) {
-		pr_err("alg: rsa: decrypt test failed. Invalid output\n");
+	if (memchr_inv(outbuf_dec, 0, out_len - vecs->m_size) ||
+	    memcmp(vecs->m, outbuf_dec + out_len - vecs->m_size,
+		   vecs->m_size)) {
+		pr_err("alg: akcipher: decrypt test failed. Invalid output\n");
+		hexdump(outbuf_dec, out_len);
 		err = -EINVAL;
 	}
 free_all:
@@ -1891,28 +2031,22 @@ free_xbuf:
 	return err;
 }
 
-static int test_rsa(struct crypto_akcipher *tfm, struct akcipher_testvec *vecs,
-		    unsigned int tcount)
+static int test_akcipher(struct crypto_akcipher *tfm, const char *alg,
+			 struct akcipher_testvec *vecs, unsigned int tcount)
 {
+	const char *algo =
+		crypto_tfm_alg_driver_name(crypto_akcipher_tfm(tfm));
 	int ret, i;
 
 	for (i = 0; i < tcount; i++) {
-		ret = do_test_rsa(tfm, vecs++);
-		if (ret) {
-			pr_err("alg: rsa: test failed on vector %d, err=%d\n",
-			       i + 1, ret);
-			return ret;
-		}
-	}
-	return 0;
-}
-
-static int test_akcipher(struct crypto_akcipher *tfm, const char *alg,
-			 struct akcipher_testvec *vecs, unsigned int tcount)
-{
-	if (strncmp(alg, "rsa", 3) == 0)
-		return test_rsa(tfm, vecs, tcount);
+		ret = test_akcipher_one(tfm, vecs++);
+		if (!ret)
+			continue;
 
+		pr_err("alg: akcipher: test %d failed for %s, err=%d\n",
+		       i + 1, algo, ret);
+		return ret;
+	}
 	return 0;
 }
 
@@ -2729,6 +2863,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "dh",
+		.test = alg_test_kpp,
+		.fips_allowed = 1,
+		.suite = {
+			.kpp = {
+				.vecs = dh_tv_template,
+				.count = DH_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "digest_null",
 		.test = alg_test_null,
 	}, {
@@ -3157,6 +3301,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "ecdh",
+		.test = alg_test_kpp,
+		.fips_allowed = 1,
+		.suite = {
+			.kpp = {
+				.vecs = ecdh_tv_template,
+				.count = ECDH_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "gcm(aes)",
 		.test = alg_test_aead,
 		.fips_allowed = 1,
@@ -3249,6 +3403,46 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "hmac(sha3-224)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_224_tv_template,
+				.count = HMAC_SHA3_224_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "hmac(sha3-256)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_256_tv_template,
+				.count = HMAC_SHA3_256_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "hmac(sha3-384)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_384_tv_template,
+				.count = HMAC_SHA3_384_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "hmac(sha3-512)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_512_tv_template,
+				.count = HMAC_SHA3_512_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "hmac(sha384)",
 		.test = alg_test_hash,
 		.fips_allowed = 1,
@@ -3659,6 +3853,46 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "sha3-224",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_224_tv_template,
+				.count = SHA3_224_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "sha3-256",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_256_tv_template,
+				.count = SHA3_256_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "sha3-384",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_384_tv_template,
+				.count = SHA3_384_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "sha3-512",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_512_tv_template,
+				.count = SHA3_512_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "sha384",
 		.test = alg_test_hash,
 		.fips_allowed = 1,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 487ec880e889..acb6bbff781a 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -133,6 +133,17 @@ struct akcipher_testvec {
 	bool public_key_vec;
 };
 
+struct kpp_testvec {
+	unsigned char *secret;
+	unsigned char *b_public;
+	unsigned char *expected_a_public;
+	unsigned char *expected_ss;
+	unsigned short secret_size;
+	unsigned short b_public_size;
+	unsigned short expected_a_public_size;
+	unsigned short expected_ss_size;
+};
+
 static char zeroed_string[48];
 
 /*
@@ -141,7 +152,7 @@ static char zeroed_string[48];
 #ifdef CONFIG_CRYPTO_FIPS
 #define RSA_TEST_VECTORS	2
 #else
-#define RSA_TEST_VECTORS	4
+#define RSA_TEST_VECTORS	5
 #endif
 static struct akcipher_testvec rsa_tv_template[] = {
 	{
@@ -327,6 +338,516 @@ static struct akcipher_testvec rsa_tv_template[] = {
 	.m_size = 8,
 	.c_size = 256,
 	.public_key_vec = true,
+	}, {
+	.key =
+	"\x30\x82\x09\x29" /* sequence of 2345 bytes */
+	"\x02\x01\x00" /* version integer of 1 byte */
+	"\x02\x82\x02\x01" /* modulus - integer of 513 bytes */
+	"\x00\xC3\x8B\x55\x7B\x73\x4D\xFF\xE9\x9B\xC6\xDC\x67\x3C\xB4\x8E"
+	"\xA0\x86\xED\xF2\xB9\x50\x5C\x54\x5C\xBA\xE4\xA1\xB2\xA7\xAE\x2F"
+	"\x1B\x7D\xF1\xFB\xAC\x79\xC5\xDF\x1A\x00\xC9\xB2\xC1\x61\x25\x33"
+	"\xE6\x9C\xE9\xCF\xD6\x27\xC4\x4E\x44\x30\x44\x5E\x08\xA1\x87\x52"
+	"\xCC\x6B\x97\x70\x8C\xBC\xA5\x06\x31\x0C\xD4\x2F\xD5\x7D\x26\x24"
+	"\xA2\xE2\xAC\x78\xF4\x53\x14\xCE\xF7\x19\x2E\xD7\xF7\xE6\x0C\xB9"
+	"\x56\x7F\x0B\xF1\xB1\xE2\x43\x70\xBD\x86\x1D\xA1\xCC\x2B\x19\x08"
+	"\x76\xEF\x91\xAC\xBF\x20\x24\x0D\x38\xC0\x89\xB8\x9A\x70\xB3\x64"
+	"\xD9\x8F\x80\x41\x10\x5B\x9F\xB1\xCB\x76\x43\x00\x21\x25\x36\xD4"
+	"\x19\xFC\x55\x95\x10\xE4\x26\x74\x98\x2C\xD9\xBD\x0B\x2B\x04\xC2"
+	"\xAC\x82\x38\xB4\xDD\x4C\x04\x7E\x51\x36\x40\x1E\x0B\xC4\x7C\x25"
+	"\xDD\x4B\xB2\xE7\x20\x0A\x57\xF9\xB4\x94\xC3\x08\x33\x22\x6F\x8B"
+	"\x48\xDB\x03\x68\x5A\x5B\xBA\xAE\xF3\xAD\xCF\xC3\x6D\xBA\xF1\x28"
+	"\x67\x7E\x6C\x79\x07\xDE\xFC\xED\xE7\x96\xE3\x6C\xE0\x2C\x87\xF8"
+	"\x02\x01\x28\x38\x43\x21\x53\x84\x69\x75\x78\x15\x7E\xEE\xD2\x1B"
+	"\xB9\x23\x40\xA8\x86\x1E\x38\x83\xB2\x73\x1D\x53\xFB\x9E\x2A\x8A"
+	"\xB2\x75\x35\x01\xC3\xC3\xC4\x94\xE8\x84\x86\x64\x81\xF4\x42\xAA"
+	"\x3C\x0E\xD6\x4F\xBC\x0A\x09\x2D\xE7\x1B\xD4\x10\xA8\x54\xEA\x89"
+	"\x84\x8A\xCB\xF7\x5A\x3C\xCA\x76\x08\x29\x62\xB4\x6A\x22\xDF\x14"
+	"\x95\x71\xFD\xB6\x86\x39\xB8\x8B\xF8\x91\x7F\x38\xAA\x14\xCD\xE5"
+	"\xF5\x1D\xC2\x6D\x53\x69\x52\x84\x7F\xA3\x1A\x5E\x26\x04\x83\x06"
+	"\x73\x52\x56\xCF\x76\x26\xC9\xDD\x75\xD7\xFC\xF4\x69\xD8\x7B\x55"
+	"\xB7\x68\x13\x53\xB9\xE7\x89\xC3\xE8\xD6\x6E\xA7\x6D\xEA\x81\xFD"
+	"\xC4\xB7\x05\x5A\xB7\x41\x0A\x23\x8E\x03\x8A\x1C\xAE\xD3\x1E\xCE"
+	"\xE3\x5E\xFC\x19\x4A\xEE\x61\x9B\x8E\xE5\xE5\xDD\x85\xF9\x41\xEC"
+	"\x14\x53\x92\xF7\xDD\x06\x85\x02\x91\xE3\xEB\x6C\x43\x03\xB1\x36"
+	"\x7B\x89\x5A\xA8\xEB\xFC\xD5\xA8\x35\xDC\x81\xD9\x5C\xBD\xCA\xDC"
+	"\x9B\x98\x0B\x06\x5D\x0C\x5B\xEE\xF3\xD5\xCC\x57\xC9\x71\x2F\x90"
+	"\x3B\x3C\xF0\x8E\x4E\x35\x48\xAE\x63\x74\xA9\xFC\x72\x75\x8E\x34"
+	"\xA8\xF2\x1F\xEA\xDF\x3A\x37\x2D\xE5\x39\x39\xF8\x57\x58\x3C\x04"
+	"\xFE\x87\x06\x98\xBC\x7B\xD3\x21\x36\x60\x25\x54\xA7\x3D\xFA\x91"
+	"\xCC\xA8\x0B\x92\x8E\xB4\xF7\x06\xFF\x1E\x95\xCB\x07\x76\x97\x3B"
+	"\x9D"
+	"\x02\x03\x01\x00\x01" /* public key integer of 3 bytes */
+	"\x02\x82\x02\x00" /* private key integer of 512 bytes */
+	"\x74\xA9\xE0\x6A\x32\xB4\xCA\x85\xD9\x86\x9F\x60\x88\x7B\x40\xCC"
+	"\xCD\x33\x91\xA8\xB6\x25\x1F\xBF\xE3\x51\x1C\x97\xB6\x2A\xD9\xB8"
+	"\x11\x40\x19\xE3\x21\x13\xC8\xB3\x7E\xDC\xD7\x65\x40\x4C\x2D\xD6"
+	"\xDC\xAF\x32\x6C\x96\x75\x2C\x2C\xCA\x8F\x3F\x7A\xEE\xC4\x09\xC6"
+	"\x24\x3A\xC9\xCF\x6D\x8D\x17\x50\x94\x52\xD3\xE7\x0F\x2F\x7E\x94"
+	"\x1F\xA0\xBE\xD9\x25\xE8\x38\x42\x7C\x27\xD2\x79\xF8\x2A\x87\x38"
+	"\xEF\xBB\x74\x8B\xA8\x6E\x8C\x08\xC6\xC7\x4F\x0C\xBC\x79\xC6\xEF"
+	"\x0E\xA7\x5E\xE4\xF8\x8C\x09\xC7\x5E\x37\xCC\x87\x77\xCD\xCF\xD1"
+	"\x6D\x28\x1B\xA9\x62\xC0\xB8\x16\xA7\x8B\xF9\xBB\xCC\xB4\x15\x7F"
+	"\x1B\x69\x03\xF2\x7B\xEB\xE5\x8C\x14\xD6\x23\x4F\x52\x6F\x18\xA6"
+	"\x4B\x5B\x01\xAD\x35\xF9\x48\x53\xB3\x86\x35\x66\xD7\xE7\x29\xC0"
+	"\x09\xB5\xC6\xE6\xFA\xC4\xDA\x19\xBE\xD7\x4D\x41\x14\xBE\x6F\xDF"
+	"\x1B\xAB\xC0\xCA\x88\x07\xAC\xF1\x7D\x35\x83\x67\x28\x2D\x50\xE9"
+	"\xCE\x27\x71\x5E\x1C\xCF\xD2\x30\x65\x79\x72\x2F\x9C\xE1\xD2\x39"
+	"\x7F\xEF\x3B\x01\xF2\x14\x1D\xDF\xBD\x51\xD3\xA1\x53\x62\xCF\x5F"
+	"\x79\x84\xCE\x06\x96\x69\x29\x49\x82\x1C\x71\x4A\xA1\x66\xC8\x2F"
+	"\xFD\x7B\x96\x7B\xFC\xC4\x26\x58\xC4\xFC\x7C\xAF\xB5\xE8\x95\x83"
+	"\x87\xCB\x46\xDE\x97\xA7\xB3\xA2\x54\x5B\xD7\xAF\xAB\xEB\xC8\xF3"
+	"\x55\x9D\x48\x2B\x30\x9C\xDC\x26\x4B\xC2\x89\x45\x13\xB2\x01\x9A"
+	"\xA4\x65\xC3\xEC\x24\x2D\x26\x97\xEB\x80\x8A\x9D\x03\xBC\x59\x66"
+	"\x9E\xE2\xBB\xBB\x63\x19\x64\x93\x11\x7B\x25\x65\x30\xCD\x5B\x4B"
+	"\x2C\xFF\xDC\x2D\x30\x87\x1F\x3C\x88\x07\xD0\xFC\x48\xCC\x05\x8A"
+	"\xA2\xC8\x39\x3E\xD5\x51\xBC\x0A\xBE\x6D\xA8\xA0\xF6\x88\x06\x79"
+	"\x13\xFF\x1B\x45\xDA\x54\xC9\x24\x25\x8A\x75\x0A\x26\xD1\x69\x81"
+	"\x14\x14\xD1\x79\x7D\x8E\x76\xF2\xE0\xEB\xDD\x0F\xDE\xC2\xEC\x80"
+	"\xD7\xDC\x16\x99\x92\xBE\xCB\x40\x0C\xCE\x7C\x3B\x46\xA2\x5B\x5D"
+	"\x0C\x45\xEB\xE1\x00\xDE\x72\x50\xB1\xA6\x0B\x76\xC5\x8D\xFC\x82"
+	"\x38\x6D\x99\x14\x1D\x1A\x4A\xD3\x7C\x53\xB8\x12\x46\xA2\x30\x38"
+	"\x82\xF4\x96\x6E\x8C\xCE\x47\x0D\xAF\x0A\x3B\x45\xB7\x43\x95\x43"
+	"\x9E\x02\x2C\x44\x07\x6D\x1F\x3C\x66\x89\x09\xB6\x1F\x06\x30\xCC"
+	"\xAD\xCE\x7D\x9A\xDE\x3E\xFB\x6C\xE4\x58\x43\xD2\x4F\xA5\x9E\x5E"
+	"\xA7\x7B\xAE\x3A\xF6\x7E\xD9\xDB\xD3\xF5\xC5\x41\xAF\xE6\x9C\x91"
+	"\x02\x82\x01\x01" /* prime1 - integer of 257 bytes */
+	"\x00\xE0\xA6\x6C\xF0\xA2\xF8\x81\x85\x36\x43\xD0\x13\x0B\x33\x8B"
+	"\x8F\x78\x3D\xAC\xC7\x5E\x46\x6A\x7F\x05\xAE\x3E\x26\x0A\xA6\xD0"
+	"\x51\xF3\xC8\x61\xF5\x77\x22\x48\x10\x87\x4C\xD5\xA4\xD5\xAE\x2D"
+	"\x4E\x7A\xFE\x1C\x31\xE7\x6B\xFF\xA4\x69\x20\xF9\x2A\x0B\x99\xBE"
+	"\x7C\x32\x68\xAD\xB0\xC6\x94\x81\x41\x75\xDC\x06\x78\x0A\xB4\xCF"
+	"\xCD\x1B\x2D\x31\xE4\x7B\xEA\xA8\x35\x99\x75\x57\xC6\x0E\xF6\x78"
+	"\x4F\xA0\x92\x4A\x00\x1B\xE7\x96\xF2\x5B\xFD\x2C\x0A\x0A\x13\x81"
+	"\xAF\xCB\x59\x87\x31\xD9\x83\x65\xF2\x22\x48\xD0\x03\x67\x39\xF6"
+	"\xFF\xA8\x36\x07\x3A\x68\xE3\x7B\xA9\x64\xFD\x9C\xF7\xB1\x3D\xBF"
+	"\x26\x5C\xCC\x7A\xFC\xA2\x8F\x51\xD1\xE1\xE2\x3C\xEC\x06\x75\x7C"
+	"\x34\xF9\xA9\x33\x70\x11\xAD\x5A\xDC\x5F\xCF\x50\xF6\x23\x2F\x39"
+	"\xAC\x92\x48\x53\x4D\x01\x96\x3C\xD8\xDC\x1F\x23\x23\x78\x80\x34"
+	"\x54\x14\x76\x8B\xB6\xBB\xFB\x88\x78\x31\x59\x28\xD2\xB1\x75\x17"
+	"\x88\x04\x4A\x78\x62\x18\x2E\xF5\xFB\x9B\xEF\x15\xD8\x16\x47\xC6"
+	"\x42\xB1\x02\xDA\x9E\xE3\x84\x90\xB4\x2D\xC3\xCE\x13\xC9\x12\x7D"
+	"\x3E\xCD\x39\x39\xC9\xAD\xA1\x1A\xE6\xD5\xAD\x5A\x09\x4D\x1B\x0C"
+	"\xAB"
+	"\x02\x82\x01\x01" /* prime 2 - integer of 257 bytes */
+	"\x00\xDE\xD5\x1B\xF6\xCD\x83\xB1\xC6\x47\x7E\xB9\xC0\x6B\xA9\xB8"
+	"\x02\xF3\xAE\x40\x5D\xFC\xD3\xE5\x4E\xF1\xE3\x39\x04\x52\x84\x89"
+	"\x40\x37\xBB\xC2\xCD\x7F\x71\x77\x17\xDF\x6A\x4C\x31\x24\x7F\xB9"
+	"\x7E\x7F\xC8\x43\x4A\x3C\xEB\x8D\x1B\x7F\x21\x51\x67\x45\x8F\xA0"
+	"\x36\x29\x3A\x18\x45\xA5\x32\xEC\x74\x88\x3C\x98\x5D\x67\x3B\xD7"
+	"\x51\x1F\xE9\xAE\x09\x01\xDE\xDE\x7C\xFB\x60\xD1\xA5\x6C\xE9\x6A"
+	"\x93\x04\x02\x3A\xBB\x67\x02\xB9\xFD\x23\xF0\x02\x2B\x49\x85\xC9"
+	"\x5B\xE7\x4B\xDF\xA3\xF4\xEE\x59\x4C\x45\xEF\x8B\xC1\x6B\xDE\xDE"
+	"\xBC\x1A\xFC\xD2\x76\x3F\x33\x74\xA9\x8E\xA3\x7E\x0C\xC6\xCE\x70"
+	"\xA1\x5B\xA6\x77\xEA\x76\xEB\x18\xCE\xB9\xD7\x78\x8D\xAE\x06\xBB"
+	"\xD3\x1F\x16\x0D\x05\xAB\x4F\xC6\x52\xC8\x6B\x36\x51\x7D\x1D\x27"
+	"\xAF\x88\x9A\x6F\xCC\x25\x2E\x74\x06\x72\xCE\x9E\xDB\xE0\x9D\x30"
+	"\xEF\x55\xA5\x58\x21\xA7\x42\x12\x2C\x2C\x23\x87\xC1\x0F\xE8\x51"
+	"\xDA\x53\xDA\xFC\x05\x36\xDF\x08\x0E\x08\x36\xBE\x5C\x86\x9E\xCA"
+	"\x68\x90\x33\x12\x0B\x14\x82\xAB\x90\x1A\xD4\x49\x32\x9C\xBD\xAA"
+	"\xAB\x4E\x38\xF1\xEE\xED\x3D\x3F\xE8\xBD\x48\x56\xA6\x64\xEE\xC8"
+	"\xD7"
+	"\x02\x82\x01\x01" /* exponent 1 - integer of 257 bytes */
+	"\x00\x96\x5E\x6F\x8F\x06\xD6\xE6\x03\x1F\x96\x76\x81\x38\xBF\x30"
+	"\xCC\x40\x84\xAF\xD0\xE7\x06\xA5\x24\x0E\xCE\x59\xA5\x26\xFE\x0F"
+	"\x74\xBB\x83\xC6\x26\x02\xAF\x3C\xA3\x6B\x9C\xFF\x68\x0C\xEB\x40"
+	"\x42\x46\xCB\x2E\x5E\x2C\xF4\x3A\x32\x77\x77\xED\xAF\xBA\x02\x17"
+	"\xE1\x93\xF0\x43\x4A\x8F\x31\x39\xEF\x72\x0F\x6B\x79\x10\x59\x84"
+	"\xBA\x5A\x55\x7F\x0E\xDB\xEE\xEE\xD6\xA9\xB8\x44\x9F\x3A\xC6\xB9"
+	"\x33\x3B\x5C\x90\x11\xD0\x9B\xCC\x8A\xBF\x0E\x10\x5B\x4B\xF1\x50"
+	"\x9E\x35\xB3\xE0\x6D\x7A\x95\x9C\x38\x5D\xC0\x75\x13\xC2\x15\xA7"
+	"\x81\xEA\xBA\xF7\x4D\x9E\x85\x9D\xF1\x7D\xBA\xD0\x45\x6F\x2A\xD0"
+	"\x76\xC2\x28\xD0\xAD\xA7\xB5\xDC\xE3\x6A\x99\xFF\x83\x50\xB3\x75"
+	"\x07\x14\x91\xAF\xEF\x74\xB5\x9F\x9A\xE0\xBA\xA9\x0B\x87\xF3\x85"
+	"\x5C\x40\xB2\x0E\xA7\xFD\xC6\xED\x45\x8E\xD9\x7C\xB0\xB2\x68\xC6"
+	"\x1D\xFD\x70\x78\x06\x41\x7F\x95\x12\x36\x9D\xE2\x58\x5D\x15\xEE"
+	"\x41\x49\xF5\xFA\xEC\x56\x19\xA0\xE6\xE0\xB2\x40\xE1\xD9\xD0\x03"
+	"\x22\x02\xCF\xD1\x3C\x07\x38\x65\x8F\x65\x0E\xAA\x32\xCE\x25\x05"
+	"\x16\x73\x51\xB9\x9F\x88\x0B\xCD\x30\xF3\x97\xCC\x2B\x6B\xA4\x0E"
+	"\x6F"
+	"\x02\x82\x01\x00" /* exponent 2 - integer of 256 bytes */
+	"\x2A\x5F\x3F\xB8\x08\x90\x58\x47\xA9\xE4\xB1\x11\xA3\xE7\x5B\xF4"
+	"\x43\xBE\x08\xC3\x56\x86\x3C\x7E\x6C\x84\x96\x9C\xF9\xCB\xF6\x05"
+	"\x5E\x13\xB8\x11\x37\x80\xAD\xF2\xBE\x2B\x0A\x5D\xF5\xE0\xCB\xB7"
+	"\x00\x39\x66\x82\x41\x5F\x51\x2F\xBF\x56\xE8\x91\xC8\xAA\x6C\xFE"
+	"\x9F\x8C\x4A\x7D\x43\xD2\x91\x1F\xFF\x9F\xF6\x21\x1C\xB6\x46\x55"
+	"\x48\xCA\x38\xAB\xC1\xCD\x4D\x65\x5A\xAF\xA8\x6D\xDA\x6D\xF0\x34"
+	"\x10\x79\x14\x0D\xFA\xA2\x8C\x17\x54\xB4\x18\xD5\x7E\x5F\x90\x50"
+	"\x87\x84\xE7\xFB\xD7\x61\x53\x5D\xAB\x96\xC7\x6E\x7A\x42\xA0\xFC"
+	"\x07\xED\xB7\x5F\x80\xD9\x19\xFF\xFB\xFD\x9E\xC4\x73\x31\x62\x3D"
+	"\x6C\x9E\x15\x03\x62\xA5\x85\xCC\x19\x8E\x9D\x7F\xE3\x6D\xA8\x5D"
+	"\x96\xF5\xAC\x78\x3D\x81\x27\xE7\x29\xF1\x29\x1D\x09\xBB\x77\x86"
+	"\x6B\x65\x62\x88\xE1\x31\x1A\x22\xF7\xC5\xCE\x73\x65\x1C\xBE\xE7"
+	"\x63\xD3\xD3\x14\x63\x27\xAF\x28\xF3\x23\xB6\x76\xC1\xBD\x9D\x82"
+	"\xF4\x9B\x19\x7D\x2C\x57\xF0\xC2\x2A\x51\xAE\x95\x0D\x8C\x38\x54"
+	"\xF5\xC6\xA0\x51\xB7\x0E\xB9\xEC\xE7\x0D\x22\xF6\x1A\xD3\xFE\x16"
+	"\x21\x03\xB7\x0D\x85\xD3\x35\xC9\xDD\xE4\x59\x85\xBE\x7F\xA1\x75"
+	"\x02\x82\x01\x01" /* coefficient - integer of 257 bytes */
+	"\x00\xB9\x48\xD2\x54\x2F\x19\x54\x64\xAE\x62\x80\x61\x89\x80\xB4"
+	"\x48\x0B\x8D\x7E\x1B\x0F\x50\x08\x82\x3F\xED\x75\x84\xB7\x13\xE4"
+	"\xF8\x8D\xA8\xBB\x54\x21\x4C\x5A\x54\x07\x16\x4B\xB4\xA4\x9E\x30"
+	"\xBF\x7A\x30\x1B\x39\x60\xA3\x21\x53\xFB\xB0\xDC\x0F\x7C\x2C\xFB"
+	"\xAA\x95\x7D\x51\x39\x28\x33\x1F\x25\x31\x53\xF5\xD2\x64\x2B\xF2"
+	"\x1E\xB3\xC0\x6A\x0B\xC9\xA4\x42\x64\x5C\xFB\x15\xA3\xE8\x4C\x3A"
+	"\x9C\x3C\xBE\xA3\x39\x83\x23\xE3\x6D\x18\xCC\xC2\xDC\x63\x8D\xBA"
+	"\x98\xE0\xE0\x31\x4A\x2B\x37\x9C\x4D\x6B\xF3\x9F\x51\xE4\x43\x5C"
+	"\x83\x5F\xBF\x5C\xFE\x92\x45\x01\xAF\xF5\xC2\xF4\xB7\x56\x93\xA5"
+	"\xF4\xAA\x67\x3C\x48\x37\xBD\x9A\x3C\xFE\xA5\x9A\xB0\xD1\x6B\x85"
+	"\xDD\x81\xD4\xFA\xAD\x31\x83\xA8\x22\x9B\xFD\xB4\x61\xDC\x7A\x51"
+	"\x59\x62\x10\x1B\x7E\x44\xA3\xFE\x90\x51\x5A\x3E\x02\x87\xAD\xFA"
+	"\xDD\x0B\x1F\x3D\x35\xAF\xEE\x13\x85\x51\xA7\x42\xC0\xEE\x9E\x20"
+	"\xE9\xD0\x29\xB2\xE4\x21\xE4\x6D\x62\xB9\xF4\x48\x4A\xD8\x46\x8E"
+	"\x61\xA6\x2C\x5D\xDF\x8F\x97\x2B\x3A\x75\x1D\x83\x17\x6F\xC6\xB0"
+	"\xDE\xFC\x14\x25\x06\x5A\x60\xBB\xB8\x21\x89\xD1\xEF\x57\xF1\x71"
+	"\x3D",
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\x5c\xce\x9c\xd7\x9a\x9e\xa1\xfe\x7a\x82\x3c\x68\x27\x98\xe3\x5d"
+	"\xd5\xd7\x07\x29\xf5\xfb\xc3\x1a\x7f\x63\x1e\x62\x31\x3b\x19\x87"
+	"\x79\x4f\xec\x7b\xf3\xcb\xea\x9b\x95\x52\x3a\x40\xe5\x87\x7b\x72"
+	"\xd1\x72\xc9\xfb\x54\x63\xd8\xc9\xd7\x2c\xfc\x7b\xc3\x14\x1e\xbc"
+	"\x18\xb4\x34\xa1\xbf\x14\xb1\x37\x31\x6e\xf0\x1b\x35\x19\x54\x07"
+	"\xf7\x99\xec\x3e\x63\xe2\xcd\x61\x28\x65\xc3\xcd\xb1\x38\x36\xa5"
+	"\xb2\xd7\xb0\xdc\x1f\xf5\xef\x19\xc7\x53\x32\x2d\x1c\x26\xda\xe4"
+	"\x0d\xd6\x90\x7e\x28\xd8\xdc\xe4\x61\x05\xd2\x25\x90\x01\xd3\x96"
+	"\x6d\xa6\xcf\x58\x20\xbb\x03\xf4\x01\xbc\x79\xb9\x18\xd8\xb8\xba"
+	"\xbd\x93\xfc\xf2\x62\x5d\x8c\x66\x1e\x0e\x84\x59\x93\xdd\xe2\x93"
+	"\xa2\x62\x7d\x08\x82\x7a\xdd\xfc\xb8\xbc\xc5\x4f\x9c\x4e\xbf\xb4"
+	"\xfc\xf4\xc5\x01\xe8\x00\x70\x4d\x28\x26\xcc\x2e\xfe\x0e\x58\x41"
+	"\x8b\xec\xaf\x7c\x4b\x54\xd0\xa0\x64\xf9\x32\xf4\x2e\x47\x65\x0a"
+	"\x67\x88\x39\x3a\xdb\xb2\xdb\x7b\xb5\xf6\x17\xa8\xd9\xc6\x5e\x28"
+	"\x13\x82\x8a\x99\xdb\x60\x08\xa5\x23\x37\xfa\x88\x90\x31\xc8\x9d"
+	"\x8f\xec\xfb\x85\x9f\xb1\xce\xa6\x24\x50\x46\x44\x47\xcb\x65\xd1"
+	"\xdf\xc0\xb1\x6c\x90\x1f\x99\x8e\x4d\xd5\x9e\x31\x07\x66\x87\xdf"
+	"\x01\xaa\x56\x3c\x71\xe0\x2b\x6f\x67\x3b\x23\xed\xc2\xbd\x03\x30"
+	"\x79\x76\x02\x10\x10\x98\x85\x8a\xff\xfd\x0b\xda\xa5\xd9\x32\x48"
+	"\x02\xa0\x0b\xb9\x2a\x8a\x18\xca\xc6\x8f\x3f\xbb\x16\xb2\xaa\x98"
+	"\x27\xe3\x60\x43\xed\x15\x70\xd4\x57\x15\xfe\x19\xd4\x9b\x13\x78"
+	"\x8a\xf7\x21\xf1\xa2\xa2\x2d\xb3\x09\xcf\x44\x91\x6e\x08\x3a\x30"
+	"\x81\x3e\x90\x93\x8a\x67\x33\x00\x59\x54\x9a\x25\xd3\x49\x8e\x9f"
+	"\xc1\x4b\xe5\x86\xf3\x50\x4c\xbc\xc5\xd3\xf5\x3a\x54\xe1\x36\x3f"
+	"\xe2\x5a\xb4\x37\xc0\xeb\x70\x35\xec\xf6\xb7\xe8\x44\x3b\x7b\xf3"
+	"\xf1\xf2\x1e\xdb\x60\x7d\xd5\xbe\xf0\x71\x34\x90\x4c\xcb\xd4\x35"
+	"\x51\xc7\xdd\xd8\xc9\x81\xf5\x5d\x57\x46\x2c\xb1\x7b\x9b\xaa\xcb"
+	"\xd1\x22\x25\x49\x44\xa3\xd4\x6b\x29\x7b\xd8\xb2\x07\x93\xbf\x3d"
+	"\x52\x49\x84\x79\xef\xb8\xe5\xc4\xad\xca\xa8\xc6\xf6\xa6\x76\x70"
+	"\x5b\x0b\xe5\x83\xc6\x0e\xef\x55\xf2\xe7\xff\x04\xea\xe6\x13\xbe"
+	"\x40\xe1\x40\x45\x48\x66\x75\x31\xae\x35\x64\x91\x11\x6f\xda\xee"
+	"\x26\x86\x45\x6f\x0b\xd5\x9f\x03\xb1\x65\x5b\xdb\xa4\xe4\xf9\x45",
+	.key_len = 2349,
+	.m_size = 8,
+	.c_size = 512,
+	}
+};
+
+#define DH_TEST_VECTORS 2
+
+struct kpp_testvec dh_tv_template[] = {
+	{
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x01\x00" /* type */
+	"\x11\x02" /* len */
+	"\x00\x01\x00\x00" /* key_size */
+	"\x00\x01\x00\x00" /* p_size */
+	"\x01\x00\x00\x00" /* g_size */
+#else
+	"\x00\x01" /* type */
+	"\x02\x11" /* len */
+	"\x00\x00\x01\x00" /* key_size */
+	"\x00\x00\x01\x00" /* p_size */
+	"\x00\x00\x00\x01" /* g_size */
+#endif
+	/* xa */
+	"\x44\xc1\x48\x36\xa7\x2b\x6f\x4e\x43\x03\x68\xad\x31\x00\xda\xf3"
+	"\x2a\x01\xa8\x32\x63\x5f\x89\x32\x1f\xdf\x4c\xa1\x6a\xbc\x10\x15"
+	"\x90\x35\xc9\x26\x41\xdf\x7b\xaa\x56\x56\x3d\x85\x44\xb5\xc0\x8e"
+	"\x37\x83\x06\x50\xb3\x5f\x0e\x28\x2c\xd5\x46\x15\xe3\xda\x7d\x74"
+	"\x87\x13\x91\x4f\xd4\x2d\xf6\xc7\x5e\x14\x2c\x11\xc2\x26\xb4\x3a"
+	"\xe3\xb2\x36\x20\x11\x3b\x22\xf2\x06\x65\x66\xe2\x57\x58\xf8\x22"
+	"\x1a\x94\xbd\x2b\x0e\x8c\x55\xad\x61\x23\x45\x2b\x19\x1e\x63\x3a"
+	"\x13\x61\xe3\xa0\x79\x70\x3e\x6d\x98\x32\xbc\x7f\x82\xc3\x11\xd8"
+	"\xeb\x53\xb5\xfc\xb5\xd5\x3c\x4a\xea\x92\x3e\x01\xce\x15\x65\xd4"
+	"\xaa\x85\xc1\x11\x90\x83\x31\x6e\xfe\xe7\x7f\x7d\xed\xab\xf9\x29"
+	"\xf8\xc7\xf1\x68\xc6\xb7\xe4\x1f\x2f\x28\xa0\xc9\x1a\x50\x64\x29"
+	"\x4b\x01\x6d\x1a\xda\x46\x63\x21\x07\x40\x8c\x8e\x4c\x6f\xb5\xe5"
+	"\x12\xf3\xc2\x1b\x48\x27\x5e\x27\x01\xb1\xaa\xed\x68\x9b\x83\x18"
+	"\x8f\xb1\xeb\x1f\x04\xd1\x3c\x79\xed\x4b\xf7\x0a\x33\xdc\xe0\xc6"
+	"\xd8\x02\x51\x59\x00\x74\x30\x07\x4c\x2d\xac\xe4\x13\xf1\x80\xf0"
+	"\xce\xfa\xff\xa9\xce\x29\x46\xdd\x9d\xad\xd1\xc3\xc6\x58\x1a\x63"
+	/* p */
+	"\xb9\x36\x3a\xf1\x82\x1f\x60\xd3\x22\x47\xb8\xbc\x2d\x22\x6b\x81"
+	"\x7f\xe8\x20\x06\x09\x23\x73\x49\x9a\x59\x8b\x35\x25\xf8\x31\xbc"
+	"\x7d\xa8\x1c\x9d\x56\x0d\x1a\xf7\x4b\x4f\x96\xa4\x35\x77\x6a\x89"
+	"\xab\x42\x00\x49\x21\x71\xed\x28\x16\x1d\x87\x5a\x10\xa7\x9c\x64"
+	"\x94\xd4\x87\x3d\x28\xef\x44\xfe\x4b\xe2\xb4\x15\x8c\x82\xa6\xf3"
+	"\x50\x5f\xa8\xe8\xa2\x60\xe7\x00\x86\x78\x05\xd4\x78\x19\xa1\x98"
+	"\x62\x4e\x4a\x00\x78\x56\x96\xe6\xcf\xd7\x10\x1b\x74\x5d\xd0\x26"
+	"\x61\xdb\x6b\x32\x09\x51\xd8\xa5\xfd\x54\x16\x71\x01\xb3\x39\xe6"
+	"\x4e\x69\xb1\xd7\x06\x8f\xd6\x1e\xdc\x72\x25\x26\x74\xc8\x41\x06"
+	"\x5c\xd1\x26\x5c\xb0\x2f\xf9\x59\x13\xc1\x2a\x0f\x78\xea\x7b\xf7"
+	"\xbd\x59\xa0\x90\x1d\xfc\x33\x5b\x4c\xbf\x05\x9c\x3a\x3f\x69\xa2"
+	"\x45\x61\x4e\x10\x6a\xb3\x17\xc5\x68\x30\xfb\x07\x5f\x34\xc6\xfb"
+	"\x73\x07\x3c\x70\xf6\xae\xe7\x72\x84\xc3\x18\x81\x8f\xe8\x11\x1f"
+	"\x3d\x83\x83\x01\x2a\x14\x73\xbf\x32\x32\x2e\xc9\x4d\xdb\x2a\xca"
+	"\xee\x71\xf9\xda\xad\xe8\x82\x0b\x4d\x0c\x1f\xb6\x1d\xef\x00\x67"
+	"\x74\x3d\x95\xe0\xb7\xc4\x30\x8a\x24\x87\x12\x47\x27\x70\x0d\x73"
+	/* g */
+	"\x02",
+	.b_public =
+	"\x2a\x67\x5c\xfd\x63\x5d\xc0\x97\x0a\x8b\xa2\x1f\xf8\x8a\xcb\x54"
+	"\xca\x2f\xd3\x49\x3f\x01\x8e\x87\xfe\xcc\x94\xa0\x3e\xd4\x26\x79"
+	"\x9a\x94\x3c\x11\x81\x58\x5c\x60\x3d\xf5\x98\x90\x89\x64\x62\x1f"
+	"\xbd\x05\x6d\x2b\xcd\x84\x40\x9b\x4a\x1f\xe0\x19\xf1\xca\x20\xb3"
+	"\x4e\xa0\x4f\x15\xcc\xa5\xfe\xa5\xb4\xf5\x0b\x18\x7a\x5a\x37\xaa"
+	"\x58\x00\x19\x7f\xe2\xa3\xd9\x1c\x44\x57\xcc\xde\x2e\xc1\x38\xea"
+	"\xeb\xe3\x90\x40\xc4\x6c\xf7\xcd\xe9\x22\x50\x71\xf5\x7c\xdb\x37"
+	"\x0e\x80\xc3\xed\x7e\xb1\x2b\x2f\xbe\x71\xa6\x11\xa5\x9d\xf5\x39"
+	"\xf1\xa2\xe5\x85\xbc\x25\x91\x4e\x84\x8d\x26\x9f\x4f\xe6\x0f\xa6"
+	"\x2b\x6b\xf9\x0d\xaf\x6f\xbb\xfa\x2d\x79\x15\x31\x57\xae\x19\x60"
+	"\x22\x0a\xf5\xfd\x98\x0e\xbf\x5d\x49\x75\x58\x37\xbc\x7f\xf5\x21"
+	"\x56\x1e\xd5\xb3\x50\x0b\xca\x96\xf3\xd1\x3f\xb3\x70\xa8\x6d\x63"
+	"\x48\xfb\x3d\xd7\x29\x91\x45\xb5\x48\xcd\xb6\x78\x30\xf2\x3f\x1e"
+	"\xd6\x22\xd6\x35\x9b\xf9\x1f\x85\xae\xab\x4b\xd7\xe0\xc7\x86\x67"
+	"\x3f\x05\x7f\xa6\x0d\x2f\x0d\xbf\x53\x5f\x4d\x2c\x6d\x5e\x57\x40"
+	"\x30\x3a\x23\x98\xf9\xb4\x32\xf5\x32\x83\xdd\x0b\xae\x33\x97\x2f",
+	.expected_a_public =
+	"\x5c\x24\xdf\xeb\x5b\x4b\xf8\xc5\xef\x39\x48\x82\xe0\x1e\x62\xee"
+	"\x8a\xae\xdf\x93\x6c\x2b\x16\x95\x92\x16\x3f\x16\x7b\x75\x03\x85"
+	"\xd9\xf1\x69\xc2\x14\x87\x45\xfc\xa4\x19\xf6\xf0\xa4\xf3\xec\xd4"
+	"\x6c\x5c\x03\x3b\x94\xc2\x2f\x92\xe4\xce\xb3\xe4\x72\xe8\x17\xe6"
+	"\x23\x7e\x00\x01\x09\x59\x13\xbf\xc1\x2f\x99\xa9\x07\xaa\x02\x23"
+	"\x4a\xca\x39\x4f\xbc\xec\x0f\x27\x4f\x19\x93\x6c\xb9\x30\x52\xfd"
+	"\x2b\x9d\x86\xf1\x06\x1e\xb6\x56\x27\x4a\xc9\x8a\xa7\x8a\x48\x5e"
+	"\xb5\x60\xcb\xdf\xff\x03\x26\x10\xbf\x90\x8f\x46\x60\xeb\x9b\x9a"
+	"\xd6\x6f\x44\x91\x03\x92\x18\x2c\x96\x5e\x40\x19\xfb\xf4\x4f\x3a"
+	"\x02\x7b\xaf\xcc\x22\x20\x79\xb9\xf8\x9f\x8f\x85\x6b\xec\x44\xbb"
+	"\xe6\xa8\x8e\xb1\xe8\x2c\xee\x64\xee\xf8\xbd\x00\xf3\xe2\x2b\x93"
+	"\xcd\xe7\xc4\xdf\xc9\x19\x46\xfe\xb6\x07\x73\xc1\x8a\x64\x79\x26"
+	"\xe7\x30\xad\x2a\xdf\xe6\x8f\x59\xf5\x81\xbf\x4a\x29\x91\xe7\xb7"
+	"\xcf\x48\x13\x27\x75\x79\x40\xd9\xd6\x32\x52\x4e\x6a\x86\xae\x6f"
+	"\xc2\xbf\xec\x1f\xc2\x69\xb2\xb6\x59\xe5\xa5\x17\xa4\x77\xb7\x62"
+	"\x46\xde\xe8\xd2\x89\x78\x9a\xef\xa3\xb5\x8f\x26\xec\x80\xda\x39",
+	.expected_ss =
+	"\x8f\xf3\xac\xa2\xea\x22\x11\x5c\x45\x65\x1a\x77\x75\x2e\xcf\x46"
+	"\x23\x14\x1e\x67\x53\x4d\x35\xb0\x38\x1d\x4e\xb9\x41\x9a\x21\x24"
+	"\x6e\x9f\x40\xfe\x90\x51\xb1\x06\xa4\x7b\x87\x17\x2f\xe7\x5e\x22"
+	"\xf0\x7b\x54\x84\x0a\xac\x0a\x90\xd2\xd7\xe8\x7f\xe7\xe3\x30\x75"
+	"\x01\x1f\x24\x75\x56\xbe\xcc\x8d\x1e\x68\x0c\x41\x72\xd3\xfa\xbb"
+	"\xe5\x9c\x60\xc7\x28\x77\x0c\xbe\x89\xab\x08\xd6\x21\xe7\x2e\x1a"
+	"\x58\x7a\xca\x4f\x22\xf3\x2b\x30\xfd\xf4\x98\xc1\xa3\xf8\xf6\xcc"
+	"\xa9\xe4\xdb\x5b\xee\xd5\x5c\x6f\x62\x4c\xd1\x1a\x02\x2a\x23\xe4"
+	"\xb5\x57\xf3\xf9\xec\x04\x83\x54\xfe\x08\x5e\x35\xac\xfb\xa8\x09"
+	"\x82\x32\x60\x11\xb2\x16\x62\x6b\xdf\xda\xde\x9c\xcb\x63\x44\x6c"
+	"\x59\x26\x6a\x8f\xb0\x24\xcb\xa6\x72\x48\x1e\xeb\xe0\xe1\x09\x44"
+	"\xdd\xee\x66\x6d\x84\xcf\xa5\xc1\xb8\x36\x74\xd3\x15\x96\xc3\xe4"
+	"\xc6\x5a\x4d\x23\x97\x0c\x5c\xcb\xa9\xf5\x29\xc2\x0e\xff\x93\x82"
+	"\xd3\x34\x49\xad\x64\xa6\xb1\xc0\x59\x28\x75\x60\xa7\x8a\xb0\x11"
+	"\x56\x89\x42\x74\x11\xf5\xf6\x5e\x6f\x16\x54\x6a\xb1\x76\x4d\x50"
+	"\x8a\x68\xc1\x5b\x82\xb9\x0d\x00\x32\x50\xed\x88\x87\x48\x92\x17",
+	.secret_size = 529,
+	.b_public_size = 256,
+	.expected_a_public_size = 256,
+	.expected_ss_size = 256,
+	},
+	{
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x01\x00" /* type */
+	"\x11\x02" /* len */
+	"\x00\x01\x00\x00" /* key_size */
+	"\x00\x01\x00\x00" /* p_size */
+	"\x01\x00\x00\x00" /* g_size */
+#else
+	"\x00\x01" /* type */
+	"\x02\x11" /* len */
+	"\x00\x00\x01\x00" /* key_size */
+	"\x00\x00\x01\x00" /* p_size */
+	"\x00\x00\x00\x01" /* g_size */
+#endif
+	/* xa */
+	"\x4d\x75\xa8\x6e\xba\x23\x3a\x0c\x63\x56\xc8\xc9\x5a\xa7\xd6\x0e"
+	"\xed\xae\x40\x78\x87\x47\x5f\xe0\xa7\x7b\xba\x84\x88\x67\x4e\xe5"
+	"\x3c\xcc\x5c\x6a\xe7\x4a\x20\xec\xbe\xcb\xf5\x52\x62\x9f\x37\x80"
+	"\x0c\x72\x7b\x83\x66\xa4\xf6\x7f\x95\x97\x1c\x6a\x5c\x7e\xf1\x67"
+	"\x37\xb3\x93\x39\x3d\x0b\x55\x35\xd9\xe5\x22\x04\x9f\xf8\xc1\x04"
+	"\xce\x13\xa5\xac\xe1\x75\x05\xd1\x2b\x53\xa2\x84\xef\xb1\x18\xf4"
+	"\x66\xdd\xea\xe6\x24\x69\x5a\x49\xe0\x7a\xd8\xdf\x1b\xb7\xf1\x6d"
+	"\x9b\x50\x2c\xc8\x1c\x1c\xa3\xb4\x37\xfb\x66\x3f\x67\x71\x73\xa9"
+	"\xff\x5f\xd9\xa2\x25\x6e\x25\x1b\x26\x54\xbf\x0c\xc6\xdb\xea\x0a"
+	"\x52\x6c\x16\x7c\x27\x68\x15\x71\x58\x73\x9d\xe6\xc2\x80\xaa\x97"
+	"\x31\x66\xfb\xa6\xfb\xfd\xd0\x9c\x1d\xbe\x81\x48\xf5\x9a\x32\xf1"
+	"\x69\x62\x18\x78\xae\x72\x36\xe6\x94\x27\xd1\xff\x18\x4f\x28\x6a"
+	"\x16\xbd\x6a\x60\xee\xe5\xf9\x6d\x16\xe4\xb8\xa6\x41\x9b\x23\x7e"
+	"\xf7\x9d\xd1\x1d\x03\x15\x66\x3a\xcf\xb6\x2c\x13\x96\x2c\x52\x21"
+	"\xe4\x2d\x48\x7a\x8a\x5d\xb2\x88\xed\x98\x61\x79\x8b\x6a\x1e\x5f"
+	"\xd0\x8a\x2d\x99\x5a\x2b\x0f\xbc\xef\x53\x8f\x32\xc1\xa2\x99\x26"
+	/* p */
+	"\xb9\x36\x3a\xf1\x82\x1f\x60\xd3\x22\x47\xb8\xbc\x2d\x22\x6b\x81"
+	"\x7f\xe8\x20\x06\x09\x23\x73\x49\x9a\x59\x8b\x35\x25\xf8\x31\xbc"
+	"\x7d\xa8\x1c\x9d\x56\x0d\x1a\xf7\x4b\x4f\x96\xa4\x35\x77\x6a\x89"
+	"\xab\x42\x00\x49\x21\x71\xed\x28\x16\x1d\x87\x5a\x10\xa7\x9c\x64"
+	"\x94\xd4\x87\x3d\x28\xef\x44\xfe\x4b\xe2\xb4\x15\x8c\x82\xa6\xf3"
+	"\x50\x5f\xa8\xe8\xa2\x60\xe7\x00\x86\x78\x05\xd4\x78\x19\xa1\x98"
+	"\x62\x4e\x4a\x00\x78\x56\x96\xe6\xcf\xd7\x10\x1b\x74\x5d\xd0\x26"
+	"\x61\xdb\x6b\x32\x09\x51\xd8\xa5\xfd\x54\x16\x71\x01\xb3\x39\xe6"
+	"\x4e\x69\xb1\xd7\x06\x8f\xd6\x1e\xdc\x72\x25\x26\x74\xc8\x41\x06"
+	"\x5c\xd1\x26\x5c\xb0\x2f\xf9\x59\x13\xc1\x2a\x0f\x78\xea\x7b\xf7"
+	"\xbd\x59\xa0\x90\x1d\xfc\x33\x5b\x4c\xbf\x05\x9c\x3a\x3f\x69\xa2"
+	"\x45\x61\x4e\x10\x6a\xb3\x17\xc5\x68\x30\xfb\x07\x5f\x34\xc6\xfb"
+	"\x73\x07\x3c\x70\xf6\xae\xe7\x72\x84\xc3\x18\x81\x8f\xe8\x11\x1f"
+	"\x3d\x83\x83\x01\x2a\x14\x73\xbf\x32\x32\x2e\xc9\x4d\xdb\x2a\xca"
+	"\xee\x71\xf9\xda\xad\xe8\x82\x0b\x4d\x0c\x1f\xb6\x1d\xef\x00\x67"
+	"\x74\x3d\x95\xe0\xb7\xc4\x30\x8a\x24\x87\x12\x47\x27\x70\x0d\x73"
+	/* g */
+	"\x02",
+	.b_public =
+	"\x99\x4d\xd9\x01\x84\x8e\x4a\x5b\xb8\xa5\x64\x8c\x6c\x00\x5c\x0e"
+	"\x1e\x1b\xee\x5d\x9f\x53\xe3\x16\x70\x01\xed\xbf\x4f\x14\x36\x6e"
+	"\xe4\x43\x45\x43\x49\xcc\xb1\xb0\x2a\xc0\x6f\x22\x55\x42\x17\x94"
+	"\x18\x83\xd7\x2a\x5c\x51\x54\xf8\x4e\x7c\x10\xda\x76\x68\x57\x77"
+	"\x1e\x62\x03\x30\x04\x7b\x4c\x39\x9c\x54\x01\x54\xec\xef\xb3\x55"
+	"\xa4\xc0\x24\x6d\x3d\xbd\xcc\x46\x5b\x00\x96\xc7\xea\x93\xd1\x3f"
+	"\xf2\x6a\x72\xe3\xf2\xc1\x92\x24\x5b\xda\x48\x70\x2c\xa9\x59\x97"
+	"\x19\xb1\xd6\x54\xb3\x9c\x2e\xb0\x63\x07\x9b\x5e\xac\xb5\xf2\xb1"
+	"\x5b\xf8\xf3\xd7\x2d\x37\x9b\x68\x6c\xf8\x90\x07\xbc\x37\x9a\xa5"
+	"\xe2\x91\x12\x25\x47\x77\xe3\x3d\xb2\x95\x69\x44\x0b\x91\x1e\xaf"
+	"\x7c\x8c\x7c\x34\x41\x6a\xab\x60\x6e\xc6\x52\xec\x7e\x94\x0a\x37"
+	"\xec\x98\x90\xdf\x3f\x02\xbd\x23\x52\xdd\xd9\xe5\x31\x80\x74\x25"
+	"\xb6\xd2\xd3\xcc\xd5\xcc\x6d\xf9\x7e\x4d\x78\xab\x77\x51\xfa\x77"
+	"\x19\x94\x49\x8c\x05\xd4\x75\xed\xd2\xb3\x64\x57\xe0\x52\x99\xc0"
+	"\x83\xe3\xbb\x5e\x2b\xf1\xd2\xc0\xb1\x37\x36\x0b\x7c\xb5\x63\x96"
+	"\x8e\xde\x04\x23\x11\x95\x62\x11\x9a\xce\x6f\x63\xc8\xd5\xd1\x8f",
+	.expected_a_public =
+	"\x90\x89\xe4\x82\xd6\x0a\xcf\x1a\xae\xce\x1b\x66\xa7\x19\x71\x18"
+	"\x8f\x95\x4b\x5b\x80\x45\x4a\x5a\x43\x99\x4d\x37\xcf\xa3\xa7\x28"
+	"\x9c\xc7\x73\xf1\xb2\x17\xf6\x99\xe3\x6b\x56\xcb\x3e\x35\x60\x7d"
+	"\x65\xc7\x84\x6b\x3e\x60\xee\xcd\xd2\x70\xe7\xc9\x32\x1c\xf0\xb4"
+	"\xf9\x52\xd9\x88\x75\xfd\x40\x2c\xa7\xbe\x19\x1c\x0a\xae\x93\xe1"
+	"\x71\xc7\xcd\x4f\x33\x5c\x10\x7d\x39\x56\xfc\x73\x84\xb2\x67\xc3"
+	"\x77\x26\x20\x97\x2b\xf8\x13\x43\x93\x9c\x9a\xa4\x08\xc7\x34\x83"
+	"\xe6\x98\x61\xe7\x16\x30\x2c\xb1\xdb\x2a\xb2\xcc\xc3\x02\xa5\x3c"
+	"\x71\x50\x14\x83\xc7\xbb\xa4\xbe\x98\x1b\xfe\xcb\x43\xe9\x97\x62"
+	"\xd6\xf0\x8c\xcb\x1c\xba\x1e\xa8\xa6\xa6\x50\xfc\x85\x7d\x47\xbf"
+	"\xf4\x3e\x23\xd3\x5f\xb2\x71\x3e\x40\x94\xaa\x87\x83\x2c\x6c\x8e"
+	"\x60\xfd\xdd\xf7\xf4\x76\x03\xd3\x1d\xec\x18\x51\xa3\xf2\x44\x1a"
+	"\x3f\xb4\x7c\x18\x0d\x68\x65\x92\x54\x0d\x2d\x81\x16\xf1\x84\x66"
+	"\x89\x92\xd0\x1a\x5e\x1f\x42\x46\x5b\xe5\x83\x86\x80\xd9\xcd\x3a"
+	"\x5a\x2f\xb9\x59\x9b\xe4\x43\x84\x64\xf3\x09\x1a\x0a\xa2\x64\x0f"
+	"\x77\x4e\x8d\x8b\xe6\x88\xd1\xfc\xaf\x8f\xdf\x1d\xbc\x31\xb3\xbd",
+	.expected_ss =
+	"\x34\xc3\x35\x14\x88\x46\x26\x23\x97\xbb\xdd\x28\x5c\x94\xf6\x47"
+	"\xca\xb3\x19\xaf\xca\x44\x9b\xc2\x7d\x89\xfd\x96\x14\xfd\x6d\x58"
+	"\xd8\xc4\x6b\x61\x2a\x0d\xf2\x36\x45\xc8\xe4\xa4\xed\x81\x53\x81"
+	"\x66\x1e\xe0\x5a\xb1\x78\x2d\x0b\x5c\xb4\xd1\xfc\x90\xc6\x9c\xdb"
+	"\x5a\x30\x0b\x14\x7d\xbe\xb3\x7d\xb1\xb2\x76\x3c\x6c\xef\x74\x6b"
+	"\xe7\x1f\x64\x0c\xab\x65\xe1\x76\x5c\x3d\x83\xb5\x8a\xfb\xaf\x0f"
+	"\xf2\x06\x14\x8f\xa0\xf6\xc1\x89\x78\xf2\xba\x72\x73\x3c\xf7\x76"
+	"\x21\x67\xbc\x24\x31\xb8\x09\x65\x0f\x0c\x02\x32\x4a\x98\x14\xfc"
+	"\x72\x2c\x25\x60\x68\x5f\x2f\x30\x1e\x5b\xf0\x3b\xd1\xa2\x87\xa0"
+	"\x54\xdf\xdb\xc0\xee\x0a\x0f\x47\xc9\x90\x20\x2c\xf9\xe3\x52\xad"
+	"\x27\x65\x8d\x54\x8d\xa8\xa1\xf3\xed\x15\xd4\x94\x28\x90\x31\x93"
+	"\x1b\xc0\x51\xbb\x43\x5d\x76\x3b\x1d\x2a\x71\x50\xea\x5d\x48\x94"
+	"\x7f\x6f\xf1\x48\xdb\x30\xe5\xae\x64\x79\xd9\x7a\xdb\xc6\xff\xd8"
+	"\x5e\x5a\x64\xbd\xf6\x85\x04\xe8\x28\x6a\xac\xef\xce\x19\x8e\x9a"
+	"\xfe\x75\xc0\x27\x69\xe3\xb3\x7b\x21\xa7\xb1\x16\xa4\x85\x23\xee"
+	"\xb0\x1b\x04\x6e\xbd\xab\x16\xde\xfd\x86\x6b\xa9\x95\xd7\x0b\xfd",
+	.secret_size = 529,
+	.b_public_size = 256,
+	.expected_a_public_size = 256,
+	.expected_ss_size = 256,
+	}
+};
+
+#ifdef CONFIG_CRYPTO_FIPS
+#define ECDH_TEST_VECTORS 1
+#else
+#define ECDH_TEST_VECTORS 2
+#endif
+struct kpp_testvec ecdh_tv_template[] = {
+	{
+#ifndef CONFIG_CRYPTO_FIPS
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x02\x00" /* type */
+	"\x20\x00" /* len */
+	"\x01\x00" /* curve_id */
+	"\x18\x00" /* key_size */
+#else
+	"\x00\x02" /* type */
+	"\x00\x20" /* len */
+	"\x00\x01" /* curve_id */
+	"\x00\x18" /* key_size */
+#endif
+	"\xb5\x05\xb1\x71\x1e\xbf\x8c\xda"
+	"\x4e\x19\x1e\x62\x1f\x23\x23\x31"
+	"\x36\x1e\xd3\x84\x2f\xcc\x21\x72",
+	.b_public =
+	"\xc3\xba\x67\x4b\x71\xec\xd0\x76"
+	"\x7a\x99\x75\x64\x36\x13\x9a\x94"
+	"\x5d\x8b\xdc\x60\x90\x91\xfd\x3f"
+	"\xb0\x1f\x8a\x0a\x68\xc6\x88\x6e"
+	"\x83\x87\xdd\x67\x09\xf8\x8d\x96"
+	"\x07\xd6\xbd\x1c\xe6\x8d\x9d\x67",
+	.expected_a_public =
+	"\x1a\x04\xdb\xa5\xe1\xdd\x4e\x79"
+	"\xa3\xe6\xef\x0e\x5c\x80\x49\x85"
+	"\xfa\x78\xb4\xef\x49\xbd\x4c\x7c"
+	"\x22\x90\x21\x02\xf9\x1b\x81\x5d"
+	"\x0c\x8a\xa8\x98\xd6\x27\x69\x88"
+	"\x5e\xbc\x94\xd8\x15\x9e\x21\xce",
+	.expected_ss =
+	"\xf4\x57\xcc\x4f\x1f\x4e\x31\xcc"
+	"\xe3\x40\x60\xc8\x06\x93\xc6\x2e"
+	"\x99\x80\x81\x28\xaf\xc5\x51\x74",
+	.secret_size = 32,
+	.b_public_size = 48,
+	.expected_a_public_size = 48,
+	.expected_ss_size = 24
+	}, {
+#endif
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x02\x00" /* type */
+	"\x28\x00" /* len */
+	"\x02\x00" /* curve_id */
+	"\x20\x00" /* key_size */
+#else
+	"\x00\x02" /* type */
+	"\x00\x28" /* len */
+	"\x00\x02" /* curve_id */
+	"\x00\x20" /* key_size */
+#endif
+	"\x24\xd1\x21\xeb\xe5\xcf\x2d\x83"
+	"\xf6\x62\x1b\x6e\x43\x84\x3a\xa3"
+	"\x8b\xe0\x86\xc3\x20\x19\xda\x92"
+	"\x50\x53\x03\xe1\xc0\xea\xb8\x82",
+	.expected_a_public =
+	"\x1a\x7f\xeb\x52\x00\xbd\x3c\x31"
+	"\x7d\xb6\x70\xc1\x86\xa6\xc7\xc4"
+	"\x3b\xc5\x5f\x6c\x6f\x58\x3c\xf5"
+	"\xb6\x63\x82\x77\x33\x24\xa1\x5f"
+	"\x6a\xca\x43\x6f\xf7\x7e\xff\x02"
+	"\x37\x08\xcc\x40\x5e\x7a\xfd\x6a"
+	"\x6a\x02\x6e\x41\x87\x68\x38\x77"
+	"\xfa\xa9\x44\x43\x2d\xef\x09\xdf",
+	.expected_ss =
+	"\xea\x17\x6f\x7e\x6e\x57\x26\x38"
+	"\x8b\xfb\x41\xeb\xba\xc8\x6d\xa5"
+	"\xa8\x72\xd1\xff\xc9\x47\x3d\xaa"
+	"\x58\x43\x9f\x34\x0f\x8c\xf3\xc9",
+	.b_public =
+	"\xcc\xb4\xda\x74\xb1\x47\x3f\xea"
+	"\x6c\x70\x9e\x38\x2d\xc7\xaa\xb7"
+	"\x29\xb2\x47\x03\x19\xab\xdd\x34"
+	"\xbd\xa8\x2c\x93\xe1\xa4\x74\xd9"
+	"\x64\x63\xf7\x70\x20\x2f\xa4\xe6"
+	"\x9f\x4a\x38\xcc\xc0\x2c\x49\x2f"
+	"\xb1\x32\xbb\xaf\x22\x61\xda\xcb"
+	"\x6f\xdb\xa9\xaa\xfc\x77\x81\xf3",
+	.secret_size = 40,
+	.b_public_size = 64,
+	.expected_a_public_size = 64,
+	.expected_ss_size = 32
 	}
 };
 
@@ -376,6 +897,131 @@ static struct hash_testvec md4_tv_template [] = {
 	},
 };
 
+#define SHA3_224_TEST_VECTORS	3
+static struct hash_testvec sha3_224_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\x6b\x4e\x03\x42\x36\x67\xdb\xb7"
+				"\x3b\x6e\x15\x45\x4f\x0e\xb1\xab"
+				"\xd4\x59\x7f\x9a\x1b\x07\x8e\x3f"
+				"\x5b\x5a\x6b\xc7",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x9e\x86\xff\x69\x55\x7c\xa9\x5f"
+				"\x40\x5f\x08\x12\x69\x68\x5b\x38"
+				"\xe3\xa8\x19\xb3\x09\xee\x94\x2f"
+				"\x48\x2b\x6a\x8b",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+				"jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x8a\x24\x10\x8b\x15\x4a\xda\x21"
+				"\xc9\xfd\x55\x74\x49\x44\x79\xba"
+				"\x5c\x7e\x7a\xb7\x6e\xf2\x64\xea"
+				"\xd0\xfc\xce\x33",
+	},
+};
+
+#define SHA3_256_TEST_VECTORS	3
+static struct hash_testvec sha3_256_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\xa7\xff\xc6\xf8\xbf\x1e\xd7\x66"
+				"\x51\xc1\x47\x56\xa0\x61\xd6\x62"
+				"\xf5\x80\xff\x4d\xe4\x3b\x49\xfa"
+				"\x82\xd8\x0a\x4b\x80\xf8\x43\x4a",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x80\x08\x4b\xf2\xfb\xa0\x24\x75"
+				"\x72\x6f\xeb\x2c\xab\x2d\x82\x15"
+				"\xea\xb1\x4b\xc6\xbd\xd8\xbf\xb2"
+				"\xc8\x15\x12\x57\x03\x2e\xcd\x8b",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+			     "jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x41\xc0\xdb\xa2\xa9\xd6\x24\x08"
+				"\x49\x10\x03\x76\xa8\x23\x5e\x2c"
+				"\x82\xe1\xb9\x99\x8a\x99\x9e\x21"
+				"\xdb\x32\xdd\x97\x49\x6d\x33\x76",
+	},
+};
+
+
+#define SHA3_384_TEST_VECTORS	3
+static struct hash_testvec sha3_384_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\x0c\x63\xa7\x5b\x84\x5e\x4f\x7d"
+				"\x01\x10\x7d\x85\x2e\x4c\x24\x85"
+				"\xc5\x1a\x50\xaa\xaa\x94\xfc\x61"
+				"\x99\x5e\x71\xbb\xee\x98\x3a\x2a"
+				"\xc3\x71\x38\x31\x26\x4a\xdb\x47"
+				"\xfb\x6b\xd1\xe0\x58\xd5\xf0\x04",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x18\x15\xf7\x74\xf3\x20\x49\x1b"
+				"\x48\x56\x9e\xfe\xc7\x94\xd2\x49"
+				"\xee\xb5\x9a\xae\x46\xd2\x2b\xf7"
+				"\x7d\xaf\xe2\x5c\x5e\xdc\x28\xd7"
+				"\xea\x44\xf9\x3e\xe1\x23\x4a\xa8"
+				"\x8f\x61\xc9\x19\x12\xa4\xcc\xd9",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+			     "jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x99\x1c\x66\x57\x55\xeb\x3a\x4b"
+				"\x6b\xbd\xfb\x75\xc7\x8a\x49\x2e"
+				"\x8c\x56\xa2\x2c\x5c\x4d\x7e\x42"
+				"\x9b\xfd\xbc\x32\xb9\xd4\xad\x5a"
+				"\xa0\x4a\x1f\x07\x6e\x62\xfe\xa1"
+				"\x9e\xef\x51\xac\xd0\x65\x7c\x22",
+	},
+};
+
+
+#define SHA3_512_TEST_VECTORS	3
+static struct hash_testvec sha3_512_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\xa6\x9f\x73\xcc\xa2\x3a\x9a\xc5"
+				"\xc8\xb5\x67\xdc\x18\x5a\x75\x6e"
+				"\x97\xc9\x82\x16\x4f\xe2\x58\x59"
+				"\xe0\xd1\xdc\xc1\x47\x5c\x80\xa6"
+				"\x15\xb2\x12\x3a\xf1\xf5\xf9\x4c"
+				"\x11\xe3\xe9\x40\x2c\x3a\xc5\x58"
+				"\xf5\x00\x19\x9d\x95\xb6\xd3\xe3"
+				"\x01\x75\x85\x86\x28\x1d\xcd\x26",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x69\x7f\x2d\x85\x61\x72\xcb\x83"
+				"\x09\xd6\xb8\xb9\x7d\xac\x4d\xe3"
+				"\x44\xb5\x49\xd4\xde\xe6\x1e\xdf"
+				"\xb4\x96\x2d\x86\x98\xb7\xfa\x80"
+				"\x3f\x4f\x93\xff\x24\x39\x35\x86"
+				"\xe2\x8b\x5b\x95\x7a\xc3\xd1\xd3"
+				"\x69\x42\x0c\xe5\x33\x32\x71\x2f"
+				"\x99\x7b\xd3\x36\xd0\x9a\xb0\x2a",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+			     "jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x04\xa3\x71\xe8\x4e\xcf\xb5\xb8"
+				"\xb7\x7c\xb4\x86\x10\xfc\xa8\x18"
+				"\x2d\xd4\x57\xce\x6f\x32\x6a\x0f"
+				"\xd3\xd7\xec\x2f\x1e\x91\x63\x6d"
+				"\xee\x69\x1f\xbe\x0c\x98\x53\x02"
+				"\xba\x1b\x0d\x8d\xc7\x8c\x08\x63"
+				"\x46\xb5\x33\xb4\x9c\x03\x0d\x99"
+				"\xa2\x7d\xaf\x11\x39\xd6\xe7\x5e",
+	},
+};
+
+
 /*
  * MD5 test vectors from RFC1321
  */
@@ -3246,6 +3892,394 @@ static struct hash_testvec hmac_sha512_tv_template[] = {
 	},
 };
 
+#define HMAC_SHA3_224_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_224_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\x3b\x16\x54\x6b\xbc\x7b\xe2\x70"
+			  "\x6a\x03\x1d\xca\xfd\x56\x37\x3d"
+			  "\x98\x84\x36\x76\x41\xd8\xc5\x9a"
+			  "\xf3\xc8\x60\xf7",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\x7f\xdb\x8d\xd8\x8b\xd2\xf6\x0d"
+			  "\x1b\x79\x86\x34\xad\x38\x68\x11"
+			  "\xc2\xcf\xc8\x5b\xfa\xf5\xd5\x2b"
+			  "\xba\xce\x5e\x66",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\xb4\xa1\xf0\x4c\x00\x28\x7a\x9b"
+			  "\x7f\x60\x75\xb3\x13\xd2\x79\xb8"
+			  "\x33\xbc\x8f\x75\x12\x43\x52\xd0"
+			  "\x5f\xb9\x99\x5f",
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x05\xd8\xcd\x6d\x00\xfa\xea\x8d"
+			  "\x1e\xb6\x8a\xde\x28\x73\x0b\xbd"
+			  "\x3c\xba\xb6\x92\x9f\x0a\x08\x6b"
+			  "\x29\xcd\x62\xa0",
+	},
+};
+
+#define HMAC_SHA3_256_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_256_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\xba\x85\x19\x23\x10\xdf\xfa\x96"
+			  "\xe2\xa3\xa4\x0e\x69\x77\x43\x51"
+			  "\x14\x0b\xb7\x18\x5e\x12\x02\xcd"
+			  "\xcc\x91\x75\x89\xf9\x5e\x16\xbb",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\xc7\xd4\x07\x2e\x78\x88\x77\xae"
+			  "\x35\x96\xbb\xb0\xda\x73\xb8\x87"
+			  "\xc9\x17\x1f\x93\x09\x5b\x29\x4a"
+			  "\xe8\x57\xfb\xe2\x64\x5e\x1b\xa5",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\xed\x73\xa3\x74\xb9\x6c\x00\x52"
+			  "\x35\xf9\x48\x03\x2f\x09\x67\x4a"
+			  "\x58\xc0\xce\x55\x5c\xfc\x1f\x22"
+			  "\x3b\x02\x35\x65\x60\x31\x2c\x3b",
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x65\xc5\xb0\x6d\x4c\x3d\xe3\x2a"
+			  "\x7a\xef\x87\x63\x26\x1e\x49\xad"
+			  "\xb6\xe2\x29\x3e\xc8\xe7\xc6\x1e"
+			  "\x8d\xe6\x17\x01\xfc\x63\xe1\x23",
+	},
+};
+
+#define HMAC_SHA3_384_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_384_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\x68\xd2\xdc\xf7\xfd\x4d\xdd\x0a"
+			  "\x22\x40\xc8\xa4\x37\x30\x5f\x61"
+			  "\xfb\x73\x34\xcf\xb5\xd0\x22\x6e"
+			  "\x1b\xc2\x7d\xc1\x0a\x2e\x72\x3a"
+			  "\x20\xd3\x70\xb4\x77\x43\x13\x0e"
+			  "\x26\xac\x7e\x3d\x53\x28\x86\xbd",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\xf1\x10\x1f\x8c\xbf\x97\x66\xfd"
+			  "\x67\x64\xd2\xed\x61\x90\x3f\x21"
+			  "\xca\x9b\x18\xf5\x7c\xf3\xe1\xa2"
+			  "\x3c\xa1\x35\x08\xa9\x32\x43\xce"
+			  "\x48\xc0\x45\xdc\x00\x7f\x26\xa2"
+			  "\x1b\x3f\x5e\x0e\x9d\xf4\xc2\x0a",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\x0f\xc1\x95\x13\xbf\x6b\xd8\x78"
+			  "\x03\x70\x16\x70\x6a\x0e\x57\xbc"
+			  "\x52\x81\x39\x83\x6b\x9a\x42\xc3"
+			  "\xd4\x19\xe4\x98\xe0\xe1\xfb\x96"
+			  "\x16\xfd\x66\x91\x38\xd3\x3a\x11"
+			  "\x05\xe0\x7c\x72\xb6\x95\x3b\xcc",
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x02\x6f\xdf\x6b\x50\x74\x1e\x37"
+			  "\x38\x99\xc9\xf7\xd5\x40\x6d\x4e"
+			  "\xb0\x9f\xc6\x66\x56\x36\xfc\x1a"
+			  "\x53\x00\x29\xdd\xf5\xcf\x3c\xa5"
+			  "\xa9\x00\xed\xce\x01\xf5\xf6\x1e"
+			  "\x2f\x40\x8c\xdf\x2f\xd3\xe7\xe8",
+	},
+};
+
+#define HMAC_SHA3_512_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_512_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\xeb\x3f\xbd\x4b\x2e\xaa\xb8\xf5"
+			  "\xc5\x04\xbd\x3a\x41\x46\x5a\xac"
+			  "\xec\x15\x77\x0a\x7c\xab\xac\x53"
+			  "\x1e\x48\x2f\x86\x0b\x5e\xc7\xba"
+			  "\x47\xcc\xb2\xc6\xf2\xaf\xce\x8f"
+			  "\x88\xd2\x2b\x6d\xc6\x13\x80\xf2"
+			  "\x3a\x66\x8f\xd3\x88\x8b\xb8\x05"
+			  "\x37\xc0\xa0\xb8\x64\x07\x68\x9e",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\x5a\x4b\xfe\xab\x61\x66\x42\x7c"
+			  "\x7a\x36\x47\xb7\x47\x29\x2b\x83"
+			  "\x84\x53\x7c\xdb\x89\xaf\xb3\xbf"
+			  "\x56\x65\xe4\xc5\xe7\x09\x35\x0b"
+			  "\x28\x7b\xae\xc9\x21\xfd\x7c\xa0"
+			  "\xee\x7a\x0c\x31\xd0\x22\xa9\x5e"
+			  "\x1f\xc9\x2b\xa9\xd7\x7d\xf8\x83"
+			  "\x96\x02\x75\xbe\xb4\xe6\x20\x24",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\x00\xf7\x51\xa9\xe5\x06\x95\xb0"
+			  "\x90\xed\x69\x11\xa4\xb6\x55\x24"
+			  "\x95\x1c\xdc\x15\xa7\x3a\x5d\x58"
+			  "\xbb\x55\x21\x5e\xa2\xcd\x83\x9a"
+			  "\xc7\x9d\x2b\x44\xa3\x9b\xaf\xab"
+			  "\x27\xe8\x3f\xde\x9e\x11\xf6\x34"
+			  "\x0b\x11\xd9\x91\xb1\xb9\x1b\xf2"
+			  "\xee\xe7\xfc\x87\x24\x26\xc3\xa4",
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa",
+		.ksize	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x38\xa4\x56\xa0\x04\xbd\x10\xd3"
+			  "\x2c\x9a\xb8\x33\x66\x84\x11\x28"
+			  "\x62\xc3\xdb\x61\xad\xcc\xa3\x18"
+			  "\x29\x35\x5e\xaf\x46\xfd\x5c\x73"
+			  "\xd0\x6a\x1f\x0d\x13\xfe\xc9\xa6"
+			  "\x52\xfb\x38\x11\xb5\x77\xb1\xb1"
+			  "\xd1\xb9\x78\x9f\x97\xae\x5b\x83"
+			  "\xc6\xf4\x4d\xfc\xf1\xd6\x7e\xba",
+	},
+};
+
 /*
  * Poly1305 test vectors from RFC7539 A.3.
  */
diff --git a/drivers/Makefile b/drivers/Makefile
index a7187b999c5e..f93771346218 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_GENERIC_PHY)	+= phy/
 
 # GPIO must come after pinctrl as gpios may need to mux pins etc
 obj-$(CONFIG_PINCTRL)		+= pinctrl/
-obj-y				+= gpio/
+obj-$(CONFIG_GPIOLIB)		+= gpio/
 obj-y				+= pwm/
 obj-$(CONFIG_PCI)		+= pci/
 obj-$(CONFIG_PARISC)		+= parisc/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index b7e2e776397d..acad70a0bb0d 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -213,6 +213,10 @@ config ACPI_CPU_FREQ_PSS
 	bool
 	select THERMAL
 
+config ACPI_PROCESSOR_CSTATE
+	def_bool y
+	depends on IA64 || X86
+
 config ACPI_PROCESSOR_IDLE
 	bool
 	select CPU_IDLE
@@ -234,7 +238,7 @@ config ACPI_CPPC_LIB
 config ACPI_PROCESSOR
 	tristate "Processor"
 	depends on X86 || IA64 || ARM64
-	select ACPI_PROCESSOR_IDLE if X86 || IA64
+	select ACPI_PROCESSOR_IDLE
 	select ACPI_CPU_FREQ_PSS if X86 || IA64
 	default y
 	help
@@ -291,8 +295,8 @@ config ACPI_THERMAL
 config ACPI_NUMA
 	bool "NUMA support"
 	depends on NUMA
-	depends on (X86 || IA64)
-	default y if IA64_GENERIC || IA64_SGI_SN2
+	depends on (X86 || IA64 || ARM64)
+	default y if IA64_GENERIC || IA64_SGI_SN2 || ARM64
 
 config ACPI_CUSTOM_DSDT_FILE
 	string "Custom DSDT Table file to include"
@@ -311,9 +315,12 @@ config ACPI_CUSTOM_DSDT
 	bool
 	default ACPI_CUSTOM_DSDT_FILE != ""
 
+config ARCH_HAS_ACPI_TABLE_UPGRADE
+	def_bool n
+
 config ACPI_TABLE_UPGRADE
 	bool "Allow upgrading ACPI tables via initrd"
-	depends on BLK_DEV_INITRD && X86
+	depends on BLK_DEV_INITRD && ARCH_HAS_ACPI_TABLE_UPGRADE
 	default y
 	help
 	  This option provides functionality to upgrade arbitrary ACPI tables
@@ -475,6 +482,7 @@ config ACPI_NFIT_DEBUG
 	  issue.
 
 source "drivers/acpi/apei/Kconfig"
+source "drivers/acpi/dptf/Kconfig"
 
 config ACPI_EXTLOG
 	tristate "Extended Error Log support"
@@ -519,6 +527,20 @@ config XPOWER_PMIC_OPREGION
 	help
 	  This config adds ACPI operation region support for XPower AXP288 PMIC.
 
+config BXT_WC_PMIC_OPREGION
+	bool "ACPI operation region support for BXT WhiskeyCove PMIC"
+	depends on INTEL_SOC_PMIC
+	help
+	  This config adds ACPI operation region support for BXT WhiskeyCove PMIC.
+
 endif
 
+config ACPI_CONFIGFS
+	tristate "ACPI configfs support"
+	select CONFIGFS_FS
+	help
+	  Select this option to enable support for ACPI configuration from
+	  userspace. The configurable ACPI groups will be visible under
+	  /config/acpi, assuming configfs is mounted under /config.
+
 endif	# ACPI
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 251ce85a66fb..88f54f03e3d2 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -44,7 +44,6 @@ acpi-y				+= acpi_lpss.o acpi_apd.o
 acpi-y				+= acpi_platform.o
 acpi-y				+= acpi_pnp.o
 acpi-$(CONFIG_ARM_AMBA)	+= acpi_amba.o
-acpi-y				+= int340x_thermal.o
 acpi-y				+= power.o
 acpi-y				+= event.o
 acpi-$(CONFIG_ACPI_REDUCED_HARDWARE_ONLY) += evged.o
@@ -99,5 +98,9 @@ obj-$(CONFIG_ACPI_EXTLOG)	+= acpi_extlog.o
 obj-$(CONFIG_PMIC_OPREGION)	+= pmic/intel_pmic.o
 obj-$(CONFIG_CRC_PMIC_OPREGION) += pmic/intel_pmic_crc.o
 obj-$(CONFIG_XPOWER_PMIC_OPREGION) += pmic/intel_pmic_xpower.o
+obj-$(CONFIG_BXT_WC_PMIC_OPREGION) += pmic/intel_pmic_bxtwc.o
+
+obj-$(CONFIG_ACPI_CONFIGFS)	+= acpi_configfs.o
 
 video-objs			+= acpi_video.o video_detect.o
+obj-y				+= dptf/
diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c
new file mode 100644
index 000000000000..146a77fb762d
--- /dev/null
+++ b/drivers/acpi/acpi_configfs.c
@@ -0,0 +1,267 @@
+/*
+ * ACPI configfs support
+ *
+ * Copyright (c) 2016 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "ACPI configfs: " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/configfs.h>
+#include <linux/acpi.h>
+
+static struct config_group *acpi_table_group;
+
+struct acpi_table {
+	struct config_item cfg;
+	struct acpi_table_header *header;
+};
+
+static ssize_t acpi_table_aml_write(struct config_item *cfg,
+				    const void *data, size_t size)
+{
+	const struct acpi_table_header *header = data;
+	struct acpi_table *table;
+	int ret;
+
+	table = container_of(cfg, struct acpi_table, cfg);
+
+	if (table->header) {
+		pr_err("table already loaded\n");
+		return -EBUSY;
+	}
+
+	if (header->length != size) {
+		pr_err("invalid table length\n");
+		return -EINVAL;
+	}
+
+	if (memcmp(header->signature, ACPI_SIG_SSDT, 4)) {
+		pr_err("invalid table signature\n");
+		return -EINVAL;
+	}
+
+	table = container_of(cfg, struct acpi_table, cfg);
+
+	table->header = kmemdup(header, header->length, GFP_KERNEL);
+	if (!table->header)
+		return -ENOMEM;
+
+	ret = acpi_load_table(table->header);
+	if (ret) {
+		kfree(table->header);
+		table->header = NULL;
+	}
+
+	return ret;
+}
+
+static inline struct acpi_table_header *get_header(struct config_item *cfg)
+{
+	struct acpi_table *table = container_of(cfg, struct acpi_table, cfg);
+
+	if (!table->header)
+		pr_err("table not loaded\n");
+
+	return table->header;
+}
+
+static ssize_t acpi_table_aml_read(struct config_item *cfg,
+				   void *data, size_t size)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	if (data)
+		memcpy(data, h, h->length);
+
+	return h->length;
+}
+
+#define MAX_ACPI_TABLE_SIZE (128 * 1024)
+
+CONFIGFS_BIN_ATTR(acpi_table_, aml, NULL, MAX_ACPI_TABLE_SIZE);
+
+struct configfs_bin_attribute *acpi_table_bin_attrs[] = {
+	&acpi_table_attr_aml,
+	NULL,
+};
+
+ssize_t acpi_table_signature_show(struct config_item *cfg, char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%.*s\n", ACPI_NAME_SIZE, h->signature);
+}
+
+ssize_t acpi_table_length_show(struct config_item *cfg, char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%d\n", h->length);
+}
+
+ssize_t acpi_table_revision_show(struct config_item *cfg, char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%d\n", h->revision);
+}
+
+ssize_t acpi_table_oem_id_show(struct config_item *cfg, char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%.*s\n", ACPI_OEM_ID_SIZE, h->oem_id);
+}
+
+ssize_t acpi_table_oem_table_id_show(struct config_item *cfg, char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%.*s\n", ACPI_OEM_TABLE_ID_SIZE, h->oem_table_id);
+}
+
+ssize_t acpi_table_oem_revision_show(struct config_item *cfg, char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%d\n", h->oem_revision);
+}
+
+ssize_t acpi_table_asl_compiler_id_show(struct config_item *cfg, char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%.*s\n", ACPI_NAME_SIZE, h->asl_compiler_id);
+}
+
+ssize_t acpi_table_asl_compiler_revision_show(struct config_item *cfg,
+					      char *str)
+{
+	struct acpi_table_header *h = get_header(cfg);
+
+	if (!h)
+		return -EINVAL;
+
+	return sprintf(str, "%d\n", h->asl_compiler_revision);
+}
+
+CONFIGFS_ATTR_RO(acpi_table_, signature);
+CONFIGFS_ATTR_RO(acpi_table_, length);
+CONFIGFS_ATTR_RO(acpi_table_, revision);
+CONFIGFS_ATTR_RO(acpi_table_, oem_id);
+CONFIGFS_ATTR_RO(acpi_table_, oem_table_id);
+CONFIGFS_ATTR_RO(acpi_table_, oem_revision);
+CONFIGFS_ATTR_RO(acpi_table_, asl_compiler_id);
+CONFIGFS_ATTR_RO(acpi_table_, asl_compiler_revision);
+
+struct configfs_attribute *acpi_table_attrs[] = {
+	&acpi_table_attr_signature,
+	&acpi_table_attr_length,
+	&acpi_table_attr_revision,
+	&acpi_table_attr_oem_id,
+	&acpi_table_attr_oem_table_id,
+	&acpi_table_attr_oem_revision,
+	&acpi_table_attr_asl_compiler_id,
+	&acpi_table_attr_asl_compiler_revision,
+	NULL,
+};
+
+static struct config_item_type acpi_table_type = {
+	.ct_owner = THIS_MODULE,
+	.ct_bin_attrs = acpi_table_bin_attrs,
+	.ct_attrs = acpi_table_attrs,
+};
+
+static struct config_item *acpi_table_make_item(struct config_group *group,
+						const char *name)
+{
+	struct acpi_table *table;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return ERR_PTR(-ENOMEM);
+
+	config_item_init_type_name(&table->cfg, name, &acpi_table_type);
+	return &table->cfg;
+}
+
+struct configfs_group_operations acpi_table_group_ops = {
+	.make_item = acpi_table_make_item,
+};
+
+static struct config_item_type acpi_tables_type = {
+	.ct_owner = THIS_MODULE,
+	.ct_group_ops = &acpi_table_group_ops,
+};
+
+static struct config_item_type acpi_root_group_type = {
+	.ct_owner = THIS_MODULE,
+};
+
+static struct configfs_subsystem acpi_configfs = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "acpi",
+			.ci_type = &acpi_root_group_type,
+		},
+	},
+	.su_mutex = __MUTEX_INITIALIZER(acpi_configfs.su_mutex),
+};
+
+static int __init acpi_configfs_init(void)
+{
+	int ret;
+	struct config_group *root = &acpi_configfs.su_group;
+
+	config_group_init(root);
+
+	ret = configfs_register_subsystem(&acpi_configfs);
+	if (ret)
+		return ret;
+
+	acpi_table_group = configfs_register_default_group(root, "table",
+							   &acpi_tables_type);
+	return PTR_ERR_OR_ZERO(acpi_table_group);
+}
+module_init(acpi_configfs_init);
+
+static void __exit acpi_configfs_exit(void)
+{
+	configfs_unregister_default_group(acpi_table_group);
+	configfs_unregister_subsystem(&acpi_configfs);
+}
+module_exit(acpi_configfs_exit);
+
+MODULE_AUTHOR("Octavian Purdila <octavian.purdila@intel.com>");
+MODULE_DESCRIPTION("ACPI configfs support");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/acpi/acpi_lpat.c b/drivers/acpi/acpi_lpat.c
index feb61c1630eb..c1c4877ca96c 100644
--- a/drivers/acpi/acpi_lpat.c
+++ b/drivers/acpi/acpi_lpat.c
@@ -13,7 +13,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/acpi.h>
 #include <acpi/acpi_lpat.h>
 
@@ -157,5 +157,3 @@ void acpi_lpat_free_conversion_table(struct acpi_lpat_conversion_table
 	}
 }
 EXPORT_SYMBOL_GPL(acpi_lpat_free_conversion_table);
-
-MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index c1d138e128cb..c5557d070954 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -1246,6 +1246,9 @@ static int acpi_video_device_enumerate(struct acpi_video_bus *video)
 	union acpi_object *dod = NULL;
 	union acpi_object *obj;
 
+	if (!video->cap._DOD)
+		return AE_NOT_EXIST;
+
 	status = acpi_evaluate_object(video->device->handle, "_DOD", NULL, &buffer);
 	if (!ACPI_SUCCESS(status)) {
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _DOD"));
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index 5d575a955940..e50573de25f1 100644
--- a/drivers/acpi/apei/Makefile
+++ b/drivers/acpi/apei/Makefile
@@ -3,4 +3,4 @@ obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o
 obj-$(CONFIG_ACPI_APEI_EINJ)	+= einj.o
 obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o
 
-apei-y := apei-base.o hest.o erst.o
+apei-y := apei-base.o hest.o erst.o bert.o
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index 16129c78b489..6e9f14c0a71b 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -1,6 +1,6 @@
 /*
  * apei-internal.h - ACPI Platform Error Interface internal
- * definations.
+ * definitions.
  */
 
 #ifndef APEI_INTERNAL_H
diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c
new file mode 100644
index 000000000000..a05b5c0cf181
--- /dev/null
+++ b/drivers/acpi/apei/bert.c
@@ -0,0 +1,150 @@
+/*
+ * APEI Boot Error Record Table (BERT) support
+ *
+ * Copyright 2011 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * Under normal circumstances, when a hardware error occurs, the error
+ * handler receives control and processes the error. This gives OSPM a
+ * chance to process the error condition, report it, and optionally attempt
+ * recovery. In some cases, the system is unable to process an error.
+ * For example, system firmware or a management controller may choose to
+ * reset the system or the system might experience an uncontrolled crash
+ * or reset.The boot error source is used to report unhandled errors that
+ * occurred in a previous boot. This mechanism is described in the BERT
+ * table.
+ *
+ * For more information about BERT, please refer to ACPI Specification
+ * version 4.0, section 17.3.1
+ *
+ * This file is licensed under GPLv2.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+
+#include "apei-internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "BERT: " fmt
+
+static int bert_disable;
+
+static void __init bert_print_all(struct acpi_bert_region *region,
+				  unsigned int region_len)
+{
+	struct acpi_hest_generic_status *estatus =
+		(struct acpi_hest_generic_status *)region;
+	int remain = region_len;
+	u32 estatus_len;
+
+	if (!estatus->block_status)
+		return;
+
+	while (remain > sizeof(struct acpi_bert_region)) {
+		if (cper_estatus_check(estatus)) {
+			pr_err(FW_BUG "Invalid error record.\n");
+			return;
+		}
+
+		estatus_len = cper_estatus_len(estatus);
+		if (remain < estatus_len) {
+			pr_err(FW_BUG "Truncated status block (length: %u).\n",
+			       estatus_len);
+			return;
+		}
+
+		pr_info_once("Error records from previous boot:\n");
+
+		cper_estatus_print(KERN_INFO HW_ERR, estatus);
+
+		/*
+		 * Because the boot error source is "one-time polled" type,
+		 * clear Block Status of current Generic Error Status Block,
+		 * once it's printed.
+		 */
+		estatus->block_status = 0;
+
+		estatus = (void *)estatus + estatus_len;
+		/* No more error records. */
+		if (!estatus->block_status)
+			return;
+
+		remain -= estatus_len;
+	}
+}
+
+static int __init setup_bert_disable(char *str)
+{
+	bert_disable = 1;
+
+	return 0;
+}
+__setup("bert_disable", setup_bert_disable);
+
+static int __init bert_check_table(struct acpi_table_bert *bert_tab)
+{
+	if (bert_tab->header.length < sizeof(struct acpi_table_bert) ||
+	    bert_tab->region_length < sizeof(struct acpi_bert_region))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init bert_init(void)
+{
+	struct acpi_bert_region *boot_error_region;
+	struct acpi_table_bert *bert_tab;
+	unsigned int region_len;
+	acpi_status status;
+	int rc = 0;
+
+	if (acpi_disabled)
+		return 0;
+
+	if (bert_disable) {
+		pr_info("Boot Error Record Table support is disabled.\n");
+		return 0;
+	}
+
+	status = acpi_get_table(ACPI_SIG_BERT, 0, (struct acpi_table_header **)&bert_tab);
+	if (status == AE_NOT_FOUND)
+		return 0;
+
+	if (ACPI_FAILURE(status)) {
+		pr_err("get table failed, %s.\n", acpi_format_exception(status));
+		return -EINVAL;
+	}
+
+	rc = bert_check_table(bert_tab);
+	if (rc) {
+		pr_err(FW_BUG "table invalid.\n");
+		return rc;
+	}
+
+	region_len = bert_tab->region_length;
+	if (!request_mem_region(bert_tab->address, region_len, "APEI BERT")) {
+		pr_err("Can't request iomem region <%016llx-%016llx>.\n",
+		       (unsigned long long)bert_tab->address,
+		       (unsigned long long)bert_tab->address + region_len - 1);
+		return -EIO;
+	}
+
+	boot_error_region = ioremap_cache(bert_tab->address, region_len);
+	if (boot_error_region) {
+		bert_print_all(boot_error_region, region_len);
+		iounmap(boot_error_region);
+	} else {
+		rc = -ENOMEM;
+	}
+
+	release_mem_region(bert_tab->address, region_len);
+
+	return rc;
+}
+
+late_initcall(bert_init);
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 559c1173de1c..eebb7e39c49c 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -33,7 +33,8 @@
 
 #include "apei-internal.h"
 
-#define EINJ_PFX "EINJ: "
+#undef pr_fmt
+#define pr_fmt(fmt) "EINJ: " fmt
 
 #define SPIN_UNIT		100			/* 100ns */
 /* Firmware should respond within 1 milliseconds */
@@ -179,8 +180,7 @@ static int einj_get_available_error_type(u32 *type)
 static int einj_timedout(u64 *t)
 {
 	if ((s64)*t < SPIN_UNIT) {
-		pr_warning(FW_WARN EINJ_PFX
-			   "Firmware does not respond in time\n");
+		pr_warning(FW_WARN "Firmware does not respond in time\n");
 		return 1;
 	}
 	*t -= SPIN_UNIT;
@@ -307,8 +307,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 	r = request_mem_region(trigger_paddr, sizeof(*trigger_tab),
 			       "APEI EINJ Trigger Table");
 	if (!r) {
-		pr_err(EINJ_PFX
-	"Can not request [mem %#010llx-%#010llx] for Trigger table\n",
+		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger table\n",
 		       (unsigned long long)trigger_paddr,
 		       (unsigned long long)trigger_paddr +
 			    sizeof(*trigger_tab) - 1);
@@ -316,13 +315,12 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 	}
 	trigger_tab = ioremap_cache(trigger_paddr, sizeof(*trigger_tab));
 	if (!trigger_tab) {
-		pr_err(EINJ_PFX "Failed to map trigger table!\n");
+		pr_err("Failed to map trigger table!\n");
 		goto out_rel_header;
 	}
 	rc = einj_check_trigger_header(trigger_tab);
 	if (rc) {
-		pr_warning(FW_BUG EINJ_PFX
-			   "The trigger error action table is invalid\n");
+		pr_warning(FW_BUG "Invalid trigger error action table.\n");
 		goto out_rel_header;
 	}
 
@@ -336,8 +334,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 			       table_size - sizeof(*trigger_tab),
 			       "APEI EINJ Trigger Table");
 	if (!r) {
-		pr_err(EINJ_PFX
-"Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n",
+		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n",
 		       (unsigned long long)trigger_paddr + sizeof(*trigger_tab),
 		       (unsigned long long)trigger_paddr + table_size - 1);
 		goto out_rel_header;
@@ -345,7 +342,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 	iounmap(trigger_tab);
 	trigger_tab = ioremap_cache(trigger_paddr, table_size);
 	if (!trigger_tab) {
-		pr_err(EINJ_PFX "Failed to map trigger table!\n");
+		pr_err("Failed to map trigger table!\n");
 		goto out_rel_entry;
 	}
 	trigger_entry = (struct acpi_whea_header *)
@@ -695,34 +692,42 @@ static int __init einj_init(void)
 	struct dentry *fentry;
 	struct apei_exec_context ctx;
 
-	if (acpi_disabled)
+	if (acpi_disabled) {
+		pr_warn("ACPI disabled.\n");
 		return -ENODEV;
+	}
 
 	status = acpi_get_table(ACPI_SIG_EINJ, 0,
 				(struct acpi_table_header **)&einj_tab);
-	if (status == AE_NOT_FOUND)
+	if (status == AE_NOT_FOUND) {
+		pr_warn("EINJ table not found.\n");
 		return -ENODEV;
+	}
 	else if (ACPI_FAILURE(status)) {
-		const char *msg = acpi_format_exception(status);
-		pr_err(EINJ_PFX "Failed to get table, %s\n", msg);
+		pr_err("Failed to get EINJ table: %s\n",
+				acpi_format_exception(status));
 		return -EINVAL;
 	}
 
 	rc = einj_check_table(einj_tab);
 	if (rc) {
-		pr_warning(FW_BUG EINJ_PFX "EINJ table is invalid\n");
+		pr_warn(FW_BUG "Invalid EINJ table.n");
 		return -EINVAL;
 	}
 
 	rc = -ENOMEM;
 	einj_debug_dir = debugfs_create_dir("einj", apei_get_debugfs_dir());
-	if (!einj_debug_dir)
+	if (!einj_debug_dir) {
+		pr_err("Error creating debugfs node.\n");
 		goto err_cleanup;
+	}
+
 	fentry = debugfs_create_file("available_error_type", S_IRUSR,
 				     einj_debug_dir, NULL,
 				     &available_error_type_fops);
 	if (!fentry)
 		goto err_cleanup;
+
 	fentry = debugfs_create_file("error_type", S_IRUSR | S_IWUSR,
 				     einj_debug_dir, NULL, &error_type_fops);
 	if (!fentry)
@@ -735,14 +740,22 @@ static int __init einj_init(void)
 	apei_resources_init(&einj_resources);
 	einj_exec_ctx_init(&ctx);
 	rc = apei_exec_collect_resources(&ctx, &einj_resources);
-	if (rc)
+	if (rc) {
+		pr_err("Error collecting EINJ resources.\n");
 		goto err_fini;
+	}
+
 	rc = apei_resources_request(&einj_resources, "APEI EINJ");
-	if (rc)
+	if (rc) {
+		pr_err("Error requesting memory/port resources.\n");
 		goto err_fini;
+	}
+
 	rc = apei_exec_pre_map_gars(&ctx);
-	if (rc)
+	if (rc) {
+		pr_err("Error pre-mapping GARs.\n");
 		goto err_release;
+	}
 
 	rc = -ENOMEM;
 	einj_param = einj_get_parameter_address();
@@ -787,7 +800,7 @@ static int __init einj_init(void)
 			goto err_unmap;
 	}
 
-	pr_info(EINJ_PFX "Error INJection is initialized.\n");
+	pr_info("Error INJection is initialized.\n");
 
 	return 0;
 
@@ -798,6 +811,7 @@ err_unmap:
 			sizeof(struct einj_parameter);
 
 		acpi_os_unmap_iomem(einj_param, size);
+		pr_err("Error creating param extension debugfs nodes.\n");
 	}
 	apei_exec_post_unmap_gars(&ctx);
 err_release:
@@ -805,6 +819,7 @@ err_release:
 err_fini:
 	apei_resources_fini(&einj_resources);
 err_cleanup:
+	pr_err("Error creating primary debugfs nodes.\n");
 	debugfs_remove_recursive(einj_debug_dir);
 
 	return rc;
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 006c3894c6ea..f096ab3cb54d 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -927,7 +927,8 @@ static int erst_open_pstore(struct pstore_info *psi);
 static int erst_close_pstore(struct pstore_info *psi);
 static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
 			   struct timespec *time, char **buf,
-			   bool *compressed, struct pstore_info *psi);
+			   bool *compressed, ssize_t *ecc_notice_size,
+			   struct pstore_info *psi);
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
 		       u64 *id, unsigned int part, int count, bool compressed,
 		       size_t size, struct pstore_info *psi);
@@ -987,7 +988,8 @@ static int erst_close_pstore(struct pstore_info *psi)
 
 static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
 			   struct timespec *time, char **buf,
-			   bool *compressed, struct pstore_info *psi)
+			   bool *compressed, ssize_t *ecc_notice_size,
+			   struct pstore_info *psi)
 {
 	int rc;
 	ssize_t len = 0;
@@ -1033,6 +1035,7 @@ skip:
 	memcpy(*buf, rcd->data, len - sizeof(*rcd));
 	*id = record_id;
 	*compressed = false;
+	*ecc_notice_size = 0;
 	if (uuid_le_cmp(rcd->sec_hdr.section_type,
 			CPER_SECTION_TYPE_DMESG_Z) == 0) {
 		*type = PSTORE_TYPE_DMESG;
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 262ca31b86d9..85b7d07fe5c8 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -30,6 +30,9 @@
 #include <linux/acpi.h>
 #include <linux/slab.h>
 #include <linux/regulator/machine.h>
+#include <linux/workqueue.h>
+#include <linux/reboot.h>
+#include <linux/delay.h>
 #ifdef CONFIG_X86
 #include <asm/mpspec.h>
 #endif
@@ -174,22 +177,17 @@ void acpi_bus_detach_private_data(acpi_handle handle)
 EXPORT_SYMBOL_GPL(acpi_bus_detach_private_data);
 
 static void acpi_print_osc_error(acpi_handle handle,
-	struct acpi_osc_context *context, char *error)
+				 struct acpi_osc_context *context, char *error)
 {
-	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER};
 	int i;
 
-	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer)))
-		printk(KERN_DEBUG "%s: %s\n", context->uuid_str, error);
-	else {
-		printk(KERN_DEBUG "%s (%s): %s\n",
-		       (char *)buffer.pointer, context->uuid_str, error);
-		kfree(buffer.pointer);
-	}
-	printk(KERN_DEBUG "_OSC request data:");
+	acpi_handle_debug(handle, "(%s): %s\n", context->uuid_str, error);
+
+	pr_debug("_OSC request data:");
 	for (i = 0; i < context->cap.length; i += sizeof(u32))
-		printk(" %x", *((u32 *)(context->cap.pointer + i)));
-	printk("\n");
+		pr_debug(" %x", *((u32 *)(context->cap.pointer + i)));
+
+	pr_debug("\n");
 }
 
 acpi_status acpi_str_to_uuid(char *str, u8 *uuid)
@@ -302,6 +300,14 @@ out_kfree:
 EXPORT_SYMBOL(acpi_run_osc);
 
 bool osc_sb_apei_support_acked;
+
+/*
+ * ACPI 6.0 Section 8.4.4.2 Idle State Coordination
+ * OSPM supports platform coordinated low power idle(LPI) states
+ */
+bool osc_pc_lpi_support_confirmed;
+EXPORT_SYMBOL_GPL(osc_pc_lpi_support_confirmed);
+
 static u8 sb_uuid_str[] = "0811B06E-4A27-44F9-8D60-3CBBC22E7B48";
 static void acpi_bus_osc_support(void)
 {
@@ -322,6 +328,7 @@ static void acpi_bus_osc_support(void)
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT;
 
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT;
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PCLPI_SUPPORT;
 
 	if (!ghes_disable)
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_APEI_SUPPORT;
@@ -329,9 +336,12 @@ static void acpi_bus_osc_support(void)
 		return;
 	if (ACPI_SUCCESS(acpi_run_osc(handle, &context))) {
 		u32 *capbuf_ret = context.ret.pointer;
-		if (context.ret.length > OSC_SUPPORT_DWORD)
+		if (context.ret.length > OSC_SUPPORT_DWORD) {
 			osc_sb_apei_support_acked =
 				capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_APEI_SUPPORT;
+			osc_pc_lpi_support_confirmed =
+				capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_PCLPI_SUPPORT;
+		}
 		kfree(context.ret.pointer);
 	}
 	/* do we need to check other returned cap? Sounds no */
@@ -475,6 +485,56 @@ static void acpi_device_remove_notify_handler(struct acpi_device *device)
 					   acpi_device_notify);
 }
 
+/* Handle events targeting \_SB device (at present only graceful shutdown) */
+
+#define ACPI_SB_NOTIFY_SHUTDOWN_REQUEST 0x81
+#define ACPI_SB_INDICATE_INTERVAL	10000
+
+static void sb_notify_work(struct work_struct *dummy)
+{
+	acpi_handle sb_handle;
+
+	orderly_poweroff(true);
+
+	/*
+	 * After initiating graceful shutdown, the ACPI spec requires OSPM
+	 * to evaluate _OST method once every 10seconds to indicate that
+	 * the shutdown is in progress
+	 */
+	acpi_get_handle(NULL, "\\_SB", &sb_handle);
+	while (1) {
+		pr_info("Graceful shutdown in progress.\n");
+		acpi_evaluate_ost(sb_handle, ACPI_OST_EC_OSPM_SHUTDOWN,
+				ACPI_OST_SC_OS_SHUTDOWN_IN_PROGRESS, NULL);
+		msleep(ACPI_SB_INDICATE_INTERVAL);
+	}
+}
+
+static void acpi_sb_notify(acpi_handle handle, u32 event, void *data)
+{
+	static DECLARE_WORK(acpi_sb_work, sb_notify_work);
+
+	if (event == ACPI_SB_NOTIFY_SHUTDOWN_REQUEST) {
+		if (!work_busy(&acpi_sb_work))
+			schedule_work(&acpi_sb_work);
+	} else
+		pr_warn("event %x is not supported by \\_SB device\n", event);
+}
+
+static int __init acpi_setup_sb_notify_handler(void)
+{
+	acpi_handle sb_handle;
+
+	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &sb_handle)))
+		return -ENXIO;
+
+	if (ACPI_FAILURE(acpi_install_notify_handler(sb_handle, ACPI_DEVICE_NOTIFY,
+						acpi_sb_notify, NULL)))
+		return -EINVAL;
+
+	return 0;
+}
+
 /* --------------------------------------------------------------------------
                              Device Matching
    -------------------------------------------------------------------------- */
@@ -961,8 +1021,7 @@ void __init acpi_early_init(void)
 /**
  * acpi_subsystem_init - Finalize the early initialization of ACPI.
  *
- * Switch over the platform to the ACPI mode (if possible), initialize the
- * handling of ACPI events, install the interrupt and global lock handlers.
+ * Switch over the platform to the ACPI mode (if possible).
  *
  * Doing this too early is generally unsafe, but at the same time it needs to be
  * done before all things that really depend on ACPI.  The right spot appears to
@@ -990,6 +1049,13 @@ void __init acpi_subsystem_init(void)
 	}
 }
 
+static acpi_status acpi_bus_table_handler(u32 event, void *table, void *context)
+{
+	acpi_scan_table_handler(event, table, context);
+
+	return acpi_sysfs_table_handler(event, table, context);
+}
+
 static int __init acpi_bus_init(void)
 {
 	int result;
@@ -1043,6 +1109,8 @@ static int __init acpi_bus_init(void)
 	 * _PDC control method may load dynamic SSDT tables,
 	 * and we need to install the table handler before that.
 	 */
+	status = acpi_install_table_handler(acpi_bus_table_handler, NULL);
+
 	acpi_sysfs_init();
 
 	acpi_early_processor_set_pdc();
@@ -1124,6 +1192,7 @@ static int __init acpi_init(void)
 	acpi_sleep_proc_init();
 	acpi_wakeup_device_init();
 	acpi_debugger_init();
+	acpi_setup_sb_notify_handler();
 	return 0;
 }
 
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 5c3b0918d5fd..148f4e5ca104 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -53,6 +53,10 @@
 #define ACPI_BUTTON_DEVICE_NAME_LID	"Lid Switch"
 #define ACPI_BUTTON_TYPE_LID		0x05
 
+#define ACPI_BUTTON_LID_INIT_IGNORE	0x00
+#define ACPI_BUTTON_LID_INIT_OPEN	0x01
+#define ACPI_BUTTON_LID_INIT_METHOD	0x02
+
 #define _COMPONENT		ACPI_BUTTON_COMPONENT
 ACPI_MODULE_NAME("button");
 
@@ -105,6 +109,7 @@ struct acpi_button {
 
 static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier);
 static struct acpi_device *lid_device;
+static u8 lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
 
 /* --------------------------------------------------------------------------
                               FS Interface (/proc)
@@ -113,16 +118,52 @@ static struct acpi_device *lid_device;
 static struct proc_dir_entry *acpi_button_dir;
 static struct proc_dir_entry *acpi_lid_dir;
 
+static int acpi_lid_evaluate_state(struct acpi_device *device)
+{
+	unsigned long long lid_state;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(device->handle, "_LID", NULL, &lid_state);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return lid_state ? 1 : 0;
+}
+
+static int acpi_lid_notify_state(struct acpi_device *device, int state)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+	int ret;
+
+	/* input layer checks if event is redundant */
+	input_report_switch(button->input, SW_LID, !state);
+	input_sync(button->input);
+
+	if (state)
+		pm_wakeup_event(&device->dev, 0);
+
+	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
+	if (ret == NOTIFY_DONE)
+		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
+						   device);
+	if (ret == NOTIFY_DONE || ret == NOTIFY_OK) {
+		/*
+		 * It is also regarded as success if the notifier_chain
+		 * returns NOTIFY_OK or NOTIFY_DONE.
+		 */
+		ret = 0;
+	}
+	return ret;
+}
+
 static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
 {
 	struct acpi_device *device = seq->private;
-	acpi_status status;
-	unsigned long long state;
+	int state;
 
-	status = acpi_evaluate_integer(device->handle, "_LID", NULL, &state);
+	state = acpi_lid_evaluate_state(device);
 	seq_printf(seq, "state:      %s\n",
-		   ACPI_FAILURE(status) ? "unsupported" :
-			(state ? "open" : "closed"));
+		   state < 0 ? "unsupported" : (state ? "open" : "closed"));
 	return 0;
 }
 
@@ -231,51 +272,37 @@ EXPORT_SYMBOL(acpi_lid_notifier_unregister);
 
 int acpi_lid_open(void)
 {
-	acpi_status status;
-	unsigned long long state;
-
 	if (!lid_device)
 		return -ENODEV;
 
-	status = acpi_evaluate_integer(lid_device->handle, "_LID", NULL,
-				       &state);
-	if (ACPI_FAILURE(status))
-		return -ENODEV;
-
-	return !!state;
+	return acpi_lid_evaluate_state(lid_device);
 }
 EXPORT_SYMBOL(acpi_lid_open);
 
-static int acpi_lid_send_state(struct acpi_device *device)
+static int acpi_lid_update_state(struct acpi_device *device)
 {
-	struct acpi_button *button = acpi_driver_data(device);
-	unsigned long long state;
-	acpi_status status;
-	int ret;
-
-	status = acpi_evaluate_integer(device->handle, "_LID", NULL, &state);
-	if (ACPI_FAILURE(status))
-		return -ENODEV;
+	int state;
 
-	/* input layer checks if event is redundant */
-	input_report_switch(button->input, SW_LID, !state);
-	input_sync(button->input);
+	state = acpi_lid_evaluate_state(device);
+	if (state < 0)
+		return state;
 
-	if (state)
-		pm_wakeup_event(&device->dev, 0);
+	return acpi_lid_notify_state(device, state);
+}
 
-	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
-	if (ret == NOTIFY_DONE)
-		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
-						   device);
-	if (ret == NOTIFY_DONE || ret == NOTIFY_OK) {
-		/*
-		 * It is also regarded as success if the notifier_chain
-		 * returns NOTIFY_OK or NOTIFY_DONE.
-		 */
-		ret = 0;
+static void acpi_lid_initialize_state(struct acpi_device *device)
+{
+	switch (lid_init_state) {
+	case ACPI_BUTTON_LID_INIT_OPEN:
+		(void)acpi_lid_notify_state(device, 1);
+		break;
+	case ACPI_BUTTON_LID_INIT_METHOD:
+		(void)acpi_lid_update_state(device);
+		break;
+	case ACPI_BUTTON_LID_INIT_IGNORE:
+	default:
+		break;
 	}
-	return ret;
 }
 
 static void acpi_button_notify(struct acpi_device *device, u32 event)
@@ -290,7 +317,7 @@ static void acpi_button_notify(struct acpi_device *device, u32 event)
 	case ACPI_BUTTON_NOTIFY_STATUS:
 		input = button->input;
 		if (button->type == ACPI_BUTTON_TYPE_LID) {
-			acpi_lid_send_state(device);
+			acpi_lid_update_state(device);
 		} else {
 			int keycode;
 
@@ -335,7 +362,7 @@ static int acpi_button_resume(struct device *dev)
 
 	button->suspended = false;
 	if (button->type == ACPI_BUTTON_TYPE_LID)
-		return acpi_lid_send_state(device);
+		acpi_lid_initialize_state(device);
 	return 0;
 }
 #endif
@@ -416,7 +443,7 @@ static int acpi_button_add(struct acpi_device *device)
 	if (error)
 		goto err_remove_fs;
 	if (button->type == ACPI_BUTTON_TYPE_LID) {
-		acpi_lid_send_state(device);
+		acpi_lid_initialize_state(device);
 		/*
 		 * This assumes there's only one lid device, or if there are
 		 * more we only care about the last one...
@@ -446,4 +473,42 @@ static int acpi_button_remove(struct acpi_device *device)
 	return 0;
 }
 
+static int param_set_lid_init_state(const char *val, struct kernel_param *kp)
+{
+	int result = 0;
+
+	if (!strncmp(val, "open", sizeof("open") - 1)) {
+		lid_init_state = ACPI_BUTTON_LID_INIT_OPEN;
+		pr_info("Notify initial lid state as open\n");
+	} else if (!strncmp(val, "method", sizeof("method") - 1)) {
+		lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
+		pr_info("Notify initial lid state with _LID return value\n");
+	} else if (!strncmp(val, "ignore", sizeof("ignore") - 1)) {
+		lid_init_state = ACPI_BUTTON_LID_INIT_IGNORE;
+		pr_info("Do not notify initial lid state\n");
+	} else
+		result = -EINVAL;
+	return result;
+}
+
+static int param_get_lid_init_state(char *buffer, struct kernel_param *kp)
+{
+	switch (lid_init_state) {
+	case ACPI_BUTTON_LID_INIT_OPEN:
+		return sprintf(buffer, "open");
+	case ACPI_BUTTON_LID_INIT_METHOD:
+		return sprintf(buffer, "method");
+	case ACPI_BUTTON_LID_INIT_IGNORE:
+		return sprintf(buffer, "ignore");
+	default:
+		return sprintf(buffer, "invalid");
+	}
+	return 0;
+}
+
+module_param_call(lid_init_state,
+		  param_set_lid_init_state, param_get_lid_init_state,
+		  NULL, 0644);
+MODULE_PARM_DESC(lid_init_state, "Behavior for reporting LID initial state");
+
 module_acpi_driver(acpi_button_driver);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 8adac69dba3d..2e981732805b 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -299,8 +299,10 @@ int acpi_get_psd_map(struct cpudata **all_cpu_data)
 			continue;
 
 		cpc_ptr = per_cpu(cpc_desc_ptr, i);
-		if (!cpc_ptr)
-			continue;
+		if (!cpc_ptr) {
+			retval = -EFAULT;
+			goto err_ret;
+		}
 
 		pdomain = &(cpc_ptr->domain_info);
 		cpumask_set_cpu(i, pr->shared_cpu_map);
@@ -322,8 +324,10 @@ int acpi_get_psd_map(struct cpudata **all_cpu_data)
 				continue;
 
 			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
-			if (!match_cpc_ptr)
-				continue;
+			if (!match_cpc_ptr) {
+				retval = -EFAULT;
+				goto err_ret;
+			}
 
 			match_pdomain = &(match_cpc_ptr->domain_info);
 			if (match_pdomain->domain != pdomain->domain)
@@ -353,8 +357,10 @@ int acpi_get_psd_map(struct cpudata **all_cpu_data)
 				continue;
 
 			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
-			if (!match_cpc_ptr)
-				continue;
+			if (!match_cpc_ptr) {
+				retval = -EFAULT;
+				goto err_ret;
+			}
 
 			match_pdomain = &(match_cpc_ptr->domain_info);
 			if (match_pdomain->domain != pdomain->domain)
@@ -595,9 +601,6 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 	/* Store CPU Logical ID */
 	cpc_ptr->cpu_id = pr->id;
 
-	/* Plug it into this CPUs CPC descriptor. */
-	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
-
 	/* Parse PSD data for this CPU */
 	ret = acpi_get_psd(cpc_ptr, handle);
 	if (ret)
@@ -610,6 +613,9 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 			goto out_free;
 	}
 
+	/* Plug PSD data into this CPUs CPC descriptor. */
+	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
+
 	/* Everything looks okay */
 	pr_debug("Parsed CPC struct for CPU: %d\n", pr->id);
 
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index e8e128dede29..0c00208b423e 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/types.h>
@@ -33,12 +33,7 @@
 
 #include "internal.h"
 
-#define ACPI_DOCK_DRIVER_DESCRIPTION "ACPI Dock Station Driver"
-
 ACPI_MODULE_NAME("dock");
-MODULE_AUTHOR("Kristen Carlson Accardi");
-MODULE_DESCRIPTION(ACPI_DOCK_DRIVER_DESCRIPTION);
-MODULE_LICENSE("GPL");
 
 static bool immediate_undock = 1;
 module_param(immediate_undock, bool, 0644);
diff --git a/drivers/acpi/dptf/Kconfig b/drivers/acpi/dptf/Kconfig
new file mode 100644
index 000000000000..ac0a6ed0cf46
--- /dev/null
+++ b/drivers/acpi/dptf/Kconfig
@@ -0,0 +1,15 @@
+config DPTF_POWER
+	tristate "DPTF Platform Power Participant"
+	depends on X86
+	help
+	  This driver adds support for Dynamic Platform and Thermal Framework
+	  (DPTF) Platform Power Participant device (INT3407) support.
+	  This participant is responsible for exposing platform telemetry:
+		max_platform_power
+		platform_power_source
+		adapter_rating
+		battery_steady_power
+		charger_type
+
+	  To compile this driver as a module, choose M here:
+	  the module will be called dptf_power.
diff --git a/drivers/acpi/dptf/Makefile b/drivers/acpi/dptf/Makefile
new file mode 100644
index 000000000000..06ea8809583d
--- /dev/null
+++ b/drivers/acpi/dptf/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_ACPI)             += int340x_thermal.o
+obj-$(CONFIG_DPTF_POWER)	+= dptf_power.o
+
+ccflags-y += -Idrivers/acpi
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
new file mode 100644
index 000000000000..734642dc5008
--- /dev/null
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -0,0 +1,128 @@
+/*
+ * dptf_power:  DPTF platform power driver
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/platform_device.h>
+
+/*
+ * Presentation of attributes which are defined for INT3407. They are:
+ * PMAX : Maximum platform powe
+ * PSRC : Platform power source
+ * ARTG : Adapter rating
+ * CTYP : Charger type
+ * PBSS : Battery steady power
+ */
+#define DPTF_POWER_SHOW(name, object) \
+static ssize_t name##_show(struct device *dev,\
+			   struct device_attribute *attr,\
+			   char *buf)\
+{\
+	struct platform_device *pdev = to_platform_device(dev);\
+	struct acpi_device *acpi_dev = platform_get_drvdata(pdev);\
+	unsigned long long val;\
+	acpi_status status;\
+\
+	status = acpi_evaluate_integer(acpi_dev->handle, #object,\
+				       NULL, &val);\
+	if (ACPI_SUCCESS(status))\
+		return sprintf(buf, "%d\n", (int)val);\
+	else \
+		return -EINVAL;\
+}
+
+DPTF_POWER_SHOW(max_platform_power_mw, PMAX)
+DPTF_POWER_SHOW(platform_power_source, PSRC)
+DPTF_POWER_SHOW(adapter_rating_mw, ARTG)
+DPTF_POWER_SHOW(battery_steady_power_mw, PBSS)
+DPTF_POWER_SHOW(charger_type, CTYP)
+
+static DEVICE_ATTR_RO(max_platform_power_mw);
+static DEVICE_ATTR_RO(platform_power_source);
+static DEVICE_ATTR_RO(adapter_rating_mw);
+static DEVICE_ATTR_RO(battery_steady_power_mw);
+static DEVICE_ATTR_RO(charger_type);
+
+static struct attribute *dptf_power_attrs[] = {
+	&dev_attr_max_platform_power_mw.attr,
+	&dev_attr_platform_power_source.attr,
+	&dev_attr_adapter_rating_mw.attr,
+	&dev_attr_battery_steady_power_mw.attr,
+	&dev_attr_charger_type.attr,
+	NULL
+};
+
+static struct attribute_group dptf_power_attribute_group = {
+	.attrs = dptf_power_attrs,
+	.name = "dptf_power"
+};
+
+static int dptf_power_add(struct platform_device *pdev)
+{
+	struct acpi_device *acpi_dev;
+	acpi_status status;
+	unsigned long long ptype;
+	int result;
+
+	acpi_dev = ACPI_COMPANION(&(pdev->dev));
+	if (!acpi_dev)
+		return -ENODEV;
+
+	status = acpi_evaluate_integer(acpi_dev->handle, "PTYP", NULL, &ptype);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	if (ptype != 0x11)
+		return -ENODEV;
+
+	result = sysfs_create_group(&pdev->dev.kobj,
+				    &dptf_power_attribute_group);
+	if (result)
+		return result;
+
+	platform_set_drvdata(pdev, acpi_dev);
+
+	return 0;
+}
+
+static int dptf_power_remove(struct platform_device *pdev)
+{
+
+	sysfs_remove_group(&pdev->dev.kobj, &dptf_power_attribute_group);
+
+	return 0;
+}
+
+static const struct acpi_device_id int3407_device_ids[] = {
+	{"INT3407", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, int3407_device_ids);
+
+static struct platform_driver dptf_power_driver = {
+	.probe = dptf_power_add,
+	.remove = dptf_power_remove,
+	.driver = {
+		.name = "DPTF Platform Power",
+		.acpi_match_table = int3407_device_ids,
+	},
+};
+
+module_platform_driver(dptf_power_driver);
+
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ACPI DPTF platform power driver");
diff --git a/drivers/acpi/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c
index 33505c651f62..33505c651f62 100644
--- a/drivers/acpi/int340x_thermal.c
+++ b/drivers/acpi/dptf/int340x_thermal.c
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 290d6f5be44b..999a10914678 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1359,13 +1359,9 @@ static void ec_remove_handlers(struct acpi_ec *ec)
 	}
 }
 
-static int acpi_ec_add(struct acpi_device *device)
+static struct acpi_ec *acpi_ec_alloc(void)
 {
-	struct acpi_ec *ec = NULL;
-	int ret;
-
-	strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
-	strcpy(acpi_device_class(device), ACPI_EC_CLASS);
+	struct acpi_ec *ec;
 
 	/* Check for boot EC */
 	if (boot_ec) {
@@ -1376,9 +1372,21 @@ static int acpi_ec_add(struct acpi_device *device)
 			first_ec = NULL;
 	} else {
 		ec = make_acpi_ec();
-		if (!ec)
-			return -ENOMEM;
 	}
+	return ec;
+}
+
+static int acpi_ec_add(struct acpi_device *device)
+{
+	struct acpi_ec *ec = NULL;
+	int ret;
+
+	strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
+	strcpy(acpi_device_class(device), ACPI_EC_CLASS);
+
+	ec = acpi_ec_alloc();
+	if (!ec)
+		return -ENOMEM;
 	if (ec_parse_device(device->handle, 0, ec, NULL) !=
 		AE_CTRL_TERMINATE) {
 			kfree(ec);
@@ -1465,27 +1473,31 @@ static const struct acpi_device_id ec_device_ids[] = {
 int __init acpi_ec_dsdt_probe(void)
 {
 	acpi_status status;
+	struct acpi_ec *ec;
+	int ret;
 
-	if (boot_ec)
-		return 0;
-
+	ec = acpi_ec_alloc();
+	if (!ec)
+		return -ENOMEM;
 	/*
 	 * Finding EC from DSDT if there is no ECDT EC available. When this
 	 * function is invoked, ACPI tables have been fully loaded, we can
 	 * walk namespace now.
 	 */
-	boot_ec = make_acpi_ec();
-	if (!boot_ec)
-		return -ENOMEM;
 	status = acpi_get_devices(ec_device_ids[0].id,
-				  ec_parse_device, boot_ec, NULL);
-	if (ACPI_FAILURE(status) || !boot_ec->handle)
-		return -ENODEV;
-	if (!ec_install_handlers(boot_ec)) {
-		first_ec = boot_ec;
-		return 0;
+				  ec_parse_device, ec, NULL);
+	if (ACPI_FAILURE(status) || !ec->handle) {
+		ret = -ENODEV;
+		goto error;
 	}
-	return -EFAULT;
+	ret = ec_install_handlers(ec);
+
+error:
+	if (ret)
+		kfree(ec);
+	else
+		first_ec = boot_ec = ec;
+	return ret;
 }
 
 #if 0
@@ -1529,6 +1541,11 @@ static int ec_clear_on_resume(const struct dmi_system_id *id)
 	return 0;
 }
 
+/*
+ * Some ECDTs contain wrong register addresses.
+ * MSI MS-171F
+ * https://bugzilla.kernel.org/show_bug.cgi?id=12461
+ */
 static int ec_correct_ecdt(const struct dmi_system_id *id)
 {
 	pr_debug("Detected system needing ECDT address correction.\n");
@@ -1538,16 +1555,6 @@ static int ec_correct_ecdt(const struct dmi_system_id *id)
 
 static struct dmi_system_id ec_dmi_table[] __initdata = {
 	{
-	ec_correct_ecdt, "Asus L4R", {
-	DMI_MATCH(DMI_BIOS_VERSION, "1008.006"),
-	DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),
-	DMI_MATCH(DMI_BOARD_NAME, "L4R") }, NULL},
-	{
-	ec_correct_ecdt, "Asus M6R", {
-	DMI_MATCH(DMI_BIOS_VERSION, "0207"),
-	DMI_MATCH(DMI_PRODUCT_NAME, "M6R"),
-	DMI_MATCH(DMI_BOARD_NAME, "M6R") }, NULL},
-	{
 	ec_correct_ecdt, "MSI MS-171F", {
 	DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star"),
 	DMI_MATCH(DMI_PRODUCT_NAME, "MS-171F"),}, NULL},
@@ -1559,12 +1566,13 @@ static struct dmi_system_id ec_dmi_table[] __initdata = {
 
 int __init acpi_ec_ecdt_probe(void)
 {
-	int ret = 0;
+	int ret;
 	acpi_status status;
 	struct acpi_table_ecdt *ecdt_ptr;
+	struct acpi_ec *ec;
 
-	boot_ec = make_acpi_ec();
-	if (!boot_ec)
+	ec = acpi_ec_alloc();
+	if (!ec)
 		return -ENOMEM;
 	/*
 	 * Generate a boot ec context
@@ -1588,28 +1596,20 @@ int __init acpi_ec_ecdt_probe(void)
 
 	pr_info("EC description table is found, configuring boot EC\n");
 	if (EC_FLAGS_CORRECT_ECDT) {
-		/*
-		 * Asus L4R, Asus M6R
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=9399
-		 * MSI MS-171F
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=12461
-		 */
-		boot_ec->command_addr = ecdt_ptr->data.address;
-		boot_ec->data_addr = ecdt_ptr->control.address;
+		ec->command_addr = ecdt_ptr->data.address;
+		ec->data_addr = ecdt_ptr->control.address;
 	} else {
-		boot_ec->command_addr = ecdt_ptr->control.address;
-		boot_ec->data_addr = ecdt_ptr->data.address;
+		ec->command_addr = ecdt_ptr->control.address;
+		ec->data_addr = ecdt_ptr->data.address;
 	}
-	boot_ec->gpe = ecdt_ptr->gpe;
-	boot_ec->handle = ACPI_ROOT_OBJECT;
-	ret = ec_install_handlers(boot_ec);
-	if (!ret)
-		first_ec = boot_ec;
+	ec->gpe = ecdt_ptr->gpe;
+	ec->handle = ACPI_ROOT_OBJECT;
+	ret = ec_install_handlers(ec);
 error:
-	if (ret) {
-		kfree(boot_ec);
-		boot_ec = NULL;
-	}
+	if (ret)
+		kfree(ec);
+	else
+		first_ec = boot_ec = ec;
 	return ret;
 }
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 27cc7feabfe4..940218ff0193 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -87,6 +87,9 @@ bool acpi_queue_hotplug_work(struct work_struct *work);
 void acpi_device_hotplug(struct acpi_device *adev, u32 src);
 bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent);
 
+acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context);
+void acpi_scan_table_handler(u32 event, void *table, void *context);
+
 /* --------------------------------------------------------------------------
                      Device Node Initialization / Removal
    -------------------------------------------------------------------------- */
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index d176e0ece470..ce3a7a16f03f 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -18,22 +18,21 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  */
+
+#define pr_fmt(fmt) "ACPI: " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/acpi.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/numa.h>
 #include <linux/nodemask.h>
 #include <linux/topology.h>
 
-#define PREFIX "ACPI: "
-
-#define ACPI_NUMA	0x80000000
-#define _COMPONENT	ACPI_NUMA
-ACPI_MODULE_NAME("numa");
-
 static nodemask_t nodes_found_map = NODE_MASK_NONE;
 
 /* maps to convert between proximity domain and logical node ID */
@@ -43,6 +42,7 @@ static int node_to_pxm_map[MAX_NUMNODES]
 			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
 
 unsigned char acpi_srat_revision __initdata;
+int acpi_numa __initdata;
 
 int pxm_to_node(int pxm)
 {
@@ -128,68 +128,63 @@ EXPORT_SYMBOL(acpi_map_pxm_to_online_node);
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {
-
-	ACPI_FUNCTION_NAME("acpi_table_print_srat_entry");
-
-	if (!header)
-		return;
-
 	switch (header->type) {
-
 	case ACPI_SRAT_TYPE_CPU_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
 		{
 			struct acpi_srat_cpu_affinity *p =
 			    (struct acpi_srat_cpu_affinity *)header;
-			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-					  "SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
-					  p->apic_id, p->local_sapic_eid,
-					  p->proximity_domain_lo,
-					  (p->flags & ACPI_SRAT_CPU_ENABLED)?
-					  "enabled" : "disabled"));
+			pr_debug("SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
+				 p->apic_id, p->local_sapic_eid,
+				 p->proximity_domain_lo,
+				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
+				 "enabled" : "disabled");
 		}
-#endif				/* ACPI_DEBUG_OUTPUT */
 		break;
 
 	case ACPI_SRAT_TYPE_MEMORY_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
 		{
 			struct acpi_srat_mem_affinity *p =
 			    (struct acpi_srat_mem_affinity *)header;
-			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-					  "SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n",
-					  (unsigned long)p->base_address,
-					  (unsigned long)p->length,
-					  p->proximity_domain,
-					  (p->flags & ACPI_SRAT_MEM_ENABLED)?
-					  "enabled" : "disabled",
-					  (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)?
-					  " hot-pluggable" : "",
-					  (p->flags & ACPI_SRAT_MEM_NON_VOLATILE)?
-					  " non-volatile" : ""));
+			pr_debug("SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n",
+				 (unsigned long)p->base_address,
+				 (unsigned long)p->length,
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_MEM_ENABLED) ?
+				 "enabled" : "disabled",
+				 (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
+				 " hot-pluggable" : "",
+				 (p->flags & ACPI_SRAT_MEM_NON_VOLATILE) ?
+				 " non-volatile" : "");
 		}
-#endif				/* ACPI_DEBUG_OUTPUT */
 		break;
 
 	case ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
 		{
 			struct acpi_srat_x2apic_cpu_affinity *p =
 			    (struct acpi_srat_x2apic_cpu_affinity *)header;
-			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-					  "SRAT Processor (x2apicid[0x%08x]) in"
-					  " proximity domain %d %s\n",
-					  p->apic_id,
-					  p->proximity_domain,
-					  (p->flags & ACPI_SRAT_CPU_ENABLED) ?
-					  "enabled" : "disabled"));
+			pr_debug("SRAT Processor (x2apicid[0x%08x]) in proximity domain %d %s\n",
+				 p->apic_id,
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
+				 "enabled" : "disabled");
 		}
-#endif				/* ACPI_DEBUG_OUTPUT */
 		break;
+
+	case ACPI_SRAT_TYPE_GICC_AFFINITY:
+		{
+			struct acpi_srat_gicc_affinity *p =
+			    (struct acpi_srat_gicc_affinity *)header;
+			pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
+				 p->acpi_processor_uid,
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_GICC_ENABLED) ?
+				 "enabled" : "disabled");
+		}
+		break;
+
 	default:
-		printk(KERN_WARNING PREFIX
-		       "Found unsupported SRAT entry (type = 0x%x)\n",
-		       header->type);
+		pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
+			header->type);
 		break;
 	}
 }
@@ -217,12 +212,117 @@ static int __init slit_valid(struct acpi_table_slit *slit)
 	return 1;
 }
 
+void __init bad_srat(void)
+{
+	pr_err("SRAT: SRAT not used.\n");
+	acpi_numa = -1;
+}
+
+int __init srat_disabled(void)
+{
+	return acpi_numa < 0;
+}
+
+#if defined(CONFIG_X86) || defined(CONFIG_ARM64)
+/*
+ * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them.  I/O localities are
+ * not supported at this point.
+ */
+void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
+{
+	int i, j;
+
+	for (i = 0; i < slit->locality_count; i++) {
+		const int from_node = pxm_to_node(i);
+
+		if (from_node == NUMA_NO_NODE)
+			continue;
+
+		for (j = 0; j < slit->locality_count; j++) {
+			const int to_node = pxm_to_node(j);
+
+			if (to_node == NUMA_NO_NODE)
+				continue;
+
+			numa_set_distance(from_node, to_node,
+				slit->entry[slit->locality_count * i + j]);
+		}
+	}
+}
+
+/*
+ * Default callback for parsing of the Proximity Domain <-> Memory
+ * Area mappings
+ */
+int __init
+acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
+{
+	u64 start, end;
+	u32 hotpluggable;
+	int node, pxm;
+
+	if (srat_disabled())
+		goto out_err;
+	if (ma->header.length < sizeof(struct acpi_srat_mem_affinity)) {
+		pr_err("SRAT: Unexpected header length: %d\n",
+		       ma->header.length);
+		goto out_err_bad_srat;
+	}
+	if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
+		goto out_err;
+	hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+	if (hotpluggable && !IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		goto out_err;
+
+	start = ma->base_address;
+	end = start + ma->length;
+	pxm = ma->proximity_domain;
+	if (acpi_srat_revision <= 1)
+		pxm &= 0xff;
+
+	node = acpi_map_pxm_to_node(pxm);
+	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+		pr_err("SRAT: Too many proximity domains.\n");
+		goto out_err_bad_srat;
+	}
+
+	if (numa_add_memblk(node, start, end) < 0) {
+		pr_err("SRAT: Failed to add memblk to node %u [mem %#010Lx-%#010Lx]\n",
+		       node, (unsigned long long) start,
+		       (unsigned long long) end - 1);
+		goto out_err_bad_srat;
+	}
+
+	node_set(node, numa_nodes_parsed);
+
+	pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n",
+		node, pxm,
+		(unsigned long long) start, (unsigned long long) end - 1,
+		hotpluggable ? " hotplug" : "",
+		ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : "");
+
+	/* Mark hotplug range in memblock. */
+	if (hotpluggable && memblock_mark_hotplug(start, ma->length))
+		pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
+			(unsigned long long)start, (unsigned long long)end - 1);
+
+	max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
+
+	return 0;
+out_err_bad_srat:
+	bad_srat();
+out_err:
+	return -EINVAL;
+}
+#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
+
 static int __init acpi_parse_slit(struct acpi_table_header *table)
 {
 	struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
 
 	if (!slit_valid(slit)) {
-		printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n");
+		pr_info("SLIT table looks invalid. Not used.\n");
 		return -EINVAL;
 	}
 	acpi_numa_slit_init(slit);
@@ -233,12 +333,9 @@ static int __init acpi_parse_slit(struct acpi_table_header *table)
 void __init __weak
 acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 {
-	printk(KERN_WARNING PREFIX
-	       "Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id);
-	return;
+	pr_warn("Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id);
 }
 
-
 static int __init
 acpi_parse_x2apic_affinity(struct acpi_subtable_header *header,
 			   const unsigned long end)
@@ -275,6 +372,24 @@ acpi_parse_processor_affinity(struct acpi_subtable_header *header,
 	return 0;
 }
 
+static int __init
+acpi_parse_gicc_affinity(struct acpi_subtable_header *header,
+			 const unsigned long end)
+{
+	struct acpi_srat_gicc_affinity *processor_affinity;
+
+	processor_affinity = (struct acpi_srat_gicc_affinity *)header;
+	if (!processor_affinity)
+		return -EINVAL;
+
+	acpi_table_print_srat_entry(header);
+
+	/* let architecture-dependent part to do it */
+	acpi_numa_gicc_affinity_init(processor_affinity);
+
+	return 0;
+}
+
 static int __initdata parsed_numa_memblks;
 
 static int __init
@@ -319,6 +434,9 @@ int __init acpi_numa_init(void)
 {
 	int cnt = 0;
 
+	if (acpi_disabled)
+		return -EINVAL;
+
 	/*
 	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
 	 * SRAT cpu entries could have different order with that in MADT.
@@ -327,13 +445,15 @@ int __init acpi_numa_init(void)
 
 	/* SRAT: Static Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
-		struct acpi_subtable_proc srat_proc[2];
+		struct acpi_subtable_proc srat_proc[3];
 
 		memset(srat_proc, 0, sizeof(srat_proc));
 		srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
 		srat_proc[0].handler = acpi_parse_processor_affinity;
 		srat_proc[1].id = ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY;
 		srat_proc[1].handler = acpi_parse_x2apic_affinity;
+		srat_proc[2].id = ACPI_SRAT_TYPE_GICC_AFFINITY;
+		srat_proc[2].handler = acpi_parse_gicc_affinity;
 
 		acpi_table_parse_entries_array(ACPI_SIG_SRAT,
 					sizeof(struct acpi_table_srat),
@@ -347,8 +467,6 @@ int __init acpi_numa_init(void)
 	/* SLIT: System Locality Information Table */
 	acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
 
-	acpi_numa_arch_fixup();
-
 	if (cnt < 0)
 		return cnt;
 	else if (!parsed_numa_memblks)
diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index 7188e53b6b7c..f62c68e24317 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -22,8 +22,9 @@
  *  General Public License for more details.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -33,30 +34,11 @@
 #include <linux/dmi.h>
 #include <linux/pci-acpi.h>
 
-static bool debug;
 static int check_sta_before_sun;
 
-#define DRIVER_VERSION 	"0.1"
-#define DRIVER_AUTHOR	"Alex Chiang <achiang@hp.com>"
-#define DRIVER_DESC	"ACPI PCI Slot Detection Driver"
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL");
-MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
-module_param(debug, bool, 0644);
-
 #define _COMPONENT		ACPI_PCI_COMPONENT
 ACPI_MODULE_NAME("pci_slot");
 
-#define MY_NAME "pci_slot"
-#define err(format, arg...) pr_err("%s: " format , MY_NAME , ## arg)
-#define info(format, arg...) pr_info("%s: " format , MY_NAME , ## arg)
-#define dbg(format, arg...)					\
-	do {							\
-		if (debug)					\
-			pr_debug("%s: " format,	MY_NAME , ## arg); \
-	} while (0)
-
 #define SLOT_NAME_SIZE 21		/* Inspired by #define in acpiphp.h */
 
 struct acpi_pci_slot {
@@ -76,7 +58,7 @@ check_slot(acpi_handle handle, unsigned long long *sun)
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 
 	acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
-	dbg("Checking slot on path: %s\n", (char *)buffer.pointer);
+	pr_debug("Checking slot on path: %s\n", (char *)buffer.pointer);
 
 	if (check_sta_before_sun) {
 		/* If SxFy doesn't have _STA, we just assume it's there */
@@ -87,14 +69,16 @@ check_slot(acpi_handle handle, unsigned long long *sun)
 
 	status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
 	if (ACPI_FAILURE(status)) {
-		dbg("_ADR returned %d on %s\n", status, (char *)buffer.pointer);
+		pr_debug("_ADR returned %d on %s\n",
+			 status, (char *)buffer.pointer);
 		goto out;
 	}
 
 	/* No _SUN == not a slot == bail */
 	status = acpi_evaluate_integer(handle, "_SUN", NULL, sun);
 	if (ACPI_FAILURE(status)) {
-		dbg("_SUN returned %d on %s\n", status, (char *)buffer.pointer);
+		pr_debug("_SUN returned %d on %s\n",
+			 status, (char *)buffer.pointer);
 		goto out;
 	}
 
@@ -132,15 +116,13 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	}
 
 	slot = kmalloc(sizeof(*slot), GFP_KERNEL);
-	if (!slot) {
-		err("%s: cannot allocate memory\n", __func__);
+	if (!slot)
 		return AE_OK;
-	}
 
 	snprintf(name, sizeof(name), "%llu", sun);
 	pci_slot = pci_create_slot(pci_bus, device, name, NULL);
 	if (IS_ERR(pci_slot)) {
-		err("pci_create_slot returned %ld\n", PTR_ERR(pci_slot));
+		pr_err("pci_create_slot returned %ld\n", PTR_ERR(pci_slot));
 		kfree(slot);
 		return AE_OK;
 	}
@@ -150,8 +132,8 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 
 	get_device(&pci_bus->dev);
 
-	dbg("pci_slot: %p, pci_bus: %x, device: %d, name: %s\n",
-		pci_slot, pci_bus->number, device, name);
+	pr_debug("%p, pci_bus: %x, device: %d, name: %s\n",
+		 pci_slot, pci_bus->number, device, name);
 
 	return AE_OK;
 }
@@ -186,7 +168,8 @@ void acpi_pci_slot_remove(struct pci_bus *bus)
 
 static int do_sta_before_sun(const struct dmi_system_id *d)
 {
-	info("%s detected: will evaluate _STA before calling _SUN\n", d->ident);
+	pr_info("%s detected: will evaluate _STA before calling _SUN\n",
+		d->ident);
 	check_sta_before_sun = 1;
 	return 0;
 }
diff --git a/drivers/acpi/pmic/intel_pmic.c b/drivers/acpi/pmic/intel_pmic.c
index bd772cd56494..ca18e0d23df9 100644
--- a/drivers/acpi/pmic/intel_pmic.c
+++ b/drivers/acpi/pmic/intel_pmic.c
@@ -13,7 +13,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/acpi.h>
 #include <linux/regmap.h>
 #include <acpi/acpi_lpat.h>
@@ -21,12 +21,19 @@
 
 #define PMIC_POWER_OPREGION_ID		0x8d
 #define PMIC_THERMAL_OPREGION_ID	0x8c
+#define PMIC_REGS_OPREGION_ID		0x8f
+
+struct intel_pmic_regs_handler_ctx {
+	unsigned int val;
+	u16 addr;
+};
 
 struct intel_pmic_opregion {
 	struct mutex lock;
 	struct acpi_lpat_conversion_table *lpat_table;
 	struct regmap *regmap;
 	struct intel_pmic_opregion_data *data;
+	struct intel_pmic_regs_handler_ctx ctx;
 };
 
 static int pmic_get_reg_bit(int address, struct pmic_table *table,
@@ -131,7 +138,7 @@ static int pmic_thermal_aux(struct intel_pmic_opregion *opregion, int reg,
 }
 
 static int pmic_thermal_pen(struct intel_pmic_opregion *opregion, int reg,
-			    u32 function, u64 *value)
+			    int bit, u32 function, u64 *value)
 {
 	struct intel_pmic_opregion_data *d = opregion->data;
 	struct regmap *regmap = opregion->regmap;
@@ -140,12 +147,12 @@ static int pmic_thermal_pen(struct intel_pmic_opregion *opregion, int reg,
 		return -ENXIO;
 
 	if (function == ACPI_READ)
-		return d->get_policy(regmap, reg, value);
+		return d->get_policy(regmap, reg, bit, value);
 
 	if (*value != 0 && *value != 1)
 		return -EINVAL;
 
-	return d->update_policy(regmap, reg, *value);
+	return d->update_policy(regmap, reg, bit, *value);
 }
 
 static bool pmic_thermal_is_temp(int address)
@@ -170,13 +177,13 @@ static acpi_status intel_pmic_thermal_handler(u32 function,
 {
 	struct intel_pmic_opregion *opregion = region_context;
 	struct intel_pmic_opregion_data *d = opregion->data;
-	int reg, result;
+	int reg, bit, result;
 
 	if (bits != 32 || !value64)
 		return AE_BAD_PARAMETER;
 
 	result = pmic_get_reg_bit(address, d->thermal_table,
-				  d->thermal_table_count, &reg, NULL);
+				  d->thermal_table_count, &reg, &bit);
 	if (result == -ENOENT)
 		return AE_BAD_PARAMETER;
 
@@ -187,7 +194,8 @@ static acpi_status intel_pmic_thermal_handler(u32 function,
 	else if (pmic_thermal_is_aux(address))
 		result = pmic_thermal_aux(opregion, reg, function, value64);
 	else if (pmic_thermal_is_pen(address))
-		result = pmic_thermal_pen(opregion, reg, function, value64);
+		result = pmic_thermal_pen(opregion, reg, bit,
+						function, value64);
 	else
 		result = -EINVAL;
 
@@ -203,6 +211,48 @@ static acpi_status intel_pmic_thermal_handler(u32 function,
 	return AE_OK;
 }
 
+static acpi_status intel_pmic_regs_handler(u32 function,
+		acpi_physical_address address, u32 bits, u64 *value64,
+		void *handler_context, void *region_context)
+{
+	struct intel_pmic_opregion *opregion = region_context;
+	int result = 0;
+
+	switch (address) {
+	case 0:
+		return AE_OK;
+	case 1:
+		opregion->ctx.addr |= (*value64 & 0xff) << 8;
+		return AE_OK;
+	case 2:
+		opregion->ctx.addr |= *value64 & 0xff;
+		return AE_OK;
+	case 3:
+		opregion->ctx.val = *value64 & 0xff;
+		return AE_OK;
+	case 4:
+		if (*value64) {
+			result = regmap_write(opregion->regmap, opregion->ctx.addr,
+					      opregion->ctx.val);
+		} else {
+			result = regmap_read(opregion->regmap, opregion->ctx.addr,
+					     &opregion->ctx.val);
+			if (result == 0)
+				*value64 = opregion->ctx.val;
+		}
+		memset(&opregion->ctx, 0x00, sizeof(opregion->ctx));
+	}
+
+	if (result < 0) {
+		if (result == -EINVAL)
+			return AE_BAD_PARAMETER;
+		else
+			return AE_ERROR;
+	}
+
+	return AE_OK;
+}
+
 int intel_pmic_install_opregion_handler(struct device *dev, acpi_handle handle,
 					struct regmap *regmap,
 					struct intel_pmic_opregion_data *d)
@@ -242,16 +292,30 @@ int intel_pmic_install_opregion_handler(struct device *dev, acpi_handle handle,
 		acpi_remove_address_space_handler(handle, PMIC_POWER_OPREGION_ID,
 						  intel_pmic_power_handler);
 		ret = -ENODEV;
-		goto out_error;
+		goto out_remove_power_handler;
+	}
+
+	status = acpi_install_address_space_handler(handle,
+			PMIC_REGS_OPREGION_ID, intel_pmic_regs_handler, NULL,
+			opregion);
+	if (ACPI_FAILURE(status)) {
+		ret = -ENODEV;
+		goto out_remove_thermal_handler;
 	}
 
 	opregion->data = d;
 	return 0;
 
+out_remove_thermal_handler:
+	acpi_remove_address_space_handler(handle, PMIC_THERMAL_OPREGION_ID,
+					  intel_pmic_thermal_handler);
+
+out_remove_power_handler:
+	acpi_remove_address_space_handler(handle, PMIC_POWER_OPREGION_ID,
+					  intel_pmic_power_handler);
+
 out_error:
 	acpi_lpat_free_conversion_table(opregion->lpat_table);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(intel_pmic_install_opregion_handler);
-
-MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/pmic/intel_pmic.h b/drivers/acpi/pmic/intel_pmic.h
index d4e90af8f0dd..e8bfa7b865a5 100644
--- a/drivers/acpi/pmic/intel_pmic.h
+++ b/drivers/acpi/pmic/intel_pmic.h
@@ -12,8 +12,8 @@ struct intel_pmic_opregion_data {
 	int (*update_power)(struct regmap *r, int reg, int bit, bool on);
 	int (*get_raw_temp)(struct regmap *r, int reg);
 	int (*update_aux)(struct regmap *r, int reg, int raw_temp);
-	int (*get_policy)(struct regmap *r, int reg, u64 *value);
-	int (*update_policy)(struct regmap *r, int reg, int enable);
+	int (*get_policy)(struct regmap *r, int reg, int bit, u64 *value);
+	int (*update_policy)(struct regmap *r, int reg, int bit, int enable);
 	struct pmic_table *power_table;
 	int power_table_count;
 	struct pmic_table *thermal_table;
diff --git a/drivers/acpi/pmic/intel_pmic_bxtwc.c b/drivers/acpi/pmic/intel_pmic_bxtwc.c
new file mode 100644
index 000000000000..90011aad4d20
--- /dev/null
+++ b/drivers/acpi/pmic/intel_pmic_bxtwc.c
@@ -0,0 +1,420 @@
+/*
+ * intel_pmic_bxtwc.c - Intel BXT WhiskeyCove PMIC operation region driver
+ *
+ * Copyright (C) 2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/mfd/intel_soc_pmic.h>
+#include <linux/regmap.h>
+#include <linux/platform_device.h>
+#include "intel_pmic.h"
+
+#define WHISKEY_COVE_ALRT_HIGH_BIT_MASK 0x0F
+#define WHISKEY_COVE_ADC_HIGH_BIT(x)	(((x & 0x0F) << 8))
+#define WHISKEY_COVE_ADC_CURSRC(x)	(((x & 0xF0) >> 4))
+#define VR_MODE_DISABLED        0
+#define VR_MODE_AUTO            BIT(0)
+#define VR_MODE_NORMAL          BIT(1)
+#define VR_MODE_SWITCH          BIT(2)
+#define VR_MODE_ECO             (BIT(0)|BIT(1))
+#define VSWITCH2_OUTPUT         BIT(5)
+#define VSWITCH1_OUTPUT         BIT(4)
+#define VUSBPHY_CHARGE          BIT(1)
+
+static struct pmic_table power_table[] = {
+	{
+		.address = 0x0,
+		.reg = 0x63,
+		.bit = VR_MODE_AUTO,
+	}, /* VDD1 -> VDD1CNT */
+	{
+		.address = 0x04,
+		.reg = 0x65,
+		.bit = VR_MODE_AUTO,
+	}, /* VDD2 -> VDD2CNT */
+	{
+		.address = 0x08,
+		.reg = 0x67,
+		.bit = VR_MODE_AUTO,
+	}, /* VDD3 -> VDD3CNT */
+	{
+		.address = 0x0c,
+		.reg = 0x6d,
+		.bit = VR_MODE_AUTO,
+	}, /* VLFX -> VFLEXCNT */
+	{
+		.address = 0x10,
+		.reg = 0x6f,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP1A -> VPROG1ACNT */
+	{
+		.address = 0x14,
+		.reg = 0x70,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP1B -> VPROG1BCNT */
+	{
+		.address = 0x18,
+		.reg = 0x71,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP1C -> VPROG1CCNT */
+	{
+		.address = 0x1c,
+		.reg = 0x72,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP1D -> VPROG1DCNT */
+	{
+		.address = 0x20,
+		.reg = 0x73,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP2A -> VPROG2ACNT */
+	{
+		.address = 0x24,
+		.reg = 0x74,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP2B -> VPROG2BCNT */
+	{
+		.address = 0x28,
+		.reg = 0x75,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP2C -> VPROG2CCNT */
+	{
+		.address = 0x2c,
+		.reg = 0x76,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP3A -> VPROG3ACNT */
+	{
+		.address = 0x30,
+		.reg = 0x77,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP3B -> VPROG3BCNT */
+	{
+		.address = 0x34,
+		.reg = 0x78,
+		.bit = VSWITCH2_OUTPUT,
+	}, /* VSW2 -> VLD0CNT Bit 5*/
+	{
+		.address = 0x38,
+		.reg = 0x78,
+		.bit = VSWITCH1_OUTPUT,
+	}, /* VSW1 -> VLD0CNT Bit 4 */
+	{
+		.address = 0x3c,
+		.reg = 0x78,
+		.bit = VUSBPHY_CHARGE,
+	}, /* VUPY -> VLDOCNT Bit 1 */
+	{
+		.address = 0x40,
+		.reg = 0x7b,
+		.bit = VR_MODE_NORMAL,
+	}, /* VRSO -> VREFSOCCNT*/
+	{
+		.address = 0x44,
+		.reg = 0xA0,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP1E -> VPROG1ECNT */
+	{
+		.address = 0x48,
+		.reg = 0xA1,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP1F -> VPROG1FCNT */
+	{
+		.address = 0x4c,
+		.reg = 0xA2,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP2D -> VPROG2DCNT */
+	{
+		.address = 0x50,
+		.reg = 0xA3,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP4A -> VPROG4ACNT */
+	{
+		.address = 0x54,
+		.reg = 0xA4,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP4B -> VPROG4BCNT */
+	{
+		.address = 0x58,
+		.reg = 0xA5,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP4C -> VPROG4CCNT */
+	{
+		.address = 0x5c,
+		.reg = 0xA6,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP4D -> VPROG4DCNT */
+	{
+		.address = 0x60,
+		.reg = 0xA7,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP5A -> VPROG5ACNT */
+	{
+		.address = 0x64,
+		.reg = 0xA8,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP5B -> VPROG5BCNT */
+	{
+		.address = 0x68,
+		.reg = 0xA9,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP6A -> VPROG6ACNT */
+	{
+		.address = 0x6c,
+		.reg = 0xAA,
+		.bit = VR_MODE_NORMAL,
+	}, /* VP6B -> VPROG6BCNT */
+	{
+		.address = 0x70,
+		.reg = 0x36,
+		.bit = BIT(2),
+	}, /* SDWN_N -> MODEMCTRL Bit 2 */
+	{
+		.address = 0x74,
+		.reg = 0x36,
+		.bit = BIT(0),
+	} /* MOFF -> MODEMCTRL Bit 0 */
+};
+
+static struct pmic_table thermal_table[] = {
+	{
+		.address = 0x00,
+		.reg = 0x4F39
+	},
+	{
+		.address = 0x04,
+		.reg = 0x4F24
+	},
+	{
+		.address = 0x08,
+		.reg = 0x4F26
+	},
+	{
+		.address = 0x0c,
+		.reg = 0x4F3B
+	},
+	{
+		.address = 0x10,
+		.reg = 0x4F28
+	},
+	{
+		.address = 0x14,
+		.reg = 0x4F2A
+	},
+	{
+		.address = 0x18,
+		.reg = 0x4F3D
+	},
+	{
+		.address = 0x1c,
+		.reg = 0x4F2C
+	},
+	{
+		.address = 0x20,
+		.reg = 0x4F2E
+	},
+	{
+		.address = 0x24,
+		.reg = 0x4F3F
+	},
+	{
+		.address = 0x28,
+		.reg = 0x4F30
+	},
+	{
+		.address = 0x30,
+		.reg = 0x4F41
+	},
+	{
+		.address = 0x34,
+		.reg = 0x4F32
+	},
+	{
+		.address = 0x3c,
+		.reg = 0x4F43
+	},
+	{
+		.address = 0x40,
+		.reg = 0x4F34
+	},
+	{
+		.address = 0x48,
+		.reg = 0x4F6A,
+		.bit = 0,
+	},
+	{
+		.address = 0x4C,
+		.reg = 0x4F6A,
+		.bit = 1
+	},
+	{
+		.address = 0x50,
+		.reg = 0x4F6A,
+		.bit = 2
+	},
+	{
+		.address = 0x54,
+		.reg = 0x4F6A,
+		.bit = 4
+	},
+	{
+		.address = 0x58,
+		.reg = 0x4F6A,
+		.bit = 5
+	},
+	{
+		.address = 0x5C,
+		.reg = 0x4F6A,
+		.bit = 3
+	},
+};
+
+static int intel_bxtwc_pmic_get_power(struct regmap *regmap, int reg,
+		int bit, u64 *value)
+{
+	int data;
+
+	if (regmap_read(regmap, reg, &data))
+		return -EIO;
+
+	*value = (data & bit) ? 1 : 0;
+	return 0;
+}
+
+static int intel_bxtwc_pmic_update_power(struct regmap *regmap, int reg,
+		int bit, bool on)
+{
+	u8 val, mask = bit;
+
+	if (on)
+		val = 0xFF;
+	else
+		val = 0x0;
+
+	return regmap_update_bits(regmap, reg, mask, val);
+}
+
+static int intel_bxtwc_pmic_get_raw_temp(struct regmap *regmap, int reg)
+{
+	unsigned int val, adc_val, reg_val;
+	u8 temp_l, temp_h, cursrc;
+	unsigned long rlsb;
+	static const unsigned long rlsb_array[] = {
+		0, 260420, 130210, 65100, 32550, 16280,
+		8140, 4070, 2030, 0, 260420, 130210 };
+
+	if (regmap_read(regmap, reg, &val))
+		return -EIO;
+	temp_l = (u8) val;
+
+	if (regmap_read(regmap, (reg - 1), &val))
+		return -EIO;
+	temp_h = (u8) val;
+
+	reg_val = temp_l | WHISKEY_COVE_ADC_HIGH_BIT(temp_h);
+	cursrc = WHISKEY_COVE_ADC_CURSRC(temp_h);
+	rlsb = rlsb_array[cursrc];
+	adc_val = reg_val * rlsb / 1000;
+
+	return adc_val;
+}
+
+static int
+intel_bxtwc_pmic_update_aux(struct regmap *regmap, int reg, int raw)
+{
+	u32 bsr_num;
+	u16 resi_val, count = 0, thrsh = 0;
+	u8 alrt_h, alrt_l, cursel = 0;
+
+	bsr_num = raw;
+	bsr_num /= (1 << 5);
+
+	count = fls(bsr_num) - 1;
+
+	cursel = clamp_t(s8, (count - 7), 0, 7);
+	thrsh = raw / (1 << (4 + cursel));
+
+	resi_val = (cursel << 9) | thrsh;
+	alrt_h = (resi_val >> 8) & WHISKEY_COVE_ALRT_HIGH_BIT_MASK;
+	if (regmap_update_bits(regmap,
+				reg - 1,
+				WHISKEY_COVE_ALRT_HIGH_BIT_MASK,
+				alrt_h))
+		return -EIO;
+
+	alrt_l = (u8)resi_val;
+	return regmap_write(regmap, reg, alrt_l);
+}
+
+static int
+intel_bxtwc_pmic_get_policy(struct regmap *regmap, int reg, int bit, u64 *value)
+{
+	u8 mask = BIT(bit);
+	unsigned int val;
+
+	if (regmap_read(regmap, reg, &val))
+		return -EIO;
+
+	*value = (val & mask) >> bit;
+	return 0;
+}
+
+static int
+intel_bxtwc_pmic_update_policy(struct regmap *regmap,
+				int reg, int bit, int enable)
+{
+	u8 mask = BIT(bit), val = enable << bit;
+
+	return regmap_update_bits(regmap, reg, mask, val);
+}
+
+static struct intel_pmic_opregion_data intel_bxtwc_pmic_opregion_data = {
+	.get_power      = intel_bxtwc_pmic_get_power,
+	.update_power   = intel_bxtwc_pmic_update_power,
+	.get_raw_temp   = intel_bxtwc_pmic_get_raw_temp,
+	.update_aux     = intel_bxtwc_pmic_update_aux,
+	.get_policy     = intel_bxtwc_pmic_get_policy,
+	.update_policy  = intel_bxtwc_pmic_update_policy,
+	.power_table      = power_table,
+	.power_table_count = ARRAY_SIZE(power_table),
+	.thermal_table     = thermal_table,
+	.thermal_table_count = ARRAY_SIZE(thermal_table),
+};
+
+static int intel_bxtwc_pmic_opregion_probe(struct platform_device *pdev)
+{
+	struct intel_soc_pmic *pmic = dev_get_drvdata(pdev->dev.parent);
+
+	return intel_pmic_install_opregion_handler(&pdev->dev,
+			ACPI_HANDLE(pdev->dev.parent),
+			pmic->regmap,
+			&intel_bxtwc_pmic_opregion_data);
+}
+
+static struct platform_device_id bxt_wc_opregion_id_table[] = {
+	{ .name = "bxt_wcove_region" },
+	{},
+};
+
+static struct platform_driver intel_bxtwc_pmic_opregion_driver = {
+	.probe = intel_bxtwc_pmic_opregion_probe,
+	.driver = {
+		.name = "bxt_whiskey_cove_pmic",
+	},
+	.id_table = bxt_wc_opregion_id_table,
+};
+
+static int __init intel_bxtwc_pmic_opregion_driver_init(void)
+{
+	return platform_driver_register(&intel_bxtwc_pmic_opregion_driver);
+}
+device_initcall(intel_bxtwc_pmic_opregion_driver_init);
diff --git a/drivers/acpi/pmic/intel_pmic_crc.c b/drivers/acpi/pmic/intel_pmic_crc.c
index fcd1852dcdee..d7f1761ab1bc 100644
--- a/drivers/acpi/pmic/intel_pmic_crc.c
+++ b/drivers/acpi/pmic/intel_pmic_crc.c
@@ -141,7 +141,8 @@ static int intel_crc_pmic_update_aux(struct regmap *regmap, int reg, int raw)
 		regmap_update_bits(regmap, reg - 1, 0x3, raw >> 8) ? -EIO : 0;
 }
 
-static int intel_crc_pmic_get_policy(struct regmap *regmap, int reg, u64 *value)
+static int intel_crc_pmic_get_policy(struct regmap *regmap,
+					int reg, int bit, u64 *value)
 {
 	int pen;
 
@@ -152,7 +153,7 @@ static int intel_crc_pmic_get_policy(struct regmap *regmap, int reg, u64 *value)
 }
 
 static int intel_crc_pmic_update_policy(struct regmap *regmap,
-					int reg, int enable)
+					int reg, int bit, int enable)
 {
 	int alert0;
 
diff --git a/drivers/acpi/pmic/intel_pmic_xpower.c b/drivers/acpi/pmic/intel_pmic_xpower.c
index 6a082d4de12c..e6e991ac20f3 100644
--- a/drivers/acpi/pmic/intel_pmic_xpower.c
+++ b/drivers/acpi/pmic/intel_pmic_xpower.c
@@ -13,7 +13,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/mfd/axp20x.h>
 #include <linux/regmap.h>
@@ -262,7 +262,4 @@ static int __init intel_xpower_pmic_opregion_driver_init(void)
 {
 	return platform_driver_register(&intel_xpower_pmic_opregion_driver);
 }
-module_init(intel_xpower_pmic_opregion_driver_init);
-
-MODULE_DESCRIPTION("XPower AXP288 ACPI operation region driver");
-MODULE_LICENSE("GPL");
+device_initcall(intel_xpower_pmic_opregion_driver_init);
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 33a38d604630..9125d7d96372 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -108,13 +108,12 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry,
 	return -EINVAL;
 }
 
-static phys_cpuid_t map_madt_entry(int type, u32 acpi_id)
+static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt,
+				   int type, u32 acpi_id)
 {
 	unsigned long madt_end, entry;
 	phys_cpuid_t phys_id = PHYS_CPUID_INVALID;	/* CPU hardware ID */
-	struct acpi_table_madt *madt;
 
-	madt = get_madt_table();
 	if (!madt)
 		return phys_id;
 
@@ -145,6 +144,25 @@ static phys_cpuid_t map_madt_entry(int type, u32 acpi_id)
 	return phys_id;
 }
 
+phys_cpuid_t __init acpi_map_madt_entry(u32 acpi_id)
+{
+	struct acpi_table_madt *madt = NULL;
+	acpi_size tbl_size;
+	phys_cpuid_t rv;
+
+	acpi_get_table_with_size(ACPI_SIG_MADT, 0,
+				 (struct acpi_table_header **)&madt,
+				 &tbl_size);
+	if (!madt)
+		return PHYS_CPUID_INVALID;
+
+	rv = map_madt_entry(madt, 1, acpi_id);
+
+	early_acpi_os_unmap_memory(madt, tbl_size);
+
+	return rv;
+}
+
 static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -185,7 +203,7 @@ phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
 
 	phys_id = map_mat_entry(handle, type, acpi_id);
 	if (invalid_phys_cpuid(phys_id))
-		phys_id = map_madt_entry(type, acpi_id);
+		phys_id = map_madt_entry(get_madt_table(), type, acpi_id);
 
 	return phys_id;
 }
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index d2fa8cb82d2b..0ca14ac7bb28 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -90,7 +90,7 @@ static void acpi_processor_notify(acpi_handle handle, u32 event, void *data)
 						  pr->performance_platform_limit);
 		break;
 	case ACPI_PROCESSOR_NOTIFY_POWER:
-		acpi_processor_cst_has_changed(pr);
+		acpi_processor_power_state_has_changed(pr);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 444e3745c8b3..cea52528aa18 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -59,6 +59,12 @@ module_param(latency_factor, uint, 0644);
 
 static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device);
 
+struct cpuidle_driver acpi_idle_driver = {
+	.name =		"acpi_idle",
+	.owner =	THIS_MODULE,
+};
+
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
 static
 DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate);
 
@@ -297,7 +303,6 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *cst;
 
-
 	if (nocst)
 		return -ENODEV;
 
@@ -570,7 +575,7 @@ static int acpi_processor_power_verify(struct acpi_processor *pr)
 	return (working);
 }
 
-static int acpi_processor_get_power_info(struct acpi_processor *pr)
+static int acpi_processor_get_cstate_info(struct acpi_processor *pr)
 {
 	unsigned int i;
 	int result;
@@ -804,36 +809,12 @@ static void acpi_idle_enter_freeze(struct cpuidle_device *dev,
 	acpi_idle_do_entry(cx);
 }
 
-struct cpuidle_driver acpi_idle_driver = {
-	.name =		"acpi_idle",
-	.owner =	THIS_MODULE,
-};
-
-/**
- * acpi_processor_setup_cpuidle_cx - prepares and configures CPUIDLE
- * device i.e. per-cpu data
- *
- * @pr: the ACPI processor
- * @dev : the cpuidle device
- */
 static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
 					   struct cpuidle_device *dev)
 {
 	int i, count = CPUIDLE_DRIVER_STATE_START;
 	struct acpi_processor_cx *cx;
 
-	if (!pr->flags.power_setup_done)
-		return -EINVAL;
-
-	if (pr->flags.power == 0) {
-		return -EINVAL;
-	}
-
-	if (!dev)
-		return -EINVAL;
-
-	dev->cpu = pr->id;
-
 	if (max_cstate == 0)
 		max_cstate = 1;
 
@@ -856,31 +837,13 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
 	return 0;
 }
 
-/**
- * acpi_processor_setup_cpuidle states- prepares and configures cpuidle
- * global state data i.e. idle routines
- *
- * @pr: the ACPI processor
- */
-static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
+static int acpi_processor_setup_cstates(struct acpi_processor *pr)
 {
 	int i, count = CPUIDLE_DRIVER_STATE_START;
 	struct acpi_processor_cx *cx;
 	struct cpuidle_state *state;
 	struct cpuidle_driver *drv = &acpi_idle_driver;
 
-	if (!pr->flags.power_setup_done)
-		return -EINVAL;
-
-	if (pr->flags.power == 0)
-		return -EINVAL;
-
-	drv->safe_state_index = -1;
-	for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) {
-		drv->states[i].name[0] = '\0';
-		drv->states[i].desc[0] = '\0';
-	}
-
 	if (max_cstate == 0)
 		max_cstate = 1;
 
@@ -892,7 +855,7 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 
 		state = &drv->states[count];
 		snprintf(state->name, CPUIDLE_NAME_LEN, "C%d", i);
-		strncpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
+		strlcpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
 		state->exit_latency = cx->latency;
 		state->target_residency = cx->latency * latency_factor;
 		state->enter = acpi_idle_enter;
@@ -925,6 +888,450 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 	return 0;
 }
 
+static inline void acpi_processor_cstate_first_run_checks(void)
+{
+	acpi_status status;
+	static int first_run;
+
+	if (first_run)
+		return;
+	dmi_check_system(processor_power_dmi_table);
+	max_cstate = acpi_processor_cstate_check(max_cstate);
+	if (max_cstate < ACPI_C_STATES_MAX)
+		pr_notice("ACPI: processor limited to max C-state %d\n",
+			  max_cstate);
+	first_run++;
+
+	if (acpi_gbl_FADT.cst_control && !nocst) {
+		status = acpi_os_write_port(acpi_gbl_FADT.smi_command,
+					    acpi_gbl_FADT.cst_control, 8);
+		if (ACPI_FAILURE(status))
+			ACPI_EXCEPTION((AE_INFO, status,
+					"Notifying BIOS of _CST ability failed"));
+	}
+}
+#else
+
+static inline int disabled_by_idle_boot_param(void) { return 0; }
+static inline void acpi_processor_cstate_first_run_checks(void) { }
+static int acpi_processor_get_cstate_info(struct acpi_processor *pr)
+{
+	return -ENODEV;
+}
+
+static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
+					   struct cpuidle_device *dev)
+{
+	return -EINVAL;
+}
+
+static int acpi_processor_setup_cstates(struct acpi_processor *pr)
+{
+	return -EINVAL;
+}
+
+#endif /* CONFIG_ACPI_PROCESSOR_CSTATE */
+
+struct acpi_lpi_states_array {
+	unsigned int size;
+	unsigned int composite_states_size;
+	struct acpi_lpi_state *entries;
+	struct acpi_lpi_state *composite_states[ACPI_PROCESSOR_MAX_POWER];
+};
+
+static int obj_get_integer(union acpi_object *obj, u32 *value)
+{
+	if (obj->type != ACPI_TYPE_INTEGER)
+		return -EINVAL;
+
+	*value = obj->integer.value;
+	return 0;
+}
+
+static int acpi_processor_evaluate_lpi(acpi_handle handle,
+				       struct acpi_lpi_states_array *info)
+{
+	acpi_status status;
+	int ret = 0;
+	int pkg_count, state_idx = 1, loop;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *lpi_data;
+	struct acpi_lpi_state *lpi_state;
+
+	status = acpi_evaluate_object(handle, "_LPI", NULL, &buffer);
+	if (ACPI_FAILURE(status)) {
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No _LPI, giving up\n"));
+		return -ENODEV;
+	}
+
+	lpi_data = buffer.pointer;
+
+	/* There must be at least 4 elements = 3 elements + 1 package */
+	if (!lpi_data || lpi_data->type != ACPI_TYPE_PACKAGE ||
+	    lpi_data->package.count < 4) {
+		pr_debug("not enough elements in _LPI\n");
+		ret = -ENODATA;
+		goto end;
+	}
+
+	pkg_count = lpi_data->package.elements[2].integer.value;
+
+	/* Validate number of power states. */
+	if (pkg_count < 1 || pkg_count != lpi_data->package.count - 3) {
+		pr_debug("count given by _LPI is not valid\n");
+		ret = -ENODATA;
+		goto end;
+	}
+
+	lpi_state = kcalloc(pkg_count, sizeof(*lpi_state), GFP_KERNEL);
+	if (!lpi_state) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	info->size = pkg_count;
+	info->entries = lpi_state;
+
+	/* LPI States start at index 3 */
+	for (loop = 3; state_idx <= pkg_count; loop++, state_idx++, lpi_state++) {
+		union acpi_object *element, *pkg_elem, *obj;
+
+		element = &lpi_data->package.elements[loop];
+		if (element->type != ACPI_TYPE_PACKAGE || element->package.count < 7)
+			continue;
+
+		pkg_elem = element->package.elements;
+
+		obj = pkg_elem + 6;
+		if (obj->type == ACPI_TYPE_BUFFER) {
+			struct acpi_power_register *reg;
+
+			reg = (struct acpi_power_register *)obj->buffer.pointer;
+			if (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO &&
+			    reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)
+				continue;
+
+			lpi_state->address = reg->address;
+			lpi_state->entry_method =
+				reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE ?
+				ACPI_CSTATE_FFH : ACPI_CSTATE_SYSTEMIO;
+		} else if (obj->type == ACPI_TYPE_INTEGER) {
+			lpi_state->entry_method = ACPI_CSTATE_INTEGER;
+			lpi_state->address = obj->integer.value;
+		} else {
+			continue;
+		}
+
+		/* elements[7,8] skipped for now i.e. Residency/Usage counter*/
+
+		obj = pkg_elem + 9;
+		if (obj->type == ACPI_TYPE_STRING)
+			strlcpy(lpi_state->desc, obj->string.pointer,
+				ACPI_CX_DESC_LEN);
+
+		lpi_state->index = state_idx;
+		if (obj_get_integer(pkg_elem + 0, &lpi_state->min_residency)) {
+			pr_debug("No min. residency found, assuming 10 us\n");
+			lpi_state->min_residency = 10;
+		}
+
+		if (obj_get_integer(pkg_elem + 1, &lpi_state->wake_latency)) {
+			pr_debug("No wakeup residency found, assuming 10 us\n");
+			lpi_state->wake_latency = 10;
+		}
+
+		if (obj_get_integer(pkg_elem + 2, &lpi_state->flags))
+			lpi_state->flags = 0;
+
+		if (obj_get_integer(pkg_elem + 3, &lpi_state->arch_flags))
+			lpi_state->arch_flags = 0;
+
+		if (obj_get_integer(pkg_elem + 4, &lpi_state->res_cnt_freq))
+			lpi_state->res_cnt_freq = 1;
+
+		if (obj_get_integer(pkg_elem + 5, &lpi_state->enable_parent_state))
+			lpi_state->enable_parent_state = 0;
+	}
+
+	acpi_handle_debug(handle, "Found %d power states\n", state_idx);
+end:
+	kfree(buffer.pointer);
+	return ret;
+}
+
+/*
+ * flat_state_cnt - the number of composite LPI states after the process of flattening
+ */
+static int flat_state_cnt;
+
+/**
+ * combine_lpi_states - combine local and parent LPI states to form a composite LPI state
+ *
+ * @local: local LPI state
+ * @parent: parent LPI state
+ * @result: composite LPI state
+ */
+static bool combine_lpi_states(struct acpi_lpi_state *local,
+			       struct acpi_lpi_state *parent,
+			       struct acpi_lpi_state *result)
+{
+	if (parent->entry_method == ACPI_CSTATE_INTEGER) {
+		if (!parent->address) /* 0 means autopromotable */
+			return false;
+		result->address = local->address + parent->address;
+	} else {
+		result->address = parent->address;
+	}
+
+	result->min_residency = max(local->min_residency, parent->min_residency);
+	result->wake_latency = local->wake_latency + parent->wake_latency;
+	result->enable_parent_state = parent->enable_parent_state;
+	result->entry_method = local->entry_method;
+
+	result->flags = parent->flags;
+	result->arch_flags = parent->arch_flags;
+	result->index = parent->index;
+
+	strlcpy(result->desc, local->desc, ACPI_CX_DESC_LEN);
+	strlcat(result->desc, "+", ACPI_CX_DESC_LEN);
+	strlcat(result->desc, parent->desc, ACPI_CX_DESC_LEN);
+	return true;
+}
+
+#define ACPI_LPI_STATE_FLAGS_ENABLED			BIT(0)
+
+static void stash_composite_state(struct acpi_lpi_states_array *curr_level,
+				  struct acpi_lpi_state *t)
+{
+	curr_level->composite_states[curr_level->composite_states_size++] = t;
+}
+
+static int flatten_lpi_states(struct acpi_processor *pr,
+			      struct acpi_lpi_states_array *curr_level,
+			      struct acpi_lpi_states_array *prev_level)
+{
+	int i, j, state_count = curr_level->size;
+	struct acpi_lpi_state *p, *t = curr_level->entries;
+
+	curr_level->composite_states_size = 0;
+	for (j = 0; j < state_count; j++, t++) {
+		struct acpi_lpi_state *flpi;
+
+		if (!(t->flags & ACPI_LPI_STATE_FLAGS_ENABLED))
+			continue;
+
+		if (flat_state_cnt >= ACPI_PROCESSOR_MAX_POWER) {
+			pr_warn("Limiting number of LPI states to max (%d)\n",
+				ACPI_PROCESSOR_MAX_POWER);
+			pr_warn("Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n");
+			break;
+		}
+
+		flpi = &pr->power.lpi_states[flat_state_cnt];
+
+		if (!prev_level) { /* leaf/processor node */
+			memcpy(flpi, t, sizeof(*t));
+			stash_composite_state(curr_level, flpi);
+			flat_state_cnt++;
+			continue;
+		}
+
+		for (i = 0; i < prev_level->composite_states_size; i++) {
+			p = prev_level->composite_states[i];
+			if (t->index <= p->enable_parent_state &&
+			    combine_lpi_states(p, t, flpi)) {
+				stash_composite_state(curr_level, flpi);
+				flat_state_cnt++;
+				flpi++;
+			}
+		}
+	}
+
+	kfree(curr_level->entries);
+	return 0;
+}
+
+static int acpi_processor_get_lpi_info(struct acpi_processor *pr)
+{
+	int ret, i;
+	acpi_status status;
+	acpi_handle handle = pr->handle, pr_ahandle;
+	struct acpi_device *d = NULL;
+	struct acpi_lpi_states_array info[2], *tmp, *prev, *curr;
+
+	if (!osc_pc_lpi_support_confirmed)
+		return -EOPNOTSUPP;
+
+	if (!acpi_has_method(handle, "_LPI"))
+		return -EINVAL;
+
+	flat_state_cnt = 0;
+	prev = &info[0];
+	curr = &info[1];
+	handle = pr->handle;
+	ret = acpi_processor_evaluate_lpi(handle, prev);
+	if (ret)
+		return ret;
+	flatten_lpi_states(pr, prev, NULL);
+
+	status = acpi_get_parent(handle, &pr_ahandle);
+	while (ACPI_SUCCESS(status)) {
+		acpi_bus_get_device(pr_ahandle, &d);
+		handle = pr_ahandle;
+
+		if (strcmp(acpi_device_hid(d), ACPI_PROCESSOR_CONTAINER_HID))
+			break;
+
+		/* can be optional ? */
+		if (!acpi_has_method(handle, "_LPI"))
+			break;
+
+		ret = acpi_processor_evaluate_lpi(handle, curr);
+		if (ret)
+			break;
+
+		/* flatten all the LPI states in this level of hierarchy */
+		flatten_lpi_states(pr, curr, prev);
+
+		tmp = prev, prev = curr, curr = tmp;
+
+		status = acpi_get_parent(handle, &pr_ahandle);
+	}
+
+	pr->power.count = flat_state_cnt;
+	/* reset the index after flattening */
+	for (i = 0; i < pr->power.count; i++)
+		pr->power.lpi_states[i].index = i;
+
+	/* Tell driver that _LPI is supported. */
+	pr->flags.has_lpi = 1;
+	pr->flags.power = 1;
+
+	return 0;
+}
+
+int __weak acpi_processor_ffh_lpi_probe(unsigned int cpu)
+{
+	return -ENODEV;
+}
+
+int __weak acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+{
+	return -ENODEV;
+}
+
+/**
+ * acpi_idle_lpi_enter - enters an ACPI any LPI state
+ * @dev: the target CPU
+ * @drv: cpuidle driver containing cpuidle state info
+ * @index: index of target state
+ *
+ * Return: 0 for success or negative value for error
+ */
+static int acpi_idle_lpi_enter(struct cpuidle_device *dev,
+			       struct cpuidle_driver *drv, int index)
+{
+	struct acpi_processor *pr;
+	struct acpi_lpi_state *lpi;
+
+	pr = __this_cpu_read(processors);
+
+	if (unlikely(!pr))
+		return -EINVAL;
+
+	lpi = &pr->power.lpi_states[index];
+	if (lpi->entry_method == ACPI_CSTATE_FFH)
+		return acpi_processor_ffh_lpi_enter(lpi);
+
+	return -EINVAL;
+}
+
+static int acpi_processor_setup_lpi_states(struct acpi_processor *pr)
+{
+	int i;
+	struct acpi_lpi_state *lpi;
+	struct cpuidle_state *state;
+	struct cpuidle_driver *drv = &acpi_idle_driver;
+
+	if (!pr->flags.has_lpi)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < pr->power.count && i < CPUIDLE_STATE_MAX; i++) {
+		lpi = &pr->power.lpi_states[i];
+
+		state = &drv->states[i];
+		snprintf(state->name, CPUIDLE_NAME_LEN, "LPI-%d", i);
+		strlcpy(state->desc, lpi->desc, CPUIDLE_DESC_LEN);
+		state->exit_latency = lpi->wake_latency;
+		state->target_residency = lpi->min_residency;
+		if (lpi->arch_flags)
+			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+		state->enter = acpi_idle_lpi_enter;
+		drv->safe_state_index = i;
+	}
+
+	drv->state_count = i;
+
+	return 0;
+}
+
+/**
+ * acpi_processor_setup_cpuidle_states- prepares and configures cpuidle
+ * global state data i.e. idle routines
+ *
+ * @pr: the ACPI processor
+ */
+static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
+{
+	int i;
+	struct cpuidle_driver *drv = &acpi_idle_driver;
+
+	if (!pr->flags.power_setup_done || !pr->flags.power)
+		return -EINVAL;
+
+	drv->safe_state_index = -1;
+	for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) {
+		drv->states[i].name[0] = '\0';
+		drv->states[i].desc[0] = '\0';
+	}
+
+	if (pr->flags.has_lpi)
+		return acpi_processor_setup_lpi_states(pr);
+
+	return acpi_processor_setup_cstates(pr);
+}
+
+/**
+ * acpi_processor_setup_cpuidle_dev - prepares and configures CPUIDLE
+ * device i.e. per-cpu data
+ *
+ * @pr: the ACPI processor
+ * @dev : the cpuidle device
+ */
+static int acpi_processor_setup_cpuidle_dev(struct acpi_processor *pr,
+					    struct cpuidle_device *dev)
+{
+	if (!pr->flags.power_setup_done || !pr->flags.power || !dev)
+		return -EINVAL;
+
+	dev->cpu = pr->id;
+	if (pr->flags.has_lpi)
+		return acpi_processor_ffh_lpi_probe(pr->id);
+
+	return acpi_processor_setup_cpuidle_cx(pr, dev);
+}
+
+static int acpi_processor_get_power_info(struct acpi_processor *pr)
+{
+	int ret;
+
+	ret = acpi_processor_get_lpi_info(pr);
+	if (ret)
+		ret = acpi_processor_get_cstate_info(pr);
+
+	return ret;
+}
+
 int acpi_processor_hotplug(struct acpi_processor *pr)
 {
 	int ret = 0;
@@ -933,18 +1340,15 @@ int acpi_processor_hotplug(struct acpi_processor *pr)
 	if (disabled_by_idle_boot_param())
 		return 0;
 
-	if (nocst)
-		return -ENODEV;
-
 	if (!pr->flags.power_setup_done)
 		return -ENODEV;
 
 	dev = per_cpu(acpi_cpuidle_device, pr->id);
 	cpuidle_pause_and_lock();
 	cpuidle_disable_device(dev);
-	acpi_processor_get_power_info(pr);
-	if (pr->flags.power) {
-		acpi_processor_setup_cpuidle_cx(pr, dev);
+	ret = acpi_processor_get_power_info(pr);
+	if (!ret && pr->flags.power) {
+		acpi_processor_setup_cpuidle_dev(pr, dev);
 		ret = cpuidle_enable_device(dev);
 	}
 	cpuidle_resume_and_unlock();
@@ -952,7 +1356,7 @@ int acpi_processor_hotplug(struct acpi_processor *pr)
 	return ret;
 }
 
-int acpi_processor_cst_has_changed(struct acpi_processor *pr)
+int acpi_processor_power_state_has_changed(struct acpi_processor *pr)
 {
 	int cpu;
 	struct acpi_processor *_pr;
@@ -961,9 +1365,6 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 	if (disabled_by_idle_boot_param())
 		return 0;
 
-	if (nocst)
-		return -ENODEV;
-
 	if (!pr->flags.power_setup_done)
 		return -ENODEV;
 
@@ -1000,7 +1401,7 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 			acpi_processor_get_power_info(_pr);
 			if (_pr->flags.power) {
 				dev = per_cpu(acpi_cpuidle_device, cpu);
-				acpi_processor_setup_cpuidle_cx(_pr, dev);
+				acpi_processor_setup_cpuidle_dev(_pr, dev);
 				cpuidle_enable_device(dev);
 			}
 		}
@@ -1015,35 +1416,16 @@ static int acpi_processor_registered;
 
 int acpi_processor_power_init(struct acpi_processor *pr)
 {
-	acpi_status status;
 	int retval;
 	struct cpuidle_device *dev;
-	static int first_run;
 
 	if (disabled_by_idle_boot_param())
 		return 0;
 
-	if (!first_run) {
-		dmi_check_system(processor_power_dmi_table);
-		max_cstate = acpi_processor_cstate_check(max_cstate);
-		if (max_cstate < ACPI_C_STATES_MAX)
-			printk(KERN_NOTICE
-			       "ACPI: processor limited to max C-state %d\n",
-			       max_cstate);
-		first_run++;
-	}
-
-	if (acpi_gbl_FADT.cst_control && !nocst) {
-		status =
-		    acpi_os_write_port(acpi_gbl_FADT.smi_command, acpi_gbl_FADT.cst_control, 8);
-		if (ACPI_FAILURE(status)) {
-			ACPI_EXCEPTION((AE_INFO, status,
-					"Notifying BIOS of _CST ability failed"));
-		}
-	}
+	acpi_processor_cstate_first_run_checks();
 
-	acpi_processor_get_power_info(pr);
-	pr->flags.power_setup_done = 1;
+	if (!acpi_processor_get_power_info(pr))
+		pr->flags.power_setup_done = 1;
 
 	/*
 	 * Install the idle handler if processor power management is supported.
@@ -1066,7 +1448,7 @@ int acpi_processor_power_init(struct acpi_processor *pr)
 			return -ENOMEM;
 		per_cpu(acpi_cpuidle_device, pr->id) = dev;
 
-		acpi_processor_setup_cpuidle_cx(pr, dev);
+		acpi_processor_setup_cpuidle_dev(pr, dev);
 
 		/* Register per-cpu cpuidle_device. Cpuidle driver
 		 * must already be registered before registering device
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 5f28cf778349..405056b95b05 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -494,6 +494,8 @@ static void acpi_device_del(struct acpi_device *device)
 	device_del(&device->dev);
 }
 
+static BLOCKING_NOTIFIER_HEAD(acpi_reconfig_chain);
+
 static LIST_HEAD(acpi_device_del_list);
 static DEFINE_MUTEX(acpi_device_del_lock);
 
@@ -514,6 +516,9 @@ static void acpi_device_del_work_fn(struct work_struct *work_not_used)
 
 		mutex_unlock(&acpi_device_del_lock);
 
+		blocking_notifier_call_chain(&acpi_reconfig_chain,
+					     ACPI_RECONFIG_DEVICE_REMOVE, adev);
+
 		acpi_device_del(adev);
 		/*
 		 * Drop references to all power resources that might have been
@@ -1406,7 +1411,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	acpi_bus_get_flags(device);
 	device->flags.match_driver = false;
 	device->flags.initialized = true;
-	device->flags.visited = false;
+	acpi_device_clear_enumerated(device);
 	device_initialize(&device->dev);
 	dev_set_uevent_suppress(&device->dev, true);
 	acpi_init_coherency(device);
@@ -1676,15 +1681,20 @@ static void acpi_default_enumeration(struct acpi_device *device)
 	bool is_spi_i2c_slave = false;
 
 	/*
-	 * Do not enemerate SPI/I2C slaves as they will be enuerated by their
+	 * Do not enumerate SPI/I2C slaves as they will be enumerated by their
 	 * respective parents.
 	 */
 	INIT_LIST_HEAD(&resource_list);
 	acpi_dev_get_resources(device, &resource_list, acpi_check_spi_i2c_slave,
 			       &is_spi_i2c_slave);
 	acpi_dev_free_resource_list(&resource_list);
-	if (!is_spi_i2c_slave)
+	if (!is_spi_i2c_slave) {
 		acpi_create_platform_device(device);
+		acpi_device_set_enumerated(device);
+	} else {
+		blocking_notifier_call_chain(&acpi_reconfig_chain,
+					     ACPI_RECONFIG_DEVICE_ADD, device);
+	}
 }
 
 static const struct acpi_device_id generic_device_ids[] = {
@@ -1751,7 +1761,7 @@ static void acpi_bus_attach(struct acpi_device *device)
 	acpi_bus_get_status(device);
 	/* Skip devices that are not present. */
 	if (!acpi_device_is_present(device)) {
-		device->flags.visited = false;
+		acpi_device_clear_enumerated(device);
 		device->flags.power_manageable = 0;
 		return;
 	}
@@ -1766,7 +1776,7 @@ static void acpi_bus_attach(struct acpi_device *device)
 
 		device->flags.initialized = true;
 	}
-	device->flags.visited = false;
+
 	ret = acpi_scan_attach_handler(device);
 	if (ret < 0)
 		return;
@@ -1780,7 +1790,6 @@ static void acpi_bus_attach(struct acpi_device *device)
 		if (!ret && device->pnp.type.platform_id)
 			acpi_default_enumeration(device);
 	}
-	device->flags.visited = true;
 
  ok:
 	list_for_each_entry(child, &device->children, node)
@@ -1872,7 +1881,7 @@ void acpi_bus_trim(struct acpi_device *adev)
 	 */
 	acpi_device_set_power(adev, ACPI_STATE_D3_COLD);
 	adev->flags.initialized = false;
-	adev->flags.visited = false;
+	acpi_device_clear_enumerated(adev);
 }
 EXPORT_SYMBOL_GPL(acpi_bus_trim);
 
@@ -1916,6 +1925,8 @@ static int acpi_bus_scan_fixed(void)
 	return result < 0 ? result : 0;
 }
 
+static bool acpi_scan_initialized;
+
 int __init acpi_scan_init(void)
 {
 	int result;
@@ -1960,6 +1971,8 @@ int __init acpi_scan_init(void)
 
 	acpi_update_all_gpes();
 
+	acpi_scan_initialized = true;
+
  out:
 	mutex_unlock(&acpi_scan_lock);
 	return result;
@@ -2003,3 +2016,57 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr)
 
 	return count;
 }
+
+struct acpi_table_events_work {
+	struct work_struct work;
+	void *table;
+	u32 event;
+};
+
+static void acpi_table_events_fn(struct work_struct *work)
+{
+	struct acpi_table_events_work *tew;
+
+	tew = container_of(work, struct acpi_table_events_work, work);
+
+	if (tew->event == ACPI_TABLE_EVENT_LOAD) {
+		acpi_scan_lock_acquire();
+		acpi_bus_scan(ACPI_ROOT_OBJECT);
+		acpi_scan_lock_release();
+	}
+
+	kfree(tew);
+}
+
+void acpi_scan_table_handler(u32 event, void *table, void *context)
+{
+	struct acpi_table_events_work *tew;
+
+	if (!acpi_scan_initialized)
+		return;
+
+	if (event != ACPI_TABLE_EVENT_LOAD)
+		return;
+
+	tew = kmalloc(sizeof(*tew), GFP_KERNEL);
+	if (!tew)
+		return;
+
+	INIT_WORK(&tew->work, acpi_table_events_fn);
+	tew->table = table;
+	tew->event = event;
+
+	schedule_work(&tew->work);
+}
+
+int acpi_reconfig_notifier_register(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&acpi_reconfig_chain, nb);
+}
+EXPORT_SYMBOL(acpi_reconfig_notifier_register);
+
+int acpi_reconfig_notifier_unregister(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&acpi_reconfig_chain, nb);
+}
+EXPORT_SYMBOL(acpi_reconfig_notifier_unregister);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 7a2e4d45b266..2b38c1bb0446 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -47,15 +47,32 @@ static void acpi_sleep_tts_switch(u32 acpi_state)
 	}
 }
 
-static int tts_notify_reboot(struct notifier_block *this,
+static void acpi_sleep_pts_switch(u32 acpi_state)
+{
+	acpi_status status;
+
+	status = acpi_execute_simple_method(NULL, "\\_PTS", acpi_state);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		/*
+		 * OS can't evaluate the _PTS object correctly. Some warning
+		 * message will be printed. But it won't break anything.
+		 */
+		printk(KERN_NOTICE "Failure in evaluating _PTS object\n");
+	}
+}
+
+static int sleep_notify_reboot(struct notifier_block *this,
 			unsigned long code, void *x)
 {
 	acpi_sleep_tts_switch(ACPI_STATE_S5);
+
+	acpi_sleep_pts_switch(ACPI_STATE_S5);
+
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block tts_notifier = {
-	.notifier_call	= tts_notify_reboot,
+static struct notifier_block sleep_notifier = {
+	.notifier_call	= sleep_notify_reboot,
 	.next		= NULL,
 	.priority	= 0,
 };
@@ -899,9 +916,9 @@ int __init acpi_sleep_init(void)
 	pr_info(PREFIX "(supports%s)\n", supported);
 
 	/*
-	 * Register the tts_notifier to reboot notifier list so that the _TTS
-	 * object can also be evaluated when the system enters S5.
+	 * Register the sleep_notifier to reboot notifier list so that the _TTS
+	 * and _PTS object can also be evaluated when the system enters S5.
 	 */
-	register_reboot_notifier(&tts_notifier);
+	register_reboot_notifier(&sleep_notifier);
 	return 0;
 }
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 4b3a9e27f1b6..358165e9f5b8 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -378,8 +378,7 @@ static void acpi_table_attr_init(struct acpi_table_attr *table_attr,
 	return;
 }
 
-static acpi_status
-acpi_sysfs_table_handler(u32 event, void *table, void *context)
+acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context)
 {
 	struct acpi_table_attr *table_attr;
 
@@ -452,9 +451,8 @@ static int acpi_tables_sysfs_init(void)
 
 	kobject_uevent(tables_kobj, KOBJ_ADD);
 	kobject_uevent(dynamic_tables_kobj, KOBJ_ADD);
-	status = acpi_install_table_handler(acpi_sysfs_table_handler, NULL);
 
-	return ACPI_FAILURE(status) ? -EINVAL : 0;
+	return 0;
 err_dynamic_tables:
 	kobject_put(tables_kobj);
 err:
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index a372f9eaa15d..9f0ad6ebb368 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -34,6 +34,8 @@
 #include <linux/bootmem.h>
 #include <linux/earlycpio.h>
 #include <linux/memblock.h>
+#include <linux/initrd.h>
+#include <linux/acpi.h>
 #include "internal.h"
 
 #ifdef CONFIG_ACPI_CUSTOM_DSDT
@@ -481,8 +483,10 @@ static DECLARE_BITMAP(acpi_initrd_installed, NR_ACPI_INITRD_TABLES);
 
 #define MAP_CHUNK_SIZE   (NR_FIX_BTMAPS << PAGE_SHIFT)
 
-static void __init acpi_table_initrd_init(void *data, size_t size)
+void __init acpi_table_upgrade(void)
 {
+	void *data = (void *)initrd_start;
+	size_t size = initrd_end - initrd_start;
 	int sig, no, table_nr = 0, total_offset = 0;
 	long offset = 0;
 	struct acpi_table_header *table;
@@ -540,7 +544,7 @@ static void __init acpi_table_initrd_init(void *data, size_t size)
 		return;
 
 	acpi_tables_addr =
-		memblock_find_in_range(0, max_low_pfn_mapped << PAGE_SHIFT,
+		memblock_find_in_range(0, ACPI_TABLE_UPGRADE_MAX_PHYS,
 				       all_tables_size, PAGE_SIZE);
 	if (!acpi_tables_addr) {
 		WARN_ON(1);
@@ -578,10 +582,10 @@ static void __init acpi_table_initrd_init(void *data, size_t size)
 			clen = size;
 			if (clen > MAP_CHUNK_SIZE - slop)
 				clen = MAP_CHUNK_SIZE - slop;
-			dest_p = early_ioremap(dest_addr & PAGE_MASK,
-						 clen + slop);
+			dest_p = early_memremap(dest_addr & PAGE_MASK,
+						clen + slop);
 			memcpy(dest_p + slop, src_p, clen);
-			early_iounmap(dest_p, clen + slop);
+			early_memunmap(dest_p, clen + slop);
 			src_p += clen;
 			dest_addr += clen;
 			size -= clen;
@@ -696,10 +700,6 @@ next_table:
 	}
 }
 #else
-static void __init acpi_table_initrd_init(void *data, size_t size)
-{
-}
-
 static acpi_status
 acpi_table_initrd_override(struct acpi_table_header *existing_table,
 			   acpi_physical_address *address,
@@ -742,11 +742,6 @@ acpi_os_table_override(struct acpi_table_header *existing_table,
 	return AE_OK;
 }
 
-void __init early_acpi_table_init(void *data, size_t size)
-{
-	acpi_table_initrd_init(data, size);
-}
-
 /*
  * acpi_table_init()
  *
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 82707f9824ca..f4ebe39539af 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -1259,7 +1259,8 @@ static int __init acpi_thermal_init(void)
 		return -ENODEV;
 	}
 
-	acpi_thermal_pm_queue = create_workqueue("acpi_thermal_pm");
+	acpi_thermal_pm_queue = alloc_workqueue("acpi_thermal_pm",
+						WQ_HIGHPRI | WQ_MEM_RECLAIM, 0);
 	if (!acpi_thermal_pm_queue)
 		return -ENODEV;
 
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 3d1327615f72..a6b36fc53aec 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -167,6 +167,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"),
 		},
 	},
+        {
+         .callback = video_detect_force_video,
+         .ident = "ThinkPad X201T",
+         .matches = {
+                DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+                DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"),
+                },
+        },
 
 	/* The native backlight controls do not work on some older machines */
 	{
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index e2dc4c045146..2c8be74f401d 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -98,12 +98,12 @@ config SATA_AHCI_PLATFORM
 
 	  If unsure, say N.
 
-config AHCI_BRCMSTB
-	tristate "Broadcom STB AHCI SATA support"
-	depends on ARCH_BRCMSTB || BMIPS_GENERIC
+config AHCI_BRCM
+	tristate "Broadcom AHCI SATA support"
+	depends on ARCH_BRCMSTB || BMIPS_GENERIC || ARCH_BCM_NSP
 	help
 	  This option enables support for the AHCI SATA3 controller found on
-	  STB SoC's.
+	  Broadcom SoC's.
 
 	  If unsure, say N.
 
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 0b2afb7e5f35..a46e6b784bda 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_SATA_INIC162X)	+= sata_inic162x.o
 obj-$(CONFIG_SATA_SIL24)	+= sata_sil24.o
 obj-$(CONFIG_SATA_DWC)		+= sata_dwc_460ex.o
 obj-$(CONFIG_SATA_HIGHBANK)	+= sata_highbank.o libahci.o
-obj-$(CONFIG_AHCI_BRCMSTB)	+= ahci_brcmstb.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_BRCM)		+= ahci_brcm.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_CEVA)		+= ahci_ceva.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_DA850)	+= ahci_da850.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_IMX)		+= ahci_imx.o libahci.o libahci_platform.o
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index a83bbcc58b4c..90eabaf81215 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -580,7 +580,7 @@ static struct pci_driver ahci_pci_driver = {
 	},
 };
 
-#if defined(CONFIG_PATA_MARVELL) || defined(CONFIG_PATA_MARVELL_MODULE)
+#if IS_ENABLED(CONFIG_PATA_MARVELL)
 static int marvell_enable;
 #else
 static int marvell_enable = 1;
diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcm.c
index e87bcec0fd7c..6f8a7341fa08 100644
--- a/drivers/ata/ahci_brcmstb.c
+++ b/drivers/ata/ahci_brcm.c
@@ -71,6 +71,12 @@
 	(DATA_ENDIAN << DMADESC_ENDIAN_SHIFT) |		\
 	(MMIO_ENDIAN << MMIO_ENDIAN_SHIFT))
 
+enum brcm_ahci_version {
+	BRCM_SATA_BCM7425 = 1,
+	BRCM_SATA_BCM7445,
+	BRCM_SATA_NSP,
+};
+
 enum brcm_ahci_quirks {
 	BRCM_AHCI_QUIRK_NO_NCQ		= BIT(0),
 	BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE	= BIT(1),
@@ -81,6 +87,7 @@ struct brcm_ahci_priv {
 	void __iomem *top_ctrl;
 	u32 port_mask;
 	u32 quirks;
+	enum brcm_ahci_version version;
 };
 
 static const struct ata_port_info ahci_brcm_port_info = {
@@ -247,9 +254,19 @@ static u32 brcm_ahci_get_portmask(struct platform_device *pdev,
 
 static void brcm_sata_init(struct brcm_ahci_priv *priv)
 {
+	void __iomem *ctrl = priv->top_ctrl + SATA_TOP_CTRL_BUS_CTRL;
+
 	/* Configure endianness */
-	brcm_sata_writereg(BUS_CTRL_ENDIAN_CONF,
-			   priv->top_ctrl + SATA_TOP_CTRL_BUS_CTRL);
+	if (priv->version ==  BRCM_SATA_NSP) {
+		u32 data = brcm_sata_readreg(ctrl);
+
+		data &= ~((0x03 << DMADATA_ENDIAN_SHIFT) |
+			(0x03 << DMADESC_ENDIAN_SHIFT));
+		data |= (0x02 << DMADATA_ENDIAN_SHIFT) |
+			(0x02 << DMADESC_ENDIAN_SHIFT);
+		brcm_sata_writereg(data, ctrl);
+	} else
+		brcm_sata_writereg(BUS_CTRL_ENDIAN_CONF, ctrl);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -282,8 +299,17 @@ static struct scsi_host_template ahci_platform_sht = {
 	AHCI_SHT(DRV_NAME),
 };
 
+static const struct of_device_id ahci_of_match[] = {
+	{.compatible = "brcm,bcm7425-ahci", .data = (void *)BRCM_SATA_BCM7425},
+	{.compatible = "brcm,bcm7445-ahci", .data = (void *)BRCM_SATA_BCM7445},
+	{.compatible = "brcm,bcm-nsp-ahci", .data = (void *)BRCM_SATA_NSP},
+	{},
+};
+MODULE_DEVICE_TABLE(of, ahci_of_match);
+
 static int brcm_ahci_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *of_id;
 	struct device *dev = &pdev->dev;
 	struct brcm_ahci_priv *priv;
 	struct ahci_host_priv *hpriv;
@@ -293,6 +319,12 @@ static int brcm_ahci_probe(struct platform_device *pdev)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+
+	of_id = of_match_node(ahci_of_match, pdev->dev.of_node);
+	if (!of_id)
+		return -ENODEV;
+
+	priv->version = (enum brcm_ahci_version)of_id->data;
 	priv->dev = dev;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "top-ctrl");
@@ -300,7 +332,8 @@ static int brcm_ahci_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->top_ctrl))
 		return PTR_ERR(priv->top_ctrl);
 
-	if (of_device_is_compatible(dev->of_node, "brcm,bcm7425-ahci")) {
+	if ((priv->version == BRCM_SATA_BCM7425) ||
+		(priv->version == BRCM_SATA_NSP)) {
 		priv->quirks |= BRCM_AHCI_QUIRK_NO_NCQ;
 		priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE;
 	}
@@ -354,13 +387,6 @@ static int brcm_ahci_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id ahci_of_match[] = {
-	{.compatible = "brcm,bcm7425-ahci"},
-	{.compatible = "brcm,bcm7445-ahci"},
-	{},
-};
-MODULE_DEVICE_TABLE(of, ahci_of_match);
-
 static SIMPLE_DEV_PM_OPS(ahci_brcm_pm_ops, brcm_ahci_suspend, brcm_ahci_resume);
 
 static struct platform_driver brcm_ahci_driver = {
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 71b07198e207..7461a587b39b 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1975,7 +1975,7 @@ unsigned int ahci_qc_issue(struct ata_queued_cmd *qc)
 	 */
 	pp->active_link = qc->dev->link;
 
-	if (qc->tf.protocol == ATA_PROT_NCQ)
+	if (ata_is_ncq(qc->tf.protocol))
 		writel(1 << qc->tag, port_mmio + PORT_SCR_ACT);
 
 	if (pp->fbs_enabled && pp->fbs_last_dev != qc->dev->link->pmp) {
@@ -2392,12 +2392,20 @@ static int ahci_port_start(struct ata_port *ap)
 static void ahci_port_stop(struct ata_port *ap)
 {
 	const char *emsg = NULL;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+	void __iomem *host_mmio = hpriv->mmio;
 	int rc;
 
 	/* de-initialize port */
 	rc = ahci_deinit_port(ap, &emsg);
 	if (rc)
 		ata_port_warn(ap, "%s (%d)\n", emsg, rc);
+
+	/*
+	 * Clear GHC.IS to prevent stuck INTx after disabling MSI and
+	 * re-enabling INTx.
+	 */
+	writel(1 << ap->port_no, host_mmio + HOST_IRQ_STAT);
 }
 
 void ahci_print_info(struct ata_host *host, const char *scc_s)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 31c183aed368..67339b4f92f1 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1238,7 +1238,7 @@ static int ata_read_native_max_address(struct ata_device *dev, u64 *max_sectors)
 	} else
 		tf.command = ATA_CMD_READ_NATIVE_MAX;
 
-	tf.protocol |= ATA_PROT_NODATA;
+	tf.protocol = ATA_PROT_NODATA;
 	tf.device |= ATA_LBA;
 
 	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
@@ -1297,7 +1297,7 @@ static int ata_set_max_sectors(struct ata_device *dev, u64 new_sectors)
 		tf.device |= (new_sectors >> 24) & 0xf;
 	}
 
-	tf.protocol |= ATA_PROT_NODATA;
+	tf.protocol = ATA_PROT_NODATA;
 	tf.device |= ATA_LBA;
 
 	tf.lbal = (new_sectors >> 0) & 0xff;
@@ -4848,7 +4848,7 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc)
 {
 	struct ata_link *link = qc->dev->link;
 
-	if (qc->tf.protocol == ATA_PROT_NCQ) {
+	if (ata_is_ncq(qc->tf.protocol)) {
 		if (!ata_tag_valid(link->active_tag))
 			return 0;
 	} else {
@@ -5013,7 +5013,7 @@ void __ata_qc_complete(struct ata_queued_cmd *qc)
 		ata_sg_clean(qc);
 
 	/* command should be marked inactive atomically with qc completion */
-	if (qc->tf.protocol == ATA_PROT_NCQ) {
+	if (ata_is_ncq(qc->tf.protocol)) {
 		link->sactive &= ~(1 << qc->tag);
 		if (!link->sactive)
 			ap->nr_active_links--;
@@ -5050,7 +5050,7 @@ static void ata_verify_xfer(struct ata_queued_cmd *qc)
 {
 	struct ata_device *dev = qc->dev;
 
-	if (ata_is_nodata(qc->tf.protocol))
+	if (!ata_is_data(qc->tf.protocol))
 		return;
 
 	if ((dev->mwdma_mask || dev->udma_mask) && ata_is_pio(qc->tf.protocol))
@@ -5133,7 +5133,9 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 		switch (qc->tf.command) {
 		case ATA_CMD_SET_FEATURES:
 			if (qc->tf.feature != SETFEATURES_WC_ON &&
-			    qc->tf.feature != SETFEATURES_WC_OFF)
+			    qc->tf.feature != SETFEATURES_WC_OFF &&
+			    qc->tf.feature != SETFEATURES_RA_ON &&
+			    qc->tf.feature != SETFEATURES_RA_OFF)
 				break;
 			/* fall through */
 		case ATA_CMD_INIT_DEV_PARAMS: /* CHS translation changed */
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index c6f017458958..0e1ec37070d1 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2607,9 +2607,13 @@ static void ata_eh_link_report(struct ata_link *link)
 				[DMA_FROM_DEVICE]	= "in",
 			};
 			static const char *prot_str[] = {
+				[ATA_PROT_UNKNOWN]	= "unknown",
+				[ATA_PROT_NODATA]	= "nodata",
 				[ATA_PROT_PIO]		= "pio",
 				[ATA_PROT_DMA]		= "dma",
-				[ATA_PROT_NCQ]		= "ncq",
+				[ATA_PROT_NCQ]		= "ncq dma",
+				[ATA_PROT_NCQ_NODATA]	= "ncq nodata",
+				[ATAPI_PROT_NODATA]	= "nodata",
 				[ATAPI_PROT_PIO]	= "pio",
 				[ATAPI_PROT_DMA]	= "dma",
 			};
@@ -3177,7 +3181,7 @@ static void ata_eh_park_issue_cmd(struct ata_device *dev, int park)
 	}
 
 	tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
-	tf.protocol |= ATA_PROT_NODATA;
+	tf.protocol = ATA_PROT_NODATA;
 	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
 	if (park && (err_mask || tf.lbal != 0xc4)) {
 		ata_dev_err(dev, "head unload failed!\n");
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index bfec66fb26e2..e207b33e4ce9 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -304,7 +304,7 @@ static void ata_scsi_set_invalid_field(struct ata_device *dev,
 				       struct scsi_cmnd *cmd, u16 field, u8 bit)
 {
 	ata_scsi_set_sense(dev, cmd, ILLEGAL_REQUEST, 0x24, 0x0);
-	/* "Invalid field in cbd" */
+	/* "Invalid field in CDB" */
 	scsi_set_sense_field_pointer(cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE,
 				     field, bit, 1);
 }
@@ -1190,7 +1190,7 @@ static int atapi_drain_needed(struct request *rq)
 	if (likely(rq->cmd_type != REQ_TYPE_BLOCK_PC))
 		return 0;
 
-	if (!blk_rq_bytes(rq) || (rq->cmd_flags & REQ_WRITE))
+	if (!blk_rq_bytes(rq) || op_is_write(req_op(rq)))
 		return 0;
 
 	return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC;
@@ -2075,8 +2075,8 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
 		0x03,
 		0x20,	/* SBC-2 (no version claimed) */
 
-		0x02,
-		0x60	/* SPC-3 (no version claimed) */
+		0x03,
+		0x00	/* SPC-3 (no version claimed) */
 	};
 	const u8 versions_zbc[] = {
 		0x00,
@@ -2097,7 +2097,10 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
 		0,
 		0x5,	/* claim SPC-3 version compatibility */
 		2,
-		95 - 4
+		95 - 4,
+		0,
+		0,
+		2
 	};
 
 	VPRINTK("ENTER\n");
@@ -2109,8 +2112,10 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
 	    (args->dev->link->ap->pflags & ATA_PFLAG_EXTERNAL))
 		hdr[1] |= (1 << 7);
 
-	if (args->dev->class == ATA_DEV_ZAC)
+	if (args->dev->class == ATA_DEV_ZAC) {
 		hdr[0] = TYPE_ZBC;
+		hdr[2] = 0x7; /* claim SPC-5 version compatibility */
+	}
 
 	memcpy(rbuf, hdr, sizeof(hdr));
 	memcpy(&rbuf[8], "ATA     ", 8);
@@ -2314,7 +2319,7 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 	 * with the unmap bit set.
 	 */
 	if (ata_id_has_trim(args->id)) {
-		put_unaligned_be64(65535 * 512 / 8, &rbuf[36]);
+		put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM, &rbuf[36]);
 		put_unaligned_be32(1, &rbuf[28]);
 	}
 
@@ -2424,15 +2429,17 @@ static void modecpy(u8 *dest, const u8 *src, int n, bool changeable)
 static unsigned int ata_msense_caching(u16 *id, u8 *buf, bool changeable)
 {
 	modecpy(buf, def_cache_mpage, sizeof(def_cache_mpage), changeable);
-	if (changeable || ata_id_wcache_enabled(id))
-		buf[2] |= (1 << 2);	/* write cache enable */
-	if (!changeable && !ata_id_rahead_enabled(id))
-		buf[12] |= (1 << 5);	/* disable read ahead */
+	if (changeable) {
+		buf[2] |= (1 << 2);	/* ata_mselect_caching() */
+	} else {
+		buf[2] |= (ata_id_wcache_enabled(id) << 2);	/* write cache enable */
+		buf[12] |= (!ata_id_rahead_enabled(id) << 5);	/* disable read ahead */
+	}
 	return sizeof(def_cache_mpage);
 }
 
 /**
- *	ata_msense_ctl_mode - Simulate MODE SENSE control mode page
+ *	ata_msense_control - Simulate MODE SENSE control mode page
  *	@dev: ATA device of interest
  *	@buf: output buffer
  *	@changeable: whether changeable parameters are requested
@@ -2442,12 +2449,17 @@ static unsigned int ata_msense_caching(u16 *id, u8 *buf, bool changeable)
  *	LOCKING:
  *	None.
  */
-static unsigned int ata_msense_ctl_mode(struct ata_device *dev, u8 *buf,
+static unsigned int ata_msense_control(struct ata_device *dev, u8 *buf,
 					bool changeable)
 {
 	modecpy(buf, def_control_mpage, sizeof(def_control_mpage), changeable);
-	if (changeable && (dev->flags & ATA_DFLAG_D_SENSE))
-		buf[2] |= (1 << 2);	/* Descriptor sense requested */
+	if (changeable) {
+		buf[2] |= (1 << 2);	/* ata_mselect_control() */
+	} else {
+		bool d_sense = (dev->flags & ATA_DFLAG_D_SENSE);
+
+		buf[2] |= (d_sense << 2);	/* descriptor format sense data */
+	}
 	return sizeof(def_control_mpage);
 }
 
@@ -2566,13 +2578,13 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf)
 		break;
 
 	case CONTROL_MPAGE:
-		p += ata_msense_ctl_mode(args->dev, p, page_control == 1);
+		p += ata_msense_control(args->dev, p, page_control == 1);
 		break;
 
 	case ALL_MPAGES:
 		p += ata_msense_rw_recovery(p, page_control == 1);
 		p += ata_msense_caching(args->id, p, page_control == 1);
-		p += ata_msense_ctl_mode(args->dev, p, page_control == 1);
+		p += ata_msense_control(args->dev, p, page_control == 1);
 		break;
 
 	default:		/* invalid page code */
@@ -3077,6 +3089,9 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc)
 		goto invalid_fld;
 	}
 
+	if (ata_is_ncq(tf->protocol) && (cdb[2] & 0x3) == 0)
+		tf->protocol = ATA_PROT_NCQ_NODATA;
+
 	/* enable LBA */
 	tf->flags |= ATA_TFLAG_LBA;
 
@@ -3125,8 +3140,8 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc)
 		tf->command = cdb[9];
 	}
 
-	/* For NCQ commands with FPDMA protocol, copy the tag value */
-	if (tf->protocol == ATA_PROT_NCQ)
+	/* For NCQ commands copy the tag value */
+	if (ata_is_ncq(tf->protocol))
 		tf->nsect = qc->tag << 3;
 
 	/* enforce correct master/slave bit */
@@ -3305,7 +3320,13 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
 		goto invalid_param_len;
 
 	buf = page_address(sg_page(scsi_sglist(scmd)));
-	size = ata_set_lba_range_entries(buf, 512, block, n_block);
+
+	if (n_block <= 65535 * ATA_MAX_TRIM_RNUM) {
+		size = ata_set_lba_range_entries(buf, ATA_MAX_TRIM_RNUM, block, n_block);
+	} else {
+		fp = 2;
+		goto invalid_fld;
+	}
 
 	if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
 		/* Newer devices support queued TRIM commands */
@@ -3454,7 +3475,7 @@ static unsigned int ata_scsi_zbc_in_xlat(struct ata_queued_cmd *qc)
 		goto invalid_param_len;
 	}
 	sect = n_block / 512;
-	options = cdb[14];
+	options = cdb[14] & 0xbf;
 
 	if (ata_ncq_enabled(qc->dev) &&
 	    ata_fpdma_zac_mgmt_in_supported(qc->dev)) {
@@ -3464,7 +3485,7 @@ static unsigned int ata_scsi_zbc_in_xlat(struct ata_queued_cmd *qc)
 		tf->nsect = qc->tag << 3;
 		tf->feature = sect & 0xff;
 		tf->hob_feature = (sect >> 8) & 0xff;
-		tf->auxiliary = ATA_SUBCMD_ZAC_MGMT_IN_REPORT_ZONES;
+		tf->auxiliary = ATA_SUBCMD_ZAC_MGMT_IN_REPORT_ZONES | (options << 8);
 	} else {
 		tf->command = ATA_CMD_ZAC_MGMT_IN;
 		tf->feature = ATA_SUBCMD_ZAC_MGMT_IN_REPORT_ZONES;
@@ -3506,7 +3527,7 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc)
 	struct scsi_cmnd *scmd = qc->scsicmd;
 	struct ata_device *dev = qc->dev;
 	const u8 *cdb = scmd->cmnd;
-	u8 reset_all, sa;
+	u8 all, sa;
 	u64 block;
 	u32 n_block;
 	u16 fp = (u16)-1;
@@ -3533,20 +3554,20 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc)
 	if (block > dev->n_sectors)
 		goto out_of_range;
 
-	reset_all = cdb[14] & 0x1;
+	all = cdb[14] & 0x1;
 
 	if (ata_ncq_enabled(qc->dev) &&
 	    ata_fpdma_zac_mgmt_out_supported(qc->dev)) {
-		tf->protocol = ATA_PROT_NCQ;
+		tf->protocol = ATA_PROT_NCQ_NODATA;
 		tf->command = ATA_CMD_NCQ_NON_DATA;
-		tf->hob_nsect = ATA_SUBCMD_NCQ_NON_DATA_ZAC_MGMT_OUT;
+		tf->feature = ATA_SUBCMD_NCQ_NON_DATA_ZAC_MGMT_OUT;
 		tf->nsect = qc->tag << 3;
-		tf->auxiliary = sa | (reset_all & 0x1) << 8;
+		tf->auxiliary = sa | ((u16)all << 8);
 	} else {
 		tf->protocol = ATA_PROT_NODATA;
 		tf->command = ATA_CMD_ZAC_MGMT_OUT;
 		tf->feature = sa;
-		tf->hob_feature = reset_all & 0x1;
+		tf->hob_feature = all;
 	}
 	tf->lbah = (block >> 16) & 0xff;
 	tf->lbam = (block >> 8) & 0xff;
@@ -3667,7 +3688,7 @@ static int ata_mselect_control(struct ata_queued_cmd *qc,
 	/*
 	 * Check that read-only bits are not modified.
 	 */
-	ata_msense_ctl_mode(dev, mpage, false);
+	ata_msense_control(dev, mpage, false);
 	for (i = 0; i < CONTROL_MPAGE_LEN - 2; i++) {
 		if (i == 0)
 			continue;
@@ -4039,11 +4060,6 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
 	args.done = cmd->scsi_done;
 
 	switch(scsicmd[0]) {
-	/* TODO: worth improving? */
-	case FORMAT_UNIT:
-		ata_scsi_invalid_field(dev, cmd, 0);
-		break;
-
 	case INQUIRY:
 		if (scsicmd[1] & 2)		   /* is CmdDt set?  */
 		    ata_scsi_invalid_field(dev, cmd, 1);
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index e2d94972962d..7ef16c085058 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -495,12 +495,13 @@ struct ata_show_ering_arg {
 static int ata_show_ering(struct ata_ering_entry *ent, void *void_arg)
 {
 	struct ata_show_ering_arg* arg = void_arg;
-	struct timespec time;
+	u64 seconds;
+	u32 rem;
 
-	jiffies_to_timespec(ent->timestamp,&time);
+	seconds = div_u64_rem(ent->timestamp, HZ, &rem);
 	arg->written += sprintf(arg->buf + arg->written,
-			       "[%5lu.%06lu]",
-			       time.tv_sec, time.tv_nsec);
+			        "[%5llu.%09lu]", seconds,
+				rem * NSEC_PER_SEC / HZ);
 	arg->written += get_ata_err_names(ent->err_mask,
 					  arg->buf + arg->written);
 	return 0;
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 80fe0f6fed29..b4d54771c9fe 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -565,7 +565,7 @@ chan_request_fail:
 	qc->ap->hsm_task_state = HSM_ST_ERR;
 
 	cf_ctrl_reset(acdev);
-	spin_unlock_irqrestore(qc->ap->lock, flags);
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
 sff_intr:
 	dma_complete(acdev);
 }
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 970f7767e5fd..49d705c9f0f7 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -183,8 +183,8 @@ static void atiixp_set_dmamode(struct ata_port *ap, struct ata_device *adev)
 	 *	We must now look at the PIO mode situation. We may need to
 	 *	adjust the PIO mode to keep the timings acceptable
 	 */
-	 if (adev->dma_mode >= XFER_MW_DMA_2)
-	 	wanted_pio = 4;
+	if (adev->dma_mode >= XFER_MW_DMA_2)
+		wanted_pio = 4;
 	else if (adev->dma_mode == XFER_MW_DMA_1)
 		wanted_pio = 3;
 	else if (adev->dma_mode == XFER_MW_DMA_0)
diff --git a/drivers/ata/pata_hpt366.c b/drivers/ata/pata_hpt366.c
index e5fb7525a5df..a219a503c229 100644
--- a/drivers/ata/pata_hpt366.c
+++ b/drivers/ata/pata_hpt366.c
@@ -368,7 +368,7 @@ static int hpt36x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 
 	/* PCI clocking determines the ATA timing values to use */
 	/* info_hpt366 is safe against re-entry so we can scribble on it */
-	switch ((reg1 & 0x700) >> 8) {
+	switch ((reg1 & 0xf00) >> 8) {
 	case 9:
 		hpriv = &hpt366_40;
 		break;
diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c
index ae9feb1ba8f7..ff468a6fd8dd 100644
--- a/drivers/ata/pata_marvell.c
+++ b/drivers/ata/pata_marvell.c
@@ -146,7 +146,7 @@ static int marvell_init_one (struct pci_dev *pdev, const struct pci_device_id *i
 	if (pdev->device == 0x6101)
 		ppi[1] = &ata_dummy_port_info;
 
-#if defined(CONFIG_SATA_AHCI) || defined(CONFIG_SATA_AHCI_MODULE)
+#if IS_ENABLED(CONFIG_SATA_AHCI)
 	if (!marvell_pata_active(pdev)) {
 		printk(KERN_INFO DRV_NAME ": PATA port not active, deferring to AHCI driver.\n");
 		return -ENODEV;
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 00c2af1d211b..e0939bd5ea73 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -259,11 +259,8 @@ static int sata_dwc_dma_init_old(struct platform_device *pdev,
 	/* Get physical SATA DMA register base address */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	hsdev->dma->regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(hsdev->dma->regs)) {
-		dev_err(&pdev->dev,
-			"ioremap failed for AHBDMA register address\n");
+	if (IS_ERR(hsdev->dma->regs))
 		return PTR_ERR(hsdev->dma->regs);
-	}
 
 	/* Initialize AHB DMAC */
 	return dw_dma_probe(hsdev->dma);
@@ -281,7 +278,7 @@ static void sata_dwc_dma_exit_old(struct sata_dwc_device *hsdev)
 
 static const char *get_prot_descript(u8 protocol)
 {
-	switch ((enum ata_tf_protocols)protocol) {
+	switch (protocol) {
 	case ATA_PROT_NODATA:
 		return "ATA no data";
 	case ATA_PROT_PIO:
@@ -290,6 +287,8 @@ static const char *get_prot_descript(u8 protocol)
 		return "ATA DMA";
 	case ATA_PROT_NCQ:
 		return "ATA NCQ";
+	case ATA_PROT_NCQ_NODATA:
+		return "ATA NCQ no data";
 	case ATAPI_PROT_NODATA:
 		return "ATAPI no data";
 	case ATAPI_PROT_PIO:
@@ -1225,11 +1224,8 @@ static int sata_dwc_probe(struct platform_device *ofdev)
 	/* Ioremap SATA registers */
 	res = platform_get_resource(ofdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&ofdev->dev, res);
-	if (IS_ERR(base)) {
-		dev_err(&ofdev->dev,
-			"ioremap failed for SATA register address\n");
+	if (IS_ERR(base))
 		return PTR_ERR(base);
-	}
 	dev_dbg(&ofdev->dev, "ioremap done for SATA register address\n");
 
 	/* Synopsys DWC SATA specific Registers */
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 3657ac1cb801..8e2e4757adcb 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -121,6 +121,7 @@ int pm_clk_add(struct device *dev, const char *con_id)
 {
 	return __pm_clk_add(dev, con_id, NULL);
 }
+EXPORT_SYMBOL_GPL(pm_clk_add);
 
 /**
  * pm_clk_add_clk - Start using a device clock for power management.
@@ -136,9 +137,42 @@ int pm_clk_add_clk(struct device *dev, struct clk *clk)
 {
 	return __pm_clk_add(dev, NULL, clk);
 }
+EXPORT_SYMBOL_GPL(pm_clk_add_clk);
 
 
 /**
+ * of_pm_clk_add_clk - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @name: Name of clock that is going to be used for power management.
+ *
+ * Add the clock described in the 'clocks' device-tree node that matches
+ * with the 'name' provided, to the list of clocks used for the power
+ * management of @dev. On success, returns 0. Returns a negative error
+ * code if the clock is not found or cannot be added.
+ */
+int of_pm_clk_add_clk(struct device *dev, const char *name)
+{
+	struct clk *clk;
+	int ret;
+
+	if (!dev || !dev->of_node || !name)
+		return -EINVAL;
+
+	clk = of_clk_get_by_name(dev->of_node, name);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ret = pm_clk_add_clk(dev, clk);
+	if (ret) {
+		clk_put(clk);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_pm_clk_add_clk);
+
+/**
  * of_pm_clk_add_clks - Start using device clock(s) for power management.
  * @dev: Device whose clock(s) is going to be used for power management.
  *
@@ -192,6 +226,7 @@ error:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(of_pm_clk_add_clks);
 
 /**
  * __pm_clk_remove - Destroy PM clock entry.
@@ -252,6 +287,7 @@ void pm_clk_remove(struct device *dev, const char *con_id)
 
 	__pm_clk_remove(ce);
 }
+EXPORT_SYMBOL_GPL(pm_clk_remove);
 
 /**
  * pm_clk_remove_clk - Stop using a device clock for power management.
@@ -285,6 +321,7 @@ void pm_clk_remove_clk(struct device *dev, struct clk *clk)
 
 	__pm_clk_remove(ce);
 }
+EXPORT_SYMBOL_GPL(pm_clk_remove_clk);
 
 /**
  * pm_clk_init - Initialize a device's list of power management clocks.
@@ -299,6 +336,7 @@ void pm_clk_init(struct device *dev)
 	if (psd)
 		INIT_LIST_HEAD(&psd->clock_list);
 }
+EXPORT_SYMBOL_GPL(pm_clk_init);
 
 /**
  * pm_clk_create - Create and initialize a device's list of PM clocks.
@@ -311,6 +349,7 @@ int pm_clk_create(struct device *dev)
 {
 	return dev_pm_get_subsys_data(dev);
 }
+EXPORT_SYMBOL_GPL(pm_clk_create);
 
 /**
  * pm_clk_destroy - Destroy a device's list of power management clocks.
@@ -345,6 +384,7 @@ void pm_clk_destroy(struct device *dev)
 		__pm_clk_remove(ce);
 	}
 }
+EXPORT_SYMBOL_GPL(pm_clk_destroy);
 
 /**
  * pm_clk_suspend - Disable clocks in a device's PM clock list.
@@ -375,6 +415,7 @@ int pm_clk_suspend(struct device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pm_clk_suspend);
 
 /**
  * pm_clk_resume - Enable clocks in a device's PM clock list.
@@ -400,6 +441,7 @@ int pm_clk_resume(struct device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pm_clk_resume);
 
 /**
  * pm_clk_notify - Notify routine for device addition and removal.
@@ -480,6 +522,7 @@ int pm_clk_runtime_suspend(struct device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pm_clk_runtime_suspend);
 
 int pm_clk_runtime_resume(struct device *dev)
 {
@@ -495,6 +538,7 @@ int pm_clk_runtime_resume(struct device *dev)
 
 	return pm_generic_runtime_resume(dev);
 }
+EXPORT_SYMBOL_GPL(pm_clk_runtime_resume);
 
 #else /* !CONFIG_PM_CLK */
 
@@ -598,3 +642,4 @@ void pm_clk_add_notifier(struct bus_type *bus,
 	clknb->nb.notifier_call = pm_clk_notify;
 	bus_register_notifier(bus, &clknb->nb);
 }
+EXPORT_SYMBOL_GPL(pm_clk_add_notifier);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index de23b648fce3..a1f2aff33997 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -187,8 +187,7 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 	struct gpd_link *link;
 	int ret = 0;
 
-	if (genpd->status == GPD_STATE_ACTIVE
-	    || (genpd->prepared_count > 0 && genpd->suspend_power_off))
+	if (genpd->status == GPD_STATE_ACTIVE)
 		return 0;
 
 	/*
@@ -735,82 +734,24 @@ static int pm_genpd_prepare(struct device *dev)
 
 	mutex_lock(&genpd->lock);
 
-	if (genpd->prepared_count++ == 0) {
+	if (genpd->prepared_count++ == 0)
 		genpd->suspended_count = 0;
-		genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF;
-	}
 
 	mutex_unlock(&genpd->lock);
 
-	if (genpd->suspend_power_off)
-		return 0;
-
-	/*
-	 * The PM domain must be in the GPD_STATE_ACTIVE state at this point,
-	 * so genpd_poweron() will return immediately, but if the device
-	 * is suspended (e.g. it's been stopped by genpd_stop_dev()), we need
-	 * to make it operational.
-	 */
-	pm_runtime_resume(dev);
-	__pm_runtime_disable(dev, false);
-
 	ret = pm_generic_prepare(dev);
 	if (ret) {
 		mutex_lock(&genpd->lock);
 
-		if (--genpd->prepared_count == 0)
-			genpd->suspend_power_off = false;
+		genpd->prepared_count--;
 
 		mutex_unlock(&genpd->lock);
-		pm_runtime_enable(dev);
 	}
 
 	return ret;
 }
 
 /**
- * pm_genpd_suspend - Suspend a device belonging to an I/O PM domain.
- * @dev: Device to suspend.
- *
- * Suspend a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a PM domain consisting of I/O devices.
- */
-static int pm_genpd_suspend(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_suspend(dev);
-}
-
-/**
- * pm_genpd_suspend_late - Late suspend of a device from an I/O PM domain.
- * @dev: Device to suspend.
- *
- * Carry out a late suspend of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a PM domain consisting of I/O devices.
- */
-static int pm_genpd_suspend_late(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_suspend_late(dev);
-}
-
-/**
  * pm_genpd_suspend_noirq - Completion of suspend of device in an I/O PM domain.
  * @dev: Device to suspend.
  *
@@ -820,6 +761,7 @@ static int pm_genpd_suspend_late(struct device *dev)
 static int pm_genpd_suspend_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -827,11 +769,14 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off
-	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
+	if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))
 		return 0;
 
-	genpd_stop_dev(genpd, dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start) {
+		ret = pm_runtime_force_suspend(dev);
+		if (ret)
+			return ret;
+	}
 
 	/*
 	 * Since all of the "noirq" callbacks are executed sequentially, it is
@@ -853,6 +798,7 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 static int pm_genpd_resume_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -860,8 +806,7 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off
-	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
+	if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))
 		return 0;
 
 	/*
@@ -872,93 +817,10 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	pm_genpd_sync_poweron(genpd, true);
 	genpd->suspended_count--;
 
-	return genpd_start_dev(genpd, dev);
-}
-
-/**
- * pm_genpd_resume_early - Early resume of a device in an I/O PM domain.
- * @dev: Device to resume.
- *
- * Carry out an early resume of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
- */
-static int pm_genpd_resume_early(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_resume_early(dev);
-}
-
-/**
- * pm_genpd_resume - Resume of device in an I/O PM domain.
- * @dev: Device to resume.
- *
- * Resume a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a power domain consisting of I/O devices.
- */
-static int pm_genpd_resume(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_resume(dev);
-}
-
-/**
- * pm_genpd_freeze - Freezing a device in an I/O PM domain.
- * @dev: Device to freeze.
- *
- * Freeze a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a power domain consisting of I/O devices.
- */
-static int pm_genpd_freeze(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_freeze(dev);
-}
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_resume(dev);
 
-/**
- * pm_genpd_freeze_late - Late freeze of a device in an I/O PM domain.
- * @dev: Device to freeze.
- *
- * Carry out a late freeze of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
- */
-static int pm_genpd_freeze_late(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_freeze_late(dev);
+	return ret;
 }
 
 /**
@@ -973,6 +835,7 @@ static int pm_genpd_freeze_late(struct device *dev)
 static int pm_genpd_freeze_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -980,7 +843,10 @@ static int pm_genpd_freeze_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_stop_dev(genpd, dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_suspend(dev);
+
+	return ret;
 }
 
 /**
@@ -993,6 +859,7 @@ static int pm_genpd_freeze_noirq(struct device *dev)
 static int pm_genpd_thaw_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1000,51 +867,10 @@ static int pm_genpd_thaw_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ?
-		0 : genpd_start_dev(genpd, dev);
-}
-
-/**
- * pm_genpd_thaw_early - Early thaw of device in an I/O PM domain.
- * @dev: Device to thaw.
- *
- * Carry out an early thaw of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
- */
-static int pm_genpd_thaw_early(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_thaw_early(dev);
-}
-
-/**
- * pm_genpd_thaw - Thaw a device belonging to an I/O power domain.
- * @dev: Device to thaw.
- *
- * Thaw a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a power domain consisting of I/O devices.
- */
-static int pm_genpd_thaw(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_resume(dev);
 
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_thaw(dev);
+	return ret;
 }
 
 /**
@@ -1057,6 +883,7 @@ static int pm_genpd_thaw(struct device *dev)
 static int pm_genpd_restore_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1072,30 +899,20 @@ static int pm_genpd_restore_noirq(struct device *dev)
 	 * At this point suspended_count == 0 means we are being run for the
 	 * first time for the given domain in the present cycle.
 	 */
-	if (genpd->suspended_count++ == 0) {
+	if (genpd->suspended_count++ == 0)
 		/*
 		 * The boot kernel might put the domain into arbitrary state,
 		 * so make it appear as powered off to pm_genpd_sync_poweron(),
 		 * so that it tries to power it on in case it was really off.
 		 */
 		genpd->status = GPD_STATE_POWER_OFF;
-		if (genpd->suspend_power_off) {
-			/*
-			 * If the domain was off before the hibernation, make
-			 * sure it will be off going forward.
-			 */
-			genpd_power_off(genpd, true);
-
-			return 0;
-		}
-	}
-
-	if (genpd->suspend_power_off)
-		return 0;
 
 	pm_genpd_sync_poweron(genpd, true);
 
-	return genpd_start_dev(genpd, dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_resume(dev);
+
+	return ret;
 }
 
 /**
@@ -1110,7 +927,6 @@ static int pm_genpd_restore_noirq(struct device *dev)
 static void pm_genpd_complete(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	bool run_complete;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1118,20 +934,15 @@ static void pm_genpd_complete(struct device *dev)
 	if (IS_ERR(genpd))
 		return;
 
+	pm_generic_complete(dev);
+
 	mutex_lock(&genpd->lock);
 
-	run_complete = !genpd->suspend_power_off;
-	if (--genpd->prepared_count == 0)
-		genpd->suspend_power_off = false;
+	genpd->prepared_count--;
+	if (!genpd->prepared_count)
+		genpd_queue_power_off_work(genpd);
 
 	mutex_unlock(&genpd->lock);
-
-	if (run_complete) {
-		pm_generic_complete(dev);
-		pm_runtime_set_active(dev);
-		pm_runtime_enable(dev);
-		pm_request_idle(dev);
-	}
 }
 
 /**
@@ -1173,18 +984,10 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 #else /* !CONFIG_PM_SLEEP */
 
 #define pm_genpd_prepare		NULL
-#define pm_genpd_suspend		NULL
-#define pm_genpd_suspend_late		NULL
 #define pm_genpd_suspend_noirq		NULL
-#define pm_genpd_resume_early		NULL
 #define pm_genpd_resume_noirq		NULL
-#define pm_genpd_resume			NULL
-#define pm_genpd_freeze			NULL
-#define pm_genpd_freeze_late		NULL
 #define pm_genpd_freeze_noirq		NULL
-#define pm_genpd_thaw_early		NULL
 #define pm_genpd_thaw_noirq		NULL
-#define pm_genpd_thaw			NULL
 #define pm_genpd_restore_noirq		NULL
 #define pm_genpd_complete		NULL
 
@@ -1455,12 +1258,14 @@ EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
  * @genpd: PM domain object to initialize.
  * @gov: PM domain governor to associate with the domain (may be NULL).
  * @is_off: Initial value of the domain's power_is_off field.
+ *
+ * Returns 0 on successful initialization, else a negative error code.
  */
-void pm_genpd_init(struct generic_pm_domain *genpd,
-		   struct dev_power_governor *gov, bool is_off)
+int pm_genpd_init(struct generic_pm_domain *genpd,
+		  struct dev_power_governor *gov, bool is_off)
 {
 	if (IS_ERR_OR_NULL(genpd))
-		return;
+		return -EINVAL;
 
 	INIT_LIST_HEAD(&genpd->master_links);
 	INIT_LIST_HEAD(&genpd->slave_links);
@@ -1476,24 +1281,24 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.runtime_suspend = genpd_runtime_suspend;
 	genpd->domain.ops.runtime_resume = genpd_runtime_resume;
 	genpd->domain.ops.prepare = pm_genpd_prepare;
-	genpd->domain.ops.suspend = pm_genpd_suspend;
-	genpd->domain.ops.suspend_late = pm_genpd_suspend_late;
+	genpd->domain.ops.suspend = pm_generic_suspend;
+	genpd->domain.ops.suspend_late = pm_generic_suspend_late;
 	genpd->domain.ops.suspend_noirq = pm_genpd_suspend_noirq;
 	genpd->domain.ops.resume_noirq = pm_genpd_resume_noirq;
-	genpd->domain.ops.resume_early = pm_genpd_resume_early;
-	genpd->domain.ops.resume = pm_genpd_resume;
-	genpd->domain.ops.freeze = pm_genpd_freeze;
-	genpd->domain.ops.freeze_late = pm_genpd_freeze_late;
+	genpd->domain.ops.resume_early = pm_generic_resume_early;
+	genpd->domain.ops.resume = pm_generic_resume;
+	genpd->domain.ops.freeze = pm_generic_freeze;
+	genpd->domain.ops.freeze_late = pm_generic_freeze_late;
 	genpd->domain.ops.freeze_noirq = pm_genpd_freeze_noirq;
 	genpd->domain.ops.thaw_noirq = pm_genpd_thaw_noirq;
-	genpd->domain.ops.thaw_early = pm_genpd_thaw_early;
-	genpd->domain.ops.thaw = pm_genpd_thaw;
-	genpd->domain.ops.poweroff = pm_genpd_suspend;
-	genpd->domain.ops.poweroff_late = pm_genpd_suspend_late;
+	genpd->domain.ops.thaw_early = pm_generic_thaw_early;
+	genpd->domain.ops.thaw = pm_generic_thaw;
+	genpd->domain.ops.poweroff = pm_generic_poweroff;
+	genpd->domain.ops.poweroff_late = pm_generic_poweroff_late;
 	genpd->domain.ops.poweroff_noirq = pm_genpd_suspend_noirq;
 	genpd->domain.ops.restore_noirq = pm_genpd_restore_noirq;
-	genpd->domain.ops.restore_early = pm_genpd_resume_early;
-	genpd->domain.ops.restore = pm_genpd_resume;
+	genpd->domain.ops.restore_early = pm_generic_restore_early;
+	genpd->domain.ops.restore = pm_generic_restore;
 	genpd->domain.ops.complete = pm_genpd_complete;
 
 	if (genpd->flags & GENPD_FLAG_PM_CLK) {
@@ -1518,6 +1323,8 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(pm_genpd_init);
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index b74690418504..e097d355cc04 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1045,10 +1045,14 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status)
 		 */
 		if (!parent->power.disable_depth
 		    && !parent->power.ignore_children
-		    && parent->power.runtime_status != RPM_ACTIVE)
+		    && parent->power.runtime_status != RPM_ACTIVE) {
+			dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n",
+				dev_name(dev),
+				dev_name(parent));
 			error = -EBUSY;
-		else if (dev->power.runtime_status == RPM_SUSPENDED)
+		} else if (dev->power.runtime_status == RPM_SUSPENDED) {
 			atomic_inc(&parent->power.child_count);
+		}
 
 		spin_unlock(&parent->power.lock);
 
@@ -1256,7 +1260,7 @@ void pm_runtime_allow(struct device *dev)
 
 	dev->power.runtime_auto = true;
 	if (atomic_dec_and_test(&dev->power.usage_count))
-		rpm_idle(dev, RPM_AUTO);
+		rpm_idle(dev, RPM_AUTO | RPM_ASYNC);
 
  out:
 	spin_unlock_irq(&dev->power.lock);
@@ -1506,6 +1510,9 @@ int pm_runtime_force_resume(struct device *dev)
 		goto out;
 	}
 
+	if (!pm_runtime_status_suspended(dev))
+		goto out;
+
 	ret = pm_runtime_set_active(dev);
 	if (ret)
 		goto out;
diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c
index 1a8ec3b2b601..4735318f4268 100644
--- a/drivers/base/regmap/regmap-i2c.c
+++ b/drivers/base/regmap/regmap-i2c.c
@@ -259,7 +259,7 @@ static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c,
 {
 	if (i2c_check_functionality(i2c->adapter, I2C_FUNC_I2C))
 		return &regmap_i2c;
-	else if (config->reg_bits == 8 &&
+	else if (config->val_bits == 8 && config->reg_bits == 8 &&
 		 i2c_check_functionality(i2c->adapter,
 					 I2C_FUNC_SMBUS_I2C_BLOCK))
 		return &regmap_i2c_smbus_i2c_block;
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 26f799e71c82..ec262476d043 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -268,13 +268,16 @@ static irqreturn_t regmap_irq_thread(int irq, void *d)
 	bool handled = false;
 	u32 reg;
 
+	if (chip->handle_pre_irq)
+		chip->handle_pre_irq(chip->irq_drv_data);
+
 	if (chip->runtime_pm) {
 		ret = pm_runtime_get_sync(map->dev);
 		if (ret < 0) {
 			dev_err(map->dev, "IRQ thread failed to resume: %d\n",
 				ret);
 			pm_runtime_put(map->dev);
-			return IRQ_NONE;
+			goto exit;
 		}
 	}
 
@@ -296,7 +299,7 @@ static irqreturn_t regmap_irq_thread(int irq, void *d)
 		if (ret != 0) {
 			dev_err(map->dev, "Failed to read IRQ status: %d\n",
 				ret);
-			return IRQ_NONE;
+			goto exit;
 		}
 
 		for (i = 0; i < data->chip->num_regs; i++) {
@@ -312,7 +315,7 @@ static irqreturn_t regmap_irq_thread(int irq, void *d)
 				break;
 			default:
 				BUG();
-				return IRQ_NONE;
+				goto exit;
 			}
 		}
 
@@ -329,7 +332,7 @@ static irqreturn_t regmap_irq_thread(int irq, void *d)
 					ret);
 				if (chip->runtime_pm)
 					pm_runtime_put(map->dev);
-				return IRQ_NONE;
+				goto exit;
 			}
 		}
 	}
@@ -365,6 +368,10 @@ static irqreturn_t regmap_irq_thread(int irq, void *d)
 	if (chip->runtime_pm)
 		pm_runtime_put(map->dev);
 
+exit:
+	if (chip->handle_post_irq)
+		chip->handle_post_irq(chip->irq_drv_data);
+
 	if (handled)
 		return IRQ_HANDLED;
 	else
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index df2d2ef5d6b3..51fa7d66a393 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1777,8 +1777,6 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 	size_t val_bytes = map->format.val_bytes;
 	size_t total_size = val_bytes * val_count;
 
-	if (map->bus && !map->format.parse_inplace)
-		return -EINVAL;
 	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 
@@ -1789,7 +1787,8 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 	 *
 	 * The first if block is used for memory mapped io. It does not allow
 	 * val_bytes of 3 for example.
-	 * The second one is used for busses which do not have this limitation
+	 * The second one is for busses that do not provide raw I/O.
+	 * The third one is used for busses which do not have these limitations
 	 * and can write arbitrary value lengths.
 	 */
 	if (!map->bus) {
@@ -1825,6 +1824,32 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 		}
 out:
 		map->unlock(map->lock_arg);
+	} else if (map->bus && !map->format.parse_inplace) {
+		const u8 *u8 = val;
+		const u16 *u16 = val;
+		const u32 *u32 = val;
+		unsigned int ival;
+
+		for (i = 0; i < val_count; i++) {
+			switch (map->format.val_bytes) {
+			case 4:
+				ival = u32[i];
+				break;
+			case 2:
+				ival = u16[i];
+				break;
+			case 1:
+				ival = u8[i];
+				break;
+			default:
+				return -EINVAL;
+			}
+
+			ret = regmap_write(map, reg + (i * map->reg_stride),
+					   ival);
+			if (ret)
+				return ret;
+		}
 	} else if (map->use_single_write ||
 		   (map->max_raw_write && map->max_raw_write < total_size)) {
 		int chunk_stride = map->reg_stride;
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 8b7d7f8e5851..df3c97cb4c99 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -77,6 +77,14 @@ static DEVICE_ATTR_RO(book_siblings);
 static DEVICE_ATTR_RO(book_siblings_list);
 #endif
 
+#ifdef CONFIG_SCHED_DRAWER
+define_id_show_func(drawer_id);
+static DEVICE_ATTR_RO(drawer_id);
+define_siblings_show_func(drawer_siblings, drawer_cpumask);
+static DEVICE_ATTR_RO(drawer_siblings);
+static DEVICE_ATTR_RO(drawer_siblings_list);
+#endif
+
 static struct attribute *default_attrs[] = {
 	&dev_attr_physical_package_id.attr,
 	&dev_attr_core_id.attr,
@@ -89,6 +97,11 @@ static struct attribute *default_attrs[] = {
 	&dev_attr_book_siblings.attr,
 	&dev_attr_book_siblings_list.attr,
 #endif
+#ifdef CONFIG_SCHED_DRAWER
+	&dev_attr_drawer_id.attr,
+	&dev_attr_drawer_siblings.attr,
+	&dev_attr_drawer_siblings_list.attr,
+#endif
 	NULL
 };
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c04bd9bc39fd..ba5145d384d8 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -339,7 +339,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
 		goto io_error;
 
-	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
 		if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) ||
 		    bio->bi_iter.bi_size & ~PAGE_MASK)
 			goto io_error;
@@ -347,9 +347,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		goto out;
 	}
 
-	rw = bio_rw(bio);
-	if (rw == READA)
-		rw = READ;
+	rw = bio_data_dir(bio);
 
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
@@ -509,7 +507,9 @@ static struct brd_device *brd_alloc(int i)
 	blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
-
+#ifdef CONFIG_BLK_DEV_RAM_DAX
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
+#endif
 	disk = brd->brd_disk = alloc_disk(max_part);
 	if (!disk)
 		goto out_free_queue;
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 63c2064689f8..db9d6bb6352d 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1951,7 +1951,6 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 	if (cciss_create_ld_sysfs_entry(h, drv_index))
 		goto cleanup_queue;
 	disk->private_data = h->drv[drv_index];
-	disk->driverfs_dev = &h->drv[drv_index]->dev;
 
 	/* Set up queue information */
 	blk_queue_bounce_limit(disk->queue, h->pdev->dma_mask);
@@ -1973,7 +1972,7 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 	/* allows the interrupt handler to start the queue */
 	wmb();
 	h->drv[drv_index]->queue = disk->queue;
-	add_disk(disk);
+	device_add_disk(&h->drv[drv_index]->dev, disk);
 	return 0;
 
 cleanup_queue:
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 10459a145062..0a1aaf8c24c4 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -137,19 +137,19 @@ void wait_until_done_or_force_detached(struct drbd_device *device, struct drbd_b
 
 static int _drbd_md_sync_page_io(struct drbd_device *device,
 				 struct drbd_backing_dev *bdev,
-				 sector_t sector, int rw)
+				 sector_t sector, int op)
 {
 	struct bio *bio;
 	/* we do all our meta data IO in aligned 4k blocks. */
 	const int size = 4096;
-	int err;
+	int err, op_flags = 0;
 
 	device->md_io.done = 0;
 	device->md_io.error = -ENODEV;
 
-	if ((rw & WRITE) && !test_bit(MD_NO_FUA, &device->flags))
-		rw |= REQ_FUA | REQ_FLUSH;
-	rw |= REQ_SYNC | REQ_NOIDLE;
+	if ((op == REQ_OP_WRITE) && !test_bit(MD_NO_FUA, &device->flags))
+		op_flags |= REQ_FUA | REQ_PREFLUSH;
+	op_flags |= REQ_SYNC | REQ_NOIDLE;
 
 	bio = bio_alloc_drbd(GFP_NOIO);
 	bio->bi_bdev = bdev->md_bdev;
@@ -159,9 +159,9 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 		goto out;
 	bio->bi_private = device;
 	bio->bi_end_io = drbd_md_endio;
-	bio->bi_rw = rw;
+	bio_set_op_attrs(bio, op, op_flags);
 
-	if (!(rw & WRITE) && device->state.disk == D_DISKLESS && device->ldev == NULL)
+	if (op != REQ_OP_WRITE && device->state.disk == D_DISKLESS && device->ldev == NULL)
 		/* special case, drbd_md_read() during drbd_adm_attach(): no get_ldev */
 		;
 	else if (!get_ldev_if_state(device, D_ATTACHING)) {
@@ -174,10 +174,10 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 	bio_get(bio); /* one bio_put() is in the completion handler */
 	atomic_inc(&device->md_io.in_use); /* drbd_md_put_buffer() is in the completion handler */
 	device->md_io.submit_jif = jiffies;
-	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
+	if (drbd_insert_fault(device, (op == REQ_OP_WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
 		bio_io_error(bio);
 	else
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	wait_until_done_or_force_detached(device, bdev, &device->md_io.done);
 	if (!bio->bi_error)
 		err = device->md_io.error;
@@ -188,7 +188,7 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 }
 
 int drbd_md_sync_page_io(struct drbd_device *device, struct drbd_backing_dev *bdev,
-			 sector_t sector, int rw)
+			 sector_t sector, int op)
 {
 	int err;
 	D_ASSERT(device, atomic_read(&device->md_io.in_use) == 1);
@@ -197,19 +197,21 @@ int drbd_md_sync_page_io(struct drbd_device *device, struct drbd_backing_dev *bd
 
 	dynamic_drbd_dbg(device, "meta_data io: %s [%d]:%s(,%llus,%s) %pS\n",
 	     current->comm, current->pid, __func__,
-	     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ",
+	     (unsigned long long)sector, (op == REQ_OP_WRITE) ? "WRITE" : "READ",
 	     (void*)_RET_IP_ );
 
 	if (sector < drbd_md_first_sector(bdev) ||
 	    sector + 7 > drbd_md_last_sector(bdev))
 		drbd_alert(device, "%s [%d]:%s(,%llus,%s) out of range md access!\n",
 		     current->comm, current->pid, __func__,
-		     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
+		     (unsigned long long)sector,
+		     (op == REQ_OP_WRITE) ? "WRITE" : "READ");
 
-	err = _drbd_md_sync_page_io(device, bdev, sector, rw);
+	err = _drbd_md_sync_page_io(device, bdev, sector, op);
 	if (err) {
 		drbd_err(device, "drbd_md_sync_page_io(,%llus,%s) failed with error %d\n",
-		    (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ", err);
+		    (unsigned long long)sector,
+		    (op == REQ_OP_WRITE) ? "WRITE" : "READ", err);
 	}
 	return err;
 }
@@ -256,7 +258,7 @@ bool drbd_al_begin_io_fastpath(struct drbd_device *device, struct drbd_interval
 	unsigned first = i->sector >> (AL_EXTENT_SHIFT-9);
 	unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9);
 
-	D_ASSERT(device, (unsigned)(last - first) <= 1);
+	D_ASSERT(device, first <= last);
 	D_ASSERT(device, atomic_read(&device->local_cnt) > 0);
 
 	/* FIXME figure out a fast path for bios crossing AL extent boundaries */
@@ -339,6 +341,8 @@ static int __al_write_transaction(struct drbd_device *device, struct al_transact
 
 	i = 0;
 
+	drbd_bm_reset_al_hints(device);
+
 	/* Even though no one can start to change this list
 	 * once we set the LC_LOCKED -- from drbd_al_begin_io(),
 	 * lc_try_lock_for_transaction() --, someone may still
@@ -768,10 +772,18 @@ static bool lazy_bitmap_update_due(struct drbd_device *device)
 
 static void maybe_schedule_on_disk_bitmap_update(struct drbd_device *device, bool rs_done)
 {
-	if (rs_done)
-		set_bit(RS_DONE, &device->flags);
-		/* and also set RS_PROGRESS below */
-	else if (!lazy_bitmap_update_due(device))
+	if (rs_done) {
+		struct drbd_connection *connection = first_peer_device(device)->connection;
+		if (connection->agreed_pro_version <= 95 ||
+		    is_sync_target_state(device->state.conn))
+			set_bit(RS_DONE, &device->flags);
+			/* and also set RS_PROGRESS below */
+
+		/* Else: rather wait for explicit notification via receive_state,
+		 * to avoid uuids-rotated-too-fast causing full resync
+		 * in next handshake, in case the replication link breaks
+		 * at the most unfortunate time... */
+	} else if (!lazy_bitmap_update_due(device))
 		return;
 
 	drbd_device_post_work(device, RS_PROGRESS);
@@ -830,6 +842,13 @@ static int update_sync_bits(struct drbd_device *device,
 	return count;
 }
 
+static bool plausible_request_size(int size)
+{
+	return size > 0
+		&& size <= DRBD_MAX_BATCH_BIO_SIZE
+		&& IS_ALIGNED(size, 512);
+}
+
 /* clear the bit corresponding to the piece of storage in question:
  * size byte of data starting from sector.  Only clear a bits of the affected
  * one ore more _aligned_ BM_BLOCK_SIZE blocks.
@@ -845,11 +864,11 @@ int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
 	unsigned long count = 0;
 	sector_t esector, nr_sectors;
 
-	/* This would be an empty REQ_FLUSH, be silent. */
+	/* This would be an empty REQ_PREFLUSH, be silent. */
 	if ((mode == SET_OUT_OF_SYNC) && size == 0)
 		return 0;
 
-	if (size <= 0 || !IS_ALIGNED(size, 512) || size > DRBD_MAX_DISCARD_SIZE) {
+	if (!plausible_request_size(size)) {
 		drbd_err(device, "%s: sector=%llus size=%d nonsense!\n",
 				drbd_change_sync_fname[mode],
 				(unsigned long long)sector, size);
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 92d6fc020a65..ab62b81c2ca7 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -96,6 +96,13 @@ struct drbd_bitmap {
 	struct page **bm_pages;
 	spinlock_t bm_lock;
 
+	/* exclusively to be used by __al_write_transaction(),
+	 * drbd_bm_mark_for_writeout() and
+	 * and drbd_bm_write_hinted() -> bm_rw() called from there.
+	 */
+	unsigned int n_bitmap_hints;
+	unsigned int al_bitmap_hints[AL_UPDATES_PER_TRANSACTION];
+
 	/* see LIMITATIONS: above */
 
 	unsigned long bm_set;       /* nr of set bits; THINK maybe atomic_t? */
@@ -242,6 +249,11 @@ static void bm_set_page_need_writeout(struct page *page)
 	set_bit(BM_PAGE_NEED_WRITEOUT, &page_private(page));
 }
 
+void drbd_bm_reset_al_hints(struct drbd_device *device)
+{
+	device->bitmap->n_bitmap_hints = 0;
+}
+
 /**
  * drbd_bm_mark_for_writeout() - mark a page with a "hint" to be considered for writeout
  * @device:	DRBD device.
@@ -253,6 +265,7 @@ static void bm_set_page_need_writeout(struct page *page)
  */
 void drbd_bm_mark_for_writeout(struct drbd_device *device, int page_nr)
 {
+	struct drbd_bitmap *b = device->bitmap;
 	struct page *page;
 	if (page_nr >= device->bitmap->bm_number_of_pages) {
 		drbd_warn(device, "BAD: page_nr: %u, number_of_pages: %u\n",
@@ -260,7 +273,9 @@ void drbd_bm_mark_for_writeout(struct drbd_device *device, int page_nr)
 		return;
 	}
 	page = device->bitmap->bm_pages[page_nr];
-	set_bit(BM_PAGE_HINT_WRITEOUT, &page_private(page));
+	BUG_ON(b->n_bitmap_hints >= ARRAY_SIZE(b->al_bitmap_hints));
+	if (!test_and_set_bit(BM_PAGE_HINT_WRITEOUT, &page_private(page)))
+		b->al_bitmap_hints[b->n_bitmap_hints++] = page_nr;
 }
 
 static int bm_test_page_unchanged(struct page *page)
@@ -427,8 +442,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want)
 }
 
 /*
- * called on driver init only. TODO call when a device is created.
- * allocates the drbd_bitmap, and stores it in device->bitmap.
+ * allocates the drbd_bitmap and stores it in device->bitmap.
  */
 int drbd_bm_init(struct drbd_device *device)
 {
@@ -633,7 +647,8 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi
 	unsigned long bits, words, owords, obits;
 	unsigned long want, have, onpages; /* number of pages */
 	struct page **npages, **opages = NULL;
-	int err = 0, growing;
+	int err = 0;
+	bool growing;
 
 	if (!expect(b))
 		return -ENOMEM;
@@ -980,7 +995,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 	struct drbd_bitmap *b = device->bitmap;
 	struct page *page;
 	unsigned int len;
-	unsigned int rw = (ctx->flags & BM_AIO_READ) ? READ : WRITE;
+	unsigned int op = (ctx->flags & BM_AIO_READ) ? REQ_OP_READ : REQ_OP_WRITE;
 
 	sector_t on_disk_sector =
 		device->ldev->md.md_offset + device->ldev->md.bm_offset;
@@ -1011,12 +1026,12 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 	bio_add_page(bio, page, len, 0);
 	bio->bi_private = ctx;
 	bio->bi_end_io = drbd_bm_endio;
+	bio_set_op_attrs(bio, op, 0);
 
-	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) {
-		bio->bi_rw |= rw;
+	if (drbd_insert_fault(device, (op == REQ_OP_WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) {
 		bio_io_error(bio);
 	} else {
-		submit_bio(rw, bio);
+		submit_bio(bio);
 		/* this should not count as user activity and cause the
 		 * resync to throttle -- see drbd_rs_should_slow_down(). */
 		atomic_add(len >> 9, &device->rs_sect_ev);
@@ -1030,7 +1045,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 {
 	struct drbd_bm_aio_ctx *ctx;
 	struct drbd_bitmap *b = device->bitmap;
-	int num_pages, i, count = 0;
+	unsigned int num_pages, i, count = 0;
 	unsigned long now;
 	char ppb[10];
 	int err = 0;
@@ -1078,16 +1093,37 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 	now = jiffies;
 
 	/* let the layers below us try to merge these bios... */
-	for (i = 0; i < num_pages; i++) {
-		/* ignore completely unchanged pages */
-		if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
-			break;
-		if (!(flags & BM_AIO_READ)) {
-			if ((flags & BM_AIO_WRITE_HINTED) &&
-			    !test_and_clear_bit(BM_PAGE_HINT_WRITEOUT,
-				    &page_private(b->bm_pages[i])))
-				continue;
 
+	if (flags & BM_AIO_READ) {
+		for (i = 0; i < num_pages; i++) {
+			atomic_inc(&ctx->in_flight);
+			bm_page_io_async(ctx, i);
+			++count;
+			cond_resched();
+		}
+	} else if (flags & BM_AIO_WRITE_HINTED) {
+		/* ASSERT: BM_AIO_WRITE_ALL_PAGES is not set. */
+		unsigned int hint;
+		for (hint = 0; hint < b->n_bitmap_hints; hint++) {
+			i = b->al_bitmap_hints[hint];
+			if (i >= num_pages) /* == -1U: no hint here. */
+				continue;
+			/* Several AL-extents may point to the same page. */
+			if (!test_and_clear_bit(BM_PAGE_HINT_WRITEOUT,
+			    &page_private(b->bm_pages[i])))
+				continue;
+			/* Has it even changed? */
+			if (bm_test_page_unchanged(b->bm_pages[i]))
+				continue;
+			atomic_inc(&ctx->in_flight);
+			bm_page_io_async(ctx, i);
+			++count;
+		}
+	} else {
+		for (i = 0; i < num_pages; i++) {
+			/* ignore completely unchanged pages */
+			if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
+				break;
 			if (!(flags & BM_AIO_WRITE_ALL_PAGES) &&
 			    bm_test_page_unchanged(b->bm_pages[i])) {
 				dynamic_drbd_dbg(device, "skipped bm write for idx %u\n", i);
@@ -1100,11 +1136,11 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 				dynamic_drbd_dbg(device, "skipped bm lazy write for idx %u\n", i);
 				continue;
 			}
+			atomic_inc(&ctx->in_flight);
+			bm_page_io_async(ctx, i);
+			++count;
+			cond_resched();
 		}
-		atomic_inc(&ctx->in_flight);
-		bm_page_io_async(ctx, i);
-		++count;
-		cond_resched();
 	}
 
 	/*
@@ -1121,10 +1157,14 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 		kref_put(&ctx->kref, &drbd_bm_aio_ctx_destroy);
 
 	/* summary for global bitmap IO */
-	if (flags == 0)
-		drbd_info(device, "bitmap %s of %u pages took %lu jiffies\n",
-			 (flags & BM_AIO_READ) ? "READ" : "WRITE",
-			 count, jiffies - now);
+	if (flags == 0) {
+		unsigned int ms = jiffies_to_msecs(jiffies - now);
+		if (ms > 5) {
+			drbd_info(device, "bitmap %s of %u pages took %u ms\n",
+				 (flags & BM_AIO_READ) ? "READ" : "WRITE",
+				 count, ms);
+		}
+	}
 
 	if (ctx->error) {
 		drbd_alert(device, "we had at least one MD IO ERROR during bitmap IO\n");
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index 4de95bbff486..be91a8d7c22a 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -237,14 +237,9 @@ static void seq_print_peer_request_flags(struct seq_file *m, struct drbd_peer_re
 	seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C");
 	seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync");
 
-	if (f & EE_IS_TRIM) {
-		seq_putc(m, sep);
-		sep = '|';
-		if (f & EE_IS_TRIM_USE_ZEROOUT)
-			seq_puts(m, "zero-out");
-		else
-			seq_puts(m, "trim");
-	}
+	if (f & EE_IS_TRIM)
+		__seq_print_rq_state_bit(m, f & EE_IS_TRIM_USE_ZEROOUT, &sep, "zero-out", "trim");
+	seq_print_rq_state_bit(m, f & EE_WRITE_SAME, &sep, "write-same");
 	seq_putc(m, '\n');
 }
 
@@ -908,7 +903,7 @@ static int drbd_version_open(struct inode *inode, struct file *file)
 	return single_open(file, drbd_version_show, NULL);
 }
 
-static struct file_operations drbd_version_fops = {
+static const struct file_operations drbd_version_fops = {
 	.owner = THIS_MODULE,
 	.open = drbd_version_open,
 	.llseek = seq_lseek,
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 7a1cf7eaa71d..7b54354976a5 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -468,9 +468,15 @@ enum {
 	/* this is/was a write request */
 	__EE_WRITE,
 
+	/* this is/was a write same request */
+	__EE_WRITE_SAME,
+
 	/* this originates from application on peer
 	 * (not some resync or verify or other DRBD internal request) */
 	__EE_APPLICATION,
+
+	/* If it contains only 0 bytes, send back P_RS_DEALLOCATED */
+	__EE_RS_THIN_REQ,
 };
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
@@ -484,7 +490,9 @@ enum {
 #define EE_IN_INTERVAL_TREE	(1<<__EE_IN_INTERVAL_TREE)
 #define EE_SUBMITTED		(1<<__EE_SUBMITTED)
 #define EE_WRITE		(1<<__EE_WRITE)
+#define EE_WRITE_SAME		(1<<__EE_WRITE_SAME)
 #define EE_APPLICATION		(1<<__EE_APPLICATION)
+#define EE_RS_THIN_REQ		(1<<__EE_RS_THIN_REQ)
 
 /* flag bits per device */
 enum {
@@ -1123,6 +1131,7 @@ extern int drbd_send_ov_request(struct drbd_peer_device *, sector_t sector, int
 extern int drbd_send_bitmap(struct drbd_device *device);
 extern void drbd_send_sr_reply(struct drbd_peer_device *, enum drbd_state_rv retcode);
 extern void conn_send_sr_reply(struct drbd_connection *connection, enum drbd_state_rv retcode);
+extern int drbd_send_rs_deallocated(struct drbd_peer_device *, struct drbd_peer_request *);
 extern void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev);
 extern void drbd_device_cleanup(struct drbd_device *device);
 void drbd_print_uuids(struct drbd_device *device, const char *text);
@@ -1327,14 +1336,14 @@ struct bm_extent {
 #endif
 #endif
 
-/* BIO_MAX_SIZE is 256 * PAGE_SIZE,
+/* Estimate max bio size as 256 * PAGE_SIZE,
  * so for typical PAGE_SIZE of 4k, that is (1<<20) Byte.
  * Since we may live in a mixed-platform cluster,
  * we limit us to a platform agnostic constant here for now.
  * A followup commit may allow even bigger BIO sizes,
  * once we thought that through. */
 #define DRBD_MAX_BIO_SIZE (1U << 20)
-#if DRBD_MAX_BIO_SIZE > BIO_MAX_SIZE
+#if DRBD_MAX_BIO_SIZE > (BIO_MAX_PAGES << PAGE_SHIFT)
 #error Architecture not supported: DRBD_MAX_BIO_SIZE > BIO_MAX_SIZE
 #endif
 #define DRBD_MAX_BIO_SIZE_SAFE (1U << 12)       /* Works always = 4k */
@@ -1342,11 +1351,11 @@ struct bm_extent {
 #define DRBD_MAX_SIZE_H80_PACKET (1U << 15) /* Header 80 only allows packets up to 32KiB data */
 #define DRBD_MAX_BIO_SIZE_P95    (1U << 17) /* Protocol 95 to 99 allows bios up to 128KiB */
 
-/* For now, don't allow more than one activity log extent worth of data
- * to be discarded in one go. We may need to rework drbd_al_begin_io()
- * to allow for even larger discard ranges */
-#define DRBD_MAX_DISCARD_SIZE	AL_EXTENT_SIZE
-#define DRBD_MAX_DISCARD_SECTORS (DRBD_MAX_DISCARD_SIZE >> 9)
+/* For now, don't allow more than half of what we can "activate" in one
+ * activity log transaction to be discarded in one go. We may need to rework
+ * drbd_al_begin_io() to allow for even larger discard ranges */
+#define DRBD_MAX_BATCH_BIO_SIZE	 (AL_UPDATES_PER_TRANSACTION/2*AL_EXTENT_SIZE)
+#define DRBD_MAX_BBIO_SECTORS    (DRBD_MAX_BATCH_BIO_SIZE >> 9)
 
 extern int  drbd_bm_init(struct drbd_device *device);
 extern int  drbd_bm_resize(struct drbd_device *device, sector_t sectors, int set_new_bits);
@@ -1369,6 +1378,7 @@ extern int  drbd_bm_e_weight(struct drbd_device *device, unsigned long enr);
 extern int  drbd_bm_read(struct drbd_device *device) __must_hold(local);
 extern void drbd_bm_mark_for_writeout(struct drbd_device *device, int page_nr);
 extern int  drbd_bm_write(struct drbd_device *device) __must_hold(local);
+extern void drbd_bm_reset_al_hints(struct drbd_device *device) __must_hold(local);
 extern int  drbd_bm_write_hinted(struct drbd_device *device) __must_hold(local);
 extern int  drbd_bm_write_lazy(struct drbd_device *device, unsigned upper_idx) __must_hold(local);
 extern int drbd_bm_write_all(struct drbd_device *device) __must_hold(local);
@@ -1483,12 +1493,14 @@ enum determine_dev_size {
 extern enum determine_dev_size
 drbd_determine_dev_size(struct drbd_device *, enum dds_flags, struct resize_parms *) __must_hold(local);
 extern void resync_after_online_grow(struct drbd_device *);
-extern void drbd_reconsider_max_bio_size(struct drbd_device *device, struct drbd_backing_dev *bdev);
+extern void drbd_reconsider_queue_parameters(struct drbd_device *device,
+			struct drbd_backing_dev *bdev, struct o_qlim *o);
 extern enum drbd_state_rv drbd_set_role(struct drbd_device *device,
 					enum drbd_role new_role,
 					int force);
 extern bool conn_try_outdate_peer(struct drbd_connection *connection);
 extern void conn_try_outdate_peer_async(struct drbd_connection *connection);
+extern enum drbd_peer_state conn_khelper(struct drbd_connection *connection, char *cmd);
 extern int drbd_khelper(struct drbd_device *device, char *cmd);
 
 /* drbd_worker.c */
@@ -1507,7 +1519,7 @@ extern int drbd_resync_finished(struct drbd_device *device);
 extern void *drbd_md_get_buffer(struct drbd_device *device, const char *intent);
 extern void drbd_md_put_buffer(struct drbd_device *device);
 extern int drbd_md_sync_page_io(struct drbd_device *device,
-		struct drbd_backing_dev *bdev, sector_t sector, int rw);
+		struct drbd_backing_dev *bdev, sector_t sector, int op);
 extern void drbd_ov_out_of_sync_found(struct drbd_device *, sector_t, int);
 extern void wait_until_done_or_force_detached(struct drbd_device *device,
 		struct drbd_backing_dev *bdev, unsigned int *done);
@@ -1548,6 +1560,8 @@ extern void start_resync_timer_fn(unsigned long data);
 extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
 
 /* drbd_receiver.c */
+extern int drbd_issue_discard_or_zero_out(struct drbd_device *device,
+		sector_t start, unsigned int nr_sectors, bool discard);
 extern int drbd_receiver(struct drbd_thread *thi);
 extern int drbd_ack_receiver(struct drbd_thread *thi);
 extern void drbd_send_ping_wf(struct work_struct *ws);
@@ -1557,11 +1571,11 @@ extern bool drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector
 		bool throttle_if_app_is_waiting);
 extern int drbd_submit_peer_request(struct drbd_device *,
 				    struct drbd_peer_request *, const unsigned,
-				    const int);
+				    const unsigned, const int);
 extern int drbd_free_peer_reqs(struct drbd_device *, struct list_head *);
 extern struct drbd_peer_request *drbd_alloc_peer_req(struct drbd_peer_device *, u64,
 						     sector_t, unsigned int,
-						     bool,
+						     unsigned int,
 						     gfp_t) __must_hold(local);
 extern void __drbd_free_peer_req(struct drbd_device *, struct drbd_peer_request *,
 				 int);
@@ -1635,8 +1649,6 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
 /* drbd_proc.c */
 extern struct proc_dir_entry *drbd_proc;
 extern const struct file_operations drbd_proc_fops;
-extern const char *drbd_conn_str(enum drbd_conns s);
-extern const char *drbd_role_str(enum drbd_role s);
 
 /* drbd_actlog.c */
 extern bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval *i);
@@ -2095,13 +2107,22 @@ static inline void _sub_unacked(struct drbd_device *device, int n, const char *f
 	ERR_IF_CNT_IS_NEGATIVE(unacked_cnt, func, line);
 }
 
+static inline bool is_sync_target_state(enum drbd_conns connection_state)
+{
+	return	connection_state == C_SYNC_TARGET ||
+		connection_state == C_PAUSED_SYNC_T;
+}
+
+static inline bool is_sync_source_state(enum drbd_conns connection_state)
+{
+	return	connection_state == C_SYNC_SOURCE ||
+		connection_state == C_PAUSED_SYNC_S;
+}
+
 static inline bool is_sync_state(enum drbd_conns connection_state)
 {
-	return
-	   (connection_state == C_SYNC_SOURCE
-	||  connection_state == C_SYNC_TARGET
-	||  connection_state == C_PAUSED_SYNC_S
-	||  connection_state == C_PAUSED_SYNC_T);
+	return	is_sync_source_state(connection_state) ||
+		is_sync_target_state(connection_state);
 }
 
 /**
diff --git a/drivers/block/drbd/drbd_interval.h b/drivers/block/drbd/drbd_interval.h
index f210543f05f4..23c5a94428d2 100644
--- a/drivers/block/drbd/drbd_interval.h
+++ b/drivers/block/drbd/drbd_interval.h
@@ -6,13 +6,13 @@
 
 struct drbd_interval {
 	struct rb_node rb;
-	sector_t sector;	/* start sector of the interval */
-	unsigned int size;	/* size in bytes */
-	sector_t end;		/* highest interval end in subtree */
-	int local:1		/* local or remote request? */;
-	int waiting:1;		/* someone is waiting for this to complete */
-	int completed:1;	/* this has been completed already;
-				 * ignore for conflict detection */
+	sector_t sector;		/* start sector of the interval */
+	unsigned int size;		/* size in bytes */
+	sector_t end;			/* highest interval end in subtree */
+	unsigned int local:1		/* local or remote request? */;
+	unsigned int waiting:1;		/* someone is waiting for completion */
+	unsigned int completed:1;	/* this has been completed already;
+					 * ignore for conflict detection */
 };
 
 static inline void drbd_clear_interval(struct drbd_interval *i)
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 2ba1494b2799..0501ae0c517b 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -31,7 +31,7 @@
 #include <linux/module.h>
 #include <linux/jiffies.h>
 #include <linux/drbd.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/types.h>
 #include <net/sock.h>
 #include <linux/ctype.h>
@@ -920,6 +920,31 @@ void drbd_gen_and_send_sync_uuid(struct drbd_peer_device *peer_device)
 	}
 }
 
+/* communicated if (agreed_features & DRBD_FF_WSAME) */
+void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct request_queue *q)
+{
+	if (q) {
+		p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q));
+		p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q));
+		p->qlim->alignment_offset = cpu_to_be32(queue_alignment_offset(q));
+		p->qlim->io_min = cpu_to_be32(queue_io_min(q));
+		p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
+		p->qlim->discard_enabled = blk_queue_discard(q);
+		p->qlim->discard_zeroes_data = queue_discard_zeroes_data(q);
+		p->qlim->write_same_capable = !!q->limits.max_write_same_sectors;
+	} else {
+		q = device->rq_queue;
+		p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q));
+		p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q));
+		p->qlim->alignment_offset = 0;
+		p->qlim->io_min = cpu_to_be32(queue_io_min(q));
+		p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
+		p->qlim->discard_enabled = 0;
+		p->qlim->discard_zeroes_data = 0;
+		p->qlim->write_same_capable = 0;
+	}
+}
+
 int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enum dds_flags flags)
 {
 	struct drbd_device *device = peer_device->device;
@@ -928,29 +953,37 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu
 	sector_t d_size, u_size;
 	int q_order_type;
 	unsigned int max_bio_size;
+	unsigned int packet_size;
+
+	sock = &peer_device->connection->data;
+	p = drbd_prepare_command(peer_device, sock);
+	if (!p)
+		return -EIO;
 
+	packet_size = sizeof(*p);
+	if (peer_device->connection->agreed_features & DRBD_FF_WSAME)
+		packet_size += sizeof(p->qlim[0]);
+
+	memset(p, 0, packet_size);
 	if (get_ldev_if_state(device, D_NEGOTIATING)) {
-		D_ASSERT(device, device->ldev->backing_bdev);
+		struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
 		d_size = drbd_get_max_capacity(device->ldev);
 		rcu_read_lock();
 		u_size = rcu_dereference(device->ldev->disk_conf)->disk_size;
 		rcu_read_unlock();
 		q_order_type = drbd_queue_order_type(device);
-		max_bio_size = queue_max_hw_sectors(device->ldev->backing_bdev->bd_disk->queue) << 9;
+		max_bio_size = queue_max_hw_sectors(q) << 9;
 		max_bio_size = min(max_bio_size, DRBD_MAX_BIO_SIZE);
+		assign_p_sizes_qlim(device, p, q);
 		put_ldev(device);
 	} else {
 		d_size = 0;
 		u_size = 0;
 		q_order_type = QUEUE_ORDERED_NONE;
 		max_bio_size = DRBD_MAX_BIO_SIZE; /* ... multiple BIOs per peer_request */
+		assign_p_sizes_qlim(device, p, NULL);
 	}
 
-	sock = &peer_device->connection->data;
-	p = drbd_prepare_command(peer_device, sock);
-	if (!p)
-		return -EIO;
-
 	if (peer_device->connection->agreed_pro_version <= 94)
 		max_bio_size = min(max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
 	else if (peer_device->connection->agreed_pro_version < 100)
@@ -962,7 +995,8 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu
 	p->max_bio_size = cpu_to_be32(max_bio_size);
 	p->queue_order_type = cpu_to_be16(q_order_type);
 	p->dds_flags = cpu_to_be16(flags);
-	return drbd_send_command(peer_device, sock, P_SIZES, sizeof(*p), NULL, 0);
+
+	return drbd_send_command(peer_device, sock, P_SIZES, packet_size, NULL, 0);
 }
 
 /**
@@ -1377,6 +1411,22 @@ int drbd_send_ack_ex(struct drbd_peer_device *peer_device, enum drbd_packet cmd,
 			      cpu_to_be64(block_id));
 }
 
+int drbd_send_rs_deallocated(struct drbd_peer_device *peer_device,
+			     struct drbd_peer_request *peer_req)
+{
+	struct drbd_socket *sock;
+	struct p_block_desc *p;
+
+	sock = &peer_device->connection->data;
+	p = drbd_prepare_command(peer_device, sock);
+	if (!p)
+		return -EIO;
+	p->sector = cpu_to_be64(peer_req->i.sector);
+	p->blksize = cpu_to_be32(peer_req->i.size);
+	p->pad = 0;
+	return drbd_send_command(peer_device, sock, P_RS_DEALLOCATED, sizeof(*p), NULL, 0);
+}
+
 int drbd_send_drequest(struct drbd_peer_device *peer_device, int cmd,
 		       sector_t sector, int size, u64 block_id)
 {
@@ -1561,6 +1611,9 @@ static int _drbd_send_bio(struct drbd_peer_device *peer_device, struct bio *bio)
 					 ? 0 : MSG_MORE);
 		if (err)
 			return err;
+		/* REQ_OP_WRITE_SAME has only one segment */
+		if (bio_op(bio) == REQ_OP_WRITE_SAME)
+			break;
 	}
 	return 0;
 }
@@ -1579,6 +1632,9 @@ static int _drbd_send_zc_bio(struct drbd_peer_device *peer_device, struct bio *b
 				      bio_iter_last(bvec, iter) ? 0 : MSG_MORE);
 		if (err)
 			return err;
+		/* REQ_OP_WRITE_SAME has only one segment */
+		if (bio_op(bio) == REQ_OP_WRITE_SAME)
+			break;
 	}
 	return 0;
 }
@@ -1603,15 +1659,17 @@ static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device,
 	return 0;
 }
 
-static u32 bio_flags_to_wire(struct drbd_connection *connection, unsigned long bi_rw)
+static u32 bio_flags_to_wire(struct drbd_connection *connection,
+			     struct bio *bio)
 {
 	if (connection->agreed_pro_version >= 95)
-		return  (bi_rw & REQ_SYNC ? DP_RW_SYNC : 0) |
-			(bi_rw & REQ_FUA ? DP_FUA : 0) |
-			(bi_rw & REQ_FLUSH ? DP_FLUSH : 0) |
-			(bi_rw & REQ_DISCARD ? DP_DISCARD : 0);
+		return  (bio->bi_rw & REQ_SYNC ? DP_RW_SYNC : 0) |
+			(bio->bi_rw & REQ_FUA ? DP_FUA : 0) |
+			(bio->bi_rw & REQ_PREFLUSH ? DP_FLUSH : 0) |
+			(bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) |
+			(bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0);
 	else
-		return bi_rw & REQ_SYNC ? DP_RW_SYNC : 0;
+		return bio->bi_rw & REQ_SYNC ? DP_RW_SYNC : 0;
 }
 
 /* Used to send write or TRIM aka REQ_DISCARD requests
@@ -1622,6 +1680,8 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 	struct drbd_device *device = peer_device->device;
 	struct drbd_socket *sock;
 	struct p_data *p;
+	struct p_wsame *wsame = NULL;
+	void *digest_out;
 	unsigned int dp_flags = 0;
 	int digest_size;
 	int err;
@@ -1636,7 +1696,7 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 	p->sector = cpu_to_be64(req->i.sector);
 	p->block_id = (unsigned long)req;
 	p->seq_num = cpu_to_be32(atomic_inc_return(&device->packet_seq));
-	dp_flags = bio_flags_to_wire(peer_device->connection, req->master_bio->bi_rw);
+	dp_flags = bio_flags_to_wire(peer_device->connection, req->master_bio);
 	if (device->state.conn >= C_SYNC_SOURCE &&
 	    device->state.conn <= C_PAUSED_SYNC_T)
 		dp_flags |= DP_MAY_SET_IN_SYNC;
@@ -1657,12 +1717,29 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 		err = __send_command(peer_device->connection, device->vnr, sock, P_TRIM, sizeof(*t), NULL, 0);
 		goto out;
 	}
+	if (dp_flags & DP_WSAME) {
+		/* this will only work if DRBD_FF_WSAME is set AND the
+		 * handshake agreed that all nodes and backend devices are
+		 * WRITE_SAME capable and agree on logical_block_size */
+		wsame = (struct p_wsame*)p;
+		digest_out = wsame + 1;
+		wsame->size = cpu_to_be32(req->i.size);
+	} else
+		digest_out = p + 1;
 
 	/* our digest is still only over the payload.
 	 * TRIM does not carry any payload. */
 	if (digest_size)
-		drbd_csum_bio(peer_device->connection->integrity_tfm, req->master_bio, p + 1);
-	err = __send_command(peer_device->connection, device->vnr, sock, P_DATA, sizeof(*p) + digest_size, NULL, req->i.size);
+		drbd_csum_bio(peer_device->connection->integrity_tfm, req->master_bio, digest_out);
+	if (wsame) {
+		err =
+		    __send_command(peer_device->connection, device->vnr, sock, P_WSAME,
+				   sizeof(*wsame) + digest_size, NULL,
+				   bio_iovec(req->master_bio).bv_len);
+	} else
+		err =
+		    __send_command(peer_device->connection, device->vnr, sock, P_DATA,
+				   sizeof(*p) + digest_size, NULL, req->i.size);
 	if (!err) {
 		/* For protocol A, we have to memcpy the payload into
 		 * socket buffers, as we may complete right away
@@ -3061,7 +3138,7 @@ void drbd_md_write(struct drbd_device *device, void *b)
 	D_ASSERT(device, drbd_md_ss(device->ldev) == device->ldev->md.md_offset);
 	sector = device->ldev->md.md_offset;
 
-	if (drbd_md_sync_page_io(device, device->ldev, sector, WRITE)) {
+	if (drbd_md_sync_page_io(device, device->ldev, sector, REQ_OP_WRITE)) {
 		/* this was a try anyways ... */
 		drbd_err(device, "meta data update failed!\n");
 		drbd_chk_io_error(device, 1, DRBD_META_IO_ERROR);
@@ -3263,7 +3340,8 @@ int drbd_md_read(struct drbd_device *device, struct drbd_backing_dev *bdev)
 	 * Affects the paranoia out-of-range access check in drbd_md_sync_page_io(). */
 	bdev->md.md_size_sect = 8;
 
-	if (drbd_md_sync_page_io(device, bdev, bdev->md.md_offset, READ)) {
+	if (drbd_md_sync_page_io(device, bdev, bdev->md.md_offset,
+				 REQ_OP_READ)) {
 		/* NOTE: can't do normal error processing here as this is
 		   called BEFORE disk is attached */
 		drbd_err(device, "Error while reading metadata.\n");
@@ -3505,7 +3583,12 @@ static int w_bitmap_io(struct drbd_work *w, int unused)
 	struct bm_io_work *work = &device->bm_io_work;
 	int rv = -EIO;
 
-	D_ASSERT(device, atomic_read(&device->ap_bio_cnt) == 0);
+	if (work->flags != BM_LOCKED_CHANGE_ALLOWED) {
+		int cnt = atomic_read(&device->ap_bio_cnt);
+		if (cnt)
+			drbd_err(device, "FIXME: ap_bio_cnt %d, expected 0; queued for '%s'\n",
+					cnt, work->why);
+	}
 
 	if (get_ldev(device)) {
 		drbd_bm_lock(device, work->why, work->flags);
@@ -3585,18 +3668,20 @@ void drbd_queue_bitmap_io(struct drbd_device *device,
 int drbd_bitmap_io(struct drbd_device *device, int (*io_fn)(struct drbd_device *),
 		char *why, enum bm_flag flags)
 {
+	/* Only suspend io, if some operation is supposed to be locked out */
+	const bool do_suspend_io = flags & (BM_DONT_CLEAR|BM_DONT_SET|BM_DONT_TEST);
 	int rv;
 
 	D_ASSERT(device, current != first_peer_device(device)->connection->worker.task);
 
-	if ((flags & BM_LOCKED_SET_ALLOWED) == 0)
+	if (do_suspend_io)
 		drbd_suspend_io(device);
 
 	drbd_bm_lock(device, why, flags);
 	rv = io_fn(device);
 	drbd_bm_unlock(device);
 
-	if ((flags & BM_LOCKED_SET_ALLOWED) == 0)
+	if (do_suspend_io)
 		drbd_resume_io(device);
 
 	return rv;
@@ -3635,6 +3720,8 @@ const char *cmdname(enum drbd_packet cmd)
 	 * one PRO_VERSION */
 	static const char *cmdnames[] = {
 		[P_DATA]	        = "Data",
+		[P_WSAME]	        = "WriteSame",
+		[P_TRIM]	        = "Trim",
 		[P_DATA_REPLY]	        = "DataReply",
 		[P_RS_DATA_REPLY]	= "RSDataReply",
 		[P_BARRIER]	        = "Barrier",
@@ -3679,6 +3766,8 @@ const char *cmdname(enum drbd_packet cmd)
 		[P_CONN_ST_CHG_REPLY]	= "conn_st_chg_reply",
 		[P_RETRY_WRITE]		= "retry_write",
 		[P_PROTOCOL_UPDATE]	= "protocol_update",
+		[P_RS_THIN_REQ]         = "rs_thin_req",
+		[P_RS_DEALLOCATED]      = "rs_deallocated",
 
 		/* enum drbd_packet, but not commands - obsoleted flags:
 		 *	P_MAY_IGNORE
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 0bac9c8246bc..f35db29cac76 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -343,7 +343,7 @@ int drbd_khelper(struct drbd_device *device, char *cmd)
 			 (char[20]) { }, /* address family */
 			 (char[60]) { }, /* address */
 			NULL };
-	char mb[12];
+	char mb[14];
 	char *argv[] = {usermode_helper, cmd, mb, NULL };
 	struct drbd_connection *connection = first_peer_device(device)->connection;
 	struct sib_info sib;
@@ -352,7 +352,7 @@ int drbd_khelper(struct drbd_device *device, char *cmd)
 	if (current == connection->worker.task)
 		set_bit(CALLBACK_PENDING, &connection->flags);
 
-	snprintf(mb, 12, "minor-%d", device_to_minor(device));
+	snprintf(mb, 14, "minor-%d", device_to_minor(device));
 	setup_khelper_env(connection, envp);
 
 	/* The helper may take some time.
@@ -387,7 +387,7 @@ int drbd_khelper(struct drbd_device *device, char *cmd)
 	return ret;
 }
 
-static int conn_khelper(struct drbd_connection *connection, char *cmd)
+enum drbd_peer_state conn_khelper(struct drbd_connection *connection, char *cmd)
 {
 	char *envp[] = { "HOME=/",
 			"TERM=linux",
@@ -442,19 +442,17 @@ static enum drbd_fencing_p highest_fencing_policy(struct drbd_connection *connec
 	}
 	rcu_read_unlock();
 
-	if (fp == FP_NOT_AVAIL) {
-		/* IO Suspending works on the whole resource.
-		   Do it only for one device. */
-		vnr = 0;
-		peer_device = idr_get_next(&connection->peer_devices, &vnr);
-		drbd_change_state(peer_device->device, CS_VERBOSE | CS_HARD, NS(susp_fen, 0));
-	}
-
 	return fp;
 }
 
+static bool resource_is_supended(struct drbd_resource *resource)
+{
+	return resource->susp || resource->susp_fen || resource->susp_nod;
+}
+
 bool conn_try_outdate_peer(struct drbd_connection *connection)
 {
+	struct drbd_resource * const resource = connection->resource;
 	unsigned int connect_cnt;
 	union drbd_state mask = { };
 	union drbd_state val = { };
@@ -462,21 +460,41 @@ bool conn_try_outdate_peer(struct drbd_connection *connection)
 	char *ex_to_string;
 	int r;
 
-	spin_lock_irq(&connection->resource->req_lock);
+	spin_lock_irq(&resource->req_lock);
 	if (connection->cstate >= C_WF_REPORT_PARAMS) {
 		drbd_err(connection, "Expected cstate < C_WF_REPORT_PARAMS\n");
-		spin_unlock_irq(&connection->resource->req_lock);
+		spin_unlock_irq(&resource->req_lock);
 		return false;
 	}
 
 	connect_cnt = connection->connect_cnt;
-	spin_unlock_irq(&connection->resource->req_lock);
+	spin_unlock_irq(&resource->req_lock);
 
 	fp = highest_fencing_policy(connection);
 	switch (fp) {
 	case FP_NOT_AVAIL:
 		drbd_warn(connection, "Not fencing peer, I'm not even Consistent myself.\n");
-		goto out;
+		spin_lock_irq(&resource->req_lock);
+		if (connection->cstate < C_WF_REPORT_PARAMS) {
+			_conn_request_state(connection,
+					    (union drbd_state) { { .susp_fen = 1 } },
+					    (union drbd_state) { { .susp_fen = 0 } },
+					    CS_VERBOSE | CS_HARD | CS_DC_SUSP);
+			/* We are no longer suspended due to the fencing policy.
+			 * We may still be suspended due to the on-no-data-accessible policy.
+			 * If that was OND_IO_ERROR, fail pending requests. */
+			if (!resource_is_supended(resource))
+				_tl_restart(connection, CONNECTION_LOST_WHILE_PENDING);
+		}
+		/* Else: in case we raced with a connection handshake,
+		 * let the handshake figure out if we maybe can RESEND,
+		 * and do not resume/fail pending requests here.
+		 * Worst case is we stay suspended for now, which may be
+		 * resolved by either re-establishing the replication link, or
+		 * the next link failure, or eventually the administrator.  */
+		spin_unlock_irq(&resource->req_lock);
+		return false;
+
 	case FP_DONT_CARE:
 		return true;
 	default: ;
@@ -485,17 +503,17 @@ bool conn_try_outdate_peer(struct drbd_connection *connection)
 	r = conn_khelper(connection, "fence-peer");
 
 	switch ((r>>8) & 0xff) {
-	case 3: /* peer is inconsistent */
+	case P_INCONSISTENT: /* peer is inconsistent */
 		ex_to_string = "peer is inconsistent or worse";
 		mask.pdsk = D_MASK;
 		val.pdsk = D_INCONSISTENT;
 		break;
-	case 4: /* peer got outdated, or was already outdated */
+	case P_OUTDATED: /* peer got outdated, or was already outdated */
 		ex_to_string = "peer was fenced";
 		mask.pdsk = D_MASK;
 		val.pdsk = D_OUTDATED;
 		break;
-	case 5: /* peer was down */
+	case P_DOWN: /* peer was down */
 		if (conn_highest_disk(connection) == D_UP_TO_DATE) {
 			/* we will(have) create(d) a new UUID anyways... */
 			ex_to_string = "peer is unreachable, assumed to be dead";
@@ -505,7 +523,7 @@ bool conn_try_outdate_peer(struct drbd_connection *connection)
 			ex_to_string = "peer unreachable, doing nothing since disk != UpToDate";
 		}
 		break;
-	case 6: /* Peer is primary, voluntarily outdate myself.
+	case P_PRIMARY: /* Peer is primary, voluntarily outdate myself.
 		 * This is useful when an unconnected R_SECONDARY is asked to
 		 * become R_PRIMARY, but finds the other peer being active. */
 		ex_to_string = "peer is active";
@@ -513,7 +531,9 @@ bool conn_try_outdate_peer(struct drbd_connection *connection)
 		mask.disk = D_MASK;
 		val.disk = D_OUTDATED;
 		break;
-	case 7:
+	case P_FENCING:
+		/* THINK: do we need to handle this
+		 * like case 4, or more like case 5? */
 		if (fp != FP_STONITH)
 			drbd_err(connection, "fence-peer() = 7 && fencing != Stonith !!!\n");
 		ex_to_string = "peer was stonithed";
@@ -529,13 +549,11 @@ bool conn_try_outdate_peer(struct drbd_connection *connection)
 	drbd_info(connection, "fence-peer helper returned %d (%s)\n",
 		  (r>>8) & 0xff, ex_to_string);
 
- out:
-
 	/* Not using
 	   conn_request_state(connection, mask, val, CS_VERBOSE);
 	   here, because we might were able to re-establish the connection in the
 	   meantime. */
-	spin_lock_irq(&connection->resource->req_lock);
+	spin_lock_irq(&resource->req_lock);
 	if (connection->cstate < C_WF_REPORT_PARAMS && !test_bit(STATE_SENT, &connection->flags)) {
 		if (connection->connect_cnt != connect_cnt)
 			/* In case the connection was established and droped
@@ -544,7 +562,7 @@ bool conn_try_outdate_peer(struct drbd_connection *connection)
 		else
 			_conn_request_state(connection, mask, val, CS_VERBOSE);
 	}
-	spin_unlock_irq(&connection->resource->req_lock);
+	spin_unlock_irq(&resource->req_lock);
 
 	return conn_highest_pdsk(connection) <= D_OUTDATED;
 }
@@ -1154,51 +1172,160 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc)
 	return 0;
 }
 
+static void blk_queue_discard_granularity(struct request_queue *q, unsigned int granularity)
+{
+	q->limits.discard_granularity = granularity;
+}
+
+static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
+{
+	/* when we introduced REQ_WRITE_SAME support, we also bumped
+	 * our maximum supported batch bio size used for discards. */
+	if (connection->agreed_features & DRBD_FF_WSAME)
+		return DRBD_MAX_BBIO_SECTORS;
+	/* before, with DRBD <= 8.4.6, we only allowed up to one AL_EXTENT_SIZE. */
+	return AL_EXTENT_SIZE >> 9;
+}
+
+static void decide_on_discard_support(struct drbd_device *device,
+			struct request_queue *q,
+			struct request_queue *b,
+			bool discard_zeroes_if_aligned)
+{
+	/* q = drbd device queue (device->rq_queue)
+	 * b = backing device queue (device->ldev->backing_bdev->bd_disk->queue),
+	 *     or NULL if diskless
+	 */
+	struct drbd_connection *connection = first_peer_device(device)->connection;
+	bool can_do = b ? blk_queue_discard(b) : true;
+
+	if (can_do && b && !b->limits.discard_zeroes_data && !discard_zeroes_if_aligned) {
+		can_do = false;
+		drbd_info(device, "discard_zeroes_data=0 and discard_zeroes_if_aligned=no: disabling discards\n");
+	}
+	if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) {
+		can_do = false;
+		drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n");
+	}
+	if (can_do) {
+		/* We don't care for the granularity, really.
+		 * Stacking limits below should fix it for the local
+		 * device.  Whether or not it is a suitable granularity
+		 * on the remote device is not our problem, really. If
+		 * you care, you need to use devices with similar
+		 * topology on all peers. */
+		blk_queue_discard_granularity(q, 512);
+		q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+	} else {
+		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
+		blk_queue_discard_granularity(q, 0);
+		q->limits.max_discard_sectors = 0;
+	}
+}
+
+static void fixup_discard_if_not_supported(struct request_queue *q)
+{
+	/* To avoid confusion, if this queue does not support discard, clear
+	 * max_discard_sectors, which is what lsblk -D reports to the user.
+	 * Older kernels got this wrong in "stack limits".
+	 * */
+	if (!blk_queue_discard(q)) {
+		blk_queue_max_discard_sectors(q, 0);
+		blk_queue_discard_granularity(q, 0);
+	}
+}
+
+static void decide_on_write_same_support(struct drbd_device *device,
+			struct request_queue *q,
+			struct request_queue *b, struct o_qlim *o)
+{
+	struct drbd_peer_device *peer_device = first_peer_device(device);
+	struct drbd_connection *connection = peer_device->connection;
+	bool can_do = b ? b->limits.max_write_same_sectors : true;
+
+	if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_WSAME)) {
+		can_do = false;
+		drbd_info(peer_device, "peer does not support WRITE_SAME\n");
+	}
+
+	if (o) {
+		/* logical block size; queue_logical_block_size(NULL) is 512 */
+		unsigned int peer_lbs = be32_to_cpu(o->logical_block_size);
+		unsigned int me_lbs_b = queue_logical_block_size(b);
+		unsigned int me_lbs = queue_logical_block_size(q);
+
+		if (me_lbs_b != me_lbs) {
+			drbd_warn(device,
+				"logical block size of local backend does not match (drbd:%u, backend:%u); was this a late attach?\n",
+				me_lbs, me_lbs_b);
+			/* rather disable write same than trigger some BUG_ON later in the scsi layer. */
+			can_do = false;
+		}
+		if (me_lbs_b != peer_lbs) {
+			drbd_warn(peer_device, "logical block sizes do not match (me:%u, peer:%u); this may cause problems.\n",
+				me_lbs, peer_lbs);
+			if (can_do) {
+				drbd_dbg(peer_device, "logical block size mismatch: WRITE_SAME disabled.\n");
+				can_do = false;
+			}
+			me_lbs = max(me_lbs, me_lbs_b);
+			/* We cannot change the logical block size of an in-use queue.
+			 * We can only hope that access happens to be properly aligned.
+			 * If not, the peer will likely produce an IO error, and detach. */
+			if (peer_lbs > me_lbs) {
+				if (device->state.role != R_PRIMARY) {
+					blk_queue_logical_block_size(q, peer_lbs);
+					drbd_warn(peer_device, "logical block size set to %u\n", peer_lbs);
+				} else {
+					drbd_warn(peer_device,
+						"current Primary must NOT adjust logical block size (%u -> %u); hope for the best.\n",
+						me_lbs, peer_lbs);
+				}
+			}
+		}
+		if (can_do && !o->write_same_capable) {
+			/* If we introduce an open-coded write-same loop on the receiving side,
+			 * the peer would present itself as "capable". */
+			drbd_dbg(peer_device, "WRITE_SAME disabled (peer device not capable)\n");
+			can_do = false;
+		}
+	}
+
+	blk_queue_max_write_same_sectors(q, can_do ? DRBD_MAX_BBIO_SECTORS : 0);
+}
+
 static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev,
-				   unsigned int max_bio_size)
+				   unsigned int max_bio_size, struct o_qlim *o)
 {
 	struct request_queue * const q = device->rq_queue;
 	unsigned int max_hw_sectors = max_bio_size >> 9;
 	unsigned int max_segments = 0;
 	struct request_queue *b = NULL;
+	struct disk_conf *dc;
+	bool discard_zeroes_if_aligned = true;
 
 	if (bdev) {
 		b = bdev->backing_bdev->bd_disk->queue;
 
 		max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
 		rcu_read_lock();
-		max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs;
+		dc = rcu_dereference(device->ldev->disk_conf);
+		max_segments = dc->max_bio_bvecs;
+		discard_zeroes_if_aligned = dc->discard_zeroes_if_aligned;
 		rcu_read_unlock();
 
 		blk_set_stacking_limits(&q->limits);
-		blk_queue_max_write_same_sectors(q, 0);
 	}
 
-	blk_queue_logical_block_size(q, 512);
 	blk_queue_max_hw_sectors(q, max_hw_sectors);
 	/* This is the workaround for "bio would need to, but cannot, be split" */
 	blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
 	blk_queue_segment_boundary(q, PAGE_SIZE-1);
+	decide_on_discard_support(device, q, b, discard_zeroes_if_aligned);
+	decide_on_write_same_support(device, q, b, o);
 
 	if (b) {
-		struct drbd_connection *connection = first_peer_device(device)->connection;
-
-		blk_queue_max_discard_sectors(q, DRBD_MAX_DISCARD_SECTORS);
-
-		if (blk_queue_discard(b) &&
-		    (connection->cstate < C_CONNECTED || connection->agreed_features & FF_TRIM)) {
-			/* We don't care, stacking below should fix it for the local device.
-			 * Whether or not it is a suitable granularity on the remote device
-			 * is not our problem, really. If you care, you need to
-			 * use devices with similar topology on all peers. */
-			q->limits.discard_granularity = 512;
-			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
-		} else {
-			blk_queue_max_discard_sectors(q, 0);
-			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
-			q->limits.discard_granularity = 0;
-		}
-
 		blk_queue_stack_limits(q, b);
 
 		if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
@@ -1208,15 +1335,10 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 			q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages;
 		}
 	}
-	/* To avoid confusion, if this queue does not support discard, clear
-	 * max_discard_sectors, which is what lsblk -D reports to the user.  */
-	if (!blk_queue_discard(q)) {
-		blk_queue_max_discard_sectors(q, 0);
-		q->limits.discard_granularity = 0;
-	}
+	fixup_discard_if_not_supported(q);
 }
 
-void drbd_reconsider_max_bio_size(struct drbd_device *device, struct drbd_backing_dev *bdev)
+void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o)
 {
 	unsigned int now, new, local, peer;
 
@@ -1259,7 +1381,7 @@ void drbd_reconsider_max_bio_size(struct drbd_device *device, struct drbd_backin
 	if (new != now)
 		drbd_info(device, "max BIO size = %u\n", new);
 
-	drbd_setup_queue_param(device, bdev, new);
+	drbd_setup_queue_param(device, bdev, new, o);
 }
 
 /* Starts the worker thread */
@@ -1348,6 +1470,43 @@ static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b)
 		a->disk_drain != b->disk_drain;
 }
 
+static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *disk_conf,
+			       struct drbd_backing_dev *nbc)
+{
+	struct request_queue * const q = nbc->backing_bdev->bd_disk->queue;
+
+	if (disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
+		disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
+	if (disk_conf->al_extents > drbd_al_extents_max(nbc))
+		disk_conf->al_extents = drbd_al_extents_max(nbc);
+
+	if (!blk_queue_discard(q)
+	    || (!q->limits.discard_zeroes_data && !disk_conf->discard_zeroes_if_aligned)) {
+		if (disk_conf->rs_discard_granularity) {
+			disk_conf->rs_discard_granularity = 0; /* disable feature */
+			drbd_info(device, "rs_discard_granularity feature disabled\n");
+		}
+	}
+
+	if (disk_conf->rs_discard_granularity) {
+		int orig_value = disk_conf->rs_discard_granularity;
+		int remainder;
+
+		if (q->limits.discard_granularity > disk_conf->rs_discard_granularity)
+			disk_conf->rs_discard_granularity = q->limits.discard_granularity;
+
+		remainder = disk_conf->rs_discard_granularity % q->limits.discard_granularity;
+		disk_conf->rs_discard_granularity += remainder;
+
+		if (disk_conf->rs_discard_granularity > q->limits.max_discard_sectors << 9)
+			disk_conf->rs_discard_granularity = q->limits.max_discard_sectors << 9;
+
+		if (disk_conf->rs_discard_granularity != orig_value)
+			drbd_info(device, "rs_discard_granularity changed to %d\n",
+				  disk_conf->rs_discard_granularity);
+	}
+}
+
 int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
@@ -1395,10 +1554,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	if (!expect(new_disk_conf->resync_rate >= 1))
 		new_disk_conf->resync_rate = 1;
 
-	if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
-		new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
-	if (new_disk_conf->al_extents > drbd_al_extents_max(device->ldev))
-		new_disk_conf->al_extents = drbd_al_extents_max(device->ldev);
+	sanitize_disk_conf(device, new_disk_conf, device->ldev);
 
 	if (new_disk_conf->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX)
 		new_disk_conf->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX;
@@ -1457,6 +1613,9 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	if (write_ordering_changed(old_disk_conf, new_disk_conf))
 		drbd_bump_write_ordering(device->resource, NULL, WO_BDEV_FLUSH);
 
+	if (old_disk_conf->discard_zeroes_if_aligned != new_disk_conf->discard_zeroes_if_aligned)
+		drbd_reconsider_queue_parameters(device, device->ldev, NULL);
+
 	drbd_md_sync(device);
 
 	if (device->state.conn >= C_CONNECTED) {
@@ -1693,10 +1852,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto fail;
 
-	if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
-		new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
-	if (new_disk_conf->al_extents > drbd_al_extents_max(nbc))
-		new_disk_conf->al_extents = drbd_al_extents_max(nbc);
+	sanitize_disk_conf(device, new_disk_conf, nbc);
 
 	if (drbd_get_max_capacity(nbc) < new_disk_conf->disk_size) {
 		drbd_err(device, "max capacity %llu smaller than disk size %llu\n",
@@ -1838,7 +1994,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	device->read_cnt = 0;
 	device->writ_cnt = 0;
 
-	drbd_reconsider_max_bio_size(device, device->ldev);
+	drbd_reconsider_queue_parameters(device, device->ldev, NULL);
 
 	/* If I am currently not R_PRIMARY,
 	 * but meta data primary indicator is set,
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index 6537b25db9c1..be2b93fd2c11 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -25,7 +25,7 @@
 
 #include <linux/module.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/proc_fs.h>
@@ -122,18 +122,18 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 
 	x = res/50;
 	y = 20-x;
-	seq_printf(seq, "\t[");
+	seq_puts(seq, "\t[");
 	for (i = 1; i < x; i++)
-		seq_printf(seq, "=");
-	seq_printf(seq, ">");
+		seq_putc(seq, '=');
+	seq_putc(seq, '>');
 	for (i = 0; i < y; i++)
 		seq_printf(seq, ".");
-	seq_printf(seq, "] ");
+	seq_puts(seq, "] ");
 
 	if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T)
-		seq_printf(seq, "verified:");
+		seq_puts(seq, "verified:");
 	else
-		seq_printf(seq, "sync'ed:");
+		seq_puts(seq, "sync'ed:");
 	seq_printf(seq, "%3u.%u%% ", res / 10, res % 10);
 
 	/* if more than a few GB, display in MB */
@@ -146,7 +146,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 			    (unsigned long) Bit2KB(rs_left),
 			    (unsigned long) Bit2KB(rs_total));
 
-	seq_printf(seq, "\n\t");
+	seq_puts(seq, "\n\t");
 
 	/* see drivers/md/md.c
 	 * We do not want to overflow, so the order of operands and
@@ -175,9 +175,9 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 		rt / 3600, (rt % 3600) / 60, rt % 60);
 
 	dbdt = Bit2KB(db/dt);
-	seq_printf(seq, " speed: ");
+	seq_puts(seq, " speed: ");
 	seq_printf_with_thousands_grouping(seq, dbdt);
-	seq_printf(seq, " (");
+	seq_puts(seq, " (");
 	/* ------------------------- ~3s average ------------------------ */
 	if (proc_details >= 1) {
 		/* this is what drbd_rs_should_slow_down() uses */
@@ -188,7 +188,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 		db = device->rs_mark_left[i] - rs_left;
 		dbdt = Bit2KB(db/dt);
 		seq_printf_with_thousands_grouping(seq, dbdt);
-		seq_printf(seq, " -- ");
+		seq_puts(seq, " -- ");
 	}
 
 	/* --------------------- long term average ---------------------- */
@@ -200,11 +200,11 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 	db = rs_total - rs_left;
 	dbdt = Bit2KB(db/dt);
 	seq_printf_with_thousands_grouping(seq, dbdt);
-	seq_printf(seq, ")");
+	seq_putc(seq, ')');
 
 	if (state.conn == C_SYNC_TARGET ||
 	    state.conn == C_VERIFY_S) {
-		seq_printf(seq, " want: ");
+		seq_puts(seq, " want: ");
 		seq_printf_with_thousands_grouping(seq, device->c_sync_rate);
 	}
 	seq_printf(seq, " K/sec%s\n", stalled ? " (stalled)" : "");
@@ -231,7 +231,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 			(unsigned long long)bm_bits * BM_SECT_PER_BIT);
 		if (stop_sector != 0 && stop_sector != ULLONG_MAX)
 			seq_printf(seq, " stop sector: %llu", stop_sector);
-		seq_printf(seq, "\n");
+		seq_putc(seq, '\n');
 	}
 }
 
@@ -276,7 +276,7 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 	rcu_read_lock();
 	idr_for_each_entry(&drbd_devices, device, i) {
 		if (prev_i != i - 1)
-			seq_printf(seq, "\n");
+			seq_putc(seq, '\n');
 		prev_i = i;
 
 		state = device->state;
diff --git a/drivers/block/drbd/drbd_protocol.h b/drivers/block/drbd/drbd_protocol.h
index ef9245363dcc..4d296800f706 100644
--- a/drivers/block/drbd/drbd_protocol.h
+++ b/drivers/block/drbd/drbd_protocol.h
@@ -60,6 +60,15 @@ enum drbd_packet {
 	 * which is why I chose TRIM here, to disambiguate. */
 	P_TRIM                = 0x31,
 
+	/* Only use these two if both support FF_THIN_RESYNC */
+	P_RS_THIN_REQ         = 0x32, /* Request a block for resync or reply P_RS_DEALLOCATED */
+	P_RS_DEALLOCATED      = 0x33, /* Contains only zeros on sync source node */
+
+	/* REQ_WRITE_SAME.
+	 * On a receiving side without REQ_WRITE_SAME,
+	 * we may fall back to an opencoded loop instead. */
+	P_WSAME               = 0x34,
+
 	P_MAY_IGNORE	      = 0x100, /* Flag to test if (cmd > P_MAY_IGNORE) ... */
 	P_MAX_OPT_CMD	      = 0x101,
 
@@ -106,16 +115,20 @@ struct p_header100 {
 	u32	  pad;
 } __packed;
 
-/* these defines must not be changed without changing the protocol version */
-#define DP_HARDBARRIER	      1 /* depricated */
+/* These defines must not be changed without changing the protocol version.
+ * New defines may only be introduced together with protocol version bump or
+ * new protocol feature flags.
+ */
+#define DP_HARDBARRIER	      1 /* no longer used */
 #define DP_RW_SYNC	      2 /* equals REQ_SYNC    */
 #define DP_MAY_SET_IN_SYNC    4
 #define DP_UNPLUG             8 /* not used anymore   */
 #define DP_FUA               16 /* equals REQ_FUA     */
-#define DP_FLUSH             32 /* equals REQ_FLUSH   */
+#define DP_FLUSH             32 /* equals REQ_PREFLUSH   */
 #define DP_DISCARD           64 /* equals REQ_DISCARD */
 #define DP_SEND_RECEIVE_ACK 128 /* This is a proto B write request */
 #define DP_SEND_WRITE_ACK   256 /* This is a proto C write request */
+#define DP_WSAME            512 /* equiv. REQ_WRITE_SAME */
 
 struct p_data {
 	u64	    sector;    /* 64 bits sector number */
@@ -129,6 +142,11 @@ struct p_trim {
 	u32	    size;	/* == bio->bi_size */
 } __packed;
 
+struct p_wsame {
+	struct p_data p_data;
+	u32           size;     /* == bio->bi_size */
+} __packed;
+
 /*
  * commands which share a struct:
  *  p_block_ack:
@@ -160,7 +178,23 @@ struct p_block_req {
  *   ReportParams
  */
 
-#define FF_TRIM      1
+/* supports TRIM/DISCARD on the "wire" protocol */
+#define DRBD_FF_TRIM 1
+
+/* Detect all-zeros during resync, and rather TRIM/UNMAP/DISCARD those blocks
+ * instead of fully allocate a supposedly thin volume on initial resync */
+#define DRBD_FF_THIN_RESYNC 2
+
+/* supports REQ_WRITE_SAME on the "wire" protocol.
+ * Note: this flag is overloaded,
+ * its presence also
+ *   - indicates support for 128 MiB "batch bios",
+ *     max discard size of 128 MiB
+ *     instead of 4M before that.
+ *   - indicates that we exchange additional settings in p_sizes
+ *     drbd_send_sizes()/receive_sizes()
+ */
+#define DRBD_FF_WSAME 4
 
 struct p_connection_features {
 	u32 protocol_min;
@@ -235,6 +269,40 @@ struct p_rs_uuid {
 	u64	    uuid;
 } __packed;
 
+/* optional queue_limits if (agreed_features & DRBD_FF_WSAME)
+ * see also struct queue_limits, as of late 2015 */
+struct o_qlim {
+	/* we don't need it yet, but we may as well communicate it now */
+	u32 physical_block_size;
+
+	/* so the original in struct queue_limits is unsigned short,
+	 * but I'd have to put in padding anyways. */
+	u32 logical_block_size;
+
+	/* One incoming bio becomes one DRBD request,
+	 * which may be translated to several bio on the receiving side.
+	 * We don't need to communicate chunk/boundary/segment ... limits.
+	 */
+
+	/* various IO hints may be useful with "diskless client" setups */
+	u32 alignment_offset;
+	u32 io_min;
+	u32 io_opt;
+
+	/* We may need to communicate integrity stuff at some point,
+	 * but let's not get ahead of ourselves. */
+
+	/* Backend discard capabilities.
+	 * Receiving side uses "blkdev_issue_discard()", no need to communicate
+	 * more specifics.  If the backend cannot do discards, the DRBD peer
+	 * may fall back to blkdev_issue_zeroout().
+	 */
+	u8 discard_enabled;
+	u8 discard_zeroes_data;
+	u8 write_same_capable;
+	u8 _pad;
+} __packed;
+
 struct p_sizes {
 	u64	    d_size;  /* size of disk */
 	u64	    u_size;  /* user requested size */
@@ -242,6 +310,9 @@ struct p_sizes {
 	u32	    max_bio_size;  /* Maximal size of a BIO */
 	u16	    queue_order_type;  /* not yet implemented in DRBD*/
 	u16	    dds_flags; /* use enum dds_flags here. */
+
+	/* optional queue_limits if (agreed_features & DRBD_FF_WSAME) */
+	struct o_qlim qlim[0];
 } __packed;
 
 struct p_state {
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 050aaa1c0350..df45713dfbe8 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -25,7 +25,7 @@
 
 #include <linux/module.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/sock.h>
 
 #include <linux/drbd.h>
@@ -48,7 +48,7 @@
 #include "drbd_req.h"
 #include "drbd_vli.h"
 
-#define PRO_FEATURES (FF_TRIM)
+#define PRO_FEATURES (DRBD_FF_TRIM|DRBD_FF_THIN_RESYNC|DRBD_FF_WSAME)
 
 struct packet_info {
 	enum drbd_packet cmd;
@@ -361,14 +361,17 @@ You must not have the req_lock:
  drbd_wait_ee_list_empty()
 */
 
+/* normal: payload_size == request size (bi_size)
+ * w_same: payload_size == logical_block_size
+ * trim: payload_size == 0 */
 struct drbd_peer_request *
 drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
-		    unsigned int data_size, bool has_payload, gfp_t gfp_mask) __must_hold(local)
+		    unsigned int request_size, unsigned int payload_size, gfp_t gfp_mask) __must_hold(local)
 {
 	struct drbd_device *device = peer_device->device;
 	struct drbd_peer_request *peer_req;
 	struct page *page = NULL;
-	unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT;
+	unsigned nr_pages = (payload_size + PAGE_SIZE -1) >> PAGE_SHIFT;
 
 	if (drbd_insert_fault(device, DRBD_FAULT_AL_EE))
 		return NULL;
@@ -380,7 +383,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
 		return NULL;
 	}
 
-	if (has_payload && data_size) {
+	if (nr_pages) {
 		page = drbd_alloc_pages(peer_device, nr_pages,
 					gfpflags_allow_blocking(gfp_mask));
 		if (!page)
@@ -390,7 +393,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
 	memset(peer_req, 0, sizeof(*peer_req));
 	INIT_LIST_HEAD(&peer_req->w.list);
 	drbd_clear_interval(&peer_req->i);
-	peer_req->i.size = data_size;
+	peer_req->i.size = request_size;
 	peer_req->i.sector = sector;
 	peer_req->submit_jif = jiffies;
 	peer_req->peer_device = peer_device;
@@ -1204,13 +1207,84 @@ static int drbd_recv_header(struct drbd_connection *connection, struct packet_in
 	return err;
 }
 
-static void drbd_flush(struct drbd_connection *connection)
+/* This is blkdev_issue_flush, but asynchronous.
+ * We want to submit to all component volumes in parallel,
+ * then wait for all completions.
+ */
+struct issue_flush_context {
+	atomic_t pending;
+	int error;
+	struct completion done;
+};
+struct one_flush_context {
+	struct drbd_device *device;
+	struct issue_flush_context *ctx;
+};
+
+void one_flush_endio(struct bio *bio)
 {
-	int rv;
-	struct drbd_peer_device *peer_device;
-	int vnr;
+	struct one_flush_context *octx = bio->bi_private;
+	struct drbd_device *device = octx->device;
+	struct issue_flush_context *ctx = octx->ctx;
+
+	if (bio->bi_error) {
+		ctx->error = bio->bi_error;
+		drbd_info(device, "local disk FLUSH FAILED with status %d\n", bio->bi_error);
+	}
+	kfree(octx);
+	bio_put(bio);
+
+	clear_bit(FLUSH_PENDING, &device->flags);
+	put_ldev(device);
+	kref_put(&device->kref, drbd_destroy_device);
+
+	if (atomic_dec_and_test(&ctx->pending))
+		complete(&ctx->done);
+}
+
+static void submit_one_flush(struct drbd_device *device, struct issue_flush_context *ctx)
+{
+	struct bio *bio = bio_alloc(GFP_NOIO, 0);
+	struct one_flush_context *octx = kmalloc(sizeof(*octx), GFP_NOIO);
+	if (!bio || !octx) {
+		drbd_warn(device, "Could not allocate a bio, CANNOT ISSUE FLUSH\n");
+		/* FIXME: what else can I do now?  disconnecting or detaching
+		 * really does not help to improve the state of the world, either.
+		 */
+		kfree(octx);
+		if (bio)
+			bio_put(bio);
+
+		ctx->error = -ENOMEM;
+		put_ldev(device);
+		kref_put(&device->kref, drbd_destroy_device);
+		return;
+	}
 
+	octx->device = device;
+	octx->ctx = ctx;
+	bio->bi_bdev = device->ldev->backing_bdev;
+	bio->bi_private = octx;
+	bio->bi_end_io = one_flush_endio;
+	bio_set_op_attrs(bio, REQ_OP_FLUSH, WRITE_FLUSH);
+
+	device->flush_jif = jiffies;
+	set_bit(FLUSH_PENDING, &device->flags);
+	atomic_inc(&ctx->pending);
+	submit_bio(bio);
+}
+
+static void drbd_flush(struct drbd_connection *connection)
+{
 	if (connection->resource->write_ordering >= WO_BDEV_FLUSH) {
+		struct drbd_peer_device *peer_device;
+		struct issue_flush_context ctx;
+		int vnr;
+
+		atomic_set(&ctx.pending, 1);
+		ctx.error = 0;
+		init_completion(&ctx.done);
+
 		rcu_read_lock();
 		idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
 			struct drbd_device *device = peer_device->device;
@@ -1220,31 +1294,24 @@ static void drbd_flush(struct drbd_connection *connection)
 			kref_get(&device->kref);
 			rcu_read_unlock();
 
-			/* Right now, we have only this one synchronous code path
-			 * for flushes between request epochs.
-			 * We may want to make those asynchronous,
-			 * or at least parallelize the flushes to the volume devices.
-			 */
-			device->flush_jif = jiffies;
-			set_bit(FLUSH_PENDING, &device->flags);
-			rv = blkdev_issue_flush(device->ldev->backing_bdev,
-					GFP_NOIO, NULL);
-			clear_bit(FLUSH_PENDING, &device->flags);
-			if (rv) {
-				drbd_info(device, "local disk flush failed with status %d\n", rv);
-				/* would rather check on EOPNOTSUPP, but that is not reliable.
-				 * don't try again for ANY return value != 0
-				 * if (rv == -EOPNOTSUPP) */
-				drbd_bump_write_ordering(connection->resource, NULL, WO_DRAIN_IO);
-			}
-			put_ldev(device);
-			kref_put(&device->kref, drbd_destroy_device);
+			submit_one_flush(device, &ctx);
 
 			rcu_read_lock();
-			if (rv)
-				break;
 		}
 		rcu_read_unlock();
+
+		/* Do we want to add a timeout,
+		 * if disk-timeout is set? */
+		if (!atomic_dec_and_test(&ctx.pending))
+			wait_for_completion(&ctx.done);
+
+		if (ctx.error) {
+			/* would rather check on EOPNOTSUPP, but that is not reliable.
+			 * don't try again for ANY return value != 0
+			 * if (rv == -EOPNOTSUPP) */
+			/* Any error is already reported by bio_endio callback. */
+			drbd_bump_write_ordering(connection->resource, NULL, WO_DRAIN_IO);
+		}
 	}
 }
 
@@ -1379,6 +1446,120 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
 		drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]);
 }
 
+/*
+ * We *may* ignore the discard-zeroes-data setting, if so configured.
+ *
+ * Assumption is that it "discard_zeroes_data=0" is only because the backend
+ * may ignore partial unaligned discards.
+ *
+ * LVM/DM thin as of at least
+ *   LVM version:     2.02.115(2)-RHEL7 (2015-01-28)
+ *   Library version: 1.02.93-RHEL7 (2015-01-28)
+ *   Driver version:  4.29.0
+ * still behaves this way.
+ *
+ * For unaligned (wrt. alignment and granularity) or too small discards,
+ * we zero-out the initial (and/or) trailing unaligned partial chunks,
+ * but discard all the aligned full chunks.
+ *
+ * At least for LVM/DM thin, the result is effectively "discard_zeroes_data=1".
+ */
+int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, bool discard)
+{
+	struct block_device *bdev = device->ldev->backing_bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
+	sector_t tmp, nr;
+	unsigned int max_discard_sectors, granularity;
+	int alignment;
+	int err = 0;
+
+	if (!discard)
+		goto zero_out;
+
+	/* Zero-sector (unknown) and one-sector granularities are the same.  */
+	granularity = max(q->limits.discard_granularity >> 9, 1U);
+	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
+
+	max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22));
+	max_discard_sectors -= max_discard_sectors % granularity;
+	if (unlikely(!max_discard_sectors))
+		goto zero_out;
+
+	if (nr_sectors < granularity)
+		goto zero_out;
+
+	tmp = start;
+	if (sector_div(tmp, granularity) != alignment) {
+		if (nr_sectors < 2*granularity)
+			goto zero_out;
+		/* start + gran - (start + gran - align) % gran */
+		tmp = start + granularity - alignment;
+		tmp = start + granularity - sector_div(tmp, granularity);
+
+		nr = tmp - start;
+		err |= blkdev_issue_zeroout(bdev, start, nr, GFP_NOIO, 0);
+		nr_sectors -= nr;
+		start = tmp;
+	}
+	while (nr_sectors >= granularity) {
+		nr = min_t(sector_t, nr_sectors, max_discard_sectors);
+		err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0);
+		nr_sectors -= nr;
+		start += nr;
+	}
+ zero_out:
+	if (nr_sectors) {
+		err |= blkdev_issue_zeroout(bdev, start, nr_sectors, GFP_NOIO, 0);
+	}
+	return err != 0;
+}
+
+static bool can_do_reliable_discards(struct drbd_device *device)
+{
+	struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
+	struct disk_conf *dc;
+	bool can_do;
+
+	if (!blk_queue_discard(q))
+		return false;
+
+	if (q->limits.discard_zeroes_data)
+		return true;
+
+	rcu_read_lock();
+	dc = rcu_dereference(device->ldev->disk_conf);
+	can_do = dc->discard_zeroes_if_aligned;
+	rcu_read_unlock();
+	return can_do;
+}
+
+static void drbd_issue_peer_discard(struct drbd_device *device, struct drbd_peer_request *peer_req)
+{
+	/* If the backend cannot discard, or does not guarantee
+	 * read-back zeroes in discarded ranges, we fall back to
+	 * zero-out.  Unless configuration specifically requested
+	 * otherwise. */
+	if (!can_do_reliable_discards(device))
+		peer_req->flags |= EE_IS_TRIM_USE_ZEROOUT;
+
+	if (drbd_issue_discard_or_zero_out(device, peer_req->i.sector,
+	    peer_req->i.size >> 9, !(peer_req->flags & EE_IS_TRIM_USE_ZEROOUT)))
+		peer_req->flags |= EE_WAS_ERROR;
+	drbd_endio_write_sec_final(peer_req);
+}
+
+static void drbd_issue_peer_wsame(struct drbd_device *device,
+				  struct drbd_peer_request *peer_req)
+{
+	struct block_device *bdev = device->ldev->backing_bdev;
+	sector_t s = peer_req->i.sector;
+	sector_t nr = peer_req->i.size >> 9;
+	if (blkdev_issue_write_same(bdev, s, nr, GFP_NOIO, peer_req->pages))
+		peer_req->flags |= EE_WAS_ERROR;
+	drbd_endio_write_sec_final(peer_req);
+}
+
+
 /**
  * drbd_submit_peer_request()
  * @device:	DRBD device.
@@ -1398,7 +1579,8 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
 /* TODO allocate from our own bio_set. */
 int drbd_submit_peer_request(struct drbd_device *device,
 			     struct drbd_peer_request *peer_req,
-			     const unsigned rw, const int fault_type)
+			     const unsigned op, const unsigned op_flags,
+			     const int fault_type)
 {
 	struct bio *bios = NULL;
 	struct bio *bio;
@@ -1409,7 +1591,13 @@ int drbd_submit_peer_request(struct drbd_device *device,
 	unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT;
 	int err = -ENOMEM;
 
-	if (peer_req->flags & EE_IS_TRIM_USE_ZEROOUT) {
+	/* TRIM/DISCARD: for now, always use the helper function
+	 * blkdev_issue_zeroout(..., discard=true).
+	 * It's synchronous, but it does the right thing wrt. bio splitting.
+	 * Correctness first, performance later.  Next step is to code an
+	 * asynchronous variant of the same.
+	 */
+	if (peer_req->flags & (EE_IS_TRIM|EE_WRITE_SAME)) {
 		/* wait for all pending IO completions, before we start
 		 * zeroing things out. */
 		conn_wait_active_ee_empty(peer_req->peer_device->connection);
@@ -1417,22 +1605,22 @@ int drbd_submit_peer_request(struct drbd_device *device,
 		 * so we can find it to present it in debugfs */
 		peer_req->submit_jif = jiffies;
 		peer_req->flags |= EE_SUBMITTED;
-		spin_lock_irq(&device->resource->req_lock);
-		list_add_tail(&peer_req->w.list, &device->active_ee);
-		spin_unlock_irq(&device->resource->req_lock);
-		if (blkdev_issue_zeroout(device->ldev->backing_bdev,
-			sector, data_size >> 9, GFP_NOIO, false))
-			peer_req->flags |= EE_WAS_ERROR;
-		drbd_endio_write_sec_final(peer_req);
+
+		/* If this was a resync request from receive_rs_deallocated(),
+		 * it is already on the sync_ee list */
+		if (list_empty(&peer_req->w.list)) {
+			spin_lock_irq(&device->resource->req_lock);
+			list_add_tail(&peer_req->w.list, &device->active_ee);
+			spin_unlock_irq(&device->resource->req_lock);
+		}
+
+		if (peer_req->flags & EE_IS_TRIM)
+			drbd_issue_peer_discard(device, peer_req);
+		else /* EE_WRITE_SAME */
+			drbd_issue_peer_wsame(device, peer_req);
 		return 0;
 	}
 
-	/* Discards don't have any payload.
-	 * But the scsi layer still expects a bio_vec it can use internally,
-	 * see sd_setup_discard_cmnd() and blk_add_request_payload(). */
-	if (peer_req->flags & EE_IS_TRIM)
-		nr_pages = 1;
-
 	/* In most cases, we will only need one bio.  But in case the lower
 	 * level restrictions happen to be different at this offset on this
 	 * side than those of the sending peer, we may need to submit the
@@ -1450,7 +1638,7 @@ next_bio:
 	/* > peer_req->i.sector, unless this is the first bio */
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_bdev = device->ldev->backing_bdev;
-	bio->bi_rw = rw;
+	bio_set_op_attrs(bio, op, op_flags);
 	bio->bi_private = peer_req;
 	bio->bi_end_io = drbd_peer_request_endio;
 
@@ -1458,11 +1646,6 @@ next_bio:
 	bios = bio;
 	++n_bios;
 
-	if (rw & REQ_DISCARD) {
-		bio->bi_iter.bi_size = data_size;
-		goto submit;
-	}
-
 	page_chain_for_each(page) {
 		unsigned len = min_t(unsigned, data_size, PAGE_SIZE);
 		if (!bio_add_page(bio, page, len, 0)) {
@@ -1484,7 +1667,6 @@ next_bio:
 		--nr_pages;
 	}
 	D_ASSERT(device, data_size == 0);
-submit:
 	D_ASSERT(device, page == NULL);
 
 	atomic_set(&peer_req->pending_bios, n_bios);
@@ -1608,8 +1790,26 @@ static int receive_Barrier(struct drbd_connection *connection, struct packet_inf
 	return 0;
 }
 
+/* quick wrapper in case payload size != request_size (write same) */
+static void drbd_csum_ee_size(struct crypto_ahash *h,
+			      struct drbd_peer_request *r, void *d,
+			      unsigned int payload_size)
+{
+	unsigned int tmp = r->i.size;
+	r->i.size = payload_size;
+	drbd_csum_ee(h, r, d);
+	r->i.size = tmp;
+}
+
 /* used from receive_RSDataReply (recv_resync_read)
- * and from receive_Data */
+ * and from receive_Data.
+ * data_size: actual payload ("data in")
+ * 	for normal writes that is bi_size.
+ * 	for discards, that is zero.
+ * 	for write same, it is logical_block_size.
+ * both trim and write same have the bi_size ("data len to be affected")
+ * as extra argument in the packet header.
+ */
 static struct drbd_peer_request *
 read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 	      struct packet_info *pi) __must_hold(local)
@@ -1624,6 +1824,7 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 	void *dig_vv = peer_device->connection->int_dig_vv;
 	unsigned long *data;
 	struct p_trim *trim = (pi->cmd == P_TRIM) ? pi->data : NULL;
+	struct p_trim *wsame = (pi->cmd == P_WSAME) ? pi->data : NULL;
 
 	digest_size = 0;
 	if (!trim && peer_device->connection->peer_integrity_tfm) {
@@ -1638,38 +1839,60 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 		data_size -= digest_size;
 	}
 
+	/* assume request_size == data_size, but special case trim and wsame. */
+	ds = data_size;
 	if (trim) {
-		D_ASSERT(peer_device, data_size == 0);
-		data_size = be32_to_cpu(trim->size);
+		if (!expect(data_size == 0))
+			return NULL;
+		ds = be32_to_cpu(trim->size);
+	} else if (wsame) {
+		if (data_size != queue_logical_block_size(device->rq_queue)) {
+			drbd_err(peer_device, "data size (%u) != drbd logical block size (%u)\n",
+				data_size, queue_logical_block_size(device->rq_queue));
+			return NULL;
+		}
+		if (data_size != bdev_logical_block_size(device->ldev->backing_bdev)) {
+			drbd_err(peer_device, "data size (%u) != backend logical block size (%u)\n",
+				data_size, bdev_logical_block_size(device->ldev->backing_bdev));
+			return NULL;
+		}
+		ds = be32_to_cpu(wsame->size);
 	}
 
-	if (!expect(IS_ALIGNED(data_size, 512)))
+	if (!expect(IS_ALIGNED(ds, 512)))
 		return NULL;
-	/* prepare for larger trim requests. */
-	if (!trim && !expect(data_size <= DRBD_MAX_BIO_SIZE))
+	if (trim || wsame) {
+		if (!expect(ds <= (DRBD_MAX_BBIO_SECTORS << 9)))
+			return NULL;
+	} else if (!expect(ds <= DRBD_MAX_BIO_SIZE))
 		return NULL;
 
 	/* even though we trust out peer,
 	 * we sometimes have to double check. */
-	if (sector + (data_size>>9) > capacity) {
+	if (sector + (ds>>9) > capacity) {
 		drbd_err(device, "request from peer beyond end of local disk: "
 			"capacity: %llus < sector: %llus + size: %u\n",
 			(unsigned long long)capacity,
-			(unsigned long long)sector, data_size);
+			(unsigned long long)sector, ds);
 		return NULL;
 	}
 
 	/* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD
 	 * "criss-cross" setup, that might cause write-out on some other DRBD,
 	 * which in turn might block on the other node at this very place.  */
-	peer_req = drbd_alloc_peer_req(peer_device, id, sector, data_size, trim == NULL, GFP_NOIO);
+	peer_req = drbd_alloc_peer_req(peer_device, id, sector, ds, data_size, GFP_NOIO);
 	if (!peer_req)
 		return NULL;
 
 	peer_req->flags |= EE_WRITE;
-	if (trim)
+	if (trim) {
+		peer_req->flags |= EE_IS_TRIM;
 		return peer_req;
+	}
+	if (wsame)
+		peer_req->flags |= EE_WRITE_SAME;
 
+	/* receive payload size bytes into page chain */
 	ds = data_size;
 	page = peer_req->pages;
 	page_chain_for_each(page) {
@@ -1689,7 +1912,7 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 	}
 
 	if (digest_size) {
-		drbd_csum_ee(peer_device->connection->peer_integrity_tfm, peer_req, dig_vv);
+		drbd_csum_ee_size(peer_device->connection->peer_integrity_tfm, peer_req, dig_vv, data_size);
 		if (memcmp(dig_in, dig_vv, digest_size)) {
 			drbd_err(device, "Digest integrity check FAILED: %llus +%u\n",
 				(unsigned long long)sector, data_size);
@@ -1830,7 +2053,8 @@ static int recv_resync_read(struct drbd_peer_device *peer_device, sector_t secto
 	spin_unlock_irq(&device->resource->req_lock);
 
 	atomic_add(pi->size >> 9, &device->rs_sect_ev);
-	if (drbd_submit_peer_request(device, peer_req, WRITE, DRBD_FAULT_RS_WR) == 0)
+	if (drbd_submit_peer_request(device, peer_req, REQ_OP_WRITE, 0,
+				     DRBD_FAULT_RS_WR) == 0)
 		return 0;
 
 	/* don't care for the reason here */
@@ -2065,13 +2289,13 @@ static inline int overlaps(sector_t s1, int l1, sector_t s2, int l2)
 static bool overlapping_resync_write(struct drbd_device *device, struct drbd_peer_request *peer_req)
 {
 	struct drbd_peer_request *rs_req;
-	bool rv = 0;
+	bool rv = false;
 
 	spin_lock_irq(&device->resource->req_lock);
 	list_for_each_entry(rs_req, &device->sync_ee, w.list) {
 		if (overlaps(peer_req->i.sector, peer_req->i.size,
 			     rs_req->i.sector, rs_req->i.size)) {
-			rv = 1;
+			rv = true;
 			break;
 		}
 	}
@@ -2152,12 +2376,19 @@ static int wait_for_and_update_peer_seq(struct drbd_peer_device *peer_device, co
 /* see also bio_flags_to_wire()
  * DRBD_REQ_*, because we need to semantically map the flags to data packet
  * flags and back. We may replicate to other kernel versions. */
-static unsigned long wire_flags_to_bio(u32 dpf)
+static unsigned long wire_flags_to_bio_flags(u32 dpf)
 {
 	return  (dpf & DP_RW_SYNC ? REQ_SYNC : 0) |
 		(dpf & DP_FUA ? REQ_FUA : 0) |
-		(dpf & DP_FLUSH ? REQ_FLUSH : 0) |
-		(dpf & DP_DISCARD ? REQ_DISCARD : 0);
+		(dpf & DP_FLUSH ? REQ_PREFLUSH : 0);
+}
+
+static unsigned long wire_flags_to_bio_op(u32 dpf)
+{
+	if (dpf & DP_DISCARD)
+		return REQ_OP_DISCARD;
+	else
+		return REQ_OP_WRITE;
 }
 
 static void fail_postponed_requests(struct drbd_device *device, sector_t sector,
@@ -2303,7 +2534,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 	struct drbd_peer_request *peer_req;
 	struct p_data *p = pi->data;
 	u32 peer_seq = be32_to_cpu(p->seq_num);
-	int rw = WRITE;
+	int op, op_flags;
 	u32 dp_flags;
 	int err, tp;
 
@@ -2342,14 +2573,11 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 	peer_req->flags |= EE_APPLICATION;
 
 	dp_flags = be32_to_cpu(p->dp_flags);
-	rw |= wire_flags_to_bio(dp_flags);
+	op = wire_flags_to_bio_op(dp_flags);
+	op_flags = wire_flags_to_bio_flags(dp_flags);
 	if (pi->cmd == P_TRIM) {
-		struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
-		peer_req->flags |= EE_IS_TRIM;
-		if (!blk_queue_discard(q))
-			peer_req->flags |= EE_IS_TRIM_USE_ZEROOUT;
 		D_ASSERT(peer_device, peer_req->i.size > 0);
-		D_ASSERT(peer_device, rw & REQ_DISCARD);
+		D_ASSERT(peer_device, op == REQ_OP_DISCARD);
 		D_ASSERT(peer_device, peer_req->pages == NULL);
 	} else if (peer_req->pages == NULL) {
 		D_ASSERT(device, peer_req->i.size == 0);
@@ -2414,11 +2642,11 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 		update_peer_seq(peer_device, peer_seq);
 		spin_lock_irq(&device->resource->req_lock);
 	}
-	/* if we use the zeroout fallback code, we process synchronously
-	 * and we wait for all pending requests, respectively wait for
+	/* TRIM and WRITE_SAME are processed synchronously,
+	 * we wait for all pending requests, respectively wait for
 	 * active_ee to become empty in drbd_submit_peer_request();
 	 * better not add ourselves here. */
-	if ((peer_req->flags & EE_IS_TRIM_USE_ZEROOUT) == 0)
+	if ((peer_req->flags & (EE_IS_TRIM|EE_WRITE_SAME)) == 0)
 		list_add_tail(&peer_req->w.list, &device->active_ee);
 	spin_unlock_irq(&device->resource->req_lock);
 
@@ -2433,7 +2661,8 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 		peer_req->flags |= EE_CALL_AL_COMPLETE_IO;
 	}
 
-	err = drbd_submit_peer_request(device, peer_req, rw, DRBD_FAULT_DT_WR);
+	err = drbd_submit_peer_request(device, peer_req, op, op_flags,
+				       DRBD_FAULT_DT_WR);
 	if (!err)
 		return 0;
 
@@ -2449,7 +2678,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 	}
 
 out_interrupted:
-	drbd_may_finish_epoch(connection, peer_req->epoch, EV_PUT + EV_CLEANUP);
+	drbd_may_finish_epoch(connection, peer_req->epoch, EV_PUT | EV_CLEANUP);
 	put_ldev(device);
 	drbd_free_peer_req(device, peer_req);
 	return err;
@@ -2574,6 +2803,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		case P_DATA_REQUEST:
 			drbd_send_ack_rp(peer_device, P_NEG_DREPLY, p);
 			break;
+		case P_RS_THIN_REQ:
 		case P_RS_DATA_REQUEST:
 		case P_CSUM_RS_REQUEST:
 		case P_OV_REQUEST:
@@ -2599,7 +2829,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 	 * "criss-cross" setup, that might cause write-out on some other DRBD,
 	 * which in turn might block on the other node at this very place.  */
 	peer_req = drbd_alloc_peer_req(peer_device, p->block_id, sector, size,
-			true /* has real payload */, GFP_NOIO);
+			size, GFP_NOIO);
 	if (!peer_req) {
 		put_ldev(device);
 		return -ENOMEM;
@@ -2613,6 +2843,12 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		peer_req->flags |= EE_APPLICATION;
 		goto submit;
 
+	case P_RS_THIN_REQ:
+		/* If at some point in the future we have a smart way to
+		   find out if this data block is completely deallocated,
+		   then we would do something smarter here than reading
+		   the block... */
+		peer_req->flags |= EE_RS_THIN_REQ;
 	case P_RS_DATA_REQUEST:
 		peer_req->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
@@ -2723,7 +2959,8 @@ submit_for_resync:
 submit:
 	update_receiver_timing_details(connection, drbd_submit_peer_request);
 	inc_unacked(device);
-	if (drbd_submit_peer_request(device, peer_req, READ, fault_type) == 0)
+	if (drbd_submit_peer_request(device, peer_req, REQ_OP_READ, 0,
+				     fault_type) == 0)
 		return 0;
 
 	/* don't care for the reason here */
@@ -2957,7 +3194,8 @@ static void drbd_uuid_dump(struct drbd_device *device, char *text, u64 *uuid,
 -1091   requires proto 91
 -1096   requires proto 96
  */
-static int drbd_uuid_compare(struct drbd_device *const device, int *rule_nr) __must_hold(local)
+
+static int drbd_uuid_compare(struct drbd_device *const device, enum drbd_role const peer_role, int *rule_nr) __must_hold(local)
 {
 	struct drbd_peer_device *const peer_device = first_peer_device(device);
 	struct drbd_connection *const connection = peer_device ? peer_device->connection : NULL;
@@ -3037,8 +3275,39 @@ static int drbd_uuid_compare(struct drbd_device *const device, int *rule_nr) __m
 		 * next bit (weight 2) is set when peer was primary */
 		*rule_nr = 40;
 
+		/* Neither has the "crashed primary" flag set,
+		 * only a replication link hickup. */
+		if (rct == 0)
+			return 0;
+
+		/* Current UUID equal and no bitmap uuid; does not necessarily
+		 * mean this was a "simultaneous hard crash", maybe IO was
+		 * frozen, so no UUID-bump happened.
+		 * This is a protocol change, overload DRBD_FF_WSAME as flag
+		 * for "new-enough" peer DRBD version. */
+		if (device->state.role == R_PRIMARY || peer_role == R_PRIMARY) {
+			*rule_nr = 41;
+			if (!(connection->agreed_features & DRBD_FF_WSAME)) {
+				drbd_warn(peer_device, "Equivalent unrotated UUIDs, but current primary present.\n");
+				return -(0x10000 | PRO_VERSION_MAX | (DRBD_FF_WSAME << 8));
+			}
+			if (device->state.role == R_PRIMARY && peer_role == R_PRIMARY) {
+				/* At least one has the "crashed primary" bit set,
+				 * both are primary now, but neither has rotated its UUIDs?
+				 * "Can not happen." */
+				drbd_err(peer_device, "Equivalent unrotated UUIDs, but both are primary. Can not resolve this.\n");
+				return -100;
+			}
+			if (device->state.role == R_PRIMARY)
+				return 1;
+			return -1;
+		}
+
+		/* Both are secondary.
+		 * Really looks like recovery from simultaneous hard crash.
+		 * Check which had been primary before, and arbitrate. */
 		switch (rct) {
-		case 0: /* !self_pri && !peer_pri */ return 0;
+		case 0: /* !self_pri && !peer_pri */ return 0; /* already handled */
 		case 1: /*  self_pri && !peer_pri */ return 1;
 		case 2: /* !self_pri &&  peer_pri */ return -1;
 		case 3: /*  self_pri &&  peer_pri */
@@ -3165,7 +3434,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
 	drbd_uuid_dump(device, "peer", device->p_uuid,
 		       device->p_uuid[UI_SIZE], device->p_uuid[UI_FLAGS]);
 
-	hg = drbd_uuid_compare(device, &rule_nr);
+	hg = drbd_uuid_compare(device, peer_role, &rule_nr);
 	spin_unlock_irq(&device->ldev->md.uuid_lock);
 
 	drbd_info(device, "uuid_compare()=%d by rule %d\n", hg, rule_nr);
@@ -3174,6 +3443,15 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
 		drbd_alert(device, "Unrelated data, aborting!\n");
 		return C_MASK;
 	}
+	if (hg < -0x10000) {
+		int proto, fflags;
+		hg = -hg;
+		proto = hg & 0xff;
+		fflags = (hg >> 8) & 0xff;
+		drbd_alert(device, "To resolve this both sides have to support at least protocol %d and feature flags 0x%x\n",
+					proto, fflags);
+		return C_MASK;
+	}
 	if (hg < -1000) {
 		drbd_alert(device, "To resolve this both sides have to support at least protocol %d\n", -hg - 1000);
 		return C_MASK;
@@ -3403,7 +3681,8 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in
 		 */
 
 		peer_integrity_tfm = crypto_alloc_ahash(integrity_alg, 0, CRYPTO_ALG_ASYNC);
-		if (!peer_integrity_tfm) {
+		if (IS_ERR(peer_integrity_tfm)) {
+			peer_integrity_tfm = NULL;
 			drbd_err(connection, "peer data-integrity-alg %s not supported\n",
 				 integrity_alg);
 			goto disconnect;
@@ -3754,6 +4033,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 	struct drbd_peer_device *peer_device;
 	struct drbd_device *device;
 	struct p_sizes *p = pi->data;
+	struct o_qlim *o = (connection->agreed_features & DRBD_FF_WSAME) ? p->qlim : NULL;
 	enum determine_dev_size dd = DS_UNCHANGED;
 	sector_t p_size, p_usize, p_csize, my_usize;
 	int ldsc = 0; /* local disk size changed */
@@ -3773,6 +4053,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 	device->p_size = p_size;
 
 	if (get_ldev(device)) {
+		sector_t new_size, cur_size;
 		rcu_read_lock();
 		my_usize = rcu_dereference(device->ldev->disk_conf)->disk_size;
 		rcu_read_unlock();
@@ -3789,11 +4070,13 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 
 		/* Never shrink a device with usable data during connect.
 		   But allow online shrinking if we are connected. */
-		if (drbd_new_dev_size(device, device->ldev, p_usize, 0) <
-		    drbd_get_capacity(device->this_bdev) &&
+		new_size = drbd_new_dev_size(device, device->ldev, p_usize, 0);
+		cur_size = drbd_get_capacity(device->this_bdev);
+		if (new_size < cur_size &&
 		    device->state.disk >= D_OUTDATED &&
 		    device->state.conn < C_CONNECTED) {
-			drbd_err(device, "The peer's disk size is too small!\n");
+			drbd_err(device, "The peer's disk size is too small! (%llu < %llu sectors)\n",
+					(unsigned long long)new_size, (unsigned long long)cur_size);
 			conn_request_state(peer_device->connection, NS(conn, C_DISCONNECTING), CS_HARD);
 			put_ldev(device);
 			return -EIO;
@@ -3827,14 +4110,14 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 	}
 
 	device->peer_max_bio_size = be32_to_cpu(p->max_bio_size);
-	/* Leave drbd_reconsider_max_bio_size() before drbd_determine_dev_size().
+	/* Leave drbd_reconsider_queue_parameters() before drbd_determine_dev_size().
 	   In case we cleared the QUEUE_FLAG_DISCARD from our queue in
-	   drbd_reconsider_max_bio_size(), we can be sure that after
+	   drbd_reconsider_queue_parameters(), we can be sure that after
 	   drbd_determine_dev_size() no REQ_DISCARDs are in the queue. */
 
 	ddsf = be16_to_cpu(p->dds_flags);
 	if (get_ldev(device)) {
-		drbd_reconsider_max_bio_size(device, device->ldev);
+		drbd_reconsider_queue_parameters(device, device->ldev, o);
 		dd = drbd_determine_dev_size(device, ddsf, NULL);
 		put_ldev(device);
 		if (dd == DS_ERROR)
@@ -3854,7 +4137,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 		 * However, if he sends a zero current size,
 		 * take his (user-capped or) backing disk size anyways.
 		 */
-		drbd_reconsider_max_bio_size(device, NULL);
+		drbd_reconsider_queue_parameters(device, NULL, o);
 		drbd_set_my_capacity(device, p_csize ?: p_usize ?: p_size);
 	}
 
@@ -4587,9 +4870,75 @@ static int receive_out_of_sync(struct drbd_connection *connection, struct packet
 	return 0;
 }
 
+static int receive_rs_deallocated(struct drbd_connection *connection, struct packet_info *pi)
+{
+	struct drbd_peer_device *peer_device;
+	struct p_block_desc *p = pi->data;
+	struct drbd_device *device;
+	sector_t sector;
+	int size, err = 0;
+
+	peer_device = conn_peer_device(connection, pi->vnr);
+	if (!peer_device)
+		return -EIO;
+	device = peer_device->device;
+
+	sector = be64_to_cpu(p->sector);
+	size = be32_to_cpu(p->blksize);
+
+	dec_rs_pending(device);
+
+	if (get_ldev(device)) {
+		struct drbd_peer_request *peer_req;
+		const int op = REQ_OP_DISCARD;
+
+		peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER, sector,
+					       size, 0, GFP_NOIO);
+		if (!peer_req) {
+			put_ldev(device);
+			return -ENOMEM;
+		}
+
+		peer_req->w.cb = e_end_resync_block;
+		peer_req->submit_jif = jiffies;
+		peer_req->flags |= EE_IS_TRIM;
+
+		spin_lock_irq(&device->resource->req_lock);
+		list_add_tail(&peer_req->w.list, &device->sync_ee);
+		spin_unlock_irq(&device->resource->req_lock);
+
+		atomic_add(pi->size >> 9, &device->rs_sect_ev);
+		err = drbd_submit_peer_request(device, peer_req, op, 0, DRBD_FAULT_RS_WR);
+
+		if (err) {
+			spin_lock_irq(&device->resource->req_lock);
+			list_del(&peer_req->w.list);
+			spin_unlock_irq(&device->resource->req_lock);
+
+			drbd_free_peer_req(device, peer_req);
+			put_ldev(device);
+			err = 0;
+			goto fail;
+		}
+
+		inc_unacked(device);
+
+		/* No put_ldev() here. Gets called in drbd_endio_write_sec_final(),
+		   as well as drbd_rs_complete_io() */
+	} else {
+	fail:
+		drbd_rs_complete_io(device, sector);
+		drbd_send_ack_ex(peer_device, P_NEG_ACK, sector, size, ID_SYNCER);
+	}
+
+	atomic_add(size >> 9, &device->rs_sect_in);
+
+	return err;
+}
+
 struct data_cmd {
 	int expect_payload;
-	size_t pkt_size;
+	unsigned int pkt_size;
 	int (*fn)(struct drbd_connection *, struct packet_info *);
 };
 
@@ -4614,11 +4963,14 @@ static struct data_cmd drbd_cmd_handler[] = {
 	[P_OV_REQUEST]      = { 0, sizeof(struct p_block_req), receive_DataRequest },
 	[P_OV_REPLY]        = { 1, sizeof(struct p_block_req), receive_DataRequest },
 	[P_CSUM_RS_REQUEST] = { 1, sizeof(struct p_block_req), receive_DataRequest },
+	[P_RS_THIN_REQ]     = { 0, sizeof(struct p_block_req), receive_DataRequest },
 	[P_DELAY_PROBE]     = { 0, sizeof(struct p_delay_probe93), receive_skip },
 	[P_OUT_OF_SYNC]     = { 0, sizeof(struct p_block_desc), receive_out_of_sync },
 	[P_CONN_ST_CHG_REQ] = { 0, sizeof(struct p_req_state), receive_req_conn_state },
 	[P_PROTOCOL_UPDATE] = { 1, sizeof(struct p_protocol), receive_protocol },
 	[P_TRIM]	    = { 0, sizeof(struct p_trim), receive_Data },
+	[P_RS_DEALLOCATED]  = { 0, sizeof(struct p_block_desc), receive_rs_deallocated },
+	[P_WSAME]	    = { 1, sizeof(struct p_wsame), receive_Data },
 };
 
 static void drbdd(struct drbd_connection *connection)
@@ -4628,7 +4980,7 @@ static void drbdd(struct drbd_connection *connection)
 	int err;
 
 	while (get_t_state(&connection->receiver) == RUNNING) {
-		struct data_cmd *cmd;
+		struct data_cmd const *cmd;
 
 		drbd_thread_current_set_cpu(&connection->receiver);
 		update_receiver_timing_details(connection, drbd_recv_header);
@@ -4643,11 +4995,18 @@ static void drbdd(struct drbd_connection *connection)
 		}
 
 		shs = cmd->pkt_size;
+		if (pi.cmd == P_SIZES && connection->agreed_features & DRBD_FF_WSAME)
+			shs += sizeof(struct o_qlim);
 		if (pi.size > shs && !cmd->expect_payload) {
 			drbd_err(connection, "No payload expected %s l:%d\n",
 				 cmdname(pi.cmd), pi.size);
 			goto err_out;
 		}
+		if (pi.size < shs) {
+			drbd_err(connection, "%s: unexpected packet size, expected:%d received:%d\n",
+				 cmdname(pi.cmd), (int)shs, pi.size);
+			goto err_out;
+		}
 
 		if (shs) {
 			update_receiver_timing_details(connection, drbd_recv_all_warn);
@@ -4783,9 +5142,11 @@ static int drbd_disconnected(struct drbd_peer_device *peer_device)
 
 	drbd_md_sync(device);
 
-	/* serialize with bitmap writeout triggered by the state change,
-	 * if any. */
-	wait_event(device->misc_wait, !test_bit(BITMAP_IO, &device->flags));
+	if (get_ldev(device)) {
+		drbd_bitmap_io(device, &drbd_bm_write_copy_pages,
+				"write from disconnected", BM_LOCKED_CHANGE_ALLOWED);
+		put_ldev(device);
+	}
 
 	/* tcp_close and release of sendpage pages can be deferred.  I don't
 	 * want to use SO_LINGER, because apparently it can be deferred for
@@ -4892,8 +5253,12 @@ static int drbd_do_features(struct drbd_connection *connection)
 	drbd_info(connection, "Handshake successful: "
 	     "Agreed network protocol version %d\n", connection->agreed_pro_version);
 
-	drbd_info(connection, "Agreed to%ssupport TRIM on protocol level\n",
-		  connection->agreed_features & FF_TRIM ? " " : " not ");
+	drbd_info(connection, "Feature flags enabled on protocol level: 0x%x%s%s%s.\n",
+		  connection->agreed_features,
+		  connection->agreed_features & DRBD_FF_TRIM ? " TRIM" : "",
+		  connection->agreed_features & DRBD_FF_THIN_RESYNC ? " THIN_RESYNC" : "",
+		  connection->agreed_features & DRBD_FF_WSAME ? " WRITE_SAME" :
+		  connection->agreed_features ? "" : " none");
 
 	return 1;
 
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 2255dcfebd2b..66b8e4bb74d8 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -47,8 +47,7 @@ static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *r
 			    &device->vdisk->part0, req->start_jif);
 }
 
-static struct drbd_request *drbd_req_new(struct drbd_device *device,
-					       struct bio *bio_src)
+static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio *bio_src)
 {
 	struct drbd_request *req;
 
@@ -58,10 +57,12 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device,
 	memset(req, 0, sizeof(*req));
 
 	drbd_req_make_private_bio(req, bio_src);
-	req->rq_state    = bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0;
-	req->device   = device;
-	req->master_bio  = bio_src;
-	req->epoch       = 0;
+	req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
+		      | (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0)
+		      | (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0);
+	req->device = device;
+	req->master_bio = bio_src;
+	req->epoch = 0;
 
 	drbd_clear_interval(&req->i);
 	req->i.sector     = bio_src->bi_iter.bi_sector;
@@ -218,7 +219,6 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m)
 {
 	const unsigned s = req->rq_state;
 	struct drbd_device *device = req->device;
-	int rw;
 	int error, ok;
 
 	/* we must not complete the master bio, while it is
@@ -242,8 +242,6 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m)
 		return;
 	}
 
-	rw = bio_rw(req->master_bio);
-
 	/*
 	 * figure out whether to report success or failure.
 	 *
@@ -267,7 +265,7 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m)
 	 * epoch number.  If they match, increase the current_tle_nr,
 	 * and reset the transfer log epoch write_cnt.
 	 */
-	if (rw == WRITE &&
+	if (op_is_write(bio_op(req->master_bio)) &&
 	    req->epoch == atomic_read(&first_peer_device(device)->connection->current_tle_nr))
 		start_new_tl_epoch(first_peer_device(device)->connection);
 
@@ -284,11 +282,14 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m)
 	 * because no path was available, in which case
 	 * it was not even added to the transfer_log.
 	 *
-	 * READA may fail, and will not be retried.
+	 * read-ahead may fail, and will not be retried.
 	 *
 	 * WRITE should have used all available paths already.
 	 */
-	if (!ok && rw == READ && !list_empty(&req->tl_requests))
+	if (!ok &&
+	    bio_op(req->master_bio) == REQ_OP_READ &&
+	    !(req->master_bio->bi_rw & REQ_RAHEAD) &&
+	    !list_empty(&req->tl_requests))
 		req->rq_state |= RQ_POSTPONED;
 
 	if (!(req->rq_state & RQ_POSTPONED)) {
@@ -644,7 +645,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		__drbd_chk_io_error(device, DRBD_READ_ERROR);
 		/* fall through. */
 	case READ_AHEAD_COMPLETED_WITH_ERROR:
-		/* it is legal to fail READA, no __drbd_chk_io_error in that case. */
+		/* it is legal to fail read-ahead, no __drbd_chk_io_error in that case. */
 		mod_rq_state(req, m, RQ_LOCAL_PENDING, RQ_LOCAL_COMPLETED);
 		break;
 
@@ -656,7 +657,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		break;
 
 	case QUEUE_FOR_NET_READ:
-		/* READ or READA, and
+		/* READ, and
 		 * no local disk,
 		 * or target area marked as invalid,
 		 * or just got an io-error. */
@@ -977,16 +978,20 @@ static void complete_conflicting_writes(struct drbd_request *req)
 	sector_t sector = req->i.sector;
 	int size = req->i.size;
 
-	i = drbd_find_overlap(&device->write_requests, sector, size);
-	if (!i)
-		return;
-
 	for (;;) {
-		prepare_to_wait(&device->misc_wait, &wait, TASK_UNINTERRUPTIBLE);
-		i = drbd_find_overlap(&device->write_requests, sector, size);
-		if (!i)
+		drbd_for_each_overlap(i, &device->write_requests, sector, size) {
+			/* Ignore, if already completed to upper layers. */
+			if (i->completed)
+				continue;
+			/* Handle the first found overlap.  After the schedule
+			 * we have to restart the tree walk. */
+			break;
+		}
+		if (!i)	/* if any */
 			break;
+
 		/* Indicate to wake up device->misc_wait on progress.  */
+		prepare_to_wait(&device->misc_wait, &wait, TASK_UNINTERRUPTIBLE);
 		i->waiting = true;
 		spin_unlock_irq(&device->resource->req_lock);
 		schedule();
@@ -995,7 +1000,7 @@ static void complete_conflicting_writes(struct drbd_request *req)
 	finish_wait(&device->misc_wait, &wait);
 }
 
-/* called within req_lock and rcu_read_lock() */
+/* called within req_lock */
 static void maybe_pull_ahead(struct drbd_device *device)
 {
 	struct drbd_connection *connection = first_peer_device(device)->connection;
@@ -1132,7 +1137,7 @@ static int drbd_process_write_request(struct drbd_request *req)
 	 * replicating, in which case there is no point. */
 	if (unlikely(req->i.size == 0)) {
 		/* The only size==0 bios we expect are empty flushes. */
-		D_ASSERT(device, req->master_bio->bi_rw & REQ_FLUSH);
+		D_ASSERT(device, req->master_bio->bi_rw & REQ_PREFLUSH);
 		if (remote)
 			_req_mod(req, QUEUE_AS_DRBD_BARRIER);
 		return remote;
@@ -1152,12 +1157,29 @@ static int drbd_process_write_request(struct drbd_request *req)
 	return remote;
 }
 
+static void drbd_process_discard_req(struct drbd_request *req)
+{
+	int err = drbd_issue_discard_or_zero_out(req->device,
+				req->i.sector, req->i.size >> 9, true);
+
+	if (err)
+		req->private_bio->bi_error = -EIO;
+	bio_endio(req->private_bio);
+}
+
 static void
 drbd_submit_req_private_bio(struct drbd_request *req)
 {
 	struct drbd_device *device = req->device;
 	struct bio *bio = req->private_bio;
-	const int rw = bio_rw(bio);
+	unsigned int type;
+
+	if (bio_op(bio) != REQ_OP_READ)
+		type = DRBD_FAULT_DT_WR;
+	else if (bio->bi_rw & REQ_RAHEAD)
+		type = DRBD_FAULT_DT_RA;
+	else
+		type = DRBD_FAULT_DT_RD;
 
 	bio->bi_bdev = device->ldev->backing_bdev;
 
@@ -1167,11 +1189,10 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 	 * stable storage, and this is a WRITE, we may not even submit
 	 * this bio. */
 	if (get_ldev(device)) {
-		if (drbd_insert_fault(device,
-				      rw == WRITE ? DRBD_FAULT_DT_WR
-				    : rw == READ  ? DRBD_FAULT_DT_RD
-				    :               DRBD_FAULT_DT_RA))
+		if (drbd_insert_fault(device, type))
 			bio_io_error(bio);
+		else if (bio_op(bio) == REQ_OP_DISCARD)
+			drbd_process_discard_req(req);
 		else
 			generic_make_request(bio);
 		put_ldev(device);
@@ -1223,24 +1244,45 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 	/* Update disk stats */
 	_drbd_start_io_acct(device, req);
 
+	/* process discards always from our submitter thread */
+	if (bio_op(bio) & REQ_OP_DISCARD)
+		goto queue_for_submitter_thread;
+
 	if (rw == WRITE && req->private_bio && req->i.size
 	&& !test_bit(AL_SUSPENDED, &device->flags)) {
-		if (!drbd_al_begin_io_fastpath(device, &req->i)) {
-			atomic_inc(&device->ap_actlog_cnt);
-			drbd_queue_write(device, req);
-			return NULL;
-		}
+		if (!drbd_al_begin_io_fastpath(device, &req->i))
+			goto queue_for_submitter_thread;
 		req->rq_state |= RQ_IN_ACT_LOG;
 		req->in_actlog_jif = jiffies;
 	}
-
 	return req;
+
+ queue_for_submitter_thread:
+	atomic_inc(&device->ap_actlog_cnt);
+	drbd_queue_write(device, req);
+	return NULL;
+}
+
+/* Require at least one path to current data.
+ * We don't want to allow writes on C_STANDALONE D_INCONSISTENT:
+ * We would not allow to read what was written,
+ * we would not have bumped the data generation uuids,
+ * we would cause data divergence for all the wrong reasons.
+ *
+ * If we don't see at least one D_UP_TO_DATE, we will fail this request,
+ * which either returns EIO, or, if OND_SUSPEND_IO is set, suspends IO,
+ * and queues for retry later.
+ */
+static bool may_do_writes(struct drbd_device *device)
+{
+	const union drbd_dev_state s = device->state;
+	return s.disk == D_UP_TO_DATE || s.pdsk == D_UP_TO_DATE;
 }
 
 static void drbd_send_and_submit(struct drbd_device *device, struct drbd_request *req)
 {
 	struct drbd_resource *resource = device->resource;
-	const int rw = bio_rw(req->master_bio);
+	const int rw = bio_data_dir(req->master_bio);
 	struct bio_and_error m = { NULL, };
 	bool no_remote = false;
 	bool submit_private_bio = false;
@@ -1270,7 +1312,7 @@ static void drbd_send_and_submit(struct drbd_device *device, struct drbd_request
 		goto out;
 	}
 
-	/* We fail READ/READA early, if we can not serve it.
+	/* We fail READ early, if we can not serve it.
 	 * We must do this before req is registered on any lists.
 	 * Otherwise, drbd_req_complete() will queue failed READ for retry. */
 	if (rw != WRITE) {
@@ -1291,6 +1333,12 @@ static void drbd_send_and_submit(struct drbd_device *device, struct drbd_request
 	}
 
 	if (rw == WRITE) {
+		if (req->private_bio && !may_do_writes(device)) {
+			bio_put(req->private_bio);
+			req->private_bio = NULL;
+			put_ldev(device);
+			goto nodata;
+		}
 		if (!drbd_process_write_request(req))
 			no_remote = true;
 	} else {
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index bb2ef78165e5..eb49e7f2da91 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -206,6 +206,8 @@ enum drbd_req_state_bits {
 
 	/* Set when this is a write, clear for a read */
 	__RQ_WRITE,
+	__RQ_WSAME,
+	__RQ_UNMAP,
 
 	/* Should call drbd_al_complete_io() for this request... */
 	__RQ_IN_ACT_LOG,
@@ -241,10 +243,11 @@ enum drbd_req_state_bits {
 #define RQ_NET_OK          (1UL << __RQ_NET_OK)
 #define RQ_NET_SIS         (1UL << __RQ_NET_SIS)
 
-/* 0x1f8 */
 #define RQ_NET_MASK        (((1UL << __RQ_NET_MAX)-1) & ~RQ_LOCAL_MASK)
 
 #define RQ_WRITE           (1UL << __RQ_WRITE)
+#define RQ_WSAME           (1UL << __RQ_WSAME)
+#define RQ_UNMAP           (1UL << __RQ_UNMAP)
 #define RQ_IN_ACT_LOG      (1UL << __RQ_IN_ACT_LOG)
 #define RQ_POSTPONED	   (1UL << __RQ_POSTPONED)
 #define RQ_COMPLETION_SUSP (1UL << __RQ_COMPLETION_SUSP)
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 5a7ef7873b67..eea0c4aec978 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -814,7 +814,7 @@ is_valid_state(struct drbd_device *device, union drbd_state ns)
 	}
 
 	if (rv <= 0)
-		/* already found a reason to abort */;
+		goto out; /* already found a reason to abort */
 	else if (ns.role == R_SECONDARY && device->open_cnt)
 		rv = SS_DEVICE_IN_USE;
 
@@ -862,6 +862,7 @@ is_valid_state(struct drbd_device *device, union drbd_state ns)
 	else if (ns.conn >= C_CONNECTED && ns.pdsk == D_UNKNOWN)
 		rv = SS_CONNECTED_OUTDATES;
 
+out:
 	rcu_read_unlock();
 
 	return rv;
@@ -906,6 +907,15 @@ is_valid_soft_transition(union drbd_state os, union drbd_state ns, struct drbd_c
 	      (ns.conn >= C_CONNECTED && os.conn == C_WF_REPORT_PARAMS)))
 		rv = SS_IN_TRANSIENT_STATE;
 
+	/* Do not promote during resync handshake triggered by "force primary".
+	 * This is a hack. It should really be rejected by the peer during the
+	 * cluster wide state change request. */
+	if (os.role != R_PRIMARY && ns.role == R_PRIMARY
+		&& ns.pdsk == D_UP_TO_DATE
+		&& ns.disk != D_UP_TO_DATE && ns.disk != D_DISKLESS
+		&& (ns.conn <= C_WF_SYNC_UUID || ns.conn != os.conn))
+			rv = SS_IN_TRANSIENT_STATE;
+
 	if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED)
 		rv = SS_NEED_CONNECTION;
 
@@ -1628,6 +1638,26 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
 #undef REMEMBER_STATE_CHANGE
 }
 
+/* takes old and new peer disk state */
+static bool lost_contact_to_peer_data(enum drbd_disk_state os, enum drbd_disk_state ns)
+{
+	if ((os >= D_INCONSISTENT && os != D_UNKNOWN && os != D_OUTDATED)
+	&&  (ns < D_INCONSISTENT || ns == D_UNKNOWN || ns == D_OUTDATED))
+		return true;
+
+	/* Scenario, starting with normal operation
+	 * Connected Primary/Secondary UpToDate/UpToDate
+	 * NetworkFailure Primary/Unknown UpToDate/DUnknown (frozen)
+	 * ...
+	 * Connected Primary/Secondary UpToDate/Diskless (resumed; needs to bump uuid!)
+	 */
+	if (os == D_UNKNOWN
+	&&  (ns == D_DISKLESS || ns == D_FAILED || ns == D_OUTDATED))
+		return true;
+
+	return false;
+}
+
 /**
  * after_state_ch() - Perform after state change actions that may sleep
  * @device:	DRBD device.
@@ -1675,7 +1705,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 			what = RESEND;
 
 		if ((os.disk == D_ATTACHING || os.disk == D_NEGOTIATING) &&
-		    conn_lowest_disk(connection) > D_NEGOTIATING)
+		    conn_lowest_disk(connection) == D_UP_TO_DATE)
 			what = RESTART_FROZEN_DISK_IO;
 
 		if (resource->susp_nod && what != NOTHING) {
@@ -1699,6 +1729,13 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 			idr_for_each_entry(&connection->peer_devices, peer_device, vnr)
 				clear_bit(NEW_CUR_UUID, &peer_device->device->flags);
 			rcu_read_unlock();
+
+			/* We should actively create a new uuid, _before_
+			 * we resume/resent, if the peer is diskless
+			 * (recovery from a multiple error scenario).
+			 * Currently, this happens with a slight delay
+			 * below when checking lost_contact_to_peer_data() ...
+			 */
 			_tl_restart(connection, RESEND);
 			_conn_request_state(connection,
 					    (union drbd_state) { { .susp_fen = 1 } },
@@ -1742,12 +1779,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 				BM_LOCKED_TEST_ALLOWED);
 
 	/* Lost contact to peer's copy of the data */
-	if ((os.pdsk >= D_INCONSISTENT &&
-	     os.pdsk != D_UNKNOWN &&
-	     os.pdsk != D_OUTDATED)
-	&&  (ns.pdsk < D_INCONSISTENT ||
-	     ns.pdsk == D_UNKNOWN ||
-	     ns.pdsk == D_OUTDATED)) {
+	if (lost_contact_to_peer_data(os.pdsk, ns.pdsk)) {
 		if (get_ldev(device)) {
 			if ((ns.role == R_PRIMARY || ns.peer == R_PRIMARY) &&
 			    device->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) {
@@ -1934,12 +1966,17 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 
 	/* This triggers bitmap writeout of potentially still unwritten pages
 	 * if the resync finished cleanly, or aborted because of peer disk
-	 * failure, or because of connection loss.
+	 * failure, or on transition from resync back to AHEAD/BEHIND.
+	 *
+	 * Connection loss is handled in drbd_disconnected() by the receiver.
+	 *
 	 * For resync aborted because of local disk failure, we cannot do
 	 * any bitmap writeout anymore.
+	 *
 	 * No harm done if some bits change during this phase.
 	 */
-	if (os.conn > C_CONNECTED && ns.conn <= C_CONNECTED && get_ldev(device)) {
+	if ((os.conn > C_CONNECTED && os.conn < C_AHEAD) &&
+	    (ns.conn == C_CONNECTED || ns.conn >= C_AHEAD) && get_ldev(device)) {
 		drbd_queue_bitmap_io(device, &drbd_bm_write_copy_pages, NULL,
 			"write from resync_finished", BM_LOCKED_CHANGE_ALLOWED);
 		put_ldev(device);
@@ -2160,9 +2197,7 @@ conn_set_state(struct drbd_connection *connection, union drbd_state mask, union
 			ns.disk = os.disk;
 
 		rv = _drbd_set_state(device, ns, flags, NULL);
-		if (rv < SS_SUCCESS)
-			BUG();
-
+		BUG_ON(rv < SS_SUCCESS);
 		ns.i = device->state.i;
 		ns_max.role = max_role(ns.role, ns_max.role);
 		ns_max.peer = max_role(ns.peer, ns_max.peer);
diff --git a/drivers/block/drbd/drbd_state.h b/drivers/block/drbd/drbd_state.h
index bd989536f888..6c9d5d4a8a75 100644
--- a/drivers/block/drbd/drbd_state.h
+++ b/drivers/block/drbd/drbd_state.h
@@ -140,7 +140,7 @@ extern void drbd_resume_al(struct drbd_device *device);
 extern bool conn_all_vols_unconf(struct drbd_connection *connection);
 
 /**
- * drbd_request_state() - Reqest a state change
+ * drbd_request_state() - Request a state change
  * @device:	DRBD device.
  * @mask:	mask of state bits to change.
  * @val:	value of new state bits.
diff --git a/drivers/block/drbd/drbd_strings.c b/drivers/block/drbd/drbd_strings.c
index 80b0f63c7075..0eeab14776e9 100644
--- a/drivers/block/drbd/drbd_strings.c
+++ b/drivers/block/drbd/drbd_strings.c
@@ -26,7 +26,7 @@
 #include <linux/drbd.h>
 #include "drbd_strings.h"
 
-static const char *drbd_conn_s_names[] = {
+static const char * const drbd_conn_s_names[] = {
 	[C_STANDALONE]       = "StandAlone",
 	[C_DISCONNECTING]    = "Disconnecting",
 	[C_UNCONNECTED]      = "Unconnected",
@@ -53,13 +53,13 @@ static const char *drbd_conn_s_names[] = {
 	[C_BEHIND]           = "Behind",
 };
 
-static const char *drbd_role_s_names[] = {
+static const char * const drbd_role_s_names[] = {
 	[R_PRIMARY]   = "Primary",
 	[R_SECONDARY] = "Secondary",
 	[R_UNKNOWN]   = "Unknown"
 };
 
-static const char *drbd_disk_s_names[] = {
+static const char * const drbd_disk_s_names[] = {
 	[D_DISKLESS]     = "Diskless",
 	[D_ATTACHING]    = "Attaching",
 	[D_FAILED]       = "Failed",
@@ -71,7 +71,7 @@ static const char *drbd_disk_s_names[] = {
 	[D_UP_TO_DATE]   = "UpToDate",
 };
 
-static const char *drbd_state_sw_errors[] = {
+static const char * const drbd_state_sw_errors[] = {
 	[-SS_TWO_PRIMARIES] = "Multiple primaries not allowed by config",
 	[-SS_NO_UP_TO_DATE_DISK] = "Need access to UpToDate data",
 	[-SS_NO_LOCAL_DISK] = "Can not resync without local disk",
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 4d87499f0d54..35dbb3dca47e 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -173,8 +173,8 @@ void drbd_peer_request_endio(struct bio *bio)
 {
 	struct drbd_peer_request *peer_req = bio->bi_private;
 	struct drbd_device *device = peer_req->peer_device->device;
-	int is_write = bio_data_dir(bio) == WRITE;
-	int is_discard = !!(bio->bi_rw & REQ_DISCARD);
+	bool is_write = bio_data_dir(bio) == WRITE;
+	bool is_discard = !!(bio_op(bio) == REQ_OP_DISCARD);
 
 	if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
@@ -248,18 +248,26 @@ void drbd_request_endio(struct bio *bio)
 
 	/* to avoid recursion in __req_mod */
 	if (unlikely(bio->bi_error)) {
-		if (bio->bi_rw & REQ_DISCARD)
-			what = (bio->bi_error == -EOPNOTSUPP)
-				? DISCARD_COMPLETED_NOTSUPP
-				: DISCARD_COMPLETED_WITH_ERROR;
-		else
-			what = (bio_data_dir(bio) == WRITE)
-			? WRITE_COMPLETED_WITH_ERROR
-			: (bio_rw(bio) == READ)
-			  ? READ_COMPLETED_WITH_ERROR
-			  : READ_AHEAD_COMPLETED_WITH_ERROR;
-	} else
+		switch (bio_op(bio)) {
+		case REQ_OP_DISCARD:
+			if (bio->bi_error == -EOPNOTSUPP)
+				what = DISCARD_COMPLETED_NOTSUPP;
+			else
+				what = DISCARD_COMPLETED_WITH_ERROR;
+			break;
+		case REQ_OP_READ:
+			if (bio->bi_rw & REQ_RAHEAD)
+				what = READ_AHEAD_COMPLETED_WITH_ERROR;
+			else
+				what = READ_COMPLETED_WITH_ERROR;
+			break;
+		default:
+			what = WRITE_COMPLETED_WITH_ERROR;
+			break;
+		}
+	} else {
 		what = COMPLETED_OK;
+	}
 
 	bio_put(req->private_bio);
 	req->private_bio = ERR_PTR(bio->bi_error);
@@ -320,6 +328,10 @@ void drbd_csum_bio(struct crypto_ahash *tfm, struct bio *bio, void *digest)
 		sg_set_page(&sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
 		ahash_request_set_crypt(req, &sg, NULL, sg.length);
 		crypto_ahash_update(req);
+		/* REQ_OP_WRITE_SAME has only one segment,
+		 * checksum the payload only once. */
+		if (bio_op(bio) == REQ_OP_WRITE_SAME)
+			break;
 	}
 	ahash_request_set_crypt(req, NULL, digest, 0);
 	crypto_ahash_final(req);
@@ -387,7 +399,7 @@ static int read_for_csum(struct drbd_peer_device *peer_device, sector_t sector,
 	/* GFP_TRY, because if there is no memory available right now, this may
 	 * be rescheduled for later. It is "only" background resync, after all. */
 	peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER /* unused */, sector,
-				       size, true /* has real payload */, GFP_TRY);
+				       size, size, GFP_TRY);
 	if (!peer_req)
 		goto defer;
 
@@ -397,7 +409,8 @@ static int read_for_csum(struct drbd_peer_device *peer_device, sector_t sector,
 	spin_unlock_irq(&device->resource->req_lock);
 
 	atomic_add(size >> 9, &device->rs_sect_ev);
-	if (drbd_submit_peer_request(device, peer_req, READ, DRBD_FAULT_RS_RD) == 0)
+	if (drbd_submit_peer_request(device, peer_req, REQ_OP_READ, 0,
+				     DRBD_FAULT_RS_RD) == 0)
 		return 0;
 
 	/* If it failed because of ENOMEM, retry should help.  If it failed
@@ -582,6 +595,7 @@ static int make_resync_request(struct drbd_device *const device, int cancel)
 	int number, rollback_i, size;
 	int align, requeue = 0;
 	int i = 0;
+	int discard_granularity = 0;
 
 	if (unlikely(cancel))
 		return 0;
@@ -601,6 +615,12 @@ static int make_resync_request(struct drbd_device *const device, int cancel)
 		return 0;
 	}
 
+	if (connection->agreed_features & DRBD_FF_THIN_RESYNC) {
+		rcu_read_lock();
+		discard_granularity = rcu_dereference(device->ldev->disk_conf)->rs_discard_granularity;
+		rcu_read_unlock();
+	}
+
 	max_bio_size = queue_max_hw_sectors(device->rq_queue) << 9;
 	number = drbd_rs_number_requests(device);
 	if (number <= 0)
@@ -665,6 +685,9 @@ next_sector:
 			if (sector & ((1<<(align+3))-1))
 				break;
 
+			if (discard_granularity && size == discard_granularity)
+				break;
+
 			/* do not cross extent boundaries */
 			if (((bit+1) & BM_BLOCKS_PER_BM_EXT_MASK) == 0)
 				break;
@@ -711,7 +734,8 @@ next_sector:
 			int err;
 
 			inc_rs_pending(device);
-			err = drbd_send_drequest(peer_device, P_RS_DATA_REQUEST,
+			err = drbd_send_drequest(peer_device,
+						 size == discard_granularity ? P_RS_THIN_REQ : P_RS_DATA_REQUEST,
 						 sector, size, ID_SYNCER);
 			if (err) {
 				drbd_err(device, "drbd_send_drequest() failed, aborting...\n");
@@ -828,6 +852,7 @@ static void ping_peer(struct drbd_device *device)
 
 int drbd_resync_finished(struct drbd_device *device)
 {
+	struct drbd_connection *connection = first_peer_device(device)->connection;
 	unsigned long db, dt, dbdt;
 	unsigned long n_oos;
 	union drbd_state os, ns;
@@ -849,8 +874,7 @@ int drbd_resync_finished(struct drbd_device *device)
 		if (dw) {
 			dw->w.cb = w_resync_finished;
 			dw->device = device;
-			drbd_queue_work(&first_peer_device(device)->connection->sender_work,
-					&dw->w);
+			drbd_queue_work(&connection->sender_work, &dw->w);
 			return 1;
 		}
 		drbd_err(device, "Warn failed to drbd_rs_del_all() and to kmalloc(dw).\n");
@@ -963,6 +987,30 @@ int drbd_resync_finished(struct drbd_device *device)
 	_drbd_set_state(device, ns, CS_VERBOSE, NULL);
 out_unlock:
 	spin_unlock_irq(&device->resource->req_lock);
+
+	/* If we have been sync source, and have an effective fencing-policy,
+	 * once *all* volumes are back in sync, call "unfence". */
+	if (os.conn == C_SYNC_SOURCE) {
+		enum drbd_disk_state disk_state = D_MASK;
+		enum drbd_disk_state pdsk_state = D_MASK;
+		enum drbd_fencing_p fp = FP_DONT_CARE;
+
+		rcu_read_lock();
+		fp = rcu_dereference(device->ldev->disk_conf)->fencing;
+		if (fp != FP_DONT_CARE) {
+			struct drbd_peer_device *peer_device;
+			int vnr;
+			idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
+				struct drbd_device *device = peer_device->device;
+				disk_state = min_t(enum drbd_disk_state, disk_state, device->state.disk);
+				pdsk_state = min_t(enum drbd_disk_state, pdsk_state, device->state.pdsk);
+			}
+		}
+		rcu_read_unlock();
+		if (disk_state == D_UP_TO_DATE && pdsk_state == D_UP_TO_DATE)
+			conn_khelper(connection, "unfence-peer");
+	}
+
 	put_ldev(device);
 out:
 	device->rs_total  = 0;
@@ -999,7 +1047,6 @@ static void move_to_net_ee_or_free(struct drbd_device *device, struct drbd_peer_
 
 /**
  * w_e_end_data_req() - Worker callback, to send a P_DATA_REPLY packet in response to a P_DATA_REQUEST
- * @device:	DRBD device.
  * @w:		work object.
  * @cancel:	The connection will be closed anyways
  */
@@ -1035,6 +1082,30 @@ int w_e_end_data_req(struct drbd_work *w, int cancel)
 	return err;
 }
 
+static bool all_zero(struct drbd_peer_request *peer_req)
+{
+	struct page *page = peer_req->pages;
+	unsigned int len = peer_req->i.size;
+
+	page_chain_for_each(page) {
+		unsigned int l = min_t(unsigned int, len, PAGE_SIZE);
+		unsigned int i, words = l / sizeof(long);
+		unsigned long *d;
+
+		d = kmap_atomic(page);
+		for (i = 0; i < words; i++) {
+			if (d[i]) {
+				kunmap_atomic(d);
+				return false;
+			}
+		}
+		kunmap_atomic(d);
+		len -= l;
+	}
+
+	return true;
+}
+
 /**
  * w_e_end_rsdata_req() - Worker callback to send a P_RS_DATA_REPLY packet in response to a P_RS_DATA_REQUEST
  * @w:		work object.
@@ -1063,7 +1134,10 @@ int w_e_end_rsdata_req(struct drbd_work *w, int cancel)
 	} else if (likely((peer_req->flags & EE_WAS_ERROR) == 0)) {
 		if (likely(device->state.pdsk >= D_INCONSISTENT)) {
 			inc_rs_pending(device);
-			err = drbd_send_block(peer_device, P_RS_DATA_REPLY, peer_req);
+			if (peer_req->flags & EE_RS_THIN_REQ && all_zero(peer_req))
+				err = drbd_send_rs_deallocated(peer_device, peer_req);
+			else
+				err = drbd_send_block(peer_device, P_RS_DATA_REPLY, peer_req);
 		} else {
 			if (__ratelimit(&drbd_ratelimit_state))
 				drbd_err(device, "Not sending RSDataReply, "
@@ -1633,7 +1707,7 @@ static bool use_checksum_based_resync(struct drbd_connection *connection, struct
 	rcu_read_unlock();
 	return connection->agreed_pro_version >= 89 &&		/* supported? */
 		connection->csums_tfm &&			/* configured? */
-		(csums_after_crash_only == 0			/* use for each resync? */
+		(csums_after_crash_only == false		/* use for each resync? */
 		 || test_bit(CRASHED_PRIMARY, &device->flags));	/* or only after Primary crash? */
 }
 
@@ -1768,7 +1842,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 			device->bm_resync_fo = 0;
 			device->use_csums = use_checksum_based_resync(connection, device);
 		} else {
-			device->use_csums = 0;
+			device->use_csums = false;
 		}
 
 		/* Since protocol 96, we must serialize drbd_gen_and_send_sync_uuid
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 84708a5f8c52..c557057fe8ae 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3822,8 +3822,9 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive)
 	bio.bi_flags |= (1 << BIO_QUIET);
 	bio.bi_private = &cbdata;
 	bio.bi_end_io = floppy_rb0_cb;
+	bio_set_op_attrs(&bio, REQ_OP_READ, 0);
 
-	submit_bio(READ, &bio);
+	submit_bio(&bio);
 	process_fd_request();
 
 	init_completion(&cbdata.complete);
@@ -4349,8 +4350,7 @@ static int __init do_floppy_init(void)
 		/* to be cleaned up... */
 		disks[drive]->private_data = (void *)(long)drive;
 		disks[drive]->flags |= GENHD_FL_REMOVABLE;
-		disks[drive]->driverfs_dev = &floppy_device[drive].dev;
-		add_disk(disks[drive]);
+		device_add_disk(&floppy_device[drive].dev, disks[drive]);
 	}
 
 	return 0;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1fa8cc235977..075377eee0c0 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -447,7 +447,7 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
 
 static inline void handle_partial_read(struct loop_cmd *cmd, long bytes)
 {
-	if (bytes < 0 || (cmd->rq->cmd_flags & REQ_WRITE))
+	if (bytes < 0 || op_is_write(req_op(cmd->rq)))
 		return;
 
 	if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
@@ -541,10 +541,10 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 
 	pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
-	if (rq->cmd_flags & REQ_WRITE) {
-		if (rq->cmd_flags & REQ_FLUSH)
+	if (op_is_write(req_op(rq))) {
+		if (req_op(rq) == REQ_OP_FLUSH)
 			ret = lo_req_flush(lo, rq);
-		else if (rq->cmd_flags & REQ_DISCARD)
+		else if (req_op(rq) == REQ_OP_DISCARD)
 			ret = lo_discard(lo, rq, pos);
 		else if (lo->transfer)
 			ret = lo_write_transfer(lo, rq, pos);
@@ -1659,8 +1659,8 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (lo->lo_state != Lo_bound)
 		return -EIO;
 
-	if (lo->use_dio && !(cmd->rq->cmd_flags & (REQ_FLUSH |
-					REQ_DISCARD)))
+	if (lo->use_dio && (req_op(cmd->rq) != REQ_OP_FLUSH ||
+	    req_op(cmd->rq) == REQ_OP_DISCARD))
 		cmd->use_aio = true;
 	else
 		cmd->use_aio = false;
@@ -1672,7 +1672,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 static void loop_handle_cmd(struct loop_cmd *cmd)
 {
-	const bool write = cmd->rq->cmd_flags & REQ_WRITE;
+	const bool write = op_is_write(req_op(cmd->rq));
 	struct loop_device *lo = cmd->rq->q->queuedata;
 	int ret = 0;
 
@@ -1765,6 +1765,7 @@ static int loop_add(struct loop_device **l, int i)
 	 */
 	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 
+	err = -ENOMEM;
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
index 145ce2aa2e78..e937fcf71769 100644
--- a/drivers/block/mg_disk.c
+++ b/drivers/block/mg_disk.c
@@ -687,15 +687,13 @@ static unsigned int mg_issue_req(struct request *req,
 		unsigned int sect_num,
 		unsigned int sect_cnt)
 {
-	switch (rq_data_dir(req)) {
-	case READ:
+	if (rq_data_dir(req) == READ) {
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr)
 				!= MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return host->error;
 		}
-		break;
-	case WRITE:
+	} else {
 		/* TODO : handler */
 		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
@@ -714,7 +712,6 @@ static unsigned int mg_issue_req(struct request *req,
 		mod_timer(&host->timer, jiffies + 3 * HZ);
 		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
-		break;
 	}
 	return MG_ERR_NONE;
 }
@@ -1018,7 +1015,7 @@ probe_err_7:
 probe_err_6:
 	blk_cleanup_queue(host->breq);
 probe_err_5:
-	unregister_blkdev(MG_DISK_MAJ, MG_DISK_NAME);
+	unregister_blkdev(host->major, MG_DISK_NAME);
 probe_err_4:
 	if (!prv_data->use_polling)
 		free_irq(host->irq, host);
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 6053e4659fa2..2aca98e8e427 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3765,7 +3765,7 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 			return -ENODATA;
 	}
 
-	if (rq->cmd_flags & REQ_DISCARD) {
+	if (req_op(rq) == REQ_OP_DISCARD) {
 		int err;
 
 		err = mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq));
@@ -3956,7 +3956,6 @@ static int mtip_block_initialize(struct driver_data *dd)
 	if (rv)
 		goto disk_index_error;
 
-	dd->disk->driverfs_dev	= &dd->pdev->dev;
 	dd->disk->major		= dd->major;
 	dd->disk->first_minor	= index * MTIP_MAX_MINORS;
 	dd->disk->minors 	= MTIP_MAX_MINORS;
@@ -4008,7 +4007,7 @@ skip_create_disk:
 
 	/*
 	 * if rebuild pending, start the service thread, and delay the block
-	 * queue creation and add_disk()
+	 * queue creation and device_add_disk()
 	 */
 	if (wait_for_rebuild == MTIP_FTL_REBUILD_MAGIC)
 		goto start_service_thread;
@@ -4042,7 +4041,7 @@ skip_create_disk:
 	set_capacity(dd->disk, capacity);
 
 	/* Enable the block device and add it to /dev */
-	add_disk(dd->disk);
+	device_add_disk(&dd->pdev->dev, dd->disk);
 
 	dd->bdev = bdget_disk(dd->disk, 0);
 	/*
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 6a48ed41963f..6f55b262b5ce 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -282,9 +282,9 @@ static int nbd_send_req(struct nbd_device *nbd, struct request *req)
 
 	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
 		type = NBD_CMD_DISC;
-	else if (req->cmd_flags & REQ_DISCARD)
+	else if (req_op(req) == REQ_OP_DISCARD)
 		type = NBD_CMD_TRIM;
-	else if (req->cmd_flags & REQ_FLUSH)
+	else if (req_op(req) == REQ_OP_FLUSH)
 		type = NBD_CMD_FLUSH;
 	else if (rq_data_dir(req) == WRITE)
 		type = NBD_CMD_WRITE;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index cab97593ba54..75a7f88d6717 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -448,7 +448,7 @@ static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	struct request *rq;
 	struct bio *bio = rqd->bio;
 
-	rq = blk_mq_alloc_request(q, bio_rw(bio), 0);
+	rq = blk_mq_alloc_request(q, bio_data_dir(bio), 0);
 	if (IS_ERR(rq))
 		return -ENOMEM;
 
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index c2854a2bfdb0..92900f5f0b47 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -321,7 +321,7 @@ static void osdblk_rq_fn(struct request_queue *q)
 		 * driver-specific, etc.
 		 */
 
-		do_flush = rq->cmd_flags & REQ_FLUSH;
+		do_flush = (req_op(rq) == REQ_OP_FLUSH);
 		do_write = (rq_data_dir(rq) == WRITE);
 
 		if (!do_flush) { /* osd_flush does not use a bio */
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index d06c62eccdf0..9393bc730acf 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -1074,7 +1074,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 			BUG();
 
 		atomic_inc(&pkt->io_wait);
-		bio->bi_rw = READ;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		pkt_queue_bio(pd, bio);
 		frames_read++;
 	}
@@ -1336,7 +1336,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 
 	/* Start the write request */
 	atomic_set(&pkt->io_wait, 1);
-	pkt->w_bio->bi_rw = WRITE;
+	bio_set_op_attrs(pkt->w_bio, REQ_OP_WRITE, 0);
 	pkt_queue_bio(pd, pkt->w_bio);
 }
 
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 4b7e405830d7..76f33c84ce3d 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -196,7 +196,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
 	while ((req = blk_fetch_request(q))) {
-		if (req->cmd_flags & REQ_FLUSH) {
+		if (req_op(req) == REQ_OP_FLUSH) {
 			if (ps3disk_submit_flush_request(dev, req))
 				break;
 		} else if (req->cmd_type == REQ_TYPE_FS) {
@@ -256,7 +256,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 		return IRQ_HANDLED;
 	}
 
-	if (req->cmd_flags & REQ_FLUSH) {
+	if (req_op(req) == REQ_OP_FLUSH) {
 		read = 0;
 		op = "flush";
 	} else {
@@ -487,7 +487,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	gendisk->fops = &ps3disk_fops;
 	gendisk->queue = queue;
 	gendisk->private_data = dev;
-	gendisk->driverfs_dev = &dev->sbd.core;
 	snprintf(gendisk->disk_name, sizeof(gendisk->disk_name), PS3DISK_NAME,
 		 devidx+'a');
 	priv->blocking_factor = dev->blk_size >> 9;
@@ -499,7 +498,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 		 gendisk->disk_name, priv->model, priv->raw_capacity >> 11,
 		 get_capacity(gendisk) >> 11);
 
-	add_disk(gendisk);
+	device_add_disk(&dev->sbd.core, gendisk);
 	return 0;
 
 fail_cleanup_queue:
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 56847fcda086..456b4fe21559 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -773,14 +773,13 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
 	gendisk->fops = &ps3vram_fops;
 	gendisk->queue = queue;
 	gendisk->private_data = dev;
-	gendisk->driverfs_dev = &dev->core;
 	strlcpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name));
 	set_capacity(gendisk, priv->size >> 9);
 
 	dev_info(&dev->core, "%s: Using %lu MiB of GPU memory\n",
 		 gendisk->disk_name, get_capacity(gendisk) >> 11);
 
-	add_disk(gendisk);
+	device_add_disk(&dev->core, gendisk);
 	return 0;
 
 fail_cleanup_queue:
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 81666a56415e..450662055d97 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3286,9 +3286,9 @@ static void rbd_queue_workfn(struct work_struct *work)
 		goto err;
 	}
 
-	if (rq->cmd_flags & REQ_DISCARD)
+	if (req_op(rq) == REQ_OP_DISCARD)
 		op_type = OBJ_OP_DISCARD;
-	else if (rq->cmd_flags & REQ_WRITE)
+	else if (req_op(rq) == REQ_OP_WRITE)
 		op_type = OBJ_OP_WRITE;
 	else
 		op_type = OBJ_OP_READ;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index e1b8b7061d2f..f81d70b39d10 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -230,8 +230,7 @@ int rsxx_attach_dev(struct rsxx_cardinfo *card)
 			set_capacity(card->gendisk, card->size8 >> 9);
 		else
 			set_capacity(card->gendisk, 0);
-		add_disk(card->gendisk);
-
+		device_add_disk(CARD_TO_DEV(card), card->gendisk);
 		card->bdev_attached = 1;
 	}
 
@@ -308,7 +307,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
 
 	snprintf(card->gendisk->disk_name, sizeof(card->gendisk->disk_name),
 		 "rsxx%d", card->disk_id);
-	card->gendisk->driverfs_dev = &card->dev->dev;
 	card->gendisk->major = card->major;
 	card->gendisk->first_minor = 0;
 	card->gendisk->fops = &rsxx_fops;
diff --git a/drivers/block/rsxx/dma.c b/drivers/block/rsxx/dma.c
index cf8cd293abb5..5a20385f87d0 100644
--- a/drivers/block/rsxx/dma.c
+++ b/drivers/block/rsxx/dma.c
@@ -705,7 +705,7 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 		dma_cnt[i] = 0;
 	}
 
-	if (bio->bi_rw & REQ_DISCARD) {
+	if (bio_op(bio) == REQ_OP_DISCARD) {
 		bv_len = bio->bi_iter.bi_size;
 
 		while (bv_len > 0) {
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 910e065918af..3822eae102db 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -597,7 +597,7 @@ static void skd_request_fn(struct request_queue *q)
 		data_dir = rq_data_dir(req);
 		io_flags = req->cmd_flags;
 
-		if (io_flags & REQ_FLUSH)
+		if (req_op(req) == REQ_OP_FLUSH)
 			flush++;
 
 		if (io_flags & REQ_FUA)
@@ -4690,10 +4690,10 @@ static int skd_bdev_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return -EIO;
 }
 
-static int skd_bdev_attach(struct skd_device *skdev)
+static int skd_bdev_attach(struct device *parent, struct skd_device *skdev)
 {
 	pr_debug("%s:%s:%d add_disk\n", skdev->name, __func__, __LINE__);
-	add_disk(skdev->disk);
+	device_add_disk(parent, skdev->disk);
 	return 0;
 }
 
@@ -4812,8 +4812,6 @@ static int skd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, skdev);
 
-	skdev->disk->driverfs_dev = &pdev->dev;
-
 	for (i = 0; i < SKD_MAX_BARS; i++) {
 		skdev->mem_phys[i] = pci_resource_start(pdev, i);
 		skdev->mem_size[i] = (u32)pci_resource_len(pdev, i);
@@ -4851,7 +4849,7 @@ static int skd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 					      (SKD_START_WAIT_SECONDS * HZ));
 	if (skdev->gendisk_on > 0) {
 		/* device came on-line after reset */
-		skd_bdev_attach(skdev);
+		skd_bdev_attach(&pdev->dev, skdev);
 		rc = 0;
 	} else {
 		/* we timed out, something is wrong with the device,
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 4b911ed96ea3..cab157331c4e 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -804,7 +804,6 @@ static int probe_disk(struct vdc_port *port)
 	g->fops = &vdc_fops;
 	g->queue = q;
 	g->private_data = port;
-	g->driverfs_dev = &port->vio.vdev->dev;
 
 	set_capacity(g, port->vdisk_size);
 
@@ -835,7 +834,7 @@ static int probe_disk(struct vdc_port *port)
 	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
 	       port->vio.ver.major, port->vio.ver.minor);
 
-	add_disk(g);
+	device_add_disk(&port->vio.vdev->dev, g);
 
 	return 0;
 }
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 7939b9f87441..d0a3e6d4515f 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -344,7 +344,6 @@ static int add_bio(struct cardinfo *card)
 	int offset;
 	struct bio *bio;
 	struct bio_vec vec;
-	int rw;
 
 	bio = card->currentbio;
 	if (!bio && card->bio) {
@@ -359,7 +358,6 @@ static int add_bio(struct cardinfo *card)
 	if (!bio)
 		return 0;
 
-	rw = bio_rw(bio);
 	if (card->mm_pages[card->Ready].cnt >= DESC_PER_PAGE)
 		return 0;
 
@@ -369,7 +367,7 @@ static int add_bio(struct cardinfo *card)
 				  vec.bv_page,
 				  vec.bv_offset,
 				  vec.bv_len,
-				  (rw == READ) ?
+				  bio_op(bio) == REQ_OP_READ ?
 				  PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE);
 
 	p = &card->mm_pages[card->Ready];
@@ -398,7 +396,7 @@ static int add_bio(struct cardinfo *card)
 					 DMASCR_CHAIN_EN |
 					 DMASCR_SEM_EN |
 					 pci_cmds);
-	if (rw == WRITE)
+	if (bio_op(bio) == REQ_OP_WRITE)
 		desc->control_bits |= cpu_to_le32(DMASCR_TRANSFER_READ);
 	desc->sem_control_bits = desc->control_bits;
 
@@ -462,7 +460,7 @@ static void process_page(unsigned long data)
 				le32_to_cpu(desc->local_addr)>>9,
 				le32_to_cpu(desc->transfer_size));
 			dump_dmastat(card, control);
-		} else if ((bio->bi_rw & REQ_WRITE) &&
+		} else if (op_is_write(bio_op(bio)) &&
 			   le32_to_cpu(desc->local_addr) >> 9 ==
 				card->init_size) {
 			card->init_size += le32_to_cpu(desc->transfer_size) >> 9;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 42758b52768c..1523e05c46fc 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -172,7 +172,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
 	vbr->req = req;
-	if (req->cmd_flags & REQ_FLUSH) {
+	if (req_op(req) == REQ_OP_FLUSH) {
 		vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
 		vbr->out_hdr.sector = 0;
 		vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
@@ -236,25 +236,22 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 static int virtblk_get_id(struct gendisk *disk, char *id_str)
 {
 	struct virtio_blk *vblk = disk->private_data;
+	struct request_queue *q = vblk->disk->queue;
 	struct request *req;
-	struct bio *bio;
 	int err;
 
-	bio = bio_map_kern(vblk->disk->queue, id_str, VIRTIO_BLK_ID_BYTES,
-			   GFP_KERNEL);
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	req = blk_make_request(vblk->disk->queue, bio, GFP_KERNEL);
-	if (IS_ERR(req)) {
-		bio_put(bio);
+	req = blk_get_request(q, READ, GFP_KERNEL);
+	if (IS_ERR(req))
 		return PTR_ERR(req);
-	}
-
 	req->cmd_type = REQ_TYPE_DRV_PRIV;
+
+	err = blk_rq_map_kern(q, req, id_str, VIRTIO_BLK_ID_BYTES, GFP_KERNEL);
+	if (err)
+		goto out;
+
 	err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+out:
 	blk_put_request(req);
-
 	return err;
 }
 
@@ -656,7 +653,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 	vblk->disk->first_minor = index_to_minor(index);
 	vblk->disk->private_data = vblk;
 	vblk->disk->fops = &virtblk_fops;
-	vblk->disk->driverfs_dev = &vdev->dev;
 	vblk->disk->flags |= GENHD_FL_EXT_DEVT;
 	vblk->index = index;
 
@@ -733,7 +729,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	add_disk(vblk->disk);
+	device_add_disk(&vdev->dev, vblk->disk);
 	err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial);
 	if (err)
 		goto out_del_disk;
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 4809c1501d7e..4a80ee752597 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -501,7 +501,7 @@ static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif,
 	struct xen_vbd *vbd = &blkif->vbd;
 	int rc = -EACCES;
 
-	if ((operation != READ) && vbd->readonly)
+	if ((operation != REQ_OP_READ) && vbd->readonly)
 		goto out;
 
 	if (likely(req->nr_sects)) {
@@ -1014,7 +1014,7 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring,
 	preq.sector_number = req->u.discard.sector_number;
 	preq.nr_sects      = req->u.discard.nr_sectors;
 
-	err = xen_vbd_translate(&preq, blkif, WRITE);
+	err = xen_vbd_translate(&preq, blkif, REQ_OP_WRITE);
 	if (err) {
 		pr_warn("access denied: DISCARD [%llu->%llu] on dev=%04x\n",
 			preq.sector_number,
@@ -1229,6 +1229,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 	struct bio **biolist = pending_req->biolist;
 	int i, nbio = 0;
 	int operation;
+	int operation_flags = 0;
 	struct blk_plug plug;
 	bool drain = false;
 	struct grant_page **pages = pending_req->segments;
@@ -1247,17 +1248,19 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 	switch (req_operation) {
 	case BLKIF_OP_READ:
 		ring->st_rd_req++;
-		operation = READ;
+		operation = REQ_OP_READ;
 		break;
 	case BLKIF_OP_WRITE:
 		ring->st_wr_req++;
-		operation = WRITE_ODIRECT;
+		operation = REQ_OP_WRITE;
+		operation_flags = WRITE_ODIRECT;
 		break;
 	case BLKIF_OP_WRITE_BARRIER:
 		drain = true;
 	case BLKIF_OP_FLUSH_DISKCACHE:
 		ring->st_f_req++;
-		operation = WRITE_FLUSH;
+		operation = REQ_OP_WRITE;
+		operation_flags = WRITE_FLUSH;
 		break;
 	default:
 		operation = 0; /* make gcc happy */
@@ -1269,7 +1272,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 	nseg = req->operation == BLKIF_OP_INDIRECT ?
 	       req->u.indirect.nr_segments : req->u.rw.nr_segments;
 
-	if (unlikely(nseg == 0 && operation != WRITE_FLUSH) ||
+	if (unlikely(nseg == 0 && operation_flags != WRITE_FLUSH) ||
 	    unlikely((req->operation != BLKIF_OP_INDIRECT) &&
 		     (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) ||
 	    unlikely((req->operation == BLKIF_OP_INDIRECT) &&
@@ -1310,7 +1313,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 
 	if (xen_vbd_translate(&preq, ring->blkif, operation) != 0) {
 		pr_debug("access denied: %s of [%llu,%llu] on dev=%04x\n",
-			 operation == READ ? "read" : "write",
+			 operation == REQ_OP_READ ? "read" : "write",
 			 preq.sector_number,
 			 preq.sector_number + preq.nr_sects,
 			 ring->blkif->vbd.pdevice);
@@ -1369,6 +1372,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 			bio->bi_private = pending_req;
 			bio->bi_end_io  = end_block_io_op;
 			bio->bi_iter.bi_sector  = preq.sector_number;
+			bio_set_op_attrs(bio, operation, operation_flags);
 		}
 
 		preq.sector_number += seg[i].nsec;
@@ -1376,7 +1380,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 
 	/* This will be hit if the operation was a flush or discard. */
 	if (!bio) {
-		BUG_ON(operation != WRITE_FLUSH);
+		BUG_ON(operation_flags != WRITE_FLUSH);
 
 		bio = bio_alloc(GFP_KERNEL, 0);
 		if (unlikely(bio == NULL))
@@ -1386,20 +1390,21 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 		bio->bi_bdev    = preq.bdev;
 		bio->bi_private = pending_req;
 		bio->bi_end_io  = end_block_io_op;
+		bio_set_op_attrs(bio, operation, operation_flags);
 	}
 
 	atomic_set(&pending_req->pendcnt, nbio);
 	blk_start_plug(&plug);
 
 	for (i = 0; i < nbio; i++)
-		submit_bio(operation, biolist[i]);
+		submit_bio(biolist[i]);
 
 	/* Let the I/Os go.. */
 	blk_finish_plug(&plug);
 
-	if (operation == READ)
+	if (operation == REQ_OP_READ)
 		ring->st_rd_sect += preq.nr_sects;
-	else if (operation & WRITE)
+	else if (operation == REQ_OP_WRITE)
 		ring->st_wr_sect += preq.nr_sects;
 
 	return 0;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 3355f1cdd4e5..2994cfa44c8a 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -480,7 +480,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags))
 		vbd->flush_support = true;
 
-	if (q && blk_queue_secdiscard(q))
+	if (q && blk_queue_secure_erase(q))
 		vbd->discard_secure = true;
 
 	pr_debug("Successful creation of handle=%04x (dom=%u)\n",
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index fcc5b4e0aef2..0b6682a33e3b 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -196,6 +196,7 @@ struct blkfront_info
 	unsigned int nr_ring_pages;
 	struct request_queue *rq;
 	unsigned int feature_flush;
+	unsigned int feature_fua;
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
 	unsigned int discard_granularity;
@@ -547,7 +548,7 @@ static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_inf
 	ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
 	ring_req->u.discard.id = id;
 	ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
-	if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+	if (req_op(req) == REQ_OP_SECURE_ERASE && info->feature_secdiscard)
 		ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
 	else
 		ring_req->u.discard.flag = 0;
@@ -746,7 +747,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		 * The indirect operation can only be a BLKIF_OP_READ or
 		 * BLKIF_OP_WRITE
 		 */
-		BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+		BUG_ON(req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA);
 		ring_req->operation = BLKIF_OP_INDIRECT;
 		ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
 			BLKIF_OP_WRITE : BLKIF_OP_READ;
@@ -758,7 +759,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		ring_req->u.rw.handle = info->handle;
 		ring_req->operation = rq_data_dir(req) ?
 			BLKIF_OP_WRITE : BLKIF_OP_READ;
-		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+		if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) {
 			/*
 			 * Ideally we can do an unordered flush-to-disk.
 			 * In case the backend onlysupports barriers, use that.
@@ -766,19 +767,14 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 			 * implement it the same way.  (It's also a FLUSH+FUA,
 			 * since it is guaranteed ordered WRT previous writes.)
 			 */
-			switch (info->feature_flush &
-				((REQ_FLUSH|REQ_FUA))) {
-			case REQ_FLUSH|REQ_FUA:
+			if (info->feature_flush && info->feature_fua)
 				ring_req->operation =
 					BLKIF_OP_WRITE_BARRIER;
-				break;
-			case REQ_FLUSH:
+			else if (info->feature_flush)
 				ring_req->operation =
 					BLKIF_OP_FLUSH_DISKCACHE;
-				break;
-			default:
+			else
 				ring_req->operation = 0;
-			}
 		}
 		ring_req->u.rw.nr_segments = num_grant;
 		if (unlikely(require_extra_req)) {
@@ -847,7 +843,8 @@ static int blkif_queue_request(struct request *req, struct blkfront_ring_info *r
 	if (unlikely(rinfo->dev_info->connected != BLKIF_STATE_CONNECTED))
 		return 1;
 
-	if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE)))
+	if (unlikely(req_op(req) == REQ_OP_DISCARD ||
+		     req_op(req) == REQ_OP_SECURE_ERASE))
 		return blkif_queue_discard_req(req, rinfo);
 	else
 		return blkif_queue_rw_req(req, rinfo);
@@ -867,10 +864,10 @@ static inline bool blkif_request_flush_invalid(struct request *req,
 					       struct blkfront_info *info)
 {
 	return ((req->cmd_type != REQ_TYPE_FS) ||
-		((req->cmd_flags & REQ_FLUSH) &&
-		 !(info->feature_flush & REQ_FLUSH)) ||
+		((req_op(req) == REQ_OP_FLUSH) &&
+		 !info->feature_flush) ||
 		((req->cmd_flags & REQ_FUA) &&
-		 !(info->feature_flush & REQ_FUA)));
+		 !info->feature_fua));
 }
 
 static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -955,7 +952,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 		rq->limits.discard_granularity = info->discard_granularity;
 		rq->limits.discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, rq);
+			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
@@ -981,24 +978,22 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 	return 0;
 }
 
-static const char *flush_info(unsigned int feature_flush)
+static const char *flush_info(struct blkfront_info *info)
 {
-	switch (feature_flush & ((REQ_FLUSH | REQ_FUA))) {
-	case REQ_FLUSH|REQ_FUA:
+	if (info->feature_flush && info->feature_fua)
 		return "barrier: enabled;";
-	case REQ_FLUSH:
+	else if (info->feature_flush)
 		return "flush diskcache: enabled;";
-	default:
+	else
 		return "barrier or flush: disabled;";
-	}
 }
 
 static void xlvbd_flush(struct blkfront_info *info)
 {
-	blk_queue_write_cache(info->rq, info->feature_flush & REQ_FLUSH,
-				info->feature_flush & REQ_FUA);
+	blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
+			      info->feature_fua ? true : false);
 	pr_info("blkfront: %s: %s %s %s %s %s\n",
-		info->gd->disk_name, flush_info(info->feature_flush),
+		info->gd->disk_name, flush_info(info),
 		"persistent grants:", info->feature_persistent ?
 		"enabled;" : "disabled;", "indirect descriptors:",
 		info->max_indirect_segments ? "enabled;" : "disabled;");
@@ -1139,7 +1134,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	gd->first_minor = minor;
 	gd->fops = &xlvbd_block_fops;
 	gd->private_data = info;
-	gd->driverfs_dev = &(info->xbdev->dev);
 	set_capacity(gd, capacity);
 
 	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
@@ -1597,7 +1591,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
-				queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
+				queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
 			}
 			blk_mq_complete_request(req, error);
 			break;
@@ -1617,6 +1611,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			if (unlikely(error)) {
 				if (error == -EOPNOTSUPP)
 					error = 0;
+				info->feature_fua = 0;
 				info->feature_flush = 0;
 				xlvbd_flush(info);
 			}
@@ -2064,7 +2059,7 @@ static int blkif_recover(struct blkfront_info *info)
 				bio_trim(cloned_bio, offset, size);
 				cloned_bio->bi_private = split_bio;
 				cloned_bio->bi_end_io = split_bio_end;
-				submit_bio(cloned_bio->bi_rw, cloned_bio);
+				submit_bio(cloned_bio);
 			}
 			/*
 			 * Now we have to wait for all those smaller bios to
@@ -2073,7 +2068,7 @@ static int blkif_recover(struct blkfront_info *info)
 			continue;
 		}
 		/* We don't need to split this bio */
-		submit_bio(bio->bi_rw, bio);
+		submit_bio(bio);
 	}
 
 	return 0;
@@ -2108,11 +2103,16 @@ static int blkfront_resume(struct xenbus_device *dev)
 			/*
 			 * Get the bios in the request so we can re-queue them.
 			 */
-			if (shadow[j].request->cmd_flags &
-					(REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+			if (req_op(shadow[i].request) == REQ_OP_FLUSH ||
+			    req_op(shadow[i].request) == REQ_OP_DISCARD ||
+			    req_op(shadow[i].request) == REQ_OP_SECURE_ERASE ||
+			    shadow[j].request->cmd_flags & REQ_FUA) {
 				/*
 				 * Flush operations don't contain bios, so
 				 * we need to requeue the whole request
+				 *
+				 * XXX: but this doesn't make any sense for a
+				 * write with the FUA flag set..
 				 */
 				list_add(&shadow[j].request->queuelist, &info->requests);
 				continue;
@@ -2298,6 +2298,7 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 	unsigned int indirect_segments;
 
 	info->feature_flush = 0;
+	info->feature_fua = 0;
 
 	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
 			"feature-barrier", "%d", &barrier,
@@ -2310,8 +2311,11 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 	 *
 	 * If there are barriers, then we use flush.
 	 */
-	if (!err && barrier)
-		info->feature_flush = REQ_FLUSH | REQ_FUA;
+	if (!err && barrier) {
+		info->feature_flush = 1;
+		info->feature_fua = 1;
+	}
+
 	/*
 	 * And if there is "feature-flush-cache" use that above
 	 * barriers.
@@ -2320,8 +2324,10 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 			"feature-flush-cache", "%d", &flush,
 			NULL);
 
-	if (!err && flush)
-		info->feature_flush = REQ_FLUSH;
+	if (!err && flush) {
+		info->feature_flush = 1;
+		info->feature_fua = 0;
+	}
 
 	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
 			"feature-discard", "%d", &discard,
@@ -2441,7 +2447,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	for (i = 0; i < info->nr_rings; i++)
 		kick_pending_request_queues(&info->rinfo[i]);
 
-	add_disk(info->gd);
+	device_add_disk(&info->xbdev->dev, info->gd);
 
 	info->is_ready = 1;
 }
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 9e2a83c3f19f..7454cf188c8e 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -882,7 +882,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 	offset = (bio->bi_iter.bi_sector &
 		  (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
 
-	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
 		zram_bio_discard(zram, index, offset, bio);
 		bio_endio(bio);
 		return;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 1b257ea9776a..5d475b3a0b2e 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2032,7 +2032,7 @@ static int cdrom_read_subchannel(struct cdrom_device_info *cdi,
 
 	init_cdrom_command(&cgc, buffer, 16, CGC_DATA_READ);
 	cgc.cmd[0] = GPCMD_READ_SUBCHANNEL;
-	cgc.cmd[1] = 2;     /* MSF addressing */
+	cgc.cmd[1] = subchnl->cdsc_format;/* MSF or LBA addressing */
 	cgc.cmd[2] = 0x40;  /* request subQ data */
 	cgc.cmd[3] = mcn ? 2 : 1;
 	cgc.cmd[8] = 16;
@@ -2041,17 +2041,27 @@ static int cdrom_read_subchannel(struct cdrom_device_info *cdi,
 		return ret;
 
 	subchnl->cdsc_audiostatus = cgc.buffer[1];
-	subchnl->cdsc_format = CDROM_MSF;
 	subchnl->cdsc_ctrl = cgc.buffer[5] & 0xf;
 	subchnl->cdsc_trk = cgc.buffer[6];
 	subchnl->cdsc_ind = cgc.buffer[7];
 
-	subchnl->cdsc_reladdr.msf.minute = cgc.buffer[13];
-	subchnl->cdsc_reladdr.msf.second = cgc.buffer[14];
-	subchnl->cdsc_reladdr.msf.frame = cgc.buffer[15];
-	subchnl->cdsc_absaddr.msf.minute = cgc.buffer[9];
-	subchnl->cdsc_absaddr.msf.second = cgc.buffer[10];
-	subchnl->cdsc_absaddr.msf.frame = cgc.buffer[11];
+	if (subchnl->cdsc_format == CDROM_LBA) {
+		subchnl->cdsc_absaddr.lba = ((cgc.buffer[8] << 24) |
+						(cgc.buffer[9] << 16) |
+						(cgc.buffer[10] << 8) |
+						(cgc.buffer[11]));
+		subchnl->cdsc_reladdr.lba = ((cgc.buffer[12] << 24) |
+						(cgc.buffer[13] << 16) |
+						(cgc.buffer[14] << 8) |
+						(cgc.buffer[15]));
+	} else {
+		subchnl->cdsc_reladdr.msf.minute = cgc.buffer[13];
+		subchnl->cdsc_reladdr.msf.second = cgc.buffer[14];
+		subchnl->cdsc_reladdr.msf.frame = cgc.buffer[15];
+		subchnl->cdsc_absaddr.msf.minute = cgc.buffer[9];
+		subchnl->cdsc_absaddr.msf.second = cgc.buffer[10];
+		subchnl->cdsc_absaddr.msf.frame = cgc.buffer[11];
+	}
 
 	return 0;
 }
@@ -3022,7 +3032,7 @@ static noinline int mmc_ioctl_cdrom_subchannel(struct cdrom_device_info *cdi,
 	if (!((requested == CDROM_MSF) ||
 	      (requested == CDROM_LBA)))
 		return -EINVAL;
-	q.cdsc_format = CDROM_MSF;
+
 	ret = cdrom_read_subchannel(cdi, &q, 0);
 	if (ret)
 		return ret;
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index ac51149e9777..56ad5a5936a9 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -90,7 +90,7 @@ config HW_RANDOM_BCM63XX
 
 config HW_RANDOM_BCM2835
 	tristate "Broadcom BCM2835 Random Number Generator support"
-	depends on ARCH_BCM2835
+	depends on ARCH_BCM2835 || ARCH_BCM_NSP || ARCH_BCM_5301X
 	default HW_RANDOM
 	---help---
 	  This driver provides kernel-side support for the Random Number
@@ -396,6 +396,20 @@ config HW_RANDOM_PIC32
 
 	  If unsure, say Y.
 
+config HW_RANDOM_MESON
+	tristate "Amlogic Meson Random Number Generator support"
+	depends on HW_RANDOM
+	depends on ARCH_MESON || COMPILE_TEST
+	default y
+	---help---
+	  This driver provides kernel-side support for the Random Number
+	  Generator hardware found on Amlogic Meson SoCs.
+
+	  To compile this driver as a module, choose M here. the
+	  module will be called meson-rng.
+
+	  If unsure, say Y.
+
 endif # HW_RANDOM
 
 config UML_RANDOM
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 63022b49f160..04bb0b03356f 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -34,3 +34,4 @@ obj-$(CONFIG_HW_RANDOM_ST) += st-rng.o
 obj-$(CONFIG_HW_RANDOM_XGENE) += xgene-rng.o
 obj-$(CONFIG_HW_RANDOM_STM32) += stm32-rng.o
 obj-$(CONFIG_HW_RANDOM_PIC32) += pic32-rng.o
+obj-$(CONFIG_HW_RANDOM_MESON) += meson-rng.o
diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
index 7192ec25f667..af2149273fe0 100644
--- a/drivers/char/hw_random/bcm2835-rng.c
+++ b/drivers/char/hw_random/bcm2835-rng.c
@@ -19,6 +19,7 @@
 #define RNG_CTRL	0x0
 #define RNG_STATUS	0x4
 #define RNG_DATA	0x8
+#define RNG_INT_MASK	0x10
 
 /* enable rng */
 #define RNG_RBGEN	0x1
@@ -26,10 +27,24 @@
 /* the initial numbers generated are "less random" so will be discarded */
 #define RNG_WARMUP_COUNT 0x40000
 
+#define RNG_INT_OFF	0x1
+
+static void __init nsp_rng_init(void __iomem *base)
+{
+	u32 val;
+
+	/* mask the interrupt */
+	val = readl(base + RNG_INT_MASK);
+	val |= RNG_INT_OFF;
+	writel(val, base + RNG_INT_MASK);
+}
+
 static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max,
 			       bool wait)
 {
 	void __iomem *rng_base = (void __iomem *)rng->priv;
+	u32 max_words = max / sizeof(u32);
+	u32 num_words, count;
 
 	while ((__raw_readl(rng_base + RNG_STATUS) >> 24) == 0) {
 		if (!wait)
@@ -37,8 +52,14 @@ static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max,
 		cpu_relax();
 	}
 
-	*(u32 *)buf = __raw_readl(rng_base + RNG_DATA);
-	return sizeof(u32);
+	num_words = readl(rng_base + RNG_STATUS) >> 24;
+	if (num_words > max_words)
+		num_words = max_words;
+
+	for (count = 0; count < num_words; count++)
+		((u32 *)buf)[count] = readl(rng_base + RNG_DATA);
+
+	return num_words * sizeof(u32);
 }
 
 static struct hwrng bcm2835_rng_ops = {
@@ -46,10 +67,19 @@ static struct hwrng bcm2835_rng_ops = {
 	.read	= bcm2835_rng_read,
 };
 
+static const struct of_device_id bcm2835_rng_of_match[] = {
+	{ .compatible = "brcm,bcm2835-rng"},
+	{ .compatible = "brcm,bcm-nsp-rng", .data = nsp_rng_init},
+	{ .compatible = "brcm,bcm5301x-rng", .data = nsp_rng_init},
+	{},
+};
+
 static int bcm2835_rng_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
+	void (*rng_setup)(void __iomem *base);
+	const struct of_device_id *rng_id;
 	void __iomem *rng_base;
 	int err;
 
@@ -61,6 +91,15 @@ static int bcm2835_rng_probe(struct platform_device *pdev)
 	}
 	bcm2835_rng_ops.priv = (unsigned long)rng_base;
 
+	rng_id = of_match_node(bcm2835_rng_of_match, np);
+	if (!rng_id)
+		return -EINVAL;
+
+	/* Check for rng init function, execute it */
+	rng_setup = rng_id->data;
+	if (rng_setup)
+		rng_setup(rng_base);
+
 	/* set warm-up count & enable */
 	__raw_writel(RNG_WARMUP_COUNT, rng_base + RNG_STATUS);
 	__raw_writel(RNG_RBGEN, rng_base + RNG_CTRL);
@@ -90,10 +129,6 @@ static int bcm2835_rng_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id bcm2835_rng_of_match[] = {
-	{ .compatible = "brcm,bcm2835-rng", },
-	{},
-};
 MODULE_DEVICE_TABLE(of, bcm2835_rng_of_match);
 
 static struct platform_driver bcm2835_rng_driver = {
diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c
index ed44561ea647..23d358553b21 100644
--- a/drivers/char/hw_random/exynos-rng.c
+++ b/drivers/char/hw_random/exynos-rng.c
@@ -45,12 +45,12 @@ struct exynos_rng {
 
 static u32 exynos_rng_readl(struct exynos_rng *rng, u32 offset)
 {
-	return	__raw_readl(rng->mem + offset);
+	return	readl_relaxed(rng->mem + offset);
 }
 
 static void exynos_rng_writel(struct exynos_rng *rng, u32 val, u32 offset)
 {
-	__raw_writel(val, rng->mem + offset);
+	writel_relaxed(val, rng->mem + offset);
 }
 
 static int exynos_rng_configure(struct exynos_rng *exynos_rng)
diff --git a/drivers/char/hw_random/meson-rng.c b/drivers/char/hw_random/meson-rng.c
new file mode 100644
index 000000000000..0cfd81bcaeac
--- /dev/null
+++ b/drivers/char/hw_random/meson-rng.c
@@ -0,0 +1,131 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ * Copyright (C) 2014 Amlogic, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ * Copyright (C) 2014 Amlogic, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/hw_random.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/of.h>
+
+#define RNG_DATA 0x00
+
+struct meson_rng_data {
+	void __iomem *base;
+	struct platform_device *pdev;
+	struct hwrng rng;
+};
+
+static int meson_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
+{
+	struct meson_rng_data *data =
+			container_of(rng, struct meson_rng_data, rng);
+
+	if (max < sizeof(u32))
+		return 0;
+
+	*(u32 *)buf = readl_relaxed(data->base + RNG_DATA);
+
+	return sizeof(u32);
+}
+
+static int meson_rng_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct meson_rng_data *data;
+	struct resource *res;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->base))
+		return PTR_ERR(data->base);
+
+	data->rng.name = pdev->name;
+	data->rng.read = meson_rng_read;
+
+	platform_set_drvdata(pdev, data);
+
+	return devm_hwrng_register(dev, &data->rng);
+}
+
+static const struct of_device_id meson_rng_of_match[] = {
+	{ .compatible = "amlogic,meson-rng", },
+	{},
+};
+
+static struct platform_driver meson_rng_driver = {
+	.probe	= meson_rng_probe,
+	.driver	= {
+		.name = "meson-rng",
+		.of_match_table = meson_rng_of_match,
+	},
+};
+
+module_platform_driver(meson_rng_driver);
+
+MODULE_ALIAS("platform:meson-rng");
+MODULE_DESCRIPTION("Meson H/W Random Number Generator driver");
+MODULE_AUTHOR("Lawrence Mok <lawrence.mok@amlogic.com>");
+MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 8a1432e8bb80..01d4be2c354b 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -384,7 +384,12 @@ static int omap_rng_probe(struct platform_device *pdev)
 	}
 
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(&pdev->dev);
+		goto err_ioremap;
+	}
 
 	ret = (dev->of_node) ? of_get_omap_rng_device_details(priv, pdev) :
 				get_omap_rng_device_details(priv);
@@ -435,8 +440,15 @@ static int __maybe_unused omap_rng_suspend(struct device *dev)
 static int __maybe_unused omap_rng_resume(struct device *dev)
 {
 	struct omap_rng_dev *priv = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret) {
+		dev_err(dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
 
-	pm_runtime_get_sync(dev);
 	priv->pdata->init(priv);
 
 	return 0;
diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c
index 92a810648bd0..63d84e6f1891 100644
--- a/drivers/char/hw_random/stm32-rng.c
+++ b/drivers/char/hw_random/stm32-rng.c
@@ -69,8 +69,12 @@ static int stm32_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
 		}
 
 		/* If error detected or data not ready... */
-		if (sr != RNG_SR_DRDY)
+		if (sr != RNG_SR_DRDY) {
+			if (WARN_ONCE(sr & (RNG_SR_SEIS | RNG_SR_CEIS),
+					"bad RNG status - %x\n", sr))
+				writel_relaxed(0, priv->base + RNG_SR);
 			break;
+		}
 
 		*(u32 *)data = readl_relaxed(priv->base + RNG_DR);
 
@@ -79,10 +83,6 @@ static int stm32_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
 		max -= sizeof(u32);
 	}
 
-	if (WARN_ONCE(sr & (RNG_SR_SEIS | RNG_SR_CEIS),
-		      "bad RNG status - %x\n", sr))
-		writel_relaxed(0, priv->base + RNG_SR);
-
 	pm_runtime_mark_last_busy((struct device *) priv->rng.priv);
 	pm_runtime_put_sync_autosuspend((struct device *) priv->rng.priv);
 
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index b7445b6ae5a4..c822d72629d5 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -31,23 +31,18 @@ config CPU_FREQ_BOOST_SW
 	depends on THERMAL
 
 config CPU_FREQ_STAT
-	tristate "CPU frequency translation statistics"
+	bool "CPU frequency transition statistics"
 	default y
 	help
-	  This driver exports CPU frequency statistics information through sysfs
-	  file system.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called cpufreq_stats.
+	  Export CPU frequency statistics information through sysfs.
 
 	  If in doubt, say N.
 
 config CPU_FREQ_STAT_DETAILS
-	bool "CPU frequency translation statistics details"
+	bool "CPU frequency transition statistics details"
 	depends on CPU_FREQ_STAT
 	help
-	  This will show detail CPU frequency translation table in sysfs file
-	  system.
+	  Show detailed CPU frequency transition table in sysfs.
 
 	  If in doubt, say N.
 
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 32a15052f363..297e9128fe9f 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -468,20 +468,17 @@ unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct acpi_processor_performance *perf;
 	struct cpufreq_frequency_table *entry;
-	unsigned int next_perf_state, next_freq, freq;
+	unsigned int next_perf_state, next_freq, index;
 
 	/*
 	 * Find the closest frequency above target_freq.
-	 *
-	 * The table is sorted in the reverse order with respect to the
-	 * frequency and all of the entries are valid (see the initialization).
 	 */
-	entry = policy->freq_table;
-	do {
-		entry++;
-		freq = entry->frequency;
-	} while (freq >= target_freq && freq != CPUFREQ_TABLE_END);
-	entry--;
+	if (policy->cached_target_freq == target_freq)
+		index = policy->cached_resolved_idx;
+	else
+		index = cpufreq_table_find_index_dl(policy, target_freq);
+
+	entry = &policy->freq_table[index];
 	next_freq = entry->frequency;
 	next_perf_state = entry->driver_data;
 
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index 404360cad25c..042023bbbf62 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -48,9 +48,8 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 	struct dbs_data *od_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = od_data->tuners;
-	struct od_policy_dbs_info *od_info = to_dbs_info(policy_dbs);
 
-	if (!od_info->freq_table)
+	if (!policy->freq_table)
 		return freq_next;
 
 	rdmsr_on_cpu(policy->cpu, MSR_AMD64_FREQ_SENSITIVITY_ACTUAL,
@@ -92,10 +91,9 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 		else {
 			unsigned int index;
 
-			cpufreq_frequency_table_target(policy,
-				od_info->freq_table, policy->cur - 1,
-				CPUFREQ_RELATION_H, &index);
-			freq_next = od_info->freq_table[index].frequency;
+			index = cpufreq_table_find_index_h(policy,
+							   policy->cur - 1);
+			freq_next = policy->freq_table[index].frequency;
 		}
 
 		data->freq_prev = freq_next;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 5617c7087d77..3dd4884c6f9e 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -74,19 +74,12 @@ static inline bool has_target(void)
 }
 
 /* internal prototypes */
-static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
+static int cpufreq_init_governor(struct cpufreq_policy *policy);
+static void cpufreq_exit_governor(struct cpufreq_policy *policy);
 static int cpufreq_start_governor(struct cpufreq_policy *policy);
-
-static inline void cpufreq_exit_governor(struct cpufreq_policy *policy)
-{
-	(void)cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-}
-
-static inline void cpufreq_stop_governor(struct cpufreq_policy *policy)
-{
-	(void)cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-}
+static void cpufreq_stop_governor(struct cpufreq_policy *policy);
+static void cpufreq_governor_limits(struct cpufreq_policy *policy);
 
 /**
  * Two notifier lists: the "policy" list is involved in the
@@ -133,15 +126,6 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
-struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
-
-	return policy && !policy_is_inactive(policy) ?
-		policy->freq_table : NULL;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
-
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -354,6 +338,7 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 		pr_debug("FREQ: %lu - CPU: %lu\n",
 			 (unsigned long)freqs->new, (unsigned long)freqs->cpu);
 		trace_cpu_frequency(freqs->new, freqs->cpu);
+		cpufreq_stats_record_transition(policy, freqs->new);
 		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
 				CPUFREQ_POSTCHANGE, freqs);
 		if (likely(policy) && likely(policy->cpu == freqs->cpu))
@@ -507,6 +492,38 @@ void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
 
+/**
+ * cpufreq_driver_resolve_freq - Map a target frequency to a driver-supported
+ * one.
+ * @target_freq: target frequency to resolve.
+ *
+ * The target to driver frequency mapping is cached in the policy.
+ *
+ * Return: Lowest driver-supported frequency greater than or equal to the
+ * given target_freq, subject to policy (min/max) and driver limitations.
+ */
+unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
+					 unsigned int target_freq)
+{
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	policy->cached_target_freq = target_freq;
+
+	if (cpufreq_driver->target_index) {
+		int idx;
+
+		idx = cpufreq_frequency_table_target(policy, target_freq,
+						     CPUFREQ_RELATION_L);
+		policy->cached_resolved_idx = idx;
+		return policy->freq_table[idx].frequency;
+	}
+
+	if (cpufreq_driver->resolve_freq)
+		return cpufreq_driver->resolve_freq(policy, target_freq);
+
+	return target_freq;
+}
+EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);
+
 /*********************************************************************
  *                          SYSFS INTERFACE                          *
  *********************************************************************/
@@ -1115,6 +1132,7 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
 					     CPUFREQ_REMOVE_POLICY, policy);
 
 	down_write(&policy->rwsem);
+	cpufreq_stats_free_table(policy);
 	cpufreq_remove_dev_symlink(policy);
 	kobj = &policy->kobj;
 	cmp = &policy->kobj_unregister;
@@ -1265,13 +1283,12 @@ static int cpufreq_online(unsigned int cpu)
 		}
 	}
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-				     CPUFREQ_START, policy);
-
 	if (new_policy) {
 		ret = cpufreq_add_dev_interface(policy);
 		if (ret)
 			goto out_exit_policy;
+
+		cpufreq_stats_create_table(policy);
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
 
@@ -1280,6 +1297,9 @@ static int cpufreq_online(unsigned int cpu)
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 	}
 
+	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+				     CPUFREQ_START, policy);
+
 	ret = cpufreq_init_policy(policy);
 	if (ret) {
 		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
@@ -1556,9 +1576,6 @@ static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy)
 {
 	unsigned int new_freq;
 
-	if (cpufreq_suspended)
-		return 0;
-
 	new_freq = cpufreq_driver->get(policy->cpu);
 	if (!new_freq)
 		return 0;
@@ -1864,14 +1881,17 @@ static int __target_intermediate(struct cpufreq_policy *policy,
 	return ret;
 }
 
-static int __target_index(struct cpufreq_policy *policy,
-			  struct cpufreq_frequency_table *freq_table, int index)
+static int __target_index(struct cpufreq_policy *policy, int index)
 {
 	struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0};
 	unsigned int intermediate_freq = 0;
+	unsigned int newfreq = policy->freq_table[index].frequency;
 	int retval = -EINVAL;
 	bool notify;
 
+	if (newfreq == policy->cur)
+		return 0;
+
 	notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION);
 	if (notify) {
 		/* Handle switching to intermediate frequency */
@@ -1886,7 +1906,7 @@ static int __target_index(struct cpufreq_policy *policy,
 				freqs.old = freqs.new;
 		}
 
-		freqs.new = freq_table[index].frequency;
+		freqs.new = newfreq;
 		pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n",
 			 __func__, policy->cpu, freqs.old, freqs.new);
 
@@ -1923,17 +1943,13 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			    unsigned int relation)
 {
 	unsigned int old_target_freq = target_freq;
-	struct cpufreq_frequency_table *freq_table;
-	int index, retval;
+	int index;
 
 	if (cpufreq_disabled())
 		return -ENODEV;
 
 	/* Make sure that target_freq is within supported range */
-	if (target_freq > policy->max)
-		target_freq = policy->max;
-	if (target_freq < policy->min)
-		target_freq = policy->min;
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
 
 	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
 		 policy->cpu, target_freq, relation, old_target_freq);
@@ -1956,23 +1972,9 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	if (!cpufreq_driver->target_index)
 		return -EINVAL;
 
-	freq_table = cpufreq_frequency_get_table(policy->cpu);
-	if (unlikely(!freq_table)) {
-		pr_err("%s: Unable to find freq_table\n", __func__);
-		return -EINVAL;
-	}
-
-	retval = cpufreq_frequency_table_target(policy, freq_table, target_freq,
-						relation, &index);
-	if (unlikely(retval)) {
-		pr_err("%s: Unable to find matching freq\n", __func__);
-		return retval;
-	}
-
-	if (freq_table[index].frequency == policy->cur)
-		return 0;
+	index = cpufreq_frequency_table_target(policy, target_freq, relation);
 
-	return __target_index(policy, freq_table, index);
+	return __target_index(policy, index);
 }
 EXPORT_SYMBOL_GPL(__cpufreq_driver_target);
 
@@ -1997,7 +1999,7 @@ __weak struct cpufreq_governor *cpufreq_fallback_governor(void)
 	return NULL;
 }
 
-static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
+static int cpufreq_init_governor(struct cpufreq_policy *policy)
 {
 	int ret;
 
@@ -2025,36 +2027,82 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
 		}
 	}
 
-	if (event == CPUFREQ_GOV_POLICY_INIT)
-		if (!try_module_get(policy->governor->owner))
-			return -EINVAL;
-
-	pr_debug("%s: for CPU %u, event %u\n", __func__, policy->cpu, event);
+	if (!try_module_get(policy->governor->owner))
+		return -EINVAL;
 
-	ret = policy->governor->governor(policy, event);
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
 
-	if (event == CPUFREQ_GOV_POLICY_INIT) {
-		if (ret)
+	if (policy->governor->init) {
+		ret = policy->governor->init(policy);
+		if (ret) {
 			module_put(policy->governor->owner);
-		else
-			policy->governor->initialized++;
-	} else if (event == CPUFREQ_GOV_POLICY_EXIT) {
-		policy->governor->initialized--;
-		module_put(policy->governor->owner);
+			return ret;
+		}
 	}
 
-	return ret;
+	return 0;
+}
+
+static void cpufreq_exit_governor(struct cpufreq_policy *policy)
+{
+	if (cpufreq_suspended || !policy->governor)
+		return;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
+	if (policy->governor->exit)
+		policy->governor->exit(policy);
+
+	module_put(policy->governor->owner);
 }
 
 static int cpufreq_start_governor(struct cpufreq_policy *policy)
 {
 	int ret;
 
+	if (cpufreq_suspended)
+		return 0;
+
+	if (!policy->governor)
+		return -EINVAL;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy)
 		cpufreq_update_current_freq(policy);
 
-	ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
-	return ret ? ret : cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+	if (policy->governor->start) {
+		ret = policy->governor->start(policy);
+		if (ret)
+			return ret;
+	}
+
+	if (policy->governor->limits)
+		policy->governor->limits(policy);
+
+	return 0;
+}
+
+static void cpufreq_stop_governor(struct cpufreq_policy *policy)
+{
+	if (cpufreq_suspended || !policy->governor)
+		return;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
+	if (policy->governor->stop)
+		policy->governor->stop(policy);
+}
+
+static void cpufreq_governor_limits(struct cpufreq_policy *policy)
+{
+	if (cpufreq_suspended || !policy->governor)
+		return;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
+	if (policy->governor->limits)
+		policy->governor->limits(policy);
 }
 
 int cpufreq_register_governor(struct cpufreq_governor *governor)
@@ -2069,7 +2117,6 @@ int cpufreq_register_governor(struct cpufreq_governor *governor)
 
 	mutex_lock(&cpufreq_governor_mutex);
 
-	governor->initialized = 0;
 	err = -EBUSY;
 	if (!find_governor(governor->name)) {
 		err = 0;
@@ -2184,6 +2231,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	policy->min = new_policy->min;
 	policy->max = new_policy->max;
 
+	policy->cached_target_freq = UINT_MAX;
+
 	pr_debug("new min and max freqs are %u - %u kHz\n",
 		 policy->min, policy->max);
 
@@ -2195,7 +2244,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	if (new_policy->governor == policy->governor) {
 		pr_debug("cpufreq: governor limits update\n");
-		return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+		cpufreq_governor_limits(policy);
+		return 0;
 	}
 
 	pr_debug("governor switch\n");
@@ -2210,7 +2260,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	/* start new governor */
 	policy->governor = new_policy->governor;
-	ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+	ret = cpufreq_init_governor(policy);
 	if (!ret) {
 		ret = cpufreq_start_governor(policy);
 		if (!ret) {
@@ -2224,7 +2274,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
+		if (cpufreq_init_governor(policy))
 			policy->governor = NULL;
 		else
 			cpufreq_start_governor(policy);
@@ -2309,26 +2359,25 @@ static struct notifier_block __refdata cpufreq_cpu_notifier = {
  *********************************************************************/
 static int cpufreq_boost_set_sw(int state)
 {
-	struct cpufreq_frequency_table *freq_table;
 	struct cpufreq_policy *policy;
 	int ret = -EINVAL;
 
 	for_each_active_policy(policy) {
-		freq_table = cpufreq_frequency_get_table(policy->cpu);
-		if (freq_table) {
-			ret = cpufreq_frequency_table_cpuinfo(policy,
-							freq_table);
-			if (ret) {
-				pr_err("%s: Policy frequency update failed\n",
-				       __func__);
-				break;
-			}
-
-			down_write(&policy->rwsem);
-			policy->user_policy.max = policy->max;
-			cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
-			up_write(&policy->rwsem);
+		if (!policy->freq_table)
+			continue;
+
+		ret = cpufreq_frequency_table_cpuinfo(policy,
+						      policy->freq_table);
+		if (ret) {
+			pr_err("%s: Policy frequency update failed\n",
+			       __func__);
+			break;
 		}
+
+		down_write(&policy->rwsem);
+		policy->user_policy.max = policy->max;
+		cpufreq_governor_limits(policy);
+		up_write(&policy->rwsem);
 	}
 
 	return ret;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 316df247e00d..18da4f8051d3 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -17,7 +17,6 @@
 struct cs_policy_dbs_info {
 	struct policy_dbs_info policy_dbs;
 	unsigned int down_skip;
-	unsigned int requested_freq;
 };
 
 static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
@@ -75,19 +74,17 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 
 	/* Check for frequency increase */
 	if (load > dbs_data->up_threshold) {
+		unsigned int requested_freq = policy->cur;
+
 		dbs_info->down_skip = 0;
 
 		/* if we are already at full speed then break out early */
-		if (dbs_info->requested_freq == policy->max)
+		if (requested_freq == policy->max)
 			goto out;
 
-		dbs_info->requested_freq += get_freq_target(cs_tuners, policy);
-
-		if (dbs_info->requested_freq > policy->max)
-			dbs_info->requested_freq = policy->max;
+		requested_freq += get_freq_target(cs_tuners, policy);
 
-		__cpufreq_driver_target(policy, dbs_info->requested_freq,
-			CPUFREQ_RELATION_H);
+		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_H);
 		goto out;
 	}
 
@@ -98,36 +95,27 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 
 	/* Check for frequency decrease */
 	if (load < cs_tuners->down_threshold) {
-		unsigned int freq_target;
+		unsigned int freq_target, requested_freq = policy->cur;
 		/*
 		 * if we cannot reduce the frequency anymore, break out early
 		 */
-		if (policy->cur == policy->min)
+		if (requested_freq == policy->min)
 			goto out;
 
 		freq_target = get_freq_target(cs_tuners, policy);
-		if (dbs_info->requested_freq > freq_target)
-			dbs_info->requested_freq -= freq_target;
+		if (requested_freq > freq_target)
+			requested_freq -= freq_target;
 		else
-			dbs_info->requested_freq = policy->min;
+			requested_freq = policy->min;
 
-		__cpufreq_driver_target(policy, dbs_info->requested_freq,
-				CPUFREQ_RELATION_L);
+		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_L);
 	}
 
  out:
 	return dbs_data->sampling_rate;
 }
 
-static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-				void *data);
-
-static struct notifier_block cs_cpufreq_notifier_block = {
-	.notifier_call = dbs_cpufreq_notifier,
-};
-
 /************************** sysfs interface ************************/
-static struct dbs_governor cs_dbs_gov;
 
 static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set,
 					  const char *buf, size_t count)
@@ -268,15 +256,13 @@ static void cs_free(struct policy_dbs_info *policy_dbs)
 	kfree(to_dbs_info(policy_dbs));
 }
 
-static int cs_init(struct dbs_data *dbs_data, bool notify)
+static int cs_init(struct dbs_data *dbs_data)
 {
 	struct cs_dbs_tuners *tuners;
 
 	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
-	if (!tuners) {
-		pr_err("%s: kzalloc failed\n", __func__);
+	if (!tuners)
 		return -ENOMEM;
-	}
 
 	tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD;
 	tuners->freq_step = DEF_FREQUENCY_STEP;
@@ -288,19 +274,11 @@ static int cs_init(struct dbs_data *dbs_data, bool notify)
 	dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
 		jiffies_to_usecs(10);
 
-	if (notify)
-		cpufreq_register_notifier(&cs_cpufreq_notifier_block,
-					  CPUFREQ_TRANSITION_NOTIFIER);
-
 	return 0;
 }
 
-static void cs_exit(struct dbs_data *dbs_data, bool notify)
+static void cs_exit(struct dbs_data *dbs_data)
 {
-	if (notify)
-		cpufreq_unregister_notifier(&cs_cpufreq_notifier_block,
-					    CPUFREQ_TRANSITION_NOTIFIER);
-
 	kfree(dbs_data->tuners);
 }
 
@@ -309,16 +287,10 @@ static void cs_start(struct cpufreq_policy *policy)
 	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
 
 	dbs_info->down_skip = 0;
-	dbs_info->requested_freq = policy->cur;
 }
 
-static struct dbs_governor cs_dbs_gov = {
-	.gov = {
-		.name = "conservative",
-		.governor = cpufreq_governor_dbs,
-		.max_transition_latency = TRANSITION_LATENCY_LIMIT,
-		.owner = THIS_MODULE,
-	},
+static struct dbs_governor cs_governor = {
+	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"),
 	.kobj_type = { .default_attrs = cs_attributes },
 	.gov_dbs_timer = cs_dbs_timer,
 	.alloc = cs_alloc,
@@ -328,33 +300,7 @@ static struct dbs_governor cs_dbs_gov = {
 	.start = cs_start,
 };
 
-#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_dbs_gov.gov)
-
-static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-				void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
-	struct cs_policy_dbs_info *dbs_info;
-
-	if (!policy)
-		return 0;
-
-	/* policy isn't governed by conservative governor */
-	if (policy->governor != CPU_FREQ_GOV_CONSERVATIVE)
-		return 0;
-
-	dbs_info = to_dbs_info(policy->governor_data);
-	/*
-	 * we only care if our internally tracked freq moves outside the 'valid'
-	 * ranges of frequency available to us otherwise we do not change it
-	*/
-	if (dbs_info->requested_freq > policy->max
-			|| dbs_info->requested_freq < policy->min)
-		dbs_info->requested_freq = freq->new;
-
-	return 0;
-}
+#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_governor.gov)
 
 static int __init cpufreq_gov_dbs_init(void)
 {
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index be498d56dd69..e415349ab31b 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -336,17 +336,6 @@ static inline void gov_clear_update_util(struct cpufreq_policy *policy)
 	synchronize_sched();
 }
 
-static void gov_cancel_work(struct cpufreq_policy *policy)
-{
-	struct policy_dbs_info *policy_dbs = policy->governor_data;
-
-	gov_clear_update_util(policy_dbs->policy);
-	irq_work_sync(&policy_dbs->irq_work);
-	cancel_work_sync(&policy_dbs->work);
-	atomic_set(&policy_dbs->work_count, 0);
-	policy_dbs->work_in_progress = false;
-}
-
 static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy,
 						     struct dbs_governor *gov)
 {
@@ -389,7 +378,7 @@ static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs,
 	gov->free(policy_dbs);
 }
 
-static int cpufreq_governor_init(struct cpufreq_policy *policy)
+int cpufreq_dbs_governor_init(struct cpufreq_policy *policy)
 {
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct dbs_data *dbs_data;
@@ -429,7 +418,7 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 
 	gov_attr_set_init(&dbs_data->attr_set, &policy_dbs->list);
 
-	ret = gov->init(dbs_data, !policy->governor->initialized);
+	ret = gov->init(dbs_data);
 	if (ret)
 		goto free_policy_dbs_info;
 
@@ -458,13 +447,13 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 		goto out;
 
 	/* Failure, so roll back. */
-	pr_err("cpufreq: Governor initialization failed (dbs_data kobject init error %d)\n", ret);
+	pr_err("initialization failed (dbs_data kobject init error %d)\n", ret);
 
 	policy->governor_data = NULL;
 
 	if (!have_governor_per_policy())
 		gov->gdbs_data = NULL;
-	gov->exit(dbs_data, !policy->governor->initialized);
+	gov->exit(dbs_data);
 	kfree(dbs_data);
 
 free_policy_dbs_info:
@@ -474,8 +463,9 @@ out:
 	mutex_unlock(&gov_dbs_data_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_init);
 
-static int cpufreq_governor_exit(struct cpufreq_policy *policy)
+void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy)
 {
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
@@ -493,17 +483,17 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy)
 		if (!have_governor_per_policy())
 			gov->gdbs_data = NULL;
 
-		gov->exit(dbs_data, policy->governor->initialized == 1);
+		gov->exit(dbs_data);
 		kfree(dbs_data);
 	}
 
 	free_policy_dbs_info(policy_dbs, gov);
 
 	mutex_unlock(&gov_dbs_data_mutex);
-	return 0;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_exit);
 
-static int cpufreq_governor_start(struct cpufreq_policy *policy)
+int cpufreq_dbs_governor_start(struct cpufreq_policy *policy)
 {
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
@@ -539,47 +529,28 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy)
 	gov_set_update_util(policy_dbs, sampling_rate);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_start);
 
-static int cpufreq_governor_stop(struct cpufreq_policy *policy)
+void cpufreq_dbs_governor_stop(struct cpufreq_policy *policy)
 {
-	gov_cancel_work(policy);
-	return 0;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+
+	gov_clear_update_util(policy_dbs->policy);
+	irq_work_sync(&policy_dbs->irq_work);
+	cancel_work_sync(&policy_dbs->work);
+	atomic_set(&policy_dbs->work_count, 0);
+	policy_dbs->work_in_progress = false;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_stop);
 
-static int cpufreq_governor_limits(struct cpufreq_policy *policy)
+void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
 {
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 
 	mutex_lock(&policy_dbs->timer_mutex);
-
-	if (policy->max < policy->cur)
-		__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
-	else if (policy->min > policy->cur)
-		__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
-
+	cpufreq_policy_apply_limits(policy);
 	gov_update_sample_delay(policy_dbs, 0);
 
 	mutex_unlock(&policy_dbs->timer_mutex);
-
-	return 0;
-}
-
-int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event)
-{
-	if (event == CPUFREQ_GOV_POLICY_INIT) {
-		return cpufreq_governor_init(policy);
-	} else if (policy->governor_data) {
-		switch (event) {
-		case CPUFREQ_GOV_POLICY_EXIT:
-			return cpufreq_governor_exit(policy);
-		case CPUFREQ_GOV_START:
-			return cpufreq_governor_start(policy);
-		case CPUFREQ_GOV_STOP:
-			return cpufreq_governor_stop(policy);
-		case CPUFREQ_GOV_LIMITS:
-			return cpufreq_governor_limits(policy);
-		}
-	}
-	return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_limits);
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 34eb214b6d57..ef1037e9c92b 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -138,8 +138,8 @@ struct dbs_governor {
 	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy);
 	struct policy_dbs_info *(*alloc)(void);
 	void (*free)(struct policy_dbs_info *policy_dbs);
-	int (*init)(struct dbs_data *dbs_data, bool notify);
-	void (*exit)(struct dbs_data *dbs_data, bool notify);
+	int (*init)(struct dbs_data *dbs_data);
+	void (*exit)(struct dbs_data *dbs_data);
 	void (*start)(struct cpufreq_policy *policy);
 };
 
@@ -148,6 +148,25 @@ static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy
 	return container_of(policy->governor, struct dbs_governor, gov);
 }
 
+/* Governor callback routines */
+int cpufreq_dbs_governor_init(struct cpufreq_policy *policy);
+void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy);
+int cpufreq_dbs_governor_start(struct cpufreq_policy *policy);
+void cpufreq_dbs_governor_stop(struct cpufreq_policy *policy);
+void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy);
+
+#define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_)			\
+	{								\
+		.name = _name_,						\
+		.max_transition_latency	= TRANSITION_LATENCY_LIMIT,	\
+		.owner = THIS_MODULE,					\
+		.init = cpufreq_dbs_governor_init,			\
+		.exit = cpufreq_dbs_governor_exit,			\
+		.start = cpufreq_dbs_governor_start,			\
+		.stop = cpufreq_dbs_governor_stop,			\
+		.limits = cpufreq_dbs_governor_limits,			\
+	}
+
 /* Governor specific operations */
 struct od_ops {
 	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
@@ -155,7 +174,6 @@ struct od_ops {
 };
 
 unsigned int dbs_update(struct cpufreq_policy *policy);
-int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event);
 void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 300163430516..3a1f49f5f4c6 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -65,34 +65,30 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 {
 	unsigned int freq_req, freq_reduc, freq_avg;
 	unsigned int freq_hi, freq_lo;
-	unsigned int index = 0;
+	unsigned int index;
 	unsigned int delay_hi_us;
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
 	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cpufreq_frequency_table *freq_table = policy->freq_table;
 
-	if (!dbs_info->freq_table) {
+	if (!freq_table) {
 		dbs_info->freq_lo = 0;
 		dbs_info->freq_lo_delay_us = 0;
 		return freq_next;
 	}
 
-	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_next,
-			relation, &index);
-	freq_req = dbs_info->freq_table[index].frequency;
+	index = cpufreq_frequency_table_target(policy, freq_next, relation);
+	freq_req = freq_table[index].frequency;
 	freq_reduc = freq_req * od_tuners->powersave_bias / 1000;
 	freq_avg = freq_req - freq_reduc;
 
 	/* Find freq bounds for freq_avg in freq_table */
-	index = 0;
-	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
-			CPUFREQ_RELATION_H, &index);
-	freq_lo = dbs_info->freq_table[index].frequency;
-	index = 0;
-	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
-			CPUFREQ_RELATION_L, &index);
-	freq_hi = dbs_info->freq_table[index].frequency;
+	index = cpufreq_table_find_index_h(policy, freq_avg);
+	freq_lo = freq_table[index].frequency;
+	index = cpufreq_table_find_index_l(policy, freq_avg);
+	freq_hi = freq_table[index].frequency;
 
 	/* Find out how long we have to be in hi and lo freqs */
 	if (freq_hi == freq_lo) {
@@ -113,7 +109,6 @@ static void ondemand_powersave_bias_init(struct cpufreq_policy *policy)
 {
 	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
 
-	dbs_info->freq_table = cpufreq_frequency_get_table(policy->cpu);
 	dbs_info->freq_lo = 0;
 }
 
@@ -361,17 +356,15 @@ static void od_free(struct policy_dbs_info *policy_dbs)
 	kfree(to_dbs_info(policy_dbs));
 }
 
-static int od_init(struct dbs_data *dbs_data, bool notify)
+static int od_init(struct dbs_data *dbs_data)
 {
 	struct od_dbs_tuners *tuners;
 	u64 idle_time;
 	int cpu;
 
 	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
-	if (!tuners) {
-		pr_err("%s: kzalloc failed\n", __func__);
+	if (!tuners)
 		return -ENOMEM;
-	}
 
 	cpu = get_cpu();
 	idle_time = get_cpu_idle_time_us(cpu, NULL);
@@ -402,7 +395,7 @@ static int od_init(struct dbs_data *dbs_data, bool notify)
 	return 0;
 }
 
-static void od_exit(struct dbs_data *dbs_data, bool notify)
+static void od_exit(struct dbs_data *dbs_data)
 {
 	kfree(dbs_data->tuners);
 }
@@ -420,12 +413,7 @@ static struct od_ops od_ops = {
 };
 
 static struct dbs_governor od_dbs_gov = {
-	.gov = {
-		.name = "ondemand",
-		.governor = cpufreq_governor_dbs,
-		.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-		.owner = THIS_MODULE,
-	},
+	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("ondemand"),
 	.kobj_type = { .default_attrs = od_attributes },
 	.gov_dbs_timer = od_dbs_timer,
 	.alloc = od_alloc,
diff --git a/drivers/cpufreq/cpufreq_ondemand.h b/drivers/cpufreq/cpufreq_ondemand.h
index f0121db3cd9e..640ea4e97106 100644
--- a/drivers/cpufreq/cpufreq_ondemand.h
+++ b/drivers/cpufreq/cpufreq_ondemand.h
@@ -13,7 +13,6 @@
 
 struct od_policy_dbs_info {
 	struct policy_dbs_info policy_dbs;
-	struct cpufreq_frequency_table *freq_table;
 	unsigned int freq_lo;
 	unsigned int freq_lo_delay_us;
 	unsigned int freq_hi_delay_us;
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index af9f4b96f5a8..dafb679adc58 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -16,27 +16,16 @@
 #include <linux/init.h>
 #include <linux/module.h>
 
-static int cpufreq_governor_performance(struct cpufreq_policy *policy,
-					unsigned int event)
+static void cpufreq_gov_performance_limits(struct cpufreq_policy *policy)
 {
-	switch (event) {
-	case CPUFREQ_GOV_START:
-	case CPUFREQ_GOV_LIMITS:
-		pr_debug("setting to %u kHz because of event %u\n",
-						policy->max, event);
-		__cpufreq_driver_target(policy, policy->max,
-						CPUFREQ_RELATION_H);
-		break;
-	default:
-		break;
-	}
-	return 0;
+	pr_debug("setting to %u kHz\n", policy->max);
+	__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
 }
 
 static struct cpufreq_governor cpufreq_gov_performance = {
 	.name		= "performance",
-	.governor	= cpufreq_governor_performance,
 	.owner		= THIS_MODULE,
+	.limits		= cpufreq_gov_performance_limits,
 };
 
 static int __init cpufreq_gov_performance_init(void)
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index b8b400232a74..78a651038faf 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -16,26 +16,15 @@
 #include <linux/init.h>
 #include <linux/module.h>
 
-static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
-					unsigned int event)
+static void cpufreq_gov_powersave_limits(struct cpufreq_policy *policy)
 {
-	switch (event) {
-	case CPUFREQ_GOV_START:
-	case CPUFREQ_GOV_LIMITS:
-		pr_debug("setting to %u kHz because of event %u\n",
-							policy->min, event);
-		__cpufreq_driver_target(policy, policy->min,
-						CPUFREQ_RELATION_L);
-		break;
-	default:
-		break;
-	}
-	return 0;
+	pr_debug("setting to %u kHz\n", policy->min);
+	__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
 }
 
 static struct cpufreq_governor cpufreq_gov_powersave = {
 	.name		= "powersave",
-	.governor	= cpufreq_governor_powersave,
+	.limits		= cpufreq_gov_powersave_limits,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 5e370a30a964..06d3abdffd3a 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 #include <linux/cputime.h>
 
-static spinlock_t cpufreq_stats_lock;
+static DEFINE_SPINLOCK(cpufreq_stats_lock);
 
 struct cpufreq_stats {
 	unsigned int total_trans;
@@ -52,6 +52,9 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	ssize_t len = 0;
 	int i;
 
+	if (policy->fast_switch_enabled)
+		return 0;
+
 	cpufreq_stats_update(stats);
 	for (i = 0; i < stats->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stats->freq_table[i],
@@ -68,6 +71,9 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 	ssize_t len = 0;
 	int i, j;
 
+	if (policy->fast_switch_enabled)
+		return 0;
+
 	len += snprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
 	len += snprintf(buf + len, PAGE_SIZE - len, "         : ");
 	for (i = 0; i < stats->state_num; i++) {
@@ -130,7 +136,7 @@ static int freq_table_get_index(struct cpufreq_stats *stats, unsigned int freq)
 	return -1;
 }
 
-static void __cpufreq_stats_free_table(struct cpufreq_policy *policy)
+void cpufreq_stats_free_table(struct cpufreq_policy *policy)
 {
 	struct cpufreq_stats *stats = policy->stats;
 
@@ -146,39 +152,25 @@ static void __cpufreq_stats_free_table(struct cpufreq_policy *policy)
 	policy->stats = NULL;
 }
 
-static void cpufreq_stats_free_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy;
-
-	policy = cpufreq_cpu_get(cpu);
-	if (!policy)
-		return;
-
-	__cpufreq_stats_free_table(policy);
-
-	cpufreq_cpu_put(policy);
-}
-
-static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
+void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 {
 	unsigned int i = 0, count = 0, ret = -ENOMEM;
 	struct cpufreq_stats *stats;
 	unsigned int alloc_size;
-	unsigned int cpu = policy->cpu;
 	struct cpufreq_frequency_table *pos, *table;
 
 	/* We need cpufreq table for creating stats table */
-	table = cpufreq_frequency_get_table(cpu);
+	table = policy->freq_table;
 	if (unlikely(!table))
-		return 0;
+		return;
 
 	/* stats already initialized */
 	if (policy->stats)
-		return -EEXIST;
+		return;
 
 	stats = kzalloc(sizeof(*stats), GFP_KERNEL);
 	if (!stats)
-		return -ENOMEM;
+		return;
 
 	/* Find total allocation size */
 	cpufreq_for_each_valid_entry(pos, table)
@@ -215,80 +207,32 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	policy->stats = stats;
 	ret = sysfs_create_group(&policy->kobj, &stats_attr_group);
 	if (!ret)
-		return 0;
+		return;
 
 	/* We failed, release resources */
 	policy->stats = NULL;
 	kfree(stats->time_in_state);
 free_stat:
 	kfree(stats);
-
-	return ret;
-}
-
-static void cpufreq_stats_create_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy;
-
-	/*
-	 * "likely(!policy)" because normally cpufreq_stats will be registered
-	 * before cpufreq driver
-	 */
-	policy = cpufreq_cpu_get(cpu);
-	if (likely(!policy))
-		return;
-
-	__cpufreq_stats_create_table(policy);
-
-	cpufreq_cpu_put(policy);
 }
 
-static int cpufreq_stat_notifier_policy(struct notifier_block *nb,
-		unsigned long val, void *data)
+void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
+				     unsigned int new_freq)
 {
-	int ret = 0;
-	struct cpufreq_policy *policy = data;
-
-	if (val == CPUFREQ_CREATE_POLICY)
-		ret = __cpufreq_stats_create_table(policy);
-	else if (val == CPUFREQ_REMOVE_POLICY)
-		__cpufreq_stats_free_table(policy);
-
-	return ret;
-}
-
-static int cpufreq_stat_notifier_trans(struct notifier_block *nb,
-		unsigned long val, void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	struct cpufreq_policy *policy = cpufreq_cpu_get(freq->cpu);
-	struct cpufreq_stats *stats;
+	struct cpufreq_stats *stats = policy->stats;
 	int old_index, new_index;
 
-	if (!policy) {
-		pr_err("%s: No policy found\n", __func__);
-		return 0;
-	}
-
-	if (val != CPUFREQ_POSTCHANGE)
-		goto put_policy;
-
-	if (!policy->stats) {
+	if (!stats) {
 		pr_debug("%s: No stats found\n", __func__);
-		goto put_policy;
+		return;
 	}
 
-	stats = policy->stats;
-
 	old_index = stats->last_index;
-	new_index = freq_table_get_index(stats, freq->new);
+	new_index = freq_table_get_index(stats, new_freq);
 
 	/* We can't do stats->time_in_state[-1]= .. */
-	if (old_index == -1 || new_index == -1)
-		goto put_policy;
-
-	if (old_index == new_index)
-		goto put_policy;
+	if (old_index == -1 || new_index == -1 || old_index == new_index)
+		return;
 
 	cpufreq_stats_update(stats);
 
@@ -297,61 +241,4 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb,
 	stats->trans_table[old_index * stats->max_state + new_index]++;
 #endif
 	stats->total_trans++;
-
-put_policy:
-	cpufreq_cpu_put(policy);
-	return 0;
 }
-
-static struct notifier_block notifier_policy_block = {
-	.notifier_call = cpufreq_stat_notifier_policy
-};
-
-static struct notifier_block notifier_trans_block = {
-	.notifier_call = cpufreq_stat_notifier_trans
-};
-
-static int __init cpufreq_stats_init(void)
-{
-	int ret;
-	unsigned int cpu;
-
-	spin_lock_init(&cpufreq_stats_lock);
-	ret = cpufreq_register_notifier(&notifier_policy_block,
-				CPUFREQ_POLICY_NOTIFIER);
-	if (ret)
-		return ret;
-
-	for_each_online_cpu(cpu)
-		cpufreq_stats_create_table(cpu);
-
-	ret = cpufreq_register_notifier(&notifier_trans_block,
-				CPUFREQ_TRANSITION_NOTIFIER);
-	if (ret) {
-		cpufreq_unregister_notifier(&notifier_policy_block,
-				CPUFREQ_POLICY_NOTIFIER);
-		for_each_online_cpu(cpu)
-			cpufreq_stats_free_table(cpu);
-		return ret;
-	}
-
-	return 0;
-}
-static void __exit cpufreq_stats_exit(void)
-{
-	unsigned int cpu;
-
-	cpufreq_unregister_notifier(&notifier_policy_block,
-			CPUFREQ_POLICY_NOTIFIER);
-	cpufreq_unregister_notifier(&notifier_trans_block,
-			CPUFREQ_TRANSITION_NOTIFIER);
-	for_each_online_cpu(cpu)
-		cpufreq_stats_free_table(cpu);
-}
-
-MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>");
-MODULE_DESCRIPTION("Export cpufreq stats via sysfs");
-MODULE_LICENSE("GPL");
-
-module_init(cpufreq_stats_init);
-module_exit(cpufreq_stats_exit);
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 9f3dec9a3f36..bd897e3e134d 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -65,66 +65,66 @@ static int cpufreq_userspace_policy_init(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
-				   unsigned int event)
+static void cpufreq_userspace_policy_exit(struct cpufreq_policy *policy)
+{
+	mutex_lock(&userspace_mutex);
+	kfree(policy->governor_data);
+	policy->governor_data = NULL;
+	mutex_unlock(&userspace_mutex);
+}
+
+static int cpufreq_userspace_policy_start(struct cpufreq_policy *policy)
 {
 	unsigned int *setspeed = policy->governor_data;
-	unsigned int cpu = policy->cpu;
-	int rc = 0;
 
-	if (event == CPUFREQ_GOV_POLICY_INIT)
-		return cpufreq_userspace_policy_init(policy);
+	BUG_ON(!policy->cur);
+	pr_debug("started managing cpu %u\n", policy->cpu);
 
-	if (!setspeed)
-		return -EINVAL;
-
-	switch (event) {
-	case CPUFREQ_GOV_POLICY_EXIT:
-		mutex_lock(&userspace_mutex);
-		policy->governor_data = NULL;
-		kfree(setspeed);
-		mutex_unlock(&userspace_mutex);
-		break;
-	case CPUFREQ_GOV_START:
-		BUG_ON(!policy->cur);
-		pr_debug("started managing cpu %u\n", cpu);
-
-		mutex_lock(&userspace_mutex);
-		per_cpu(cpu_is_managed, cpu) = 1;
-		*setspeed = policy->cur;
-		mutex_unlock(&userspace_mutex);
-		break;
-	case CPUFREQ_GOV_STOP:
-		pr_debug("managing cpu %u stopped\n", cpu);
-
-		mutex_lock(&userspace_mutex);
-		per_cpu(cpu_is_managed, cpu) = 0;
-		*setspeed = 0;
-		mutex_unlock(&userspace_mutex);
-		break;
-	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&userspace_mutex);
-		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
-			cpu, policy->min, policy->max, policy->cur, *setspeed);
-
-		if (policy->max < *setspeed)
-			__cpufreq_driver_target(policy, policy->max,
-						CPUFREQ_RELATION_H);
-		else if (policy->min > *setspeed)
-			__cpufreq_driver_target(policy, policy->min,
-						CPUFREQ_RELATION_L);
-		else
-			__cpufreq_driver_target(policy, *setspeed,
-						CPUFREQ_RELATION_L);
-		mutex_unlock(&userspace_mutex);
-		break;
-	}
-	return rc;
+	mutex_lock(&userspace_mutex);
+	per_cpu(cpu_is_managed, policy->cpu) = 1;
+	*setspeed = policy->cur;
+	mutex_unlock(&userspace_mutex);
+	return 0;
+}
+
+static void cpufreq_userspace_policy_stop(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed = policy->governor_data;
+
+	pr_debug("managing cpu %u stopped\n", policy->cpu);
+
+	mutex_lock(&userspace_mutex);
+	per_cpu(cpu_is_managed, policy->cpu) = 0;
+	*setspeed = 0;
+	mutex_unlock(&userspace_mutex);
+}
+
+static void cpufreq_userspace_policy_limits(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed = policy->governor_data;
+
+	mutex_lock(&userspace_mutex);
+
+	pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
+		 policy->cpu, policy->min, policy->max, policy->cur, *setspeed);
+
+	if (policy->max < *setspeed)
+		__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
+	else if (policy->min > *setspeed)
+		__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
+	else
+		__cpufreq_driver_target(policy, *setspeed, CPUFREQ_RELATION_L);
+
+	mutex_unlock(&userspace_mutex);
 }
 
 static struct cpufreq_governor cpufreq_gov_userspace = {
 	.name		= "userspace",
-	.governor	= cpufreq_governor_userspace,
+	.init		= cpufreq_userspace_policy_init,
+	.exit		= cpufreq_userspace_policy_exit,
+	.start		= cpufreq_userspace_policy_start,
+	.stop		= cpufreq_userspace_policy_stop,
+	.limits		= cpufreq_userspace_policy_limits,
 	.store_setspeed	= cpufreq_set,
 	.show_setspeed	= show_speed,
 	.owner		= THIS_MODULE,
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index 7e336d20c184..b95a872800ec 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -38,26 +38,6 @@ struct davinci_cpufreq {
 };
 static struct davinci_cpufreq cpufreq;
 
-static int davinci_verify_speed(struct cpufreq_policy *policy)
-{
-	struct davinci_cpufreq_config *pdata = cpufreq.dev->platform_data;
-	struct cpufreq_frequency_table *freq_table = pdata->freq_table;
-	struct clk *armclk = cpufreq.armclk;
-
-	if (freq_table)
-		return cpufreq_frequency_table_verify(policy, freq_table);
-
-	if (policy->cpu)
-		return -EINVAL;
-
-	cpufreq_verify_within_cpu_limits(policy);
-	policy->min = clk_round_rate(armclk, policy->min * 1000) / 1000;
-	policy->max = clk_round_rate(armclk, policy->max * 1000) / 1000;
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-						policy->cpuinfo.max_freq);
-	return 0;
-}
-
 static int davinci_target(struct cpufreq_policy *policy, unsigned int idx)
 {
 	struct davinci_cpufreq_config *pdata = cpufreq.dev->platform_data;
@@ -121,7 +101,7 @@ static int davinci_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver davinci_driver = {
 	.flags		= CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify		= davinci_verify_speed,
+	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= davinci_target,
 	.get		= cpufreq_generic_get,
 	.init		= davinci_cpu_init,
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index a8f1daffc9bc..3bbbf9e6960c 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -63,8 +63,6 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 	else
 		return 0;
 }
-EXPORT_SYMBOL_GPL(cpufreq_frequency_table_cpuinfo);
-
 
 int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 				   struct cpufreq_frequency_table *table)
@@ -108,20 +106,16 @@ EXPORT_SYMBOL_GPL(cpufreq_frequency_table_verify);
  */
 int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy)
 {
-	struct cpufreq_frequency_table *table =
-		cpufreq_frequency_get_table(policy->cpu);
-	if (!table)
+	if (!policy->freq_table)
 		return -ENODEV;
 
-	return cpufreq_frequency_table_verify(policy, table);
+	return cpufreq_frequency_table_verify(policy, policy->freq_table);
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_frequency_table_verify);
 
-int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
-				   struct cpufreq_frequency_table *table,
-				   unsigned int target_freq,
-				   unsigned int relation,
-				   unsigned int *index)
+int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
+				 unsigned int target_freq,
+				 unsigned int relation)
 {
 	struct cpufreq_frequency_table optimal = {
 		.driver_data = ~0,
@@ -132,7 +126,9 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 		.frequency = 0,
 	};
 	struct cpufreq_frequency_table *pos;
+	struct cpufreq_frequency_table *table = policy->freq_table;
 	unsigned int freq, diff, i = 0;
+	int index;
 
 	pr_debug("request for target %u kHz (relation: %u) for cpu %u\n",
 					target_freq, relation, policy->cpu);
@@ -196,25 +192,26 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 		}
 	}
 	if (optimal.driver_data > i) {
-		if (suboptimal.driver_data > i)
-			return -EINVAL;
-		*index = suboptimal.driver_data;
-	} else
-		*index = optimal.driver_data;
+		if (suboptimal.driver_data > i) {
+			WARN(1, "Invalid frequency table: %d\n", policy->cpu);
+			return 0;
+		}
 
-	pr_debug("target index is %u, freq is:%u kHz\n", *index,
-		 table[*index].frequency);
+		index = suboptimal.driver_data;
+	} else
+		index = optimal.driver_data;
 
-	return 0;
+	pr_debug("target index is %u, freq is:%u kHz\n", index,
+		 table[index].frequency);
+	return index;
 }
-EXPORT_SYMBOL_GPL(cpufreq_frequency_table_target);
+EXPORT_SYMBOL_GPL(cpufreq_table_index_unsorted);
 
 int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 		unsigned int freq)
 {
-	struct cpufreq_frequency_table *pos, *table;
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
 
-	table = cpufreq_frequency_get_table(policy->cpu);
 	if (unlikely(!table)) {
 		pr_debug("%s: Unable to find frequency table\n", __func__);
 		return -ENOENT;
@@ -300,15 +297,72 @@ struct freq_attr *cpufreq_generic_attr[] = {
 };
 EXPORT_SYMBOL_GPL(cpufreq_generic_attr);
 
+static int set_freq_table_sorted(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
+	struct cpufreq_frequency_table *prev = NULL;
+	int ascending = 0;
+
+	policy->freq_table_sorted = CPUFREQ_TABLE_UNSORTED;
+
+	cpufreq_for_each_valid_entry(pos, table) {
+		if (!prev) {
+			prev = pos;
+			continue;
+		}
+
+		if (pos->frequency == prev->frequency) {
+			pr_warn("Duplicate freq-table entries: %u\n",
+				pos->frequency);
+			return -EINVAL;
+		}
+
+		/* Frequency increased from prev to pos */
+		if (pos->frequency > prev->frequency) {
+			/* But frequency was decreasing earlier */
+			if (ascending < 0) {
+				pr_debug("Freq table is unsorted\n");
+				return 0;
+			}
+
+			ascending++;
+		} else {
+			/* Frequency decreased from prev to pos */
+
+			/* But frequency was increasing earlier */
+			if (ascending > 0) {
+				pr_debug("Freq table is unsorted\n");
+				return 0;
+			}
+
+			ascending--;
+		}
+
+		prev = pos;
+	}
+
+	if (ascending > 0)
+		policy->freq_table_sorted = CPUFREQ_TABLE_SORTED_ASCENDING;
+	else
+		policy->freq_table_sorted = CPUFREQ_TABLE_SORTED_DESCENDING;
+
+	pr_debug("Freq table is sorted in %s order\n",
+		 ascending > 0 ? "ascending" : "descending");
+
+	return 0;
+}
+
 int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 				      struct cpufreq_frequency_table *table)
 {
-	int ret = cpufreq_frequency_table_cpuinfo(policy, table);
+	int ret;
 
-	if (!ret)
-		policy->freq_table = table;
+	ret = cpufreq_frequency_table_cpuinfo(policy, table);
+	if (ret)
+		return ret;
 
-	return ret;
+	policy->freq_table = table;
+	return set_freq_table_sorted(policy);
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 28690b284846..9ec033b4f2d9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -97,7 +97,6 @@ static inline u64 div_ext_fp(u64 x, u64 y)
  *			read from MPERF MSR between last and current sample
  * @tsc:		Difference of time stamp counter between last and
  *			current sample
- * @freq:		Effective frequency calculated from APERF/MPERF
  * @time:		Current time from scheduler
  *
  * This structure is used in the cpudata structure to store performance sample
@@ -109,7 +108,6 @@ struct sample {
 	u64 aperf;
 	u64 mperf;
 	u64 tsc;
-	int freq;
 	u64 time;
 };
 
@@ -282,9 +280,9 @@ struct cpu_defaults {
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);
 
-static struct pstate_adjust_policy pid_params;
-static struct pstate_funcs pstate_funcs;
-static int hwp_active;
+static struct pstate_adjust_policy pid_params __read_mostly;
+static struct pstate_funcs pstate_funcs __read_mostly;
+static int hwp_active __read_mostly;
 
 #ifdef CONFIG_ACPI
 static bool acpi_ppc;
@@ -808,7 +806,8 @@ static void __init intel_pstate_sysfs_expose_params(void)
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
-	wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
+	if (static_cpu_has(X86_FEATURE_HWP_NOTIFY))
+		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
@@ -945,7 +944,7 @@ static int core_get_max_pstate(void)
 			if (err)
 				goto skip_tar;
 
-			tdp_msr = MSR_CONFIG_TDP_NOMINAL + tdp_ctrl;
+			tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3);
 			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
 			if (err)
 				goto skip_tar;
@@ -973,7 +972,7 @@ static int core_get_turbo_pstate(void)
 	u64 value;
 	int nont, ret;
 
-	rdmsrl(MSR_NHM_TURBO_RATIO_LIMIT, value);
+	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
 	nont = core_get_max_pstate();
 	ret = (value) & 255;
 	if (ret <= nont)
@@ -1002,7 +1001,7 @@ static int knl_get_turbo_pstate(void)
 	u64 value;
 	int nont, ret;
 
-	rdmsrl(MSR_NHM_TURBO_RATIO_LIMIT, value);
+	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
 	nont = core_get_max_pstate();
 	ret = (((value) >> 8) & 0xFF);
 	if (ret <= nont)
@@ -1092,6 +1091,26 @@ static struct cpu_defaults knl_params = {
 	},
 };
 
+static struct cpu_defaults bxt_params = {
+	.pid_policy = {
+		.sample_rate_ms = 10,
+		.deadband = 0,
+		.setpoint = 60,
+		.p_gain_pct = 14,
+		.d_gain_pct = 0,
+		.i_gain_pct = 4,
+	},
+	.funcs = {
+		.get_max = core_get_max_pstate,
+		.get_max_physical = core_get_max_pstate_physical,
+		.get_min = core_get_min_pstate,
+		.get_turbo = core_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
+		.get_val = core_get_val,
+		.get_target_pstate = get_target_pstate_use_cpu_load,
+	},
+};
+
 static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 {
 	int max_perf = cpu->pstate.turbo_pstate;
@@ -1114,17 +1133,12 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static inline void intel_pstate_record_pstate(struct cpudata *cpu, int pstate)
-{
-	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
-	cpu->pstate.current_pstate = pstate;
-}
-
 static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 {
 	int pstate = cpu->pstate.min_pstate;
 
-	intel_pstate_record_pstate(cpu, pstate);
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
+	cpu->pstate.current_pstate = pstate;
 	/*
 	 * Generally, there is no guarantee that this code will always run on
 	 * the CPU being updated, so force the register update to run on the
@@ -1284,10 +1298,11 @@ static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
 
 	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 	pstate = clamp_t(int, pstate, min_perf, max_perf);
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
-	intel_pstate_record_pstate(cpu, pstate);
+	cpu->pstate.current_pstate = pstate;
 	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
 }
 
@@ -1352,11 +1367,12 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(INTEL_FAM6_SKYLAKE_DESKTOP,	core_params),
 	ICPU(INTEL_FAM6_BROADWELL_XEON_D,	core_params),
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_params),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		bxt_params),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
 
-static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] = {
+static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
 	ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params),
 	{}
 };
@@ -1576,12 +1592,12 @@ static struct cpufreq_driver intel_pstate_driver = {
 	.name		= "intel_pstate",
 };
 
-static int __initdata no_load;
-static int __initdata no_hwp;
-static int __initdata hwp_only;
-static unsigned int force_load;
+static int no_load __initdata;
+static int no_hwp __initdata;
+static int hwp_only __initdata;
+static unsigned int force_load __initdata;
 
-static int intel_pstate_msrs_not_valid(void)
+static int __init intel_pstate_msrs_not_valid(void)
 {
 	if (!pstate_funcs.get_max() ||
 	    !pstate_funcs.get_min() ||
@@ -1591,7 +1607,7 @@ static int intel_pstate_msrs_not_valid(void)
 	return 0;
 }
 
-static void copy_pid_params(struct pstate_adjust_policy *policy)
+static void __init copy_pid_params(struct pstate_adjust_policy *policy)
 {
 	pid_params.sample_rate_ms = policy->sample_rate_ms;
 	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
@@ -1602,7 +1618,7 @@ static void copy_pid_params(struct pstate_adjust_policy *policy)
 	pid_params.setpoint = policy->setpoint;
 }
 
-static void copy_cpu_funcs(struct pstate_funcs *funcs)
+static void __init copy_cpu_funcs(struct pstate_funcs *funcs)
 {
 	pstate_funcs.get_max   = funcs->get_max;
 	pstate_funcs.get_max_physical = funcs->get_max_physical;
@@ -1617,7 +1633,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 
 #ifdef CONFIG_ACPI
 
-static bool intel_pstate_no_acpi_pss(void)
+static bool __init intel_pstate_no_acpi_pss(void)
 {
 	int i;
 
@@ -1646,7 +1662,7 @@ static bool intel_pstate_no_acpi_pss(void)
 	return true;
 }
 
-static bool intel_pstate_has_acpi_ppc(void)
+static bool __init intel_pstate_has_acpi_ppc(void)
 {
 	int i;
 
@@ -1674,7 +1690,7 @@ struct hw_vendor_info {
 };
 
 /* Hardware vendor-specific info that has its own power management modes */
-static struct hw_vendor_info vendor_info[] = {
+static struct hw_vendor_info vendor_info[] __initdata = {
 	{1, "HP    ", "ProLiant", PSS},
 	{1, "ORACLE", "X4-2    ", PPC},
 	{1, "ORACLE", "X4-2L   ", PPC},
@@ -1693,7 +1709,7 @@ static struct hw_vendor_info vendor_info[] = {
 	{0, "", ""},
 };
 
-static bool intel_pstate_platform_pwr_mgmt_exists(void)
+static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
 {
 	struct acpi_table_header hdr;
 	struct hw_vendor_info *v_info;
diff --git a/drivers/cpufreq/mvebu-cpufreq.c b/drivers/cpufreq/mvebu-cpufreq.c
index e920889b9ac2..ed915ee85dd9 100644
--- a/drivers/cpufreq/mvebu-cpufreq.c
+++ b/drivers/cpufreq/mvebu-cpufreq.c
@@ -70,7 +70,7 @@ static int __init armada_xp_pmsu_cpufreq_init(void)
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 		if (IS_ERR(clk)) {
 			pr_err("Cannot get clock for CPU %d\n", cpu);
 			return PTR_ERR(clk);
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index a7ecb9a84c15..3f0ce2ae35ee 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -555,8 +555,6 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->min = policy->cpuinfo.min_freq =
 		ioread32(&pcch_hdr->minimum_frequency) * 1000;
 
-	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
-
 	pr_debug("init: policy->max is %d, policy->min is %d\n",
 		policy->max, policy->min);
 out:
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 6bd715b7f11c..87796e0864e9 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -64,12 +64,14 @@
 /**
  * struct global_pstate_info -	Per policy data structure to maintain history of
  *				global pstates
- * @highest_lpstate:		The local pstate from which we are ramping down
+ * @highest_lpstate_idx:	The local pstate index from which we are
+ *				ramping down
  * @elapsed_time:		Time in ms spent in ramping down from
- *				highest_lpstate
+ *				highest_lpstate_idx
  * @last_sampled_time:		Time from boot in ms when global pstates were
  *				last set
- * @last_lpstate,last_gpstate:	Last set values for local and global pstates
+ * @last_lpstate_idx,		Last set value of local pstate and global
+ * last_gpstate_idx		pstate in terms of cpufreq table index
  * @timer:			Is used for ramping down if cpu goes idle for
  *				a long time with global pstate held high
  * @gpstate_lock:		A spinlock to maintain synchronization between
@@ -77,11 +79,11 @@
  *				governer's target_index calls
  */
 struct global_pstate_info {
-	int highest_lpstate;
+	int highest_lpstate_idx;
 	unsigned int elapsed_time;
 	unsigned int last_sampled_time;
-	int last_lpstate;
-	int last_gpstate;
+	int last_lpstate_idx;
+	int last_gpstate_idx;
 	spinlock_t gpstate_lock;
 	struct timer_list timer;
 };
@@ -124,29 +126,47 @@ static int nr_chips;
 static DEFINE_PER_CPU(struct chip *, chip_info);
 
 /*
- * Note: The set of pstates consists of contiguous integers, the
- * smallest of which is indicated by powernv_pstate_info.min, the
- * largest of which is indicated by powernv_pstate_info.max.
+ * Note:
+ * The set of pstates consists of contiguous integers.
+ * powernv_pstate_info stores the index of the frequency table for
+ * max, min and nominal frequencies. It also stores number of
+ * available frequencies.
  *
- * The nominal pstate is the highest non-turbo pstate in this
- * platform. This is indicated by powernv_pstate_info.nominal.
+ * powernv_pstate_info.nominal indicates the index to the highest
+ * non-turbo frequency.
  */
 static struct powernv_pstate_info {
-	int min;
-	int max;
-	int nominal;
-	int nr_pstates;
+	unsigned int min;
+	unsigned int max;
+	unsigned int nominal;
+	unsigned int nr_pstates;
 } powernv_pstate_info;
 
+/* Use following macros for conversions between pstate_id and index */
+static inline int idx_to_pstate(unsigned int i)
+{
+	return powernv_freqs[i].driver_data;
+}
+
+static inline unsigned int pstate_to_idx(int pstate)
+{
+	/*
+	 * abs() is deliberately used so that is works with
+	 * both monotonically increasing and decreasing
+	 * pstate values
+	 */
+	return abs(pstate - idx_to_pstate(powernv_pstate_info.max));
+}
+
 static inline void reset_gpstates(struct cpufreq_policy *policy)
 {
 	struct global_pstate_info *gpstates = policy->driver_data;
 
-	gpstates->highest_lpstate = 0;
+	gpstates->highest_lpstate_idx = 0;
 	gpstates->elapsed_time = 0;
 	gpstates->last_sampled_time = 0;
-	gpstates->last_lpstate = 0;
-	gpstates->last_gpstate = 0;
+	gpstates->last_lpstate_idx = 0;
+	gpstates->last_gpstate_idx = 0;
 }
 
 /*
@@ -156,9 +176,10 @@ static inline void reset_gpstates(struct cpufreq_policy *policy)
 static int init_powernv_pstates(void)
 {
 	struct device_node *power_mgt;
-	int i, pstate_min, pstate_max, pstate_nominal, nr_pstates = 0;
+	int i, nr_pstates = 0;
 	const __be32 *pstate_ids, *pstate_freqs;
 	u32 len_ids, len_freqs;
+	u32 pstate_min, pstate_max, pstate_nominal;
 
 	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
 	if (!power_mgt) {
@@ -208,6 +229,7 @@ static int init_powernv_pstates(void)
 		return -ENODEV;
 	}
 
+	powernv_pstate_info.nr_pstates = nr_pstates;
 	pr_debug("NR PStates %d\n", nr_pstates);
 	for (i = 0; i < nr_pstates; i++) {
 		u32 id = be32_to_cpu(pstate_ids[i]);
@@ -216,15 +238,17 @@ static int init_powernv_pstates(void)
 		pr_debug("PState id %d freq %d MHz\n", id, freq);
 		powernv_freqs[i].frequency = freq * 1000; /* kHz */
 		powernv_freqs[i].driver_data = id;
+
+		if (id == pstate_max)
+			powernv_pstate_info.max = i;
+		else if (id == pstate_nominal)
+			powernv_pstate_info.nominal = i;
+		else if (id == pstate_min)
+			powernv_pstate_info.min = i;
 	}
+
 	/* End of list marker entry */
 	powernv_freqs[i].frequency = CPUFREQ_TABLE_END;
-
-	powernv_pstate_info.min = pstate_min;
-	powernv_pstate_info.max = pstate_max;
-	powernv_pstate_info.nominal = pstate_nominal;
-	powernv_pstate_info.nr_pstates = nr_pstates;
-
 	return 0;
 }
 
@@ -233,12 +257,12 @@ static unsigned int pstate_id_to_freq(int pstate_id)
 {
 	int i;
 
-	i = powernv_pstate_info.max - pstate_id;
+	i = pstate_to_idx(pstate_id);
 	if (i >= powernv_pstate_info.nr_pstates || i < 0) {
 		pr_warn("PState id %d outside of PState table, "
 			"reporting nominal id %d instead\n",
-			pstate_id, powernv_pstate_info.nominal);
-		i = powernv_pstate_info.max - powernv_pstate_info.nominal;
+			pstate_id, idx_to_pstate(powernv_pstate_info.nominal));
+		i = powernv_pstate_info.nominal;
 	}
 
 	return powernv_freqs[i].frequency;
@@ -252,7 +276,7 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
 					char *buf)
 {
 	return sprintf(buf, "%u\n",
-		pstate_id_to_freq(powernv_pstate_info.nominal));
+		powernv_freqs[powernv_pstate_info.nominal].frequency);
 }
 
 struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
@@ -426,7 +450,7 @@ static void set_pstate(void *data)
  */
 static inline unsigned int get_nominal_index(void)
 {
-	return powernv_pstate_info.max - powernv_pstate_info.nominal;
+	return powernv_pstate_info.nominal;
 }
 
 static void powernv_cpufreq_throttle_check(void *data)
@@ -435,20 +459,22 @@ static void powernv_cpufreq_throttle_check(void *data)
 	unsigned int cpu = smp_processor_id();
 	unsigned long pmsr;
 	int pmsr_pmax;
+	unsigned int pmsr_pmax_idx;
 
 	pmsr = get_pmspr(SPRN_PMSR);
 	chip = this_cpu_read(chip_info);
 
 	/* Check for Pmax Capping */
 	pmsr_pmax = (s8)PMSR_MAX(pmsr);
-	if (pmsr_pmax != powernv_pstate_info.max) {
+	pmsr_pmax_idx = pstate_to_idx(pmsr_pmax);
+	if (pmsr_pmax_idx != powernv_pstate_info.max) {
 		if (chip->throttled)
 			goto next;
 		chip->throttled = true;
-		if (pmsr_pmax < powernv_pstate_info.nominal) {
-			pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
+		if (pmsr_pmax_idx > powernv_pstate_info.nominal) {
+			pr_warn_once("CPU %d on Chip %u has Pmax(%d) reduced below nominal frequency(%d)\n",
 				     cpu, chip->id, pmsr_pmax,
-				     powernv_pstate_info.nominal);
+				     idx_to_pstate(powernv_pstate_info.nominal));
 			chip->throttle_sub_turbo++;
 		} else {
 			chip->throttle_turbo++;
@@ -484,34 +510,35 @@ next:
 
 /**
  * calc_global_pstate - Calculate global pstate
- * @elapsed_time:	Elapsed time in milliseconds
- * @local_pstate:	New local pstate
- * @highest_lpstate:	pstate from which its ramping down
+ * @elapsed_time:		Elapsed time in milliseconds
+ * @local_pstate_idx:		New local pstate
+ * @highest_lpstate_idx:	pstate from which its ramping down
  *
  * Finds the appropriate global pstate based on the pstate from which its
  * ramping down and the time elapsed in ramping down. It follows a quadratic
  * equation which ensures that it reaches ramping down to pmin in 5sec.
  */
 static inline int calc_global_pstate(unsigned int elapsed_time,
-				     int highest_lpstate, int local_pstate)
+				     int highest_lpstate_idx,
+				     int local_pstate_idx)
 {
-	int pstate_diff;
+	int index_diff;
 
 	/*
 	 * Using ramp_down_percent we get the percentage of rampdown
 	 * that we are expecting to be dropping. Difference between
-	 * highest_lpstate and powernv_pstate_info.min will give a absolute
+	 * highest_lpstate_idx and powernv_pstate_info.min will give a absolute
 	 * number of how many pstates we will drop eventually by the end of
 	 * 5 seconds, then just scale it get the number pstates to be dropped.
 	 */
-	pstate_diff =  ((int)ramp_down_percent(elapsed_time) *
-			(highest_lpstate - powernv_pstate_info.min)) / 100;
+	index_diff =  ((int)ramp_down_percent(elapsed_time) *
+			(powernv_pstate_info.min - highest_lpstate_idx)) / 100;
 
 	/* Ensure that global pstate is >= to local pstate */
-	if (highest_lpstate - pstate_diff < local_pstate)
-		return local_pstate;
+	if (highest_lpstate_idx + index_diff >= local_pstate_idx)
+		return local_pstate_idx;
 	else
-		return highest_lpstate - pstate_diff;
+		return highest_lpstate_idx + index_diff;
 }
 
 static inline void  queue_gpstate_timer(struct global_pstate_info *gpstates)
@@ -546,7 +573,7 @@ void gpstate_timer_handler(unsigned long data)
 {
 	struct cpufreq_policy *policy = (struct cpufreq_policy *)data;
 	struct global_pstate_info *gpstates = policy->driver_data;
-	int gpstate_id;
+	int gpstate_idx;
 	unsigned int time_diff = jiffies_to_msecs(jiffies)
 					- gpstates->last_sampled_time;
 	struct powernv_smp_call_data freq_data;
@@ -556,29 +583,29 @@ void gpstate_timer_handler(unsigned long data)
 
 	gpstates->last_sampled_time += time_diff;
 	gpstates->elapsed_time += time_diff;
-	freq_data.pstate_id = gpstates->last_lpstate;
+	freq_data.pstate_id = idx_to_pstate(gpstates->last_lpstate_idx);
 
-	if ((gpstates->last_gpstate == freq_data.pstate_id) ||
+	if ((gpstates->last_gpstate_idx == gpstates->last_lpstate_idx) ||
 	    (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME)) {
-		gpstate_id = freq_data.pstate_id;
+		gpstate_idx = pstate_to_idx(freq_data.pstate_id);
 		reset_gpstates(policy);
-		gpstates->highest_lpstate = freq_data.pstate_id;
+		gpstates->highest_lpstate_idx = gpstate_idx;
 	} else {
-		gpstate_id = calc_global_pstate(gpstates->elapsed_time,
-						gpstates->highest_lpstate,
-						freq_data.pstate_id);
+		gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
+						 gpstates->highest_lpstate_idx,
+						 freq_data.pstate_id);
 	}
 
 	/*
 	 * If local pstate is equal to global pstate, rampdown is over
 	 * So timer is not required to be queued.
 	 */
-	if (gpstate_id != freq_data.pstate_id)
+	if (gpstate_idx != gpstates->last_lpstate_idx)
 		queue_gpstate_timer(gpstates);
 
-	freq_data.gpstate_id = gpstate_id;
-	gpstates->last_gpstate = freq_data.gpstate_id;
-	gpstates->last_lpstate = freq_data.pstate_id;
+	freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
+	gpstates->last_gpstate_idx = pstate_to_idx(freq_data.gpstate_id);
+	gpstates->last_lpstate_idx = pstate_to_idx(freq_data.pstate_id);
 
 	spin_unlock(&gpstates->gpstate_lock);
 
@@ -595,7 +622,7 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 					unsigned int new_index)
 {
 	struct powernv_smp_call_data freq_data;
-	unsigned int cur_msec, gpstate_id;
+	unsigned int cur_msec, gpstate_idx;
 	struct global_pstate_info *gpstates = policy->driver_data;
 
 	if (unlikely(rebooting) && new_index != get_nominal_index())
@@ -607,15 +634,15 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 	cur_msec = jiffies_to_msecs(get_jiffies_64());
 
 	spin_lock(&gpstates->gpstate_lock);
-	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
+	freq_data.pstate_id = idx_to_pstate(new_index);
 
 	if (!gpstates->last_sampled_time) {
-		gpstate_id = freq_data.pstate_id;
-		gpstates->highest_lpstate = freq_data.pstate_id;
+		gpstate_idx = new_index;
+		gpstates->highest_lpstate_idx = new_index;
 		goto gpstates_done;
 	}
 
-	if (gpstates->last_gpstate > freq_data.pstate_id) {
+	if (gpstates->last_gpstate_idx < new_index) {
 		gpstates->elapsed_time += cur_msec -
 						 gpstates->last_sampled_time;
 
@@ -626,34 +653,34 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 		 */
 		if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) {
 			reset_gpstates(policy);
-			gpstates->highest_lpstate = freq_data.pstate_id;
-			gpstate_id = freq_data.pstate_id;
+			gpstates->highest_lpstate_idx = new_index;
+			gpstate_idx = new_index;
 		} else {
 		/* Elaspsed_time is less than 5 seconds, continue to rampdown */
-			gpstate_id = calc_global_pstate(gpstates->elapsed_time,
-							gpstates->highest_lpstate,
-							freq_data.pstate_id);
+			gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
+							 gpstates->highest_lpstate_idx,
+							 new_index);
 		}
 	} else {
 		reset_gpstates(policy);
-		gpstates->highest_lpstate = freq_data.pstate_id;
-		gpstate_id = freq_data.pstate_id;
+		gpstates->highest_lpstate_idx = new_index;
+		gpstate_idx = new_index;
 	}
 
 	/*
 	 * If local pstate is equal to global pstate, rampdown is over
 	 * So timer is not required to be queued.
 	 */
-	if (gpstate_id != freq_data.pstate_id)
+	if (gpstate_idx != new_index)
 		queue_gpstate_timer(gpstates);
 	else
 		del_timer_sync(&gpstates->timer);
 
 gpstates_done:
-	freq_data.gpstate_id = gpstate_id;
+	freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
 	gpstates->last_sampled_time = cur_msec;
-	gpstates->last_gpstate = freq_data.gpstate_id;
-	gpstates->last_lpstate = freq_data.pstate_id;
+	gpstates->last_gpstate_idx = gpstate_idx;
+	gpstates->last_lpstate_idx = new_index;
 
 	spin_unlock(&gpstates->gpstate_lock);
 
@@ -759,9 +786,7 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 		struct cpufreq_policy policy;
 
 		cpufreq_get_policy(&policy, cpu);
-		cpufreq_frequency_table_target(&policy, policy.freq_table,
-					       policy.cur,
-					       CPUFREQ_RELATION_C, &index);
+		index = cpufreq_table_find_index_c(&policy, policy.cur);
 		powernv_cpufreq_target_index(&policy, index);
 		cpumask_andnot(&mask, &mask, policy.cpus);
 	}
@@ -847,8 +872,8 @@ static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 	struct powernv_smp_call_data freq_data;
 	struct global_pstate_info *gpstates = policy->driver_data;
 
-	freq_data.pstate_id = powernv_pstate_info.min;
-	freq_data.gpstate_id = powernv_pstate_info.min;
+	freq_data.pstate_id = idx_to_pstate(powernv_pstate_info.min);
+	freq_data.gpstate_id = idx_to_pstate(powernv_pstate_info.min);
 	smp_call_function_single(policy->cpu, set_pstate, &freq_data, 1);
 	del_timer_sync(&gpstates->timer);
 }
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index 7c4cd5c634f2..dc112481a408 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -94,7 +94,7 @@ static int pmi_notifier(struct notifier_block *nb,
 				       unsigned long event, void *data)
 {
 	struct cpufreq_policy *policy = data;
-	struct cpufreq_frequency_table *cbe_freqs;
+	struct cpufreq_frequency_table *cbe_freqs = policy->freq_table;
 	u8 node;
 
 	/* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY
@@ -103,7 +103,6 @@ static int pmi_notifier(struct notifier_block *nb,
 	if (event == CPUFREQ_START)
 		return 0;
 
-	cbe_freqs = cpufreq_frequency_get_table(policy->cpu);
 	node = cbe_cpu_to_node(policy->cpu);
 
 	pr_debug("got notified, event=%lu, node=%u\n", event, node);
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index ae8eaed77b70..7b596fa38ad2 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -293,12 +293,8 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 		     __func__, policy, target_freq, relation);
 
 	if (ftab) {
-		if (cpufreq_frequency_table_target(policy, ftab,
-						   target_freq, relation,
-						   &index)) {
-			s3c_freq_dbg("%s: table failed\n", __func__);
-			return -EINVAL;
-		}
+		index = cpufreq_frequency_table_target(policy, target_freq,
+						       relation);
 
 		s3c_freq_dbg("%s: adjust %d to entry %d (%u)\n", __func__,
 			     target_freq, index, ftab[index].frequency);
@@ -315,7 +311,6 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 		pll = NULL;
 	} else {
 		struct cpufreq_policy tmp_policy;
-		int ret;
 
 		/* we keep the cpu pll table in Hz, to ensure we get an
 		 * accurate value for the PLL output. */
@@ -323,20 +318,14 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 		tmp_policy.min = policy->min * 1000;
 		tmp_policy.max = policy->max * 1000;
 		tmp_policy.cpu = policy->cpu;
+		tmp_policy.freq_table = pll_reg;
 
-		/* cpufreq_frequency_table_target uses a pointer to 'index'
-		 * which is the number of the table entry, not the value of
+		/* cpufreq_frequency_table_target returns the index
+		 * of the table entry, not the value of
 		 * the table entry's index field. */
 
-		ret = cpufreq_frequency_table_target(&tmp_policy, pll_reg,
-						     target_freq, relation,
-						     &index);
-
-		if (ret < 0) {
-			pr_err("%s: no PLL available\n", __func__);
-			goto err_notpossible;
-		}
-
+		index = cpufreq_frequency_table_target(&tmp_policy, target_freq,
+						       relation);
 		pll = pll_reg + index;
 
 		s3c_freq_dbg("%s: target %u => %u\n",
@@ -346,10 +335,6 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 	}
 
 	return s3c_cpufreq_settarget(policy, target_freq, pll);
-
- err_notpossible:
-	pr_err("no compatible settings for %d\n", target_freq);
-	return -EINVAL;
 }
 
 struct clk *s3c_cpufreq_clk_get(struct device *dev, const char *name)
@@ -571,11 +556,7 @@ static int s3c_cpufreq_build_freq(void)
 {
 	int size, ret;
 
-	if (!cpu_cur.info->calc_freqtable)
-		return -EINVAL;
-
 	kfree(ftab);
-	ftab = NULL;
 
 	size = cpu_cur.info->calc_freqtable(&cpu_cur, NULL, 0);
 	size++;
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 06d85917b6d5..9e07588ea9f5 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -246,12 +246,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 	new_freq = s5pv210_freq_table[index].frequency;
 
 	/* Finding current running level index */
-	if (cpufreq_frequency_table_target(policy, s5pv210_freq_table,
-					   old_freq, CPUFREQ_RELATION_H,
-					   &priv_index)) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	priv_index = cpufreq_table_find_index_h(policy, old_freq);
 
 	arm_volt = dvs_conf[index].arm_volt;
 	int_volt = dvs_conf[index].int_volt;
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index e342565e8715..4ba3d3fe142f 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -36,26 +36,12 @@
 static int arm_enter_idle_state(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv, int idx)
 {
-	int ret;
-
-	if (!idx) {
-		cpu_do_idle();
-		return idx;
-	}
-
-	ret = cpu_pm_enter();
-	if (!ret) {
-		/*
-		 * Pass idle state index to cpu_suspend which in turn will
-		 * call the CPU ops suspend protocol with idle index as a
-		 * parameter.
-		 */
-		ret = arm_cpuidle_suspend(idx);
-
-		cpu_pm_exit();
-	}
-
-	return ret ? -1 : idx;
+	/*
+	 * Pass idle state index to arm_cpuidle_suspend which in turn
+	 * will call the CPU ops suspend protocol with idle index as a
+	 * parameter.
+	 */
+	return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, idx);
 }
 
 static struct cpuidle_driver arm_idle_driver = {
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index d77ba2f12242..1af94e2d1a25 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -159,6 +159,19 @@ config CRYPTO_GHASH_S390
 
 	  It is available as of z196.
 
+config CRYPTO_CRC32_S390
+	tristate "CRC-32 algorithms"
+	depends on S390
+	select CRYPTO_HASH
+	select CRC32
+	help
+	  Select this option if you want to use hardware accelerated
+	  implementations of CRC algorithms.  With this option, you
+	  can optimize the computation of CRC-32 (IEEE 802.3 Ethernet)
+	  and CRC-32C (Castagnoli).
+
+	  It is available with IBM z13 or later.
+
 config CRYPTO_DEV_MV_CESA
 	tristate "Marvell's Cryptographic Engine"
 	depends on PLAT_ORION
diff --git a/drivers/crypto/bfin_crc.c b/drivers/crypto/bfin_crc.c
index 95b73968cf72..10db7df366c8 100644
--- a/drivers/crypto/bfin_crc.c
+++ b/drivers/crypto/bfin_crc.c
@@ -588,11 +588,6 @@ static int bfin_crypto_crc_probe(struct platform_device *pdev)
 	crypto_init_queue(&crc->queue, CRC_CCRYPTO_QUEUE_LENGTH);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "Cannot get IORESOURCE_MEM\n");
-		return -ENOENT;
-	}
-
 	crc->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR((void *)crc->regs)) {
 		dev_err(&pdev->dev, "Cannot map CRC IO\n");
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index 5652a53415dc..64bf3024b680 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -1,6 +1,6 @@
 config CRYPTO_DEV_FSL_CAAM
 	tristate "Freescale CAAM-Multicore driver backend"
-	depends on FSL_SOC || ARCH_MXC
+	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE
 	help
 	  Enables the driver module for Freescale's Cryptographic Accelerator
 	  and Assurance Module (CAAM), also known as the SEC version 4 (SEC4).
@@ -99,6 +99,18 @@ config CRYPTO_DEV_FSL_CAAM_AHASH_API
 	  To compile this as a module, choose M here: the module
 	  will be called caamhash.
 
+config CRYPTO_DEV_FSL_CAAM_PKC_API
+        tristate "Register public key cryptography implementations with Crypto API"
+        depends on CRYPTO_DEV_FSL_CAAM && CRYPTO_DEV_FSL_CAAM_JR
+        default y
+        select CRYPTO_RSA
+        help
+          Selecting this will allow SEC Public key support for RSA.
+          Supported cryptographic primitives: encryption, decryption,
+          signature and verification.
+          To compile this as a module, choose M here: the module
+          will be called caam_pkc.
+
 config CRYPTO_DEV_FSL_CAAM_RNG_API
 	tristate "Register caam device for hwrng API"
 	depends on CRYPTO_DEV_FSL_CAAM && CRYPTO_DEV_FSL_CAAM_JR
@@ -116,10 +128,6 @@ config CRYPTO_DEV_FSL_CAAM_IMX
 	def_bool SOC_IMX6 || SOC_IMX7D
 	depends on CRYPTO_DEV_FSL_CAAM
 
-config CRYPTO_DEV_FSL_CAAM_LE
-	def_bool CRYPTO_DEV_FSL_CAAM_IMX || SOC_LS1021A
-	depends on CRYPTO_DEV_FSL_CAAM
-
 config CRYPTO_DEV_FSL_CAAM_DEBUG
 	bool "Enable debug output in CAAM driver"
 	depends on CRYPTO_DEV_FSL_CAAM
diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile
index 550758a333e7..08bf5515ae8a 100644
--- a/drivers/crypto/caam/Makefile
+++ b/drivers/crypto/caam/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the CAAM backend and dependent components
 #
 ifeq ($(CONFIG_CRYPTO_DEV_FSL_CAAM_DEBUG), y)
-	EXTRA_CFLAGS := -DDEBUG
+	ccflags-y := -DDEBUG
 endif
 
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM) += caam.o
@@ -10,6 +10,8 @@ obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_JR) += caam_jr.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API) += caamalg.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_AHASH_API) += caamhash.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API) += caamrng.o
+obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_PKC_API) += caam_pkc.o
 
 caam-objs := ctrl.o
 caam_jr-objs := jr.o key_gen.o error.o
+caam_pkc-y := caampkc.o pkc_desc.o
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 5845d4a08797..f1ecc8df8d41 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -847,7 +847,7 @@ static int ahash_update_ctx(struct ahash_request *req)
 							 *next_buflen, 0);
 		} else {
 			(edesc->sec4_sg + sec4_sg_src_index - 1)->len |=
-							SEC4_SG_LEN_FIN;
+				cpu_to_caam32(SEC4_SG_LEN_FIN);
 		}
 
 		state->current_buf = !state->current_buf;
@@ -949,7 +949,8 @@ static int ahash_final_ctx(struct ahash_request *req)
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
 						buf, state->buf_dma, buflen,
 						last_buflen);
-	(edesc->sec4_sg + sec4_sg_src_index - 1)->len |= SEC4_SG_LEN_FIN;
+	(edesc->sec4_sg + sec4_sg_src_index - 1)->len |=
+		cpu_to_caam32(SEC4_SG_LEN_FIN);
 
 	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
new file mode 100644
index 000000000000..851015e652b8
--- /dev/null
+++ b/drivers/crypto/caam/caampkc.c
@@ -0,0 +1,607 @@
+/*
+ * caam - Freescale FSL CAAM support for Public Key Cryptography
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * There is no Shared Descriptor for PKC so that the Job Descriptor must carry
+ * all the desired key parameters, input and output pointers.
+ */
+#include "compat.h"
+#include "regs.h"
+#include "intern.h"
+#include "jr.h"
+#include "error.h"
+#include "desc_constr.h"
+#include "sg_sw_sec4.h"
+#include "caampkc.h"
+
+#define DESC_RSA_PUB_LEN	(2 * CAAM_CMD_SZ + sizeof(struct rsa_pub_pdb))
+#define DESC_RSA_PRIV_F1_LEN	(2 * CAAM_CMD_SZ + \
+				 sizeof(struct rsa_priv_f1_pdb))
+
+static void rsa_io_unmap(struct device *dev, struct rsa_edesc *edesc,
+			 struct akcipher_request *req)
+{
+	dma_unmap_sg(dev, req->dst, edesc->dst_nents, DMA_FROM_DEVICE);
+	dma_unmap_sg(dev, req->src, edesc->src_nents, DMA_TO_DEVICE);
+
+	if (edesc->sec4_sg_bytes)
+		dma_unmap_single(dev, edesc->sec4_sg_dma, edesc->sec4_sg_bytes,
+				 DMA_TO_DEVICE);
+}
+
+static void rsa_pub_unmap(struct device *dev, struct rsa_edesc *edesc,
+			  struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct rsa_pub_pdb *pdb = &edesc->pdb.pub;
+
+	dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+	dma_unmap_single(dev, pdb->e_dma, key->e_sz, DMA_TO_DEVICE);
+}
+
+static void rsa_priv_f1_unmap(struct device *dev, struct rsa_edesc *edesc,
+			      struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct rsa_priv_f1_pdb *pdb = &edesc->pdb.priv_f1;
+
+	dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+	dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE);
+}
+
+/* RSA Job Completion handler */
+static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context)
+{
+	struct akcipher_request *req = context;
+	struct rsa_edesc *edesc;
+
+	if (err)
+		caam_jr_strstatus(dev, err);
+
+	edesc = container_of(desc, struct rsa_edesc, hw_desc[0]);
+
+	rsa_pub_unmap(dev, edesc, req);
+	rsa_io_unmap(dev, edesc, req);
+	kfree(edesc);
+
+	akcipher_request_complete(req, err);
+}
+
+static void rsa_priv_f1_done(struct device *dev, u32 *desc, u32 err,
+			     void *context)
+{
+	struct akcipher_request *req = context;
+	struct rsa_edesc *edesc;
+
+	if (err)
+		caam_jr_strstatus(dev, err);
+
+	edesc = container_of(desc, struct rsa_edesc, hw_desc[0]);
+
+	rsa_priv_f1_unmap(dev, edesc, req);
+	rsa_io_unmap(dev, edesc, req);
+	kfree(edesc);
+
+	akcipher_request_complete(req, err);
+}
+
+static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
+					 size_t desclen)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct device *dev = ctx->dev;
+	struct rsa_edesc *edesc;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	int sgc;
+	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
+	int src_nents, dst_nents;
+
+	src_nents = sg_nents_for_len(req->src, req->src_len);
+	dst_nents = sg_nents_for_len(req->dst, req->dst_len);
+
+	if (src_nents > 1)
+		sec4_sg_len = src_nents;
+	if (dst_nents > 1)
+		sec4_sg_len += dst_nents;
+
+	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc, hw desc commands and link tables */
+	edesc = kzalloc(sizeof(*edesc) + desclen + sec4_sg_bytes,
+			GFP_DMA | flags);
+	if (!edesc)
+		return ERR_PTR(-ENOMEM);
+
+	sgc = dma_map_sg(dev, req->src, src_nents, DMA_TO_DEVICE);
+	if (unlikely(!sgc)) {
+		dev_err(dev, "unable to map source\n");
+		goto src_fail;
+	}
+
+	sgc = dma_map_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
+	if (unlikely(!sgc)) {
+		dev_err(dev, "unable to map destination\n");
+		goto dst_fail;
+	}
+
+	edesc->sec4_sg = (void *)edesc + sizeof(*edesc) + desclen;
+
+	sec4_sg_index = 0;
+	if (src_nents > 1) {
+		sg_to_sec4_sg_last(req->src, src_nents, edesc->sec4_sg, 0);
+		sec4_sg_index += src_nents;
+	}
+	if (dst_nents > 1)
+		sg_to_sec4_sg_last(req->dst, dst_nents,
+				   edesc->sec4_sg + sec4_sg_index, 0);
+
+	/* Save nents for later use in Job Descriptor */
+	edesc->src_nents = src_nents;
+	edesc->dst_nents = dst_nents;
+
+	if (!sec4_sg_bytes)
+		return edesc;
+
+	edesc->sec4_sg_dma = dma_map_single(dev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, edesc->sec4_sg_dma)) {
+		dev_err(dev, "unable to map S/G table\n");
+		goto sec4_sg_fail;
+	}
+
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+
+	return edesc;
+
+sec4_sg_fail:
+	dma_unmap_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
+dst_fail:
+	dma_unmap_sg(dev, req->src, src_nents, DMA_TO_DEVICE);
+src_fail:
+	kfree(edesc);
+	return ERR_PTR(-ENOMEM);
+}
+
+static int set_rsa_pub_pdb(struct akcipher_request *req,
+			   struct rsa_edesc *edesc)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *dev = ctx->dev;
+	struct rsa_pub_pdb *pdb = &edesc->pdb.pub;
+	int sec4_sg_index = 0;
+
+	pdb->n_dma = dma_map_single(dev, key->n, key->n_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->n_dma)) {
+		dev_err(dev, "Unable to map RSA modulus memory\n");
+		return -ENOMEM;
+	}
+
+	pdb->e_dma = dma_map_single(dev, key->e, key->e_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->e_dma)) {
+		dev_err(dev, "Unable to map RSA public exponent memory\n");
+		dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
+
+	if (edesc->src_nents > 1) {
+		pdb->sgf |= RSA_PDB_SGF_F;
+		pdb->f_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += edesc->src_nents;
+	} else {
+		pdb->f_dma = sg_dma_address(req->src);
+	}
+
+	if (edesc->dst_nents > 1) {
+		pdb->sgf |= RSA_PDB_SGF_G;
+		pdb->g_dma = edesc->sec4_sg_dma +
+			     sec4_sg_index * sizeof(struct sec4_sg_entry);
+	} else {
+		pdb->g_dma = sg_dma_address(req->dst);
+	}
+
+	pdb->sgf |= (key->e_sz << RSA_PDB_E_SHIFT) | key->n_sz;
+	pdb->f_len = req->src_len;
+
+	return 0;
+}
+
+static int set_rsa_priv_f1_pdb(struct akcipher_request *req,
+			       struct rsa_edesc *edesc)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *dev = ctx->dev;
+	struct rsa_priv_f1_pdb *pdb = &edesc->pdb.priv_f1;
+	int sec4_sg_index = 0;
+
+	pdb->n_dma = dma_map_single(dev, key->n, key->n_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->n_dma)) {
+		dev_err(dev, "Unable to map modulus memory\n");
+		return -ENOMEM;
+	}
+
+	pdb->d_dma = dma_map_single(dev, key->d, key->d_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->d_dma)) {
+		dev_err(dev, "Unable to map RSA private exponent memory\n");
+		dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
+
+	if (edesc->src_nents > 1) {
+		pdb->sgf |= RSA_PRIV_PDB_SGF_G;
+		pdb->g_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += edesc->src_nents;
+	} else {
+		pdb->g_dma = sg_dma_address(req->src);
+	}
+
+	if (edesc->dst_nents > 1) {
+		pdb->sgf |= RSA_PRIV_PDB_SGF_F;
+		pdb->f_dma = edesc->sec4_sg_dma +
+			     sec4_sg_index * sizeof(struct sec4_sg_entry);
+	} else {
+		pdb->f_dma = sg_dma_address(req->dst);
+	}
+
+	pdb->sgf |= (key->d_sz << RSA_PDB_D_SHIFT) | key->n_sz;
+
+	return 0;
+}
+
+static int caam_rsa_enc(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *jrdev = ctx->dev;
+	struct rsa_edesc *edesc;
+	int ret;
+
+	if (unlikely(!key->n || !key->e))
+		return -EINVAL;
+
+	if (req->dst_len < key->n_sz) {
+		req->dst_len = key->n_sz;
+		dev_err(jrdev, "Output buffer length less than parameter n\n");
+		return -EOVERFLOW;
+	}
+
+	/* Allocate extended descriptor */
+	edesc = rsa_edesc_alloc(req, DESC_RSA_PUB_LEN);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Set RSA Encrypt Protocol Data Block */
+	ret = set_rsa_pub_pdb(req, edesc);
+	if (ret)
+		goto init_fail;
+
+	/* Initialize Job Descriptor */
+	init_rsa_pub_desc(edesc->hw_desc, &edesc->pdb.pub);
+
+	ret = caam_jr_enqueue(jrdev, edesc->hw_desc, rsa_pub_done, req);
+	if (!ret)
+		return -EINPROGRESS;
+
+	rsa_pub_unmap(jrdev, edesc, req);
+
+init_fail:
+	rsa_io_unmap(jrdev, edesc, req);
+	kfree(edesc);
+	return ret;
+}
+
+static int caam_rsa_dec(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *jrdev = ctx->dev;
+	struct rsa_edesc *edesc;
+	int ret;
+
+	if (unlikely(!key->n || !key->d))
+		return -EINVAL;
+
+	if (req->dst_len < key->n_sz) {
+		req->dst_len = key->n_sz;
+		dev_err(jrdev, "Output buffer length less than parameter n\n");
+		return -EOVERFLOW;
+	}
+
+	/* Allocate extended descriptor */
+	edesc = rsa_edesc_alloc(req, DESC_RSA_PRIV_F1_LEN);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Set RSA Decrypt Protocol Data Block - Private Key Form #1 */
+	ret = set_rsa_priv_f1_pdb(req, edesc);
+	if (ret)
+		goto init_fail;
+
+	/* Initialize Job Descriptor */
+	init_rsa_priv_f1_desc(edesc->hw_desc, &edesc->pdb.priv_f1);
+
+	ret = caam_jr_enqueue(jrdev, edesc->hw_desc, rsa_priv_f1_done, req);
+	if (!ret)
+		return -EINPROGRESS;
+
+	rsa_priv_f1_unmap(jrdev, edesc, req);
+
+init_fail:
+	rsa_io_unmap(jrdev, edesc, req);
+	kfree(edesc);
+	return ret;
+}
+
+static void caam_rsa_free_key(struct caam_rsa_key *key)
+{
+	kzfree(key->d);
+	kfree(key->e);
+	kfree(key->n);
+	key->d = NULL;
+	key->e = NULL;
+	key->n = NULL;
+	key->d_sz = 0;
+	key->e_sz = 0;
+	key->n_sz = 0;
+}
+
+/**
+ * caam_read_raw_data - Read a raw byte stream as a positive integer.
+ * The function skips buffer's leading zeros, copies the remained data
+ * to a buffer allocated in the GFP_DMA | GFP_KERNEL zone and returns
+ * the address of the new buffer.
+ *
+ * @buf   : The data to read
+ * @nbytes: The amount of data to read
+ */
+static inline u8 *caam_read_raw_data(const u8 *buf, size_t *nbytes)
+{
+	u8 *val;
+
+	while (!*buf && *nbytes) {
+		buf++;
+		(*nbytes)--;
+	}
+
+	val = kzalloc(*nbytes, GFP_DMA | GFP_KERNEL);
+	if (!val)
+		return NULL;
+
+	memcpy(val, buf, *nbytes);
+
+	return val;
+}
+
+static int caam_rsa_check_key_length(unsigned int len)
+{
+	if (len > 4096)
+		return -EINVAL;
+	return 0;
+}
+
+static int caam_rsa_set_pub_key(struct crypto_akcipher *tfm, const void *key,
+				unsigned int keylen)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
+	struct caam_rsa_key *rsa_key = &ctx->key;
+	int ret;
+
+	/* Free the old RSA key if any */
+	caam_rsa_free_key(rsa_key);
+
+	ret = rsa_parse_pub_key(&raw_key, key, keylen);
+	if (ret)
+		return ret;
+
+	/* Copy key in DMA zone */
+	rsa_key->e = kzalloc(raw_key.e_sz, GFP_DMA | GFP_KERNEL);
+	if (!rsa_key->e)
+		goto err;
+
+	/*
+	 * Skip leading zeros and copy the positive integer to a buffer
+	 * allocated in the GFP_DMA | GFP_KERNEL zone. The decryption descriptor
+	 * expects a positive integer for the RSA modulus and uses its length as
+	 * decryption output length.
+	 */
+	rsa_key->n = caam_read_raw_data(raw_key.n, &raw_key.n_sz);
+	if (!rsa_key->n)
+		goto err;
+
+	if (caam_rsa_check_key_length(raw_key.n_sz << 3)) {
+		caam_rsa_free_key(rsa_key);
+		return -EINVAL;
+	}
+
+	rsa_key->e_sz = raw_key.e_sz;
+	rsa_key->n_sz = raw_key.n_sz;
+
+	memcpy(rsa_key->e, raw_key.e, raw_key.e_sz);
+
+	return 0;
+err:
+	caam_rsa_free_key(rsa_key);
+	return -ENOMEM;
+}
+
+static int caam_rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key,
+				 unsigned int keylen)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
+	struct caam_rsa_key *rsa_key = &ctx->key;
+	int ret;
+
+	/* Free the old RSA key if any */
+	caam_rsa_free_key(rsa_key);
+
+	ret = rsa_parse_priv_key(&raw_key, key, keylen);
+	if (ret)
+		return ret;
+
+	/* Copy key in DMA zone */
+	rsa_key->d = kzalloc(raw_key.d_sz, GFP_DMA | GFP_KERNEL);
+	if (!rsa_key->d)
+		goto err;
+
+	rsa_key->e = kzalloc(raw_key.e_sz, GFP_DMA | GFP_KERNEL);
+	if (!rsa_key->e)
+		goto err;
+
+	/*
+	 * Skip leading zeros and copy the positive integer to a buffer
+	 * allocated in the GFP_DMA | GFP_KERNEL zone. The decryption descriptor
+	 * expects a positive integer for the RSA modulus and uses its length as
+	 * decryption output length.
+	 */
+	rsa_key->n = caam_read_raw_data(raw_key.n, &raw_key.n_sz);
+	if (!rsa_key->n)
+		goto err;
+
+	if (caam_rsa_check_key_length(raw_key.n_sz << 3)) {
+		caam_rsa_free_key(rsa_key);
+		return -EINVAL;
+	}
+
+	rsa_key->d_sz = raw_key.d_sz;
+	rsa_key->e_sz = raw_key.e_sz;
+	rsa_key->n_sz = raw_key.n_sz;
+
+	memcpy(rsa_key->d, raw_key.d, raw_key.d_sz);
+	memcpy(rsa_key->e, raw_key.e, raw_key.e_sz);
+
+	return 0;
+
+err:
+	caam_rsa_free_key(rsa_key);
+	return -ENOMEM;
+}
+
+static int caam_rsa_max_size(struct crypto_akcipher *tfm)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+
+	return (key->n) ? key->n_sz : -EINVAL;
+}
+
+/* Per session pkc's driver context creation function */
+static int caam_rsa_init_tfm(struct crypto_akcipher *tfm)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	ctx->dev = caam_jr_alloc();
+
+	if (IS_ERR(ctx->dev)) {
+		dev_err(ctx->dev, "Job Ring Device allocation for transform failed\n");
+		return PTR_ERR(ctx->dev);
+	}
+
+	return 0;
+}
+
+/* Per session pkc's driver context cleanup function */
+static void caam_rsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+
+	caam_rsa_free_key(key);
+	caam_jr_free(ctx->dev);
+}
+
+static struct akcipher_alg caam_rsa = {
+	.encrypt = caam_rsa_enc,
+	.decrypt = caam_rsa_dec,
+	.sign = caam_rsa_dec,
+	.verify = caam_rsa_enc,
+	.set_pub_key = caam_rsa_set_pub_key,
+	.set_priv_key = caam_rsa_set_priv_key,
+	.max_size = caam_rsa_max_size,
+	.init = caam_rsa_init_tfm,
+	.exit = caam_rsa_exit_tfm,
+	.base = {
+		.cra_name = "rsa",
+		.cra_driver_name = "rsa-caam",
+		.cra_priority = 3000,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct caam_rsa_ctx),
+	},
+};
+
+/* Public Key Cryptography module initialization handler */
+static int __init caam_pkc_init(void)
+{
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	struct caam_drv_private *priv;
+	u32 cha_inst, pk_inst;
+	int err;
+
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node) {
+		dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec4.0");
+		if (!dev_node)
+			return -ENODEV;
+	}
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev) {
+		of_node_put(dev_node);
+		return -ENODEV;
+	}
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+	of_node_put(dev_node);
+
+	/*
+	 * If priv is NULL, it's probably because the caam driver wasn't
+	 * properly initialized (e.g. RNG4 init failed). Thus, bail out here.
+	 */
+	if (!priv)
+		return -ENODEV;
+
+	/* Determine public key hardware accelerator presence. */
+	cha_inst = rd_reg32(&priv->ctrl->perfmon.cha_num_ls);
+	pk_inst = (cha_inst & CHA_ID_LS_PK_MASK) >> CHA_ID_LS_PK_SHIFT;
+
+	/* Do not register algorithms if PKHA is not present. */
+	if (!pk_inst)
+		return -ENODEV;
+
+	err = crypto_register_akcipher(&caam_rsa);
+	if (err)
+		dev_warn(ctrldev, "%s alg registration failed\n",
+			 caam_rsa.base.cra_driver_name);
+	else
+		dev_info(ctrldev, "caam pkc algorithms registered in /proc/crypto\n");
+
+	return err;
+}
+
+static void __exit caam_pkc_exit(void)
+{
+	crypto_unregister_akcipher(&caam_rsa);
+}
+
+module_init(caam_pkc_init);
+module_exit(caam_pkc_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("FSL CAAM support for PKC functions of crypto API");
+MODULE_AUTHOR("Freescale Semiconductor");
diff --git a/drivers/crypto/caam/caampkc.h b/drivers/crypto/caam/caampkc.h
new file mode 100644
index 000000000000..f595d159b112
--- /dev/null
+++ b/drivers/crypto/caam/caampkc.h
@@ -0,0 +1,70 @@
+/*
+ * caam - Freescale FSL CAAM support for Public Key Cryptography descriptors
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * There is no Shared Descriptor for PKC so that the Job Descriptor must carry
+ * all the desired key parameters, input and output pointers.
+ */
+
+#ifndef _PKC_DESC_H_
+#define _PKC_DESC_H_
+#include "compat.h"
+#include "pdb.h"
+
+/**
+ * caam_rsa_key - CAAM RSA key structure. Keys are allocated in DMA zone.
+ * @n           : RSA modulus raw byte stream
+ * @e           : RSA public exponent raw byte stream
+ * @d           : RSA private exponent raw byte stream
+ * @n_sz        : length in bytes of RSA modulus n
+ * @e_sz        : length in bytes of RSA public exponent
+ * @d_sz        : length in bytes of RSA private exponent
+ */
+struct caam_rsa_key {
+	u8 *n;
+	u8 *e;
+	u8 *d;
+	size_t n_sz;
+	size_t e_sz;
+	size_t d_sz;
+};
+
+/**
+ * caam_rsa_ctx - per session context.
+ * @key         : RSA key in DMA zone
+ * @dev         : device structure
+ */
+struct caam_rsa_ctx {
+	struct caam_rsa_key key;
+	struct device *dev;
+};
+
+/**
+ * rsa_edesc - s/w-extended rsa descriptor
+ * @src_nents     : number of segments in input scatterlist
+ * @dst_nents     : number of segments in output scatterlist
+ * @sec4_sg_bytes : length of h/w link table
+ * @sec4_sg_dma   : dma address of h/w link table
+ * @sec4_sg       : pointer to h/w link table
+ * @pdb           : specific RSA Protocol Data Block (PDB)
+ * @hw_desc       : descriptor followed by link tables if any
+ */
+struct rsa_edesc {
+	int src_nents;
+	int dst_nents;
+	int sec4_sg_bytes;
+	dma_addr_t sec4_sg_dma;
+	struct sec4_sg_entry *sec4_sg;
+	union {
+		struct rsa_pub_pdb pub;
+		struct rsa_priv_f1_pdb priv_f1;
+	} pdb;
+	u32 hw_desc[];
+};
+
+/* Descriptor construction primitives. */
+void init_rsa_pub_desc(u32 *desc, struct rsa_pub_pdb *pdb);
+void init_rsa_priv_f1_desc(u32 *desc, struct rsa_priv_f1_pdb *pdb);
+
+#endif
diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h
index b6955ecdfb3f..7149cd2492e0 100644
--- a/drivers/crypto/caam/compat.h
+++ b/drivers/crypto/caam/compat.h
@@ -35,8 +35,11 @@
 #include <crypto/md5.h>
 #include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
+#include <crypto/akcipher.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/rsa.h>
+#include <crypto/internal/akcipher.h>
 
 #endif /* !defined(CAAM_COMPAT_H) */
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 5ad5f3009ae0..0ec112ee5204 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -15,6 +15,9 @@
 #include "desc_constr.h"
 #include "error.h"
 
+bool caam_little_end;
+EXPORT_SYMBOL(caam_little_end);
+
 /*
  * i.MX targets tend to have clock control subsystems that can
  * enable/disable clocking to our device.
@@ -106,7 +109,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 
 
 	if (ctrlpriv->virt_en == 1) {
-		setbits32(&ctrl->deco_rsr, DECORSR_JR0);
+		clrsetbits_32(&ctrl->deco_rsr, 0, DECORSR_JR0);
 
 		while (!(rd_reg32(&ctrl->deco_rsr) & DECORSR_VALID) &&
 		       --timeout)
@@ -115,7 +118,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 		timeout = 100000;
 	}
 
-	setbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+	clrsetbits_32(&ctrl->deco_rq, 0, DECORR_RQD0ENABLE);
 
 	while (!(rd_reg32(&ctrl->deco_rq) & DECORR_DEN0) &&
 								 --timeout)
@@ -123,12 +126,12 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 
 	if (!timeout) {
 		dev_err(ctrldev, "failed to acquire DECO 0\n");
-		clrbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+		clrsetbits_32(&ctrl->deco_rq, DECORR_RQD0ENABLE, 0);
 		return -ENODEV;
 	}
 
 	for (i = 0; i < desc_len(desc); i++)
-		wr_reg32(&deco->descbuf[i], *(desc + i));
+		wr_reg32(&deco->descbuf[i], caam32_to_cpu(*(desc + i)));
 
 	flags = DECO_JQCR_WHL;
 	/*
@@ -139,7 +142,7 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 		flags |= DECO_JQCR_FOUR;
 
 	/* Instruct the DECO to execute it */
-	setbits32(&deco->jr_ctl_hi, flags);
+	clrsetbits_32(&deco->jr_ctl_hi, 0, flags);
 
 	timeout = 10000000;
 	do {
@@ -158,10 +161,10 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 		  DECO_OP_STATUS_HI_ERR_MASK;
 
 	if (ctrlpriv->virt_en == 1)
-		clrbits32(&ctrl->deco_rsr, DECORSR_JR0);
+		clrsetbits_32(&ctrl->deco_rsr, DECORSR_JR0, 0);
 
 	/* Mark the DECO as free */
-	clrbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+	clrsetbits_32(&ctrl->deco_rq, DECORR_RQD0ENABLE, 0);
 
 	if (!timeout)
 		return -EAGAIN;
@@ -349,7 +352,7 @@ static void kick_trng(struct platform_device *pdev, int ent_delay)
 	r4tst = &ctrl->r4tst[0];
 
 	/* put RNG4 into program mode */
-	setbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+	clrsetbits_32(&r4tst->rtmctl, 0, RTMCTL_PRGM);
 
 	/*
 	 * Performance-wise, it does not make sense to
@@ -363,7 +366,7 @@ static void kick_trng(struct platform_device *pdev, int ent_delay)
 	      >> RTSDCTL_ENT_DLY_SHIFT;
 	if (ent_delay <= val) {
 		/* put RNG4 into run mode */
-		clrbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+		clrsetbits_32(&r4tst->rtmctl, RTMCTL_PRGM, 0);
 		return;
 	}
 
@@ -381,9 +384,9 @@ static void kick_trng(struct platform_device *pdev, int ent_delay)
 	 * select raw sampling in both entropy shifter
 	 * and statistical checker
 	 */
-	setbits32(&val, RTMCTL_SAMP_MODE_RAW_ES_SC);
+	clrsetbits_32(&val, 0, RTMCTL_SAMP_MODE_RAW_ES_SC);
 	/* put RNG4 into run mode */
-	clrbits32(&val, RTMCTL_PRGM);
+	clrsetbits_32(&val, RTMCTL_PRGM, 0);
 	/* write back the control register */
 	wr_reg32(&r4tst->rtmctl, val);
 }
@@ -406,6 +409,23 @@ int caam_get_era(void)
 }
 EXPORT_SYMBOL(caam_get_era);
 
+#ifdef CONFIG_DEBUG_FS
+static int caam_debugfs_u64_get(void *data, u64 *val)
+{
+	*val = caam64_to_cpu(*(u64 *)data);
+	return 0;
+}
+
+static int caam_debugfs_u32_get(void *data, u64 *val)
+{
+	*val = caam32_to_cpu(*(u32 *)data);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u32_ro, caam_debugfs_u32_get, NULL, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
+#endif
+
 /* Probe routine for CAAM top (controller) level */
 static int caam_probe(struct platform_device *pdev)
 {
@@ -504,6 +524,10 @@ static int caam_probe(struct platform_device *pdev)
 		ret = -ENOMEM;
 		goto disable_caam_emi_slow;
 	}
+
+	caam_little_end = !(bool)(rd_reg32(&ctrl->perfmon.status) &
+				  (CSTA_PLEND | CSTA_ALT_PLEND));
+
 	/* Finding the page size for using the CTPR_MS register */
 	comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ms);
 	pg_size = (comp_params & CTPR_MS_PG_SZ_MASK) >> CTPR_MS_PG_SZ_SHIFT;
@@ -559,9 +583,9 @@ static int caam_probe(struct platform_device *pdev)
 	}
 
 	if (ctrlpriv->virt_en == 1)
-		setbits32(&ctrl->jrstart, JRSTART_JR0_START |
-			  JRSTART_JR1_START | JRSTART_JR2_START |
-			  JRSTART_JR3_START);
+		clrsetbits_32(&ctrl->jrstart, 0, JRSTART_JR0_START |
+			      JRSTART_JR1_START | JRSTART_JR2_START |
+			      JRSTART_JR3_START);
 
 	if (sizeof(dma_addr_t) == sizeof(u64))
 		if (of_device_is_compatible(nprop, "fsl,sec-v5.0"))
@@ -693,7 +717,7 @@ static int caam_probe(struct platform_device *pdev)
 		ctrlpriv->rng4_sh_init = ~ctrlpriv->rng4_sh_init & RDSTA_IFMASK;
 
 		/* Enable RDB bit so that RNG works faster */
-		setbits32(&ctrl->scfgr, SCFGR_RDBENABLE);
+		clrsetbits_32(&ctrl->scfgr, 0, SCFGR_RDBENABLE);
 	}
 
 	/* NOTE: RTIC detection ought to go here, around Si time */
@@ -719,48 +743,59 @@ static int caam_probe(struct platform_device *pdev)
 	ctrlpriv->ctl = debugfs_create_dir("ctl", ctrlpriv->dfs_root);
 
 	/* Controller-level - performance monitor counters */
+
 	ctrlpriv->ctl_rq_dequeued =
-		debugfs_create_u64("rq_dequeued",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->req_dequeued);
+		debugfs_create_file("rq_dequeued",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->req_dequeued,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_enc_req =
-		debugfs_create_u64("ob_rq_encrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_enc_req);
+		debugfs_create_file("ob_rq_encrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_enc_req,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_dec_req =
-		debugfs_create_u64("ib_rq_decrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_dec_req);
+		debugfs_create_file("ib_rq_decrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_dec_req,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_enc_bytes =
-		debugfs_create_u64("ob_bytes_encrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_enc_bytes);
+		debugfs_create_file("ob_bytes_encrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_enc_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_prot_bytes =
-		debugfs_create_u64("ob_bytes_protected",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_prot_bytes);
+		debugfs_create_file("ob_bytes_protected",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_prot_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_dec_bytes =
-		debugfs_create_u64("ib_bytes_decrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_dec_bytes);
+		debugfs_create_file("ib_bytes_decrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_dec_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_valid_bytes =
-		debugfs_create_u64("ib_bytes_validated",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_valid_bytes);
+		debugfs_create_file("ib_bytes_validated",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_valid_bytes,
+				    &caam_fops_u64_ro);
 
 	/* Controller level - global status values */
 	ctrlpriv->ctl_faultaddr =
-		debugfs_create_u64("fault_addr",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->faultaddr);
+		debugfs_create_file("fault_addr",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->faultaddr,
+				    &caam_fops_u32_ro);
 	ctrlpriv->ctl_faultdetail =
-		debugfs_create_u32("fault_detail",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->faultdetail);
+		debugfs_create_file("fault_detail",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->faultdetail,
+				    &caam_fops_u32_ro);
 	ctrlpriv->ctl_faultstatus =
-		debugfs_create_u32("fault_status",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->status);
+		debugfs_create_file("fault_status",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->status,
+				    &caam_fops_u32_ro);
 
 	/* Internal covering keys (useful in non-secure mode only) */
 	ctrlpriv->ctl_kek_wrap.data = &ctrlpriv->ctrl->kek[0];
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index 1e93c6af2275..26427c11ad87 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -20,19 +20,18 @@
 #define SEC4_SG_BPID_MASK	0x000000ff
 #define SEC4_SG_BPID_SHIFT	16
 #define SEC4_SG_LEN_MASK	0x3fffffff	/* Excludes EXT and FINAL */
-#define SEC4_SG_OFFS_MASK	0x00001fff
+#define SEC4_SG_OFFSET_MASK	0x00001fff
 
 struct sec4_sg_entry {
-#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+#if !defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) && \
+	defined(CONFIG_CRYPTO_DEV_FSL_CAAM_IMX)
 	u32 rsvd1;
 	dma_addr_t ptr;
 #else
 	u64 ptr;
 #endif /* CONFIG_CRYPTO_DEV_FSL_CAAM_IMX */
 	u32 len;
-	u8 rsvd2;
-	u8 buf_pool_id;
-	u16 offset;
+	u32 bpid_offset;
 };
 
 /* Max size of any CAAM descriptor in 32-bit words, inclusive of header */
@@ -454,6 +453,8 @@ struct sec4_sg_entry {
 #define OP_PCLID_PUBLICKEYPAIR	(0x14 << OP_PCLID_SHIFT)
 #define OP_PCLID_DSASIGN	(0x15 << OP_PCLID_SHIFT)
 #define OP_PCLID_DSAVERIFY	(0x16 << OP_PCLID_SHIFT)
+#define OP_PCLID_RSAENC_PUBKEY  (0x18 << OP_PCLID_SHIFT)
+#define OP_PCLID_RSADEC_PRVKEY  (0x19 << OP_PCLID_SHIFT)
 
 /* Assuming OP_TYPE = OP_TYPE_DECAP_PROTOCOL/ENCAP_PROTOCOL */
 #define OP_PCLID_IPSEC		(0x01 << OP_PCLID_SHIFT)
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index 98d07de24fc4..d3869b95e7b1 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -5,6 +5,7 @@
  */
 
 #include "desc.h"
+#include "regs.h"
 
 #define IMMEDIATE (1 << 23)
 #define CAAM_CMD_SZ sizeof(u32)
@@ -30,9 +31,11 @@
 			       LDST_SRCDST_WORD_DECOCTRL | \
 			       (LDOFF_ENABLE_AUTO_NFIFO << LDST_OFFSET_SHIFT))
 
+extern bool caam_little_end;
+
 static inline int desc_len(u32 *desc)
 {
-	return *desc & HDR_DESCLEN_MASK;
+	return caam32_to_cpu(*desc) & HDR_DESCLEN_MASK;
 }
 
 static inline int desc_bytes(void *desc)
@@ -52,7 +55,7 @@ static inline void *sh_desc_pdb(u32 *desc)
 
 static inline void init_desc(u32 *desc, u32 options)
 {
-	*desc = (options | HDR_ONE) + 1;
+	*desc = cpu_to_caam32((options | HDR_ONE) + 1);
 }
 
 static inline void init_sh_desc(u32 *desc, u32 options)
@@ -74,13 +77,21 @@ static inline void init_job_desc(u32 *desc, u32 options)
 	init_desc(desc, CMD_DESC_HDR | options);
 }
 
+static inline void init_job_desc_pdb(u32 *desc, u32 options, size_t pdb_bytes)
+{
+	u32 pdb_len = (pdb_bytes + CAAM_CMD_SZ - 1) / CAAM_CMD_SZ;
+
+	init_job_desc(desc, (((pdb_len + 1) << HDR_START_IDX_SHIFT)) | options);
+}
+
 static inline void append_ptr(u32 *desc, dma_addr_t ptr)
 {
 	dma_addr_t *offset = (dma_addr_t *)desc_end(desc);
 
-	*offset = ptr;
+	*offset = cpu_to_caam_dma(ptr);
 
-	(*desc) += CAAM_PTR_SZ / CAAM_CMD_SZ;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) +
+				CAAM_PTR_SZ / CAAM_CMD_SZ);
 }
 
 static inline void init_job_desc_shared(u32 *desc, dma_addr_t ptr, int len,
@@ -99,16 +110,17 @@ static inline void append_data(u32 *desc, void *data, int len)
 	if (len) /* avoid sparse warning: memcpy with byte count of 0 */
 		memcpy(offset, data, len);
 
-	(*desc) += (len + CAAM_CMD_SZ - 1) / CAAM_CMD_SZ;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) +
+				(len + CAAM_CMD_SZ - 1) / CAAM_CMD_SZ);
 }
 
 static inline void append_cmd(u32 *desc, u32 command)
 {
 	u32 *cmd = desc_end(desc);
 
-	*cmd = command;
+	*cmd = cpu_to_caam32(command);
 
-	(*desc)++;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) + 1);
 }
 
 #define append_u32 append_cmd
@@ -117,16 +129,22 @@ static inline void append_u64(u32 *desc, u64 data)
 {
 	u32 *offset = desc_end(desc);
 
-	*offset = upper_32_bits(data);
-	*(++offset) = lower_32_bits(data);
+	/* Only 32-bit alignment is guaranteed in descriptor buffer */
+	if (caam_little_end) {
+		*offset = cpu_to_caam32(lower_32_bits(data));
+		*(++offset) = cpu_to_caam32(upper_32_bits(data));
+	} else {
+		*offset = cpu_to_caam32(upper_32_bits(data));
+		*(++offset) = cpu_to_caam32(lower_32_bits(data));
+	}
 
-	(*desc) += 2;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) + 2);
 }
 
 /* Write command without affecting header, and return pointer to next word */
 static inline u32 *write_cmd(u32 *desc, u32 command)
 {
-	*desc = command;
+	*desc = cpu_to_caam32(command);
 
 	return desc + 1;
 }
@@ -168,14 +186,17 @@ APPEND_CMD_RET(move, MOVE)
 
 static inline void set_jump_tgt_here(u32 *desc, u32 *jump_cmd)
 {
-	*jump_cmd = *jump_cmd | (desc_len(desc) - (jump_cmd - desc));
+	*jump_cmd = cpu_to_caam32(caam32_to_cpu(*jump_cmd) |
+				  (desc_len(desc) - (jump_cmd - desc)));
 }
 
 static inline void set_move_tgt_here(u32 *desc, u32 *move_cmd)
 {
-	*move_cmd &= ~MOVE_OFFSET_MASK;
-	*move_cmd = *move_cmd | ((desc_len(desc) << (MOVE_OFFSET_SHIFT + 2)) &
-				 MOVE_OFFSET_MASK);
+	u32 val = caam32_to_cpu(*move_cmd);
+
+	val &= ~MOVE_OFFSET_MASK;
+	val |= (desc_len(desc) << (MOVE_OFFSET_SHIFT + 2)) & MOVE_OFFSET_MASK;
+	*move_cmd = cpu_to_caam32(val);
 }
 
 #define APPEND_CMD(cmd, op) \
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index 5ef4be22eb80..a81f551ac222 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -31,7 +31,7 @@ static int caam_reset_hw_jr(struct device *dev)
 	 * mask interrupts since we are going to poll
 	 * for reset completion status
 	 */
-	setbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JRCFG_IMSK);
 
 	/* initiate flush (required prior to reset) */
 	wr_reg32(&jrp->rregs->jrcommand, JRCR_RESET);
@@ -57,7 +57,7 @@ static int caam_reset_hw_jr(struct device *dev)
 	}
 
 	/* unmask interrupts */
-	clrbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, JRCFG_IMSK, 0);
 
 	return 0;
 }
@@ -147,7 +147,7 @@ static irqreturn_t caam_jr_interrupt(int irq, void *st_dev)
 	}
 
 	/* mask valid interrupts */
-	setbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JRCFG_IMSK);
 
 	/* Have valid interrupt at this point, just ACK and trigger */
 	wr_reg32(&jrp->rregs->jrintstatus, irqstate);
@@ -182,7 +182,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 			sw_idx = (tail + i) & (JOBR_DEPTH - 1);
 
 			if (jrp->outring[hw_idx].desc ==
-			    jrp->entinfo[sw_idx].desc_addr_dma)
+			    caam_dma_to_cpu(jrp->entinfo[sw_idx].desc_addr_dma))
 				break; /* found */
 		}
 		/* we should never fail to find a matching descriptor */
@@ -200,7 +200,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 		usercall = jrp->entinfo[sw_idx].callbk;
 		userarg = jrp->entinfo[sw_idx].cbkarg;
 		userdesc = jrp->entinfo[sw_idx].desc_addr_virt;
-		userstatus = jrp->outring[hw_idx].jrstatus;
+		userstatus = caam32_to_cpu(jrp->outring[hw_idx].jrstatus);
 
 		/*
 		 * Make sure all information from the job has been obtained
@@ -236,7 +236,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 	}
 
 	/* reenable / unmask IRQs */
-	clrbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, JRCFG_IMSK, 0);
 }
 
 /**
@@ -330,7 +330,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 	int head, tail, desc_size;
 	dma_addr_t desc_dma;
 
-	desc_size = (*desc & HDR_JD_LENGTH_MASK) * sizeof(u32);
+	desc_size = (caam32_to_cpu(*desc) & HDR_JD_LENGTH_MASK) * sizeof(u32);
 	desc_dma = dma_map_single(dev, desc, desc_size, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, desc_dma)) {
 		dev_err(dev, "caam_jr_enqueue(): can't map jobdesc\n");
@@ -356,7 +356,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 	head_entry->cbkarg = areq;
 	head_entry->desc_addr_dma = desc_dma;
 
-	jrp->inpring[jrp->inp_ring_write_index] = desc_dma;
+	jrp->inpring[jrp->inp_ring_write_index] = cpu_to_caam_dma(desc_dma);
 
 	/*
 	 * Guarantee that the descriptor's DMA address has been written to
@@ -444,9 +444,9 @@ static int caam_jr_init(struct device *dev)
 	spin_lock_init(&jrp->outlock);
 
 	/* Select interrupt coalescing parameters */
-	setbits32(&jrp->rregs->rconfig_lo, JOBR_INTC |
-		  (JOBR_INTC_COUNT_THLD << JRCFG_ICDCT_SHIFT) |
-		  (JOBR_INTC_TIME_THLD << JRCFG_ICTT_SHIFT));
+	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JOBR_INTC |
+		      (JOBR_INTC_COUNT_THLD << JRCFG_ICDCT_SHIFT) |
+		      (JOBR_INTC_TIME_THLD << JRCFG_ICTT_SHIFT));
 
 	return 0;
 
diff --git a/drivers/crypto/caam/pdb.h b/drivers/crypto/caam/pdb.h
index 3a87c0cf879a..aaa00dd1c601 100644
--- a/drivers/crypto/caam/pdb.h
+++ b/drivers/crypto/caam/pdb.h
@@ -1,18 +1,19 @@
 /*
  * CAAM Protocol Data Block (PDB) definition header file
  *
- * Copyright 2008-2012 Freescale Semiconductor, Inc.
+ * Copyright 2008-2016 Freescale Semiconductor, Inc.
  *
  */
 
 #ifndef CAAM_PDB_H
 #define CAAM_PDB_H
+#include "compat.h"
 
 /*
  * PDB- IPSec ESP Header Modification Options
  */
-#define PDBHMO_ESP_DECAP_SHIFT	12
-#define PDBHMO_ESP_ENCAP_SHIFT	4
+#define PDBHMO_ESP_DECAP_SHIFT	28
+#define PDBHMO_ESP_ENCAP_SHIFT	28
 /*
  * Encap and Decap - Decrement TTL (Hop Limit) - Based on the value of the
  * Options Byte IP version (IPvsn) field:
@@ -32,12 +33,23 @@
  */
 #define PDBHMO_ESP_DFBIT		(0x04 << PDBHMO_ESP_ENCAP_SHIFT)
 
+#define PDBNH_ESP_ENCAP_SHIFT		16
+#define PDBNH_ESP_ENCAP_MASK		(0xff << PDBNH_ESP_ENCAP_SHIFT)
+
+#define PDBHDRLEN_ESP_DECAP_SHIFT	16
+#define PDBHDRLEN_MASK			(0x0fff << PDBHDRLEN_ESP_DECAP_SHIFT)
+
+#define PDB_NH_OFFSET_SHIFT		8
+#define PDB_NH_OFFSET_MASK		(0xff << PDB_NH_OFFSET_SHIFT)
+
 /*
  * PDB - IPSec ESP Encap/Decap Options
  */
 #define PDBOPTS_ESP_ARSNONE	0x00 /* no antireplay window */
 #define PDBOPTS_ESP_ARS32	0x40 /* 32-entry antireplay window */
+#define PDBOPTS_ESP_ARS128	0x80 /* 128-entry antireplay window */
 #define PDBOPTS_ESP_ARS64	0xc0 /* 64-entry antireplay window */
+#define PDBOPTS_ESP_ARS_MASK	0xc0 /* antireplay window mask */
 #define PDBOPTS_ESP_IVSRC	0x20 /* IV comes from internal random gen */
 #define PDBOPTS_ESP_ESN		0x10 /* extended sequence included */
 #define PDBOPTS_ESP_OUTFMT	0x08 /* output only decapsulation (decap) */
@@ -54,35 +66,73 @@
 /*
  * General IPSec encap/decap PDB definitions
  */
+
+/**
+ * ipsec_encap_cbc - PDB part for IPsec CBC encapsulation
+ * @iv: 16-byte array initialization vector
+ */
 struct ipsec_encap_cbc {
-	u32 iv[4];
+	u8 iv[16];
 };
 
+/**
+ * ipsec_encap_ctr - PDB part for IPsec CTR encapsulation
+ * @ctr_nonce: 4-byte array nonce
+ * @ctr_initial: initial count constant
+ * @iv: initialization vector
+ */
 struct ipsec_encap_ctr {
-	u32 ctr_nonce;
+	u8 ctr_nonce[4];
 	u32 ctr_initial;
-	u32 iv[2];
+	u64 iv;
 };
 
+/**
+ * ipsec_encap_ccm - PDB part for IPsec CCM encapsulation
+ * @salt: 3-byte array salt (lower 24 bits)
+ * @ccm_opt: CCM algorithm options - MSB-LSB description:
+ *  b0_flags (8b) - CCM B0; use 0x5B for 8-byte ICV, 0x6B for 12-byte ICV,
+ *    0x7B for 16-byte ICV (cf. RFC4309, RFC3610)
+ *  ctr_flags (8b) - counter flags; constant equal to 0x3
+ *  ctr_initial (16b) - initial count constant
+ * @iv: initialization vector
+ */
 struct ipsec_encap_ccm {
-	u32 salt; /* lower 24 bits */
-	u8 b0_flags;
-	u8 ctr_flags;
-	u16 ctr_initial;
-	u32 iv[2];
+	u8 salt[4];
+	u32 ccm_opt;
+	u64 iv;
 };
 
+/**
+ * ipsec_encap_gcm - PDB part for IPsec GCM encapsulation
+ * @salt: 3-byte array salt (lower 24 bits)
+ * @rsvd: reserved, do not use
+ * @iv: initialization vector
+ */
 struct ipsec_encap_gcm {
-	u32 salt; /* lower 24 bits */
+	u8 salt[4];
 	u32 rsvd1;
-	u32 iv[2];
+	u64 iv;
 };
 
+/**
+ * ipsec_encap_pdb - PDB for IPsec encapsulation
+ * @options: MSB-LSB description
+ *  hmo (header manipulation options) - 4b
+ *  reserved - 4b
+ *  next header - 8b
+ *  next header offset - 8b
+ *  option flags (depend on selected algorithm) - 8b
+ * @seq_num_ext_hi: (optional) IPsec Extended Sequence Number (ESN)
+ * @seq_num: IPsec sequence number
+ * @spi: IPsec SPI (Security Parameters Index)
+ * @ip_hdr_len: optional IP Header length (in bytes)
+ *  reserved - 16b
+ *  Opt. IP Hdr Len - 16b
+ * @ip_hdr: optional IP Header content
+ */
 struct ipsec_encap_pdb {
-	u8 hmo_rsvd;
-	u8 ip_nh;
-	u8 ip_nh_offset;
-	u8 options;
+	u32 options;
 	u32 seq_num_ext_hi;
 	u32 seq_num;
 	union {
@@ -92,36 +142,65 @@ struct ipsec_encap_pdb {
 		struct ipsec_encap_gcm gcm;
 	};
 	u32 spi;
-	u16 rsvd1;
-	u16 ip_hdr_len;
-	u32 ip_hdr[0]; /* optional IP Header content */
+	u32 ip_hdr_len;
+	u32 ip_hdr[0];
 };
 
+/**
+ * ipsec_decap_cbc - PDB part for IPsec CBC decapsulation
+ * @rsvd: reserved, do not use
+ */
 struct ipsec_decap_cbc {
 	u32 rsvd[2];
 };
 
+/**
+ * ipsec_decap_ctr - PDB part for IPsec CTR decapsulation
+ * @ctr_nonce: 4-byte array nonce
+ * @ctr_initial: initial count constant
+ */
 struct ipsec_decap_ctr {
-	u32 salt;
+	u8 ctr_nonce[4];
 	u32 ctr_initial;
 };
 
+/**
+ * ipsec_decap_ccm - PDB part for IPsec CCM decapsulation
+ * @salt: 3-byte salt (lower 24 bits)
+ * @ccm_opt: CCM algorithm options - MSB-LSB description:
+ *  b0_flags (8b) - CCM B0; use 0x5B for 8-byte ICV, 0x6B for 12-byte ICV,
+ *    0x7B for 16-byte ICV (cf. RFC4309, RFC3610)
+ *  ctr_flags (8b) - counter flags; constant equal to 0x3
+ *  ctr_initial (16b) - initial count constant
+ */
 struct ipsec_decap_ccm {
-	u32 salt;
-	u8 iv_flags;
-	u8 ctr_flags;
-	u16 ctr_initial;
+	u8 salt[4];
+	u32 ccm_opt;
 };
 
+/**
+ * ipsec_decap_gcm - PDB part for IPsec GCN decapsulation
+ * @salt: 4-byte salt
+ * @rsvd: reserved, do not use
+ */
 struct ipsec_decap_gcm {
-	u32 salt;
+	u8 salt[4];
 	u32 resvd;
 };
 
+/**
+ * ipsec_decap_pdb - PDB for IPsec decapsulation
+ * @options: MSB-LSB description
+ *  hmo (header manipulation options) - 4b
+ *  IP header length - 12b
+ *  next header offset - 8b
+ *  option flags (depend on selected algorithm) - 8b
+ * @seq_num_ext_hi: (optional) IPsec Extended Sequence Number (ESN)
+ * @seq_num: IPsec sequence number
+ * @anti_replay: Anti-replay window; size depends on ARS (option flags)
+ */
 struct ipsec_decap_pdb {
-	u16 hmo_ip_hdr_len;
-	u8 ip_nh_offset;
-	u8 options;
+	u32 options;
 	union {
 		struct ipsec_decap_cbc cbc;
 		struct ipsec_decap_ctr ctr;
@@ -130,8 +209,7 @@ struct ipsec_decap_pdb {
 	};
 	u32 seq_num_ext_hi;
 	u32 seq_num;
-	u32 anti_replay[2];
-	u32 end_index[0];
+	__be32 anti_replay[4];
 };
 
 /*
@@ -399,4 +477,52 @@ struct dsa_verify_pdb {
 	u8 *ab; /* only used if ECC processing */
 };
 
+/* RSA Protocol Data Block */
+#define RSA_PDB_SGF_SHIFT       28
+#define RSA_PDB_E_SHIFT         12
+#define RSA_PDB_E_MASK          (0xFFF << RSA_PDB_E_SHIFT)
+#define RSA_PDB_D_SHIFT         12
+#define RSA_PDB_D_MASK          (0xFFF << RSA_PDB_D_SHIFT)
+
+#define RSA_PDB_SGF_F           (0x8 << RSA_PDB_SGF_SHIFT)
+#define RSA_PDB_SGF_G           (0x4 << RSA_PDB_SGF_SHIFT)
+#define RSA_PRIV_PDB_SGF_F      (0x4 << RSA_PDB_SGF_SHIFT)
+#define RSA_PRIV_PDB_SGF_G      (0x8 << RSA_PDB_SGF_SHIFT)
+
+#define RSA_PRIV_KEY_FRM_1      0
+
+/**
+ * RSA Encrypt Protocol Data Block
+ * @sgf: scatter-gather field
+ * @f_dma: dma address of input data
+ * @g_dma: dma address of encrypted output data
+ * @n_dma: dma address of RSA modulus
+ * @e_dma: dma address of RSA public exponent
+ * @f_len: length in octets of the input data
+ */
+struct rsa_pub_pdb {
+	u32		sgf;
+	dma_addr_t	f_dma;
+	dma_addr_t	g_dma;
+	dma_addr_t	n_dma;
+	dma_addr_t	e_dma;
+	u32		f_len;
+} __packed;
+
+/**
+ * RSA Decrypt PDB - Private Key Form #1
+ * @sgf: scatter-gather field
+ * @g_dma: dma address of encrypted input data
+ * @f_dma: dma address of output data
+ * @n_dma: dma address of RSA modulus
+ * @d_dma: dma address of RSA private exponent
+ */
+struct rsa_priv_f1_pdb {
+	u32		sgf;
+	dma_addr_t	g_dma;
+	dma_addr_t	f_dma;
+	dma_addr_t	n_dma;
+	dma_addr_t	d_dma;
+} __packed;
+
 #endif
diff --git a/drivers/crypto/caam/pkc_desc.c b/drivers/crypto/caam/pkc_desc.c
new file mode 100644
index 000000000000..4e4183e615ea
--- /dev/null
+++ b/drivers/crypto/caam/pkc_desc.c
@@ -0,0 +1,36 @@
+/*
+ * caam - Freescale FSL CAAM support for Public Key Cryptography descriptors
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * There is no Shared Descriptor for PKC so that the Job Descriptor must carry
+ * all the desired key parameters, input and output pointers.
+ */
+#include "caampkc.h"
+#include "desc_constr.h"
+
+/* Descriptor for RSA Public operation */
+void init_rsa_pub_desc(u32 *desc, struct rsa_pub_pdb *pdb)
+{
+	init_job_desc_pdb(desc, 0, sizeof(*pdb));
+	append_cmd(desc, pdb->sgf);
+	append_ptr(desc, pdb->f_dma);
+	append_ptr(desc, pdb->g_dma);
+	append_ptr(desc, pdb->n_dma);
+	append_ptr(desc, pdb->e_dma);
+	append_cmd(desc, pdb->f_len);
+	append_operation(desc, OP_TYPE_UNI_PROTOCOL | OP_PCLID_RSAENC_PUBKEY);
+}
+
+/* Descriptor for RSA Private operation - Private Key Form #1 */
+void init_rsa_priv_f1_desc(u32 *desc, struct rsa_priv_f1_pdb *pdb)
+{
+	init_job_desc_pdb(desc, 0, sizeof(*pdb));
+	append_cmd(desc, pdb->sgf);
+	append_ptr(desc, pdb->g_dma);
+	append_ptr(desc, pdb->f_dma);
+	append_ptr(desc, pdb->n_dma);
+	append_ptr(desc, pdb->d_dma);
+	append_operation(desc, OP_TYPE_UNI_PROTOCOL | OP_PCLID_RSADEC_PRVKEY |
+			 RSA_PRIV_KEY_FRM_1);
+}
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index 0ba9c40597dc..b3c5016f6458 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -8,6 +8,7 @@
 #define REGS_H
 
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include <linux/io.h>
 
 /*
@@ -65,46 +66,56 @@
  *
  */
 
-#ifdef CONFIG_ARM
-/* These are common macros for Power, put here for ARM */
-#define setbits32(_addr, _v) writel((readl(_addr) | (_v)), (_addr))
-#define clrbits32(_addr, _v) writel((readl(_addr) & ~(_v)), (_addr))
+extern bool caam_little_end;
 
-#define out_arch(type, endian, a, v)	__raw_write##type(cpu_to_##endian(v), a)
-#define in_arch(type, endian, a)	endian##_to_cpu(__raw_read##type(a))
+#define caam_to_cpu(len)				\
+static inline u##len caam##len ## _to_cpu(u##len val)	\
+{							\
+	if (caam_little_end)				\
+		return le##len ## _to_cpu(val);		\
+	else						\
+		return be##len ## _to_cpu(val);		\
+}
 
-#define out_le32(a, v)	out_arch(l, le32, a, v)
-#define in_le32(a)	in_arch(l, le32, a)
+#define cpu_to_caam(len)				\
+static inline u##len cpu_to_caam##len(u##len val)	\
+{							\
+	if (caam_little_end)				\
+		return cpu_to_le##len(val);		\
+	else						\
+		return cpu_to_be##len(val);		\
+}
 
-#define out_be32(a, v)	out_arch(l, be32, a, v)
-#define in_be32(a)	in_arch(l, be32, a)
+caam_to_cpu(16)
+caam_to_cpu(32)
+caam_to_cpu(64)
+cpu_to_caam(16)
+cpu_to_caam(32)
+cpu_to_caam(64)
 
-#define clrsetbits(type, addr, clear, set) \
-	out_##type((addr), (in_##type(addr) & ~(clear)) | (set))
+static inline void wr_reg32(void __iomem *reg, u32 data)
+{
+	if (caam_little_end)
+		iowrite32(data, reg);
+	else
+		iowrite32be(data, reg);
+}
 
-#define clrsetbits_be32(addr, clear, set) clrsetbits(be32, addr, clear, set)
-#define clrsetbits_le32(addr, clear, set) clrsetbits(le32, addr, clear, set)
-#endif
+static inline u32 rd_reg32(void __iomem *reg)
+{
+	if (caam_little_end)
+		return ioread32(reg);
 
-#ifdef __BIG_ENDIAN
-#define wr_reg32(reg, data) out_be32(reg, data)
-#define rd_reg32(reg) in_be32(reg)
-#define clrsetbits_32(addr, clear, set) clrsetbits_be32(addr, clear, set)
-#ifdef CONFIG_64BIT
-#define wr_reg64(reg, data) out_be64(reg, data)
-#define rd_reg64(reg) in_be64(reg)
-#endif
-#else
-#ifdef __LITTLE_ENDIAN
-#define wr_reg32(reg, data) __raw_writel(data, reg)
-#define rd_reg32(reg) __raw_readl(reg)
-#define clrsetbits_32(addr, clear, set) clrsetbits_le32(addr, clear, set)
-#ifdef CONFIG_64BIT
-#define wr_reg64(reg, data) __raw_writeq(data, reg)
-#define rd_reg64(reg) __raw_readq(reg)
-#endif
-#endif
-#endif
+	return ioread32be(reg);
+}
+
+static inline void clrsetbits_32(void __iomem *reg, u32 clear, u32 set)
+{
+	if (caam_little_end)
+		iowrite32((ioread32(reg) & ~clear) | set, reg);
+	else
+		iowrite32be((ioread32be(reg) & ~clear) | set, reg);
+}
 
 /*
  * The only users of these wr/rd_reg64 functions is the Job Ring (JR).
@@ -123,29 +134,67 @@
  *    base + 0x0000 : least-significant 32 bits
  *    base + 0x0004 : most-significant 32 bits
  */
+#ifdef CONFIG_64BIT
+static inline void wr_reg64(void __iomem *reg, u64 data)
+{
+	if (caam_little_end)
+		iowrite64(data, reg);
+	else
+		iowrite64be(data, reg);
+}
 
-#ifndef CONFIG_64BIT
-#if !defined(CONFIG_CRYPTO_DEV_FSL_CAAM_LE) || \
-	defined(CONFIG_CRYPTO_DEV_FSL_CAAM_IMX)
-#define REG64_MS32(reg) ((u32 __iomem *)(reg))
-#define REG64_LS32(reg) ((u32 __iomem *)(reg) + 1)
-#else
-#define REG64_MS32(reg) ((u32 __iomem *)(reg) + 1)
-#define REG64_LS32(reg) ((u32 __iomem *)(reg))
-#endif
-
-static inline void wr_reg64(u64 __iomem *reg, u64 data)
+static inline u64 rd_reg64(void __iomem *reg)
 {
-	wr_reg32(REG64_MS32(reg), data >> 32);
-	wr_reg32(REG64_LS32(reg), data);
+	if (caam_little_end)
+		return ioread64(reg);
+	else
+		return ioread64be(reg);
 }
 
-static inline u64 rd_reg64(u64 __iomem *reg)
+#else /* CONFIG_64BIT */
+static inline void wr_reg64(void __iomem *reg, u64 data)
 {
-	return ((u64)rd_reg32(REG64_MS32(reg)) << 32 |
-		(u64)rd_reg32(REG64_LS32(reg)));
+#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+	if (caam_little_end) {
+		wr_reg32((u32 __iomem *)(reg) + 1, data >> 32);
+		wr_reg32((u32 __iomem *)(reg), data);
+	} else
+#endif
+	{
+		wr_reg32((u32 __iomem *)(reg), data >> 32);
+		wr_reg32((u32 __iomem *)(reg) + 1, data);
+	}
 }
+
+static inline u64 rd_reg64(void __iomem *reg)
+{
+#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+	if (caam_little_end)
+		return ((u64)rd_reg32((u32 __iomem *)(reg) + 1) << 32 |
+			(u64)rd_reg32((u32 __iomem *)(reg)));
+	else
 #endif
+		return ((u64)rd_reg32((u32 __iomem *)(reg)) << 32 |
+			(u64)rd_reg32((u32 __iomem *)(reg) + 1));
+}
+#endif /* CONFIG_64BIT  */
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+#ifdef CONFIG_SOC_IMX7D
+#define cpu_to_caam_dma(value) \
+		(((u64)cpu_to_caam32(lower_32_bits(value)) << 32) | \
+		  (u64)cpu_to_caam32(upper_32_bits(value)))
+#define caam_dma_to_cpu(value) \
+		(((u64)caam32_to_cpu(lower_32_bits(value)) << 32) | \
+		  (u64)caam32_to_cpu(upper_32_bits(value)))
+#else
+#define cpu_to_caam_dma(value) cpu_to_caam64(value)
+#define caam_dma_to_cpu(value) caam64_to_cpu(value)
+#endif /* CONFIG_SOC_IMX7D */
+#else
+#define cpu_to_caam_dma(value) cpu_to_caam32(value)
+#define caam_dma_to_cpu(value) caam32_to_cpu(value)
+#endif /* CONFIG_ARCH_DMA_ADDR_T_64BIT  */
 
 /*
  * jr_outentry
@@ -249,6 +298,8 @@ struct caam_perfmon {
 	u32 faultliodn;	/* FALR - Fault Address LIODN	*/
 	u32 faultdetail;	/* FADR - Fault Addr Detail	*/
 	u32 rsvd2;
+#define CSTA_PLEND		BIT(10)
+#define CSTA_ALT_PLEND		BIT(18)
 	u32 status;		/* CSTA - CAAM Status */
 	u64 rsvd3;
 
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
index 12ec6616e89d..19dc64fede0d 100644
--- a/drivers/crypto/caam/sg_sw_sec4.h
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -5,18 +5,19 @@
  *
  */
 
+#include "regs.h"
+
 struct sec4_sg_entry;
 
 /*
  * convert single dma address to h/w link table format
  */
 static inline void dma_to_sec4_sg_one(struct sec4_sg_entry *sec4_sg_ptr,
-				      dma_addr_t dma, u32 len, u32 offset)
+				      dma_addr_t dma, u32 len, u16 offset)
 {
-	sec4_sg_ptr->ptr = dma;
-	sec4_sg_ptr->len = len;
-	sec4_sg_ptr->buf_pool_id = 0;
-	sec4_sg_ptr->offset = offset;
+	sec4_sg_ptr->ptr = cpu_to_caam_dma(dma);
+	sec4_sg_ptr->len = cpu_to_caam32(len);
+	sec4_sg_ptr->bpid_offset = cpu_to_caam32(offset & SEC4_SG_OFFSET_MASK);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "sec4_sg_ptr@: ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sec4_sg_ptr,
@@ -30,7 +31,7 @@ static inline void dma_to_sec4_sg_one(struct sec4_sg_entry *sec4_sg_ptr,
  */
 static inline struct sec4_sg_entry *
 sg_to_sec4_sg(struct scatterlist *sg, int sg_count,
-	      struct sec4_sg_entry *sec4_sg_ptr, u32 offset)
+	      struct sec4_sg_entry *sec4_sg_ptr, u16 offset)
 {
 	while (sg_count) {
 		dma_to_sec4_sg_one(sec4_sg_ptr, sg_dma_address(sg),
@@ -48,10 +49,10 @@ sg_to_sec4_sg(struct scatterlist *sg, int sg_count,
  */
 static inline void sg_to_sec4_sg_last(struct scatterlist *sg, int sg_count,
 				      struct sec4_sg_entry *sec4_sg_ptr,
-				      u32 offset)
+				      u16 offset)
 {
 	sec4_sg_ptr = sg_to_sec4_sg(sg, sg_count, sec4_sg_ptr, offset);
-	sec4_sg_ptr->len |= SEC4_SG_LEN_FIN;
+	sec4_sg_ptr->len |= cpu_to_caam32(SEC4_SG_LEN_FIN);
 }
 
 static inline struct sec4_sg_entry *sg_to_sec4_sg_len(
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
index 0d0d4529ee36..58a4244b4752 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
@@ -14,9 +14,8 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/scatterlist.h>
-#include <linux/crypto.h>
-#include <crypto/algapi.h>
 #include <crypto/aes.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 
 #include "ccp-crypto.h"
@@ -110,15 +109,12 @@ static int ccp_aes_xts_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	ctx->u.aes.key_len = key_len / 2;
 	sg_init_one(&ctx->u.aes.key_sg, ctx->u.aes.key, key_len);
 
-	return crypto_ablkcipher_setkey(ctx->u.aes.tfm_ablkcipher, key,
-					key_len);
+	return crypto_skcipher_setkey(ctx->u.aes.tfm_skcipher, key, key_len);
 }
 
 static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 			     unsigned int encrypt)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
 	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
 	unsigned int unit;
@@ -146,14 +142,19 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 
 	if ((unit_size == CCP_XTS_AES_UNIT_SIZE__LAST) ||
 	    (ctx->u.aes.key_len != AES_KEYSIZE_128)) {
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->u.aes.tfm_skcipher);
+
 		/* Use the fallback to process the request for any
 		 * unsupported unit sizes or key sizes
 		 */
-		ablkcipher_request_set_tfm(req, ctx->u.aes.tfm_ablkcipher);
-		ret = (encrypt) ? crypto_ablkcipher_encrypt(req) :
-				  crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
-
+		skcipher_request_set_tfm(subreq, ctx->u.aes.tfm_skcipher);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		ret = encrypt ? crypto_skcipher_encrypt(subreq) :
+				crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return ret;
 	}
 
@@ -192,23 +193,21 @@ static int ccp_aes_xts_decrypt(struct ablkcipher_request *req)
 static int ccp_aes_xts_cra_init(struct crypto_tfm *tfm)
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_ablkcipher *fallback_tfm;
+	struct crypto_skcipher *fallback_tfm;
 
 	ctx->complete = ccp_aes_xts_complete;
 	ctx->u.aes.key_len = 0;
 
-	fallback_tfm = crypto_alloc_ablkcipher(crypto_tfm_alg_name(tfm), 0,
-					       CRYPTO_ALG_ASYNC |
-					       CRYPTO_ALG_NEED_FALLBACK);
+	fallback_tfm = crypto_alloc_skcipher("xts(aes)", 0,
+					     CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(fallback_tfm)) {
-		pr_warn("could not load fallback driver %s\n",
-			crypto_tfm_alg_name(tfm));
+		pr_warn("could not load fallback driver xts(aes)\n");
 		return PTR_ERR(fallback_tfm);
 	}
-	ctx->u.aes.tfm_ablkcipher = fallback_tfm;
+	ctx->u.aes.tfm_skcipher = fallback_tfm;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_aes_req_ctx) +
-				      fallback_tfm->base.crt_ablkcipher.reqsize;
+	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_aes_req_ctx);
 
 	return 0;
 }
@@ -217,9 +216,7 @@ static void ccp_aes_xts_cra_exit(struct crypto_tfm *tfm)
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (ctx->u.aes.tfm_ablkcipher)
-		crypto_free_ablkcipher(ctx->u.aes.tfm_ablkcipher);
-	ctx->u.aes.tfm_ablkcipher = NULL;
+	crypto_free_skcipher(ctx->u.aes.tfm_skcipher);
 }
 
 static int ccp_register_aes_xts_alg(struct list_head *head,
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index a326ec20bfa8..8335b32e815e 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -17,7 +17,6 @@
 #include <linux/wait.h>
 #include <linux/pci.h>
 #include <linux/ccp.h>
-#include <linux/crypto.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
 #include <crypto/ctr.h>
@@ -69,7 +68,7 @@ static inline struct ccp_crypto_ahash_alg *
 /***** AES related defines *****/
 struct ccp_aes_ctx {
 	/* Fallback cipher for XTS with unsupported unit sizes */
-	struct crypto_ablkcipher *tfm_ablkcipher;
+	struct crypto_skcipher *tfm_skcipher;
 
 	/* Cipher used to generate CMAC K1/K2 keys */
 	struct crypto_cipher *tfm_cipher;
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index e8ef9fd24a16..e373cc6557c6 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -31,22 +31,42 @@
 
 #include "cesa.h"
 
+/* Limit of the crypto queue before reaching the backlog */
+#define CESA_CRYPTO_DEFAULT_MAX_QLEN 128
+
 static int allhwsupport = !IS_ENABLED(CONFIG_CRYPTO_DEV_MV_CESA);
 module_param_named(allhwsupport, allhwsupport, int, 0444);
 MODULE_PARM_DESC(allhwsupport, "Enable support for all hardware (even it if overlaps with the mv_cesa driver)");
 
 struct mv_cesa_dev *cesa_dev;
 
-static void mv_cesa_dequeue_req_unlocked(struct mv_cesa_engine *engine)
+struct crypto_async_request *
+mv_cesa_dequeue_req_locked(struct mv_cesa_engine *engine,
+			   struct crypto_async_request **backlog)
 {
-	struct crypto_async_request *req, *backlog;
+	struct crypto_async_request *req;
+
+	*backlog = crypto_get_backlog(&engine->queue);
+	req = crypto_dequeue_request(&engine->queue);
+
+	if (!req)
+		return NULL;
+
+	return req;
+}
+
+static void mv_cesa_rearm_engine(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req = NULL, *backlog = NULL;
 	struct mv_cesa_ctx *ctx;
 
-	spin_lock_bh(&cesa_dev->lock);
-	backlog = crypto_get_backlog(&cesa_dev->queue);
-	req = crypto_dequeue_request(&cesa_dev->queue);
-	engine->req = req;
-	spin_unlock_bh(&cesa_dev->lock);
+
+	spin_lock_bh(&engine->lock);
+	if (!engine->req) {
+		req = mv_cesa_dequeue_req_locked(engine, &backlog);
+		engine->req = req;
+	}
+	spin_unlock_bh(&engine->lock);
 
 	if (!req)
 		return;
@@ -55,8 +75,47 @@ static void mv_cesa_dequeue_req_unlocked(struct mv_cesa_engine *engine)
 		backlog->complete(backlog, -EINPROGRESS);
 
 	ctx = crypto_tfm_ctx(req->tfm);
-	ctx->ops->prepare(req, engine);
 	ctx->ops->step(req);
+
+	return;
+}
+
+static int mv_cesa_std_process(struct mv_cesa_engine *engine, u32 status)
+{
+	struct crypto_async_request *req;
+	struct mv_cesa_ctx *ctx;
+	int res;
+
+	req = engine->req;
+	ctx = crypto_tfm_ctx(req->tfm);
+	res = ctx->ops->process(req, status);
+
+	if (res == 0) {
+		ctx->ops->complete(req);
+		mv_cesa_engine_enqueue_complete_request(engine, req);
+	} else if (res == -EINPROGRESS) {
+		ctx->ops->step(req);
+	}
+
+	return res;
+}
+
+static int mv_cesa_int_process(struct mv_cesa_engine *engine, u32 status)
+{
+	if (engine->chain.first && engine->chain.last)
+		return mv_cesa_tdma_process(engine, status);
+
+	return mv_cesa_std_process(engine, status);
+}
+
+static inline void
+mv_cesa_complete_req(struct mv_cesa_ctx *ctx, struct crypto_async_request *req,
+		     int res)
+{
+	ctx->ops->cleanup(req);
+	local_bh_disable();
+	req->complete(req, res);
+	local_bh_enable();
 }
 
 static irqreturn_t mv_cesa_int(int irq, void *priv)
@@ -83,49 +142,54 @@ static irqreturn_t mv_cesa_int(int irq, void *priv)
 		writel(~status, engine->regs + CESA_SA_FPGA_INT_STATUS);
 		writel(~status, engine->regs + CESA_SA_INT_STATUS);
 
+		/* Process fetched requests */
+		res = mv_cesa_int_process(engine, status & mask);
 		ret = IRQ_HANDLED;
+
 		spin_lock_bh(&engine->lock);
 		req = engine->req;
+		if (res != -EINPROGRESS)
+			engine->req = NULL;
 		spin_unlock_bh(&engine->lock);
-		if (req) {
-			ctx = crypto_tfm_ctx(req->tfm);
-			res = ctx->ops->process(req, status & mask);
-			if (res != -EINPROGRESS) {
-				spin_lock_bh(&engine->lock);
-				engine->req = NULL;
-				mv_cesa_dequeue_req_unlocked(engine);
-				spin_unlock_bh(&engine->lock);
-				ctx->ops->cleanup(req);
-				local_bh_disable();
-				req->complete(req, res);
-				local_bh_enable();
-			} else {
-				ctx->ops->step(req);
-			}
+
+		ctx = crypto_tfm_ctx(req->tfm);
+
+		if (res && res != -EINPROGRESS)
+			mv_cesa_complete_req(ctx, req, res);
+
+		/* Launch the next pending request */
+		mv_cesa_rearm_engine(engine);
+
+		/* Iterate over the complete queue */
+		while (true) {
+			req = mv_cesa_engine_dequeue_complete_request(engine);
+			if (!req)
+				break;
+
+			mv_cesa_complete_req(ctx, req, 0);
 		}
 	}
 
 	return ret;
 }
 
-int mv_cesa_queue_req(struct crypto_async_request *req)
+int mv_cesa_queue_req(struct crypto_async_request *req,
+		      struct mv_cesa_req *creq)
 {
 	int ret;
-	int i;
+	struct mv_cesa_engine *engine = creq->engine;
+
+	spin_lock_bh(&engine->lock);
+	if (mv_cesa_req_get_type(creq) == CESA_DMA_REQ)
+		mv_cesa_tdma_chain(engine, creq);
 
-	spin_lock_bh(&cesa_dev->lock);
-	ret = crypto_enqueue_request(&cesa_dev->queue, req);
-	spin_unlock_bh(&cesa_dev->lock);
+	ret = crypto_enqueue_request(&engine->queue, req);
+	spin_unlock_bh(&engine->lock);
 
 	if (ret != -EINPROGRESS)
 		return ret;
 
-	for (i = 0; i < cesa_dev->caps->nengines; i++) {
-		spin_lock_bh(&cesa_dev->engines[i].lock);
-		if (!cesa_dev->engines[i].req)
-			mv_cesa_dequeue_req_unlocked(&cesa_dev->engines[i]);
-		spin_unlock_bh(&cesa_dev->engines[i].lock);
-	}
+	mv_cesa_rearm_engine(engine);
 
 	return -EINPROGRESS;
 }
@@ -309,6 +373,10 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa)
 	if (!dma->padding_pool)
 		return -ENOMEM;
 
+	dma->iv_pool = dmam_pool_create("cesa_iv", dev, 16, 1, 0);
+	if (!dma->iv_pool)
+		return -ENOMEM;
+
 	cesa->dma = dma;
 
 	return 0;
@@ -416,7 +484,7 @@ static int mv_cesa_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	spin_lock_init(&cesa->lock);
-	crypto_init_queue(&cesa->queue, 50);
+
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	cesa->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(cesa->regs))
@@ -489,6 +557,10 @@ static int mv_cesa_probe(struct platform_device *pdev)
 						engine);
 		if (ret)
 			goto err_cleanup;
+
+		crypto_init_queue(&engine->queue, CESA_CRYPTO_DEFAULT_MAX_QLEN);
+		atomic_set(&engine->load, 0);
+		INIT_LIST_HEAD(&engine->complete_queue);
 	}
 
 	cesa_dev = cesa;
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index 74071e45ada0..e423d33decd4 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -271,10 +271,13 @@ struct mv_cesa_op_ctx {
 /* TDMA descriptor flags */
 #define CESA_TDMA_DST_IN_SRAM			BIT(31)
 #define CESA_TDMA_SRC_IN_SRAM			BIT(30)
-#define CESA_TDMA_TYPE_MSK			GENMASK(29, 0)
+#define CESA_TDMA_END_OF_REQ			BIT(29)
+#define CESA_TDMA_BREAK_CHAIN			BIT(28)
+#define CESA_TDMA_TYPE_MSK			GENMASK(27, 0)
 #define CESA_TDMA_DUMMY				0
 #define CESA_TDMA_DATA				1
 #define CESA_TDMA_OP				2
+#define CESA_TDMA_IV				3
 
 /**
  * struct mv_cesa_tdma_desc - TDMA descriptor
@@ -390,6 +393,7 @@ struct mv_cesa_dev_dma {
 	struct dma_pool *op_pool;
 	struct dma_pool *cache_pool;
 	struct dma_pool *padding_pool;
+	struct dma_pool *iv_pool;
 };
 
 /**
@@ -398,7 +402,6 @@ struct mv_cesa_dev_dma {
  * @regs:	device registers
  * @sram_size:	usable SRAM size
  * @lock:	device lock
- * @queue:	crypto request queue
  * @engines:	array of engines
  * @dma:	dma pools
  *
@@ -410,7 +413,6 @@ struct mv_cesa_dev {
 	struct device *dev;
 	unsigned int sram_size;
 	spinlock_t lock;
-	struct crypto_queue queue;
 	struct mv_cesa_engine *engines;
 	struct mv_cesa_dev_dma *dma;
 };
@@ -429,6 +431,11 @@ struct mv_cesa_dev {
  * @int_mask:		interrupt mask cache
  * @pool:		memory pool pointing to the memory region reserved in
  *			SRAM
+ * @queue:		fifo of the pending crypto requests
+ * @load:		engine load counter, useful for load balancing
+ * @chain:		list of the current tdma descriptors being processed
+ * 			by this engine.
+ * @complete_queue:	fifo of the processed requests by the engine
  *
  * Structure storing CESA engine information.
  */
@@ -444,23 +451,27 @@ struct mv_cesa_engine {
 	size_t max_req_len;
 	u32 int_mask;
 	struct gen_pool *pool;
+	struct crypto_queue queue;
+	atomic_t load;
+	struct mv_cesa_tdma_chain chain;
+	struct list_head complete_queue;
 };
 
 /**
  * struct mv_cesa_req_ops - CESA request operations
- * @prepare:	prepare a request to be executed on the specified engine
  * @process:	process a request chunk result (should return 0 if the
  *		operation, -EINPROGRESS if it needs more steps or an error
  *		code)
  * @step:	launch the crypto operation on the next chunk
  * @cleanup:	cleanup the crypto request (release associated data)
+ * @complete:	complete the request, i.e copy result or context from sram when
+ * 		needed.
  */
 struct mv_cesa_req_ops {
-	void (*prepare)(struct crypto_async_request *req,
-			struct mv_cesa_engine *engine);
 	int (*process)(struct crypto_async_request *req, u32 status);
 	void (*step)(struct crypto_async_request *req);
 	void (*cleanup)(struct crypto_async_request *req);
+	void (*complete)(struct crypto_async_request *req);
 };
 
 /**
@@ -507,21 +518,11 @@ enum mv_cesa_req_type {
 
 /**
  * struct mv_cesa_req - CESA request
- * @type:	request type
  * @engine:	engine associated with this request
+ * @chain:	list of tdma descriptors associated  with this request
  */
 struct mv_cesa_req {
-	enum mv_cesa_req_type type;
 	struct mv_cesa_engine *engine;
-};
-
-/**
- * struct mv_cesa_tdma_req - CESA TDMA request
- * @base:	base information
- * @chain:	TDMA chain
- */
-struct mv_cesa_tdma_req {
-	struct mv_cesa_req base;
 	struct mv_cesa_tdma_chain chain;
 };
 
@@ -538,13 +539,11 @@ struct mv_cesa_sg_std_iter {
 
 /**
  * struct mv_cesa_ablkcipher_std_req - cipher standard request
- * @base:	base information
  * @op:		operation context
  * @offset:	current operation offset
  * @size:	size of the crypto operation
  */
 struct mv_cesa_ablkcipher_std_req {
-	struct mv_cesa_req base;
 	struct mv_cesa_op_ctx op;
 	unsigned int offset;
 	unsigned int size;
@@ -558,34 +557,27 @@ struct mv_cesa_ablkcipher_std_req {
  * @dst_nents:	number of entries in the dest sg list
  */
 struct mv_cesa_ablkcipher_req {
-	union {
-		struct mv_cesa_req base;
-		struct mv_cesa_tdma_req dma;
-		struct mv_cesa_ablkcipher_std_req std;
-	} req;
+	struct mv_cesa_req base;
+	struct mv_cesa_ablkcipher_std_req std;
 	int src_nents;
 	int dst_nents;
 };
 
 /**
  * struct mv_cesa_ahash_std_req - standard hash request
- * @base:	base information
  * @offset:	current operation offset
  */
 struct mv_cesa_ahash_std_req {
-	struct mv_cesa_req base;
 	unsigned int offset;
 };
 
 /**
  * struct mv_cesa_ahash_dma_req - DMA hash request
- * @base:		base information
  * @padding:		padding buffer
  * @padding_dma:	DMA address of the padding buffer
  * @cache_dma:		DMA address of the cache buffer
  */
 struct mv_cesa_ahash_dma_req {
-	struct mv_cesa_tdma_req base;
 	u8 *padding;
 	dma_addr_t padding_dma;
 	u8 *cache;
@@ -604,8 +596,8 @@ struct mv_cesa_ahash_dma_req {
  * @state:		hash state
  */
 struct mv_cesa_ahash_req {
+	struct mv_cesa_req base;
 	union {
-		struct mv_cesa_req base;
 		struct mv_cesa_ahash_dma_req dma;
 		struct mv_cesa_ahash_std_req std;
 	} req;
@@ -623,6 +615,35 @@ struct mv_cesa_ahash_req {
 
 extern struct mv_cesa_dev *cesa_dev;
 
+
+static inline void
+mv_cesa_engine_enqueue_complete_request(struct mv_cesa_engine *engine,
+					struct crypto_async_request *req)
+{
+	list_add_tail(&req->list, &engine->complete_queue);
+}
+
+static inline struct crypto_async_request *
+mv_cesa_engine_dequeue_complete_request(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req;
+
+	req = list_first_entry_or_null(&engine->complete_queue,
+				       struct crypto_async_request,
+				       list);
+	if (req)
+		list_del(&req->list);
+
+	return req;
+}
+
+
+static inline enum mv_cesa_req_type
+mv_cesa_req_get_type(struct mv_cesa_req *req)
+{
+	return req->chain.first ? CESA_DMA_REQ : CESA_STD_REQ;
+}
+
 static inline void mv_cesa_update_op_cfg(struct mv_cesa_op_ctx *op,
 					 u32 cfg, u32 mask)
 {
@@ -695,7 +716,32 @@ static inline bool mv_cesa_mac_op_is_first_frag(const struct mv_cesa_op_ctx *op)
 		CESA_SA_DESC_CFG_FIRST_FRAG;
 }
 
-int mv_cesa_queue_req(struct crypto_async_request *req);
+int mv_cesa_queue_req(struct crypto_async_request *req,
+		      struct mv_cesa_req *creq);
+
+struct crypto_async_request *
+mv_cesa_dequeue_req_locked(struct mv_cesa_engine *engine,
+			   struct crypto_async_request **backlog);
+
+static inline struct mv_cesa_engine *mv_cesa_select_engine(int weight)
+{
+	int i;
+	u32 min_load = U32_MAX;
+	struct mv_cesa_engine *selected = NULL;
+
+	for (i = 0; i < cesa_dev->caps->nengines; i++) {
+		struct mv_cesa_engine *engine = cesa_dev->engines + i;
+		u32 load = atomic_read(&engine->load);
+		if (load < min_load) {
+			min_load = load;
+			selected = engine;
+		}
+	}
+
+	atomic_add(weight, &selected->load);
+
+	return selected;
+}
 
 /*
  * Helper function that indicates whether a crypto request needs to be
@@ -765,9 +811,9 @@ static inline bool mv_cesa_req_dma_iter_next_op(struct mv_cesa_dma_iter *iter)
 	return iter->op_len;
 }
 
-void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq);
+void mv_cesa_dma_step(struct mv_cesa_req *dreq);
 
-static inline int mv_cesa_dma_process(struct mv_cesa_tdma_req *dreq,
+static inline int mv_cesa_dma_process(struct mv_cesa_req *dreq,
 				      u32 status)
 {
 	if (!(status & CESA_SA_INT_ACC0_IDMA_DONE))
@@ -779,10 +825,13 @@ static inline int mv_cesa_dma_process(struct mv_cesa_tdma_req *dreq,
 	return 0;
 }
 
-void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+void mv_cesa_dma_prepare(struct mv_cesa_req *dreq,
 			 struct mv_cesa_engine *engine);
+void mv_cesa_dma_cleanup(struct mv_cesa_req *dreq);
+void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
+			struct mv_cesa_req *dreq);
+int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status);
 
-void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq);
 
 static inline void
 mv_cesa_tdma_desc_iter_init(struct mv_cesa_tdma_chain *chain)
@@ -790,6 +839,9 @@ mv_cesa_tdma_desc_iter_init(struct mv_cesa_tdma_chain *chain)
 	memset(chain, 0, sizeof(*chain));
 }
 
+int mv_cesa_dma_add_iv_op(struct mv_cesa_tdma_chain *chain, dma_addr_t src,
+			  u32 size, u32 flags, gfp_t gfp_flags);
+
 struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
 					const struct mv_cesa_op_ctx *op_templ,
 					bool skip_ctx,
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index dcf1fceb9336..48df03a06066 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -70,25 +70,28 @@ mv_cesa_ablkcipher_dma_cleanup(struct ablkcipher_request *req)
 		dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
 			     DMA_BIDIRECTIONAL);
 	}
-	mv_cesa_dma_cleanup(&creq->req.dma);
+	mv_cesa_dma_cleanup(&creq->base);
 }
 
 static inline void mv_cesa_ablkcipher_cleanup(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ablkcipher_dma_cleanup(req);
 }
 
 static void mv_cesa_ablkcipher_std_step(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	size_t  len = min_t(size_t, req->nbytes - sreq->offset,
 			    CESA_SA_SRAM_PAYLOAD_SIZE);
 
+	mv_cesa_adjust_op(engine, &sreq->op);
+	memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
+
 	len = sg_pcopy_to_buffer(req->src, creq->src_nents,
 				 engine->sram + CESA_SA_DATA_SRAM_OFFSET,
 				 len, sreq->offset);
@@ -106,6 +109,8 @@ static void mv_cesa_ablkcipher_std_step(struct ablkcipher_request *req)
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
 	writel_relaxed(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
@@ -113,8 +118,8 @@ static int mv_cesa_ablkcipher_std_process(struct ablkcipher_request *req,
 					  u32 status)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	size_t len;
 
 	len = sg_pcopy_from_buffer(req->dst, creq->dst_nents,
@@ -133,21 +138,19 @@ static int mv_cesa_ablkcipher_process(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_req *basereq = &creq->base;
+	unsigned int ivsize;
 	int ret;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		ret = mv_cesa_dma_process(&creq->req.dma, status);
-	else
-		ret = mv_cesa_ablkcipher_std_process(ablkreq, status);
+	if (mv_cesa_req_get_type(basereq) == CESA_STD_REQ)
+		return mv_cesa_ablkcipher_std_process(ablkreq, status);
 
+	ret = mv_cesa_dma_process(basereq, status);
 	if (ret)
 		return ret;
 
-	memcpy_fromio(ablkreq->info,
-		      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
-		      crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq)));
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
+	memcpy_fromio(ablkreq->info, basereq->chain.last->data, ivsize);
 
 	return 0;
 }
@@ -157,8 +160,8 @@ static void mv_cesa_ablkcipher_step(struct crypto_async_request *req)
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->req.dma);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->base);
 	else
 		mv_cesa_ablkcipher_std_step(ablkreq);
 }
@@ -167,22 +170,19 @@ static inline void
 mv_cesa_ablkcipher_dma_prepare(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+	mv_cesa_dma_prepare(basereq, basereq->engine);
 }
 
 static inline void
 mv_cesa_ablkcipher_std_prepare(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
 
 	sreq->size = 0;
 	sreq->offset = 0;
-	mv_cesa_adjust_op(engine, &sreq->op);
-	memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
 }
 
 static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
@@ -190,9 +190,9 @@ static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-	creq->req.base.engine = engine;
+	creq->base.engine = engine;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ablkcipher_dma_prepare(ablkreq);
 	else
 		mv_cesa_ablkcipher_std_prepare(ablkreq);
@@ -206,11 +206,34 @@ mv_cesa_ablkcipher_req_cleanup(struct crypto_async_request *req)
 	mv_cesa_ablkcipher_cleanup(ablkreq);
 }
 
+static void
+mv_cesa_ablkcipher_complete(struct crypto_async_request *req)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+	struct mv_cesa_engine *engine = creq->base.engine;
+	unsigned int ivsize;
+
+	atomic_sub(ablkreq->nbytes, &engine->load);
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
+
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ) {
+		struct mv_cesa_req *basereq;
+
+		basereq = &creq->base;
+		memcpy(ablkreq->info, basereq->chain.last->data, ivsize);
+	} else {
+		memcpy_fromio(ablkreq->info,
+			      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
+			      ivsize);
+	}
+}
+
 static const struct mv_cesa_req_ops mv_cesa_ablkcipher_req_ops = {
 	.step = mv_cesa_ablkcipher_step,
 	.process = mv_cesa_ablkcipher_process,
-	.prepare = mv_cesa_ablkcipher_prepare,
 	.cleanup = mv_cesa_ablkcipher_req_cleanup,
+	.complete = mv_cesa_ablkcipher_complete,
 };
 
 static int mv_cesa_ablkcipher_cra_init(struct crypto_tfm *tfm)
@@ -295,15 +318,15 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
 	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		      GFP_KERNEL : GFP_ATOMIC;
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_req *basereq = &creq->base;
 	struct mv_cesa_ablkcipher_dma_iter iter;
 	struct mv_cesa_tdma_chain chain;
 	bool skip_ctx = false;
 	int ret;
+	unsigned int ivsize;
 
-	dreq->base.type = CESA_DMA_REQ;
-	dreq->chain.first = NULL;
-	dreq->chain.last = NULL;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	if (req->src != req->dst) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
@@ -358,12 +381,21 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 
 	} while (mv_cesa_ablkcipher_req_iter_next_op(&iter));
 
-	dreq->chain = chain;
+	/* Add output data for IV */
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
+	ret = mv_cesa_dma_add_iv_op(&chain, CESA_SA_CRYPT_IV_SRAM_OFFSET,
+				    ivsize, CESA_TDMA_SRC_IN_SRAM, flags);
+
+	if (ret)
+		goto err_free_tdma;
+
+	basereq->chain = chain;
+	basereq->chain.last->flags |= CESA_TDMA_END_OF_REQ;
 
 	return 0;
 
 err_free_tdma:
-	mv_cesa_dma_cleanup(dreq);
+	mv_cesa_dma_cleanup(basereq);
 	if (req->dst != req->src)
 		dma_unmap_sg(cesa_dev->dev, req->dst, creq->dst_nents,
 			     DMA_FROM_DEVICE);
@@ -380,11 +412,13 @@ mv_cesa_ablkcipher_std_req_init(struct ablkcipher_request *req,
 				const struct mv_cesa_op_ctx *op_templ)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	sreq->base.type = CESA_STD_REQ;
 	sreq->op = *op_templ;
 	sreq->skip_ctx = false;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	return 0;
 }
@@ -414,7 +448,6 @@ static int mv_cesa_ablkcipher_req_init(struct ablkcipher_request *req,
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_OP_CRYPT_ONLY,
 			      CESA_SA_DESC_CFG_OP_MSK);
 
-	/* TODO: add a threshold for DMA usage */
 	if (cesa_dev->caps->has_tdma)
 		ret = mv_cesa_ablkcipher_dma_req_init(req, tmpl);
 	else
@@ -423,28 +456,41 @@ static int mv_cesa_ablkcipher_req_init(struct ablkcipher_request *req,
 	return ret;
 }
 
-static int mv_cesa_des_op(struct ablkcipher_request *req,
-			  struct mv_cesa_op_ctx *tmpl)
+static int mv_cesa_ablkcipher_queue_req(struct ablkcipher_request *req,
+					struct mv_cesa_op_ctx *tmpl)
 {
-	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
 	int ret;
-
-	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
-			      CESA_SA_DESC_CFG_CRYPTM_MSK);
-
-	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_engine *engine;
 
 	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
 	if (ret)
 		return ret;
 
-	ret = mv_cesa_queue_req(&req->base);
+	engine = mv_cesa_select_engine(req->nbytes);
+	mv_cesa_ablkcipher_prepare(&req->base, engine);
+
+	ret = mv_cesa_queue_req(&req->base, &creq->base);
+
 	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
 }
 
+static int mv_cesa_des_op(struct ablkcipher_request *req,
+			  struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
+
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
+}
+
 static int mv_cesa_ecb_des_encrypt(struct ablkcipher_request *req)
 {
 	struct mv_cesa_op_ctx tmpl;
@@ -547,22 +593,13 @@ static int mv_cesa_des3_op(struct ablkcipher_request *req,
 			   struct mv_cesa_op_ctx *tmpl)
 {
 	struct mv_cesa_des3_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	int ret;
 
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_3DES,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK);
 
 	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES3_EDE_KEY_SIZE);
 
-	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
-	if (ret)
-		return ret;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ablkcipher_cleanup(req);
-
-	return ret;
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
 }
 
 static int mv_cesa_ecb_des3_ede_encrypt(struct ablkcipher_request *req)
@@ -673,7 +710,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 			  struct mv_cesa_op_ctx *tmpl)
 {
 	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	int ret, i;
+	int i;
 	u32 *key;
 	u32 cfg;
 
@@ -696,15 +733,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK |
 			      CESA_SA_DESC_CFG_AES_LEN_MSK);
 
-	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
-	if (ret)
-		return ret;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ablkcipher_cleanup(req);
-
-	return ret;
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
 }
 
 static int mv_cesa_ecb_aes_encrypt(struct ablkcipher_request *req)
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 7a5058da9151..c35912b4fffb 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -103,14 +103,14 @@ static inline void mv_cesa_ahash_dma_cleanup(struct ahash_request *req)
 
 	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
 	mv_cesa_ahash_dma_free_cache(&creq->req.dma);
-	mv_cesa_dma_cleanup(&creq->req.dma.base);
+	mv_cesa_dma_cleanup(&creq->base);
 }
 
 static inline void mv_cesa_ahash_cleanup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_cleanup(req);
 }
 
@@ -118,7 +118,7 @@ static void mv_cesa_ahash_last_cleanup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_last_cleanup(req);
 }
 
@@ -157,11 +157,23 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	struct mv_cesa_op_ctx *op;
 	unsigned int new_cache_ptr = 0;
 	u32 frag_mode;
 	size_t  len;
+	unsigned int digsize;
+	int i;
+
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
+
+	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
+	for (i = 0; i < digsize / 4; i++)
+		writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i));
+
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
 
 	if (creq->cache_ptr)
 		memcpy_toio(engine->sram + CESA_SA_DATA_SRAM_OFFSET,
@@ -237,6 +249,8 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
 	writel_relaxed(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
@@ -254,20 +268,17 @@ static int mv_cesa_ahash_std_process(struct ahash_request *req, u32 status)
 static inline void mv_cesa_ahash_dma_prepare(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma.base;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+	mv_cesa_dma_prepare(basereq, basereq->engine);
 }
 
 static void mv_cesa_ahash_std_prepare(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
 
 	sreq->offset = 0;
-	mv_cesa_adjust_op(engine, &creq->op_tmpl);
-	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
 }
 
 static void mv_cesa_ahash_step(struct crypto_async_request *req)
@@ -275,8 +286,8 @@ static void mv_cesa_ahash_step(struct crypto_async_request *req)
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->req.dma.base);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->base);
 	else
 		mv_cesa_ahash_std_step(ahashreq);
 }
@@ -285,17 +296,20 @@ static int mv_cesa_ahash_process(struct crypto_async_request *req, u32 status)
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
-	struct mv_cesa_engine *engine = creq->req.base.engine;
-	unsigned int digsize;
-	int ret, i;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		ret = mv_cesa_dma_process(&creq->req.dma.base, status);
-	else
-		ret = mv_cesa_ahash_std_process(ahashreq, status);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		return mv_cesa_dma_process(&creq->base, status);
 
-	if (ret == -EINPROGRESS)
-		return ret;
+	return mv_cesa_ahash_std_process(ahashreq, status);
+}
+
+static void mv_cesa_ahash_complete(struct crypto_async_request *req)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+	struct mv_cesa_engine *engine = creq->base.engine;
+	unsigned int digsize;
+	int i;
 
 	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
 	for (i = 0; i < digsize / 4; i++)
@@ -325,7 +339,7 @@ static int mv_cesa_ahash_process(struct crypto_async_request *req, u32 status)
 		}
 	}
 
-	return ret;
+	atomic_sub(ahashreq->nbytes, &engine->load);
 }
 
 static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
@@ -333,19 +347,13 @@ static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
-	unsigned int digsize;
-	int i;
 
-	creq->req.base.engine = engine;
+	creq->base.engine = engine;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_prepare(ahashreq);
 	else
 		mv_cesa_ahash_std_prepare(ahashreq);
-
-	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
-	for (i = 0; i < digsize / 4; i++)
-		writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i));
 }
 
 static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
@@ -362,8 +370,8 @@ static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
 static const struct mv_cesa_req_ops mv_cesa_ahash_req_ops = {
 	.step = mv_cesa_ahash_step,
 	.process = mv_cesa_ahash_process,
-	.prepare = mv_cesa_ahash_prepare,
 	.cleanup = mv_cesa_ahash_req_cleanup,
+	.complete = mv_cesa_ahash_complete,
 };
 
 static int mv_cesa_ahash_init(struct ahash_request *req,
@@ -553,15 +561,14 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		      GFP_KERNEL : GFP_ATOMIC;
-	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
-	struct mv_cesa_tdma_req *dreq = &ahashdreq->base;
+	struct mv_cesa_req *basereq = &creq->base;
 	struct mv_cesa_ahash_dma_iter iter;
 	struct mv_cesa_op_ctx *op = NULL;
 	unsigned int frag_len;
 	int ret;
 
-	dreq->chain.first = NULL;
-	dreq->chain.last = NULL;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	if (creq->src_nents) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
@@ -572,14 +579,14 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 		}
 	}
 
-	mv_cesa_tdma_desc_iter_init(&dreq->chain);
+	mv_cesa_tdma_desc_iter_init(&basereq->chain);
 	mv_cesa_ahash_req_iter_init(&iter, req);
 
 	/*
 	 * Add the cache (left-over data from a previous block) first.
 	 * This will never overflow the SRAM size.
 	 */
-	ret = mv_cesa_ahash_dma_add_cache(&dreq->chain, &iter, creq, flags);
+	ret = mv_cesa_ahash_dma_add_cache(&basereq->chain, &iter, creq, flags);
 	if (ret)
 		goto err_free_tdma;
 
@@ -590,7 +597,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 		 * data. We intentionally do not add the final op block.
 		 */
 		while (true) {
-			ret = mv_cesa_dma_add_op_transfers(&dreq->chain,
+			ret = mv_cesa_dma_add_op_transfers(&basereq->chain,
 							   &iter.base,
 							   &iter.src, flags);
 			if (ret)
@@ -601,7 +608,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 			if (!mv_cesa_ahash_req_iter_next_op(&iter))
 				break;
 
-			op = mv_cesa_dma_add_frag(&dreq->chain, &creq->op_tmpl,
+			op = mv_cesa_dma_add_frag(&basereq->chain, &creq->op_tmpl,
 						  frag_len, flags);
 			if (IS_ERR(op)) {
 				ret = PTR_ERR(op);
@@ -619,10 +626,10 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	 * operation, which depends whether this is the final request.
 	 */
 	if (creq->last_req)
-		op = mv_cesa_ahash_dma_last_req(&dreq->chain, &iter, creq,
+		op = mv_cesa_ahash_dma_last_req(&basereq->chain, &iter, creq,
 						frag_len, flags);
 	else if (frag_len)
-		op = mv_cesa_dma_add_frag(&dreq->chain, &creq->op_tmpl,
+		op = mv_cesa_dma_add_frag(&basereq->chain, &creq->op_tmpl,
 					  frag_len, flags);
 
 	if (IS_ERR(op)) {
@@ -632,7 +639,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 
 	if (op) {
 		/* Add dummy desc to wait for crypto operation end */
-		ret = mv_cesa_dma_add_dummy_end(&dreq->chain, flags);
+		ret = mv_cesa_dma_add_dummy_end(&basereq->chain, flags);
 		if (ret)
 			goto err_free_tdma;
 	}
@@ -643,10 +650,13 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	else
 		creq->cache_ptr = 0;
 
+	basereq->chain.last->flags |= (CESA_TDMA_END_OF_REQ |
+				       CESA_TDMA_BREAK_CHAIN);
+
 	return 0;
 
 err_free_tdma:
-	mv_cesa_dma_cleanup(dreq);
+	mv_cesa_dma_cleanup(basereq);
 	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
 
 err:
@@ -660,11 +670,6 @@ static int mv_cesa_ahash_req_init(struct ahash_request *req, bool *cached)
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	int ret;
 
-	if (cesa_dev->caps->has_tdma)
-		creq->req.base.type = CESA_DMA_REQ;
-	else
-		creq->req.base.type = CESA_STD_REQ;
-
 	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
 	if (creq->src_nents < 0) {
 		dev_err(cesa_dev->dev, "Invalid number of src SG");
@@ -678,19 +683,19 @@ static int mv_cesa_ahash_req_init(struct ahash_request *req, bool *cached)
 	if (*cached)
 		return 0;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (cesa_dev->caps->has_tdma)
 		ret = mv_cesa_ahash_dma_req_init(req);
 
 	return ret;
 }
 
-static int mv_cesa_ahash_update(struct ahash_request *req)
+static int mv_cesa_ahash_queue_req(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_engine *engine;
 	bool cached = false;
 	int ret;
 
-	creq->len += req->nbytes;
 	ret = mv_cesa_ahash_req_init(req, &cached);
 	if (ret)
 		return ret;
@@ -698,61 +703,48 @@ static int mv_cesa_ahash_update(struct ahash_request *req)
 	if (cached)
 		return 0;
 
-	ret = mv_cesa_queue_req(&req->base);
+	engine = mv_cesa_select_engine(req->nbytes);
+	mv_cesa_ahash_prepare(&req->base, engine);
+
+	ret = mv_cesa_queue_req(&req->base, &creq->base);
+
 	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
 }
 
+static int mv_cesa_ahash_update(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	creq->len += req->nbytes;
+
+	return mv_cesa_ahash_queue_req(req);
+}
+
 static int mv_cesa_ahash_final(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
-	bool cached = false;
-	int ret;
 
 	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
 	creq->last_req = true;
 	req->nbytes = 0;
 
-	ret = mv_cesa_ahash_req_init(req, &cached);
-	if (ret)
-		return ret;
-
-	if (cached)
-		return 0;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ahash_cleanup(req);
-
-	return ret;
+	return mv_cesa_ahash_queue_req(req);
 }
 
 static int mv_cesa_ahash_finup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
-	bool cached = false;
-	int ret;
 
 	creq->len += req->nbytes;
 	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
 	creq->last_req = true;
 
-	ret = mv_cesa_ahash_req_init(req, &cached);
-	if (ret)
-		return ret;
-
-	if (cached)
-		return 0;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ahash_cleanup(req);
-
-	return ret;
+	return mv_cesa_ahash_queue_req(req);
 }
 
 static int mv_cesa_ahash_export(struct ahash_request *req, void *hash,
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
index 0ad8f1ecf175..86a065bcc187 100644
--- a/drivers/crypto/marvell/tdma.c
+++ b/drivers/crypto/marvell/tdma.c
@@ -37,9 +37,9 @@ bool mv_cesa_req_dma_iter_next_transfer(struct mv_cesa_dma_iter *iter,
 	return true;
 }
 
-void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq)
+void mv_cesa_dma_step(struct mv_cesa_req *dreq)
 {
-	struct mv_cesa_engine *engine = dreq->base.engine;
+	struct mv_cesa_engine *engine = dreq->engine;
 
 	writel_relaxed(0, engine->regs + CESA_SA_CFG);
 
@@ -53,19 +53,25 @@ void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq)
 		       engine->regs + CESA_SA_CFG);
 	writel_relaxed(dreq->chain.first->cur_dma,
 		       engine->regs + CESA_TDMA_NEXT_ADDR);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
-void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq)
+void mv_cesa_dma_cleanup(struct mv_cesa_req *dreq)
 {
 	struct mv_cesa_tdma_desc *tdma;
 
 	for (tdma = dreq->chain.first; tdma;) {
 		struct mv_cesa_tdma_desc *old_tdma = tdma;
+		u32 type = tdma->flags & CESA_TDMA_TYPE_MSK;
 
-		if (tdma->flags & CESA_TDMA_OP)
+		if (type == CESA_TDMA_OP)
 			dma_pool_free(cesa_dev->dma->op_pool, tdma->op,
 				      le32_to_cpu(tdma->src));
+		else if (type == CESA_TDMA_IV)
+			dma_pool_free(cesa_dev->dma->iv_pool, tdma->data,
+				      le32_to_cpu(tdma->dst));
 
 		tdma = tdma->next;
 		dma_pool_free(cesa_dev->dma->tdma_desc_pool, old_tdma,
@@ -76,7 +82,7 @@ void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq)
 	dreq->chain.last = NULL;
 }
 
-void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+void mv_cesa_dma_prepare(struct mv_cesa_req *dreq,
 			 struct mv_cesa_engine *engine)
 {
 	struct mv_cesa_tdma_desc *tdma;
@@ -88,11 +94,97 @@ void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
 		if (tdma->flags & CESA_TDMA_SRC_IN_SRAM)
 			tdma->src = cpu_to_le32(tdma->src + engine->sram_dma);
 
-		if (tdma->flags & CESA_TDMA_OP)
+		if ((tdma->flags & CESA_TDMA_TYPE_MSK) == CESA_TDMA_OP)
 			mv_cesa_adjust_op(engine, tdma->op);
 	}
 }
 
+void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
+			struct mv_cesa_req *dreq)
+{
+	if (engine->chain.first == NULL && engine->chain.last == NULL) {
+		engine->chain.first = dreq->chain.first;
+		engine->chain.last  = dreq->chain.last;
+	} else {
+		struct mv_cesa_tdma_desc *last;
+
+		last = engine->chain.last;
+		last->next = dreq->chain.first;
+		engine->chain.last = dreq->chain.last;
+
+		if (!(last->flags & CESA_TDMA_BREAK_CHAIN))
+			last->next_dma = dreq->chain.first->cur_dma;
+	}
+}
+
+int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status)
+{
+	struct crypto_async_request *req = NULL;
+	struct mv_cesa_tdma_desc *tdma = NULL, *next = NULL;
+	dma_addr_t tdma_cur;
+	int res = 0;
+
+	tdma_cur = readl(engine->regs + CESA_TDMA_CUR);
+
+	for (tdma = engine->chain.first; tdma; tdma = next) {
+		spin_lock_bh(&engine->lock);
+		next = tdma->next;
+		spin_unlock_bh(&engine->lock);
+
+		if (tdma->flags & CESA_TDMA_END_OF_REQ) {
+			struct crypto_async_request *backlog = NULL;
+			struct mv_cesa_ctx *ctx;
+			u32 current_status;
+
+			spin_lock_bh(&engine->lock);
+			/*
+			 * if req is NULL, this means we're processing the
+			 * request in engine->req.
+			 */
+			if (!req)
+				req = engine->req;
+			else
+				req = mv_cesa_dequeue_req_locked(engine,
+								 &backlog);
+
+			/* Re-chaining to the next request */
+			engine->chain.first = tdma->next;
+			tdma->next = NULL;
+
+			/* If this is the last request, clear the chain */
+			if (engine->chain.first == NULL)
+				engine->chain.last  = NULL;
+			spin_unlock_bh(&engine->lock);
+
+			ctx = crypto_tfm_ctx(req->tfm);
+			current_status = (tdma->cur_dma == tdma_cur) ?
+					  status : CESA_SA_INT_ACC0_IDMA_DONE;
+			res = ctx->ops->process(req, current_status);
+			ctx->ops->complete(req);
+
+			if (res == 0)
+				mv_cesa_engine_enqueue_complete_request(engine,
+									req);
+
+			if (backlog)
+				backlog->complete(backlog, -EINPROGRESS);
+		}
+
+		if (res || tdma->cur_dma == tdma_cur)
+			break;
+	}
+
+	/* Save the last request in error to engine->req, so that the core
+	 * knows which request was fautly */
+	if (res) {
+		spin_lock_bh(&engine->lock);
+		engine->req = req;
+		spin_unlock_bh(&engine->lock);
+	}
+
+	return res;
+}
+
 static struct mv_cesa_tdma_desc *
 mv_cesa_dma_add_desc(struct mv_cesa_tdma_chain *chain, gfp_t flags)
 {
@@ -117,6 +209,32 @@ mv_cesa_dma_add_desc(struct mv_cesa_tdma_chain *chain, gfp_t flags)
 	return new_tdma;
 }
 
+int mv_cesa_dma_add_iv_op(struct mv_cesa_tdma_chain *chain, dma_addr_t src,
+			  u32 size, u32 flags, gfp_t gfp_flags)
+{
+
+	struct mv_cesa_tdma_desc *tdma;
+	u8 *iv;
+	dma_addr_t dma_handle;
+
+	tdma = mv_cesa_dma_add_desc(chain, gfp_flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	iv = dma_pool_alloc(cesa_dev->dma->iv_pool, gfp_flags, &dma_handle);
+	if (!iv)
+		return -ENOMEM;
+
+	tdma->byte_cnt = cpu_to_le32(size | BIT(31));
+	tdma->src = src;
+	tdma->dst = cpu_to_le32(dma_handle);
+	tdma->data = iv;
+
+	flags &= (CESA_TDMA_DST_IN_SRAM | CESA_TDMA_SRC_IN_SRAM);
+	tdma->flags = flags | CESA_TDMA_IV;
+	return 0;
+}
+
 struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
 					const struct mv_cesa_op_ctx *op_templ,
 					bool skip_ctx,
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index 59ed54e464a9..625ee50fd78b 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -11,7 +11,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/crypto.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -25,6 +24,7 @@
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 
 #define DCP_MAX_CHANS	4
 #define DCP_BUF_SZ	PAGE_SIZE
@@ -84,7 +84,7 @@ struct dcp_async_ctx {
 	unsigned int			hot:1;
 
 	/* Crypto-specific context */
-	struct crypto_ablkcipher	*fallback;
+	struct crypto_skcipher		*fallback;
 	unsigned int			key_len;
 	uint8_t				key[AES_KEYSIZE_128];
 };
@@ -374,20 +374,22 @@ static int dcp_chan_thread_aes(void *data)
 
 static int mxs_dcp_block_fallback(struct ablkcipher_request *req, int enc)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
-	struct dcp_async_ctx *ctx = crypto_ablkcipher_ctx(
-		crypto_ablkcipher_reqtfm(req));
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct dcp_async_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
 	int ret;
 
-	ablkcipher_request_set_tfm(req, ctx->fallback);
+	skcipher_request_set_tfm(subreq, ctx->fallback);
+	skcipher_request_set_callback(subreq, req->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   req->nbytes, req->info);
 
 	if (enc)
-		ret = crypto_ablkcipher_encrypt(req);
+		ret = crypto_skcipher_encrypt(subreq);
 	else
-		ret = crypto_ablkcipher_decrypt(req);
+		ret = crypto_skcipher_decrypt(subreq);
 
-	ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+	skcipher_request_zero(subreq);
 
 	return ret;
 }
@@ -453,28 +455,22 @@ static int mxs_dcp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 		return 0;
 	}
 
-	/* Check if the key size is supported by kernel at all. */
-	if (len != AES_KEYSIZE_192 && len != AES_KEYSIZE_256) {
-		tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-
 	/*
 	 * If the requested AES key size is not supported by the hardware,
 	 * but is supported by in-kernel software implementation, we use
 	 * software fallback.
 	 */
-	actx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	actx->fallback->base.crt_flags |=
-		tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK;
+	crypto_skcipher_clear_flags(actx->fallback, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(actx->fallback,
+				  tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_ablkcipher_setkey(actx->fallback, key, len);
+	ret = crypto_skcipher_setkey(actx->fallback, key, len);
 	if (!ret)
 		return 0;
 
 	tfm->base.crt_flags &= ~CRYPTO_TFM_RES_MASK;
-	tfm->base.crt_flags |=
-		actx->fallback->base.crt_flags & CRYPTO_TFM_RES_MASK;
+	tfm->base.crt_flags |= crypto_skcipher_get_flags(actx->fallback) &
+			       CRYPTO_TFM_RES_MASK;
 
 	return ret;
 }
@@ -484,9 +480,9 @@ static int mxs_dcp_aes_fallback_init(struct crypto_tfm *tfm)
 	const char *name = crypto_tfm_alg_name(tfm);
 	const uint32_t flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK;
 	struct dcp_async_ctx *actx = crypto_tfm_ctx(tfm);
-	struct crypto_ablkcipher *blk;
+	struct crypto_skcipher *blk;
 
-	blk = crypto_alloc_ablkcipher(name, 0, flags);
+	blk = crypto_alloc_skcipher(name, 0, flags);
 	if (IS_ERR(blk))
 		return PTR_ERR(blk);
 
@@ -499,8 +495,7 @@ static void mxs_dcp_aes_fallback_exit(struct crypto_tfm *tfm)
 {
 	struct dcp_async_ctx *actx = crypto_tfm_ctx(tfm);
 
-	crypto_free_ablkcipher(actx->fallback);
-	actx->fallback = NULL;
+	crypto_free_skcipher(actx->fallback);
 }
 
 /*
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 0794f1cc0018..42f0f229f7f7 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -392,7 +392,7 @@ static void nx_of_update_msc(struct device   *dev,
 		     ((bytes_so_far + sizeof(struct msc_triplet)) <= lenp) &&
 		     i < msc->triplets;
 		     i++) {
-			if (msc->fc > NX_MAX_FC || msc->mode > NX_MAX_MODE) {
+			if (msc->fc >= NX_MAX_FC || msc->mode >= NX_MAX_MODE) {
 				dev_err(dev, "unknown function code/mode "
 					"combo: %d/%d (ignored)\n", msc->fc,
 					msc->mode);
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index ce174d3b842c..4ab53a604312 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -528,8 +528,6 @@ static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 
 	omap_aes_dma_stop(dd);
 
-	dmaengine_terminate_all(dd->dma_lch_in);
-	dmaengine_terminate_all(dd->dma_lch_out);
 
 	return 0;
 }
@@ -580,10 +578,12 @@ static int omap_aes_copy_sgs(struct omap_aes_dev *dd)
 	sg_init_table(&dd->in_sgl, 1);
 	sg_set_buf(&dd->in_sgl, buf_in, total);
 	dd->in_sg = &dd->in_sgl;
+	dd->in_sg_len = 1;
 
 	sg_init_table(&dd->out_sgl, 1);
 	sg_set_buf(&dd->out_sgl, buf_out, total);
 	dd->out_sg = &dd->out_sgl;
+	dd->out_sg_len = 1;
 
 	return 0;
 }
@@ -604,7 +604,6 @@ static int omap_aes_prepare_req(struct crypto_engine *engine,
 			crypto_ablkcipher_reqtfm(req));
 	struct omap_aes_dev *dd = omap_aes_find_dev(ctx);
 	struct omap_aes_reqctx *rctx;
-	int len;
 
 	if (!dd)
 		return -ENODEV;
@@ -616,6 +615,14 @@ static int omap_aes_prepare_req(struct crypto_engine *engine,
 	dd->in_sg = req->src;
 	dd->out_sg = req->dst;
 
+	dd->in_sg_len = sg_nents_for_len(dd->in_sg, dd->total);
+	if (dd->in_sg_len < 0)
+		return dd->in_sg_len;
+
+	dd->out_sg_len = sg_nents_for_len(dd->out_sg, dd->total);
+	if (dd->out_sg_len < 0)
+		return dd->out_sg_len;
+
 	if (omap_aes_check_aligned(dd->in_sg, dd->total) ||
 	    omap_aes_check_aligned(dd->out_sg, dd->total)) {
 		if (omap_aes_copy_sgs(dd))
@@ -625,11 +632,6 @@ static int omap_aes_prepare_req(struct crypto_engine *engine,
 		dd->sgs_copied = 0;
 	}
 
-	len = ALIGN(dd->total, AES_BLOCK_SIZE);
-	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, len);
-	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, len);
-	BUG_ON(dd->in_sg_len < 0 || dd->out_sg_len < 0);
-
 	rctx = ablkcipher_request_ctx(req);
 	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
 	rctx->mode &= FLAGS_MODE_MASK;
@@ -1185,17 +1187,19 @@ static int omap_aes_probe(struct platform_device *pdev)
 	spin_unlock(&list_lock);
 
 	for (i = 0; i < dd->pdata->algs_info_size; i++) {
-		for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
-			algp = &dd->pdata->algs_info[i].algs_list[j];
+		if (!dd->pdata->algs_info[i].registered) {
+			for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
+				algp = &dd->pdata->algs_info[i].algs_list[j];
 
-			pr_debug("reg alg: %s\n", algp->cra_name);
-			INIT_LIST_HEAD(&algp->cra_list);
+				pr_debug("reg alg: %s\n", algp->cra_name);
+				INIT_LIST_HEAD(&algp->cra_list);
 
-			err = crypto_register_alg(algp);
-			if (err)
-				goto err_algs;
+				err = crypto_register_alg(algp);
+				if (err)
+					goto err_algs;
 
-			dd->pdata->algs_info[i].registered++;
+				dd->pdata->algs_info[i].registered++;
+			}
 		}
 	}
 
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index 3eedb03111ba..5691434ffb2d 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -560,10 +560,12 @@ static int omap_des_copy_sgs(struct omap_des_dev *dd)
 	sg_init_table(&dd->in_sgl, 1);
 	sg_set_buf(&dd->in_sgl, buf_in, dd->total);
 	dd->in_sg = &dd->in_sgl;
+	dd->in_sg_len = 1;
 
 	sg_init_table(&dd->out_sgl, 1);
 	sg_set_buf(&dd->out_sgl, buf_out, dd->total);
 	dd->out_sg = &dd->out_sgl;
+	dd->out_sg_len = 1;
 
 	return 0;
 }
@@ -595,6 +597,14 @@ static int omap_des_prepare_req(struct crypto_engine *engine,
 	dd->in_sg = req->src;
 	dd->out_sg = req->dst;
 
+	dd->in_sg_len = sg_nents_for_len(dd->in_sg, dd->total);
+	if (dd->in_sg_len < 0)
+		return dd->in_sg_len;
+
+	dd->out_sg_len = sg_nents_for_len(dd->out_sg, dd->total);
+	if (dd->out_sg_len < 0)
+		return dd->out_sg_len;
+
 	if (omap_des_copy_needed(dd->in_sg) ||
 	    omap_des_copy_needed(dd->out_sg)) {
 		if (omap_des_copy_sgs(dd))
@@ -604,10 +614,6 @@ static int omap_des_prepare_req(struct crypto_engine *engine,
 		dd->sgs_copied = 0;
 	}
 
-	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, dd->total);
-	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, dd->total);
-	BUG_ON(dd->in_sg_len < 0 || dd->out_sg_len < 0);
-
 	rctx = ablkcipher_request_ctx(req);
 	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
 	rctx->mode &= FLAGS_MODE_MASK;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 63464e86f2b1..7fe4eef12fe2 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -100,6 +100,8 @@
 
 #define DEFAULT_TIMEOUT_INTERVAL	HZ
 
+#define DEFAULT_AUTOSUSPEND_DELAY	1000
+
 /* mostly device flags */
 #define FLAGS_BUSY		0
 #define FLAGS_FINAL		1
@@ -173,7 +175,7 @@ struct omap_sham_ctx {
 	struct omap_sham_hmac_ctx base[0];
 };
 
-#define OMAP_SHAM_QUEUE_LENGTH	1
+#define OMAP_SHAM_QUEUE_LENGTH	10
 
 struct omap_sham_algs_info {
 	struct ahash_alg	*algs_list;
@@ -813,7 +815,6 @@ static int omap_sham_update_dma_stop(struct omap_sham_dev *dd)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req);
 
-	dmaengine_terminate_all(dd->dma_lch);
 
 	if (ctx->flags & BIT(FLAGS_SG)) {
 		dma_unmap_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE);
@@ -999,7 +1000,8 @@ static void omap_sham_finish_req(struct ahash_request *req, int err)
 	dd->flags &= ~(BIT(FLAGS_BUSY) | BIT(FLAGS_FINAL) | BIT(FLAGS_CPU) |
 			BIT(FLAGS_DMA_READY) | BIT(FLAGS_OUTPUT_READY));
 
-	pm_runtime_put(dd->dev);
+	pm_runtime_mark_last_busy(dd->dev);
+	pm_runtime_put_autosuspend(dd->dev);
 
 	if (req->base.complete)
 		req->base.complete(&req->base, err);
@@ -1093,7 +1095,7 @@ static int omap_sham_update(struct ahash_request *req)
 	ctx->offset = 0;
 
 	if (ctx->flags & BIT(FLAGS_FINUP)) {
-		if ((ctx->digcnt + ctx->bufcnt + ctx->total) < 9) {
+		if ((ctx->digcnt + ctx->bufcnt + ctx->total) < 240) {
 			/*
 			* OMAP HW accel works only with buffers >= 9
 			* will switch to bypass in final()
@@ -1149,9 +1151,13 @@ static int omap_sham_final(struct ahash_request *req)
 	if (ctx->flags & BIT(FLAGS_ERROR))
 		return 0; /* uncompleted hash is not needed */
 
-	/* OMAP HW accel works only with buffers >= 9 */
-	/* HMAC is always >= 9 because ipad == block size */
-	if ((ctx->digcnt + ctx->bufcnt) < 9)
+	/*
+	 * OMAP HW accel works only with buffers >= 9.
+	 * HMAC is always >= 9 because ipad == block size.
+	 * If buffersize is less than 240, we use fallback SW encoding,
+	 * as using DMA + HW in this case doesn't provide any benefit.
+	 */
+	if ((ctx->digcnt + ctx->bufcnt) < 240)
 		return omap_sham_final_shash(req);
 	else if (ctx->bufcnt)
 		return omap_sham_enqueue(req, OP_FINAL);
@@ -1328,7 +1334,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 	.halg.base	= {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "omap-sha1",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1351,7 +1357,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 	.halg.base	= {
 		.cra_name		= "md5",
 		.cra_driver_name	= "omap-md5",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1375,7 +1381,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 	.halg.base	= {
 		.cra_name		= "hmac(sha1)",
 		.cra_driver_name	= "omap-hmac-sha1",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1400,7 +1406,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 	.halg.base	= {
 		.cra_name		= "hmac(md5)",
 		.cra_driver_name	= "omap-hmac-md5",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1428,7 +1434,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 	.halg.base	= {
 		.cra_name		= "sha224",
 		.cra_driver_name	= "omap-sha224",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1450,7 +1456,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 	.halg.base	= {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "omap-sha256",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1473,7 +1479,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 	.halg.base	= {
 		.cra_name		= "hmac(sha224)",
 		.cra_driver_name	= "omap-hmac-sha224",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1497,7 +1503,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 	.halg.base	= {
 		.cra_name		= "hmac(sha256)",
 		.cra_driver_name	= "omap-hmac-sha256",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1523,7 +1529,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 	.halg.base	= {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "omap-sha384",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1545,7 +1551,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 	.halg.base	= {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "omap-sha512",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1568,7 +1574,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 	.halg.base	= {
 		.cra_name		= "hmac(sha384)",
 		.cra_driver_name	= "omap-hmac-sha384",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1592,7 +1598,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 	.halg.base	= {
 		.cra_name		= "hmac(sha512)",
 		.cra_driver_name	= "omap-hmac-sha512",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1946,6 +1952,9 @@ static int omap_sham_probe(struct platform_device *pdev)
 
 	dd->flags |= dd->pdata->flags;
 
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY);
+
 	pm_runtime_enable(dev);
 	pm_runtime_irq_safe(dev);
 
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 3b1c7ecf078f..47576098831f 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -171,7 +171,7 @@ struct spacc_ablk_ctx {
 	 * The fallback cipher. If the operation can't be done in hardware,
 	 * fallback to a software version.
 	 */
-	struct crypto_ablkcipher	*sw_cipher;
+	struct crypto_skcipher		*sw_cipher;
 };
 
 /* AEAD cipher context. */
@@ -789,33 +789,35 @@ static int spacc_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	 * request for any other size (192 bits) then we need to do a software
 	 * fallback.
 	 */
-	if (len != AES_KEYSIZE_128 && len != AES_KEYSIZE_256 &&
-	    ctx->sw_cipher) {
+	if (len != AES_KEYSIZE_128 && len != AES_KEYSIZE_256) {
+		if (!ctx->sw_cipher)
+			return -EINVAL;
+
 		/*
 		 * Set the fallback transform to use the same request flags as
 		 * the hardware transform.
 		 */
-		ctx->sw_cipher->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-		ctx->sw_cipher->base.crt_flags |=
-			cipher->base.crt_flags & CRYPTO_TFM_REQ_MASK;
+		crypto_skcipher_clear_flags(ctx->sw_cipher,
+					    CRYPTO_TFM_REQ_MASK);
+		crypto_skcipher_set_flags(ctx->sw_cipher,
+					  cipher->base.crt_flags &
+					  CRYPTO_TFM_REQ_MASK);
+
+		err = crypto_skcipher_setkey(ctx->sw_cipher, key, len);
+
+		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
+		tfm->crt_flags |=
+			crypto_skcipher_get_flags(ctx->sw_cipher) &
+			CRYPTO_TFM_RES_MASK;
 
-		err = crypto_ablkcipher_setkey(ctx->sw_cipher, key, len);
 		if (err)
 			goto sw_setkey_failed;
-	} else if (len != AES_KEYSIZE_128 && len != AES_KEYSIZE_256 &&
-		   !ctx->sw_cipher)
-		err = -EINVAL;
+	}
 
 	memcpy(ctx->key, key, len);
 	ctx->key_len = len;
 
 sw_setkey_failed:
-	if (err && ctx->sw_cipher) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |=
-			ctx->sw_cipher->base.crt_flags & CRYPTO_TFM_RES_MASK;
-	}
-
 	return err;
 }
 
@@ -910,20 +912,21 @@ static int spacc_ablk_do_fallback(struct ablkcipher_request *req,
 	struct crypto_tfm *old_tfm =
 	    crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(old_tfm);
+	SKCIPHER_REQUEST_ON_STACK(subreq, ctx->sw_cipher);
 	int err;
 
-	if (!ctx->sw_cipher)
-		return -EINVAL;
-
 	/*
 	 * Change the request to use the software fallback transform, and once
 	 * the ciphering has completed, put the old transform back into the
 	 * request.
 	 */
-	ablkcipher_request_set_tfm(req, ctx->sw_cipher);
-	err = is_encrypt ? crypto_ablkcipher_encrypt(req) :
-		crypto_ablkcipher_decrypt(req);
-	ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(old_tfm));
+	skcipher_request_set_tfm(subreq, ctx->sw_cipher);
+	skcipher_request_set_callback(subreq, req->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   req->nbytes, req->info);
+	err = is_encrypt ? crypto_skcipher_encrypt(subreq) :
+			   crypto_skcipher_decrypt(subreq);
+	skcipher_request_zero(subreq);
 
 	return err;
 }
@@ -1015,12 +1018,13 @@ static int spacc_ablk_cra_init(struct crypto_tfm *tfm)
 	ctx->generic.flags = spacc_alg->type;
 	ctx->generic.engine = engine;
 	if (alg->cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
-		ctx->sw_cipher = crypto_alloc_ablkcipher(alg->cra_name, 0,
-				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+		ctx->sw_cipher = crypto_alloc_skcipher(
+			alg->cra_name, 0, CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_NEED_FALLBACK);
 		if (IS_ERR(ctx->sw_cipher)) {
 			dev_warn(engine->dev, "failed to allocate fallback for %s\n",
 				 alg->cra_name);
-			ctx->sw_cipher = NULL;
+			return PTR_ERR(ctx->sw_cipher);
 		}
 	}
 	ctx->generic.key_offs = spacc_alg->key_offs;
@@ -1035,9 +1039,7 @@ static void spacc_ablk_cra_exit(struct crypto_tfm *tfm)
 {
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (ctx->sw_cipher)
-		crypto_free_ablkcipher(ctx->sw_cipher);
-	ctx->sw_cipher = NULL;
+	crypto_free_skcipher(ctx->sw_cipher);
 }
 
 static int spacc_ablk_encrypt(struct ablkcipher_request *req)
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index 85b44e577684..ce3cae40f949 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -4,12 +4,13 @@ config CRYPTO_DEV_QAT
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_AKCIPHER
+	select CRYPTO_DH
 	select CRYPTO_HMAC
+	select CRYPTO_RSA
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
 	select FW_LOADER
-	select ASN1
 
 config CRYPTO_DEV_QAT_DH895xCC
 	tristate "Support for Intel(R) DH895xCC"
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
index c5bd5a9abc4d..6bc68bc00d76 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
+++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
@@ -229,6 +229,7 @@ void adf_init_hw_data_c3xxx(struct adf_hw_device_data *hw_data)
 	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
 	hw_data->enable_ints = adf_enable_ints;
 	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->reset_device = adf_reset_flr;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
 }
 
diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
index 879e04cae714..618cec360b39 100644
--- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
+++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
@@ -239,6 +239,7 @@ void adf_init_hw_data_c62x(struct adf_hw_device_data *hw_data)
 	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
 	hw_data->enable_ints = adf_enable_ints;
 	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->reset_device = adf_reset_flr;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
 }
 
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
index 5fc3dbb9ada0..92fb6ffdc062 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -1,12 +1,3 @@
-$(obj)/qat_rsapubkey-asn1.o: $(obj)/qat_rsapubkey-asn1.c \
-			     $(obj)/qat_rsapubkey-asn1.h
-$(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \
-			      $(obj)/qat_rsaprivkey-asn1.h
-$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h
-
-clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h
-clean-files += qat_rsaprivkey-asn1.c qat_rsaprivkey-asn1.h
-
 obj-$(CONFIG_CRYPTO_DEV_QAT) += intel_qat.o
 intel_qat-objs := adf_cfg.o \
 	adf_isr.o \
@@ -20,8 +11,6 @@ intel_qat-objs := adf_cfg.o \
 	adf_hw_arbiter.o \
 	qat_crypto.o \
 	qat_algs.o \
-	qat_rsapubkey-asn1.o \
-	qat_rsaprivkey-asn1.o \
 	qat_asym_algs.o \
 	qat_uclo.o \
 	qat_hal.o
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index 5a07208ce778..e8822536530b 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -176,6 +176,7 @@ struct adf_hw_device_data {
 	void (*disable_iov)(struct adf_accel_dev *accel_dev);
 	void (*enable_ints)(struct adf_accel_dev *accel_dev);
 	int (*enable_vf2pf_comms)(struct adf_accel_dev *accel_dev);
+	void (*reset_device)(struct adf_accel_dev *accel_dev);
 	const char *fw_name;
 	const char *fw_mmp_name;
 	uint32_t fuses;
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index b40d9c8dad96..2839fccdd84b 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -82,18 +82,12 @@ struct adf_reset_dev_data {
 	struct work_struct reset_work;
 };
 
-void adf_dev_restore(struct adf_accel_dev *accel_dev)
+void adf_reset_sbr(struct adf_accel_dev *accel_dev)
 {
 	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
 	struct pci_dev *parent = pdev->bus->self;
 	uint16_t bridge_ctl = 0;
 
-	if (accel_dev->is_vf)
-		return;
-
-	dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
-		 accel_dev->accel_id);
-
 	if (!parent)
 		parent = pdev;
 
@@ -101,6 +95,8 @@ void adf_dev_restore(struct adf_accel_dev *accel_dev)
 		dev_info(&GET_DEV(accel_dev),
 			 "Transaction still in progress. Proceeding\n");
 
+	dev_info(&GET_DEV(accel_dev), "Secondary bus reset\n");
+
 	pci_read_config_word(parent, PCI_BRIDGE_CONTROL, &bridge_ctl);
 	bridge_ctl |= PCI_BRIDGE_CTL_BUS_RESET;
 	pci_write_config_word(parent, PCI_BRIDGE_CONTROL, bridge_ctl);
@@ -108,8 +104,40 @@ void adf_dev_restore(struct adf_accel_dev *accel_dev)
 	bridge_ctl &= ~PCI_BRIDGE_CTL_BUS_RESET;
 	pci_write_config_word(parent, PCI_BRIDGE_CONTROL, bridge_ctl);
 	msleep(100);
-	pci_restore_state(pdev);
-	pci_save_state(pdev);
+}
+EXPORT_SYMBOL_GPL(adf_reset_sbr);
+
+void adf_reset_flr(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+	u16 control = 0;
+	int pos = 0;
+
+	dev_info(&GET_DEV(accel_dev), "Function level reset\n");
+	pos = pci_pcie_cap(pdev);
+	if (!pos) {
+		dev_err(&GET_DEV(accel_dev), "Restart device failed\n");
+		return;
+	}
+	pci_read_config_word(pdev, pos + PCI_EXP_DEVCTL, &control);
+	control |= PCI_EXP_DEVCTL_BCR_FLR;
+	pci_write_config_word(pdev, pos + PCI_EXP_DEVCTL, control);
+	msleep(100);
+}
+EXPORT_SYMBOL_GPL(adf_reset_flr);
+
+void adf_dev_restore(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+
+	if (hw_device->reset_device) {
+		dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
+			 accel_dev->accel_id);
+		hw_device->reset_device(accel_dev);
+		pci_restore_state(pdev);
+		pci_save_state(pdev);
+	}
 }
 
 static void adf_device_reset_worker(struct work_struct *work)
@@ -243,7 +271,8 @@ EXPORT_SYMBOL_GPL(adf_disable_aer);
 
 int adf_init_aer(void)
 {
-	device_reset_wq = create_workqueue("qat_device_reset_wq");
+	device_reset_wq = alloc_workqueue("qat_device_reset_wq",
+					  WQ_MEM_RECLAIM, 0);
 	return !device_reset_wq ? -EFAULT : 0;
 }
 
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 75faa39bc8d0..980e07475012 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -141,6 +141,8 @@ int adf_ae_stop(struct adf_accel_dev *accel_dev);
 
 int adf_enable_aer(struct adf_accel_dev *accel_dev, struct pci_driver *adf);
 void adf_disable_aer(struct adf_accel_dev *accel_dev);
+void adf_reset_sbr(struct adf_accel_dev *accel_dev);
+void adf_reset_flr(struct adf_accel_dev *accel_dev);
 void adf_dev_restore(struct adf_accel_dev *accel_dev);
 int adf_init_aer(void);
 void adf_exit_aer(void);
diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c
index 4a526e2f1d7f..9320ae1d005b 100644
--- a/drivers/crypto/qat/qat_common/adf_sriov.c
+++ b/drivers/crypto/qat/qat_common/adf_sriov.c
@@ -292,7 +292,7 @@ EXPORT_SYMBOL_GPL(adf_sriov_configure);
 int __init adf_init_pf_wq(void)
 {
 	/* Workqueue for PF2VF responses */
-	pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq");
+	pf2vf_resp_wq = alloc_workqueue("qat_pf2vf_resp_wq", WQ_MEM_RECLAIM, 0);
 
 	return !pf2vf_resp_wq ? -ENOMEM : 0;
 }
diff --git a/drivers/crypto/qat/qat_common/adf_vf_isr.c b/drivers/crypto/qat/qat_common/adf_vf_isr.c
index aa689cabedb4..bf99e11a3403 100644
--- a/drivers/crypto/qat/qat_common/adf_vf_isr.c
+++ b/drivers/crypto/qat/qat_common/adf_vf_isr.c
@@ -321,7 +321,7 @@ EXPORT_SYMBOL_GPL(adf_vf_isr_resource_alloc);
 
 int __init adf_init_vf_wq(void)
 {
-	adf_vf_stop_wq = create_workqueue("adf_vf_stop_wq");
+	adf_vf_stop_wq = alloc_workqueue("adf_vf_stop_wq", WQ_MEM_RECLAIM, 0);
 
 	return !adf_vf_stop_wq ? -EFAULT : 0;
 }
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 1e8852a8a057..769148dbaeb3 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -947,13 +947,13 @@ static int qat_alg_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 	return 0;
 
 out_free_all:
-	memset(ctx->dec_cd, 0, sizeof(*ctx->enc_cd));
-	dma_free_coherent(dev, sizeof(*ctx->enc_cd),
+	memset(ctx->dec_cd, 0, sizeof(*ctx->dec_cd));
+	dma_free_coherent(dev, sizeof(*ctx->dec_cd),
 			  ctx->dec_cd, ctx->dec_cd_paddr);
 	ctx->dec_cd = NULL;
 out_free_enc:
-	memset(ctx->enc_cd, 0, sizeof(*ctx->dec_cd));
-	dma_free_coherent(dev, sizeof(*ctx->dec_cd),
+	memset(ctx->enc_cd, 0, sizeof(*ctx->enc_cd));
+	dma_free_coherent(dev, sizeof(*ctx->enc_cd),
 			  ctx->enc_cd, ctx->enc_cd_paddr);
 	ctx->enc_cd = NULL;
 	return -ENOMEM;
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index 05f49d4f94b2..0d35dca2e925 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -49,11 +49,12 @@
 #include <crypto/internal/rsa.h>
 #include <crypto/internal/akcipher.h>
 #include <crypto/akcipher.h>
+#include <crypto/kpp.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/dh.h>
 #include <linux/dma-mapping.h>
 #include <linux/fips.h>
 #include <crypto/scatterwalk.h>
-#include "qat_rsapubkey-asn1.h"
-#include "qat_rsaprivkey-asn1.h"
 #include "icp_qat_fw_pke.h"
 #include "adf_accel_devices.h"
 #include "adf_transport.h"
@@ -75,6 +76,14 @@ struct qat_rsa_input_params {
 			dma_addr_t d;
 			dma_addr_t n;
 		} dec;
+		struct {
+			dma_addr_t c;
+			dma_addr_t p;
+			dma_addr_t q;
+			dma_addr_t dp;
+			dma_addr_t dq;
+			dma_addr_t qinv;
+		} dec_crt;
 		u64 in_tab[8];
 	};
 } __packed __aligned(64);
@@ -95,71 +104,480 @@ struct qat_rsa_ctx {
 	char *n;
 	char *e;
 	char *d;
+	char *p;
+	char *q;
+	char *dp;
+	char *dq;
+	char *qinv;
 	dma_addr_t dma_n;
 	dma_addr_t dma_e;
 	dma_addr_t dma_d;
+	dma_addr_t dma_p;
+	dma_addr_t dma_q;
+	dma_addr_t dma_dp;
+	dma_addr_t dma_dq;
+	dma_addr_t dma_qinv;
 	unsigned int key_sz;
+	bool crt_mode;
+	struct qat_crypto_instance *inst;
+} __packed __aligned(64);
+
+struct qat_dh_input_params {
+	union {
+		struct {
+			dma_addr_t b;
+			dma_addr_t xa;
+			dma_addr_t p;
+		} in;
+		struct {
+			dma_addr_t xa;
+			dma_addr_t p;
+		} in_g2;
+		u64 in_tab[8];
+	};
+} __packed __aligned(64);
+
+struct qat_dh_output_params {
+	union {
+		dma_addr_t r;
+		u64 out_tab[8];
+	};
+} __packed __aligned(64);
+
+struct qat_dh_ctx {
+	char *g;
+	char *xa;
+	char *p;
+	dma_addr_t dma_g;
+	dma_addr_t dma_xa;
+	dma_addr_t dma_p;
+	unsigned int p_size;
+	bool g2;
 	struct qat_crypto_instance *inst;
 } __packed __aligned(64);
 
-struct qat_rsa_request {
-	struct qat_rsa_input_params in;
-	struct qat_rsa_output_params out;
+struct qat_asym_request {
+	union {
+		struct qat_rsa_input_params rsa;
+		struct qat_dh_input_params dh;
+	} in;
+	union {
+		struct qat_rsa_output_params rsa;
+		struct qat_dh_output_params dh;
+	} out;
 	dma_addr_t phy_in;
 	dma_addr_t phy_out;
 	char *src_align;
 	char *dst_align;
 	struct icp_qat_fw_pke_request req;
-	struct qat_rsa_ctx *ctx;
+	union {
+		struct qat_rsa_ctx *rsa;
+		struct qat_dh_ctx *dh;
+	} ctx;
+	union {
+		struct akcipher_request *rsa;
+		struct kpp_request *dh;
+	} areq;
 	int err;
+	void (*cb)(struct icp_qat_fw_pke_resp *resp);
 } __aligned(64);
 
-static void qat_rsa_cb(struct icp_qat_fw_pke_resp *resp)
+static void qat_dh_cb(struct icp_qat_fw_pke_resp *resp)
 {
-	struct akcipher_request *areq = (void *)(__force long)resp->opaque;
-	struct qat_rsa_request *req = PTR_ALIGN(akcipher_request_ctx(areq), 64);
-	struct device *dev = &GET_DEV(req->ctx->inst->accel_dev);
+	struct qat_asym_request *req = (void *)(__force long)resp->opaque;
+	struct kpp_request *areq = req->areq.dh;
+	struct device *dev = &GET_DEV(req->ctx.dh->inst->accel_dev);
 	int err = ICP_QAT_FW_PKE_RESP_PKE_STAT_GET(
 				resp->pke_resp_hdr.comn_resp_flags);
 
 	err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL;
 
-	if (req->src_align)
-		dma_free_coherent(dev, req->ctx->key_sz, req->src_align,
-				  req->in.enc.m);
-	else
-		dma_unmap_single(dev, req->in.enc.m, req->ctx->key_sz,
-				 DMA_TO_DEVICE);
+	if (areq->src) {
+		if (req->src_align)
+			dma_free_coherent(dev, req->ctx.dh->p_size,
+					  req->src_align, req->in.dh.in.b);
+		else
+			dma_unmap_single(dev, req->in.dh.in.b,
+					 req->ctx.dh->p_size, DMA_TO_DEVICE);
+	}
 
-	areq->dst_len = req->ctx->key_sz;
+	areq->dst_len = req->ctx.dh->p_size;
 	if (req->dst_align) {
-		char *ptr = req->dst_align;
+		scatterwalk_map_and_copy(req->dst_align, areq->dst, 0,
+					 areq->dst_len, 1);
 
-		while (!(*ptr) && areq->dst_len) {
-			areq->dst_len--;
-			ptr++;
-		}
+		dma_free_coherent(dev, req->ctx.dh->p_size, req->dst_align,
+				  req->out.dh.r);
+	} else {
+		dma_unmap_single(dev, req->out.dh.r, req->ctx.dh->p_size,
+				 DMA_FROM_DEVICE);
+	}
 
-		if (areq->dst_len != req->ctx->key_sz)
-			memmove(req->dst_align, ptr, areq->dst_len);
+	dma_unmap_single(dev, req->phy_in, sizeof(struct qat_dh_input_params),
+			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, req->phy_out,
+			 sizeof(struct qat_dh_output_params),
+			 DMA_TO_DEVICE);
 
-		scatterwalk_map_and_copy(req->dst_align, areq->dst, 0,
-					 areq->dst_len, 1);
+	kpp_request_complete(areq, err);
+}
+
+#define PKE_DH_1536 0x390c1a49
+#define PKE_DH_G2_1536 0x2e0b1a3e
+#define PKE_DH_2048 0x4d0c1a60
+#define PKE_DH_G2_2048 0x3e0b1a55
+#define PKE_DH_3072 0x510c1a77
+#define PKE_DH_G2_3072 0x3a0b1a6c
+#define PKE_DH_4096 0x690c1a8e
+#define PKE_DH_G2_4096 0x4a0b1a83
+
+static unsigned long qat_dh_fn_id(unsigned int len, bool g2)
+{
+	unsigned int bitslen = len << 3;
+
+	switch (bitslen) {
+	case 1536:
+		return g2 ? PKE_DH_G2_1536 : PKE_DH_1536;
+	case 2048:
+		return g2 ? PKE_DH_G2_2048 : PKE_DH_2048;
+	case 3072:
+		return g2 ? PKE_DH_G2_3072 : PKE_DH_3072;
+	case 4096:
+		return g2 ? PKE_DH_G2_4096 : PKE_DH_4096;
+	default:
+		return 0;
+	};
+}
+
+static inline struct qat_dh_ctx *qat_dh_get_params(struct crypto_kpp *tfm)
+{
+	return kpp_tfm_ctx(tfm);
+}
+
+static int qat_dh_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	struct qat_asym_request *qat_req =
+			PTR_ALIGN(kpp_request_ctx(req), 64);
+	struct icp_qat_fw_pke_request *msg = &qat_req->req;
+	int ret, ctr = 0;
+	int n_input_params = 0;
+
+	if (unlikely(!ctx->xa))
+		return -EINVAL;
+
+	if (req->dst_len < ctx->p_size) {
+		req->dst_len = ctx->p_size;
+		return -EOVERFLOW;
+	}
+	memset(msg, '\0', sizeof(*msg));
+	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
+					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
+
+	msg->pke_hdr.cd_pars.func_id = qat_dh_fn_id(ctx->p_size,
+						    !req->src && ctx->g2);
+	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
+		return -EINVAL;
+
+	qat_req->cb = qat_dh_cb;
+	qat_req->ctx.dh = ctx;
+	qat_req->areq.dh = req;
+	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
+	msg->pke_hdr.comn_req_flags =
+		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
+					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
 
-		dma_free_coherent(dev, req->ctx->key_sz, req->dst_align,
-				  req->out.enc.c);
+	/*
+	 * If no source is provided use g as base
+	 */
+	if (req->src) {
+		qat_req->in.dh.in.xa = ctx->dma_xa;
+		qat_req->in.dh.in.p = ctx->dma_p;
+		n_input_params = 3;
 	} else {
-		char *ptr = sg_virt(areq->dst);
+		if (ctx->g2) {
+			qat_req->in.dh.in_g2.xa = ctx->dma_xa;
+			qat_req->in.dh.in_g2.p = ctx->dma_p;
+			n_input_params = 2;
+		} else {
+			qat_req->in.dh.in.b = ctx->dma_g;
+			qat_req->in.dh.in.xa = ctx->dma_xa;
+			qat_req->in.dh.in.p = ctx->dma_p;
+			n_input_params = 3;
+		}
+	}
 
-		while (!(*ptr) && areq->dst_len) {
-			areq->dst_len--;
-			ptr++;
+	ret = -ENOMEM;
+	if (req->src) {
+		/*
+		 * src can be of any size in valid range, but HW expects it to
+		 * be the same as modulo p so in case it is different we need
+		 * to allocate a new buf and copy src data.
+		 * In other case we just need to map the user provided buffer.
+		 * Also need to make sure that it is in contiguous buffer.
+		 */
+		if (sg_is_last(req->src) && req->src_len == ctx->p_size) {
+			qat_req->src_align = NULL;
+			qat_req->in.dh.in.b = dma_map_single(dev,
+							     sg_virt(req->src),
+							     req->src_len,
+							     DMA_TO_DEVICE);
+			if (unlikely(dma_mapping_error(dev,
+						       qat_req->in.dh.in.b)))
+				return ret;
+
+		} else {
+			int shift = ctx->p_size - req->src_len;
+
+			qat_req->src_align = dma_zalloc_coherent(dev,
+								 ctx->p_size,
+								 &qat_req->in.dh.in.b,
+								 GFP_KERNEL);
+			if (unlikely(!qat_req->src_align))
+				return ret;
+
+			scatterwalk_map_and_copy(qat_req->src_align + shift,
+						 req->src, 0, req->src_len, 0);
 		}
+	}
+	/*
+	 * dst can be of any size in valid range, but HW expects it to be the
+	 * same as modulo m so in case it is different we need to allocate a
+	 * new buf and copy src data.
+	 * In other case we just need to map the user provided buffer.
+	 * Also need to make sure that it is in contiguous buffer.
+	 */
+	if (sg_is_last(req->dst) && req->dst_len == ctx->p_size) {
+		qat_req->dst_align = NULL;
+		qat_req->out.dh.r = dma_map_single(dev, sg_virt(req->dst),
+						   req->dst_len,
+						   DMA_FROM_DEVICE);
 
-		if (sg_virt(areq->dst) != ptr && areq->dst_len)
-			memmove(sg_virt(areq->dst), ptr, areq->dst_len);
+		if (unlikely(dma_mapping_error(dev, qat_req->out.dh.r)))
+			goto unmap_src;
+
+	} else {
+		qat_req->dst_align = dma_zalloc_coherent(dev, ctx->p_size,
+							 &qat_req->out.dh.r,
+							 GFP_KERNEL);
+		if (unlikely(!qat_req->dst_align))
+			goto unmap_src;
+	}
 
-		dma_unmap_single(dev, req->out.enc.c, req->ctx->key_sz,
+	qat_req->in.dh.in_tab[n_input_params] = 0;
+	qat_req->out.dh.out_tab[1] = 0;
+	/* Mapping in.in.b or in.in_g2.xa is the same */
+	qat_req->phy_in = dma_map_single(dev, &qat_req->in.dh.in.b,
+					 sizeof(struct qat_dh_input_params),
+					 DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->phy_in)))
+		goto unmap_dst;
+
+	qat_req->phy_out = dma_map_single(dev, &qat_req->out.dh.r,
+					  sizeof(struct qat_dh_output_params),
+					  DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
+		goto unmap_in_params;
+
+	msg->pke_mid.src_data_addr = qat_req->phy_in;
+	msg->pke_mid.dest_data_addr = qat_req->phy_out;
+	msg->pke_mid.opaque = (uint64_t)(__force long)qat_req;
+	msg->input_param_count = n_input_params;
+	msg->output_param_count = 1;
+
+	do {
+		ret = adf_send_message(ctx->inst->pke_tx, (uint32_t *)msg);
+	} while (ret == -EBUSY && ctr++ < 100);
+
+	if (!ret)
+		return -EINPROGRESS;
+
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_dh_output_params),
+				 DMA_TO_DEVICE);
+unmap_in_params:
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_dh_input_params),
+				 DMA_TO_DEVICE);
+unmap_dst:
+	if (qat_req->dst_align)
+		dma_free_coherent(dev, ctx->p_size, qat_req->dst_align,
+				  qat_req->out.dh.r);
+	else
+		if (!dma_mapping_error(dev, qat_req->out.dh.r))
+			dma_unmap_single(dev, qat_req->out.dh.r, ctx->p_size,
+					 DMA_FROM_DEVICE);
+unmap_src:
+	if (req->src) {
+		if (qat_req->src_align)
+			dma_free_coherent(dev, ctx->p_size, qat_req->src_align,
+					  qat_req->in.dh.in.b);
+		else
+			if (!dma_mapping_error(dev, qat_req->in.dh.in.b))
+				dma_unmap_single(dev, qat_req->in.dh.in.b,
+						 ctx->p_size,
+						 DMA_TO_DEVICE);
+	}
+	return ret;
+}
+
+static int qat_dh_check_params_length(unsigned int p_len)
+{
+	switch (p_len) {
+	case 1536:
+	case 2048:
+	case 3072:
+	case 4096:
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int qat_dh_set_params(struct qat_dh_ctx *ctx, struct dh *params)
+{
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+
+	if (unlikely(!params->p || !params->g))
+		return -EINVAL;
+
+	if (qat_dh_check_params_length(params->p_size << 3))
+		return -EINVAL;
+
+	ctx->p_size = params->p_size;
+	ctx->p = dma_zalloc_coherent(dev, ctx->p_size, &ctx->dma_p, GFP_KERNEL);
+	if (!ctx->p)
+		return -ENOMEM;
+	memcpy(ctx->p, params->p, ctx->p_size);
+
+	/* If g equals 2 don't copy it */
+	if (params->g_size == 1 && *(char *)params->g == 0x02) {
+		ctx->g2 = true;
+		return 0;
+	}
+
+	ctx->g = dma_zalloc_coherent(dev, ctx->p_size, &ctx->dma_g, GFP_KERNEL);
+	if (!ctx->g) {
+		dma_free_coherent(dev, ctx->p_size, ctx->p, ctx->dma_p);
+		ctx->p = NULL;
+		return -ENOMEM;
+	}
+	memcpy(ctx->g + (ctx->p_size - params->g_size), params->g,
+	       params->g_size);
+
+	return 0;
+}
+
+static void qat_dh_clear_ctx(struct device *dev, struct qat_dh_ctx *ctx)
+{
+	if (ctx->g) {
+		dma_free_coherent(dev, ctx->p_size, ctx->g, ctx->dma_g);
+		ctx->g = NULL;
+	}
+	if (ctx->xa) {
+		dma_free_coherent(dev, ctx->p_size, ctx->xa, ctx->dma_xa);
+		ctx->xa = NULL;
+	}
+	if (ctx->p) {
+		dma_free_coherent(dev, ctx->p_size, ctx->p, ctx->dma_p);
+		ctx->p = NULL;
+	}
+	ctx->p_size = 0;
+	ctx->g2 = false;
+}
+
+static int qat_dh_set_secret(struct crypto_kpp *tfm, void *buf,
+			     unsigned int len)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+	struct dh params;
+	int ret;
+
+	if (crypto_dh_decode_key(buf, len, &params) < 0)
+		return -EINVAL;
+
+	/* Free old secret if any */
+	qat_dh_clear_ctx(dev, ctx);
+
+	ret = qat_dh_set_params(ctx, &params);
+	if (ret < 0)
+		return ret;
+
+	ctx->xa = dma_zalloc_coherent(dev, ctx->p_size, &ctx->dma_xa,
+				      GFP_KERNEL);
+	if (!ctx->xa) {
+		qat_dh_clear_ctx(dev, ctx);
+		return -ENOMEM;
+	}
+	memcpy(ctx->xa + (ctx->p_size - params.key_size), params.key,
+	       params.key_size);
+
+	return 0;
+}
+
+static int qat_dh_max_size(struct crypto_kpp *tfm)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+
+	return ctx->p ? ctx->p_size : -EINVAL;
+}
+
+static int qat_dh_init_tfm(struct crypto_kpp *tfm)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst =
+			qat_crypto_get_instance_node(get_current_node());
+
+	if (!inst)
+		return -EINVAL;
+
+	ctx->p_size = 0;
+	ctx->g2 = false;
+	ctx->inst = inst;
+	return 0;
+}
+
+static void qat_dh_exit_tfm(struct crypto_kpp *tfm)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+
+	qat_dh_clear_ctx(dev, ctx);
+	qat_crypto_put_instance(ctx->inst);
+}
+
+static void qat_rsa_cb(struct icp_qat_fw_pke_resp *resp)
+{
+	struct qat_asym_request *req = (void *)(__force long)resp->opaque;
+	struct akcipher_request *areq = req->areq.rsa;
+	struct device *dev = &GET_DEV(req->ctx.rsa->inst->accel_dev);
+	int err = ICP_QAT_FW_PKE_RESP_PKE_STAT_GET(
+				resp->pke_resp_hdr.comn_resp_flags);
+
+	err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL;
+
+	if (req->src_align)
+		dma_free_coherent(dev, req->ctx.rsa->key_sz, req->src_align,
+				  req->in.rsa.enc.m);
+	else
+		dma_unmap_single(dev, req->in.rsa.enc.m, req->ctx.rsa->key_sz,
+				 DMA_TO_DEVICE);
+
+	areq->dst_len = req->ctx.rsa->key_sz;
+	if (req->dst_align) {
+		scatterwalk_map_and_copy(req->dst_align, areq->dst, 0,
+					 areq->dst_len, 1);
+
+		dma_free_coherent(dev, req->ctx.rsa->key_sz, req->dst_align,
+				  req->out.rsa.enc.c);
+	} else {
+		dma_unmap_single(dev, req->out.rsa.enc.c, req->ctx.rsa->key_sz,
 				 DMA_FROM_DEVICE);
 	}
 
@@ -175,8 +593,9 @@ static void qat_rsa_cb(struct icp_qat_fw_pke_resp *resp)
 void qat_alg_asym_callback(void *_resp)
 {
 	struct icp_qat_fw_pke_resp *resp = _resp;
+	struct qat_asym_request *areq = (void *)(__force long)resp->opaque;
 
-	qat_rsa_cb(resp);
+	areq->cb(resp);
 }
 
 #define PKE_RSA_EP_512 0x1c161b21
@@ -237,13 +656,42 @@ static unsigned long qat_rsa_dec_fn_id(unsigned int len)
 	};
 }
 
+#define PKE_RSA_DP2_512 0x1c131b57
+#define PKE_RSA_DP2_1024 0x26131c2d
+#define PKE_RSA_DP2_1536 0x45111d12
+#define PKE_RSA_DP2_2048 0x59121dfa
+#define PKE_RSA_DP2_3072 0x81121ed9
+#define PKE_RSA_DP2_4096 0xb1111fb2
+
+static unsigned long qat_rsa_dec_fn_id_crt(unsigned int len)
+{
+	unsigned int bitslen = len << 3;
+
+	switch (bitslen) {
+	case 512:
+		return PKE_RSA_DP2_512;
+	case 1024:
+		return PKE_RSA_DP2_1024;
+	case 1536:
+		return PKE_RSA_DP2_1536;
+	case 2048:
+		return PKE_RSA_DP2_2048;
+	case 3072:
+		return PKE_RSA_DP2_3072;
+	case 4096:
+		return PKE_RSA_DP2_4096;
+	default:
+		return 0;
+	};
+}
+
 static int qat_rsa_enc(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
-	struct qat_rsa_request *qat_req =
+	struct qat_asym_request *qat_req =
 			PTR_ALIGN(akcipher_request_ctx(req), 64);
 	struct icp_qat_fw_pke_request *msg = &qat_req->req;
 	int ret, ctr = 0;
@@ -262,14 +710,16 @@ static int qat_rsa_enc(struct akcipher_request *req)
 	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
 		return -EINVAL;
 
-	qat_req->ctx = ctx;
+	qat_req->cb = qat_rsa_cb;
+	qat_req->ctx.rsa = ctx;
+	qat_req->areq.rsa = req;
 	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
 	msg->pke_hdr.comn_req_flags =
 		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
 					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
 
-	qat_req->in.enc.e = ctx->dma_e;
-	qat_req->in.enc.n = ctx->dma_n;
+	qat_req->in.rsa.enc.e = ctx->dma_e;
+	qat_req->in.rsa.enc.n = ctx->dma_n;
 	ret = -ENOMEM;
 
 	/*
@@ -281,16 +731,16 @@ static int qat_rsa_enc(struct akcipher_request *req)
 	 */
 	if (sg_is_last(req->src) && req->src_len == ctx->key_sz) {
 		qat_req->src_align = NULL;
-		qat_req->in.enc.m = dma_map_single(dev, sg_virt(req->src),
+		qat_req->in.rsa.enc.m = dma_map_single(dev, sg_virt(req->src),
 						   req->src_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(dev, qat_req->in.enc.m)))
+		if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.enc.m)))
 			return ret;
 
 	} else {
 		int shift = ctx->key_sz - req->src_len;
 
 		qat_req->src_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->in.enc.m,
+							 &qat_req->in.rsa.enc.m,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->src_align))
 			return ret;
@@ -300,30 +750,30 @@ static int qat_rsa_enc(struct akcipher_request *req)
 	}
 	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
 		qat_req->dst_align = NULL;
-		qat_req->out.enc.c = dma_map_single(dev, sg_virt(req->dst),
-						    req->dst_len,
-						    DMA_FROM_DEVICE);
+		qat_req->out.rsa.enc.c = dma_map_single(dev, sg_virt(req->dst),
+							req->dst_len,
+							DMA_FROM_DEVICE);
 
-		if (unlikely(dma_mapping_error(dev, qat_req->out.enc.c)))
+		if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.enc.c)))
 			goto unmap_src;
 
 	} else {
 		qat_req->dst_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->out.enc.c,
+							 &qat_req->out.rsa.enc.c,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->dst_align))
 			goto unmap_src;
 
 	}
-	qat_req->in.in_tab[3] = 0;
-	qat_req->out.out_tab[1] = 0;
-	qat_req->phy_in = dma_map_single(dev, &qat_req->in.enc.m,
+	qat_req->in.rsa.in_tab[3] = 0;
+	qat_req->out.rsa.out_tab[1] = 0;
+	qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa.enc.m,
 					 sizeof(struct qat_rsa_input_params),
 					 DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_in)))
 		goto unmap_dst;
 
-	qat_req->phy_out = dma_map_single(dev, &qat_req->out.enc.c,
+	qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.enc.c,
 					  sizeof(struct qat_rsa_output_params),
 					  DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
@@ -331,7 +781,7 @@ static int qat_rsa_enc(struct akcipher_request *req)
 
 	msg->pke_mid.src_data_addr = qat_req->phy_in;
 	msg->pke_mid.dest_data_addr = qat_req->phy_out;
-	msg->pke_mid.opaque = (uint64_t)(__force long)req;
+	msg->pke_mid.opaque = (uint64_t)(__force long)qat_req;
 	msg->input_param_count = 3;
 	msg->output_param_count = 1;
 	do {
@@ -353,19 +803,19 @@ unmap_in_params:
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
-				  qat_req->out.enc.c);
+				  qat_req->out.rsa.enc.c);
 	else
-		if (!dma_mapping_error(dev, qat_req->out.enc.c))
-			dma_unmap_single(dev, qat_req->out.enc.c, ctx->key_sz,
-					 DMA_FROM_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->out.rsa.enc.c))
+			dma_unmap_single(dev, qat_req->out.rsa.enc.c,
+					 ctx->key_sz, DMA_FROM_DEVICE);
 unmap_src:
 	if (qat_req->src_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.enc.m);
+				  qat_req->in.rsa.enc.m);
 	else
-		if (!dma_mapping_error(dev, qat_req->in.enc.m))
-			dma_unmap_single(dev, qat_req->in.enc.m, ctx->key_sz,
-					 DMA_TO_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->in.rsa.enc.m))
+			dma_unmap_single(dev, qat_req->in.rsa.enc.m,
+					 ctx->key_sz, DMA_TO_DEVICE);
 	return ret;
 }
 
@@ -375,7 +825,7 @@ static int qat_rsa_dec(struct akcipher_request *req)
 	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
-	struct qat_rsa_request *qat_req =
+	struct qat_asym_request *qat_req =
 			PTR_ALIGN(akcipher_request_ctx(req), 64);
 	struct icp_qat_fw_pke_request *msg = &qat_req->req;
 	int ret, ctr = 0;
@@ -390,18 +840,30 @@ static int qat_rsa_dec(struct akcipher_request *req)
 	memset(msg, '\0', sizeof(*msg));
 	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
 					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
-	msg->pke_hdr.cd_pars.func_id = qat_rsa_dec_fn_id(ctx->key_sz);
+	msg->pke_hdr.cd_pars.func_id = ctx->crt_mode ?
+		qat_rsa_dec_fn_id_crt(ctx->key_sz) :
+		qat_rsa_dec_fn_id(ctx->key_sz);
 	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
 		return -EINVAL;
 
-	qat_req->ctx = ctx;
+	qat_req->cb = qat_rsa_cb;
+	qat_req->ctx.rsa = ctx;
+	qat_req->areq.rsa = req;
 	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
 	msg->pke_hdr.comn_req_flags =
 		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
 					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
 
-	qat_req->in.dec.d = ctx->dma_d;
-	qat_req->in.dec.n = ctx->dma_n;
+	if (ctx->crt_mode) {
+		qat_req->in.rsa.dec_crt.p = ctx->dma_p;
+		qat_req->in.rsa.dec_crt.q = ctx->dma_q;
+		qat_req->in.rsa.dec_crt.dp = ctx->dma_dp;
+		qat_req->in.rsa.dec_crt.dq = ctx->dma_dq;
+		qat_req->in.rsa.dec_crt.qinv = ctx->dma_qinv;
+	} else {
+		qat_req->in.rsa.dec.d = ctx->dma_d;
+		qat_req->in.rsa.dec.n = ctx->dma_n;
+	}
 	ret = -ENOMEM;
 
 	/*
@@ -413,16 +875,16 @@ static int qat_rsa_dec(struct akcipher_request *req)
 	 */
 	if (sg_is_last(req->src) && req->src_len == ctx->key_sz) {
 		qat_req->src_align = NULL;
-		qat_req->in.dec.c = dma_map_single(dev, sg_virt(req->src),
+		qat_req->in.rsa.dec.c = dma_map_single(dev, sg_virt(req->src),
 						   req->dst_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(dev, qat_req->in.dec.c)))
+		if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.dec.c)))
 			return ret;
 
 	} else {
 		int shift = ctx->key_sz - req->src_len;
 
 		qat_req->src_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->in.dec.c,
+							 &qat_req->in.rsa.dec.c,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->src_align))
 			return ret;
@@ -432,31 +894,34 @@ static int qat_rsa_dec(struct akcipher_request *req)
 	}
 	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
 		qat_req->dst_align = NULL;
-		qat_req->out.dec.m = dma_map_single(dev, sg_virt(req->dst),
+		qat_req->out.rsa.dec.m = dma_map_single(dev, sg_virt(req->dst),
 						    req->dst_len,
 						    DMA_FROM_DEVICE);
 
-		if (unlikely(dma_mapping_error(dev, qat_req->out.dec.m)))
+		if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.dec.m)))
 			goto unmap_src;
 
 	} else {
 		qat_req->dst_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->out.dec.m,
+							 &qat_req->out.rsa.dec.m,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->dst_align))
 			goto unmap_src;
 
 	}
 
-	qat_req->in.in_tab[3] = 0;
-	qat_req->out.out_tab[1] = 0;
-	qat_req->phy_in = dma_map_single(dev, &qat_req->in.dec.c,
+	if (ctx->crt_mode)
+		qat_req->in.rsa.in_tab[6] = 0;
+	else
+		qat_req->in.rsa.in_tab[3] = 0;
+	qat_req->out.rsa.out_tab[1] = 0;
+	qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa.dec.c,
 					 sizeof(struct qat_rsa_input_params),
 					 DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_in)))
 		goto unmap_dst;
 
-	qat_req->phy_out = dma_map_single(dev, &qat_req->out.dec.m,
+	qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.dec.m,
 					  sizeof(struct qat_rsa_output_params),
 					  DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
@@ -464,8 +929,12 @@ static int qat_rsa_dec(struct akcipher_request *req)
 
 	msg->pke_mid.src_data_addr = qat_req->phy_in;
 	msg->pke_mid.dest_data_addr = qat_req->phy_out;
-	msg->pke_mid.opaque = (uint64_t)(__force long)req;
-	msg->input_param_count = 3;
+	msg->pke_mid.opaque = (uint64_t)(__force long)qat_req;
+	if (ctx->crt_mode)
+		msg->input_param_count = 6;
+	else
+		msg->input_param_count = 3;
+
 	msg->output_param_count = 1;
 	do {
 		ret = adf_send_message(ctx->inst->pke_tx, (uint32_t *)msg);
@@ -486,26 +955,24 @@ unmap_in_params:
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
-				  qat_req->out.dec.m);
+				  qat_req->out.rsa.dec.m);
 	else
-		if (!dma_mapping_error(dev, qat_req->out.dec.m))
-			dma_unmap_single(dev, qat_req->out.dec.m, ctx->key_sz,
-					 DMA_FROM_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->out.rsa.dec.m))
+			dma_unmap_single(dev, qat_req->out.rsa.dec.m,
+					 ctx->key_sz, DMA_FROM_DEVICE);
 unmap_src:
 	if (qat_req->src_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.dec.c);
+				  qat_req->in.rsa.dec.c);
 	else
-		if (!dma_mapping_error(dev, qat_req->in.dec.c))
-			dma_unmap_single(dev, qat_req->in.dec.c, ctx->key_sz,
-					 DMA_TO_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->in.rsa.dec.c))
+			dma_unmap_single(dev, qat_req->in.rsa.dec.c,
+					 ctx->key_sz, DMA_TO_DEVICE);
 	return ret;
 }
 
-int qat_rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
-		  const void *value, size_t vlen)
+int qat_rsa_set_n(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
 {
-	struct qat_rsa_ctx *ctx = context;
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
 	const char *ptr = value;
@@ -518,11 +985,6 @@ int qat_rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
 
 	ctx->key_sz = vlen;
 	ret = -EINVAL;
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (ctx->key_sz != 256 && ctx->key_sz != 384)) {
-		pr_err("QAT: RSA: key size not allowed in FIPS mode\n");
-		goto err;
-	}
 	/* invalid key size provided */
 	if (!qat_rsa_enc_fn_id(ctx->key_sz))
 		goto err;
@@ -540,10 +1002,8 @@ err:
 	return ret;
 }
 
-int qat_rsa_get_e(void *context, size_t hdrlen, unsigned char tag,
-		  const void *value, size_t vlen)
+int qat_rsa_set_e(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
 {
-	struct qat_rsa_ctx *ctx = context;
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
 	const char *ptr = value;
@@ -559,18 +1019,15 @@ int qat_rsa_get_e(void *context, size_t hdrlen, unsigned char tag,
 	}
 
 	ctx->e = dma_zalloc_coherent(dev, ctx->key_sz, &ctx->dma_e, GFP_KERNEL);
-	if (!ctx->e) {
-		ctx->e = NULL;
+	if (!ctx->e)
 		return -ENOMEM;
-	}
+
 	memcpy(ctx->e + (ctx->key_sz - vlen), ptr, vlen);
 	return 0;
 }
 
-int qat_rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
-		  const void *value, size_t vlen)
+int qat_rsa_set_d(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
 {
-	struct qat_rsa_ctx *ctx = context;
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
 	const char *ptr = value;
@@ -585,12 +1042,6 @@ int qat_rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
 	if (!ctx->key_sz || !vlen || vlen > ctx->key_sz)
 		goto err;
 
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (vlen != 256 && vlen != 384)) {
-		pr_err("QAT: RSA: key size not allowed in FIPS mode\n");
-		goto err;
-	}
-
 	ret = -ENOMEM;
 	ctx->d = dma_zalloc_coherent(dev, ctx->key_sz, &ctx->dma_d, GFP_KERNEL);
 	if (!ctx->d)
@@ -603,12 +1054,106 @@ err:
 	return ret;
 }
 
-static int qat_rsa_setkey(struct crypto_akcipher *tfm, const void *key,
-			  unsigned int keylen, bool private)
+static void qat_rsa_drop_leading_zeros(const char **ptr, unsigned int *len)
 {
-	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
-	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
-	int ret;
+	while (!**ptr && *len) {
+		(*ptr)++;
+		(*len)--;
+	}
+}
+
+static void qat_rsa_setkey_crt(struct qat_rsa_ctx *ctx, struct rsa_key *rsa_key)
+{
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	const char *ptr;
+	unsigned int len;
+	unsigned int half_key_sz = ctx->key_sz / 2;
+
+	/* p */
+	ptr = rsa_key->p;
+	len = rsa_key->p_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto err;
+	ctx->p = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_p, GFP_KERNEL);
+	if (!ctx->p)
+		goto err;
+	memcpy(ctx->p + (half_key_sz - len), ptr, len);
+
+	/* q */
+	ptr = rsa_key->q;
+	len = rsa_key->q_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_p;
+	ctx->q = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_q, GFP_KERNEL);
+	if (!ctx->q)
+		goto free_p;
+	memcpy(ctx->q + (half_key_sz - len), ptr, len);
+
+	/* dp */
+	ptr = rsa_key->dp;
+	len = rsa_key->dp_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_q;
+	ctx->dp = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_dp,
+				      GFP_KERNEL);
+	if (!ctx->dp)
+		goto free_q;
+	memcpy(ctx->dp + (half_key_sz - len), ptr, len);
+
+	/* dq */
+	ptr = rsa_key->dq;
+	len = rsa_key->dq_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_dp;
+	ctx->dq = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_dq,
+				      GFP_KERNEL);
+	if (!ctx->dq)
+		goto free_dp;
+	memcpy(ctx->dq + (half_key_sz - len), ptr, len);
+
+	/* qinv */
+	ptr = rsa_key->qinv;
+	len = rsa_key->qinv_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_dq;
+	ctx->qinv = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_qinv,
+					GFP_KERNEL);
+	if (!ctx->qinv)
+		goto free_dq;
+	memcpy(ctx->qinv + (half_key_sz - len), ptr, len);
+
+	ctx->crt_mode = true;
+	return;
+
+free_dq:
+	memset(ctx->dq, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->dq, ctx->dma_dq);
+	ctx->dq = NULL;
+free_dp:
+	memset(ctx->dp, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->dp, ctx->dma_dp);
+	ctx->dp = NULL;
+free_q:
+	memset(ctx->q, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->q, ctx->dma_q);
+	ctx->q = NULL;
+free_p:
+	memset(ctx->p, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->p, ctx->dma_p);
+	ctx->p = NULL;
+err:
+	ctx->crt_mode = false;
+}
+
+static void qat_rsa_clear_ctx(struct device *dev, struct qat_rsa_ctx *ctx)
+{
+	unsigned int half_key_sz = ctx->key_sz / 2;
 
 	/* Free the old key if any */
 	if (ctx->n)
@@ -619,19 +1164,68 @@ static int qat_rsa_setkey(struct crypto_akcipher *tfm, const void *key,
 		memset(ctx->d, '\0', ctx->key_sz);
 		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
 	}
+	if (ctx->p) {
+		memset(ctx->p, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->p, ctx->dma_p);
+	}
+	if (ctx->q) {
+		memset(ctx->q, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->q, ctx->dma_q);
+	}
+	if (ctx->dp) {
+		memset(ctx->dp, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->dp, ctx->dma_dp);
+	}
+	if (ctx->dq) {
+		memset(ctx->dq, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->dq, ctx->dma_dq);
+	}
+	if (ctx->qinv) {
+		memset(ctx->qinv, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->qinv, ctx->dma_qinv);
+	}
 
 	ctx->n = NULL;
 	ctx->e = NULL;
 	ctx->d = NULL;
+	ctx->p = NULL;
+	ctx->q = NULL;
+	ctx->dp = NULL;
+	ctx->dq = NULL;
+	ctx->qinv = NULL;
+	ctx->crt_mode = false;
+	ctx->key_sz = 0;
+}
+
+static int qat_rsa_setkey(struct crypto_akcipher *tfm, const void *key,
+			  unsigned int keylen, bool private)
+{
+	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+	struct rsa_key rsa_key;
+	int ret;
+
+	qat_rsa_clear_ctx(dev, ctx);
 
 	if (private)
-		ret = asn1_ber_decoder(&qat_rsaprivkey_decoder, ctx, key,
-				       keylen);
+		ret = rsa_parse_priv_key(&rsa_key, key, keylen);
 	else
-		ret = asn1_ber_decoder(&qat_rsapubkey_decoder, ctx, key,
-				       keylen);
+		ret = rsa_parse_pub_key(&rsa_key, key, keylen);
+	if (ret < 0)
+		goto free;
+
+	ret = qat_rsa_set_n(ctx, rsa_key.n, rsa_key.n_sz);
 	if (ret < 0)
 		goto free;
+	ret = qat_rsa_set_e(ctx, rsa_key.e, rsa_key.e_sz);
+	if (ret < 0)
+		goto free;
+	if (private) {
+		ret = qat_rsa_set_d(ctx, rsa_key.d, rsa_key.d_sz);
+		if (ret < 0)
+			goto free;
+		qat_rsa_setkey_crt(ctx, &rsa_key);
+	}
 
 	if (!ctx->n || !ctx->e) {
 		/* invalid key provided */
@@ -646,20 +1240,7 @@ static int qat_rsa_setkey(struct crypto_akcipher *tfm, const void *key,
 
 	return 0;
 free:
-	if (ctx->d) {
-		memset(ctx->d, '\0', ctx->key_sz);
-		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
-		ctx->d = NULL;
-	}
-	if (ctx->e) {
-		dma_free_coherent(dev, ctx->key_sz, ctx->e, ctx->dma_e);
-		ctx->e = NULL;
-	}
-	if (ctx->n) {
-		dma_free_coherent(dev, ctx->key_sz, ctx->n, ctx->dma_n);
-		ctx->n = NULL;
-		ctx->key_sz = 0;
-	}
+	qat_rsa_clear_ctx(dev, ctx);
 	return ret;
 }
 
@@ -725,7 +1306,7 @@ static struct akcipher_alg rsa = {
 	.max_size = qat_rsa_max_size,
 	.init = qat_rsa_init_tfm,
 	.exit = qat_rsa_exit_tfm,
-	.reqsize = sizeof(struct qat_rsa_request) + 64,
+	.reqsize = sizeof(struct qat_asym_request) + 64,
 	.base = {
 		.cra_name = "rsa",
 		.cra_driver_name = "qat-rsa",
@@ -735,6 +1316,23 @@ static struct akcipher_alg rsa = {
 	},
 };
 
+static struct kpp_alg dh = {
+	.set_secret = qat_dh_set_secret,
+	.generate_public_key = qat_dh_compute_value,
+	.compute_shared_secret = qat_dh_compute_value,
+	.max_size = qat_dh_max_size,
+	.init = qat_dh_init_tfm,
+	.exit = qat_dh_exit_tfm,
+	.reqsize = sizeof(struct qat_asym_request) + 64,
+	.base = {
+		.cra_name = "dh",
+		.cra_driver_name = "qat-dh",
+		.cra_priority = 1000,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct qat_dh_ctx),
+	},
+};
+
 int qat_asym_algs_register(void)
 {
 	int ret = 0;
@@ -743,7 +1341,11 @@ int qat_asym_algs_register(void)
 	if (++active_devs == 1) {
 		rsa.base.cra_flags = 0;
 		ret = crypto_register_akcipher(&rsa);
+		if (ret)
+			goto unlock;
+		ret = crypto_register_kpp(&dh);
 	}
+unlock:
 	mutex_unlock(&algs_lock);
 	return ret;
 }
@@ -751,7 +1353,9 @@ int qat_asym_algs_register(void)
 void qat_asym_algs_unregister(void)
 {
 	mutex_lock(&algs_lock);
-	if (--active_devs == 0)
+	if (--active_devs == 0) {
 		crypto_unregister_akcipher(&rsa);
+		crypto_unregister_kpp(&dh);
+	}
 	mutex_unlock(&algs_lock);
 }
diff --git a/drivers/crypto/qat/qat_common/qat_rsaprivkey.asn1 b/drivers/crypto/qat/qat_common/qat_rsaprivkey.asn1
deleted file mode 100644
index f0066adb79b8..000000000000
--- a/drivers/crypto/qat/qat_common/qat_rsaprivkey.asn1
+++ /dev/null
@@ -1,11 +0,0 @@
-RsaPrivKey ::= SEQUENCE {
-	version		INTEGER,
-	n		INTEGER ({ qat_rsa_get_n }),
-	e		INTEGER ({ qat_rsa_get_e }),
-	d		INTEGER ({ qat_rsa_get_d }),
-	prime1		INTEGER,
-	prime2		INTEGER,
-	exponent1	INTEGER,
-	exponent2	INTEGER,
-	coefficient	INTEGER
-}
diff --git a/drivers/crypto/qat/qat_common/qat_rsapubkey.asn1 b/drivers/crypto/qat/qat_common/qat_rsapubkey.asn1
deleted file mode 100644
index bd667b31a21a..000000000000
--- a/drivers/crypto/qat/qat_common/qat_rsapubkey.asn1
+++ /dev/null
@@ -1,4 +0,0 @@
-RsaPubKey ::= SEQUENCE {
-	n INTEGER ({ qat_rsa_get_n }),
-	e INTEGER ({ qat_rsa_get_e })
-}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
index 6e1d5e185526..1dfcab317bed 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
@@ -252,6 +252,7 @@ void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data)
 	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
 	hw_data->enable_ints = adf_enable_ints;
 	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->reset_device = adf_reset_sbr;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
 }
 
diff --git a/drivers/crypto/qce/ablkcipher.c b/drivers/crypto/qce/ablkcipher.c
index dbcbbe242bd6..b04b42f48366 100644
--- a/drivers/crypto/qce/ablkcipher.c
+++ b/drivers/crypto/qce/ablkcipher.c
@@ -15,8 +15,8 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <crypto/aes.h>
-#include <crypto/algapi.h>
 #include <crypto/des.h>
+#include <crypto/internal/skcipher.h>
 
 #include "cipher.h"
 
@@ -189,7 +189,7 @@ static int qce_ablkcipher_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
 	memcpy(ctx->enc_key, key, keylen);
 	return 0;
 fallback:
-	ret = crypto_ablkcipher_setkey(ctx->fallback, key, keylen);
+	ret = crypto_skcipher_setkey(ctx->fallback, key, keylen);
 	if (!ret)
 		ctx->enc_keylen = keylen;
 	return ret;
@@ -212,10 +212,16 @@ static int qce_ablkcipher_crypt(struct ablkcipher_request *req, int encrypt)
 
 	if (IS_AES(rctx->flags) && ctx->enc_keylen != AES_KEYSIZE_128 &&
 	    ctx->enc_keylen != AES_KEYSIZE_256) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		ret = encrypt ? crypto_ablkcipher_encrypt(req) :
-				crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		ret = encrypt ? crypto_skcipher_encrypt(subreq) :
+				crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return ret;
 	}
 
@@ -239,10 +245,9 @@ static int qce_ablkcipher_init(struct crypto_tfm *tfm)
 	memset(ctx, 0, sizeof(*ctx));
 	tfm->crt_ablkcipher.reqsize = sizeof(struct qce_cipher_reqctx);
 
-	ctx->fallback = crypto_alloc_ablkcipher(crypto_tfm_alg_name(tfm),
-						CRYPTO_ALG_TYPE_ABLKCIPHER,
-						CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_NEED_FALLBACK);
+	ctx->fallback = crypto_alloc_skcipher(crypto_tfm_alg_name(tfm), 0,
+					      CRYPTO_ALG_ASYNC |
+					      CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(ctx->fallback))
 		return PTR_ERR(ctx->fallback);
 
@@ -253,7 +258,7 @@ static void qce_ablkcipher_exit(struct crypto_tfm *tfm)
 {
 	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_ablkcipher(ctx->fallback);
+	crypto_free_skcipher(ctx->fallback);
 }
 
 struct qce_ablkcipher_def {
diff --git a/drivers/crypto/qce/cipher.h b/drivers/crypto/qce/cipher.h
index 5c6a5f8633e5..2b0278bb6e92 100644
--- a/drivers/crypto/qce/cipher.h
+++ b/drivers/crypto/qce/cipher.h
@@ -22,7 +22,7 @@
 struct qce_cipher_ctx {
 	u8 enc_key[QCE_MAX_KEY_SIZE];
 	unsigned int enc_keylen;
-	struct crypto_ablkcipher *fallback;
+	struct crypto_skcipher *fallback;
 };
 
 /**
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 2b3a0cfe3331..dce1af0ce85c 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -155,43 +155,43 @@
  * expansion of its usage.
  */
 struct samsung_aes_variant {
-	unsigned int		    aes_offset;
+	unsigned int			aes_offset;
 };
 
 struct s5p_aes_reqctx {
-	unsigned long mode;
+	unsigned long			mode;
 };
 
 struct s5p_aes_ctx {
-	struct s5p_aes_dev         *dev;
+	struct s5p_aes_dev		*dev;
 
-	uint8_t                     aes_key[AES_MAX_KEY_SIZE];
-	uint8_t                     nonce[CTR_RFC3686_NONCE_SIZE];
-	int                         keylen;
+	uint8_t				aes_key[AES_MAX_KEY_SIZE];
+	uint8_t				nonce[CTR_RFC3686_NONCE_SIZE];
+	int				keylen;
 };
 
 struct s5p_aes_dev {
-	struct device              *dev;
-	struct clk                 *clk;
-	void __iomem               *ioaddr;
-	void __iomem               *aes_ioaddr;
-	int                         irq_fc;
+	struct device			*dev;
+	struct clk			*clk;
+	void __iomem			*ioaddr;
+	void __iomem			*aes_ioaddr;
+	int				irq_fc;
 
-	struct ablkcipher_request  *req;
-	struct s5p_aes_ctx         *ctx;
-	struct scatterlist         *sg_src;
-	struct scatterlist         *sg_dst;
+	struct ablkcipher_request	*req;
+	struct s5p_aes_ctx		*ctx;
+	struct scatterlist		*sg_src;
+	struct scatterlist		*sg_dst;
 
 	/* In case of unaligned access: */
-	struct scatterlist         *sg_src_cpy;
-	struct scatterlist         *sg_dst_cpy;
+	struct scatterlist		*sg_src_cpy;
+	struct scatterlist		*sg_dst_cpy;
 
-	struct tasklet_struct       tasklet;
-	struct crypto_queue         queue;
-	bool                        busy;
-	spinlock_t                  lock;
+	struct tasklet_struct		tasklet;
+	struct crypto_queue		queue;
+	bool				busy;
+	spinlock_t			lock;
 
-	struct samsung_aes_variant *variant;
+	struct samsung_aes_variant	*variant;
 };
 
 static struct s5p_aes_dev *s5p_dev;
@@ -421,11 +421,11 @@ static bool s5p_aes_rx(struct s5p_aes_dev *dev)
 static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
 {
 	struct platform_device *pdev = dev_id;
-	struct s5p_aes_dev     *dev  = platform_get_drvdata(pdev);
-	uint32_t                status;
-	unsigned long           flags;
-	bool			set_dma_tx = false;
-	bool			set_dma_rx = false;
+	struct s5p_aes_dev *dev = platform_get_drvdata(pdev);
+	bool set_dma_tx = false;
+	bool set_dma_rx = false;
+	unsigned long flags;
+	uint32_t status;
 
 	spin_lock_irqsave(&dev->lock, flags);
 
@@ -538,10 +538,10 @@ static int s5p_set_outdata_start(struct s5p_aes_dev *dev,
 
 static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
 {
-	struct ablkcipher_request  *req = dev->req;
-	uint32_t                    aes_control;
-	int                         err;
-	unsigned long               flags;
+	struct ablkcipher_request *req = dev->req;
+	uint32_t aes_control;
+	unsigned long flags;
+	int err;
 
 	aes_control = SSS_AES_KEY_CHANGE_MODE;
 	if (mode & FLAGS_AES_DECRYPT)
@@ -653,10 +653,10 @@ exit:
 
 static int s5p_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 {
-	struct crypto_ablkcipher   *tfm    = crypto_ablkcipher_reqtfm(req);
-	struct s5p_aes_ctx         *ctx    = crypto_ablkcipher_ctx(tfm);
-	struct s5p_aes_reqctx      *reqctx = ablkcipher_request_ctx(req);
-	struct s5p_aes_dev         *dev    = ctx->dev;
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct s5p_aes_reqctx *reqctx = ablkcipher_request_ctx(req);
+	struct s5p_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct s5p_aes_dev *dev = ctx->dev;
 
 	if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) {
 		dev_err(dev->dev, "request size is not exact amount of AES blocks\n");
@@ -671,7 +671,7 @@ static int s5p_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 static int s5p_aes_setkey(struct crypto_ablkcipher *cipher,
 			  const uint8_t *key, unsigned int keylen)
 {
-	struct crypto_tfm  *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
 	struct s5p_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (keylen != AES_KEYSIZE_128 &&
@@ -763,11 +763,11 @@ static struct crypto_alg algs[] = {
 
 static int s5p_aes_probe(struct platform_device *pdev)
 {
-	int                 i, j, err = -ENODEV;
-	struct s5p_aes_dev *pdata;
-	struct device      *dev = &pdev->dev;
-	struct resource    *res;
+	struct device *dev = &pdev->dev;
+	int i, j, err = -ENODEV;
 	struct samsung_aes_variant *variant;
+	struct s5p_aes_dev *pdata;
+	struct resource *res;
 
 	if (s5p_dev)
 		return -EEXIST;
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index c3f3d89e4831..0c49956ee0ce 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -14,10 +14,9 @@
  * Based on omap-aes.c and tegra-aes.c
  */
 
-#include <crypto/algapi.h>
 #include <crypto/aes.h>
-#include <crypto/hash.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/sha.h>
 
@@ -150,10 +149,7 @@ struct sahara_ctx {
 	/* AES-specific context */
 	int keylen;
 	u8 key[AES_KEYSIZE_128];
-	struct crypto_ablkcipher *fallback;
-
-	/* SHA-specific context */
-	struct crypto_shash *shash_fallback;
+	struct crypto_skcipher *fallback;
 };
 
 struct sahara_aes_reqctx {
@@ -620,25 +616,21 @@ static int sahara_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 		return 0;
 	}
 
-	if (keylen != AES_KEYSIZE_128 &&
-	    keylen != AES_KEYSIZE_192 && keylen != AES_KEYSIZE_256)
+	if (keylen != AES_KEYSIZE_192 && keylen != AES_KEYSIZE_256)
 		return -EINVAL;
 
 	/*
 	 * The requested key size is not supported by HW, do a fallback.
 	 */
-	ctx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	ctx->fallback->base.crt_flags |=
-		(tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(ctx->fallback, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctx->fallback, tfm->base.crt_flags &
+						 CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_ablkcipher_setkey(ctx->fallback, key, keylen);
-	if (ret) {
-		struct crypto_tfm *tfm_aux = crypto_ablkcipher_tfm(tfm);
+	ret = crypto_skcipher_setkey(ctx->fallback, key, keylen);
 
-		tfm_aux->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm_aux->crt_flags |=
-			(ctx->fallback->base.crt_flags & CRYPTO_TFM_RES_MASK);
-	}
+	tfm->base.crt_flags &= ~CRYPTO_TFM_RES_MASK;
+	tfm->base.crt_flags |= crypto_skcipher_get_flags(ctx->fallback) &
+			       CRYPTO_TFM_RES_MASK;
 	return ret;
 }
 
@@ -670,16 +662,20 @@ static int sahara_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 
 static int sahara_aes_ecb_encrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_encrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_encrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -688,16 +684,20 @@ static int sahara_aes_ecb_encrypt(struct ablkcipher_request *req)
 
 static int sahara_aes_ecb_decrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -706,16 +706,20 @@ static int sahara_aes_ecb_decrypt(struct ablkcipher_request *req)
 
 static int sahara_aes_cbc_encrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_encrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_encrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -724,16 +728,20 @@ static int sahara_aes_cbc_encrypt(struct ablkcipher_request *req)
 
 static int sahara_aes_cbc_decrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -745,8 +753,9 @@ static int sahara_aes_cra_init(struct crypto_tfm *tfm)
 	const char *name = crypto_tfm_alg_name(tfm);
 	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	ctx->fallback = crypto_alloc_ablkcipher(name, 0,
-				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+	ctx->fallback = crypto_alloc_skcipher(name, 0,
+					      CRYPTO_ALG_ASYNC |
+					      CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(ctx->fallback)) {
 		pr_err("Error allocating fallback algo %s\n", name);
 		return PTR_ERR(ctx->fallback);
@@ -761,9 +770,7 @@ static void sahara_aes_cra_exit(struct crypto_tfm *tfm)
 {
 	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (ctx->fallback)
-		crypto_free_ablkcipher(ctx->fallback);
-	ctx->fallback = NULL;
+	crypto_free_skcipher(ctx->fallback);
 }
 
 static u32 sahara_sha_init_hdr(struct sahara_dev *dev,
@@ -1180,15 +1187,6 @@ static int sahara_sha_import(struct ahash_request *req, const void *in)
 
 static int sahara_sha_cra_init(struct crypto_tfm *tfm)
 {
-	const char *name = crypto_tfm_alg_name(tfm);
-	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	ctx->shash_fallback = crypto_alloc_shash(name, 0,
-					CRYPTO_ALG_NEED_FALLBACK);
-	if (IS_ERR(ctx->shash_fallback)) {
-		pr_err("Error allocating fallback algo %s\n", name);
-		return PTR_ERR(ctx->shash_fallback);
-	}
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct sahara_sha_reqctx) +
 				 SHA_BUFFER_LEN + SHA256_BLOCK_SIZE);
@@ -1196,14 +1194,6 @@ static int sahara_sha_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static void sahara_sha_cra_exit(struct crypto_tfm *tfm)
-{
-	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_shash(ctx->shash_fallback);
-	ctx->shash_fallback = NULL;
-}
-
 static struct crypto_alg aes_algs[] = {
 {
 	.cra_name		= "ecb(aes)",
@@ -1272,7 +1262,6 @@ static struct ahash_alg sha_v3_algs[] = {
 		.cra_alignmask		= 0,
 		.cra_module		= THIS_MODULE,
 		.cra_init		= sahara_sha_cra_init,
-		.cra_exit		= sahara_sha_cra_exit,
 	}
 },
 };
@@ -1300,7 +1289,6 @@ static struct ahash_alg sha_v4_algs[] = {
 		.cra_alignmask		= 0,
 		.cra_module		= THIS_MODULE,
 		.cra_init		= sahara_sha_cra_init,
-		.cra_exit		= sahara_sha_cra_exit,
 	}
 },
 };
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index b7ee8d30147d..0418a2f41dc0 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -91,10 +91,17 @@ static unsigned short from_talitos_ptr_len(struct talitos_ptr *ptr,
 		return be16_to_cpu(ptr->len);
 }
 
-static void to_talitos_ptr_extent_clear(struct talitos_ptr *ptr, bool is_sec1)
+static void to_talitos_ptr_ext_set(struct talitos_ptr *ptr, u8 val,
+				   bool is_sec1)
 {
 	if (!is_sec1)
-		ptr->j_extent = 0;
+		ptr->j_extent = val;
+}
+
+static void to_talitos_ptr_ext_or(struct talitos_ptr *ptr, u8 val, bool is_sec1)
+{
+	if (!is_sec1)
+		ptr->j_extent |= val;
 }
 
 /*
@@ -111,7 +118,7 @@ static void map_single_talitos_ptr(struct device *dev,
 
 	to_talitos_ptr_len(ptr, len, is_sec1);
 	to_talitos_ptr(ptr, dma_addr, is_sec1);
-	to_talitos_ptr_extent_clear(ptr, is_sec1);
+	to_talitos_ptr_ext_set(ptr, 0, is_sec1);
 }
 
 /*
@@ -804,6 +811,11 @@ static void talitos_unregister_rng(struct device *dev)
  * crypto alg
  */
 #define TALITOS_CRA_PRIORITY		3000
+/*
+ * Defines a priority for doing AEAD with descriptors type
+ * HMAC_SNOOP_NO_AFEA (HSNA) instead of type IPSEC_ESP
+ */
+#define TALITOS_CRA_PRIORITY_AEAD_HSNA	(TALITOS_CRA_PRIORITY - 1)
 #define TALITOS_MAX_KEY_SIZE		96
 #define TALITOS_MAX_IV_LENGTH		16 /* max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */
 
@@ -904,35 +916,59 @@ struct talitos_edesc {
 static void talitos_sg_unmap(struct device *dev,
 			     struct talitos_edesc *edesc,
 			     struct scatterlist *src,
-			     struct scatterlist *dst)
+			     struct scatterlist *dst,
+			     unsigned int len, unsigned int offset)
 {
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 	unsigned int src_nents = edesc->src_nents ? : 1;
 	unsigned int dst_nents = edesc->dst_nents ? : 1;
 
+	if (is_sec1 && dst && dst_nents > 1) {
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl + offset,
+					   len, DMA_FROM_DEVICE);
+		sg_pcopy_from_buffer(dst, dst_nents, edesc->buf + offset, len,
+				     offset);
+	}
 	if (src != dst) {
-		dma_unmap_sg(dev, src, src_nents, DMA_TO_DEVICE);
+		if (src_nents == 1 || !is_sec1)
+			dma_unmap_sg(dev, src, src_nents, DMA_TO_DEVICE);
 
-		if (dst) {
+		if (dst && (dst_nents == 1 || !is_sec1))
 			dma_unmap_sg(dev, dst, dst_nents, DMA_FROM_DEVICE);
-		}
-	} else
+	} else if (src_nents == 1 || !is_sec1) {
 		dma_unmap_sg(dev, src, src_nents, DMA_BIDIRECTIONAL);
+	}
 }
 
 static void ipsec_esp_unmap(struct device *dev,
 			    struct talitos_edesc *edesc,
 			    struct aead_request *areq)
 {
-	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[6], DMA_FROM_DEVICE);
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+
+	if (edesc->desc.hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		unmap_single_talitos_ptr(dev, &edesc->desc.ptr[6],
+					 DMA_FROM_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[3], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[0], DMA_TO_DEVICE);
 
-	talitos_sg_unmap(dev, edesc, areq->src, areq->dst);
+	talitos_sg_unmap(dev, edesc, areq->src, areq->dst, areq->cryptlen,
+			 areq->assoclen);
 
 	if (edesc->dma_len)
 		dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len,
 				 DMA_BIDIRECTIONAL);
+
+	if (!(edesc->desc.hdr & DESC_HDR_TYPE_IPSEC_ESP)) {
+		unsigned int dst_nents = edesc->dst_nents ? : 1;
+
+		sg_pcopy_to_buffer(areq->dst, dst_nents, ctx->iv, ivsize,
+				   areq->assoclen + areq->cryptlen - ivsize);
+	}
 }
 
 /*
@@ -942,6 +978,8 @@ static void ipsec_esp_encrypt_done(struct device *dev,
 				   struct talitos_desc *desc, void *context,
 				   int err)
 {
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 	struct aead_request *areq = context;
 	struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
 	unsigned int authsize = crypto_aead_authsize(authenc);
@@ -955,8 +993,11 @@ static void ipsec_esp_encrypt_done(struct device *dev,
 
 	/* copy the generated ICV to dst */
 	if (edesc->icv_ool) {
-		icvdata = &edesc->link_tbl[edesc->src_nents +
-					   edesc->dst_nents + 2];
+		if (is_sec1)
+			icvdata = edesc->buf + areq->assoclen + areq->cryptlen;
+		else
+			icvdata = &edesc->link_tbl[edesc->src_nents +
+						   edesc->dst_nents + 2];
 		sg = sg_last(areq->dst, edesc->dst_nents);
 		memcpy((char *)sg_virt(sg) + sg->length - authsize,
 		       icvdata, authsize);
@@ -977,6 +1018,8 @@ static void ipsec_esp_decrypt_swauth_done(struct device *dev,
 	struct talitos_edesc *edesc;
 	struct scatterlist *sg;
 	char *oicv, *icv;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	edesc = container_of(desc, struct talitos_edesc, desc);
 
@@ -988,7 +1031,12 @@ static void ipsec_esp_decrypt_swauth_done(struct device *dev,
 		icv = (char *)sg_virt(sg) + sg->length - authsize;
 
 		if (edesc->dma_len) {
-			oicv = (char *)&edesc->link_tbl[edesc->src_nents +
+			if (is_sec1)
+				oicv = (char *)&edesc->dma_link_tbl +
+					       req->assoclen + req->cryptlen;
+			else
+				oicv = (char *)
+				       &edesc->link_tbl[edesc->src_nents +
 							edesc->dst_nents + 2];
 			if (edesc->icv_ool)
 				icv = oicv + authsize;
@@ -1050,8 +1098,8 @@ static int sg_to_link_tbl_offset(struct scatterlist *sg, int sg_count,
 
 		to_talitos_ptr(link_tbl_ptr + count,
 			       sg_dma_address(sg) + offset, 0);
-		link_tbl_ptr[count].len = cpu_to_be16(len);
-		link_tbl_ptr[count].j_extent = 0;
+		to_talitos_ptr_len(link_tbl_ptr + count, len, 0);
+		to_talitos_ptr_ext_set(link_tbl_ptr + count, 0, 0);
 		count++;
 		cryptlen -= len;
 		offset = 0;
@@ -1062,17 +1110,43 @@ next:
 
 	/* tag end of link table */
 	if (count > 0)
-		link_tbl_ptr[count - 1].j_extent = DESC_PTR_LNKTBL_RETURN;
+		to_talitos_ptr_ext_set(link_tbl_ptr + count - 1,
+				       DESC_PTR_LNKTBL_RETURN, 0);
 
 	return count;
 }
 
-static inline int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
-				 int cryptlen,
-				 struct talitos_ptr *link_tbl_ptr)
+int talitos_sg_map(struct device *dev, struct scatterlist *src,
+		   unsigned int len, struct talitos_edesc *edesc,
+		   struct talitos_ptr *ptr,
+		   int sg_count, unsigned int offset, int tbl_off)
 {
-	return sg_to_link_tbl_offset(sg, sg_count, 0, cryptlen,
-				     link_tbl_ptr);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	to_talitos_ptr_len(ptr, len, is_sec1);
+	to_talitos_ptr_ext_set(ptr, 0, is_sec1);
+
+	if (sg_count == 1) {
+		to_talitos_ptr(ptr, sg_dma_address(src) + offset, is_sec1);
+		return sg_count;
+	}
+	if (is_sec1) {
+		to_talitos_ptr(ptr, edesc->dma_link_tbl + offset, is_sec1);
+		return sg_count;
+	}
+	sg_count = sg_to_link_tbl_offset(src, sg_count, offset, len,
+					 &edesc->link_tbl[tbl_off]);
+	if (sg_count == 1) {
+		/* Only one segment now, so no link tbl needed*/
+		copy_talitos_ptr(ptr, &edesc->link_tbl[tbl_off], is_sec1);
+		return sg_count;
+	}
+	to_talitos_ptr(ptr, edesc->dma_link_tbl +
+			    tbl_off * sizeof(struct talitos_ptr), is_sec1);
+	to_talitos_ptr_ext_or(ptr, DESC_PTR_LNKTBL_JUMP, is_sec1);
+
+	return sg_count;
 }
 
 /*
@@ -1093,42 +1167,52 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	int tbl_off = 0;
 	int sg_count, ret;
 	int sg_link_tbl_len;
+	bool sync_needed = false;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/* hmac key */
 	map_single_talitos_ptr(dev, &desc->ptr[0], ctx->authkeylen, &ctx->key,
 			       DMA_TO_DEVICE);
 
-	sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1,
-			      (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
-							   : DMA_TO_DEVICE);
-	/* hmac data */
-	desc->ptr[1].len = cpu_to_be16(areq->assoclen);
-	if (sg_count > 1 &&
-	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0,
-					 areq->assoclen,
-					 &edesc->link_tbl[tbl_off])) > 1) {
-		to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off *
-			       sizeof(struct talitos_ptr), 0);
-		desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP;
+	sg_count = edesc->src_nents ?: 1;
+	if (is_sec1 && sg_count > 1)
+		sg_copy_to_buffer(areq->src, sg_count, edesc->buf,
+				  areq->assoclen + cryptlen);
+	else
+		sg_count = dma_map_sg(dev, areq->src, sg_count,
+				      (areq->src == areq->dst) ?
+				      DMA_BIDIRECTIONAL : DMA_TO_DEVICE);
 
-		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-					   edesc->dma_len, DMA_BIDIRECTIONAL);
+	/* hmac data */
+	ret = talitos_sg_map(dev, areq->src, areq->assoclen, edesc,
+			     &desc->ptr[1], sg_count, 0, tbl_off);
 
+	if (ret > 1) {
 		tbl_off += ret;
-	} else {
-		to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0);
-		desc->ptr[1].j_extent = 0;
+		sync_needed = true;
 	}
 
 	/* cipher iv */
-	to_talitos_ptr(&desc->ptr[2], edesc->iv_dma, 0);
-	desc->ptr[2].len = cpu_to_be16(ivsize);
-	desc->ptr[2].j_extent = 0;
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP) {
+		to_talitos_ptr(&desc->ptr[2], edesc->iv_dma, is_sec1);
+		to_talitos_ptr_len(&desc->ptr[2], ivsize, is_sec1);
+		to_talitos_ptr_ext_set(&desc->ptr[2], 0, is_sec1);
+	} else {
+		to_talitos_ptr(&desc->ptr[3], edesc->iv_dma, is_sec1);
+		to_talitos_ptr_len(&desc->ptr[3], ivsize, is_sec1);
+		to_talitos_ptr_ext_set(&desc->ptr[3], 0, is_sec1);
+	}
 
 	/* cipher key */
-	map_single_talitos_ptr(dev, &desc->ptr[3], ctx->enckeylen,
-			       (char *)&ctx->key + ctx->authkeylen,
-			       DMA_TO_DEVICE);
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		map_single_talitos_ptr(dev, &desc->ptr[3], ctx->enckeylen,
+				       (char *)&ctx->key + ctx->authkeylen,
+				       DMA_TO_DEVICE);
+	else
+		map_single_talitos_ptr(dev, &desc->ptr[2], ctx->enckeylen,
+				       (char *)&ctx->key + ctx->authkeylen,
+				       DMA_TO_DEVICE);
 
 	/*
 	 * cipher in
@@ -1136,78 +1220,82 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	 * extent is bytes of HMAC postpended to ciphertext,
 	 * typically 12 for ipsec
 	 */
-	desc->ptr[4].len = cpu_to_be16(cryptlen);
-	desc->ptr[4].j_extent = authsize;
+	to_talitos_ptr_len(&desc->ptr[4], cryptlen, is_sec1);
+	to_talitos_ptr_ext_set(&desc->ptr[4], 0, is_sec1);
 
 	sg_link_tbl_len = cryptlen;
-	if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
-		sg_link_tbl_len += authsize;
 
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) +
-			       areq->assoclen, 0);
-	} else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count,
-						areq->assoclen, sg_link_tbl_len,
-						&edesc->link_tbl[tbl_off])) >
-		   1) {
-		desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
-		to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl +
-					      tbl_off *
-					      sizeof(struct talitos_ptr), 0);
-		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-					   edesc->dma_len,
-					   DMA_BIDIRECTIONAL);
-		tbl_off += ret;
-	} else {
-		copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0);
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP) {
+		to_talitos_ptr_ext_set(&desc->ptr[4], authsize, is_sec1);
+
+		if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
+			sg_link_tbl_len += authsize;
 	}
 
-	/* cipher out */
-	desc->ptr[5].len = cpu_to_be16(cryptlen);
-	desc->ptr[5].j_extent = authsize;
+	sg_count = talitos_sg_map(dev, areq->src, cryptlen, edesc,
+				  &desc->ptr[4], sg_count, areq->assoclen,
+				  tbl_off);
 
-	if (areq->src != areq->dst)
-		sg_count = dma_map_sg(dev, areq->dst, edesc->dst_nents ? : 1,
-				      DMA_FROM_DEVICE);
+	if (sg_count > 1) {
+		tbl_off += sg_count;
+		sync_needed = true;
+	}
 
-	edesc->icv_ool = false;
+	/* cipher out */
+	if (areq->src != areq->dst) {
+		sg_count = edesc->dst_nents ? : 1;
+		if (!is_sec1 || sg_count == 1)
+			dma_map_sg(dev, areq->dst, sg_count, DMA_FROM_DEVICE);
+	}
 
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) +
-			       areq->assoclen, 0);
-	} else if ((sg_count =
-			sg_to_link_tbl_offset(areq->dst, sg_count,
-					      areq->assoclen, cryptlen,
-					      &edesc->link_tbl[tbl_off])) > 1) {
-		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
-
-		to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl +
-			       tbl_off * sizeof(struct talitos_ptr), 0);
-
-		/* Add an entry to the link table for ICV data */
-		tbl_ptr += sg_count - 1;
-		tbl_ptr->j_extent = 0;
-		tbl_ptr++;
-		tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
-		tbl_ptr->len = cpu_to_be16(authsize);
-
-		/* icv data follows link tables */
-		to_talitos_ptr(tbl_ptr, edesc->dma_link_tbl +
-					(edesc->src_nents + edesc->dst_nents +
-					 2) * sizeof(struct talitos_ptr) +
-					authsize, 0);
-		desc->ptr[5].j_extent |= DESC_PTR_LNKTBL_JUMP;
-		dma_sync_single_for_device(ctx->dev, edesc->dma_link_tbl,
-					   edesc->dma_len, DMA_BIDIRECTIONAL);
+	sg_count = talitos_sg_map(dev, areq->dst, cryptlen, edesc,
+				  &desc->ptr[5], sg_count, areq->assoclen,
+				  tbl_off);
 
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		to_talitos_ptr_ext_or(&desc->ptr[5], authsize, is_sec1);
+
+	if (sg_count > 1) {
 		edesc->icv_ool = true;
+		sync_needed = true;
+
+		if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP) {
+			struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
+			int offset = (edesc->src_nents + edesc->dst_nents + 2) *
+				     sizeof(struct talitos_ptr) + authsize;
+
+			/* Add an entry to the link table for ICV data */
+			tbl_ptr += sg_count - 1;
+			to_talitos_ptr_ext_set(tbl_ptr, 0, is_sec1);
+			tbl_ptr++;
+			to_talitos_ptr_ext_set(tbl_ptr, DESC_PTR_LNKTBL_RETURN,
+					       is_sec1);
+			to_talitos_ptr_len(tbl_ptr, authsize, is_sec1);
+
+			/* icv data follows link tables */
+			to_talitos_ptr(tbl_ptr, edesc->dma_link_tbl + offset,
+				       is_sec1);
+		}
 	} else {
-		copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0);
+		edesc->icv_ool = false;
+	}
+
+	/* ICV data */
+	if (!(desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)) {
+		to_talitos_ptr_len(&desc->ptr[6], authsize, is_sec1);
+		to_talitos_ptr(&desc->ptr[6], edesc->dma_link_tbl +
+			       areq->assoclen + cryptlen, is_sec1);
 	}
 
 	/* iv out */
-	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
-			       DMA_FROM_DEVICE);
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
+				       DMA_FROM_DEVICE);
+
+	if (sync_needed)
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+					   edesc->dma_len,
+					   DMA_BIDIRECTIONAL);
 
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
@@ -1233,7 +1321,7 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 						 bool encrypt)
 {
 	struct talitos_edesc *edesc;
-	int src_nents, dst_nents, alloc_len, dma_len;
+	int src_nents, dst_nents, alloc_len, dma_len, src_len, dst_len;
 	dma_addr_t iv_dma = 0;
 	gfp_t flags = cryptoflags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		      GFP_ATOMIC;
@@ -1251,8 +1339,8 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 		iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE);
 
 	if (!dst || dst == src) {
-		src_nents = sg_nents_for_len(src,
-					     assoclen + cryptlen + authsize);
+		src_len = assoclen + cryptlen + authsize;
+		src_nents = sg_nents_for_len(src, src_len);
 		if (src_nents < 0) {
 			dev_err(dev, "Invalid number of src SG.\n");
 			err = ERR_PTR(-EINVAL);
@@ -1260,17 +1348,18 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
 		dst_nents = dst ? src_nents : 0;
+		dst_len = 0;
 	} else { /* dst && dst != src*/
-		src_nents = sg_nents_for_len(src, assoclen + cryptlen +
-						 (encrypt ? 0 : authsize));
+		src_len = assoclen + cryptlen + (encrypt ? 0 : authsize);
+		src_nents = sg_nents_for_len(src, src_len);
 		if (src_nents < 0) {
 			dev_err(dev, "Invalid number of src SG.\n");
 			err = ERR_PTR(-EINVAL);
 			goto error_sg;
 		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
-		dst_nents = sg_nents_for_len(dst, assoclen + cryptlen +
-						 (encrypt ? authsize : 0));
+		dst_len = assoclen + cryptlen + (encrypt ? authsize : 0);
+		dst_nents = sg_nents_for_len(dst, dst_len);
 		if (dst_nents < 0) {
 			dev_err(dev, "Invalid number of dst SG.\n");
 			err = ERR_PTR(-EINVAL);
@@ -1287,8 +1376,8 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	alloc_len = sizeof(struct talitos_edesc);
 	if (src_nents || dst_nents) {
 		if (is_sec1)
-			dma_len = (src_nents ? cryptlen : 0) +
-				  (dst_nents ? cryptlen : 0);
+			dma_len = (src_nents ? src_len : 0) +
+				  (dst_nents ? dst_len : 0);
 		else
 			dma_len = (src_nents + dst_nents + 2) *
 				  sizeof(struct talitos_ptr) + authsize * 2;
@@ -1412,40 +1501,13 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-static void unmap_sg_talitos_ptr(struct device *dev, struct scatterlist *src,
-				 struct scatterlist *dst, unsigned int len,
-				 struct talitos_edesc *edesc)
-{
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
-
-	if (is_sec1) {
-		if (!edesc->src_nents) {
-			dma_unmap_sg(dev, src, 1,
-				     dst != src ? DMA_TO_DEVICE
-						: DMA_BIDIRECTIONAL);
-		}
-		if (dst && edesc->dst_nents) {
-			dma_sync_single_for_device(dev,
-						   edesc->dma_link_tbl + len,
-						   len, DMA_FROM_DEVICE);
-			sg_copy_from_buffer(dst, edesc->dst_nents ? : 1,
-					    edesc->buf + len, len);
-		} else if (dst && dst != src) {
-			dma_unmap_sg(dev, dst, 1, DMA_FROM_DEVICE);
-		}
-	} else {
-		talitos_sg_unmap(dev, edesc, src, dst);
-	}
-}
-
 static void common_nonsnoop_unmap(struct device *dev,
 				  struct talitos_edesc *edesc,
 				  struct ablkcipher_request *areq)
 {
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
 
-	unmap_sg_talitos_ptr(dev, areq->src, areq->dst, areq->nbytes, edesc);
+	talitos_sg_unmap(dev, edesc, areq->src, areq->dst, areq->nbytes, 0);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1], DMA_TO_DEVICE);
 
@@ -1470,100 +1532,6 @@ static void ablkcipher_done(struct device *dev,
 	areq->base.complete(&areq->base, err);
 }
 
-int map_sg_in_talitos_ptr(struct device *dev, struct scatterlist *src,
-			  unsigned int len, struct talitos_edesc *edesc,
-			  enum dma_data_direction dir, struct talitos_ptr *ptr)
-{
-	int sg_count;
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
-
-	to_talitos_ptr_len(ptr, len, is_sec1);
-
-	if (is_sec1) {
-		sg_count = edesc->src_nents ? : 1;
-
-		if (sg_count == 1) {
-			dma_map_sg(dev, src, 1, dir);
-			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
-		} else {
-			sg_copy_to_buffer(src, sg_count, edesc->buf, len);
-			to_talitos_ptr(ptr, edesc->dma_link_tbl, is_sec1);
-			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-						   len, DMA_TO_DEVICE);
-		}
-	} else {
-		to_talitos_ptr_extent_clear(ptr, is_sec1);
-
-		sg_count = dma_map_sg(dev, src, edesc->src_nents ? : 1, dir);
-
-		if (sg_count == 1) {
-			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
-		} else {
-			sg_count = sg_to_link_tbl(src, sg_count, len,
-						  &edesc->link_tbl[0]);
-			if (sg_count > 1) {
-				to_talitos_ptr(ptr, edesc->dma_link_tbl, 0);
-				ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
-				dma_sync_single_for_device(dev,
-							   edesc->dma_link_tbl,
-							   edesc->dma_len,
-							   DMA_BIDIRECTIONAL);
-			} else {
-				/* Only one segment now, so no link tbl needed*/
-				to_talitos_ptr(ptr, sg_dma_address(src),
-					       is_sec1);
-			}
-		}
-	}
-	return sg_count;
-}
-
-void map_sg_out_talitos_ptr(struct device *dev, struct scatterlist *dst,
-			    unsigned int len, struct talitos_edesc *edesc,
-			    enum dma_data_direction dir,
-			    struct talitos_ptr *ptr, int sg_count)
-{
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
-
-	if (dir != DMA_NONE)
-		sg_count = dma_map_sg(dev, dst, edesc->dst_nents ? : 1, dir);
-
-	to_talitos_ptr_len(ptr, len, is_sec1);
-
-	if (is_sec1) {
-		if (sg_count == 1) {
-			if (dir != DMA_NONE)
-				dma_map_sg(dev, dst, 1, dir);
-			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
-		} else {
-			to_talitos_ptr(ptr, edesc->dma_link_tbl + len, is_sec1);
-			dma_sync_single_for_device(dev,
-						   edesc->dma_link_tbl + len,
-						   len, DMA_FROM_DEVICE);
-		}
-	} else {
-		to_talitos_ptr_extent_clear(ptr, is_sec1);
-
-		if (sg_count == 1) {
-			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
-		} else {
-			struct talitos_ptr *link_tbl_ptr =
-				&edesc->link_tbl[edesc->src_nents + 1];
-
-			to_talitos_ptr(ptr, edesc->dma_link_tbl +
-					    (edesc->src_nents + 1) *
-					     sizeof(struct talitos_ptr), 0);
-			ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
-			sg_to_link_tbl(dst, sg_count, len, link_tbl_ptr);
-			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-						   edesc->dma_len,
-						   DMA_BIDIRECTIONAL);
-		}
-	}
-}
-
 static int common_nonsnoop(struct talitos_edesc *edesc,
 			   struct ablkcipher_request *areq,
 			   void (*callback) (struct device *dev,
@@ -1577,6 +1545,7 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	unsigned int cryptlen = areq->nbytes;
 	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
 	int sg_count, ret;
+	bool sync_needed = false;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
 
@@ -1586,25 +1555,39 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	/* cipher iv */
 	to_talitos_ptr(&desc->ptr[1], edesc->iv_dma, is_sec1);
 	to_talitos_ptr_len(&desc->ptr[1], ivsize, is_sec1);
-	to_talitos_ptr_extent_clear(&desc->ptr[1], is_sec1);
+	to_talitos_ptr_ext_set(&desc->ptr[1], 0, is_sec1);
 
 	/* cipher key */
 	map_single_talitos_ptr(dev, &desc->ptr[2], ctx->keylen,
 			       (char *)&ctx->key, DMA_TO_DEVICE);
 
+	sg_count = edesc->src_nents ?: 1;
+	if (is_sec1 && sg_count > 1)
+		sg_copy_to_buffer(areq->src, sg_count, edesc->buf,
+				  cryptlen);
+	else
+		sg_count = dma_map_sg(dev, areq->src, sg_count,
+				      (areq->src == areq->dst) ?
+				      DMA_BIDIRECTIONAL : DMA_TO_DEVICE);
 	/*
 	 * cipher in
 	 */
-	sg_count = map_sg_in_talitos_ptr(dev, areq->src, cryptlen, edesc,
-					 (areq->src == areq->dst) ?
-					  DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
-					  &desc->ptr[3]);
+	sg_count = talitos_sg_map(dev, areq->src, cryptlen, edesc,
+				  &desc->ptr[3], sg_count, 0, 0);
+	if (sg_count > 1)
+		sync_needed = true;
 
 	/* cipher out */
-	map_sg_out_talitos_ptr(dev, areq->dst, cryptlen, edesc,
-			       (areq->src == areq->dst) ? DMA_NONE
-							: DMA_FROM_DEVICE,
-			       &desc->ptr[4], sg_count);
+	if (areq->src != areq->dst) {
+		sg_count = edesc->dst_nents ? : 1;
+		if (!is_sec1 || sg_count == 1)
+			dma_map_sg(dev, areq->dst, sg_count, DMA_FROM_DEVICE);
+	}
+
+	ret = talitos_sg_map(dev, areq->dst, cryptlen, edesc, &desc->ptr[4],
+			     sg_count, 0, (edesc->src_nents + 1));
+	if (ret > 1)
+		sync_needed = true;
 
 	/* iv out */
 	map_single_talitos_ptr(dev, &desc->ptr[5], ivsize, ctx->iv,
@@ -1613,6 +1596,10 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	/* last DWORD empty */
 	desc->ptr[6] = zero_entry;
 
+	if (sync_needed)
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+					   edesc->dma_len, DMA_BIDIRECTIONAL);
+
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
 		common_nonsnoop_unmap(dev, edesc, areq);
@@ -1676,7 +1663,7 @@ static void common_nonsnoop_hash_unmap(struct device *dev,
 
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
 
-	unmap_sg_talitos_ptr(dev, req_ctx->psrc, NULL, 0, edesc);
+	talitos_sg_unmap(dev, edesc, req_ctx->psrc, NULL, 0, 0);
 
 	/* When using hashctx-in, must unmap it. */
 	if (from_talitos_ptr_len(&edesc->desc.ptr[1], is_sec1))
@@ -1747,8 +1734,10 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	struct device *dev = ctx->dev;
 	struct talitos_desc *desc = &edesc->desc;
 	int ret;
+	bool sync_needed = false;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
+	int sg_count;
 
 	/* first DWORD empty */
 	desc->ptr[0] = zero_entry;
@@ -1773,11 +1762,19 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	else
 		desc->ptr[2] = zero_entry;
 
+	sg_count = edesc->src_nents ?: 1;
+	if (is_sec1 && sg_count > 1)
+		sg_copy_to_buffer(areq->src, sg_count, edesc->buf, length);
+	else
+		sg_count = dma_map_sg(dev, req_ctx->psrc, sg_count,
+				      DMA_TO_DEVICE);
 	/*
 	 * data in
 	 */
-	map_sg_in_talitos_ptr(dev, req_ctx->psrc, length, edesc,
-			      DMA_TO_DEVICE, &desc->ptr[3]);
+	sg_count = talitos_sg_map(dev, req_ctx->psrc, length, edesc,
+				  &desc->ptr[3], sg_count, 0, 0);
+	if (sg_count > 1)
+		sync_needed = true;
 
 	/* fifth DWORD empty */
 	desc->ptr[4] = zero_entry;
@@ -1798,6 +1795,10 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	if (is_sec1 && from_talitos_ptr_len(&desc->ptr[3], true) == 0)
 		talitos_handle_buggy_hash(ctx, edesc, &desc->ptr[3]);
 
+	if (sync_needed)
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+					   edesc->dma_len, DMA_BIDIRECTIONAL);
+
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
 		common_nonsnoop_hash_unmap(dev, edesc, areq);
@@ -2124,6 +2125,7 @@ static int ahash_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 struct talitos_alg_template {
 	u32 type;
+	u32 priority;
 	union {
 		struct crypto_alg crypto;
 		struct ahash_alg hash;
@@ -2155,6 +2157,27 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha1),"
@@ -2176,6 +2199,29 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_PAD |
 		                     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
 	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
+	},
 	{       .type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
@@ -2196,6 +2242,27 @@ static struct talitos_alg_template driver_algs[] = {
 				     DESC_HDR_MODE1_MDEU_PAD |
 				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
 	},
+	{       .type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
+	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
@@ -2219,6 +2286,29 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha256),cbc(aes))",
@@ -2239,6 +2329,27 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha256),"
@@ -2261,6 +2372,29 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha384),cbc(aes))",
@@ -2365,6 +2499,27 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_MD5_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_MD5_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
@@ -2385,6 +2540,28 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_PAD |
 		                     DESC_HDR_MODE1_MDEU_MD5_HMAC,
 	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_MD5_HMAC,
+	},
 	/* ABLKCIPHER algorithms. */
 	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.alg.crypto = {
@@ -2901,7 +3078,10 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 	}
 
 	alg->cra_module = THIS_MODULE;
-	alg->cra_priority = TALITOS_CRA_PRIORITY;
+	if (t_alg->algt.priority)
+		alg->cra_priority = t_alg->algt.priority;
+	else
+		alg->cra_priority = TALITOS_CRA_PRIORITY;
 	alg->cra_alignmask = 0;
 	alg->cra_ctxsize = sizeof(struct talitos_ctx);
 	alg->cra_flags |= CRYPTO_ALG_KERN_DRIVER_ONLY;
diff --git a/drivers/crypto/ux500/cryp/Makefile b/drivers/crypto/ux500/cryp/Makefile
index e5d362a6f680..b497ae3dde07 100644
--- a/drivers/crypto/ux500/cryp/Makefile
+++ b/drivers/crypto/ux500/cryp/Makefile
@@ -4,9 +4,9 @@
 # * License terms: GNU General Public License (GPL) version 2  */
 
 ifdef CONFIG_CRYPTO_DEV_UX500_DEBUG
-CFLAGS_cryp_core.o := -DDEBUG -O0
-CFLAGS_cryp.o := -DDEBUG -O0
-CFLAGS_cryp_irq.o := -DDEBUG -O0
+CFLAGS_cryp_core.o := -DDEBUG
+CFLAGS_cryp.o := -DDEBUG
+CFLAGS_cryp_irq.o := -DDEBUG
 endif
 
 obj-$(CONFIG_CRYPTO_DEV_UX500_CRYP) += ux500_cryp.o
diff --git a/drivers/crypto/ux500/hash/Makefile b/drivers/crypto/ux500/hash/Makefile
index b2f90d9bac72..784d9c0a8853 100644
--- a/drivers/crypto/ux500/hash/Makefile
+++ b/drivers/crypto/ux500/hash/Makefile
@@ -4,7 +4,7 @@
 # License terms: GNU General Public License (GPL) version 2
 #
 ifdef CONFIG_CRYPTO_DEV_UX500_DEBUG
-CFLAGS_hash_core.o := -DDEBUG -O0
+CFLAGS_hash_core.o := -DDEBUG
 endif
 
 obj-$(CONFIG_CRYPTO_DEV_UX500_HASH) += ux500_hash.o
diff --git a/drivers/crypto/vmx/.gitignore b/drivers/crypto/vmx/.gitignore
new file mode 100644
index 000000000000..af4a7ce4738d
--- /dev/null
+++ b/drivers/crypto/vmx/.gitignore
@@ -0,0 +1,2 @@
+aesp8-ppc.S
+ghashp8-ppc.S
diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile
index d28ab96a2475..de6e241b0866 100644
--- a/drivers/crypto/vmx/Makefile
+++ b/drivers/crypto/vmx/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o
-vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o ghash.o
+vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
 
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 TARGET := linux-ppc64le
diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c
new file mode 100644
index 000000000000..cfb25413917c
--- /dev/null
+++ b/drivers/crypto/vmx/aes_xts.c
@@ -0,0 +1,190 @@
+/**
+ * AES XTS routines supporting VMX In-core instructions on Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundations; version 2 only.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY of FITNESS FOR A PARTICUPAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Author: Leonidas S. Barbosa <leosilva@linux.vnet.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <linux/hardirq.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/xts.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_xts_ctx {
+	struct crypto_blkcipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
+	struct aes_key tweak_key;
+};
+
+static int p8_aes_xts_init(struct crypto_tfm *tfm)
+{
+	const char *alg;
+	struct crypto_blkcipher *fallback;
+	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback =
+		crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+			"Failed to allocate transformation for '%s': %ld\n",
+			alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+		crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_blkcipher_set_flags(
+		fallback,
+		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+	ctx->fallback = fallback;
+
+	return 0;
+}
+
+static void p8_aes_xts_exit(struct crypto_tfm *tfm)
+{
+	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (ctx->fallback) {
+		crypto_free_blkcipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
+}
+
+static int p8_aes_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
+			     unsigned int keylen)
+{
+	int ret;
+	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ret = xts_check_key(tfm, key, keylen);
+	if (ret)
+		return ret;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	ret = aes_p8_set_encrypt_key(key + keylen/2, (keylen/2) * 8, &ctx->tweak_key);
+	ret += aes_p8_set_encrypt_key(key, (keylen/2) * 8, &ctx->enc_key);
+	ret += aes_p8_set_decrypt_key(key, (keylen/2) * 8, &ctx->dec_key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	return ret;
+}
+
+static int p8_aes_xts_crypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst,
+			    struct scatterlist *src,
+			    unsigned int nbytes, int enc)
+{
+	int ret;
+	u8 tweak[AES_BLOCK_SIZE];
+	u8 *iv;
+	struct blkcipher_walk walk;
+	struct p8_aes_xts_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = enc ? crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes) :
+                            crypto_blkcipher_decrypt(&fallback_desc, dst, src, nbytes);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+
+		iv = (u8 *)walk.iv;
+		ret = blkcipher_walk_virt(desc, &walk);
+		memset(tweak, 0, AES_BLOCK_SIZE);
+		aes_p8_encrypt(iv, tweak, &ctx->tweak_key);
+
+		while ((nbytes = walk.nbytes)) {
+			if (enc)
+				aes_p8_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
+						nbytes & AES_BLOCK_MASK, &ctx->enc_key, NULL, tweak);
+			else
+				aes_p8_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
+						nbytes & AES_BLOCK_MASK, &ctx->dec_key, NULL, tweak);
+
+			nbytes &= AES_BLOCK_SIZE - 1;
+			ret = blkcipher_walk_done(desc, &walk, nbytes);
+		}
+
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+	}
+	return ret;
+}
+
+static int p8_aes_xts_encrypt(struct blkcipher_desc *desc,
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
+{
+	return p8_aes_xts_crypt(desc, dst, src, nbytes, 1);
+}
+
+static int p8_aes_xts_decrypt(struct blkcipher_desc *desc,
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
+{
+	return p8_aes_xts_crypt(desc, dst, src, nbytes, 0);
+}
+
+struct crypto_alg p8_aes_xts_alg = {
+	.cra_name = "xts(aes)",
+	.cra_driver_name = "p8_aes_xts",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 2000,
+	.cra_type = &crypto_blkcipher_type,
+	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct p8_aes_xts_ctx),
+	.cra_init = p8_aes_xts_init,
+	.cra_exit = p8_aes_xts_exit,
+	.cra_blkcipher = {
+			.ivsize = AES_BLOCK_SIZE,
+			.min_keysize = 2 * AES_MIN_KEY_SIZE,
+			.max_keysize = 2 * AES_MAX_KEY_SIZE,
+			.setkey	 = p8_aes_xts_setkey,
+			.encrypt = p8_aes_xts_encrypt,
+			.decrypt = p8_aes_xts_decrypt,
+	}
+};
diff --git a/drivers/crypto/vmx/aesp8-ppc.h b/drivers/crypto/vmx/aesp8-ppc.h
index 4cd34ee54a94..01972e16a6c0 100644
--- a/drivers/crypto/vmx/aesp8-ppc.h
+++ b/drivers/crypto/vmx/aesp8-ppc.h
@@ -19,3 +19,7 @@ void aes_p8_cbc_encrypt(const u8 *in, u8 *out, size_t len,
 void aes_p8_ctr32_encrypt_blocks(const u8 *in, u8 *out,
 				 size_t len, const struct aes_key *key,
 				 const u8 *iv);
+void aes_p8_xts_encrypt(const u8 *in, u8 *out, size_t len,
+			const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
+void aes_p8_xts_decrypt(const u8 *in, u8 *out, size_t len,
+			const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index 228053921b3f..0b4a293b8a1e 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (the "License").  You may not use
+# this file except in compliance with the License.  You can obtain a copy
+# in the file LICENSE in the source distribution or at
+# https://www.openssl.org/source/license.html
+
 #
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@@ -20,6 +27,19 @@
 # instructions are interleaved. It's reckoned that eventual
 # misalignment penalties at page boundaries are in average lower
 # than additional overhead in pure AltiVec approach.
+#
+# May 2016
+#
+# Add XTS subroutine, 9x on little- and 12x improvement on big-endian
+# systems were measured.
+#
+######################################################################
+# Current large-block performance in cycles per byte processed with
+# 128-bit key (less is better).
+#
+#		CBC en-/decrypt	CTR	XTS
+# POWER8[le]	3.96/0.72	0.74	1.1
+# POWER8[be]	3.75/0.65	0.66	1.0
 
 $flavour = shift;
 
@@ -1875,6 +1895,1845 @@ Lctr32_enc8x_done:
 ___
 }}	}}}
 
+#########################################################################
+{{{	# XTS procedures						#
+# int aes_p8_xts_[en|de]crypt(const char *inp, char *out, size_t len,	#
+#                             const AES_KEY *key1, const AES_KEY *key2,	#
+#                             [const] unsigned char iv[16]);		#
+# If $key2 is NULL, then a "tweak chaining" mode is engaged, in which	#
+# input tweak value is assumed to be encrypted already, and last tweak	#
+# value, one suitable for consecutive call on same chunk of data, is	#
+# written back to original buffer. In addition, in "tweak chaining"	#
+# mode only complete input blocks are processed.			#
+
+my ($inp,$out,$len,$key1,$key2,$ivp,$rounds,$idx) =	map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout) =				map("v$_",(0..2));
+my ($output,$inptail,$inpperm,$leperm,$keyperm) =	map("v$_",(3..7));
+my ($tweak,$seven,$eighty7,$tmp,$tweak1) =		map("v$_",(8..12));
+my $taillen = $key2;
+
+   ($inp,$idx) = ($idx,$inp);				# reassign
+
+$code.=<<___;
+.globl	.${prefix}_xts_encrypt
+	mr		$inp,r3				# reassign
+	li		r3,-1
+	${UCMP}i	$len,16
+	bltlr-
+
+	lis		r0,0xfff0
+	mfspr		r12,256				# save vrsave
+	li		r11,0
+	mtspr		256,r0
+
+	vspltisb	$seven,0x07			# 0x070707..07
+	le?lvsl		$leperm,r11,r11
+	le?vspltisb	$tmp,0x0f
+	le?vxor		$leperm,$leperm,$seven
+
+	li		$idx,15
+	lvx		$tweak,0,$ivp			# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$tweak,$tweak,$inptail,$inpperm
+
+	neg		r11,$inp
+	lvsr		$inpperm,0,r11			# prepare for unaligned load
+	lvx		$inout,0,$inp
+	addi		$inp,$inp,15			# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	${UCMP}i	$key2,0				# key2==NULL?
+	beq		Lxts_enc_no_key2
+
+	?lvsl		$keyperm,0,$key2		# prepare for unaligned key
+	lwz		$rounds,240($key2)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	lvx		$rndkey0,0,$key2
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Ltweak_xts_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	bdnz		Ltweak_xts_enc
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipherlast	$tweak,$tweak,$rndkey0
+
+	li		$ivp,0				# don't chain the tweak
+	b		Lxts_enc
+
+Lxts_enc_no_key2:
+	li		$idx,-16
+	and		$len,$len,$idx			# in "tweak chaining"
+							# mode only complete
+							# blocks are processed
+Lxts_enc:
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+
+	?lvsl		$keyperm,0,$key1		# prepare for unaligned key
+	lwz		$rounds,240($key1)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	vslb		$eighty7,$seven,$seven		# 0x808080..80
+	vor		$eighty7,$eighty7,$seven	# 0x878787..87
+	vspltisb	$tmp,1				# 0x010101..01
+	vsldoi		$eighty7,$eighty7,$tmp,15	# 0x870101..01
+
+	${UCMP}i	$len,96
+	bge		_aesp8_xts_encrypt6x
+
+	andi.		$taillen,$len,15
+	subic		r0,$len,32
+	subi		$taillen,$taillen,16
+	subfe		r0,r0,r0
+	and		r0,r0,$taillen
+	add		$inp,$inp,r0
+
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	mtctr		$rounds
+	b		Loop_xts_enc
+
+.align	5
+Loop_xts_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_enc
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak
+	vcipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+	addi		$out,$out,16
+
+	subic.		$len,$len,16
+	beq		Lxts_enc_done
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+
+	subic		r0,$len,32
+	subfe		r0,r0,r0
+	and		r0,r0,$taillen
+	add		$inp,$inp,r0
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$output,$output,$rndkey0	# just in case $len<16
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	mtctr		$rounds
+	${UCMP}i	$len,16
+	bge		Loop_xts_enc
+
+	vxor		$output,$output,$tweak
+	lvsr		$inpperm,0,$len			# $inpperm is no longer needed
+	vxor		$inptail,$inptail,$inptail	# $inptail is no longer needed
+	vspltisb	$tmp,-1
+	vperm		$inptail,$inptail,$tmp,$inpperm
+	vsel		$inout,$inout,$output,$inptail
+
+	subi		r11,$out,17
+	subi		$out,$out,16
+	mtctr		$len
+	li		$len,16
+Loop_xts_enc_steal:
+	lbzu		r0,1(r11)
+	stb		r0,16(r11)
+	bdnz		Loop_xts_enc_steal
+
+	mtctr		$rounds
+	b		Loop_xts_enc			# one more time...
+
+Lxts_enc_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_enc_ret
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_enc_ret:
+	mtspr		256,r12				# restore vrsave
+	li		r3,0
+	blr
+	.long		0
+	.byte		0,12,0x04,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_xts_encrypt,.-.${prefix}_xts_encrypt
+
+.globl	.${prefix}_xts_decrypt
+	mr		$inp,r3				# reassign
+	li		r3,-1
+	${UCMP}i	$len,16
+	bltlr-
+
+	lis		r0,0xfff8
+	mfspr		r12,256				# save vrsave
+	li		r11,0
+	mtspr		256,r0
+
+	andi.		r0,$len,15
+	neg		r0,r0
+	andi.		r0,r0,16
+	sub		$len,$len,r0
+
+	vspltisb	$seven,0x07			# 0x070707..07
+	le?lvsl		$leperm,r11,r11
+	le?vspltisb	$tmp,0x0f
+	le?vxor		$leperm,$leperm,$seven
+
+	li		$idx,15
+	lvx		$tweak,0,$ivp			# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$tweak,$tweak,$inptail,$inpperm
+
+	neg		r11,$inp
+	lvsr		$inpperm,0,r11			# prepare for unaligned load
+	lvx		$inout,0,$inp
+	addi		$inp,$inp,15			# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	${UCMP}i	$key2,0				# key2==NULL?
+	beq		Lxts_dec_no_key2
+
+	?lvsl		$keyperm,0,$key2		# prepare for unaligned key
+	lwz		$rounds,240($key2)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	lvx		$rndkey0,0,$key2
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Ltweak_xts_dec:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	bdnz		Ltweak_xts_dec
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipherlast	$tweak,$tweak,$rndkey0
+
+	li		$ivp,0				# don't chain the tweak
+	b		Lxts_dec
+
+Lxts_dec_no_key2:
+	neg		$idx,$len
+	andi.		$idx,$idx,15
+	add		$len,$len,$idx			# in "tweak chaining"
+							# mode only complete
+							# blocks are processed
+Lxts_dec:
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+
+	?lvsl		$keyperm,0,$key1		# prepare for unaligned key
+	lwz		$rounds,240($key1)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	vslb		$eighty7,$seven,$seven		# 0x808080..80
+	vor		$eighty7,$eighty7,$seven	# 0x878787..87
+	vspltisb	$tmp,1				# 0x010101..01
+	vsldoi		$eighty7,$eighty7,$tmp,15	# 0x870101..01
+
+	${UCMP}i	$len,96
+	bge		_aesp8_xts_decrypt6x
+
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+	${UCMP}i	$len,16
+	blt		Ltail_xts_dec
+	be?b		Loop_xts_dec
+
+.align	5
+Loop_xts_dec:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipher	$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_dec
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak
+	vncipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+	addi		$out,$out,16
+
+	subic.		$len,$len,16
+	beq		Lxts_dec_done
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	mtctr		$rounds
+	${UCMP}i	$len,16
+	bge		Loop_xts_dec
+
+Ltail_xts_dec:
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak1,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak1,$tweak1,$tmp
+
+	subi		$inp,$inp,16
+	add		$inp,$inp,$len
+
+	vxor		$inout,$inout,$tweak		# :-(
+	vxor		$inout,$inout,$tweak1		# :-)
+
+Loop_xts_dec_short:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipher	$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_dec_short
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak1
+	vncipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	#addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+
+	lvsr		$inpperm,0,$len			# $inpperm is no longer needed
+	vxor		$inptail,$inptail,$inptail	# $inptail is no longer needed
+	vspltisb	$tmp,-1
+	vperm		$inptail,$inptail,$tmp,$inpperm
+	vsel		$inout,$inout,$output,$inptail
+
+	vxor		$rndkey0,$rndkey0,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	subi		r11,$out,1
+	mtctr		$len
+	li		$len,16
+Loop_xts_dec_steal:
+	lbzu		r0,1(r11)
+	stb		r0,16(r11)
+	bdnz		Loop_xts_dec_steal
+
+	mtctr		$rounds
+	b		Loop_xts_dec			# one more time...
+
+Lxts_dec_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_dec_ret
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_dec_ret:
+	mtspr		256,r12				# restore vrsave
+	li		r3,0
+	blr
+	.long		0
+	.byte		0,12,0x04,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_xts_decrypt,.-.${prefix}_xts_decrypt
+___
+#########################################################################
+{{	# Optimized XTS procedures					#
+my $key_=$key2;
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,3,26..31));
+    $x00=0 if ($flavour =~ /osx/);
+my ($in0,  $in1,  $in2,  $in3,  $in4,  $in5 )=map("v$_",(0..5));
+my ($out0, $out1, $out2, $out3, $out4, $out5)=map("v$_",(7,12..16));
+my ($twk0, $twk1, $twk2, $twk3, $twk4, $twk5)=map("v$_",(17..22));
+my $rndkey0="v23";	# v24-v25 rotating buffer for first found keys
+			# v26-v31 last 6 round keys
+my ($keyperm)=($out0);	# aliases with "caller", redundant assignment
+my $taillen=$x70;
+
+$code.=<<___;
+.align	5
+_aesp8_xts_encrypt6x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	mflr		r11
+	li		r7,`$FRAME+8*16+15`
+	li		r3,`$FRAME+8*16+31`
+	$PUSH		r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+	stvx		v20,r7,$sp		# ABI says so
+	addi		r7,r7,32
+	stvx		v21,r3,$sp
+	addi		r3,r3,32
+	stvx		v22,r7,$sp
+	addi		r7,r7,32
+	stvx		v23,r3,$sp
+	addi		r3,r3,32
+	stvx		v24,r7,$sp
+	addi		r7,r7,32
+	stvx		v25,r3,$sp
+	addi		r3,r3,32
+	stvx		v26,r7,$sp
+	addi		r7,r7,32
+	stvx		v27,r3,$sp
+	addi		r3,r3,32
+	stvx		v28,r7,$sp
+	addi		r7,r7,32
+	stvx		v29,r3,$sp
+	addi		r3,r3,32
+	stvx		v30,r7,$sp
+	stvx		v31,r3,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	subi		$rounds,$rounds,3	# -4 in total
+
+	lvx		$rndkey0,$x00,$key1	# load key schedule
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	lvx		v31,$x00,$key1
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_xts_enc_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key1
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_xts_enc_key
+
+	lvx		v26,$x10,$key1
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key1
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key1
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key1
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key1
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key1
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$twk5,$x70,$key1	# borrow $twk5
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$twk5,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	 vperm		$in0,$inout,$inptail,$inpperm
+	 subi		$inp,$inp,31		# undo "caller"
+	vxor		$twk0,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out0,$in0,$twk0
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in1,$x10,$inp
+	vxor		$twk1,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in1,$in1,$in1,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out1,$in1,$twk1
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in2,$x20,$inp
+	 andi.		$taillen,$len,15
+	vxor		$twk2,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in2,$in2,$in2,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out2,$in2,$twk2
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in3,$x30,$inp
+	 sub		$len,$len,$taillen
+	vxor		$twk3,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in3,$in3,$in3,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out3,$in3,$twk3
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in4,$x40,$inp
+	 subi		$len,$len,0x60
+	vxor		$twk4,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in4,$in4,$in4,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out4,$in4,$twk4
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	vxor		$twk5,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in5,$in5,$in5,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out5,$in5,$twk5
+	vxor		$tweak,$tweak,$tmp
+
+	vxor		v31,v31,$rndkey0
+	mtctr		$rounds
+	b		Loop_xts_enc6x
+
+.align	5
+Loop_xts_enc6x:
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+	vcipher		$out5,$out5,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	vcipher		$out5,$out5,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_enc6x
+
+	subic		$len,$len,96		# $len-=96
+	 vxor		$in0,$twk0,v31		# xor with last round key
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk0,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out4,$out4,v24
+	vcipher		$out5,$out5,v24
+
+	subfe.		r0,r0,r0		# borrow?-1:0
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	 vxor		$in1,$twk1,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk1,$tweak,$rndkey0
+	vcipher		$out4,$out4,v25
+	vcipher		$out5,$out5,v25
+
+	and		r0,r0,$len
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out0,$out0,v26
+	vcipher		$out1,$out1,v26
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out2,$out2,v26
+	vcipher		$out3,$out3,v26
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out4,$out4,v26
+	vcipher		$out5,$out5,v26
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in5 are loaded
+						# with last "words"
+	 vxor		$in2,$twk2,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk2,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out0,$out0,v27
+	vcipher		$out1,$out1,v27
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out2,$out2,v27
+	vcipher		$out3,$out3,v27
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out4,$out4,v27
+	vcipher		$out5,$out5,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out0,$out0,v28
+	vcipher		$out1,$out1,v28
+	 vxor		$in3,$twk3,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk3,$tweak,$rndkey0
+	vcipher		$out2,$out2,v28
+	vcipher		$out3,$out3,v28
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out4,$out4,v28
+	vcipher		$out5,$out5,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vand		$tmp,$tmp,$eighty7
+
+	vcipher		$out0,$out0,v29
+	vcipher		$out1,$out1,v29
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out2,$out2,v29
+	vcipher		$out3,$out3,v29
+	 vxor		$in4,$twk4,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk4,$tweak,$rndkey0
+	vcipher		$out4,$out4,v29
+	vcipher		$out5,$out5,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+
+	vcipher		$out0,$out0,v30
+	vcipher		$out1,$out1,v30
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out2,$out2,v30
+	vcipher		$out3,$out3,v30
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out4,$out4,v30
+	vcipher		$out5,$out5,v30
+	 vxor		$in5,$twk5,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk5,$tweak,$rndkey0
+
+	vcipherlast	$out0,$out0,$in0
+	 lvx_u		$in0,$x00,$inp		# load next input block
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipherlast	$out1,$out1,$in1
+	 lvx_u		$in1,$x10,$inp
+	vcipherlast	$out2,$out2,$in2
+	 le?vperm	$in0,$in0,$in0,$leperm
+	 lvx_u		$in2,$x20,$inp
+	 vand		$tmp,$tmp,$eighty7
+	vcipherlast	$out3,$out3,$in3
+	 le?vperm	$in1,$in1,$in1,$leperm
+	 lvx_u		$in3,$x30,$inp
+	vcipherlast	$out4,$out4,$in4
+	 le?vperm	$in2,$in2,$in2,$leperm
+	 lvx_u		$in4,$x40,$inp
+	 vxor		$tweak,$tweak,$tmp
+	vcipherlast	$tmp,$out5,$in5		# last block might be needed
+						# in stealing mode
+	 le?vperm	$in3,$in3,$in3,$leperm
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	 le?vperm	$in4,$in4,$in4,$leperm
+	 le?vperm	$in5,$in5,$in5,$leperm
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	 vxor		$out0,$in0,$twk0
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	 vxor		$out1,$in1,$twk1
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	 vxor		$out2,$in2,$twk2
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	 vxor		$out3,$in3,$twk3
+	le?vperm	$out5,$tmp,$tmp,$leperm
+	stvx_u		$out4,$x40,$out
+	 vxor		$out4,$in4,$twk4
+	le?stvx_u	$out5,$x50,$out
+	be?stvx_u	$tmp, $x50,$out
+	 vxor		$out5,$in5,$twk5
+	addi		$out,$out,0x60
+
+	mtctr		$rounds
+	beq		Loop_xts_enc6x		# did $len-=96 borrow?
+
+	addic.		$len,$len,0x60
+	beq		Lxts_enc6x_zero
+	cmpwi		$len,0x20
+	blt		Lxts_enc6x_one
+	nop
+	beq		Lxts_enc6x_two
+	cmpwi		$len,0x40
+	blt		Lxts_enc6x_three
+	nop
+	beq		Lxts_enc6x_four
+
+Lxts_enc6x_five:
+	vxor		$out0,$in1,$twk0
+	vxor		$out1,$in2,$twk1
+	vxor		$out2,$in3,$twk2
+	vxor		$out3,$in4,$twk3
+	vxor		$out4,$in5,$twk4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk5		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	vxor		$tmp,$out4,$twk5	# last block prep for stealing
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	stvx_u		$out4,$x40,$out
+	addi		$out,$out,0x50
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_four:
+	vxor		$out0,$in2,$twk0
+	vxor		$out1,$in3,$twk1
+	vxor		$out2,$in4,$twk2
+	vxor		$out3,$in5,$twk3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk4		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	vxor		$tmp,$out3,$twk4	# last block prep for stealing
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	stvx_u		$out3,$x30,$out
+	addi		$out,$out,0x40
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_three:
+	vxor		$out0,$in3,$twk0
+	vxor		$out1,$in4,$twk1
+	vxor		$out2,$in5,$twk2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk3		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$tmp,$out2,$twk3	# last block prep for stealing
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	stvx_u		$out2,$x20,$out
+	addi		$out,$out,0x30
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_two:
+	vxor		$out0,$in4,$twk0
+	vxor		$out1,$in5,$twk1
+	vxor		$out2,$out2,$out2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk2		# unused tweak
+	vxor		$tmp,$out1,$twk2	# last block prep for stealing
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	stvx_u		$out1,$x10,$out
+	addi		$out,$out,0x20
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_one:
+	vxor		$out0,$in5,$twk0
+	nop
+Loop_xts_enc1x:
+	vcipher		$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_enc1x
+
+	add		$inp,$inp,$taillen
+	cmpwi		$taillen,0
+	vcipher		$out0,$out0,v24
+
+	subi		$inp,$inp,16
+	vcipher		$out0,$out0,v25
+
+	lvsr		$inpperm,0,$taillen
+	vcipher		$out0,$out0,v26
+
+	lvx_u		$in0,0,$inp
+	vcipher		$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vcipher		$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vcipher		$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk0,$twk0,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vcipher		$out0,$out0,v30
+
+	vperm		$in0,$in0,$in0,$inpperm
+	vcipherlast	$out0,$out0,$twk0
+
+	vmr		$twk0,$twk1		# unused tweak
+	vxor		$tmp,$out0,$twk1	# last block prep for stealing
+	le?vperm	$out0,$out0,$out0,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	addi		$out,$out,0x10
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_zero:
+	cmpwi		$taillen,0
+	beq		Lxts_enc6x_done
+
+	add		$inp,$inp,$taillen
+	subi		$inp,$inp,16
+	lvx_u		$in0,0,$inp
+	lvsr		$inpperm,0,$taillen	# $in5 is no more
+	le?vperm	$in0,$in0,$in0,$leperm
+	vperm		$in0,$in0,$in0,$inpperm
+	vxor		$tmp,$tmp,$twk0
+Lxts_enc6x_steal:
+	vxor		$in0,$in0,$twk0
+	vxor		$out0,$out0,$out0
+	vspltisb	$out1,-1
+	vperm		$out0,$out0,$out1,$inpperm
+	vsel		$out0,$in0,$tmp,$out0	# $tmp is last block, remember?
+
+	subi		r30,$out,17
+	subi		$out,$out,16
+	mtctr		$taillen
+Loop_xts_enc6x_steal:
+	lbzu		r0,1(r30)
+	stb		r0,16(r30)
+	bdnz		Loop_xts_enc6x_steal
+
+	li		$taillen,0
+	mtctr		$rounds
+	b		Loop_xts_enc1x		# one more time...
+
+.align	4
+Lxts_enc6x_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_enc6x_ret
+
+	vxor		$tweak,$twk0,$rndkey0
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_enc6x_ret:
+	mtlr		r11
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$seven,r10,$sp		# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x04,1,0x80,6,6,0
+	.long		0
+
+.align	5
+_aesp8_xts_enc5x:
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		_aesp8_xts_enc5x
+
+	add		$inp,$inp,$taillen
+	cmpwi		$taillen,0
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+
+	subi		$inp,$inp,16
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	 vxor		$twk0,$twk0,v31
+
+	vcipher		$out0,$out0,v26
+	lvsr		$inpperm,r0,$taillen	# $in5 is no more
+	vcipher		$out1,$out1,v26
+	vcipher		$out2,$out2,v26
+	vcipher		$out3,$out3,v26
+	vcipher		$out4,$out4,v26
+	 vxor		$in1,$twk1,v31
+
+	vcipher		$out0,$out0,v27
+	lvx_u		$in0,0,$inp
+	vcipher		$out1,$out1,v27
+	vcipher		$out2,$out2,v27
+	vcipher		$out3,$out3,v27
+	vcipher		$out4,$out4,v27
+	 vxor		$in2,$twk2,v31
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vcipher		$out0,$out0,v28
+	vcipher		$out1,$out1,v28
+	vcipher		$out2,$out2,v28
+	vcipher		$out3,$out3,v28
+	vcipher		$out4,$out4,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vxor		$in3,$twk3,v31
+
+	vcipher		$out0,$out0,v29
+	le?vperm	$in0,$in0,$in0,$leperm
+	vcipher		$out1,$out1,v29
+	vcipher		$out2,$out2,v29
+	vcipher		$out3,$out3,v29
+	vcipher		$out4,$out4,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$in4,$twk4,v31
+
+	vcipher		$out0,$out0,v30
+	vperm		$in0,$in0,$in0,$inpperm
+	vcipher		$out1,$out1,v30
+	vcipher		$out2,$out2,v30
+	vcipher		$out3,$out3,v30
+	vcipher		$out4,$out4,v30
+
+	vcipherlast	$out0,$out0,$twk0
+	vcipherlast	$out1,$out1,$in1
+	vcipherlast	$out2,$out2,$in2
+	vcipherlast	$out3,$out3,$in3
+	vcipherlast	$out4,$out4,$in4
+	blr
+        .long   	0
+        .byte   	0,12,0x14,0,0,0,0,0
+
+.align	5
+_aesp8_xts_decrypt6x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	mflr		r11
+	li		r7,`$FRAME+8*16+15`
+	li		r3,`$FRAME+8*16+31`
+	$PUSH		r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+	stvx		v20,r7,$sp		# ABI says so
+	addi		r7,r7,32
+	stvx		v21,r3,$sp
+	addi		r3,r3,32
+	stvx		v22,r7,$sp
+	addi		r7,r7,32
+	stvx		v23,r3,$sp
+	addi		r3,r3,32
+	stvx		v24,r7,$sp
+	addi		r7,r7,32
+	stvx		v25,r3,$sp
+	addi		r3,r3,32
+	stvx		v26,r7,$sp
+	addi		r7,r7,32
+	stvx		v27,r3,$sp
+	addi		r3,r3,32
+	stvx		v28,r7,$sp
+	addi		r7,r7,32
+	stvx		v29,r3,$sp
+	addi		r3,r3,32
+	stvx		v30,r7,$sp
+	stvx		v31,r3,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	subi		$rounds,$rounds,3	# -4 in total
+
+	lvx		$rndkey0,$x00,$key1	# load key schedule
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	lvx		v31,$x00,$key1
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_xts_dec_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key1
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_xts_dec_key
+
+	lvx		v26,$x10,$key1
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key1
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key1
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key1
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key1
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key1
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$twk5,$x70,$key1	# borrow $twk5
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$twk5,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	 vperm		$in0,$inout,$inptail,$inpperm
+	 subi		$inp,$inp,31		# undo "caller"
+	vxor		$twk0,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out0,$in0,$twk0
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in1,$x10,$inp
+	vxor		$twk1,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in1,$in1,$in1,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out1,$in1,$twk1
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in2,$x20,$inp
+	 andi.		$taillen,$len,15
+	vxor		$twk2,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in2,$in2,$in2,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out2,$in2,$twk2
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in3,$x30,$inp
+	 sub		$len,$len,$taillen
+	vxor		$twk3,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in3,$in3,$in3,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out3,$in3,$twk3
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in4,$x40,$inp
+	 subi		$len,$len,0x60
+	vxor		$twk4,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in4,$in4,$in4,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out4,$in4,$twk4
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	vxor		$twk5,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in5,$in5,$in5,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out5,$in5,$twk5
+	vxor		$tweak,$tweak,$tmp
+
+	vxor		v31,v31,$rndkey0
+	mtctr		$rounds
+	b		Loop_xts_dec6x
+
+.align	5
+Loop_xts_dec6x:
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_dec6x
+
+	subic		$len,$len,96		# $len-=96
+	 vxor		$in0,$twk0,v31		# xor with last round key
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk0,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+
+	subfe.		r0,r0,r0		# borrow?-1:0
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	 vxor		$in1,$twk1,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk1,$tweak,$rndkey0
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+
+	and		r0,r0,$len
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out0,$out0,v26
+	vncipher	$out1,$out1,v26
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out4,$out4,v26
+	vncipher	$out5,$out5,v26
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in5 are loaded
+						# with last "words"
+	 vxor		$in2,$twk2,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk2,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out0,$out0,v27
+	vncipher	$out1,$out1,v27
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out4,$out4,v27
+	vncipher	$out5,$out5,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out0,$out0,v28
+	vncipher	$out1,$out1,v28
+	 vxor		$in3,$twk3,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk3,$tweak,$rndkey0
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out4,$out4,v28
+	vncipher	$out5,$out5,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vand		$tmp,$tmp,$eighty7
+
+	vncipher	$out0,$out0,v29
+	vncipher	$out1,$out1,v29
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	 vxor		$in4,$twk4,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk4,$tweak,$rndkey0
+	vncipher	$out4,$out4,v29
+	vncipher	$out5,$out5,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+
+	vncipher	$out0,$out0,v30
+	vncipher	$out1,$out1,v30
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out2,$out2,v30
+	vncipher	$out3,$out3,v30
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out4,$out4,v30
+	vncipher	$out5,$out5,v30
+	 vxor		$in5,$twk5,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk5,$tweak,$rndkey0
+
+	vncipherlast	$out0,$out0,$in0
+	 lvx_u		$in0,$x00,$inp		# load next input block
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipherlast	$out1,$out1,$in1
+	 lvx_u		$in1,$x10,$inp
+	vncipherlast	$out2,$out2,$in2
+	 le?vperm	$in0,$in0,$in0,$leperm
+	 lvx_u		$in2,$x20,$inp
+	 vand		$tmp,$tmp,$eighty7
+	vncipherlast	$out3,$out3,$in3
+	 le?vperm	$in1,$in1,$in1,$leperm
+	 lvx_u		$in3,$x30,$inp
+	vncipherlast	$out4,$out4,$in4
+	 le?vperm	$in2,$in2,$in2,$leperm
+	 lvx_u		$in4,$x40,$inp
+	 vxor		$tweak,$tweak,$tmp
+	vncipherlast	$out5,$out5,$in5
+	 le?vperm	$in3,$in3,$in3,$leperm
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	 le?vperm	$in4,$in4,$in4,$leperm
+	 le?vperm	$in5,$in5,$in5,$leperm
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	 vxor		$out0,$in0,$twk0
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	 vxor		$out1,$in1,$twk1
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	 vxor		$out2,$in2,$twk2
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	 vxor		$out3,$in3,$twk3
+	le?vperm	$out5,$out5,$out5,$leperm
+	stvx_u		$out4,$x40,$out
+	 vxor		$out4,$in4,$twk4
+	stvx_u		$out5,$x50,$out
+	 vxor		$out5,$in5,$twk5
+	addi		$out,$out,0x60
+
+	mtctr		$rounds
+	beq		Loop_xts_dec6x		# did $len-=96 borrow?
+
+	addic.		$len,$len,0x60
+	beq		Lxts_dec6x_zero
+	cmpwi		$len,0x20
+	blt		Lxts_dec6x_one
+	nop
+	beq		Lxts_dec6x_two
+	cmpwi		$len,0x40
+	blt		Lxts_dec6x_three
+	nop
+	beq		Lxts_dec6x_four
+
+Lxts_dec6x_five:
+	vxor		$out0,$in1,$twk0
+	vxor		$out1,$in2,$twk1
+	vxor		$out2,$in3,$twk2
+	vxor		$out3,$in4,$twk3
+	vxor		$out4,$in5,$twk4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk5		# unused tweak
+	vxor		$twk1,$tweak,$rndkey0
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk1
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	stvx_u		$out4,$x40,$out
+	addi		$out,$out,0x50
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_four:
+	vxor		$out0,$in2,$twk0
+	vxor		$out1,$in3,$twk1
+	vxor		$out2,$in4,$twk2
+	vxor		$out3,$in5,$twk3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk4		# unused tweak
+	vmr		$twk1,$twk5
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk5
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	stvx_u		$out3,$x30,$out
+	addi		$out,$out,0x40
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_three:
+	vxor		$out0,$in3,$twk0
+	vxor		$out1,$in4,$twk1
+	vxor		$out2,$in5,$twk2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk3		# unused tweak
+	vmr		$twk1,$twk4
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk4
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	stvx_u		$out2,$x20,$out
+	addi		$out,$out,0x30
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_two:
+	vxor		$out0,$in4,$twk0
+	vxor		$out1,$in5,$twk1
+	vxor		$out2,$out2,$out2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk2		# unused tweak
+	vmr		$twk1,$twk3
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk3
+	stvx_u		$out1,$x10,$out
+	addi		$out,$out,0x20
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_one:
+	vxor		$out0,$in5,$twk0
+	nop
+Loop_xts_dec1x:
+	vncipher	$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_dec1x
+
+	subi		r0,$taillen,1
+	vncipher	$out0,$out0,v24
+
+	andi.		r0,r0,16
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+
+	sub		$inp,$inp,r0
+	vncipher	$out0,$out0,v26
+
+	lvx_u		$in0,0,$inp
+	vncipher	$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vncipher	$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk0,$twk0,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out0,$out0,v30
+
+	mtctr		$rounds
+	vncipherlast	$out0,$out0,$twk0
+
+	vmr		$twk0,$twk1		# unused tweak
+	vmr		$twk1,$twk2
+	le?vperm	$out0,$out0,$out0,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	addi		$out,$out,0x10
+	vxor		$out0,$in0,$twk2
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_zero:
+	cmpwi		$taillen,0
+	beq		Lxts_dec6x_done
+
+	lvx_u		$in0,0,$inp
+	le?vperm	$in0,$in0,$in0,$leperm
+	vxor		$out0,$in0,$twk1
+Lxts_dec6x_steal:
+	vncipher	$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Lxts_dec6x_steal
+
+	add		$inp,$inp,$taillen
+	vncipher	$out0,$out0,v24
+
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+
+	lvx_u		$in0,0,$inp
+	vncipher	$out0,$out0,v26
+
+	lvsr		$inpperm,0,$taillen	# $in5 is no more
+	vncipher	$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vncipher	$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk1,$twk1,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out0,$out0,v30
+
+	vperm		$in0,$in0,$in0,$inpperm
+	vncipherlast	$tmp,$out0,$twk1
+
+	le?vperm	$out0,$tmp,$tmp,$leperm
+	le?stvx_u	$out0,0,$out
+	be?stvx_u	$tmp,0,$out
+
+	vxor		$out0,$out0,$out0
+	vspltisb	$out1,-1
+	vperm		$out0,$out0,$out1,$inpperm
+	vsel		$out0,$in0,$tmp,$out0
+	vxor		$out0,$out0,$twk0
+
+	subi		r30,$out,1
+	mtctr		$taillen
+Loop_xts_dec6x_steal:
+	lbzu		r0,1(r30)
+	stb		r0,16(r30)
+	bdnz		Loop_xts_dec6x_steal
+
+	li		$taillen,0
+	mtctr		$rounds
+	b		Loop_xts_dec1x		# one more time...
+
+.align	4
+Lxts_dec6x_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_dec6x_ret
+
+	vxor		$tweak,$twk0,$rndkey0
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_dec6x_ret:
+	mtlr		r11
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$seven,r10,$sp		# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x04,1,0x80,6,6,0
+	.long		0
+
+.align	5
+_aesp8_xts_dec5x:
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		_aesp8_xts_dec5x
+
+	subi		r0,$taillen,1
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+
+	andi.		r0,r0,16
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	 vxor		$twk0,$twk0,v31
+
+	sub		$inp,$inp,r0
+	vncipher	$out0,$out0,v26
+	vncipher	$out1,$out1,v26
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	vncipher	$out4,$out4,v26
+	 vxor		$in1,$twk1,v31
+
+	vncipher	$out0,$out0,v27
+	lvx_u		$in0,0,$inp
+	vncipher	$out1,$out1,v27
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	vncipher	$out4,$out4,v27
+	 vxor		$in2,$twk2,v31
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	vncipher	$out1,$out1,v28
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	vncipher	$out4,$out4,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vxor		$in3,$twk3,v31
+
+	vncipher	$out0,$out0,v29
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out1,$out1,v29
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	vncipher	$out4,$out4,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$in4,$twk4,v31
+
+	vncipher	$out0,$out0,v30
+	vncipher	$out1,$out1,v30
+	vncipher	$out2,$out2,v30
+	vncipher	$out3,$out3,v30
+	vncipher	$out4,$out4,v30
+
+	vncipherlast	$out0,$out0,$twk0
+	vncipherlast	$out1,$out1,$in1
+	vncipherlast	$out2,$out2,$in2
+	vncipherlast	$out3,$out3,$in3
+	vncipherlast	$out4,$out4,$in4
+	mtctr		$rounds
+	blr
+        .long   	0
+        .byte   	0,12,0x14,0,0,0,0,0
+___
+}}	}}}
+
 my $consts=1;
 foreach(split("\n",$code)) {
         s/\`([^\`]*)\`/eval($1)/geo;
@@ -1898,7 +3757,7 @@ foreach(split("\n",$code)) {
 	    if ($flavour =~ /le$/o) {
 		SWITCH: for($conv)  {
 		    /\?inv/ && do   { @bytes=map($_^0xf,@bytes); last; };
-		    /\?rev/ && do   { @bytes=reverse(@bytes);    last; }; 
+		    /\?rev/ && do   { @bytes=reverse(@bytes);    last; };
 		}
 	    }
 
diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c
index e163d5770438..f688c32fbcc7 100644
--- a/drivers/crypto/vmx/vmx.c
+++ b/drivers/crypto/vmx/vmx.c
@@ -31,10 +31,12 @@ extern struct shash_alg p8_ghash_alg;
 extern struct crypto_alg p8_aes_alg;
 extern struct crypto_alg p8_aes_cbc_alg;
 extern struct crypto_alg p8_aes_ctr_alg;
+extern struct crypto_alg p8_aes_xts_alg;
 static struct crypto_alg *algs[] = {
 	&p8_aes_alg,
 	&p8_aes_cbc_alg,
 	&p8_aes_ctr_alg,
+	&p8_aes_xts_alg,
 	NULL,
 };
 
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index 78dac0e9da11..a5be56ec57f2 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -75,7 +75,7 @@ config DEVFREQ_GOV_PASSIVE
 comment "DEVFREQ Drivers"
 
 config ARM_EXYNOS_BUS_DEVFREQ
-	bool "ARM EXYNOS Generic Memory Bus DEVFREQ Driver"
+	tristate "ARM EXYNOS Generic Memory Bus DEVFREQ Driver"
 	depends on ARCH_EXYNOS
 	select DEVFREQ_GOV_SIMPLE_ONDEMAND
 	select DEVFREQ_GOV_PASSIVE
diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index 39b048eda2ce..9aea2c7ecbe6 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/err.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/of.h>
@@ -481,13 +481,3 @@ static int __init devfreq_event_init(void)
 	return 0;
 }
 subsys_initcall(devfreq_event_init);
-
-static void __exit devfreq_event_exit(void)
-{
-	class_destroy(devfreq_event_class);
-}
-module_exit(devfreq_event_exit);
-
-MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
-MODULE_DESCRIPTION("DEVFREQ-Event class support");
-MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e92418facc92..478006b7764a 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -15,7 +15,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/pm_opp.h>
@@ -707,10 +707,12 @@ struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
 		if (devfreq->dev.parent
 			&& devfreq->dev.parent->of_node == node) {
 			mutex_unlock(&devfreq_list_lock);
+			of_node_put(node);
 			return devfreq;
 		}
 	}
 	mutex_unlock(&devfreq_list_lock);
+	of_node_put(node);
 
 	return ERR_PTR(-EPROBE_DEFER);
 }
@@ -1199,13 +1201,6 @@ static int __init devfreq_init(void)
 }
 subsys_initcall(devfreq_init);
 
-static void __exit devfreq_exit(void)
-{
-	class_destroy(devfreq_class);
-	destroy_workqueue(devfreq_wq);
-}
-module_exit(devfreq_exit);
-
 /*
  * The followings are helper functions for devfreq user device drivers with
  * OPP framework.
@@ -1471,7 +1466,3 @@ void devm_devfreq_unregister_notifier(struct device *dev,
 			       devm_devfreq_dev_match, devfreq));
 }
 EXPORT_SYMBOL(devm_devfreq_unregister_notifier);
-
-MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
-MODULE_DESCRIPTION("devfreq class support");
-MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig
index 1e8b4f469f38..eb6f74a2b6b9 100644
--- a/drivers/devfreq/event/Kconfig
+++ b/drivers/devfreq/event/Kconfig
@@ -14,7 +14,7 @@ menuconfig PM_DEVFREQ_EVENT
 if PM_DEVFREQ_EVENT
 
 config DEVFREQ_EVENT_EXYNOS_NOCP
-	bool "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver"
+	tristate "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver"
 	depends on ARCH_EXYNOS
 	select PM_OPP
 	help
@@ -22,7 +22,7 @@ config DEVFREQ_EVENT_EXYNOS_NOCP
 	  (Network on Chip) Probe counters to measure the bandwidth of AXI bus.
 
 config DEVFREQ_EVENT_EXYNOS_PPMU
-	bool "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver"
+	tristate "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver"
 	depends on ARCH_EXYNOS
 	select PM_OPP
 	help
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index f312485f1451..845bf25fb9fb 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -482,7 +482,8 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	if (!info->edev) {
 		dev_err(&pdev->dev,
 			"failed to allocate memory devfreq-event devices\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err;
 	}
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 2363d0a189b7..29866f7e6d7e 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -383,7 +383,7 @@ err_clk:
 static int exynos_bus_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
+	struct device_node *np = dev->of_node, *node;
 	struct devfreq_dev_profile *profile;
 	struct devfreq_simple_ondemand_data *ondemand_data;
 	struct devfreq_passive_data *passive_data;
@@ -407,7 +407,7 @@ static int exynos_bus_probe(struct platform_device *pdev)
 	/* Parse the device-tree to get the resource information */
 	ret = exynos_bus_parse_of(np, bus);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	profile = devm_kzalloc(dev, sizeof(*profile), GFP_KERNEL);
 	if (!profile) {
@@ -415,10 +415,13 @@ static int exynos_bus_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	if (of_parse_phandle(dev->of_node, "devfreq", 0))
+	node = of_parse_phandle(dev->of_node, "devfreq", 0);
+	if (node) {
+		of_node_put(node);
 		goto passive;
-	else
+	} else {
 		ret = exynos_bus_parent_parse_of(np, bus);
+	}
 
 	if (ret < 0)
 		goto err;
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index eac76a79a880..30a24d09ea6c 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -34,6 +34,7 @@ struct pstore_read_data {
 	int *count;
 	struct timespec *timespec;
 	bool *compressed;
+	ssize_t *ecc_notice_size;
 	char **buf;
 };
 
@@ -69,6 +70,7 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 			*cb_data->compressed = true;
 		else
 			*cb_data->compressed = false;
+		*cb_data->ecc_notice_size = 0;
 	} else if (sscanf(name, "dump-type%u-%u-%d-%lu",
 		   cb_data->type, &part, &cnt, &time) == 4) {
 		*cb_data->id = generic_id(time, part, cnt);
@@ -76,6 +78,7 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 		cb_data->timespec->tv_sec = time;
 		cb_data->timespec->tv_nsec = 0;
 		*cb_data->compressed = false;
+		*cb_data->ecc_notice_size = 0;
 	} else if (sscanf(name, "dump-type%u-%u-%lu",
 			  cb_data->type, &part, &time) == 3) {
 		/*
@@ -88,6 +91,7 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 		cb_data->timespec->tv_sec = time;
 		cb_data->timespec->tv_nsec = 0;
 		*cb_data->compressed = false;
+		*cb_data->ecc_notice_size = 0;
 	} else
 		return 0;
 
@@ -210,6 +214,7 @@ static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
 static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 			       int *count, struct timespec *timespec,
 			       char **buf, bool *compressed,
+			       ssize_t *ecc_notice_size,
 			       struct pstore_info *psi)
 {
 	struct pstore_read_data data;
@@ -220,6 +225,7 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 	data.count = count;
 	data.timespec = timespec;
 	data.compressed = compressed;
+	data.ecc_notice_size = ecc_notice_size;
 	data.buf = buf;
 
 	*data.buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
@@ -393,6 +399,13 @@ static __init int efivars_pstore_init(void)
 
 static __exit void efivars_pstore_exit(void)
 {
+	if (!efi_pstore_info.bufsize)
+		return;
+
+	pstore_unregister(&efi_pstore_info);
+	kfree(efi_pstore_info.buf);
+	efi_pstore_info.buf = NULL;
+	efi_pstore_info.bufsize = 0;
 }
 
 module_init(efivars_pstore_init);
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 05509f3aaee8..8730fd475bf3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -24,6 +24,9 @@
 #include <linux/of_fdt.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/acpi.h>
+#include <linux/ucs2_string.h>
 
 #include <asm/early_ioremap.h>
 
@@ -195,6 +198,96 @@ static void generic_ops_unregister(void)
 	efivars_unregister(&generic_efivars);
 }
 
+#if IS_ENABLED(CONFIG_ACPI)
+#define EFIVAR_SSDT_NAME_MAX	16
+static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata;
+static int __init efivar_ssdt_setup(char *str)
+{
+	if (strlen(str) < sizeof(efivar_ssdt))
+		memcpy(efivar_ssdt, str, strlen(str));
+	else
+		pr_warn("efivar_ssdt: name too long: %s\n", str);
+	return 0;
+}
+__setup("efivar_ssdt=", efivar_ssdt_setup);
+
+static __init int efivar_ssdt_iter(efi_char16_t *name, efi_guid_t vendor,
+				   unsigned long name_size, void *data)
+{
+	struct efivar_entry *entry;
+	struct list_head *list = data;
+	char utf8_name[EFIVAR_SSDT_NAME_MAX];
+	int limit = min_t(unsigned long, EFIVAR_SSDT_NAME_MAX, name_size);
+
+	ucs2_as_utf8(utf8_name, name, limit - 1);
+	if (strncmp(utf8_name, efivar_ssdt, limit) != 0)
+		return 0;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return 0;
+
+	memcpy(entry->var.VariableName, name, name_size);
+	memcpy(&entry->var.VendorGuid, &vendor, sizeof(efi_guid_t));
+
+	efivar_entry_add(entry, list);
+
+	return 0;
+}
+
+static __init int efivar_ssdt_load(void)
+{
+	LIST_HEAD(entries);
+	struct efivar_entry *entry, *aux;
+	unsigned long size;
+	void *data;
+	int ret;
+
+	ret = efivar_init(efivar_ssdt_iter, &entries, true, &entries);
+
+	list_for_each_entry_safe(entry, aux, &entries, list) {
+		pr_info("loading SSDT from variable %s-%pUl\n", efivar_ssdt,
+			&entry->var.VendorGuid);
+
+		list_del(&entry->list);
+
+		ret = efivar_entry_size(entry, &size);
+		if (ret) {
+			pr_err("failed to get var size\n");
+			goto free_entry;
+		}
+
+		data = kmalloc(size, GFP_KERNEL);
+		if (!data)
+			goto free_entry;
+
+		ret = efivar_entry_get(entry, NULL, &size, data);
+		if (ret) {
+			pr_err("failed to get var data\n");
+			goto free_data;
+		}
+
+		ret = acpi_load_table(data);
+		if (ret) {
+			pr_err("failed to load table: %d\n", ret);
+			goto free_data;
+		}
+
+		goto free_entry;
+
+free_data:
+		kfree(data);
+
+free_entry:
+		kfree(entry);
+	}
+
+	return ret;
+}
+#else
+static inline int efivar_ssdt_load(void) { return 0; }
+#endif
+
 /*
  * We register the efi subsystem with the firmware subsystem and the
  * efivars subsystem with the efi subsystem, if the system was booted with
@@ -218,6 +311,9 @@ static int __init efisubsys_init(void)
 	if (error)
 		goto err_put;
 
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		efivar_ssdt_load();
+
 	error = sysfs_create_group(efi_kobj, &efi_subsys_attr_group);
 	if (error) {
 		pr_err("efi: Sysfs attribute export failed with error %d.\n",
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index 03e04582791c..8263429e21b8 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -13,6 +13,7 @@
 
 #define pr_fmt(fmt) "psci: " fmt
 
+#include <linux/acpi.h>
 #include <linux/arm-smccc.h>
 #include <linux/cpuidle.h>
 #include <linux/errno.h>
@@ -256,13 +257,6 @@ static int psci_dt_cpu_init_idle(struct device_node *cpu_node, int cpu)
 	u32 *psci_states;
 	struct device_node *state_node;
 
-	/*
-	 * If the PSCI cpu_suspend function hook has not been initialized
-	 * idle states must not be enabled, so bail out
-	 */
-	if (!psci_ops.cpu_suspend)
-		return -EOPNOTSUPP;
-
 	/* Count idle states */
 	while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
 					      count))) {
@@ -310,11 +304,69 @@ free_mem:
 	return ret;
 }
 
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+
+static int __maybe_unused psci_acpi_cpu_init_idle(unsigned int cpu)
+{
+	int i, count;
+	u32 *psci_states;
+	struct acpi_lpi_state *lpi;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+
+	if (unlikely(!pr || !pr->flags.has_lpi))
+		return -EINVAL;
+
+	count = pr->power.count - 1;
+	if (count <= 0)
+		return -ENODEV;
+
+	psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL);
+	if (!psci_states)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		u32 state;
+
+		lpi = &pr->power.lpi_states[i + 1];
+		/*
+		 * Only bits[31:0] represent a PSCI power_state while
+		 * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification
+		 */
+		state = lpi->address;
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			kfree(psci_states);
+			return -EINVAL;
+		}
+		psci_states[i] = state;
+	}
+	/* Idle states parsed correctly, initialize per-cpu pointer */
+	per_cpu(psci_power_state, cpu) = psci_states;
+	return 0;
+}
+#else
+static int __maybe_unused psci_acpi_cpu_init_idle(unsigned int cpu)
+{
+	return -EINVAL;
+}
+#endif
+
 int psci_cpu_init_idle(unsigned int cpu)
 {
 	struct device_node *cpu_node;
 	int ret;
 
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	if (!acpi_disabled)
+		return psci_acpi_cpu_init_idle(cpu);
+
 	cpu_node = of_get_cpu_node(cpu, NULL);
 	if (!cpu_node)
 		return -ENODEV;
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index d7860614f87f..98dd47a30fc7 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -250,7 +250,7 @@ config GPIO_LOONGSON
 	  driver for GPIO functionality on Loongson-2F/3A/3B processors.
 
 config GPIO_LPC18XX
-	bool "NXP LPC18XX/43XX GPIO support"
+	tristate "NXP LPC18XX/43XX GPIO support"
 	default y if ARCH_LPC18XX
 	depends on OF_GPIO && (ARCH_LPC18XX || COMPILE_TEST)
 	help
@@ -874,6 +874,15 @@ config GPIO_LP3943
 	  LP3943 can be used as a GPIO expander which provides up to 16 GPIOs.
 	  Open drain outputs are required for this usage.
 
+config GPIO_MAX77620
+	tristate "GPIO support for PMIC MAX77620 and MAX20024"
+	depends on MFD_MAX77620
+	help
+	  GPIO driver for MAX77620 and MAX20024 PMIC from Maxim Semiconductor.
+	  MAX77620 PMIC has 8 pins that can be configured as GPIOs. The
+	  driver also provides interrupt support for each of the gpios.
+	  Say yes here to enable the max77620 to be used as gpio controller.
+
 config GPIO_MSIC
 	bool "Intel MSIC mixed signal gpio support"
 	depends on MFD_INTEL_MSIC
@@ -1029,11 +1038,18 @@ config GPIO_BT8XX
 	  If unsure, say N.
 
 config GPIO_INTEL_MID
-	bool "Intel Mid GPIO support"
-	depends on X86
+	bool "Intel MID GPIO support"
+	depends on X86_INTEL_MID
+	select GPIOLIB_IRQCHIP
+	help
+	  Say Y here to support Intel MID GPIO.
+
+config GPIO_MERRIFIELD
+	tristate "Intel Merrifield GPIO support"
+	depends on X86_INTEL_MID
 	select GPIOLIB_IRQCHIP
 	help
-	  Say Y here to support Intel Mid GPIO.
+	  Say Y here to support Intel Merrifield GPIO.
 
 config GPIO_ML_IOH
 	tristate "OKI SEMICONDUCTOR ML7213 IOH GPIO support"
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 991598ea3fba..2a035ed8f168 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -61,8 +61,10 @@ obj-$(CONFIG_GPIO_MAX730X)	+= gpio-max730x.o
 obj-$(CONFIG_GPIO_MAX7300)	+= gpio-max7300.o
 obj-$(CONFIG_GPIO_MAX7301)	+= gpio-max7301.o
 obj-$(CONFIG_GPIO_MAX732X)	+= gpio-max732x.o
+obj-$(CONFIG_GPIO_MAX77620)	+= gpio-max77620.o
 obj-$(CONFIG_GPIO_MB86S7X)	+= gpio-mb86s7x.o
 obj-$(CONFIG_GPIO_MENZ127)	+= gpio-menz127.o
+obj-$(CONFIG_GPIO_MERRIFIELD)	+= gpio-merrifield.o
 obj-$(CONFIG_GPIO_MC33880)	+= gpio-mc33880.o
 obj-$(CONFIG_GPIO_MC9S08DZ60)	+= gpio-mc9s08dz60.o
 obj-$(CONFIG_GPIO_MCP23S08)	+= gpio-mcp23s08.o
diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c
index 80f9ddf13343..a6607faf2fdf 100644
--- a/drivers/gpio/gpio-74x164.c
+++ b/drivers/gpio/gpio-74x164.c
@@ -35,13 +35,8 @@ struct gen_74x164_chip {
 
 static int __gen_74x164_write_config(struct gen_74x164_chip *chip)
 {
-	struct spi_transfer xfer = {
-		.tx_buf = chip->buffer,
-		.len = chip->registers,
-	};
-
-	return spi_sync_transfer(to_spi_device(chip->gpio_chip.parent),
-				 &xfer, 1);
+	return spi_write(to_spi_device(chip->gpio_chip.parent), chip->buffer,
+			 chip->registers);
 }
 
 static int gen_74x164_get_value(struct gpio_chip *gc, unsigned offset)
diff --git a/drivers/gpio/gpio-clps711x.c b/drivers/gpio/gpio-clps711x.c
index 5a690256af9b..52fd63f02134 100644
--- a/drivers/gpio/gpio-clps711x.c
+++ b/drivers/gpio/gpio-clps711x.c
@@ -20,8 +20,12 @@ static int clps711x_gpio_probe(struct platform_device *pdev)
 	void __iomem *dat, *dir;
 	struct gpio_chip *gc;
 	struct resource *res;
-	int err, id = np ? of_alias_get_id(np, "gpio") : pdev->id;
+	int err, id;
 
+	if (!np)
+		return -ENODEV;
+
+	id = of_alias_get_id(np, "gpio");
 	if ((id < 0) || (id > 4))
 		return -ENODEV;
 
@@ -63,7 +67,7 @@ static int clps711x_gpio_probe(struct platform_device *pdev)
 		break;
 	}
 
-	gc->base = id * 8;
+	gc->base = -1;
 	gc->owner = THIS_MODULE;
 	platform_set_drvdata(pdev, gc);
 
@@ -71,7 +75,7 @@ static int clps711x_gpio_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id __maybe_unused clps711x_gpio_ids[] = {
-	{ .compatible = "cirrus,clps711x-gpio" },
+	{ .compatible = "cirrus,ep7209-gpio" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, clps711x_gpio_ids);
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 34779bb375de..6193f62c0df4 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -486,6 +486,7 @@ dwapb_gpio_get_pdata(struct device *dev)
 		    pp->idx >= DWAPB_MAX_PORTS) {
 			dev_err(dev,
 				"missing/invalid port index for port%d\n", i);
+			fwnode_handle_put(fwnode);
 			return ERR_PTR(-EINVAL);
 		}
 
diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c
index 05aa538c3767..600be8418707 100644
--- a/drivers/gpio/gpio-f7188x.c
+++ b/drivers/gpio/gpio-f7188x.c
@@ -125,6 +125,7 @@ static inline void superio_exit(int base)
  * GPIO chip.
  */
 
+static int f7188x_gpio_get_direction(struct gpio_chip *chip, unsigned offset);
 static int f7188x_gpio_direction_in(struct gpio_chip *chip, unsigned offset);
 static int f7188x_gpio_get(struct gpio_chip *chip, unsigned offset);
 static int f7188x_gpio_direction_out(struct gpio_chip *chip,
@@ -139,6 +140,7 @@ static int f7188x_gpio_set_single_ended(struct gpio_chip *gc,
 		.chip = {						\
 			.label            = DRVNAME,			\
 			.owner            = THIS_MODULE,		\
+			.get_direction    = f7188x_gpio_get_direction,	\
 			.direction_input  = f7188x_gpio_direction_in,	\
 			.get              = f7188x_gpio_get,		\
 			.direction_output = f7188x_gpio_direction_out,	\
@@ -209,6 +211,26 @@ static struct f7188x_gpio_bank f81866_gpio_bank[] = {
 	F7188X_GPIO_BANK(80, 8, 0x88),
 };
 
+static int f7188x_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
+{
+	int err;
+	struct f7188x_gpio_bank *bank =
+		container_of(chip, struct f7188x_gpio_bank, chip);
+	struct f7188x_sio *sio = bank->data->sio;
+	u8 dir;
+
+	err = superio_enter(sio->addr);
+	if (err)
+		return err;
+	superio_select(sio->addr, SIO_LD_GPIO);
+
+	dir = superio_inb(sio->addr, gpio_dir(bank->regbase));
+
+	superio_exit(sio->addr);
+
+	return !(dir & 1 << offset);
+}
+
 static int f7188x_gpio_direction_in(struct gpio_chip *chip, unsigned offset)
 {
 	int err;
diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c
index cdaba13cb8e8..164de64b11fc 100644
--- a/drivers/gpio/gpio-intel-mid.c
+++ b/drivers/gpio/gpio-intel-mid.c
@@ -1,7 +1,7 @@
 /*
  * Intel MID GPIO driver
  *
- * Copyright (c) 2008-2014 Intel Corporation.
+ * Copyright (c) 2008-2014,2016 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -17,21 +17,20 @@
  * Moorestown platform Langwell chip.
  * Medfield platform Penwell chip.
  * Clovertrail platform Cloverview chip.
- * Merrifield platform Tangier chip.
  */
 
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/platform_device.h>
-#include <linux/kernel.h>
 #include <linux/delay.h>
-#include <linux/stddef.h>
-#include <linux/interrupt.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/gpio/driver.h>
-#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/stddef.h>
 
 #define INTEL_MID_IRQ_TYPE_EDGE		(1 << 0)
 #define INTEL_MID_IRQ_TYPE_LEVEL	(1 << 1)
@@ -64,10 +63,6 @@ enum GPIO_REG {
 /* intel_mid gpio driver data */
 struct intel_mid_gpio_ddata {
 	u16 ngpio;		/* number of gpio pins */
-	u32 gplr_offset;	/* offset of first GPLR register from base */
-	u32 flis_base;		/* base address of FLIS registers */
-	u32 flis_len;		/* length of FLIS registers */
-	u32 (*get_flis_offset)(int gpio);
 	u32 chip_irq_type;	/* chip interrupt type */
 };
 
@@ -252,15 +247,6 @@ static const struct intel_mid_gpio_ddata gpio_cloverview_core = {
 	.chip_irq_type = INTEL_MID_IRQ_TYPE_EDGE,
 };
 
-static const struct intel_mid_gpio_ddata gpio_tangier = {
-	.ngpio = 192,
-	.gplr_offset = 4,
-	.flis_base = 0xff0c0000,
-	.flis_len = 0x8000,
-	.get_flis_offset = NULL,
-	.chip_irq_type = INTEL_MID_IRQ_TYPE_EDGE,
-};
-
 static const struct pci_device_id intel_gpio_ids[] = {
 	{
 		/* Lincroft */
@@ -287,11 +273,6 @@ static const struct pci_device_id intel_gpio_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x08f7),
 		.driver_data = (kernel_ulong_t)&gpio_cloverview_core,
 	},
-	{
-		/* Tangier */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x1199),
-		.driver_data = (kernel_ulong_t)&gpio_tangier,
-	},
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, intel_gpio_ids);
@@ -401,7 +382,7 @@ static int intel_gpio_probe(struct pci_dev *pdev,
 	spin_lock_init(&priv->lock);
 
 	pci_set_drvdata(pdev, priv);
-	retval = gpiochip_add_data(&priv->chip, priv);
+	retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv);
 	if (retval) {
 		dev_err(&pdev->dev, "gpiochip_add error %d\n", retval);
 		return retval;
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 9df015e85ad9..fbd393b46ce0 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -383,7 +383,6 @@ static int lp_gpio_probe(struct platform_device *pdev)
 					   handle_simple_irq, IRQ_TYPE_NONE);
 		if (ret) {
 			dev_err(dev, "failed to add irqchip\n");
-			gpiochip_remove(gc);
 			return ret;
 		}
 
diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c
new file mode 100644
index 000000000000..b46b436cb97f
--- /dev/null
+++ b/drivers/gpio/gpio-max77620.c
@@ -0,0 +1,315 @@
+/*
+ * MAXIM MAX77620 GPIO driver
+ *
+ * Copyright (c) 2016, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#include <linux/gpio/driver.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/max77620.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#define GPIO_REG_ADDR(offset) (MAX77620_REG_GPIO0 + offset)
+
+struct max77620_gpio {
+	struct gpio_chip	gpio_chip;
+	struct regmap		*rmap;
+	struct device		*dev;
+	int			gpio_irq;
+	int			irq_base;
+	int			gpio_base;
+};
+
+static const struct regmap_irq max77620_gpio_irqs[] = {
+	[0] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE0,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 0,
+	},
+	[1] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE1,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 1,
+	},
+	[2] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE2,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 2,
+	},
+	[3] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE3,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 3,
+	},
+	[4] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE4,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 4,
+	},
+	[5] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE5,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 5,
+	},
+	[6] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE6,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 6,
+	},
+	[7] = {
+		.mask = MAX77620_IRQ_LVL2_GPIO_EDGE7,
+		.type_rising_mask = MAX77620_CNFG_GPIO_INT_RISING,
+		.type_falling_mask = MAX77620_CNFG_GPIO_INT_FALLING,
+		.reg_offset = 0,
+		.type_reg_offset = 7,
+	},
+};
+
+static struct regmap_irq_chip max77620_gpio_irq_chip = {
+	.name = "max77620-gpio",
+	.irqs = max77620_gpio_irqs,
+	.num_irqs = ARRAY_SIZE(max77620_gpio_irqs),
+	.num_regs = 1,
+	.num_type_reg = 8,
+	.irq_reg_stride = 1,
+	.type_reg_stride = 1,
+	.status_base = MAX77620_REG_IRQ_LVL2_GPIO,
+	.type_base = MAX77620_REG_GPIO0,
+};
+
+static int max77620_gpio_dir_input(struct gpio_chip *gc, unsigned int offset)
+{
+	struct max77620_gpio *mgpio = gpiochip_get_data(gc);
+	int ret;
+
+	ret = regmap_update_bits(mgpio->rmap, GPIO_REG_ADDR(offset),
+				 MAX77620_CNFG_GPIO_DIR_MASK,
+				 MAX77620_CNFG_GPIO_DIR_INPUT);
+	if (ret < 0)
+		dev_err(mgpio->dev, "CNFG_GPIOx dir update failed: %d\n", ret);
+
+	return ret;
+}
+
+static int max77620_gpio_get(struct gpio_chip *gc, unsigned int offset)
+{
+	struct max77620_gpio *mgpio = gpiochip_get_data(gc);
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(mgpio->rmap, GPIO_REG_ADDR(offset), &val);
+	if (ret < 0) {
+		dev_err(mgpio->dev, "CNFG_GPIOx read failed: %d\n", ret);
+		return ret;
+	}
+
+	if  (val & MAX77620_CNFG_GPIO_DIR_MASK)
+		return !!(val & MAX77620_CNFG_GPIO_INPUT_VAL_MASK);
+	else
+		return !!(val & MAX77620_CNFG_GPIO_OUTPUT_VAL_MASK);
+}
+
+static int max77620_gpio_dir_output(struct gpio_chip *gc, unsigned int offset,
+				    int value)
+{
+	struct max77620_gpio *mgpio = gpiochip_get_data(gc);
+	u8 val;
+	int ret;
+
+	val = (value) ? MAX77620_CNFG_GPIO_OUTPUT_VAL_HIGH :
+				MAX77620_CNFG_GPIO_OUTPUT_VAL_LOW;
+
+	ret = regmap_update_bits(mgpio->rmap, GPIO_REG_ADDR(offset),
+				 MAX77620_CNFG_GPIO_OUTPUT_VAL_MASK, val);
+	if (ret < 0) {
+		dev_err(mgpio->dev, "CNFG_GPIOx val update failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_update_bits(mgpio->rmap, GPIO_REG_ADDR(offset),
+				 MAX77620_CNFG_GPIO_DIR_MASK,
+				 MAX77620_CNFG_GPIO_DIR_OUTPUT);
+	if (ret < 0)
+		dev_err(mgpio->dev, "CNFG_GPIOx dir update failed: %d\n", ret);
+
+	return ret;
+}
+
+static int max77620_gpio_set_debounce(struct gpio_chip *gc,
+				      unsigned int offset,
+				      unsigned int debounce)
+{
+	struct max77620_gpio *mgpio = gpiochip_get_data(gc);
+	u8 val;
+	int ret;
+
+	switch (debounce) {
+	case 0:
+		val = MAX77620_CNFG_GPIO_DBNC_None;
+		break;
+	case 1 ... 8:
+		val = MAX77620_CNFG_GPIO_DBNC_8ms;
+		break;
+	case 9 ... 16:
+		val = MAX77620_CNFG_GPIO_DBNC_16ms;
+		break;
+	case 17 ... 32:
+		val = MAX77620_CNFG_GPIO_DBNC_32ms;
+		break;
+	default:
+		dev_err(mgpio->dev, "Illegal value %u\n", debounce);
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(mgpio->rmap, GPIO_REG_ADDR(offset),
+				 MAX77620_CNFG_GPIO_DBNC_MASK, val);
+	if (ret < 0)
+		dev_err(mgpio->dev, "CNFG_GPIOx_DBNC update failed: %d\n", ret);
+
+	return ret;
+}
+
+static void max77620_gpio_set(struct gpio_chip *gc, unsigned int offset,
+			      int value)
+{
+	struct max77620_gpio *mgpio = gpiochip_get_data(gc);
+	u8 val;
+	int ret;
+
+	val = (value) ? MAX77620_CNFG_GPIO_OUTPUT_VAL_HIGH :
+				MAX77620_CNFG_GPIO_OUTPUT_VAL_LOW;
+
+	ret = regmap_update_bits(mgpio->rmap, GPIO_REG_ADDR(offset),
+				 MAX77620_CNFG_GPIO_OUTPUT_VAL_MASK, val);
+	if (ret < 0)
+		dev_err(mgpio->dev, "CNFG_GPIO_OUT update failed: %d\n", ret);
+}
+
+static int max77620_gpio_set_single_ended(struct gpio_chip *gc,
+					  unsigned int offset,
+					  enum single_ended_mode mode)
+{
+	struct max77620_gpio *mgpio = gpiochip_get_data(gc);
+
+	switch (mode) {
+	case LINE_MODE_OPEN_DRAIN:
+		return regmap_update_bits(mgpio->rmap, GPIO_REG_ADDR(offset),
+					  MAX77620_CNFG_GPIO_DRV_MASK,
+					  MAX77620_CNFG_GPIO_DRV_OPENDRAIN);
+	case LINE_MODE_PUSH_PULL:
+		return regmap_update_bits(mgpio->rmap, GPIO_REG_ADDR(offset),
+					  MAX77620_CNFG_GPIO_DRV_MASK,
+					  MAX77620_CNFG_GPIO_DRV_PUSHPULL);
+	default:
+		break;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int max77620_gpio_to_irq(struct gpio_chip *gc, unsigned int offset)
+{
+	struct max77620_gpio *mgpio = gpiochip_get_data(gc);
+	struct max77620_chip *chip = dev_get_drvdata(mgpio->dev->parent);
+
+	return regmap_irq_get_virq(chip->gpio_irq_data, offset);
+}
+
+static int max77620_gpio_probe(struct platform_device *pdev)
+{
+	struct max77620_chip *chip =  dev_get_drvdata(pdev->dev.parent);
+	struct max77620_gpio *mgpio;
+	int gpio_irq;
+	int ret;
+
+	gpio_irq = platform_get_irq(pdev, 0);
+	if (gpio_irq <= 0) {
+		dev_err(&pdev->dev, "GPIO irq not available %d\n", gpio_irq);
+		return -ENODEV;
+	}
+
+	mgpio = devm_kzalloc(&pdev->dev, sizeof(*mgpio), GFP_KERNEL);
+	if (!mgpio)
+		return -ENOMEM;
+
+	mgpio->rmap = chip->rmap;
+	mgpio->dev = &pdev->dev;
+	mgpio->gpio_irq = gpio_irq;
+
+	mgpio->gpio_chip.label = pdev->name;
+	mgpio->gpio_chip.parent = &pdev->dev;
+	mgpio->gpio_chip.direction_input = max77620_gpio_dir_input;
+	mgpio->gpio_chip.get = max77620_gpio_get;
+	mgpio->gpio_chip.direction_output = max77620_gpio_dir_output;
+	mgpio->gpio_chip.set_debounce = max77620_gpio_set_debounce;
+	mgpio->gpio_chip.set = max77620_gpio_set;
+	mgpio->gpio_chip.set_single_ended = max77620_gpio_set_single_ended;
+	mgpio->gpio_chip.to_irq = max77620_gpio_to_irq;
+	mgpio->gpio_chip.ngpio = MAX77620_GPIO_NR;
+	mgpio->gpio_chip.can_sleep = 1;
+	mgpio->gpio_chip.base = -1;
+	mgpio->irq_base = -1;
+#ifdef CONFIG_OF_GPIO
+	mgpio->gpio_chip.of_node = pdev->dev.parent->of_node;
+#endif
+
+	platform_set_drvdata(pdev, mgpio);
+
+	ret = devm_gpiochip_add_data(&pdev->dev, &mgpio->gpio_chip, mgpio);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "gpio_init: Failed to add max77620_gpio\n");
+		return ret;
+	}
+
+	mgpio->gpio_base = mgpio->gpio_chip.base;
+	ret = devm_regmap_add_irq_chip(&pdev->dev, chip->rmap, mgpio->gpio_irq,
+				       IRQF_ONESHOT, mgpio->irq_base,
+				       &max77620_gpio_irq_chip,
+				       &chip->gpio_irq_data);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to add gpio irq_chip %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct platform_device_id max77620_gpio_devtype[] = {
+	{ .name = "max77620-gpio", },
+	{},
+};
+MODULE_DEVICE_TABLE(platform, max77620_gpio_devtype);
+
+static struct platform_driver max77620_gpio_driver = {
+	.driver.name	= "max77620-gpio",
+	.probe		= max77620_gpio_probe,
+	.id_table	= max77620_gpio_devtype,
+};
+
+module_platform_driver(max77620_gpio_driver);
+
+MODULE_DESCRIPTION("GPIO interface for MAX77620 and MAX20024 PMIC");
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_AUTHOR("Chaitanya Bandi <bandik@nvidia.com>");
+MODULE_ALIAS("platform:max77620-gpio");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-menz127.c b/drivers/gpio/gpio-menz127.c
index cc103aff45e4..a1210e330571 100644
--- a/drivers/gpio/gpio-menz127.c
+++ b/drivers/gpio/gpio-menz127.c
@@ -187,7 +187,6 @@ MODULE_DEVICE_TABLE(mcb, men_z127_ids);
 static struct mcb_driver men_z127_driver = {
 	.driver = {
 		.name = "z127-gpio",
-		.owner = THIS_MODULE,
 	},
 	.probe = men_z127_probe,
 	.remove = men_z127_remove,
diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
new file mode 100644
index 000000000000..45b51278b8ee
--- /dev/null
+++ b/drivers/gpio/gpio-merrifield.c
@@ -0,0 +1,444 @@
+/*
+ * Intel Merrifield SoC GPIO driver
+ *
+ * Copyright (c) 2016 Intel Corporation.
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/gpio/driver.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pinctrl/consumer.h>
+
+#define GCCR		0x000	/* controller configuration */
+#define GPLR		0x004	/* pin level r/o */
+#define GPDR		0x01c	/* pin direction */
+#define GPSR		0x034	/* pin set w/o */
+#define GPCR		0x04c	/* pin clear w/o */
+#define GRER		0x064	/* rising edge detect */
+#define GFER		0x07c	/* falling edge detect */
+#define GFBR		0x094	/* glitch filter bypass */
+#define GIMR		0x0ac	/* interrupt mask */
+#define GISR		0x0c4	/* interrupt source */
+#define GITR		0x300	/* input type */
+#define GLPR		0x318	/* level input polarity */
+#define GWMR		0x400	/* wake mask */
+#define GWSR		0x418	/* wake source */
+#define GSIR		0xc00	/* secure input */
+
+/* Intel Merrifield has 192 GPIO pins */
+#define MRFLD_NGPIO	192
+
+struct mrfld_gpio_pinrange {
+	unsigned int gpio_base;
+	unsigned int pin_base;
+	unsigned int npins;
+};
+
+#define GPIO_PINRANGE(gstart, gend, pstart)		\
+	{						\
+		.gpio_base = (gstart),			\
+		.pin_base = (pstart),			\
+		.npins = (gend) - (gstart) + 1,		\
+	}
+
+struct mrfld_gpio {
+	struct gpio_chip	chip;
+	void __iomem		*reg_base;
+	raw_spinlock_t		lock;
+	struct device		*dev;
+};
+
+static const struct mrfld_gpio_pinrange mrfld_gpio_ranges[] = {
+	GPIO_PINRANGE(0, 11, 146),
+	GPIO_PINRANGE(12, 13, 144),
+	GPIO_PINRANGE(14, 15, 35),
+	GPIO_PINRANGE(16, 16, 164),
+	GPIO_PINRANGE(17, 18, 105),
+	GPIO_PINRANGE(19, 22, 101),
+	GPIO_PINRANGE(23, 30, 107),
+	GPIO_PINRANGE(32, 43, 67),
+	GPIO_PINRANGE(44, 63, 195),
+	GPIO_PINRANGE(64, 67, 140),
+	GPIO_PINRANGE(68, 69, 165),
+	GPIO_PINRANGE(70, 71, 65),
+	GPIO_PINRANGE(72, 76, 228),
+	GPIO_PINRANGE(77, 86, 37),
+	GPIO_PINRANGE(87, 87, 48),
+	GPIO_PINRANGE(88, 88, 47),
+	GPIO_PINRANGE(89, 96, 49),
+	GPIO_PINRANGE(97, 97, 34),
+	GPIO_PINRANGE(102, 119, 83),
+	GPIO_PINRANGE(120, 123, 79),
+	GPIO_PINRANGE(124, 135, 115),
+	GPIO_PINRANGE(137, 142, 158),
+	GPIO_PINRANGE(154, 163, 24),
+	GPIO_PINRANGE(164, 176, 215),
+	GPIO_PINRANGE(177, 189, 127),
+	GPIO_PINRANGE(190, 191, 178),
+};
+
+static void __iomem *gpio_reg(struct gpio_chip *chip, unsigned int offset,
+			      unsigned int reg_type_offset)
+{
+	struct mrfld_gpio *priv = gpiochip_get_data(chip);
+	u8 reg = offset / 32;
+
+	return priv->reg_base + reg_type_offset + reg * 4;
+}
+
+static int mrfld_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	void __iomem *gplr = gpio_reg(chip, offset, GPLR);
+
+	return !!(readl(gplr) & BIT(offset % 32));
+}
+
+static void mrfld_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			   int value)
+{
+	struct mrfld_gpio *priv = gpiochip_get_data(chip);
+	void __iomem *gpsr, *gpcr;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&priv->lock, flags);
+
+	if (value) {
+		gpsr = gpio_reg(chip, offset, GPSR);
+		writel(BIT(offset % 32), gpsr);
+	} else {
+		gpcr = gpio_reg(chip, offset, GPCR);
+		writel(BIT(offset % 32), gpcr);
+	}
+
+	raw_spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int mrfld_gpio_direction_input(struct gpio_chip *chip,
+				      unsigned int offset)
+{
+	struct mrfld_gpio *priv = gpiochip_get_data(chip);
+	void __iomem *gpdr = gpio_reg(chip, offset, GPDR);
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&priv->lock, flags);
+
+	value = readl(gpdr);
+	value &= ~BIT(offset % 32);
+	writel(value, gpdr);
+
+	raw_spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int mrfld_gpio_direction_output(struct gpio_chip *chip,
+				       unsigned int offset, int value)
+{
+	struct mrfld_gpio *priv = gpiochip_get_data(chip);
+	void __iomem *gpdr = gpio_reg(chip, offset, GPDR);
+	unsigned long flags;
+
+	mrfld_gpio_set(chip, offset, value);
+
+	raw_spin_lock_irqsave(&priv->lock, flags);
+
+	value = readl(gpdr);
+	value |= BIT(offset % 32);
+	writel(value, gpdr);
+
+	raw_spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static void mrfld_irq_ack(struct irq_data *d)
+{
+	struct mrfld_gpio *priv = irq_data_get_irq_chip_data(d);
+	u32 gpio = irqd_to_hwirq(d);
+	void __iomem *gisr = gpio_reg(&priv->chip, gpio, GISR);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&priv->lock, flags);
+
+	writel(BIT(gpio % 32), gisr);
+
+	raw_spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void mrfld_irq_unmask_mask(struct irq_data *d, bool unmask)
+{
+	struct mrfld_gpio *priv = irq_data_get_irq_chip_data(d);
+	u32 gpio = irqd_to_hwirq(d);
+	void __iomem *gimr = gpio_reg(&priv->chip, gpio, GIMR);
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&priv->lock, flags);
+
+	if (unmask)
+		value = readl(gimr) | BIT(gpio % 32);
+	else
+		value = readl(gimr) & ~BIT(gpio % 32);
+	writel(value, gimr);
+
+	raw_spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void mrfld_irq_mask(struct irq_data *d)
+{
+	mrfld_irq_unmask_mask(d, false);
+}
+
+static void mrfld_irq_unmask(struct irq_data *d)
+{
+	mrfld_irq_unmask_mask(d, true);
+}
+
+static int mrfld_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mrfld_gpio *priv = gpiochip_get_data(gc);
+	u32 gpio = irqd_to_hwirq(d);
+	void __iomem *grer = gpio_reg(&priv->chip, gpio, GRER);
+	void __iomem *gfer = gpio_reg(&priv->chip, gpio, GFER);
+	void __iomem *gitr = gpio_reg(&priv->chip, gpio, GITR);
+	void __iomem *glpr = gpio_reg(&priv->chip, gpio, GLPR);
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&priv->lock, flags);
+
+	if (type & IRQ_TYPE_EDGE_RISING)
+		value = readl(grer) | BIT(gpio % 32);
+	else
+		value = readl(grer) & ~BIT(gpio % 32);
+	writel(value, grer);
+
+	if (type & IRQ_TYPE_EDGE_FALLING)
+		value = readl(gfer) | BIT(gpio % 32);
+	else
+		value = readl(gfer) & ~BIT(gpio % 32);
+	writel(value, gfer);
+
+	/*
+	 * To prevent glitches from triggering an unintended level interrupt,
+	 * configure GLPR register first and then configure GITR.
+	 */
+	if (type & IRQ_TYPE_LEVEL_LOW)
+		value = readl(glpr) | BIT(gpio % 32);
+	else
+		value = readl(glpr) & ~BIT(gpio % 32);
+	writel(value, glpr);
+
+	if (type & IRQ_TYPE_LEVEL_MASK) {
+		value = readl(gitr) | BIT(gpio % 32);
+		writel(value, gitr);
+
+		irq_set_handler_locked(d, handle_level_irq);
+	} else if (type & IRQ_TYPE_EDGE_BOTH) {
+		value = readl(gitr) & ~BIT(gpio % 32);
+		writel(value, gitr);
+
+		irq_set_handler_locked(d, handle_edge_irq);
+	}
+
+	raw_spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int mrfld_irq_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mrfld_gpio *priv = gpiochip_get_data(gc);
+	u32 gpio = irqd_to_hwirq(d);
+	void __iomem *gwmr = gpio_reg(&priv->chip, gpio, GWMR);
+	void __iomem *gwsr = gpio_reg(&priv->chip, gpio, GWSR);
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&priv->lock, flags);
+
+	/* Clear the existing wake status */
+	writel(BIT(gpio % 32), gwsr);
+
+	if (on)
+		value = readl(gwmr) | BIT(gpio % 32);
+	else
+		value = readl(gwmr) & ~BIT(gpio % 32);
+	writel(value, gwmr);
+
+	raw_spin_unlock_irqrestore(&priv->lock, flags);
+
+	dev_dbg(priv->dev, "%sable wake for gpio %u\n", on ? "en" : "dis", gpio);
+	return 0;
+}
+
+static struct irq_chip mrfld_irqchip = {
+	.name		= "gpio-merrifield",
+	.irq_ack	= mrfld_irq_ack,
+	.irq_mask	= mrfld_irq_mask,
+	.irq_unmask	= mrfld_irq_unmask,
+	.irq_set_type	= mrfld_irq_set_type,
+	.irq_set_wake	= mrfld_irq_set_wake,
+};
+
+static void mrfld_irq_handler(struct irq_desc *desc)
+{
+	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
+	struct mrfld_gpio *priv = gpiochip_get_data(gc);
+	struct irq_chip *irqchip = irq_desc_get_chip(desc);
+	unsigned long base, gpio;
+
+	chained_irq_enter(irqchip, desc);
+
+	/* Check GPIO controller to check which pin triggered the interrupt */
+	for (base = 0; base < priv->chip.ngpio; base += 32) {
+		void __iomem *gisr = gpio_reg(&priv->chip, base, GISR);
+		void __iomem *gimr = gpio_reg(&priv->chip, base, GIMR);
+		unsigned long pending, enabled;
+
+		pending = readl(gisr);
+		enabled = readl(gimr);
+
+		/* Only interrupts that are enabled */
+		pending &= enabled;
+
+		for_each_set_bit(gpio, &pending, 32) {
+			unsigned int irq;
+
+			irq = irq_find_mapping(gc->irqdomain, base + gpio);
+			generic_handle_irq(irq);
+		}
+	}
+
+	chained_irq_exit(irqchip, desc);
+}
+
+static void mrfld_irq_init_hw(struct mrfld_gpio *priv)
+{
+	void __iomem *reg;
+	unsigned int base;
+
+	for (base = 0; base < priv->chip.ngpio; base += 32) {
+		/* Clear the rising-edge detect register */
+		reg = gpio_reg(&priv->chip, base, GRER);
+		writel(0, reg);
+		/* Clear the falling-edge detect register */
+		reg = gpio_reg(&priv->chip, base, GFER);
+		writel(0, reg);
+	}
+}
+
+static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	const struct mrfld_gpio_pinrange *range;
+	struct mrfld_gpio *priv;
+	u32 gpio_base, irq_base;
+	void __iomem *base;
+	unsigned int i;
+	int retval;
+
+	retval = pcim_enable_device(pdev);
+	if (retval)
+		return retval;
+
+	retval = pcim_iomap_regions(pdev, BIT(1) | BIT(0), pci_name(pdev));
+	if (retval) {
+		dev_err(&pdev->dev, "I/O memory mapping error\n");
+		return retval;
+	}
+
+	base = pcim_iomap_table(pdev)[1];
+
+	irq_base = readl(base);
+	gpio_base = readl(sizeof(u32) + base);
+
+	/* Release the IO mapping, since we already get the info from BAR1 */
+	pcim_iounmap_regions(pdev, BIT(1));
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		dev_err(&pdev->dev, "can't allocate chip data\n");
+		return -ENOMEM;
+	}
+
+	priv->dev = &pdev->dev;
+	priv->reg_base = pcim_iomap_table(pdev)[0];
+
+	priv->chip.label = dev_name(&pdev->dev);
+	priv->chip.parent = &pdev->dev;
+	priv->chip.request = gpiochip_generic_request;
+	priv->chip.free = gpiochip_generic_free;
+	priv->chip.direction_input = mrfld_gpio_direction_input;
+	priv->chip.direction_output = mrfld_gpio_direction_output;
+	priv->chip.get = mrfld_gpio_get;
+	priv->chip.set = mrfld_gpio_set;
+	priv->chip.base = gpio_base;
+	priv->chip.ngpio = MRFLD_NGPIO;
+	priv->chip.can_sleep = false;
+
+	raw_spin_lock_init(&priv->lock);
+
+	pci_set_drvdata(pdev, priv);
+	retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv);
+	if (retval) {
+		dev_err(&pdev->dev, "gpiochip_add error %d\n", retval);
+		return retval;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mrfld_gpio_ranges); i++) {
+		range = &mrfld_gpio_ranges[i];
+		retval = gpiochip_add_pin_range(&priv->chip,
+						"pinctrl-merrifield",
+						range->gpio_base,
+						range->pin_base,
+						range->npins);
+		if (retval) {
+			dev_err(&pdev->dev, "failed to add GPIO pin range\n");
+			return retval;
+		}
+	}
+
+	retval = gpiochip_irqchip_add(&priv->chip, &mrfld_irqchip, irq_base,
+				      handle_simple_irq, IRQ_TYPE_NONE);
+	if (retval) {
+		dev_err(&pdev->dev, "could not connect irqchip to gpiochip\n");
+		return retval;
+	}
+
+	mrfld_irq_init_hw(priv);
+
+	gpiochip_set_chained_irqchip(&priv->chip, &mrfld_irqchip, pdev->irq,
+				     mrfld_irq_handler);
+
+	return 0;
+}
+
+static const struct pci_device_id mrfld_gpio_ids[] = {
+	{ PCI_VDEVICE(INTEL, 0x1199) },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, mrfld_gpio_ids);
+
+static struct pci_driver mrfld_gpio_driver = {
+	.name		= "gpio-merrifield",
+	.id_table	= mrfld_gpio_ids,
+	.probe		= mrfld_gpio_probe,
+};
+
+module_pci_driver(mrfld_gpio_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_DESCRIPTION("Intel Merrifield SoC GPIO driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index 6c1cb3b8c02c..6ec144baeb11 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -61,6 +61,8 @@ o        `                     ~~~~\___/~~~~    ` controller in FPGA is ,.`
 #include <linux/bitops.h>
 #include <linux/platform_device.h>
 #include <linux/mod_devicetable.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 
 static void bgpio_write8(void __iomem *reg, unsigned long data)
 {
@@ -569,6 +571,41 @@ static void __iomem *bgpio_map(struct platform_device *pdev,
 	return devm_ioremap_resource(&pdev->dev, r);
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id bgpio_of_match[] = {
+	{ .compatible = "wd,mbl-gpio" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bgpio_of_match);
+
+static struct bgpio_pdata *bgpio_parse_dt(struct platform_device *pdev,
+					  unsigned long *flags)
+{
+	struct bgpio_pdata *pdata;
+
+	if (!of_match_device(bgpio_of_match, &pdev->dev))
+		return NULL;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(struct bgpio_pdata),
+			     GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	pdata->base = -1;
+
+	if (of_property_read_bool(pdev->dev.of_node, "no-output"))
+		*flags |= BGPIOF_NO_OUTPUT;
+
+	return pdata;
+}
+#else
+static struct bgpio_pdata *bgpio_parse_dt(struct platform_device *pdev,
+					  unsigned long *flags)
+{
+	return NULL;
+}
+#endif /* CONFIG_OF */
+
 static int bgpio_pdev_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -579,10 +616,19 @@ static int bgpio_pdev_probe(struct platform_device *pdev)
 	void __iomem *dirout;
 	void __iomem *dirin;
 	unsigned long sz;
-	unsigned long flags = pdev->id_entry->driver_data;
+	unsigned long flags = 0;
 	int err;
 	struct gpio_chip *gc;
-	struct bgpio_pdata *pdata = dev_get_platdata(dev);
+	struct bgpio_pdata *pdata;
+
+	pdata = bgpio_parse_dt(pdev, &flags);
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
+
+	if (!pdata) {
+		pdata = dev_get_platdata(dev);
+		flags = pdev->id_entry->driver_data;
+	}
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dat");
 	if (!r)
@@ -646,6 +692,7 @@ MODULE_DEVICE_TABLE(platform, bgpio_id_table);
 static struct platform_driver bgpio_driver = {
 	.driver = {
 		.name = "basic-mmio-gpio",
+		.of_match_table = of_match_ptr(bgpio_of_match),
 	},
 	.id_table = bgpio_id_table,
 	.probe = bgpio_pdev_probe,
diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c
index e248707ca39e..839474430229 100644
--- a/drivers/gpio/gpio-palmas.c
+++ b/drivers/gpio/gpio-palmas.c
@@ -208,7 +208,6 @@ static int palmas_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver palmas_gpio_driver = {
 	.driver.name	= "palmas-gpio",
-	.driver.owner	= THIS_MODULE,
 	.driver.of_match_table = of_palmas_gpio_match,
 	.probe		= palmas_gpio_probe,
 };
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 5e3be32ebb8d..02f2a5621bb0 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -44,7 +44,7 @@
 
 #define PCA_GPIO_MASK		0x00FF
 #define PCA_INT			0x0100
-#define PCA_PCAL			0x0200
+#define PCA_PCAL		0x0200
 #define PCA953X_TYPE		0x1000
 #define PCA957X_TYPE		0x2000
 #define PCA_TYPE_MASK		0xF000
@@ -67,6 +67,8 @@ static const struct i2c_device_id pca953x_id[] = {
 	{ "pca9575", 16 | PCA957X_TYPE | PCA_INT, },
 	{ "pca9698", 40 | PCA953X_TYPE, },
 
+	{ "pcal9555a", 16 | PCA953X_TYPE | PCA_INT | PCA_PCAL, },
+
 	{ "max7310", 8  | PCA953X_TYPE, },
 	{ "max7312", 16 | PCA953X_TYPE | PCA_INT, },
 	{ "max7313", 16 | PCA953X_TYPE | PCA_INT, },
@@ -90,7 +92,7 @@ MODULE_DEVICE_TABLE(acpi, pca953x_acpi_ids);
 #define MAX_BANK 5
 #define BANK_SZ 8
 
-#define NBANK(chip) (chip->gpio_chip.ngpio / BANK_SZ)
+#define NBANK(chip) DIV_ROUND_UP(chip->gpio_chip.ngpio, BANK_SZ)
 
 struct pca953x_chip {
 	unsigned gpio_start;
@@ -135,7 +137,7 @@ static int pca953x_read_single(struct pca953x_chip *chip, int reg, u32 *val,
 static int pca953x_write_single(struct pca953x_chip *chip, int reg, u32 val,
 				int off)
 {
-	int ret = 0;
+	int ret;
 	int bank_shift = fls((chip->gpio_chip.ngpio - 1) / BANK_SZ);
 	int offset = off / BANK_SZ;
 
@@ -163,10 +165,13 @@ static int pca953x_write_regs(struct pca953x_chip *chip, int reg, u8 *val)
 					NBANK(chip), val);
 	} else {
 		switch (chip->chip_type) {
-		case PCA953X_TYPE:
-			ret = i2c_smbus_write_word_data(chip->client,
-			    reg << 1, cpu_to_le16(get_unaligned((u16 *)val)));
+		case PCA953X_TYPE: {
+			__le16 word = cpu_to_le16(get_unaligned((u16 *)val));
+
+			ret = i2c_smbus_write_word_data(chip->client, reg << 1,
+							(__force u16)word);
 			break;
+		}
 		case PCA957X_TYPE:
 			ret = i2c_smbus_write_byte_data(chip->client, reg << 1,
 							val[0]);
@@ -235,7 +240,6 @@ static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned off)
 		goto exit;
 
 	chip->reg_direction[off / BANK_SZ] = reg_val;
-	ret = 0;
 exit:
 	mutex_unlock(&chip->i2c_lock);
 	return ret;
@@ -286,7 +290,6 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc,
 		goto exit;
 
 	chip->reg_direction[off / BANK_SZ] = reg_val;
-	ret = 0;
 exit:
 	mutex_unlock(&chip->i2c_lock);
 	return ret;
@@ -351,7 +354,6 @@ exit:
 	mutex_unlock(&chip->i2c_lock);
 }
 
-
 static void pca953x_gpio_set_multiple(struct gpio_chip *gc,
 		unsigned long *mask, unsigned long *bits)
 {
@@ -820,7 +822,7 @@ static int pca953x_remove(struct i2c_client *client)
 {
 	struct pca953x_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct pca953x_chip *chip = i2c_get_clientdata(client);
-	int ret = 0;
+	int ret;
 
 	if (pdata && pdata->teardown) {
 		ret = pdata->teardown(client, chip->gpio_chip.base,
@@ -861,6 +863,7 @@ static const struct of_device_id pca953x_dt_ids[] = {
 	{ .compatible = "maxim,max7315", .data = OF_953X( 8, PCA_INT), },
 
 	{ .compatible = "ti,pca6107", .data = OF_953X( 8, PCA_INT), },
+	{ .compatible = "ti,pca9536", .data = OF_953X( 4, 0), },
 	{ .compatible = "ti,tca6408", .data = OF_953X( 8, PCA_INT), },
 	{ .compatible = "ti,tca6416", .data = OF_953X(16, PCA_INT), },
 	{ .compatible = "ti,tca6424", .data = OF_953X(24, PCA_INT), },
diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c
index 169c09aa33c8..d168410e2338 100644
--- a/drivers/gpio/gpio-pcf857x.c
+++ b/drivers/gpio/gpio-pcf857x.c
@@ -440,6 +440,14 @@ static int pcf857x_remove(struct i2c_client *client)
 	return status;
 }
 
+static void pcf857x_shutdown(struct i2c_client *client)
+{
+	struct pcf857x *gpio = i2c_get_clientdata(client);
+
+	/* Drive all the I/O lines high */
+	gpio->write(gpio->client, BIT(gpio->chip.ngpio) - 1);
+}
+
 static struct i2c_driver pcf857x_driver = {
 	.driver = {
 		.name	= "pcf857x",
@@ -447,6 +455,7 @@ static struct i2c_driver pcf857x_driver = {
 	},
 	.probe	= pcf857x_probe,
 	.remove	= pcf857x_remove,
+	.shutdown = pcf857x_shutdown,
 	.id_table = pcf857x_id,
 };
 
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 681c93fb9e70..b96e0b466f74 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -335,6 +335,9 @@ static const struct of_device_id gpio_rcar_of_table[] = {
 		.compatible = "renesas,gpio-r8a7791",
 		.data = &gpio_rcar_info_gen2,
 	}, {
+		.compatible = "renesas,gpio-r8a7792",
+		.data = &gpio_rcar_info_gen2,
+	}, {
 		.compatible = "renesas,gpio-r8a7793",
 		.data = &gpio_rcar_info_gen2,
 	}, {
diff --git a/drivers/gpio/gpio-rdc321x.c b/drivers/gpio/gpio-rdc321x.c
index ec945b90f54d..cbf0f9e6465b 100644
--- a/drivers/gpio/gpio-rdc321x.c
+++ b/drivers/gpio/gpio-rdc321x.c
@@ -200,7 +200,6 @@ static int rdc321x_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver rdc321x_gpio_driver = {
 	.driver.name	= "rdc321x-gpio",
-	.driver.owner	= THIS_MODULE,
 	.probe		= rdc321x_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index a03b38ee2e02..b96990c262a1 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -296,7 +296,6 @@ static int sch311x_gpio_remove(struct platform_device *pdev)
 
 static struct platform_driver sch311x_gpio_driver = {
 	.driver.name	= DRV_NAME,
-	.driver.owner	= THIS_MODULE,
 	.probe		= sch311x_gpio_probe,
 	.remove		= sch311x_gpio_remove,
 };
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 6f7af28b8966..f675132de10e 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -68,6 +68,22 @@ static void stmpe_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
 		stmpe_reg_write(stmpe, reg, mask);
 }
 
+static int stmpe_gpio_get_direction(struct gpio_chip *chip,
+				    unsigned offset)
+{
+	struct stmpe_gpio *stmpe_gpio = gpiochip_get_data(chip);
+	struct stmpe *stmpe = stmpe_gpio->stmpe;
+	u8 reg = stmpe->regs[STMPE_IDX_GPDR_LSB] - (offset / 8);
+	u8 mask = 1 << (offset % 8);
+	int ret;
+
+	ret = stmpe_reg_read(stmpe, reg);
+	if (ret < 0)
+		return ret;
+
+	return !(ret & mask);
+}
+
 static int stmpe_gpio_direction_output(struct gpio_chip *chip,
 					 unsigned offset, int val)
 {
@@ -106,6 +122,7 @@ static int stmpe_gpio_request(struct gpio_chip *chip, unsigned offset)
 static struct gpio_chip template_chip = {
 	.label			= "stmpe",
 	.owner			= THIS_MODULE,
+	.get_direction		= stmpe_gpio_get_direction,
 	.direction_input	= stmpe_gpio_direction_input,
 	.get			= stmpe_gpio_get,
 	.direction_output	= stmpe_gpio_direction_output,
@@ -416,7 +433,6 @@ static struct platform_driver stmpe_gpio_driver = {
 	.driver = {
 		.suppress_bind_attrs	= true,
 		.name			= "stmpe-gpio",
-		.owner			= THIS_MODULE,
 	},
 	.probe		= stmpe_gpio_probe,
 };
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index 24b6d643ecdb..537cec7583fc 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -129,7 +129,7 @@ static int syscon_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int val)
 
 static const struct syscon_gpio_data clps711x_mctrl_gpio = {
 	/* ARM CLPS711X SYSFLG1 Bits 8-10 */
-	.compatible	= "cirrus,clps711x-syscon1",
+	.compatible	= "cirrus,ep7209-syscon1",
 	.flags		= GPIO_SYSCON_FEAT_IN,
 	.bit_count	= 3,
 	.dat_bit_offset	= 0x40 * 8 + 8,
@@ -168,7 +168,7 @@ static const struct syscon_gpio_data keystone_dsp_gpio = {
 
 static const struct of_device_id syscon_gpio_ids[] = {
 	{
-		.compatible	= "cirrus,clps711x-mctrl-gpio",
+		.compatible	= "cirrus,ep7209-mctrl-gpio",
 		.data		= &clps711x_mctrl_gpio,
 	},
 	{
diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index 2e35ed3abbcf..8b3659352e49 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -343,7 +343,6 @@ static int tc3589x_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver tc3589x_gpio_driver = {
 	.driver.name	= "tc3589x-gpio",
-	.driver.owner	= THIS_MODULE,
 	.probe		= tc3589x_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-tps65218.c b/drivers/gpio/gpio-tps65218.c
index 0eaeac8de9de..1c09a19ae10c 100644
--- a/drivers/gpio/gpio-tps65218.c
+++ b/drivers/gpio/gpio-tps65218.c
@@ -230,6 +230,12 @@ static const struct of_device_id tps65218_dt_match[] = {
 };
 MODULE_DEVICE_TABLE(of, tps65218_dt_match);
 
+static const struct platform_device_id tps65218_gpio_id_table[] = {
+	{ "tps65218-gpio", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, tps65218_gpio_id_table);
+
 static struct platform_driver tps65218_gpio_driver = {
 	.driver = {
 		.name = "tps65218-gpio",
@@ -237,6 +243,7 @@ static struct platform_driver tps65218_gpio_driver = {
 	},
 	.probe = tps65218_gpio_probe,
 	.remove = tps65218_gpio_remove,
+	.id_table = tps65218_gpio_id_table,
 };
 
 module_platform_driver(tps65218_gpio_driver);
diff --git a/drivers/gpio/gpio-tps6586x.c b/drivers/gpio/gpio-tps6586x.c
index 6b15e68a314f..042b9a20781a 100644
--- a/drivers/gpio/gpio-tps6586x.c
+++ b/drivers/gpio/gpio-tps6586x.c
@@ -131,7 +131,6 @@ static int tps6586x_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver tps6586x_gpio_driver = {
 	.driver.name	= "tps6586x-gpio",
-	.driver.owner	= THIS_MODULE,
 	.probe		= tps6586x_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-tps65910.c b/drivers/gpio/gpio-tps65910.c
index 0ae6a5a54ea8..e63d7dabf78b 100644
--- a/drivers/gpio/gpio-tps65910.c
+++ b/drivers/gpio/gpio-tps65910.c
@@ -184,7 +184,6 @@ skip_init:
 
 static struct platform_driver tps65910_gpio_driver = {
 	.driver.name    = "tps65910-gpio",
-	.driver.owner   = THIS_MODULE,
 	.probe		= tps65910_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-viperboard.c b/drivers/gpio/gpio-viperboard.c
index dec47aafd5cd..e6d1328dddfa 100644
--- a/drivers/gpio/gpio-viperboard.c
+++ b/drivers/gpio/gpio-viperboard.c
@@ -440,7 +440,6 @@ static int vprbrd_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver vprbrd_gpio_driver = {
 	.driver.name	= "viperboard-gpio",
-	.driver.owner	= THIS_MODULE,
 	.probe		= vprbrd_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-wm831x.c b/drivers/gpio/gpio-wm831x.c
index 41ec7834059a..21f97bcd0062 100644
--- a/drivers/gpio/gpio-wm831x.c
+++ b/drivers/gpio/gpio-wm831x.c
@@ -296,7 +296,6 @@ static int wm831x_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver wm831x_gpio_driver = {
 	.driver.name	= "wm831x-gpio",
-	.driver.owner	= THIS_MODULE,
 	.probe		= wm831x_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-wm8350.c b/drivers/gpio/gpio-wm8350.c
index 07d45a3b205a..e9765707d5c1 100644
--- a/drivers/gpio/gpio-wm8350.c
+++ b/drivers/gpio/gpio-wm8350.c
@@ -139,7 +139,6 @@ static int wm8350_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver wm8350_gpio_driver = {
 	.driver.name	= "wm8350-gpio",
-	.driver.owner	= THIS_MODULE,
 	.probe		= wm8350_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-wm8994.c b/drivers/gpio/gpio-wm8994.c
index 744af388c949..2457aac8592e 100644
--- a/drivers/gpio/gpio-wm8994.c
+++ b/drivers/gpio/gpio-wm8994.c
@@ -299,7 +299,6 @@ static int wm8994_gpio_probe(struct platform_device *pdev)
 
 static struct platform_driver wm8994_gpio_driver = {
 	.driver.name	= "wm8994-gpio",
-	.driver.owner	= THIS_MODULE,
 	.probe		= wm8994_gpio_probe,
 };
 
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index d0fbb7f99523..14b2a62338ea 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -133,6 +133,53 @@ static void xgpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 }
 
 /**
+ * xgpio_set_multiple - Write the specified signals of the GPIO device.
+ * @gc:     Pointer to gpio_chip device structure.
+ * @mask:   Mask of the GPIOS to modify.
+ * @bits:   Value to be wrote on each GPIO
+ *
+ * This function writes the specified values into the specified signals of the
+ * GPIO devices.
+ */
+static void xgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask,
+			       unsigned long *bits)
+{
+	unsigned long flags;
+	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
+	struct xgpio_instance *chip = gpiochip_get_data(gc);
+	int index = xgpio_index(chip, 0);
+	int offset, i;
+
+	spin_lock_irqsave(&chip->gpio_lock[index], flags);
+
+	/* Write to GPIO signals */
+	for (i = 0; i < gc->ngpio; i++) {
+		if (*mask == 0)
+			break;
+		if (index !=  xgpio_index(chip, i)) {
+			xgpio_writereg(mm_gc->regs + XGPIO_DATA_OFFSET +
+				       xgpio_regoffset(chip, i),
+				       chip->gpio_state[index]);
+			spin_unlock_irqrestore(&chip->gpio_lock[index], flags);
+			index =  xgpio_index(chip, i);
+			spin_lock_irqsave(&chip->gpio_lock[index], flags);
+		}
+		if (__test_and_clear_bit(i, mask)) {
+			offset =  xgpio_offset(chip, i);
+			if (test_bit(i, bits))
+				chip->gpio_state[index] |= BIT(offset);
+			else
+				chip->gpio_state[index] &= ~BIT(offset);
+		}
+	}
+
+	xgpio_writereg(mm_gc->regs + XGPIO_DATA_OFFSET +
+		       xgpio_regoffset(chip, i), chip->gpio_state[index]);
+
+	spin_unlock_irqrestore(&chip->gpio_lock[index], flags);
+}
+
+/**
  * xgpio_dir_in - Set the direction of the specified GPIO signal as input.
  * @gc:     Pointer to gpio_chip device structure.
  * @gpio:   GPIO signal number.
@@ -306,6 +353,7 @@ static int xgpio_probe(struct platform_device *pdev)
 	chip->mmchip.gc.direction_output = xgpio_dir_out;
 	chip->mmchip.gc.get = xgpio_get;
 	chip->mmchip.gc.set = xgpio_set;
+	chip->mmchip.gc.set_multiple = xgpio_set_multiple;
 
 	chip->mmchip.save_regs = xgpio_save_regs;
 
diff --git a/drivers/gpio/gpio-xlp.c b/drivers/gpio/gpio-xlp.c
index 1a33a19d95b9..4620d050e5a8 100644
--- a/drivers/gpio/gpio-xlp.c
+++ b/drivers/gpio/gpio-xlp.c
@@ -19,6 +19,7 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
+#include <linux/acpi.h>
 
 /*
  * XLP GPIO has multiple 32 bit registers for each feature where each register
@@ -299,7 +300,6 @@ static int xlp_gpio_probe(struct platform_device *pdev)
 	struct gpio_chip *gc;
 	struct resource *iores;
 	struct xlp_gpio_priv *priv;
-	const struct of_device_id *of_id;
 	void __iomem *gpio_base;
 	int irq_base, irq, err;
 	int ngpio;
@@ -321,13 +321,26 @@ static int xlp_gpio_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	of_id = of_match_device(xlp_gpio_of_ids, &pdev->dev);
-	if (!of_id) {
-		dev_err(&pdev->dev, "Failed to get soc type!\n");
-		return -ENODEV;
-	}
+	if (pdev->dev.of_node) {
+		const struct of_device_id *of_id;
 
-	soc_type = (uintptr_t) of_id->data;
+		of_id = of_match_device(xlp_gpio_of_ids, &pdev->dev);
+		if (!of_id) {
+			dev_err(&pdev->dev, "Unable to match OF ID\n");
+			return -ENODEV;
+		}
+		soc_type = (uintptr_t) of_id->data;
+	} else {
+		const struct acpi_device_id *acpi_id;
+
+		acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table,
+						&pdev->dev);
+		if (!acpi_id || !acpi_id->driver_data) {
+			dev_err(&pdev->dev, "Unable to match ACPI ID\n");
+			return -ENODEV;
+		}
+		soc_type = (uintptr_t) acpi_id->driver_data;
+	}
 
 	switch (soc_type) {
 	case XLP_GPIO_VARIANT_XLP832:
@@ -388,14 +401,16 @@ static int xlp_gpio_probe(struct platform_device *pdev)
 	gc->get = xlp_gpio_get;
 
 	spin_lock_init(&priv->lock);
-	/* XLP has fixed IRQ range for GPIO interrupts */
-	if (soc_type == GPIO_VARIANT_VULCAN)
-		irq_base = irq_alloc_descs(-1, 0, gc->ngpio, 0);
-	else
+
+	/* XLP(MIPS) has fixed range for GPIO IRQs, Vulcan(ARM64) does not */
+	if (soc_type != GPIO_VARIANT_VULCAN) {
 		irq_base = irq_alloc_descs(-1, XLP_GPIO_IRQ_BASE, gc->ngpio, 0);
-	if (irq_base < 0) {
-		dev_err(&pdev->dev, "Failed to allocate IRQ numbers\n");
-		return irq_base;
+		if (irq_base < 0) {
+			dev_err(&pdev->dev, "Failed to allocate IRQ numbers\n");
+			return irq_base;
+		}
+	} else {
+		irq_base = 0;
 	}
 
 	err = gpiochip_add_data(gc, priv);
@@ -423,10 +438,19 @@ out_free_desc:
 	return err;
 }
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id xlp_gpio_acpi_match[] = {
+	{ "BRCM9006", GPIO_VARIANT_VULCAN },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, xlp_gpio_acpi_match);
+#endif
+
 static struct platform_driver xlp_gpio_driver = {
 	.driver		= {
 		.name	= "xlp-gpio",
 		.of_match_table = xlp_gpio_of_ids,
+		.acpi_match_table = ACPI_PTR(xlp_gpio_acpi_match),
 	},
 	.probe		= xlp_gpio_probe,
 };
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 2dc52585e3f2..af514618d7fb 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -836,6 +836,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip)
 	}
 
 	acpi_gpiochip_request_regions(acpi_gpio);
+	acpi_walk_dep_device_list(handle);
 }
 
 void acpi_gpiochip_remove(struct gpio_chip *chip)
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 4aabddb38b59..75e7b3919ea7 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -27,38 +27,30 @@
 
 #include "gpiolib.h"
 
-/* Private data structure for of_gpiochip_find_and_xlate */
-struct gg_data {
-	enum of_gpio_flags *flags;
-	struct of_phandle_args gpiospec;
+static int of_gpiochip_match_node(struct gpio_chip *chip, void *data)
+{
+	return chip->gpiodev->dev.of_node == data;
+}
 
-	struct gpio_desc *out_gpio;
-};
+static struct gpio_chip *of_find_gpiochip_by_node(struct device_node *np)
+{
+	return gpiochip_find(np, of_gpiochip_match_node);
+}
 
-/* Private function for resolving node pointer to gpio_chip */
-static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data)
+static struct gpio_desc *of_xlate_and_get_gpiod_flags(struct gpio_chip *chip,
+					struct of_phandle_args *gpiospec,
+					enum of_gpio_flags *flags)
 {
-	struct gg_data *gg_data = data;
 	int ret;
 
-	if ((gc->of_node != gg_data->gpiospec.np) ||
-	    (gc->of_gpio_n_cells != gg_data->gpiospec.args_count) ||
-	    (!gc->of_xlate))
-		return false;
-
-	ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags);
-	if (ret < 0) {
-		/* We've found a gpio chip, but the translation failed.
-		 * Store translation error in out_gpio.
-		 * Return false to keep looking, as more than one gpio chip
-		 * could be registered per of-node.
-		 */
-		gg_data->out_gpio = ERR_PTR(ret);
-		return false;
-	 }
-
-	gg_data->out_gpio = gpiochip_get_desc(gc, ret);
-	return true;
+	if (chip->of_gpio_n_cells != gpiospec->args_count)
+		return ERR_PTR(-EINVAL);
+
+	ret = chip->of_xlate(chip, gpiospec, flags);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	return gpiochip_get_desc(chip, ret);
 }
 
 /**
@@ -75,34 +67,37 @@ static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data)
 struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np,
 		     const char *propname, int index, enum of_gpio_flags *flags)
 {
-	/* Return -EPROBE_DEFER to support probe() functions to be called
-	 * later when the GPIO actually becomes available
-	 */
-	struct gg_data gg_data = {
-		.flags = flags,
-		.out_gpio = ERR_PTR(-EPROBE_DEFER)
-	};
+	struct of_phandle_args gpiospec;
+	struct gpio_chip *chip;
+	struct gpio_desc *desc;
 	int ret;
 
-	/* .of_xlate might decide to not fill in the flags, so clear it. */
-	if (flags)
-		*flags = 0;
-
 	ret = of_parse_phandle_with_args(np, propname, "#gpio-cells", index,
-					 &gg_data.gpiospec);
+					 &gpiospec);
 	if (ret) {
 		pr_debug("%s: can't parse '%s' property of node '%s[%d]'\n",
 			__func__, propname, np->full_name, index);
 		return ERR_PTR(ret);
 	}
 
-	gpiochip_find(&gg_data, of_gpiochip_find_and_xlate);
+	chip = of_find_gpiochip_by_node(gpiospec.np);
+	if (!chip) {
+		desc = ERR_PTR(-EPROBE_DEFER);
+		goto out;
+	}
+
+	desc = of_xlate_and_get_gpiod_flags(chip, &gpiospec, flags);
+	if (IS_ERR(desc))
+		goto out;
 
-	of_node_put(gg_data.gpiospec.np);
 	pr_debug("%s: parsed '%s' property of node '%s[%d]' - status (%d)\n",
 		 __func__, propname, np->full_name, index,
-		 PTR_ERR_OR_ZERO(gg_data.out_gpio));
-	return gg_data.out_gpio;
+		 PTR_ERR_OR_ZERO(desc));
+
+out:
+	of_node_put(gpiospec.np);
+
+	return desc;
 }
 
 int of_get_named_gpio_flags(struct device_node *np, const char *list_name,
@@ -122,6 +117,7 @@ EXPORT_SYMBOL(of_get_named_gpio_flags);
 /**
  * of_parse_own_gpio() - Get a GPIO hog descriptor, names and flags for GPIO API
  * @np:		device node to get GPIO from
+ * @chip:	GPIO chip whose hog is parsed
  * @name:	GPIO line name
  * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
  *		of_parse_own_gpio()
@@ -131,19 +127,19 @@ EXPORT_SYMBOL(of_get_named_gpio_flags);
  * value on the error condition.
  */
 static struct gpio_desc *of_parse_own_gpio(struct device_node *np,
+					   struct gpio_chip *chip,
 					   const char **name,
 					   enum gpio_lookup_flags *lflags,
 					   enum gpiod_flags *dflags)
 {
 	struct device_node *chip_np;
 	enum of_gpio_flags xlate_flags;
-	struct gg_data gg_data = {
-		.flags = &xlate_flags,
-	};
+	struct of_phandle_args gpiospec;
+	struct gpio_desc *desc;
 	u32 tmp;
-	int i, ret;
+	int ret;
 
-	chip_np = np->parent;
+	chip_np = chip->of_node;
 	if (!chip_np)
 		return ERR_PTR(-EINVAL);
 
@@ -155,25 +151,16 @@ static struct gpio_desc *of_parse_own_gpio(struct device_node *np,
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (tmp > MAX_PHANDLE_ARGS)
-		return ERR_PTR(-EINVAL);
+	gpiospec.np = chip_np;
+	gpiospec.args_count = tmp;
 
-	gg_data.gpiospec.args_count = tmp;
-	gg_data.gpiospec.np = chip_np;
-	for (i = 0; i < tmp; i++) {
-		ret = of_property_read_u32_index(np, "gpios", i,
-					   &gg_data.gpiospec.args[i]);
-		if (ret)
-			return ERR_PTR(ret);
-	}
+	ret = of_property_read_u32_array(np, "gpios", gpiospec.args, tmp);
+	if (ret)
+		return ERR_PTR(ret);
 
-	gpiochip_find(&gg_data, of_gpiochip_find_and_xlate);
-	if (!gg_data.out_gpio) {
-		if (np->parent == np)
-			return ERR_PTR(-ENXIO);
-		else
-			return ERR_PTR(-EINVAL);
-	}
+	desc = of_xlate_and_get_gpiod_flags(chip, &gpiospec, &xlate_flags);
+	if (IS_ERR(desc))
+		return desc;
 
 	if (xlate_flags & OF_GPIO_ACTIVE_LOW)
 		*lflags |= GPIO_ACTIVE_LOW;
@@ -186,14 +173,14 @@ static struct gpio_desc *of_parse_own_gpio(struct device_node *np,
 		*dflags |= GPIOD_OUT_HIGH;
 	else {
 		pr_warn("GPIO line %d (%s): no hogging state specified, bailing out\n",
-			desc_to_gpio(gg_data.out_gpio), np->name);
+			desc_to_gpio(desc), np->name);
 		return ERR_PTR(-EINVAL);
 	}
 
 	if (name && of_property_read_string(np, "line-name", name))
 		*name = np->name;
 
-	return gg_data.out_gpio;
+	return desc;
 }
 
 /**
@@ -262,7 +249,7 @@ static int of_gpiochip_scan_gpios(struct gpio_chip *chip)
 		if (!of_property_read_bool(np, "gpio-hog"))
 			continue;
 
-		desc = of_parse_own_gpio(np, &name, &lflags, &dflags);
+		desc = of_parse_own_gpio(np, chip, &name, &lflags, &dflags);
 		if (IS_ERR(desc))
 			continue;
 
@@ -410,6 +397,7 @@ static int of_gpiochip_add_pin_range(struct gpio_chip *chip)
 			break;
 
 		pctldev = of_pinctrl_get(pinspec.np);
+		of_node_put(pinspec.np);
 		if (!pctldev)
 			return -EPROBE_DEFER;
 
@@ -487,6 +475,9 @@ int of_gpiochip_add(struct gpio_chip *chip)
 		chip->of_xlate = of_gpio_simple_xlate;
 	}
 
+	if (chip->of_gpio_n_cells > MAX_PHANDLE_ARGS)
+		return -EINVAL;
+
 	status = of_gpiochip_add_pin_range(chip);
 	if (status)
 		return status;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index be74bd370f1f..53ff25ac66d8 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -16,11 +16,14 @@
 #include <linux/gpio/driver.h>
 #include <linux/gpio/machine.h>
 #include <linux/pinctrl/consumer.h>
-#include <linux/idr.h>
 #include <linux/cdev.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
 #include <linux/compat.h>
+#include <linux/anon_inodes.h>
+#include <linux/kfifo.h>
+#include <linux/poll.h>
+#include <linux/timekeeping.h>
 #include <uapi/linux/gpio.h>
 
 #include "gpiolib.h"
@@ -310,6 +313,497 @@ static int gpiochip_set_desc_names(struct gpio_chip *gc)
 	return 0;
 }
 
+/*
+ * GPIO line handle management
+ */
+
+/**
+ * struct linehandle_state - contains the state of a userspace handle
+ * @gdev: the GPIO device the handle pertains to
+ * @label: consumer label used to tag descriptors
+ * @descs: the GPIO descriptors held by this handle
+ * @numdescs: the number of descriptors held in the descs array
+ */
+struct linehandle_state {
+	struct gpio_device *gdev;
+	const char *label;
+	struct gpio_desc *descs[GPIOHANDLES_MAX];
+	u32 numdescs;
+};
+
+static long linehandle_ioctl(struct file *filep, unsigned int cmd,
+			     unsigned long arg)
+{
+	struct linehandle_state *lh = filep->private_data;
+	void __user *ip = (void __user *)arg;
+	struct gpiohandle_data ghd;
+	int i;
+
+	if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
+		int val;
+
+		/* TODO: check if descriptors are really input */
+		for (i = 0; i < lh->numdescs; i++) {
+			val = gpiod_get_value_cansleep(lh->descs[i]);
+			if (val < 0)
+				return val;
+			ghd.values[i] = val;
+		}
+
+		if (copy_to_user(ip, &ghd, sizeof(ghd)))
+			return -EFAULT;
+
+		return 0;
+	} else if (cmd == GPIOHANDLE_SET_LINE_VALUES_IOCTL) {
+		int vals[GPIOHANDLES_MAX];
+
+		/* TODO: check if descriptors are really output */
+		if (copy_from_user(&ghd, ip, sizeof(ghd)))
+			return -EFAULT;
+
+		/* Clamp all values to [0,1] */
+		for (i = 0; i < lh->numdescs; i++)
+			vals[i] = !!ghd.values[i];
+
+		/* Reuse the array setting function */
+		gpiod_set_array_value_complex(false,
+					      true,
+					      lh->numdescs,
+					      lh->descs,
+					      vals);
+		return 0;
+	}
+	return -EINVAL;
+}
+
+#ifdef CONFIG_COMPAT
+static long linehandle_ioctl_compat(struct file *filep, unsigned int cmd,
+			     unsigned long arg)
+{
+	return linehandle_ioctl(filep, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static int linehandle_release(struct inode *inode, struct file *filep)
+{
+	struct linehandle_state *lh = filep->private_data;
+	struct gpio_device *gdev = lh->gdev;
+	int i;
+
+	for (i = 0; i < lh->numdescs; i++)
+		gpiod_free(lh->descs[i]);
+	kfree(lh->label);
+	kfree(lh);
+	put_device(&gdev->dev);
+	return 0;
+}
+
+static const struct file_operations linehandle_fileops = {
+	.release = linehandle_release,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+	.unlocked_ioctl = linehandle_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = linehandle_ioctl_compat,
+#endif
+};
+
+static int linehandle_create(struct gpio_device *gdev, void __user *ip)
+{
+	struct gpiohandle_request handlereq;
+	struct linehandle_state *lh;
+	int fd, i, ret;
+
+	if (copy_from_user(&handlereq, ip, sizeof(handlereq)))
+		return -EFAULT;
+	if ((handlereq.lines == 0) || (handlereq.lines > GPIOHANDLES_MAX))
+		return -EINVAL;
+
+	lh = kzalloc(sizeof(*lh), GFP_KERNEL);
+	if (!lh)
+		return -ENOMEM;
+	lh->gdev = gdev;
+	get_device(&gdev->dev);
+
+	/* Make sure this is terminated */
+	handlereq.consumer_label[sizeof(handlereq.consumer_label)-1] = '\0';
+	if (strlen(handlereq.consumer_label)) {
+		lh->label = kstrdup(handlereq.consumer_label,
+				    GFP_KERNEL);
+		if (!lh->label) {
+			ret = -ENOMEM;
+			goto out_free_lh;
+		}
+	}
+
+	/* Request each GPIO */
+	for (i = 0; i < handlereq.lines; i++) {
+		u32 offset = handlereq.lineoffsets[i];
+		u32 lflags = handlereq.flags;
+		struct gpio_desc *desc;
+
+		desc = &gdev->descs[offset];
+		ret = gpiod_request(desc, lh->label);
+		if (ret)
+			goto out_free_descs;
+		lh->descs[i] = desc;
+
+		if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW)
+			set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+		if (lflags & GPIOHANDLE_REQUEST_OPEN_DRAIN)
+			set_bit(FLAG_OPEN_DRAIN, &desc->flags);
+		if (lflags & GPIOHANDLE_REQUEST_OPEN_SOURCE)
+			set_bit(FLAG_OPEN_SOURCE, &desc->flags);
+
+		/*
+		 * Lines have to be requested explicitly for input
+		 * or output, else the line will be treated "as is".
+		 */
+		if (lflags & GPIOHANDLE_REQUEST_OUTPUT) {
+			int val = !!handlereq.default_values[i];
+
+			ret = gpiod_direction_output(desc, val);
+			if (ret)
+				goto out_free_descs;
+		} else if (lflags & GPIOHANDLE_REQUEST_INPUT) {
+			ret = gpiod_direction_input(desc);
+			if (ret)
+				goto out_free_descs;
+		}
+		dev_dbg(&gdev->dev, "registered chardev handle for line %d\n",
+			offset);
+	}
+	/* Let i point at the last handle */
+	i--;
+	lh->numdescs = handlereq.lines;
+
+	fd = anon_inode_getfd("gpio-linehandle",
+			      &linehandle_fileops,
+			      lh,
+			      O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		ret = fd;
+		goto out_free_descs;
+	}
+
+	handlereq.fd = fd;
+	if (copy_to_user(ip, &handlereq, sizeof(handlereq))) {
+		ret = -EFAULT;
+		goto out_free_descs;
+	}
+
+	dev_dbg(&gdev->dev, "registered chardev handle for %d lines\n",
+		lh->numdescs);
+
+	return 0;
+
+out_free_descs:
+	for (; i >= 0; i--)
+		gpiod_free(lh->descs[i]);
+	kfree(lh->label);
+out_free_lh:
+	kfree(lh);
+	put_device(&gdev->dev);
+	return ret;
+}
+
+/*
+ * GPIO line event management
+ */
+
+/**
+ * struct lineevent_state - contains the state of a userspace event
+ * @gdev: the GPIO device the event pertains to
+ * @label: consumer label used to tag descriptors
+ * @desc: the GPIO descriptor held by this event
+ * @eflags: the event flags this line was requested with
+ * @irq: the interrupt that trigger in response to events on this GPIO
+ * @wait: wait queue that handles blocking reads of events
+ * @events: KFIFO for the GPIO events
+ * @read_lock: mutex lock to protect reads from colliding with adding
+ * new events to the FIFO
+ */
+struct lineevent_state {
+	struct gpio_device *gdev;
+	const char *label;
+	struct gpio_desc *desc;
+	u32 eflags;
+	int irq;
+	wait_queue_head_t wait;
+	DECLARE_KFIFO(events, struct gpioevent_data, 16);
+	struct mutex read_lock;
+};
+
+static unsigned int lineevent_poll(struct file *filep,
+				   struct poll_table_struct *wait)
+{
+	struct lineevent_state *le = filep->private_data;
+	unsigned int events = 0;
+
+	poll_wait(filep, &le->wait, wait);
+
+	if (!kfifo_is_empty(&le->events))
+		events = POLLIN | POLLRDNORM;
+
+	return events;
+}
+
+
+static ssize_t lineevent_read(struct file *filep,
+			      char __user *buf,
+			      size_t count,
+			      loff_t *f_ps)
+{
+	struct lineevent_state *le = filep->private_data;
+	unsigned int copied;
+	int ret;
+
+	if (count < sizeof(struct gpioevent_data))
+		return -EINVAL;
+
+	do {
+		if (kfifo_is_empty(&le->events)) {
+			if (filep->f_flags & O_NONBLOCK)
+				return -EAGAIN;
+
+			ret = wait_event_interruptible(le->wait,
+					!kfifo_is_empty(&le->events));
+			if (ret)
+				return ret;
+		}
+
+		if (mutex_lock_interruptible(&le->read_lock))
+			return -ERESTARTSYS;
+		ret = kfifo_to_user(&le->events, buf, count, &copied);
+		mutex_unlock(&le->read_lock);
+
+		if (ret)
+			return ret;
+
+		/*
+		 * If we couldn't read anything from the fifo (a different
+		 * thread might have been faster) we either return -EAGAIN if
+		 * the file descriptor is non-blocking, otherwise we go back to
+		 * sleep and wait for more data to arrive.
+		 */
+		if (copied == 0 && (filep->f_flags & O_NONBLOCK))
+			return -EAGAIN;
+
+	} while (copied == 0);
+
+	return copied;
+}
+
+static int lineevent_release(struct inode *inode, struct file *filep)
+{
+	struct lineevent_state *le = filep->private_data;
+	struct gpio_device *gdev = le->gdev;
+
+	free_irq(le->irq, le);
+	gpiod_free(le->desc);
+	kfree(le->label);
+	kfree(le);
+	put_device(&gdev->dev);
+	return 0;
+}
+
+static long lineevent_ioctl(struct file *filep, unsigned int cmd,
+			    unsigned long arg)
+{
+	struct lineevent_state *le = filep->private_data;
+	void __user *ip = (void __user *)arg;
+	struct gpiohandle_data ghd;
+
+	/*
+	 * We can get the value for an event line but not set it,
+	 * because it is input by definition.
+	 */
+	if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
+		int val;
+
+		val = gpiod_get_value_cansleep(le->desc);
+		if (val < 0)
+			return val;
+		ghd.values[0] = val;
+
+		if (copy_to_user(ip, &ghd, sizeof(ghd)))
+			return -EFAULT;
+
+		return 0;
+	}
+	return -EINVAL;
+}
+
+#ifdef CONFIG_COMPAT
+static long lineevent_ioctl_compat(struct file *filep, unsigned int cmd,
+				   unsigned long arg)
+{
+	return lineevent_ioctl(filep, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations lineevent_fileops = {
+	.release = lineevent_release,
+	.read = lineevent_read,
+	.poll = lineevent_poll,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+	.unlocked_ioctl = lineevent_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = lineevent_ioctl_compat,
+#endif
+};
+
+static irqreturn_t lineevent_irq_thread(int irq, void *p)
+{
+	struct lineevent_state *le = p;
+	struct gpioevent_data ge;
+	int ret;
+
+	ge.timestamp = ktime_get_real_ns();
+
+	if (le->eflags & GPIOEVENT_REQUEST_BOTH_EDGES) {
+		int level = gpiod_get_value_cansleep(le->desc);
+
+		if (level)
+			/* Emit low-to-high event */
+			ge.id = GPIOEVENT_EVENT_RISING_EDGE;
+		else
+			/* Emit high-to-low event */
+			ge.id = GPIOEVENT_EVENT_FALLING_EDGE;
+	} else if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE) {
+		/* Emit low-to-high event */
+		ge.id = GPIOEVENT_EVENT_RISING_EDGE;
+	} else if (le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE) {
+		/* Emit high-to-low event */
+		ge.id = GPIOEVENT_EVENT_FALLING_EDGE;
+	} else {
+		return IRQ_NONE;
+	}
+
+	ret = kfifo_put(&le->events, ge);
+	if (ret != 0)
+		wake_up_poll(&le->wait, POLLIN);
+
+	return IRQ_HANDLED;
+}
+
+static int lineevent_create(struct gpio_device *gdev, void __user *ip)
+{
+	struct gpioevent_request eventreq;
+	struct lineevent_state *le;
+	struct gpio_desc *desc;
+	u32 offset;
+	u32 lflags;
+	u32 eflags;
+	int fd;
+	int ret;
+	int irqflags = 0;
+
+	if (copy_from_user(&eventreq, ip, sizeof(eventreq)))
+		return -EFAULT;
+
+	le = kzalloc(sizeof(*le), GFP_KERNEL);
+	if (!le)
+		return -ENOMEM;
+	le->gdev = gdev;
+	get_device(&gdev->dev);
+
+	/* Make sure this is terminated */
+	eventreq.consumer_label[sizeof(eventreq.consumer_label)-1] = '\0';
+	if (strlen(eventreq.consumer_label)) {
+		le->label = kstrdup(eventreq.consumer_label,
+				    GFP_KERNEL);
+		if (!le->label) {
+			ret = -ENOMEM;
+			goto out_free_le;
+		}
+	}
+
+	offset = eventreq.lineoffset;
+	lflags = eventreq.handleflags;
+	eflags = eventreq.eventflags;
+
+	/* This is just wrong: we don't look for events on output lines */
+	if (lflags & GPIOHANDLE_REQUEST_OUTPUT) {
+		ret = -EINVAL;
+		goto out_free_label;
+	}
+
+	desc = &gdev->descs[offset];
+	ret = gpiod_request(desc, le->label);
+	if (ret)
+		goto out_free_desc;
+	le->desc = desc;
+	le->eflags = eflags;
+
+	if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW)
+		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+	if (lflags & GPIOHANDLE_REQUEST_OPEN_DRAIN)
+		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
+	if (lflags & GPIOHANDLE_REQUEST_OPEN_SOURCE)
+		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
+
+	ret = gpiod_direction_input(desc);
+	if (ret)
+		goto out_free_desc;
+
+	le->irq = gpiod_to_irq(desc);
+	if (le->irq <= 0) {
+		ret = -ENODEV;
+		goto out_free_desc;
+	}
+
+	if (eflags & GPIOEVENT_REQUEST_RISING_EDGE)
+		irqflags |= IRQF_TRIGGER_RISING;
+	if (eflags & GPIOEVENT_REQUEST_FALLING_EDGE)
+		irqflags |= IRQF_TRIGGER_FALLING;
+	irqflags |= IRQF_ONESHOT;
+	irqflags |= IRQF_SHARED;
+
+	INIT_KFIFO(le->events);
+	init_waitqueue_head(&le->wait);
+	mutex_init(&le->read_lock);
+
+	/* Request a thread to read the events */
+	ret = request_threaded_irq(le->irq,
+			NULL,
+			lineevent_irq_thread,
+			irqflags,
+			le->label,
+			le);
+	if (ret)
+		goto out_free_desc;
+
+	fd = anon_inode_getfd("gpio-event",
+			      &lineevent_fileops,
+			      le,
+			      O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		ret = fd;
+		goto out_free_irq;
+	}
+
+	eventreq.fd = fd;
+	if (copy_to_user(ip, &eventreq, sizeof(eventreq))) {
+		ret = -EFAULT;
+		goto out_free_irq;
+	}
+
+	return 0;
+
+out_free_irq:
+	free_irq(le->irq, le);
+out_free_desc:
+	gpiod_free(le->desc);
+out_free_label:
+	kfree(le->label);
+out_free_le:
+	kfree(le);
+	put_device(&gdev->dev);
+	return ret;
+}
+
 /**
  * gpio_ioctl() - ioctl handler for the GPIO chardev
  */
@@ -385,6 +879,10 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (copy_to_user(ip, &lineinfo, sizeof(lineinfo)))
 			return -EFAULT;
 		return 0;
+	} else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) {
+		return linehandle_create(gdev, ip);
+	} else if (cmd == GPIO_GET_LINEEVENT_IOCTL) {
+		return lineevent_create(gdev, ip);
 	}
 	return -EINVAL;
 }
@@ -548,13 +1046,14 @@ int gpiochip_add_data(struct gpio_chip *chip, void *data)
 	if (chip->parent) {
 		gdev->dev.parent = chip->parent;
 		gdev->dev.of_node = chip->parent->of_node;
-	} else {
+	}
+
 #ifdef CONFIG_OF_GPIO
 	/* If the gpiochip has an assigned OF node this takes precedence */
-		if (chip->of_node)
-			gdev->dev.of_node = chip->of_node;
+	if (chip->of_node)
+		gdev->dev.of_node = chip->of_node;
 #endif
-	}
+
 	gdev->id = ida_simple_get(&gpio_ida, 0, 0, GFP_KERNEL);
 	if (gdev->id < 0) {
 		status = gdev->id;
@@ -2333,7 +2832,7 @@ static struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 
 		desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx,
 						&of_flags);
-		if (!IS_ERR(desc) || (PTR_ERR(desc) == -EPROBE_DEFER))
+		if (!IS_ERR(desc) || (PTR_ERR(desc) != -ENOENT))
 			break;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index 252edba16e36..892d60fb225b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -421,29 +421,6 @@ static int acp_suspend(void *handle)
 
 static int acp_resume(void *handle)
 {
-	int i, ret;
-	struct acp_pm_domain *apd;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	/* return early if no ACP */
-	if (!adev->acp.acp_genpd)
-		return 0;
-
-	/* SMU block will power on ACP irrespective of ACP runtime status.
-	 * Power off explicitly based on genpd ACP runtime status so that ACP
-	 * hw and ACP-genpd status are in sync.
-	 * 'suspend_power_off' represents "Power status before system suspend"
-	*/
-	if (adev->acp.acp_genpd->gpd.suspend_power_off == true) {
-		apd = container_of(&adev->acp.acp_genpd->gpd,
-					struct acp_pm_domain, gpd);
-
-		for (i = 4; i >= 0 ; i--) {
-			ret = acp_suspend_tile(apd->cgs_dev, ACP_TILE_P1 + i);
-			if (ret)
-				pr_err("ACP tile %d tile suspend failed\n", i);
-		}
-	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index e671a7cd3463..6ac717f2056f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -148,40 +148,39 @@ static void rcar_du_vsp_plane_setup(struct rcar_du_vsp_plane *plane)
 	struct rcar_du_vsp_plane_state *state =
 		to_rcar_vsp_plane_state(plane->plane.state);
 	struct drm_framebuffer *fb = plane->plane.state->fb;
-	struct v4l2_rect src;
-	struct v4l2_rect dst;
-	dma_addr_t paddr[2] = { 0, };
-	u32 pixelformat = 0;
+	struct vsp1_du_atomic_config cfg = {
+		.pixelformat = 0,
+		.pitch = fb->pitches[0],
+		.alpha = state->alpha,
+		.zpos = state->zpos,
+	};
 	unsigned int i;
 
-	src.left = state->state.src_x >> 16;
-	src.top = state->state.src_y >> 16;
-	src.width = state->state.src_w >> 16;
-	src.height = state->state.src_h >> 16;
+	cfg.src.left = state->state.src_x >> 16;
+	cfg.src.top = state->state.src_y >> 16;
+	cfg.src.width = state->state.src_w >> 16;
+	cfg.src.height = state->state.src_h >> 16;
 
-	dst.left = state->state.crtc_x;
-	dst.top = state->state.crtc_y;
-	dst.width = state->state.crtc_w;
-	dst.height = state->state.crtc_h;
+	cfg.dst.left = state->state.crtc_x;
+	cfg.dst.top = state->state.crtc_y;
+	cfg.dst.width = state->state.crtc_w;
+	cfg.dst.height = state->state.crtc_h;
 
 	for (i = 0; i < state->format->planes; ++i) {
 		struct drm_gem_cma_object *gem;
 
 		gem = drm_fb_cma_get_gem_obj(fb, i);
-		paddr[i] = gem->paddr + fb->offsets[i];
+		cfg.mem[i] = gem->paddr + fb->offsets[i];
 	}
 
 	for (i = 0; i < ARRAY_SIZE(formats_kms); ++i) {
 		if (formats_kms[i] == state->format->fourcc) {
-			pixelformat = formats_v4l2[i];
+			cfg.pixelformat = formats_v4l2[i];
 			break;
 		}
 	}
 
-	WARN_ON(!pixelformat);
-
-	vsp1_du_atomic_update(plane->vsp->vsp, plane->index, pixelformat,
-			      fb->pitches[0], paddr, &src, &dst);
+	vsp1_du_atomic_update(plane->vsp->vsp, plane->index, &cfg);
 }
 
 static int rcar_du_vsp_plane_atomic_check(struct drm_plane *plane,
@@ -220,8 +219,7 @@ static void rcar_du_vsp_plane_atomic_update(struct drm_plane *plane,
 	if (plane->state->crtc)
 		rcar_du_vsp_plane_setup(rplane);
 	else
-		vsp1_du_atomic_update(rplane->vsp->vsp, rplane->index, 0, 0, 0,
-				      NULL, NULL);
+		vsp1_du_atomic_update(rplane->vsp->vsp, rplane->index, NULL);
 }
 
 static const struct drm_plane_helper_funcs rcar_du_vsp_plane_helper_funcs = {
@@ -269,6 +267,7 @@ static void rcar_du_vsp_plane_reset(struct drm_plane *plane)
 		return;
 
 	state->alpha = 255;
+	state->zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1;
 
 	plane->state = &state->state;
 	plane->state->plane = plane;
@@ -283,6 +282,8 @@ static int rcar_du_vsp_plane_atomic_set_property(struct drm_plane *plane,
 
 	if (property == rcdu->props.alpha)
 		rstate->alpha = val;
+	else if (property == rcdu->props.zpos)
+		rstate->zpos = val;
 	else
 		return -EINVAL;
 
@@ -299,6 +300,8 @@ static int rcar_du_vsp_plane_atomic_get_property(struct drm_plane *plane,
 
 	if (property == rcdu->props.alpha)
 		*val = rstate->alpha;
+	else if (property == rcdu->props.zpos)
+		*val = rstate->zpos;
 	else
 		return -EINVAL;
 
@@ -378,6 +381,8 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp)
 
 		drm_object_attach_property(&plane->plane.base,
 					   rcdu->props.alpha, 255);
+		drm_object_attach_property(&plane->plane.base,
+					   rcdu->props.zpos, 1);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
index df3bf3805c69..510dcc9c6816 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h
@@ -44,6 +44,7 @@ static inline struct rcar_du_vsp_plane *to_rcar_vsp_plane(struct drm_plane *p)
  * @state: base DRM plane state
  * @format: information about the pixel format used by the plane
  * @alpha: value of the plane alpha property
+ * @zpos: value of the plane zpos property
  */
 struct rcar_du_vsp_plane_state {
 	struct drm_plane_state state;
@@ -51,6 +52,7 @@ struct rcar_du_vsp_plane_state {
 	const struct rcar_du_format_info *format;
 
 	unsigned int alpha;
+	unsigned int zpos;
 };
 
 static inline struct rcar_du_vsp_plane_state *
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index af11b658984d..74e5aeaf84f9 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -107,12 +107,11 @@ struct acpi_i2c_lookup {
 	acpi_handle device_handle;
 };
 
-static int acpi_i2c_find_address(struct acpi_resource *ares, void *data)
+static int acpi_i2c_fill_info(struct acpi_resource *ares, void *data)
 {
 	struct acpi_i2c_lookup *lookup = data;
 	struct i2c_board_info *info = lookup->info;
 	struct acpi_resource_i2c_serialbus *sb;
-	acpi_handle adapter_handle;
 	acpi_status status;
 
 	if (info->addr || ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS)
@@ -122,80 +121,102 @@ static int acpi_i2c_find_address(struct acpi_resource *ares, void *data)
 	if (sb->type != ACPI_RESOURCE_SERIAL_TYPE_I2C)
 		return 1;
 
-	/*
-	 * Extract the ResourceSource and make sure that the handle matches
-	 * with the I2C adapter handle.
-	 */
 	status = acpi_get_handle(lookup->device_handle,
 				 sb->resource_source.string_ptr,
-				 &adapter_handle);
-	if (ACPI_SUCCESS(status) && adapter_handle == lookup->adapter_handle) {
-		info->addr = sb->slave_address;
-		if (sb->access_mode == ACPI_I2C_10BIT_MODE)
-			info->flags |= I2C_CLIENT_TEN;
-	}
+				 &lookup->adapter_handle);
+	if (!ACPI_SUCCESS(status))
+		return 1;
+
+	info->addr = sb->slave_address;
+	if (sb->access_mode == ACPI_I2C_10BIT_MODE)
+		info->flags |= I2C_CLIENT_TEN;
 
 	return 1;
 }
 
-static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
-				       void *data, void **return_value)
+static int acpi_i2c_get_info(struct acpi_device *adev,
+			     struct i2c_board_info *info,
+			     acpi_handle *adapter_handle)
 {
-	struct i2c_adapter *adapter = data;
 	struct list_head resource_list;
-	struct acpi_i2c_lookup lookup;
 	struct resource_entry *entry;
-	struct i2c_board_info info;
-	struct acpi_device *adev;
+	struct acpi_i2c_lookup lookup;
 	int ret;
 
-	if (acpi_bus_get_device(handle, &adev))
-		return AE_OK;
-	if (acpi_bus_get_status(adev) || !adev->status.present)
-		return AE_OK;
+	if (acpi_bus_get_status(adev) || !adev->status.present ||
+	    acpi_device_enumerated(adev))
+		return -EINVAL;
 
-	memset(&info, 0, sizeof(info));
-	info.fwnode = acpi_fwnode_handle(adev);
+	memset(info, 0, sizeof(*info));
+	info->fwnode = acpi_fwnode_handle(adev);
 
 	memset(&lookup, 0, sizeof(lookup));
-	lookup.adapter_handle = ACPI_HANDLE(&adapter->dev);
-	lookup.device_handle = handle;
-	lookup.info = &info;
+	lookup.device_handle = acpi_device_handle(adev);
+	lookup.info = info;
 
-	/*
-	 * Look up for I2cSerialBus resource with ResourceSource that
-	 * matches with this adapter.
-	 */
+	/* Look up for I2cSerialBus resource */
 	INIT_LIST_HEAD(&resource_list);
 	ret = acpi_dev_get_resources(adev, &resource_list,
-				     acpi_i2c_find_address, &lookup);
+				     acpi_i2c_fill_info, &lookup);
 	acpi_dev_free_resource_list(&resource_list);
 
-	if (ret < 0 || !info.addr)
-		return AE_OK;
+	if (ret < 0 || !info->addr)
+		return -EINVAL;
+
+	*adapter_handle = lookup.adapter_handle;
 
 	/* Then fill IRQ number if any */
 	ret = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
 	if (ret < 0)
-		return AE_OK;
+		return -EINVAL;
 
 	resource_list_for_each_entry(entry, &resource_list) {
 		if (resource_type(entry->res) == IORESOURCE_IRQ) {
-			info.irq = entry->res->start;
+			info->irq = entry->res->start;
 			break;
 		}
 	}
 
 	acpi_dev_free_resource_list(&resource_list);
 
+	strlcpy(info->type, dev_name(&adev->dev), sizeof(info->type));
+
+	return 0;
+}
+
+static void acpi_i2c_register_device(struct i2c_adapter *adapter,
+				     struct acpi_device *adev,
+				     struct i2c_board_info *info)
+{
 	adev->power.flags.ignore_parent = true;
-	strlcpy(info.type, dev_name(&adev->dev), sizeof(info.type));
-	if (!i2c_new_device(adapter, &info)) {
+	acpi_device_set_enumerated(adev);
+
+	if (!i2c_new_device(adapter, info)) {
 		adev->power.flags.ignore_parent = false;
 		dev_err(&adapter->dev,
 			"failed to add I2C device %s from ACPI\n",
 			dev_name(&adev->dev));
 	}
+}
+
+static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
+				       void *data, void **return_value)
+{
+	struct i2c_adapter *adapter = data;
+	struct acpi_device *adev;
+	acpi_handle adapter_handle;
+	struct i2c_board_info info;
+
+	if (acpi_bus_get_device(handle, &adev))
+		return AE_OK;
+
+	if (acpi_i2c_get_info(adev, &info, &adapter_handle))
+		return AE_OK;
+
+	if (adapter_handle != ACPI_HANDLE(&adapter->dev))
+		return AE_OK;
+
+	acpi_i2c_register_device(adapter, adev, &info);
 
 	return AE_OK;
 }
@@ -225,8 +246,80 @@ static void acpi_i2c_register_devices(struct i2c_adapter *adap)
 		dev_warn(&adap->dev, "failed to enumerate I2C slaves\n");
 }
 
+static int acpi_i2c_match_adapter(struct device *dev, void *data)
+{
+	struct i2c_adapter *adapter = i2c_verify_adapter(dev);
+
+	if (!adapter)
+		return 0;
+
+	return ACPI_HANDLE(dev) == (acpi_handle)data;
+}
+
+static int acpi_i2c_match_device(struct device *dev, void *data)
+{
+	return ACPI_COMPANION(dev) == data;
+}
+
+static struct i2c_adapter *acpi_i2c_find_adapter_by_handle(acpi_handle handle)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&i2c_bus_type, NULL, handle,
+			      acpi_i2c_match_adapter);
+	return dev ? i2c_verify_adapter(dev) : NULL;
+}
+
+static struct i2c_client *acpi_i2c_find_client_by_adev(struct acpi_device *adev)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&i2c_bus_type, NULL, adev, acpi_i2c_match_device);
+	return dev ? i2c_verify_client(dev) : NULL;
+}
+
+static int acpi_i2c_notify(struct notifier_block *nb, unsigned long value,
+			   void *arg)
+{
+	struct acpi_device *adev = arg;
+	struct i2c_board_info info;
+	acpi_handle adapter_handle;
+	struct i2c_adapter *adapter;
+	struct i2c_client *client;
+
+	switch (value) {
+	case ACPI_RECONFIG_DEVICE_ADD:
+		if (acpi_i2c_get_info(adev, &info, &adapter_handle))
+			break;
+
+		adapter = acpi_i2c_find_adapter_by_handle(adapter_handle);
+		if (!adapter)
+			break;
+
+		acpi_i2c_register_device(adapter, adev, &info);
+		break;
+	case ACPI_RECONFIG_DEVICE_REMOVE:
+		if (!acpi_device_enumerated(adev))
+			break;
+
+		client = acpi_i2c_find_client_by_adev(adev);
+		if (!client)
+			break;
+
+		i2c_unregister_device(client);
+		put_device(&client->dev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block i2c_acpi_notifier = {
+	.notifier_call = acpi_i2c_notify,
+};
 #else /* CONFIG_ACPI */
 static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) { }
+extern struct notifier_block i2c_acpi_notifier;
 #endif /* CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_I2C_OPREGION
@@ -1089,6 +1182,8 @@ void i2c_unregister_device(struct i2c_client *client)
 {
 	if (client->dev.of_node)
 		of_node_clear_flag(client->dev.of_node, OF_POPULATED);
+	if (ACPI_COMPANION(&client->dev))
+		acpi_device_clear_enumerated(ACPI_COMPANION(&client->dev));
 	device_unregister(&client->dev);
 }
 EXPORT_SYMBOL_GPL(i2c_unregister_device);
@@ -2117,6 +2212,8 @@ static int __init i2c_init(void)
 
 	if (IS_ENABLED(CONFIG_OF_DYNAMIC))
 		WARN_ON(of_reconfig_notifier_register(&i2c_of_notifier));
+	if (IS_ENABLED(CONFIG_ACPI))
+		WARN_ON(acpi_reconfig_notifier_register(&i2c_acpi_notifier));
 
 	return 0;
 
@@ -2132,6 +2229,8 @@ bus_err:
 
 static void __exit i2c_exit(void)
 {
+	if (IS_ENABLED(CONFIG_ACPI))
+		WARN_ON(acpi_reconfig_notifier_unregister(&i2c_acpi_notifier));
 	if (IS_ENABLED(CONFIG_OF_DYNAMIC))
 		WARN_ON(of_reconfig_notifier_unregister(&i2c_of_notifier));
 	i2c_del_driver(&dummy_driver);
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index ef907fd5ba98..bf9a2ad296ed 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -1770,7 +1770,6 @@ static int ide_cd_probe(ide_drive_t *drive)
 	drive->driver_data = info;
 
 	g->minors = 1;
-	g->driverfs_dev = &drive->gendev;
 	g->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE;
 	if (ide_cdrom_setup(drive)) {
 		put_device(&info->dev);
@@ -1780,7 +1779,7 @@ static int ide_cd_probe(ide_drive_t *drive)
 	ide_cd_read_toc(drive, &sense);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-	add_disk(g);
+	device_add_disk(&drive->gendev, g);
 	return 0;
 
 out_free_disk:
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 474173eb31bb..5887a7a09e37 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -459,9 +459,6 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	   layer. the packet must be complete, as we do not
 	   touch it at all. */
 
-	if (cgc->data_direction == CGC_DATA_WRITE)
-		flags |= REQ_WRITE;
-
 	if (cgc->sense)
 		memset(cgc->sense, 0, sizeof(struct request_sense));
 
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 05dbcce70b0e..e378ef70ed63 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -431,7 +431,7 @@ static int idedisk_prep_fn(struct request_queue *q, struct request *rq)
 	ide_drive_t *drive = q->queuedata;
 	struct ide_cmd *cmd;
 
-	if (!(rq->cmd_flags & REQ_FLUSH))
+	if (req_op(rq) != REQ_OP_FLUSH)
 		return BLKPREP_OK;
 
 	if (rq->special) {
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 2fb5350c5410..f079d8d1d856 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -206,7 +206,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive,
 	memcpy(rq->cmd, pc->c, 12);
 
 	pc->rq = rq;
-	if (rq->cmd_flags & REQ_WRITE)
+	if (cmd == WRITE)
 		pc->flags |= PC_FLAG_WRITING;
 
 	pc->flags |= PC_FLAG_DMA_OK;
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 838996a0039e..e823394ed543 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -412,12 +412,11 @@ static int ide_gd_probe(ide_drive_t *drive)
 	set_capacity(g, ide_gd_capacity(drive));
 
 	g->minors = IDE_DISK_MINORS;
-	g->driverfs_dev = &drive->gendev;
 	g->flags |= GENHD_FL_EXT_DEVT;
 	if (drive->dev_flags & IDE_DFLAG_REMOVABLE)
 		g->flags = GENHD_FL_REMOVABLE;
 	g->fops = &ide_gd_ops;
-	add_disk(g);
+	device_add_disk(&drive->gendev, g);
 	return 0;
 
 out_free_disk:
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b5dd41d13d3d..9b2ef248788d 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -46,8 +46,6 @@
  * to avoid complications with the lapic timer workaround.
  * Have not seen issues with suspend, but may need same workaround here.
  *
- * There is currently no kernel-based automatic probing/loading mechanism
- * if the driver is built as a module.
  */
 
 /* un-comment DEBUG to enable pr_debug() statements */
@@ -60,7 +58,7 @@
 #include <linux/sched.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
@@ -828,6 +826,35 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state dnv_cstates[] = {
+	{
+		.name = "C1-DNV",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 2,
+		.target_residency = 2,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C1E-DNV",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01),
+		.exit_latency = 10,
+		.target_residency = 20,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C6-DNV",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 50,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.enter = NULL }
+};
+
 /**
  * intel_idle
  * @dev: cpuidle_device
@@ -1017,6 +1044,11 @@ static const struct idle_cpu idle_cpu_bxt = {
 	.disable_promotion_to_c1e = true,
 };
 
+static const struct idle_cpu idle_cpu_dnv = {
+	.state_table = dnv_cstates,
+	.disable_promotion_to_c1e = true,
+};
+
 #define ICPU(model, cpu) \
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
 
@@ -1053,9 +1085,9 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(INTEL_FAM6_SKYLAKE_X,		idle_cpu_skx),
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		idle_cpu_knl),
 	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		idle_cpu_bxt),
+	ICPU(INTEL_FAM6_ATOM_DENVERTON,		idle_cpu_dnv),
 	{}
 };
-MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
 
 /*
  * intel_idle_probe()
@@ -1155,7 +1187,10 @@ static unsigned long long irtl_2_usec(unsigned long long irtl)
 {
 	unsigned long long ns;
 
-	ns = irtl_ns_units[(irtl >> 10) & 0x3];
+	if (!irtl)
+		return 0;
+
+	ns = irtl_ns_units[(irtl >> 10) & 0x7];
 
 	return div64_u64((irtl & 0x3FF) * ns, 1000);
 }
@@ -1168,43 +1203,39 @@ static unsigned long long irtl_2_usec(unsigned long long irtl)
 static void bxt_idle_state_table_update(void)
 {
 	unsigned long long msr;
+	unsigned int usec;
 
 	rdmsrl(MSR_PKGC6_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[2].exit_latency = usec;
 		bxt_cstates[2].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC7_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[3].exit_latency = usec;
 		bxt_cstates[3].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC8_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[4].exit_latency = usec;
 		bxt_cstates[4].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC9_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[5].exit_latency = usec;
 		bxt_cstates[5].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC10_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[6].exit_latency = usec;
 		bxt_cstates[6].target_residency = usec;
 	}
@@ -1416,34 +1447,12 @@ static int __init intel_idle_init(void)
 
 	return 0;
 }
+device_initcall(intel_idle_init);
 
-static void __exit intel_idle_exit(void)
-{
-	struct cpuidle_device *dev;
-	int i;
-
-	cpu_notifier_register_begin();
-
-	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
-		on_each_cpu(__setup_broadcast_timer, (void *)false, 1);
-	__unregister_cpu_notifier(&cpu_hotplug_notifier);
-
-	for_each_possible_cpu(i) {
-		dev = per_cpu_ptr(intel_idle_cpuidle_devices, i);
-		cpuidle_unregister_device(dev);
-	}
-
-	cpu_notifier_register_done();
-
-	cpuidle_unregister_driver(&intel_idle_driver);
-	free_percpu(intel_idle_cpuidle_devices);
-}
-
-module_init(intel_idle_init);
-module_exit(intel_idle_exit);
-
+/*
+ * We are not really modular, but we used to support that.  Meaning we also
+ * support "intel_idle.max_cstate=..." at boot and also a read-only export of
+ * it at /sys/module/intel_idle/parameters/max_cstate -- so using module_param
+ * is the easiest way (currently) to continue doing that.
+ */
 module_param(max_cstate, int, 0444);
-
-MODULE_AUTHOR("Len Brown <len.brown@intel.com>");
-MODULE_DESCRIPTION("Cpuidle driver for Intel Hardware v" INTEL_IDLE_VERSION);
-MODULE_LICENSE("GPL");
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index 880c40b23f66..4ea475775d58 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -126,7 +126,7 @@ struct sur40_image_header {
 #define VIDEO_PACKET_SIZE  16384
 
 /* polling interval (ms) */
-#define POLL_INTERVAL 4
+#define POLL_INTERVAL 1
 
 /* maximum number of contacts FIXME: this is a guess? */
 #define MAX_CONTACTS 64
@@ -151,7 +151,6 @@ struct sur40_state {
 	struct mutex lock;
 
 	struct vb2_queue queue;
-	struct vb2_alloc_ctx *alloc_ctx;
 	struct list_head buf_list;
 	spinlock_t qlock;
 	int sequence;
@@ -448,7 +447,7 @@ static void sur40_process_video(struct sur40_state *sur40)
 
 	/* return error if streaming was stopped in the meantime */
 	if (sur40->sequence == -1)
-		goto err_poll;
+		return;
 
 	/* mark as finished */
 	new_buf->vb.vb2_buf.timestamp = ktime_get_ns();
@@ -580,19 +579,13 @@ static int sur40_probe(struct usb_interface *interface,
 	sur40->queue = sur40_queue;
 	sur40->queue.drv_priv = sur40;
 	sur40->queue.lock = &sur40->lock;
+	sur40->queue.dev = sur40->dev;
 
 	/* initialize the queue */
 	error = vb2_queue_init(&sur40->queue);
 	if (error)
 		goto err_unreg_v4l2;
 
-	sur40->alloc_ctx = vb2_dma_sg_init_ctx(sur40->dev);
-	if (IS_ERR(sur40->alloc_ctx)) {
-		dev_err(sur40->dev, "Can't allocate buffer context");
-		error = PTR_ERR(sur40->alloc_ctx);
-		goto err_unreg_v4l2;
-	}
-
 	sur40->vdev = sur40_video_device;
 	sur40->vdev.v4l2_dev = &sur40->v4l2;
 	sur40->vdev.lock = &sur40->lock;
@@ -633,7 +626,6 @@ static void sur40_disconnect(struct usb_interface *interface)
 
 	video_unregister_device(&sur40->vdev);
 	v4l2_device_unregister(&sur40->v4l2);
-	vb2_dma_sg_cleanup_ctx(sur40->alloc_ctx);
 
 	input_unregister_polled_device(sur40->input);
 	input_free_polled_device(sur40->input);
@@ -653,13 +645,10 @@ static void sur40_disconnect(struct usb_interface *interface)
  */
 static int sur40_queue_setup(struct vb2_queue *q,
 		       unsigned int *nbuffers, unsigned int *nplanes,
-		       unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
-	struct sur40_state *sur40 = vb2_get_drv_priv(q);
-
 	if (q->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - q->num_buffers;
-	alloc_ctxs[0] = sur40->alloc_ctx;
 
 	if (*nplanes)
 		return sizes[0] < sur40_video_format.sizeimage ? -EINVAL : 0;
@@ -736,6 +725,7 @@ static int sur40_start_streaming(struct vb2_queue *vq, unsigned int count)
 static void sur40_stop_streaming(struct vb2_queue *vq)
 {
 	struct sur40_state *sur40 = vb2_get_drv_priv(vq);
+	vb2_wait_for_all_buffers(vq);
 	sur40->sequence = -1;
 
 	/* Release all active buffers */
@@ -793,7 +783,6 @@ static int sur40_vidioc_enum_fmt(struct file *file, void *priv,
 {
 	if (f->index != 0)
 		return -EINVAL;
-	strlcpy(f->description, "8-bit greyscale", sizeof(f->description));
 	f->pixelformat = V4L2_PIX_FMT_GREY;
 	f->flags = 0;
 	return 0;
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 85a339030e4b..61c68a1f054a 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -27,11 +27,13 @@ config NVM_DEBUG
 	It is required to create/remove targets without IOCTLs.
 
 config NVM_GENNVM
-	tristate "Generic NVM manager for Open-Channel SSDs"
+	tristate "General Non-Volatile Memory Manager for Open-Channel SSDs"
 	---help---
-	NVM media manager for Open-Channel SSDs that offload management
-	functionality to device, while keeping data placement and garbage
-	collection decisions on the host.
+	Non-volatile memory media manager for Open-Channel SSDs that implements
+	physical media metadata management and block provisioning API.
+
+	This is the standard media manager for using Open-Channel SSDs, and
+	required for targets to be instantiated.
 
 config NVM_RRPC
 	tristate "Round-robin Hybrid Open-Channel SSD target"
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 160c1a6838e1..9ebd2cfbd849 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -18,8 +18,6 @@
  *
  */
 
-#include <linux/blkdev.h>
-#include <linux/blk-mq.h>
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/sem.h>
@@ -28,46 +26,42 @@
 #include <linux/miscdevice.h>
 #include <linux/lightnvm.h>
 #include <linux/sched/sysctl.h>
-#include <uapi/linux/lightnvm.h>
 
 static LIST_HEAD(nvm_tgt_types);
+static DECLARE_RWSEM(nvm_tgtt_lock);
 static LIST_HEAD(nvm_mgrs);
 static LIST_HEAD(nvm_devices);
-static LIST_HEAD(nvm_targets);
 static DECLARE_RWSEM(nvm_lock);
 
-static struct nvm_target *nvm_find_target(const char *name)
+struct nvm_tgt_type *nvm_find_target_type(const char *name, int lock)
 {
-	struct nvm_target *tgt;
+	struct nvm_tgt_type *tmp, *tt = NULL;
 
-	list_for_each_entry(tgt, &nvm_targets, list)
-		if (!strcmp(name, tgt->disk->disk_name))
-			return tgt;
+	if (lock)
+		down_write(&nvm_tgtt_lock);
 
-	return NULL;
-}
-
-static struct nvm_tgt_type *nvm_find_target_type(const char *name)
-{
-	struct nvm_tgt_type *tt;
-
-	list_for_each_entry(tt, &nvm_tgt_types, list)
-		if (!strcmp(name, tt->name))
-			return tt;
+	list_for_each_entry(tmp, &nvm_tgt_types, list)
+		if (!strcmp(name, tmp->name)) {
+			tt = tmp;
+			break;
+		}
 
-	return NULL;
+	if (lock)
+		up_write(&nvm_tgtt_lock);
+	return tt;
 }
+EXPORT_SYMBOL(nvm_find_target_type);
 
 int nvm_register_tgt_type(struct nvm_tgt_type *tt)
 {
 	int ret = 0;
 
-	down_write(&nvm_lock);
-	if (nvm_find_target_type(tt->name))
+	down_write(&nvm_tgtt_lock);
+	if (nvm_find_target_type(tt->name, 0))
 		ret = -EEXIST;
 	else
 		list_add(&tt->list, &nvm_tgt_types);
-	up_write(&nvm_lock);
+	up_write(&nvm_tgtt_lock);
 
 	return ret;
 }
@@ -110,7 +104,7 @@ static struct nvmm_type *nvm_find_mgr_type(const char *name)
 	return NULL;
 }
 
-struct nvmm_type *nvm_init_mgr(struct nvm_dev *dev)
+static struct nvmm_type *nvm_init_mgr(struct nvm_dev *dev)
 {
 	struct nvmm_type *mt;
 	int ret;
@@ -182,20 +176,6 @@ static struct nvm_dev *nvm_find_nvm_dev(const char *name)
 	return NULL;
 }
 
-struct nvm_block *nvm_get_blk_unlocked(struct nvm_dev *dev, struct nvm_lun *lun,
-							unsigned long flags)
-{
-	return dev->mt->get_blk_unlocked(dev, lun, flags);
-}
-EXPORT_SYMBOL(nvm_get_blk_unlocked);
-
-/* Assumes that all valid pages have already been moved on release to bm */
-void nvm_put_blk_unlocked(struct nvm_dev *dev, struct nvm_block *blk)
-{
-	return dev->mt->put_blk_unlocked(dev, blk);
-}
-EXPORT_SYMBOL(nvm_put_blk_unlocked);
-
 struct nvm_block *nvm_get_blk(struct nvm_dev *dev, struct nvm_lun *lun,
 							unsigned long flags)
 {
@@ -210,6 +190,12 @@ void nvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk)
 }
 EXPORT_SYMBOL(nvm_put_blk);
 
+void nvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type)
+{
+	return dev->mt->mark_blk(dev, ppa, type);
+}
+EXPORT_SYMBOL(nvm_mark_blk);
+
 int nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	return dev->mt->submit_io(dev, rqd);
@@ -251,9 +237,10 @@ void nvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 EXPORT_SYMBOL(nvm_generic_to_addr_mode);
 
 int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
-				struct ppa_addr *ppas, int nr_ppas, int vblk)
+			const struct ppa_addr *ppas, int nr_ppas, int vblk)
 {
 	int i, plane_cnt, pl_idx;
+	struct ppa_addr ppa;
 
 	if ((!vblk || dev->plane_mode == NVM_PLANE_SINGLE) && nr_ppas == 1) {
 		rqd->nr_ppas = nr_ppas;
@@ -278,8 +265,9 @@ int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
 
 		for (i = 0; i < nr_ppas; i++) {
 			for (pl_idx = 0; pl_idx < plane_cnt; pl_idx++) {
-				ppas[i].g.pl = pl_idx;
-				rqd->ppa_list[(pl_idx * nr_ppas) + i] = ppas[i];
+				ppa = ppas[i];
+				ppa.g.pl = pl_idx;
+				rqd->ppa_list[(pl_idx * nr_ppas) + i] = ppa;
 			}
 		}
 	}
@@ -337,7 +325,7 @@ static void nvm_end_io_sync(struct nvm_rq *rqd)
 	complete(waiting);
 }
 
-int __nvm_submit_ppa(struct nvm_dev *dev, struct nvm_rq *rqd, int opcode,
+static int __nvm_submit_ppa(struct nvm_dev *dev, struct nvm_rq *rqd, int opcode,
 						int flags, void *buf, int len)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
@@ -367,7 +355,9 @@ int __nvm_submit_ppa(struct nvm_dev *dev, struct nvm_rq *rqd, int opcode,
 	/* Prevent hang_check timer from firing at us during very long I/O */
 	hang_check = sysctl_hung_task_timeout_secs;
 	if (hang_check)
-		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
+		while (!wait_for_completion_io_timeout(&wait,
+							hang_check * (HZ/2)))
+			;
 	else
 		wait_for_completion_io(&wait);
 
@@ -510,7 +500,8 @@ static int nvm_init_mlc_tbl(struct nvm_dev *dev, struct nvm_id_group *grp)
 	/* The lower page table encoding consists of a list of bytes, where each
 	 * has a lower and an upper half. The first half byte maintains the
 	 * increment value and every value after is an offset added to the
-	 * previous incrementation value */
+	 * previous incrementation value
+	 */
 	dev->lptbl[0] = mlc->pairs[0] & 0xF;
 	for (i = 1; i < dev->lps_per_blk; i++) {
 		p = mlc->pairs[i >> 1];
@@ -596,42 +587,11 @@ err_fmtype:
 	return ret;
 }
 
-static void nvm_remove_target(struct nvm_target *t)
-{
-	struct nvm_tgt_type *tt = t->type;
-	struct gendisk *tdisk = t->disk;
-	struct request_queue *q = tdisk->queue;
-
-	lockdep_assert_held(&nvm_lock);
-
-	del_gendisk(tdisk);
-	blk_cleanup_queue(q);
-
-	if (tt->exit)
-		tt->exit(tdisk->private_data);
-
-	put_disk(tdisk);
-
-	list_del(&t->list);
-	kfree(t);
-}
-
 static void nvm_free_mgr(struct nvm_dev *dev)
 {
-	struct nvm_target *tgt, *tmp;
-
 	if (!dev->mt)
 		return;
 
-	down_write(&nvm_lock);
-	list_for_each_entry_safe(tgt, tmp, &nvm_targets, list) {
-		if (tgt->dev != dev)
-			continue;
-
-		nvm_remove_target(tgt);
-	}
-	up_write(&nvm_lock);
-
 	dev->mt->unregister_mgr(dev);
 	dev->mt = NULL;
 }
@@ -778,91 +738,6 @@ void nvm_unregister(char *disk_name)
 }
 EXPORT_SYMBOL(nvm_unregister);
 
-static const struct block_device_operations nvm_fops = {
-	.owner		= THIS_MODULE,
-};
-
-static int nvm_create_target(struct nvm_dev *dev,
-						struct nvm_ioctl_create *create)
-{
-	struct nvm_ioctl_create_simple *s = &create->conf.s;
-	struct request_queue *tqueue;
-	struct gendisk *tdisk;
-	struct nvm_tgt_type *tt;
-	struct nvm_target *t;
-	void *targetdata;
-
-	if (!dev->mt) {
-		pr_info("nvm: device has no media manager registered.\n");
-		return -ENODEV;
-	}
-
-	down_write(&nvm_lock);
-	tt = nvm_find_target_type(create->tgttype);
-	if (!tt) {
-		pr_err("nvm: target type %s not found\n", create->tgttype);
-		up_write(&nvm_lock);
-		return -EINVAL;
-	}
-
-	t = nvm_find_target(create->tgtname);
-	if (t) {
-		pr_err("nvm: target name already exists.\n");
-		up_write(&nvm_lock);
-		return -EINVAL;
-	}
-	up_write(&nvm_lock);
-
-	t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
-	if (!t)
-		return -ENOMEM;
-
-	tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
-	if (!tqueue)
-		goto err_t;
-	blk_queue_make_request(tqueue, tt->make_rq);
-
-	tdisk = alloc_disk(0);
-	if (!tdisk)
-		goto err_queue;
-
-	sprintf(tdisk->disk_name, "%s", create->tgtname);
-	tdisk->flags = GENHD_FL_EXT_DEVT;
-	tdisk->major = 0;
-	tdisk->first_minor = 0;
-	tdisk->fops = &nvm_fops;
-	tdisk->queue = tqueue;
-
-	targetdata = tt->init(dev, tdisk, s->lun_begin, s->lun_end);
-	if (IS_ERR(targetdata))
-		goto err_init;
-
-	tdisk->private_data = targetdata;
-	tqueue->queuedata = targetdata;
-
-	blk_queue_max_hw_sectors(tqueue, 8 * dev->ops->max_phys_sect);
-
-	set_capacity(tdisk, tt->capacity(targetdata));
-	add_disk(tdisk);
-
-	t->type = tt;
-	t->disk = tdisk;
-	t->dev = dev;
-
-	down_write(&nvm_lock);
-	list_add_tail(&t->list, &nvm_targets);
-	up_write(&nvm_lock);
-
-	return 0;
-err_init:
-	put_disk(tdisk);
-err_queue:
-	blk_cleanup_queue(tqueue);
-err_t:
-	kfree(t);
-	return -ENOMEM;
-}
-
 static int __nvm_configure_create(struct nvm_ioctl_create *create)
 {
 	struct nvm_dev *dev;
@@ -871,11 +746,17 @@ static int __nvm_configure_create(struct nvm_ioctl_create *create)
 	down_write(&nvm_lock);
 	dev = nvm_find_nvm_dev(create->dev);
 	up_write(&nvm_lock);
+
 	if (!dev) {
 		pr_err("nvm: device not found\n");
 		return -EINVAL;
 	}
 
+	if (!dev->mt) {
+		pr_info("nvm: device has no media manager registered.\n");
+		return -ENODEV;
+	}
+
 	if (create->conf.type != NVM_CONFIG_TYPE_SIMPLE) {
 		pr_err("nvm: config type not valid\n");
 		return -EINVAL;
@@ -888,25 +769,7 @@ static int __nvm_configure_create(struct nvm_ioctl_create *create)
 		return -EINVAL;
 	}
 
-	return nvm_create_target(dev, create);
-}
-
-static int __nvm_configure_remove(struct nvm_ioctl_remove *remove)
-{
-	struct nvm_target *t;
-
-	down_write(&nvm_lock);
-	t = nvm_find_target(remove->tgtname);
-	if (!t) {
-		pr_err("nvm: target \"%s\" doesn't exist.\n", remove->tgtname);
-		up_write(&nvm_lock);
-		return -EINVAL;
-	}
-
-	nvm_remove_target(t);
-	up_write(&nvm_lock);
-
-	return 0;
+	return dev->mt->create_tgt(dev, create);
 }
 
 #ifdef CONFIG_NVM_DEBUG
@@ -941,8 +804,9 @@ static int nvm_configure_show(const char *val)
 static int nvm_configure_remove(const char *val)
 {
 	struct nvm_ioctl_remove remove;
+	struct nvm_dev *dev;
 	char opcode;
-	int ret;
+	int ret = 0;
 
 	ret = sscanf(val, "%c %256s", &opcode, remove.tgtname);
 	if (ret != 2) {
@@ -952,7 +816,13 @@ static int nvm_configure_remove(const char *val)
 
 	remove.flags = 0;
 
-	return __nvm_configure_remove(&remove);
+	list_for_each_entry(dev, &nvm_devices, devices) {
+		ret = dev->mt->remove_tgt(dev, &remove);
+		if (!ret)
+			break;
+	}
+
+	return ret;
 }
 
 static int nvm_configure_create(const char *val)
@@ -1149,6 +1019,8 @@ static long nvm_ioctl_dev_create(struct file *file, void __user *arg)
 static long nvm_ioctl_dev_remove(struct file *file, void __user *arg)
 {
 	struct nvm_ioctl_remove remove;
+	struct nvm_dev *dev;
+	int ret = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1163,7 +1035,13 @@ static long nvm_ioctl_dev_remove(struct file *file, void __user *arg)
 		return -EINVAL;
 	}
 
-	return __nvm_configure_remove(&remove);
+	list_for_each_entry(dev, &nvm_devices, devices) {
+		ret = dev->mt->remove_tgt(dev, &remove);
+		if (!ret)
+			break;
+	}
+
+	return ret;
 }
 
 static void nvm_setup_nvm_sb_info(struct nvm_sb_info *info)
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index ec9fb6876e38..b74174c6d021 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -15,22 +15,160 @@
  * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
  * USA.
  *
- * Implementation of a generic nvm manager for Open-Channel SSDs.
+ * Implementation of a general nvm manager for Open-Channel SSDs.
  */
 
 #include "gennvm.h"
 
-static int gennvm_get_area(struct nvm_dev *dev, sector_t *lba, sector_t len)
+static struct nvm_target *gen_find_target(struct gen_dev *gn, const char *name)
 {
-	struct gen_nvm *gn = dev->mp;
-	struct gennvm_area *area, *prev, *next;
+	struct nvm_target *tgt;
+
+	list_for_each_entry(tgt, &gn->targets, list)
+		if (!strcmp(name, tgt->disk->disk_name))
+			return tgt;
+
+	return NULL;
+}
+
+static const struct block_device_operations gen_fops = {
+	.owner		= THIS_MODULE,
+};
+
+static int gen_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
+{
+	struct gen_dev *gn = dev->mp;
+	struct nvm_ioctl_create_simple *s = &create->conf.s;
+	struct request_queue *tqueue;
+	struct gendisk *tdisk;
+	struct nvm_tgt_type *tt;
+	struct nvm_target *t;
+	void *targetdata;
+
+	tt = nvm_find_target_type(create->tgttype, 1);
+	if (!tt) {
+		pr_err("nvm: target type %s not found\n", create->tgttype);
+		return -EINVAL;
+	}
+
+	mutex_lock(&gn->lock);
+	t = gen_find_target(gn, create->tgtname);
+	if (t) {
+		pr_err("nvm: target name already exists.\n");
+		mutex_unlock(&gn->lock);
+		return -EINVAL;
+	}
+	mutex_unlock(&gn->lock);
+
+	t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
+	if (!t)
+		return -ENOMEM;
+
+	tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
+	if (!tqueue)
+		goto err_t;
+	blk_queue_make_request(tqueue, tt->make_rq);
+
+	tdisk = alloc_disk(0);
+	if (!tdisk)
+		goto err_queue;
+
+	sprintf(tdisk->disk_name, "%s", create->tgtname);
+	tdisk->flags = GENHD_FL_EXT_DEVT;
+	tdisk->major = 0;
+	tdisk->first_minor = 0;
+	tdisk->fops = &gen_fops;
+	tdisk->queue = tqueue;
+
+	targetdata = tt->init(dev, tdisk, s->lun_begin, s->lun_end);
+	if (IS_ERR(targetdata))
+		goto err_init;
+
+	tdisk->private_data = targetdata;
+	tqueue->queuedata = targetdata;
+
+	blk_queue_max_hw_sectors(tqueue, 8 * dev->ops->max_phys_sect);
+
+	set_capacity(tdisk, tt->capacity(targetdata));
+	add_disk(tdisk);
+
+	t->type = tt;
+	t->disk = tdisk;
+	t->dev = dev;
+
+	mutex_lock(&gn->lock);
+	list_add_tail(&t->list, &gn->targets);
+	mutex_unlock(&gn->lock);
+
+	return 0;
+err_init:
+	put_disk(tdisk);
+err_queue:
+	blk_cleanup_queue(tqueue);
+err_t:
+	kfree(t);
+	return -ENOMEM;
+}
+
+static void __gen_remove_target(struct nvm_target *t)
+{
+	struct nvm_tgt_type *tt = t->type;
+	struct gendisk *tdisk = t->disk;
+	struct request_queue *q = tdisk->queue;
+
+	del_gendisk(tdisk);
+	blk_cleanup_queue(q);
+
+	if (tt->exit)
+		tt->exit(tdisk->private_data);
+
+	put_disk(tdisk);
+
+	list_del(&t->list);
+	kfree(t);
+}
+
+/**
+ * gen_remove_tgt - Removes a target from the media manager
+ * @dev:	device
+ * @remove:	ioctl structure with target name to remove.
+ *
+ * Returns:
+ * 0: on success
+ * 1: on not found
+ * <0: on error
+ */
+static int gen_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
+{
+	struct gen_dev *gn = dev->mp;
+	struct nvm_target *t;
+
+	if (!gn)
+		return 1;
+
+	mutex_lock(&gn->lock);
+	t = gen_find_target(gn, remove->tgtname);
+	if (!t) {
+		mutex_unlock(&gn->lock);
+		return 1;
+	}
+	__gen_remove_target(t);
+	mutex_unlock(&gn->lock);
+
+	return 0;
+}
+
+static int gen_get_area(struct nvm_dev *dev, sector_t *lba, sector_t len)
+{
+	struct gen_dev *gn = dev->mp;
+	struct gen_area *area, *prev, *next;
 	sector_t begin = 0;
 	sector_t max_sectors = (dev->sec_size * dev->total_secs) >> 9;
 
 	if (len > max_sectors)
 		return -EINVAL;
 
-	area = kmalloc(sizeof(struct gennvm_area), GFP_KERNEL);
+	area = kmalloc(sizeof(struct gen_area), GFP_KERNEL);
 	if (!area)
 		return -ENOMEM;
 
@@ -64,10 +202,10 @@ static int gennvm_get_area(struct nvm_dev *dev, sector_t *lba, sector_t len)
 	return 0;
 }
 
-static void gennvm_put_area(struct nvm_dev *dev, sector_t begin)
+static void gen_put_area(struct nvm_dev *dev, sector_t begin)
 {
-	struct gen_nvm *gn = dev->mp;
-	struct gennvm_area *area;
+	struct gen_dev *gn = dev->mp;
+	struct gen_area *area;
 
 	spin_lock(&dev->lock);
 	list_for_each_entry(area, &gn->area_list, list) {
@@ -82,27 +220,27 @@ static void gennvm_put_area(struct nvm_dev *dev, sector_t begin)
 	spin_unlock(&dev->lock);
 }
 
-static void gennvm_blocks_free(struct nvm_dev *dev)
+static void gen_blocks_free(struct nvm_dev *dev)
 {
-	struct gen_nvm *gn = dev->mp;
+	struct gen_dev *gn = dev->mp;
 	struct gen_lun *lun;
 	int i;
 
-	gennvm_for_each_lun(gn, lun, i) {
+	gen_for_each_lun(gn, lun, i) {
 		if (!lun->vlun.blocks)
 			break;
 		vfree(lun->vlun.blocks);
 	}
 }
 
-static void gennvm_luns_free(struct nvm_dev *dev)
+static void gen_luns_free(struct nvm_dev *dev)
 {
-	struct gen_nvm *gn = dev->mp;
+	struct gen_dev *gn = dev->mp;
 
 	kfree(gn->luns);
 }
 
-static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
+static int gen_luns_init(struct nvm_dev *dev, struct gen_dev *gn)
 {
 	struct gen_lun *lun;
 	int i;
@@ -111,7 +249,7 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	if (!gn->luns)
 		return -ENOMEM;
 
-	gennvm_for_each_lun(gn, lun, i) {
+	gen_for_each_lun(gn, lun, i) {
 		spin_lock_init(&lun->vlun.lock);
 		INIT_LIST_HEAD(&lun->free_list);
 		INIT_LIST_HEAD(&lun->used_list);
@@ -122,14 +260,11 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
 		lun->vlun.lun_id = i % dev->luns_per_chnl;
 		lun->vlun.chnl_id = i / dev->luns_per_chnl;
 		lun->vlun.nr_free_blocks = dev->blks_per_lun;
-		lun->vlun.nr_open_blocks = 0;
-		lun->vlun.nr_closed_blocks = 0;
-		lun->vlun.nr_bad_blocks = 0;
 	}
 	return 0;
 }
 
-static int gennvm_block_bb(struct gen_nvm *gn, struct ppa_addr ppa,
+static int gen_block_bb(struct gen_dev *gn, struct ppa_addr ppa,
 							u8 *blks, int nr_blks)
 {
 	struct nvm_dev *dev = gn->dev;
@@ -149,17 +284,16 @@ static int gennvm_block_bb(struct gen_nvm *gn, struct ppa_addr ppa,
 
 		blk = &lun->vlun.blocks[i];
 		list_move_tail(&blk->list, &lun->bb_list);
-		lun->vlun.nr_bad_blocks++;
 		lun->vlun.nr_free_blocks--;
 	}
 
 	return 0;
 }
 
-static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
+static int gen_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
 {
 	struct nvm_dev *dev = private;
-	struct gen_nvm *gn = dev->mp;
+	struct gen_dev *gn = dev->mp;
 	u64 elba = slba + nlb;
 	struct gen_lun *lun;
 	struct nvm_block *blk;
@@ -167,7 +301,7 @@ static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
 	int lun_id;
 
 	if (unlikely(elba > dev->total_secs)) {
-		pr_err("gennvm: L2P data from device is out of bounds!\n");
+		pr_err("gen: L2P data from device is out of bounds!\n");
 		return -EINVAL;
 	}
 
@@ -175,7 +309,7 @@ static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
 		u64 pba = le64_to_cpu(entries[i]);
 
 		if (unlikely(pba >= dev->total_secs && pba != U64_MAX)) {
-			pr_err("gennvm: L2P data entry is out of bounds!\n");
+			pr_err("gen: L2P data entry is out of bounds!\n");
 			return -EINVAL;
 		}
 
@@ -200,16 +334,15 @@ static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
 			 * block state. The block is assumed to be open.
 			 */
 			list_move_tail(&blk->list, &lun->used_list);
-			blk->state = NVM_BLK_ST_OPEN;
+			blk->state = NVM_BLK_ST_TGT;
 			lun->vlun.nr_free_blocks--;
-			lun->vlun.nr_open_blocks++;
 		}
 	}
 
 	return 0;
 }
 
-static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
+static int gen_blocks_init(struct nvm_dev *dev, struct gen_dev *gn)
 {
 	struct gen_lun *lun;
 	struct nvm_block *block;
@@ -222,7 +355,7 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	if (!blks)
 		return -ENOMEM;
 
-	gennvm_for_each_lun(gn, lun, lun_iter) {
+	gen_for_each_lun(gn, lun, lun_iter) {
 		lun->vlun.blocks = vzalloc(sizeof(struct nvm_block) *
 							dev->blks_per_lun);
 		if (!lun->vlun.blocks) {
@@ -256,20 +389,20 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 
 			ret = nvm_get_bb_tbl(dev, ppa, blks);
 			if (ret)
-				pr_err("gennvm: could not get BB table\n");
+				pr_err("gen: could not get BB table\n");
 
-			ret = gennvm_block_bb(gn, ppa, blks, nr_blks);
+			ret = gen_block_bb(gn, ppa, blks, nr_blks);
 			if (ret)
-				pr_err("gennvm: BB table map failed\n");
+				pr_err("gen: BB table map failed\n");
 		}
 	}
 
 	if ((dev->identity.dom & NVM_RSP_L2P) && dev->ops->get_l2p_tbl) {
 		ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_secs,
-							gennvm_block_map, dev);
+							gen_block_map, dev);
 		if (ret) {
-			pr_err("gennvm: could not read L2P table.\n");
-			pr_warn("gennvm: default block initialization");
+			pr_err("gen: could not read L2P table.\n");
+			pr_warn("gen: default block initialization");
 		}
 	}
 
@@ -277,67 +410,79 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	return 0;
 }
 
-static void gennvm_free(struct nvm_dev *dev)
+static void gen_free(struct nvm_dev *dev)
 {
-	gennvm_blocks_free(dev);
-	gennvm_luns_free(dev);
+	gen_blocks_free(dev);
+	gen_luns_free(dev);
 	kfree(dev->mp);
 	dev->mp = NULL;
 }
 
-static int gennvm_register(struct nvm_dev *dev)
+static int gen_register(struct nvm_dev *dev)
 {
-	struct gen_nvm *gn;
+	struct gen_dev *gn;
 	int ret;
 
 	if (!try_module_get(THIS_MODULE))
 		return -ENODEV;
 
-	gn = kzalloc(sizeof(struct gen_nvm), GFP_KERNEL);
+	gn = kzalloc(sizeof(struct gen_dev), GFP_KERNEL);
 	if (!gn)
 		return -ENOMEM;
 
 	gn->dev = dev;
 	gn->nr_luns = dev->nr_luns;
 	INIT_LIST_HEAD(&gn->area_list);
+	mutex_init(&gn->lock);
+	INIT_LIST_HEAD(&gn->targets);
 	dev->mp = gn;
 
-	ret = gennvm_luns_init(dev, gn);
+	ret = gen_luns_init(dev, gn);
 	if (ret) {
-		pr_err("gennvm: could not initialize luns\n");
+		pr_err("gen: could not initialize luns\n");
 		goto err;
 	}
 
-	ret = gennvm_blocks_init(dev, gn);
+	ret = gen_blocks_init(dev, gn);
 	if (ret) {
-		pr_err("gennvm: could not initialize blocks\n");
+		pr_err("gen: could not initialize blocks\n");
 		goto err;
 	}
 
 	return 1;
 err:
-	gennvm_free(dev);
+	gen_free(dev);
 	module_put(THIS_MODULE);
 	return ret;
 }
 
-static void gennvm_unregister(struct nvm_dev *dev)
+static void gen_unregister(struct nvm_dev *dev)
 {
-	gennvm_free(dev);
+	struct gen_dev *gn = dev->mp;
+	struct nvm_target *t, *tmp;
+
+	mutex_lock(&gn->lock);
+	list_for_each_entry_safe(t, tmp, &gn->targets, list) {
+		if (t->dev != dev)
+			continue;
+		__gen_remove_target(t);
+	}
+	mutex_unlock(&gn->lock);
+
+	gen_free(dev);
 	module_put(THIS_MODULE);
 }
 
-static struct nvm_block *gennvm_get_blk_unlocked(struct nvm_dev *dev,
+static struct nvm_block *gen_get_blk(struct nvm_dev *dev,
 				struct nvm_lun *vlun, unsigned long flags)
 {
 	struct gen_lun *lun = container_of(vlun, struct gen_lun, vlun);
 	struct nvm_block *blk = NULL;
 	int is_gc = flags & NVM_IOTYPE_GC;
 
-	assert_spin_locked(&vlun->lock);
-
+	spin_lock(&vlun->lock);
 	if (list_empty(&lun->free_list)) {
-		pr_err_ratelimited("gennvm: lun %u have no free pages available",
+		pr_err_ratelimited("gen: lun %u have no free pages available",
 								lun->vlun.id);
 		goto out;
 	}
@@ -346,88 +491,58 @@ static struct nvm_block *gennvm_get_blk_unlocked(struct nvm_dev *dev,
 		goto out;
 
 	blk = list_first_entry(&lun->free_list, struct nvm_block, list);
-	list_move_tail(&blk->list, &lun->used_list);
-	blk->state = NVM_BLK_ST_OPEN;
 
+	list_move_tail(&blk->list, &lun->used_list);
+	blk->state = NVM_BLK_ST_TGT;
 	lun->vlun.nr_free_blocks--;
-	lun->vlun.nr_open_blocks++;
-
 out:
-	return blk;
-}
-
-static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev,
-				struct nvm_lun *vlun, unsigned long flags)
-{
-	struct nvm_block *blk;
-
-	spin_lock(&vlun->lock);
-	blk = gennvm_get_blk_unlocked(dev, vlun, flags);
 	spin_unlock(&vlun->lock);
 	return blk;
 }
 
-static void gennvm_put_blk_unlocked(struct nvm_dev *dev, struct nvm_block *blk)
+static void gen_put_blk(struct nvm_dev *dev, struct nvm_block *blk)
 {
 	struct nvm_lun *vlun = blk->lun;
 	struct gen_lun *lun = container_of(vlun, struct gen_lun, vlun);
 
-	assert_spin_locked(&vlun->lock);
-
-	if (blk->state & NVM_BLK_ST_OPEN) {
-		list_move_tail(&blk->list, &lun->free_list);
-		lun->vlun.nr_open_blocks--;
-		lun->vlun.nr_free_blocks++;
-		blk->state = NVM_BLK_ST_FREE;
-	} else if (blk->state & NVM_BLK_ST_CLOSED) {
+	spin_lock(&vlun->lock);
+	if (blk->state & NVM_BLK_ST_TGT) {
 		list_move_tail(&blk->list, &lun->free_list);
-		lun->vlun.nr_closed_blocks--;
 		lun->vlun.nr_free_blocks++;
 		blk->state = NVM_BLK_ST_FREE;
 	} else if (blk->state & NVM_BLK_ST_BAD) {
 		list_move_tail(&blk->list, &lun->bb_list);
-		lun->vlun.nr_bad_blocks++;
 		blk->state = NVM_BLK_ST_BAD;
 	} else {
 		WARN_ON_ONCE(1);
-		pr_err("gennvm: erroneous block type (%lu -> %u)\n",
+		pr_err("gen: erroneous block type (%lu -> %u)\n",
 							blk->id, blk->state);
 		list_move_tail(&blk->list, &lun->bb_list);
-		lun->vlun.nr_bad_blocks++;
-		blk->state = NVM_BLK_ST_BAD;
 	}
-}
-
-static void gennvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk)
-{
-	struct nvm_lun *vlun = blk->lun;
-
-	spin_lock(&vlun->lock);
-	gennvm_put_blk_unlocked(dev, blk);
 	spin_unlock(&vlun->lock);
 }
 
-static void gennvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type)
+static void gen_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type)
 {
-	struct gen_nvm *gn = dev->mp;
+	struct gen_dev *gn = dev->mp;
 	struct gen_lun *lun;
 	struct nvm_block *blk;
 
-	pr_debug("gennvm: ppa  (ch: %u lun: %u blk: %u pg: %u) -> %u\n",
+	pr_debug("gen: ppa  (ch: %u lun: %u blk: %u pg: %u) -> %u\n",
 			ppa.g.ch, ppa.g.lun, ppa.g.blk, ppa.g.pg, type);
 
 	if (unlikely(ppa.g.ch > dev->nr_chnls ||
 					ppa.g.lun > dev->luns_per_chnl ||
 					ppa.g.blk > dev->blks_per_lun)) {
 		WARN_ON_ONCE(1);
-		pr_err("gennvm: ppa broken (ch: %u > %u lun: %u > %u blk: %u > %u",
+		pr_err("gen: ppa broken (ch: %u > %u lun: %u > %u blk: %u > %u",
 				ppa.g.ch, dev->nr_chnls,
 				ppa.g.lun, dev->luns_per_chnl,
 				ppa.g.blk, dev->blks_per_lun);
 		return;
 	}
 
-	lun = &gn->luns[ppa.g.lun * ppa.g.ch];
+	lun = &gn->luns[(dev->luns_per_chnl * ppa.g.ch) + ppa.g.lun];
 	blk = &lun->vlun.blocks[ppa.g.blk];
 
 	/* will be moved to bb list on put_blk from target */
@@ -435,9 +550,9 @@ static void gennvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type)
 }
 
 /*
- * mark block bad in gennvm. It is expected that the target recovers separately
+ * mark block bad in gen. It is expected that the target recovers separately
  */
-static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
+static void gen_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	int bit = -1;
 	int max_secs = dev->ops->max_phys_sect;
@@ -447,25 +562,25 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
 
 	/* look up blocks and mark them as bad */
 	if (rqd->nr_ppas == 1) {
-		gennvm_mark_blk(dev, rqd->ppa_addr, NVM_BLK_ST_BAD);
+		gen_mark_blk(dev, rqd->ppa_addr, NVM_BLK_ST_BAD);
 		return;
 	}
 
 	while ((bit = find_next_bit(comp_bits, max_secs, bit + 1)) < max_secs)
-		gennvm_mark_blk(dev, rqd->ppa_list[bit], NVM_BLK_ST_BAD);
+		gen_mark_blk(dev, rqd->ppa_list[bit], NVM_BLK_ST_BAD);
 }
 
-static void gennvm_end_io(struct nvm_rq *rqd)
+static void gen_end_io(struct nvm_rq *rqd)
 {
 	struct nvm_tgt_instance *ins = rqd->ins;
 
 	if (rqd->error == NVM_RSP_ERR_FAILWRITE)
-		gennvm_mark_blk_bad(rqd->dev, rqd);
+		gen_mark_blk_bad(rqd->dev, rqd);
 
 	ins->tt->end_io(rqd);
 }
 
-static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
+static int gen_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	if (!dev->ops->submit_io)
 		return -ENODEV;
@@ -474,11 +589,11 @@ static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	nvm_generic_to_addr_mode(dev, rqd);
 
 	rqd->dev = dev;
-	rqd->end_io = gennvm_end_io;
+	rqd->end_io = gen_end_io;
 	return dev->ops->submit_io(dev, rqd);
 }
 
-static int gennvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk,
+static int gen_erase_blk(struct nvm_dev *dev, struct nvm_block *blk,
 							unsigned long flags)
 {
 	struct ppa_addr addr = block_to_ppa(dev, blk);
@@ -486,19 +601,19 @@ static int gennvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk,
 	return nvm_erase_ppa(dev, &addr, 1);
 }
 
-static int gennvm_reserve_lun(struct nvm_dev *dev, int lunid)
+static int gen_reserve_lun(struct nvm_dev *dev, int lunid)
 {
 	return test_and_set_bit(lunid, dev->lun_map);
 }
 
-static void gennvm_release_lun(struct nvm_dev *dev, int lunid)
+static void gen_release_lun(struct nvm_dev *dev, int lunid)
 {
 	WARN_ON(!test_and_clear_bit(lunid, dev->lun_map));
 }
 
-static struct nvm_lun *gennvm_get_lun(struct nvm_dev *dev, int lunid)
+static struct nvm_lun *gen_get_lun(struct nvm_dev *dev, int lunid)
 {
-	struct gen_nvm *gn = dev->mp;
+	struct gen_dev *gn = dev->mp;
 
 	if (unlikely(lunid >= dev->nr_luns))
 		return NULL;
@@ -506,66 +621,62 @@ static struct nvm_lun *gennvm_get_lun(struct nvm_dev *dev, int lunid)
 	return &gn->luns[lunid].vlun;
 }
 
-static void gennvm_lun_info_print(struct nvm_dev *dev)
+static void gen_lun_info_print(struct nvm_dev *dev)
 {
-	struct gen_nvm *gn = dev->mp;
+	struct gen_dev *gn = dev->mp;
 	struct gen_lun *lun;
 	unsigned int i;
 
 
-	gennvm_for_each_lun(gn, lun, i) {
+	gen_for_each_lun(gn, lun, i) {
 		spin_lock(&lun->vlun.lock);
 
-		pr_info("%s: lun%8u\t%u\t%u\t%u\t%u\n",
-				dev->name, i,
-				lun->vlun.nr_free_blocks,
-				lun->vlun.nr_open_blocks,
-				lun->vlun.nr_closed_blocks,
-				lun->vlun.nr_bad_blocks);
+		pr_info("%s: lun%8u\t%u\n", dev->name, i,
+						lun->vlun.nr_free_blocks);
 
 		spin_unlock(&lun->vlun.lock);
 	}
 }
 
-static struct nvmm_type gennvm = {
+static struct nvmm_type gen = {
 	.name			= "gennvm",
 	.version		= {0, 1, 0},
 
-	.register_mgr		= gennvm_register,
-	.unregister_mgr		= gennvm_unregister,
+	.register_mgr		= gen_register,
+	.unregister_mgr		= gen_unregister,
 
-	.get_blk_unlocked	= gennvm_get_blk_unlocked,
-	.put_blk_unlocked	= gennvm_put_blk_unlocked,
+	.create_tgt		= gen_create_tgt,
+	.remove_tgt		= gen_remove_tgt,
 
-	.get_blk		= gennvm_get_blk,
-	.put_blk		= gennvm_put_blk,
+	.get_blk		= gen_get_blk,
+	.put_blk		= gen_put_blk,
 
-	.submit_io		= gennvm_submit_io,
-	.erase_blk		= gennvm_erase_blk,
+	.submit_io		= gen_submit_io,
+	.erase_blk		= gen_erase_blk,
 
-	.mark_blk		= gennvm_mark_blk,
+	.mark_blk		= gen_mark_blk,
 
-	.get_lun		= gennvm_get_lun,
-	.reserve_lun		= gennvm_reserve_lun,
-	.release_lun		= gennvm_release_lun,
-	.lun_info_print		= gennvm_lun_info_print,
+	.get_lun		= gen_get_lun,
+	.reserve_lun		= gen_reserve_lun,
+	.release_lun		= gen_release_lun,
+	.lun_info_print		= gen_lun_info_print,
 
-	.get_area		= gennvm_get_area,
-	.put_area		= gennvm_put_area,
+	.get_area		= gen_get_area,
+	.put_area		= gen_put_area,
 
 };
 
-static int __init gennvm_module_init(void)
+static int __init gen_module_init(void)
 {
-	return nvm_register_mgr(&gennvm);
+	return nvm_register_mgr(&gen);
 }
 
-static void gennvm_module_exit(void)
+static void gen_module_exit(void)
 {
-	nvm_unregister_mgr(&gennvm);
+	nvm_unregister_mgr(&gen);
 }
 
-module_init(gennvm_module_init);
-module_exit(gennvm_module_exit);
+module_init(gen_module_init);
+module_exit(gen_module_exit);
 MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("Generic media manager for Open-Channel SSDs");
+MODULE_DESCRIPTION("General media manager for Open-Channel SSDs");
diff --git a/drivers/lightnvm/gennvm.h b/drivers/lightnvm/gennvm.h
index 04d7c23cfc61..8ecfa817d21d 100644
--- a/drivers/lightnvm/gennvm.h
+++ b/drivers/lightnvm/gennvm.h
@@ -34,20 +34,24 @@ struct gen_lun {
 					 */
 };
 
-struct gen_nvm {
+struct gen_dev {
 	struct nvm_dev *dev;
 
 	int nr_luns;
 	struct gen_lun *luns;
 	struct list_head area_list;
+
+	struct mutex lock;
+	struct list_head targets;
 };
 
-struct gennvm_area {
+struct gen_area {
 	struct list_head list;
 	sector_t begin;
 	sector_t end;	/* end is excluded */
 };
-#define gennvm_for_each_lun(bm, lun, i) \
+
+#define gen_for_each_lun(bm, lun, i) \
 		for ((i) = 0, lun = &(bm)->luns[0]; \
 			(i) < (bm)->nr_luns; (i)++, lun = &(bm)->luns[(i)])
 
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 2103e97a974f..37fcaadbf80c 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -48,7 +48,7 @@ static void rrpc_page_invalidate(struct rrpc *rrpc, struct rrpc_addr *a)
 }
 
 static void rrpc_invalidate_range(struct rrpc *rrpc, sector_t slba,
-								unsigned len)
+							unsigned int len)
 {
 	sector_t i;
 
@@ -96,10 +96,13 @@ static void rrpc_discard(struct rrpc *rrpc, struct bio *bio)
 	sector_t len = bio->bi_iter.bi_size / RRPC_EXPOSED_PAGE_SIZE;
 	struct nvm_rq *rqd;
 
-	do {
+	while (1) {
 		rqd = rrpc_inflight_laddr_acquire(rrpc, slba, len);
+		if (rqd)
+			break;
+
 		schedule();
-	} while (!rqd);
+	}
 
 	if (IS_ERR(rqd)) {
 		pr_err("rrpc: unable to acquire inflight IO\n");
@@ -172,39 +175,32 @@ static struct ppa_addr rrpc_ppa_to_gaddr(struct nvm_dev *dev, u64 addr)
 }
 
 /* requires lun->lock taken */
-static void rrpc_set_lun_cur(struct rrpc_lun *rlun, struct rrpc_block *rblk)
+static void rrpc_set_lun_cur(struct rrpc_lun *rlun, struct rrpc_block *new_rblk,
+						struct rrpc_block **cur_rblk)
 {
 	struct rrpc *rrpc = rlun->rrpc;
 
-	BUG_ON(!rblk);
-
-	if (rlun->cur) {
-		spin_lock(&rlun->cur->lock);
-		WARN_ON(!block_is_full(rrpc, rlun->cur));
-		spin_unlock(&rlun->cur->lock);
+	if (*cur_rblk) {
+		spin_lock(&(*cur_rblk)->lock);
+		WARN_ON(!block_is_full(rrpc, *cur_rblk));
+		spin_unlock(&(*cur_rblk)->lock);
 	}
-	rlun->cur = rblk;
+	*cur_rblk = new_rblk;
 }
 
 static struct rrpc_block *rrpc_get_blk(struct rrpc *rrpc, struct rrpc_lun *rlun,
 							unsigned long flags)
 {
-	struct nvm_lun *lun = rlun->parent;
 	struct nvm_block *blk;
 	struct rrpc_block *rblk;
 
-	spin_lock(&lun->lock);
-	blk = nvm_get_blk_unlocked(rrpc->dev, rlun->parent, flags);
+	blk = nvm_get_blk(rrpc->dev, rlun->parent, flags);
 	if (!blk) {
 		pr_err("nvm: rrpc: cannot get new block from media manager\n");
-		spin_unlock(&lun->lock);
 		return NULL;
 	}
 
 	rblk = rrpc_get_rblk(rlun, blk->id);
-	list_add_tail(&rblk->list, &rlun->open_list);
-	spin_unlock(&lun->lock);
-
 	blk->priv = rblk;
 	bitmap_zero(rblk->invalid_pages, rrpc->dev->sec_per_blk);
 	rblk->next_page = 0;
@@ -216,13 +212,7 @@ static struct rrpc_block *rrpc_get_blk(struct rrpc *rrpc, struct rrpc_lun *rlun,
 
 static void rrpc_put_blk(struct rrpc *rrpc, struct rrpc_block *rblk)
 {
-	struct rrpc_lun *rlun = rblk->rlun;
-	struct nvm_lun *lun = rlun->parent;
-
-	spin_lock(&lun->lock);
-	nvm_put_blk_unlocked(rrpc->dev, rblk->parent);
-	list_del(&rblk->list);
-	spin_unlock(&lun->lock);
+	nvm_put_blk(rrpc->dev, rblk->parent);
 }
 
 static void rrpc_put_blks(struct rrpc *rrpc)
@@ -342,7 +332,7 @@ try:
 
 		/* Perform read to do GC */
 		bio->bi_iter.bi_sector = rrpc_get_sector(rev->addr);
-		bio->bi_rw = READ;
+		bio_set_op_attrs(bio,  REQ_OP_READ, 0);
 		bio->bi_private = &wait;
 		bio->bi_end_io = rrpc_end_sync_bio;
 
@@ -364,7 +354,7 @@ try:
 		reinit_completion(&wait);
 
 		bio->bi_iter.bi_sector = rrpc_get_sector(rev->addr);
-		bio->bi_rw = WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 		bio->bi_private = &wait;
 		bio->bi_end_io = rrpc_end_sync_bio;
 
@@ -508,21 +498,11 @@ static void rrpc_gc_queue(struct work_struct *work)
 	struct rrpc *rrpc = gcb->rrpc;
 	struct rrpc_block *rblk = gcb->rblk;
 	struct rrpc_lun *rlun = rblk->rlun;
-	struct nvm_lun *lun = rblk->parent->lun;
-	struct nvm_block *blk = rblk->parent;
 
 	spin_lock(&rlun->lock);
 	list_add_tail(&rblk->prio, &rlun->prio_list);
 	spin_unlock(&rlun->lock);
 
-	spin_lock(&lun->lock);
-	lun->nr_open_blocks--;
-	lun->nr_closed_blocks++;
-	blk->state &= ~NVM_BLK_ST_OPEN;
-	blk->state |= NVM_BLK_ST_CLOSED;
-	list_move_tail(&rblk->list, &rlun->closed_list);
-	spin_unlock(&lun->lock);
-
 	mempool_free(gcb, rrpc->gcb_pool);
 	pr_debug("nvm: block '%lu' is full, allow GC (sched)\n",
 							rblk->parent->id);
@@ -596,21 +576,20 @@ out:
 	return addr;
 }
 
-/* Simple round-robin Logical to physical address translation.
- *
- * Retrieve the mapping using the active append point. Then update the ap for
- * the next write to the disk.
+/* Map logical address to a physical page. The mapping implements a round robin
+ * approach and allocates a page from the next lun available.
  *
- * Returns rrpc_addr with the physical address and block. Remember to return to
- * rrpc->addr_cache when request is finished.
+ * Returns rrpc_addr with the physical address and block. Returns NULL if no
+ * blocks in the next rlun are available.
  */
 static struct rrpc_addr *rrpc_map_page(struct rrpc *rrpc, sector_t laddr,
 								int is_gc)
 {
 	struct rrpc_lun *rlun;
-	struct rrpc_block *rblk;
+	struct rrpc_block *rblk, **cur_rblk;
 	struct nvm_lun *lun;
 	u64 paddr;
+	int gc_force = 0;
 
 	rlun = rrpc_get_lun_rr(rrpc, is_gc);
 	lun = rlun->parent;
@@ -618,41 +597,65 @@ static struct rrpc_addr *rrpc_map_page(struct rrpc *rrpc, sector_t laddr,
 	if (!is_gc && lun->nr_free_blocks < rrpc->nr_luns * 4)
 		return NULL;
 
-	spin_lock(&rlun->lock);
+	/*
+	 * page allocation steps:
+	 * 1. Try to allocate new page from current rblk
+	 * 2a. If succeed, proceed to map it in and return
+	 * 2b. If fail, first try to allocate a new block from media manger,
+	 *     and then retry step 1. Retry until the normal block pool is
+	 *     exhausted.
+	 * 3. If exhausted, and garbage collector is requesting the block,
+	 *    go to the reserved block and retry step 1.
+	 *    In the case that this fails as well, or it is not GC
+	 *    requesting, report not able to retrieve a block and let the
+	 *    caller handle further processing.
+	 */
 
+	spin_lock(&rlun->lock);
+	cur_rblk = &rlun->cur;
 	rblk = rlun->cur;
 retry:
 	paddr = rrpc_alloc_addr(rrpc, rblk);
 
-	if (paddr == ADDR_EMPTY) {
-		rblk = rrpc_get_blk(rrpc, rlun, 0);
-		if (rblk) {
-			rrpc_set_lun_cur(rlun, rblk);
-			goto retry;
-		}
+	if (paddr != ADDR_EMPTY)
+		goto done;
 
-		if (is_gc) {
-			/* retry from emergency gc block */
-			paddr = rrpc_alloc_addr(rrpc, rlun->gc_cur);
-			if (paddr == ADDR_EMPTY) {
-				rblk = rrpc_get_blk(rrpc, rlun, 1);
-				if (!rblk) {
-					pr_err("rrpc: no more blocks");
-					goto err;
-				}
-
-				rlun->gc_cur = rblk;
-				paddr = rrpc_alloc_addr(rrpc, rlun->gc_cur);
-			}
-			rblk = rlun->gc_cur;
-		}
+	if (!list_empty(&rlun->wblk_list)) {
+new_blk:
+		rblk = list_first_entry(&rlun->wblk_list, struct rrpc_block,
+									prio);
+		rrpc_set_lun_cur(rlun, rblk, cur_rblk);
+		list_del(&rblk->prio);
+		goto retry;
+	}
+	spin_unlock(&rlun->lock);
+
+	rblk = rrpc_get_blk(rrpc, rlun, gc_force);
+	if (rblk) {
+		spin_lock(&rlun->lock);
+		list_add_tail(&rblk->prio, &rlun->wblk_list);
+		/*
+		 * another thread might already have added a new block,
+		 * Therefore, make sure that one is used, instead of the
+		 * one just added.
+		 */
+		goto new_blk;
 	}
 
+	if (unlikely(is_gc) && !gc_force) {
+		/* retry from emergency gc block */
+		cur_rblk = &rlun->gc_cur;
+		rblk = rlun->gc_cur;
+		gc_force = 1;
+		spin_lock(&rlun->lock);
+		goto retry;
+	}
+
+	pr_err("rrpc: failed to allocate new block\n");
+	return NULL;
+done:
 	spin_unlock(&rlun->lock);
 	return rrpc_update_map(rrpc, laddr, rblk, paddr);
-err:
-	spin_unlock(&rlun->lock);
-	return NULL;
 }
 
 static void rrpc_run_gc(struct rrpc *rrpc, struct rrpc_block *rblk)
@@ -850,14 +853,14 @@ static int rrpc_setup_rq(struct rrpc *rrpc, struct bio *bio,
 			return NVM_IO_ERR;
 		}
 
-		if (bio_rw(bio) == WRITE)
+		if (bio_op(bio) == REQ_OP_WRITE)
 			return rrpc_write_ppalist_rq(rrpc, bio, rqd, flags,
 									npages);
 
 		return rrpc_read_ppalist_rq(rrpc, bio, rqd, flags, npages);
 	}
 
-	if (bio_rw(bio) == WRITE)
+	if (bio_op(bio) == REQ_OP_WRITE)
 		return rrpc_write_rq(rrpc, bio, rqd, flags);
 
 	return rrpc_read_rq(rrpc, bio, rqd, flags);
@@ -908,7 +911,7 @@ static blk_qc_t rrpc_make_rq(struct request_queue *q, struct bio *bio)
 	struct nvm_rq *rqd;
 	int err;
 
-	if (bio->bi_rw & REQ_DISCARD) {
+	if (bio_op(bio) == REQ_OP_DISCARD) {
 		rrpc_discard(rrpc, bio);
 		return BLK_QC_T_NONE;
 	}
@@ -1196,8 +1199,7 @@ static int rrpc_luns_init(struct rrpc *rrpc, int lun_begin, int lun_end)
 
 		rlun->rrpc = rrpc;
 		INIT_LIST_HEAD(&rlun->prio_list);
-		INIT_LIST_HEAD(&rlun->open_list);
-		INIT_LIST_HEAD(&rlun->closed_list);
+		INIT_LIST_HEAD(&rlun->wblk_list);
 
 		INIT_WORK(&rlun->ws_gc, rrpc_lun_gc);
 		spin_lock_init(&rlun->lock);
@@ -1338,14 +1340,13 @@ static int rrpc_luns_configure(struct rrpc *rrpc)
 		rblk = rrpc_get_blk(rrpc, rlun, 0);
 		if (!rblk)
 			goto err;
-
-		rrpc_set_lun_cur(rlun, rblk);
+		rrpc_set_lun_cur(rlun, rblk, &rlun->cur);
 
 		/* Emergency gc block */
 		rblk = rrpc_get_blk(rrpc, rlun, 1);
 		if (!rblk)
 			goto err;
-		rlun->gc_cur = rblk;
+		rrpc_set_lun_cur(rlun, rblk, &rlun->gc_cur);
 	}
 
 	return 0;
diff --git a/drivers/lightnvm/rrpc.h b/drivers/lightnvm/rrpc.h
index 87e84b5fc1cc..5e87d52cb983 100644
--- a/drivers/lightnvm/rrpc.h
+++ b/drivers/lightnvm/rrpc.h
@@ -56,7 +56,6 @@ struct rrpc_block {
 	struct nvm_block *parent;
 	struct rrpc_lun *rlun;
 	struct list_head prio;
-	struct list_head list;
 
 #define MAX_INVALID_PAGES_STORAGE 8
 	/* Bitmap for invalid page intries */
@@ -77,13 +76,7 @@ struct rrpc_lun {
 	struct rrpc_block *blocks;	/* Reference to block allocation */
 
 	struct list_head prio_list;	/* Blocks that may be GC'ed */
-	struct list_head open_list;	/* In-use open blocks. These are blocks
-					 * that can be both written to and read
-					 * from
-					 */
-	struct list_head closed_list;	/* In-use closed blocks. These are
-					 * blocks that can _only_ be read from
-					 */
+	struct list_head wblk_list;	/* Queued blocks to be written to */
 
 	struct work_struct ws_gc;
 
@@ -188,7 +181,7 @@ static inline int request_intersects(struct rrpc_inflight_rq *r,
 }
 
 static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr,
-			     unsigned pages, struct rrpc_inflight_rq *r)
+			     unsigned int pages, struct rrpc_inflight_rq *r)
 {
 	sector_t laddr_end = laddr + pages - 1;
 	struct rrpc_inflight_rq *rtmp;
@@ -213,7 +206,7 @@ static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr,
 }
 
 static inline int rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr,
-				 unsigned pages,
+				 unsigned int pages,
 				 struct rrpc_inflight_rq *r)
 {
 	BUG_ON((laddr + pages) > rrpc->nr_sects);
diff --git a/drivers/lightnvm/sysblk.c b/drivers/lightnvm/sysblk.c
index 994697ac786e..a75bd28aaca3 100644
--- a/drivers/lightnvm/sysblk.c
+++ b/drivers/lightnvm/sysblk.c
@@ -39,7 +39,8 @@ static inline int scan_ppa_idx(int row, int blkid)
 	return (row * MAX_BLKS_PR_SYSBLK) + blkid;
 }
 
-void nvm_sysblk_to_cpu(struct nvm_sb_info *info, struct nvm_system_block *sb)
+static void nvm_sysblk_to_cpu(struct nvm_sb_info *info,
+			      struct nvm_system_block *sb)
 {
 	info->seqnr = be32_to_cpu(sb->seqnr);
 	info->erase_cnt = be32_to_cpu(sb->erase_cnt);
@@ -48,7 +49,8 @@ void nvm_sysblk_to_cpu(struct nvm_sb_info *info, struct nvm_system_block *sb)
 	info->fs_ppa.ppa = be64_to_cpu(sb->fs_ppa);
 }
 
-void nvm_cpu_to_sysblk(struct nvm_system_block *sb, struct nvm_sb_info *info)
+static void nvm_cpu_to_sysblk(struct nvm_system_block *sb,
+			      struct nvm_sb_info *info)
 {
 	sb->magic = cpu_to_be32(NVM_SYSBLK_MAGIC);
 	sb->seqnr = cpu_to_be32(info->seqnr);
@@ -86,7 +88,7 @@ static int nvm_setup_sysblks(struct nvm_dev *dev, struct ppa_addr *sysblk_ppas)
 	return nr_rows;
 }
 
-void nvm_setup_sysblk_scan(struct nvm_dev *dev, struct sysblk_scan *s,
+static void nvm_setup_sysblk_scan(struct nvm_dev *dev, struct sysblk_scan *s,
 						struct ppa_addr *sysblk_ppas)
 {
 	memset(s, 0, sizeof(struct sysblk_scan));
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 52ba8dd82821..3cbda1af87a0 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -3,7 +3,8 @@
 #
 
 dm-mod-y	+= dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
-		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o
+		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o \
+		   dm-rq.o
 dm-multipath-y	+= dm-path-selector.o dm-mpath.o
 dm-snapshot-y	+= dm-snap.o dm-exception-store.o dm-snap-transient.o \
 		    dm-snap-persistent.o
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index eab505ee0027..76f7534d1dd1 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -294,10 +294,10 @@ static void bch_btree_node_read(struct btree *b)
 	closure_init_stack(&cl);
 
 	bio = bch_bbio_alloc(b->c);
-	bio->bi_rw	= REQ_META|READ_SYNC;
 	bio->bi_iter.bi_size = KEY_SIZE(&b->key) << 9;
 	bio->bi_end_io	= btree_node_read_endio;
 	bio->bi_private	= &cl;
+	bio_set_op_attrs(bio, REQ_OP_READ, REQ_META|READ_SYNC);
 
 	bch_bio_map(bio, b->keys.set[0].data);
 
@@ -396,8 +396,8 @@ static void do_btree_node_write(struct btree *b)
 
 	b->bio->bi_end_io	= btree_node_write_endio;
 	b->bio->bi_private	= cl;
-	b->bio->bi_rw		= REQ_META|WRITE_SYNC|REQ_FUA;
 	b->bio->bi_iter.bi_size	= roundup(set_bytes(i), block_bytes(b->c));
+	bio_set_op_attrs(b->bio, REQ_OP_WRITE, REQ_META|WRITE_SYNC|REQ_FUA);
 	bch_bio_map(b->bio, i);
 
 	/*
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 9eaf1d6e8302..864e673aec39 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -112,7 +112,7 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl)
 EXPORT_SYMBOL(closure_wait);
 
 /**
- * closure_sync - sleep until a closure a closure has nothing left to wait on
+ * closure_sync - sleep until a closure has nothing left to wait on
  *
  * Sleeps until the refcount hits 1 - the thread that's running the closure owns
  * the last refcount.
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 782cc2c8a185..9b2fe2d3e3a9 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -31,7 +31,8 @@
  * passing it, as you might expect, the function to run when nothing is pending
  * and the workqueue to run that function out of.
  *
- * continue_at() also, critically, is a macro that returns the calling function.
+ * continue_at() also, critically, requires a 'return' immediately following the
+ * location where this macro is referenced, to return to the calling function.
  * There's good reason for this.
  *
  * To use safely closures asynchronously, they must always have a refcount while
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 8b1f1d5c1819..c28df164701e 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -52,9 +52,10 @@ void bch_btree_verify(struct btree *b)
 	bio->bi_bdev		= PTR_CACHE(b->c, &b->key, 0)->bdev;
 	bio->bi_iter.bi_sector	= PTR_OFFSET(&b->key, 0);
 	bio->bi_iter.bi_size	= KEY_SIZE(&v->key) << 9;
+	bio_set_op_attrs(bio, REQ_OP_READ, REQ_META|READ_SYNC);
 	bch_bio_map(bio, sorted);
 
-	submit_bio_wait(REQ_META|READ_SYNC, bio);
+	submit_bio_wait(bio);
 	bch_bbio_free(bio, b->c);
 
 	memcpy(ondisk, sorted, KEY_SIZE(&v->key) << 9);
@@ -113,11 +114,12 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 	check = bio_clone(bio, GFP_NOIO);
 	if (!check)
 		return;
+	bio_set_op_attrs(check, REQ_OP_READ, READ_SYNC);
 
 	if (bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
-	submit_bio_wait(READ_SYNC, check);
+	submit_bio_wait(check);
 
 	bio_for_each_segment(bv, bio, iter) {
 		void *p1 = kmap_atomic(bv.bv_page);
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 86a0bb87124e..e97b0acf7b8d 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -25,7 +25,6 @@ struct bio *bch_bbio_alloc(struct cache_set *c)
 	struct bio *bio = &b->bio;
 
 	bio_init(bio);
-	bio->bi_flags		|= BIO_POOL_NONE << BIO_POOL_OFFSET;
 	bio->bi_max_vecs	 = bucket_pages(c);
 	bio->bi_io_vec		 = bio->bi_inline_vecs;
 
@@ -111,7 +110,7 @@ void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
 	struct bbio *b = container_of(bio, struct bbio, bio);
 	struct cache *ca = PTR_CACHE(c, &b->key, 0);
 
-	unsigned threshold = bio->bi_rw & REQ_WRITE
+	unsigned threshold = op_is_write(bio_op(bio))
 		? c->congested_write_threshold_us
 		: c->congested_read_threshold_us;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 29eba7219b01..6925023e12d4 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -54,11 +54,11 @@ reread:		left = ca->sb.bucket_size - offset;
 		bio_reset(bio);
 		bio->bi_iter.bi_sector	= bucket + offset;
 		bio->bi_bdev	= ca->bdev;
-		bio->bi_rw	= READ;
 		bio->bi_iter.bi_size	= len << 9;
 
 		bio->bi_end_io	= journal_read_endio;
 		bio->bi_private = &cl;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		bch_bio_map(bio, data);
 
 		closure_bio_submit(bio, &cl);
@@ -418,7 +418,7 @@ static void journal_discard_work(struct work_struct *work)
 	struct journal_device *ja =
 		container_of(work, struct journal_device, discard_work);
 
-	submit_bio(0, &ja->discard_bio);
+	submit_bio(&ja->discard_bio);
 }
 
 static void do_journal_discard(struct cache *ca)
@@ -449,10 +449,10 @@ static void do_journal_discard(struct cache *ca)
 		atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT);
 
 		bio_init(bio);
+		bio_set_op_attrs(bio, REQ_OP_DISCARD, 0);
 		bio->bi_iter.bi_sector	= bucket_to_sector(ca->set,
 						ca->sb.d[ja->discard_idx]);
 		bio->bi_bdev		= ca->bdev;
-		bio->bi_rw		= REQ_WRITE|REQ_DISCARD;
 		bio->bi_max_vecs	= 1;
 		bio->bi_io_vec		= bio->bi_inline_vecs;
 		bio->bi_iter.bi_size	= bucket_bytes(ca);
@@ -626,11 +626,12 @@ static void journal_write_unlocked(struct closure *cl)
 		bio_reset(bio);
 		bio->bi_iter.bi_sector	= PTR_OFFSET(k, i);
 		bio->bi_bdev	= ca->bdev;
-		bio->bi_rw	= REQ_WRITE|REQ_SYNC|REQ_META|REQ_FLUSH|REQ_FUA;
 		bio->bi_iter.bi_size = sectors << 9;
 
 		bio->bi_end_io	= journal_write_endio;
 		bio->bi_private = w;
+		bio_set_op_attrs(bio, REQ_OP_WRITE,
+				 REQ_SYNC|REQ_META|REQ_PREFLUSH|REQ_FUA);
 		bch_bio_map(bio, w->data);
 
 		trace_bcache_journal_write(bio);
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index b929fc944e9c..1881319f2298 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -163,7 +163,7 @@ static void read_moving(struct cache_set *c)
 		moving_init(io);
 		bio = &io->bio.bio;
 
-		bio->bi_rw	= READ;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		bio->bi_end_io	= read_moving_endio;
 
 		if (bio_alloc_pages(bio, GFP_KERNEL))
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 25fa8445bb24..69f16f43f8ab 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -205,10 +205,10 @@ static void bch_data_insert_start(struct closure *cl)
 		return bch_data_invalidate(cl);
 
 	/*
-	 * Journal writes are marked REQ_FLUSH; if the original write was a
+	 * Journal writes are marked REQ_PREFLUSH; if the original write was a
 	 * flush, it'll wait on the journal write.
 	 */
-	bio->bi_rw &= ~(REQ_FLUSH|REQ_FUA);
+	bio->bi_rw &= ~(REQ_PREFLUSH|REQ_FUA);
 
 	do {
 		unsigned i;
@@ -253,7 +253,7 @@ static void bch_data_insert_start(struct closure *cl)
 		trace_bcache_cache_insert(k);
 		bch_keylist_push(&op->insert_keys);
 
-		n->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(n, REQ_OP_WRITE, 0);
 		bch_submit_bbio(n, op->c, k, 0);
 	} while (n != bio);
 
@@ -378,12 +378,12 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 
 	if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
 	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
-	    (bio->bi_rw & REQ_DISCARD))
+	    (bio_op(bio) == REQ_OP_DISCARD))
 		goto skip;
 
 	if (mode == CACHE_MODE_NONE ||
 	    (mode == CACHE_MODE_WRITEAROUND &&
-	     (bio->bi_rw & REQ_WRITE)))
+	     op_is_write(bio_op(bio))))
 		goto skip;
 
 	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
@@ -404,7 +404,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 
 	if (!congested &&
 	    mode == CACHE_MODE_WRITEBACK &&
-	    (bio->bi_rw & REQ_WRITE) &&
+	    op_is_write(bio_op(bio)) &&
 	    (bio->bi_rw & REQ_SYNC))
 		goto rescale;
 
@@ -657,7 +657,7 @@ static inline struct search *search_alloc(struct bio *bio,
 	s->cache_miss		= NULL;
 	s->d			= d;
 	s->recoverable		= 1;
-	s->write		= (bio->bi_rw & REQ_WRITE) != 0;
+	s->write		= op_is_write(bio_op(bio));
 	s->read_dirty_data	= 0;
 	s->start_time		= jiffies;
 
@@ -668,7 +668,7 @@ static inline struct search *search_alloc(struct bio *bio,
 	s->iop.write_prio	= 0;
 	s->iop.error		= 0;
 	s->iop.flags		= 0;
-	s->iop.flush_journal	= (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0;
+	s->iop.flush_journal	= (bio->bi_rw & (REQ_PREFLUSH|REQ_FUA)) != 0;
 	s->iop.wq		= bcache_wq;
 
 	return s;
@@ -899,7 +899,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 	 * But check_overlapping drops dirty keys for which io hasn't started,
 	 * so we still want to call it.
 	 */
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		s->iop.bypass = true;
 
 	if (should_writeback(dc, s->orig_bio,
@@ -913,22 +913,22 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 		s->iop.bio = s->orig_bio;
 		bio_get(s->iop.bio);
 
-		if (!(bio->bi_rw & REQ_DISCARD) ||
+		if ((bio_op(bio) != REQ_OP_DISCARD) ||
 		    blk_queue_discard(bdev_get_queue(dc->bdev)))
 			closure_bio_submit(bio, cl);
 	} else if (s->iop.writeback) {
 		bch_writeback_add(dc);
 		s->iop.bio = bio;
 
-		if (bio->bi_rw & REQ_FLUSH) {
+		if (bio->bi_rw & REQ_PREFLUSH) {
 			/* Also need to send a flush to the backing device */
 			struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0,
 							     dc->disk.bio_split);
 
-			flush->bi_rw	= WRITE_FLUSH;
 			flush->bi_bdev	= bio->bi_bdev;
 			flush->bi_end_io = request_endio;
 			flush->bi_private = cl;
+			bio_set_op_attrs(flush, REQ_OP_WRITE, WRITE_FLUSH);
 
 			closure_bio_submit(flush, cl);
 		}
@@ -992,7 +992,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 				cached_dev_read(dc, s);
 		}
 	} else {
-		if ((bio->bi_rw & REQ_DISCARD) &&
+		if ((bio_op(bio) == REQ_OP_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
 			bio_endio(bio);
 		else
@@ -1103,7 +1103,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
 					&KEY(d->id, bio_end_sector(bio), 0));
 
-		s->iop.bypass		= (bio->bi_rw & REQ_DISCARD) != 0;
+		s->iop.bypass		= (bio_op(bio) == REQ_OP_DISCARD) != 0;
 		s->iop.writeback	= true;
 		s->iop.bio		= bio;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index f5dbb4e884d8..88ef6d14cce3 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -134,7 +134,6 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	case BCACHE_SB_VERSION_CDEV:
 	case BCACHE_SB_VERSION_CDEV_WITH_UUID:
 		sb->nbuckets	= le64_to_cpu(s->nbuckets);
-		sb->block_size	= le16_to_cpu(s->block_size);
 		sb->bucket_size	= le16_to_cpu(s->bucket_size);
 
 		sb->nr_in_set	= le16_to_cpu(s->nr_in_set);
@@ -212,8 +211,8 @@ static void __write_super(struct cache_sb *sb, struct bio *bio)
 	unsigned i;
 
 	bio->bi_iter.bi_sector	= SB_SECTOR;
-	bio->bi_rw		= REQ_SYNC|REQ_META;
 	bio->bi_iter.bi_size	= SB_SIZE;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC|REQ_META);
 	bch_bio_map(bio, NULL);
 
 	out->offset		= cpu_to_le64(sb->offset);
@@ -238,7 +237,7 @@ static void __write_super(struct cache_sb *sb, struct bio *bio)
 	pr_debug("ver %llu, flags %llu, seq %llu",
 		 sb->version, sb->flags, sb->seq);
 
-	submit_bio(REQ_WRITE, bio);
+	submit_bio(bio);
 }
 
 static void bch_write_bdev_super_unlock(struct closure *cl)
@@ -333,7 +332,7 @@ static void uuid_io_unlock(struct closure *cl)
 	up(&c->uuid_write_mutex);
 }
 
-static void uuid_io(struct cache_set *c, unsigned long rw,
+static void uuid_io(struct cache_set *c, int op, unsigned long op_flags,
 		    struct bkey *k, struct closure *parent)
 {
 	struct closure *cl = &c->uuid_write;
@@ -348,21 +347,22 @@ static void uuid_io(struct cache_set *c, unsigned long rw,
 	for (i = 0; i < KEY_PTRS(k); i++) {
 		struct bio *bio = bch_bbio_alloc(c);
 
-		bio->bi_rw	= REQ_SYNC|REQ_META|rw;
+		bio->bi_rw	= REQ_SYNC|REQ_META|op_flags;
 		bio->bi_iter.bi_size = KEY_SIZE(k) << 9;
 
 		bio->bi_end_io	= uuid_endio;
 		bio->bi_private = cl;
+		bio_set_op_attrs(bio, op, REQ_SYNC|REQ_META|op_flags);
 		bch_bio_map(bio, c->uuids);
 
 		bch_submit_bbio(bio, c, k, i);
 
-		if (!(rw & WRITE))
+		if (op != REQ_OP_WRITE)
 			break;
 	}
 
 	bch_extent_to_text(buf, sizeof(buf), k);
-	pr_debug("%s UUIDs at %s", rw & REQ_WRITE ? "wrote" : "read", buf);
+	pr_debug("%s UUIDs at %s", op == REQ_OP_WRITE ? "wrote" : "read", buf);
 
 	for (u = c->uuids; u < c->uuids + c->nr_uuids; u++)
 		if (!bch_is_zero(u->uuid, 16))
@@ -381,7 +381,7 @@ static char *uuid_read(struct cache_set *c, struct jset *j, struct closure *cl)
 		return "bad uuid pointer";
 
 	bkey_copy(&c->uuid_bucket, k);
-	uuid_io(c, READ_SYNC, k, cl);
+	uuid_io(c, REQ_OP_READ, READ_SYNC, k, cl);
 
 	if (j->version < BCACHE_JSET_VERSION_UUIDv1) {
 		struct uuid_entry_v0	*u0 = (void *) c->uuids;
@@ -426,7 +426,7 @@ static int __uuid_write(struct cache_set *c)
 		return 1;
 
 	SET_KEY_SIZE(&k.key, c->sb.bucket_size);
-	uuid_io(c, REQ_WRITE, &k.key, &cl);
+	uuid_io(c, REQ_OP_WRITE, 0, &k.key, &cl);
 	closure_sync(&cl);
 
 	bkey_copy(&c->uuid_bucket, &k.key);
@@ -498,7 +498,8 @@ static void prio_endio(struct bio *bio)
 	closure_put(&ca->prio);
 }
 
-static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
+static void prio_io(struct cache *ca, uint64_t bucket, int op,
+		    unsigned long op_flags)
 {
 	struct closure *cl = &ca->prio;
 	struct bio *bio = bch_bbio_alloc(ca->set);
@@ -507,11 +508,11 @@ static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
 
 	bio->bi_iter.bi_sector	= bucket * ca->sb.bucket_size;
 	bio->bi_bdev		= ca->bdev;
-	bio->bi_rw		= REQ_SYNC|REQ_META|rw;
 	bio->bi_iter.bi_size	= bucket_bytes(ca);
 
 	bio->bi_end_io	= prio_endio;
 	bio->bi_private = ca;
+	bio_set_op_attrs(bio, op, REQ_SYNC|REQ_META|op_flags);
 	bch_bio_map(bio, ca->disk_buckets);
 
 	closure_bio_submit(bio, &ca->prio);
@@ -557,7 +558,7 @@ void bch_prio_write(struct cache *ca)
 		BUG_ON(bucket == -1);
 
 		mutex_unlock(&ca->set->bucket_lock);
-		prio_io(ca, bucket, REQ_WRITE);
+		prio_io(ca, bucket, REQ_OP_WRITE, 0);
 		mutex_lock(&ca->set->bucket_lock);
 
 		ca->prio_buckets[i] = bucket;
@@ -599,7 +600,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
 			ca->prio_last_buckets[bucket_nr] = bucket;
 			bucket_nr++;
 
-			prio_io(ca, bucket, READ_SYNC);
+			prio_io(ca, bucket, REQ_OP_READ, READ_SYNC);
 
 			if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8))
 				pr_warn("bad csum reading priorities");
@@ -1518,7 +1519,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	    !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
 	    !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
 	    !(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
-	    !(c->moving_gc_wq = create_workqueue("bcache_gc")) ||
+	    !(c->moving_gc_wq = alloc_workqueue("bcache_gc",
+						WQ_MEM_RECLAIM, 0)) ||
 	    bch_journal_alloc(c) ||
 	    bch_btree_cache_alloc(c) ||
 	    bch_open_buckets_alloc(c) ||
@@ -1803,7 +1805,7 @@ void bch_cache_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static int cache_alloc(struct cache_sb *sb, struct cache *ca)
+static int cache_alloc(struct cache *ca)
 {
 	size_t free;
 	struct bucket *b;
@@ -1858,7 +1860,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 	if (blk_queue_discard(bdev_get_queue(ca->bdev)))
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
-	ret = cache_alloc(sb, ca);
+	ret = cache_alloc(ca);
 	if (ret != 0)
 		goto err;
 
@@ -2097,7 +2099,7 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
-	if (!(bcache_wq = create_workqueue("bcache")) ||
+	if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
 	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
 	    sysfs_create_files(bcache_kobj, files) ||
 	    bch_request_init() ||
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 60123677b382..d9fd2a62e5f6 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -182,7 +182,7 @@ static void write_dirty(struct closure *cl)
 	struct keybuf_key *w = io->bio.bi_private;
 
 	dirty_init(w);
-	io->bio.bi_rw		= WRITE;
+	bio_set_op_attrs(&io->bio, REQ_OP_WRITE, 0);
 	io->bio.bi_iter.bi_sector = KEY_START(&w->key);
 	io->bio.bi_bdev		= io->dc->bdev;
 	io->bio.bi_end_io	= dirty_endio;
@@ -251,10 +251,10 @@ static void read_dirty(struct cached_dev *dc)
 		io->dc		= dc;
 
 		dirty_init(w);
+		bio_set_op_attrs(&io->bio, REQ_OP_READ, 0);
 		io->bio.bi_iter.bi_sector = PTR_OFFSET(&w->key, 0);
 		io->bio.bi_bdev		= PTR_CACHE(dc->disk.c,
 						    &w->key, 0)->bdev;
-		io->bio.bi_rw		= READ;
 		io->bio.bi_end_io	= read_dirty_endio;
 
 		if (bio_alloc_pages(&io->bio, GFP_KERNEL))
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index d8129ec93ebd..6fff794e0c72 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -162,7 +162,7 @@ static int read_sb_page(struct mddev *mddev, loff_t offset,
 
 		if (sync_page_io(rdev, target,
 				 roundup(size, bdev_logical_block_size(rdev->bdev)),
-				 page, READ, true)) {
+				 page, REQ_OP_READ, 0, true)) {
 			page->index = index;
 			return 0;
 		}
@@ -297,7 +297,7 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
 			atomic_inc(&bitmap->pending_writes);
 			set_buffer_locked(bh);
 			set_buffer_mapped(bh);
-			submit_bh(WRITE | REQ_SYNC, bh);
+			submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
 			bh = bh->b_this_page;
 		}
 
@@ -392,7 +392,7 @@ static int read_page(struct file *file, unsigned long index,
 			atomic_inc(&bitmap->pending_writes);
 			set_buffer_locked(bh);
 			set_buffer_mapped(bh);
-			submit_bh(READ, bh);
+			submit_bh(REQ_OP_READ, 0, bh);
 		}
 		block++;
 		bh = bh->b_this_page;
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index cd77216beff1..6571c81465e1 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -574,7 +574,8 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
 {
 	int r;
 	struct dm_io_request io_req = {
-		.bi_rw = rw,
+		.bi_op = rw,
+		.bi_op_flags = 0,
 		.notify.fn = dmio_complete,
 		.notify.context = b,
 		.client = b->c->dm_io,
@@ -634,6 +635,7 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 	 * the dm_buffer's inline bio is local to bufio.
 	 */
 	b->bio.bi_private = end_io;
+	bio_set_op_attrs(&b->bio, rw, 0);
 
 	/*
 	 * We assume that if len >= PAGE_SIZE ptr is page-aligned.
@@ -660,7 +662,7 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 		ptr += PAGE_SIZE;
 	} while (len > 0);
 
-	submit_bio(rw, &b->bio);
+	submit_bio(&b->bio);
 }
 
 static void submit_io(struct dm_buffer *b, int rw, sector_t block,
@@ -1326,7 +1328,8 @@ EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers);
 int dm_bufio_issue_flush(struct dm_bufio_client *c)
 {
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE_FLUSH,
+		.bi_op = REQ_OP_WRITE,
+		.bi_op_flags = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = c->dm_io,
diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c
index 6c9049c51b2b..f092771878c2 100644
--- a/drivers/md/dm-builtin.c
+++ b/drivers/md/dm-builtin.c
@@ -1,4 +1,4 @@
-#include "dm.h"
+#include "dm-core.h"
 
 /*
  * The kobject release method must not be placed in the module itself,
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index ee0510f9a85e..718744db62df 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -788,7 +788,8 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
 
 	spin_lock_irqsave(&cache->lock, flags);
 	if (cache->need_tick_bio &&
-	    !(bio->bi_rw & (REQ_FUA | REQ_FLUSH | REQ_DISCARD))) {
+	    !(bio->bi_rw & (REQ_FUA | REQ_PREFLUSH)) &&
+	    bio_op(bio) != REQ_OP_DISCARD) {
 		pb->tick = true;
 		cache->need_tick_bio = false;
 	}
@@ -829,7 +830,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
 
 static int bio_triggers_commit(struct cache *cache, struct bio *bio)
 {
-	return bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	return bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
 }
 
 /*
@@ -851,7 +852,7 @@ static void inc_ds(struct cache *cache, struct bio *bio,
 static bool accountable_bio(struct cache *cache, struct bio *bio)
 {
 	return ((bio->bi_bdev == cache->origin_dev->bdev) &&
-		!(bio->bi_rw & REQ_DISCARD));
+		bio_op(bio) != REQ_OP_DISCARD);
 }
 
 static void accounted_begin(struct cache *cache, struct bio *bio)
@@ -1067,7 +1068,8 @@ static void dec_io_migrations(struct cache *cache)
 
 static bool discard_or_flush(struct bio *bio)
 {
-	return bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD);
+	return bio_op(bio) == REQ_OP_DISCARD ||
+	       bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
 }
 
 static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell)
@@ -1612,8 +1614,8 @@ static void process_flush_bio(struct cache *cache, struct bio *bio)
 		remap_to_cache(cache, bio, 0);
 
 	/*
-	 * REQ_FLUSH is not directed at any particular block so we don't
-	 * need to inc_ds().  REQ_FUA's are split into a write + REQ_FLUSH
+	 * REQ_PREFLUSH is not directed at any particular block so we don't
+	 * need to inc_ds().  REQ_FUA's are split into a write + REQ_PREFLUSH
 	 * by dm-core.
 	 */
 	issue(cache, bio);
@@ -1978,9 +1980,9 @@ static void process_deferred_bios(struct cache *cache)
 
 		bio = bio_list_pop(&bios);
 
-		if (bio->bi_rw & REQ_FLUSH)
+		if (bio->bi_rw & REQ_PREFLUSH)
 			process_flush_bio(cache, bio);
-		else if (bio->bi_rw & REQ_DISCARD)
+		else if (bio_op(bio) == REQ_OP_DISCARD)
 			process_discard_bio(cache, &structs, bio);
 		else
 			process_bio(cache, &structs, bio);
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
new file mode 100644
index 000000000000..40ceba1fe8be
--- /dev/null
+++ b/drivers/md/dm-core.h
@@ -0,0 +1,149 @@
+/*
+ * Internal header file _only_ for device mapper core
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef DM_CORE_INTERNAL_H
+#define DM_CORE_INTERNAL_H
+
+#include <linux/kthread.h>
+#include <linux/ktime.h>
+#include <linux/blk-mq.h>
+
+#include <trace/events/block.h>
+
+#include "dm.h"
+
+#define DM_RESERVED_MAX_IOS		1024
+
+struct dm_kobject_holder {
+	struct kobject kobj;
+	struct completion completion;
+};
+
+/*
+ * DM core internal structure that used directly by dm.c and dm-rq.c
+ * DM targets must _not_ deference a mapped_device to directly access its members!
+ */
+struct mapped_device {
+	struct srcu_struct io_barrier;
+	struct mutex suspend_lock;
+
+	/*
+	 * The current mapping (struct dm_table *).
+	 * Use dm_get_live_table{_fast} or take suspend_lock for
+	 * dereference.
+	 */
+	void __rcu *map;
+
+	struct list_head table_devices;
+	struct mutex table_devices_lock;
+
+	unsigned long flags;
+
+	struct request_queue *queue;
+	int numa_node_id;
+
+	unsigned type;
+	/* Protect queue and type against concurrent access. */
+	struct mutex type_lock;
+
+	atomic_t holders;
+	atomic_t open_count;
+
+	struct dm_target *immutable_target;
+	struct target_type *immutable_target_type;
+
+	struct gendisk *disk;
+	char name[16];
+
+	void *interface_ptr;
+
+	/*
+	 * A list of ios that arrived while we were suspended.
+	 */
+	atomic_t pending[2];
+	wait_queue_head_t wait;
+	struct work_struct work;
+	spinlock_t deferred_lock;
+	struct bio_list deferred;
+
+	/*
+	 * Event handling.
+	 */
+	wait_queue_head_t eventq;
+	atomic_t event_nr;
+	atomic_t uevent_seq;
+	struct list_head uevent_list;
+	spinlock_t uevent_lock; /* Protect access to uevent_list */
+
+	/* the number of internal suspends */
+	unsigned internal_suspend_count;
+
+	/*
+	 * Processing queue (flush)
+	 */
+	struct workqueue_struct *wq;
+
+	/*
+	 * io objects are allocated from here.
+	 */
+	mempool_t *io_pool;
+	mempool_t *rq_pool;
+
+	struct bio_set *bs;
+
+	/*
+	 * freeze/thaw support require holding onto a super block
+	 */
+	struct super_block *frozen_sb;
+
+	/* forced geometry settings */
+	struct hd_geometry geometry;
+
+	struct block_device *bdev;
+
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
+
+	/* zero-length flush that will be cloned and submitted to targets */
+	struct bio flush_bio;
+
+	struct dm_stats stats;
+
+	struct kthread_worker kworker;
+	struct task_struct *kworker_task;
+
+	/* for request-based merge heuristic in dm_request_fn() */
+	unsigned seq_rq_merge_deadline_usecs;
+	int last_rq_rw;
+	sector_t last_rq_pos;
+	ktime_t last_rq_start_time;
+
+	/* for blk-mq request-based DM support */
+	struct blk_mq_tag_set *tag_set;
+	bool use_blk_mq:1;
+	bool init_tio_pdu:1;
+};
+
+void dm_init_md_queue(struct mapped_device *md);
+void dm_init_normal_md_queue(struct mapped_device *md);
+int md_in_flight(struct mapped_device *md);
+void disable_write_same(struct mapped_device *md);
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
+unsigned __dm_get_module_param(unsigned *module_param, unsigned def, unsigned max);
+
+static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
+{
+	return !maxlen || strlen(result) + 1 >= maxlen;
+}
+
+#endif
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 4f3cb3554944..8f2e3e2ffd26 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -683,7 +683,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 				  u8 *data)
 {
 	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
-	u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
+	__le64 sector = cpu_to_le64(dmreq->iv_sector);
 	u8 buf[TCW_WHITENING_SIZE];
 	SHASH_DESC_ON_STACK(desc, tcw->crc32_tfm);
 	int i, r;
@@ -722,7 +722,7 @@ static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv,
 			    struct dm_crypt_request *dmreq)
 {
 	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
-	u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
+	__le64 sector = cpu_to_le64(dmreq->iv_sector);
 	u8 *src;
 	int r = 0;
 
@@ -1136,7 +1136,7 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone)
 	clone->bi_private = io;
 	clone->bi_end_io  = crypt_endio;
 	clone->bi_bdev    = cc->dev->bdev;
-	clone->bi_rw      = io->base_bio->bi_rw;
+	bio_set_op_attrs(clone, bio_op(io->base_bio), io->base_bio->bi_rw);
 }
 
 static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
@@ -1911,11 +1911,12 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	struct crypt_config *cc = ti->private;
 
 	/*
-	 * If bio is REQ_FLUSH or REQ_DISCARD, just bypass crypt queues.
-	 * - for REQ_FLUSH device-mapper core ensures that no IO is in-flight
-	 * - for REQ_DISCARD caller must use flush if IO ordering matters
+	 * If bio is REQ_PREFLUSH or REQ_OP_DISCARD, just bypass crypt queues.
+	 * - for REQ_PREFLUSH device-mapper core ensures that no IO is in-flight
+	 * - for REQ_OP_DISCARD caller must use flush if IO ordering matters
 	 */
-	if (unlikely(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) {
+	if (unlikely(bio->bi_rw & REQ_PREFLUSH ||
+	    bio_op(bio) == REQ_OP_DISCARD)) {
 		bio->bi_bdev = cc->dev->bdev;
 		if (bio_sectors(bio))
 			bio->bi_iter.bi_sector = cc->start +
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 665bf3285618..2faf49d8f4d7 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1540,9 +1540,9 @@ static int era_map(struct dm_target *ti, struct bio *bio)
 	remap_to_origin(era, bio);
 
 	/*
-	 * REQ_FLUSH bios carry no data, so we're not interested in them.
+	 * REQ_PREFLUSH bios carry no data, so we're not interested in them.
 	 */
-	if (!(bio->bi_rw & REQ_FLUSH) &&
+	if (!(bio->bi_rw & REQ_PREFLUSH) &&
 	    (bio_data_dir(bio) == WRITE) &&
 	    !metadata_current_marked(era->md, block)) {
 		defer_bio(era, bio);
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index b7341de87015..29b99fb6a16a 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -266,7 +266,7 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
 		data[fc->corrupt_bio_byte - 1] = fc->corrupt_bio_value;
 
 		DMDEBUG("Corrupting data bio=%p by writing %u to byte %u "
-			"(rw=%c bi_rw=%lu bi_sector=%llu cur_bytes=%u)\n",
+			"(rw=%c bi_rw=%u bi_sector=%llu cur_bytes=%u)\n",
 			bio, fc->corrupt_bio_value, fc->corrupt_bio_byte,
 			(bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_rw,
 			(unsigned long long)bio->bi_iter.bi_sector, bio_bytes);
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 06d426eb5a30..daa03e41654a 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -5,7 +5,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/device-mapper.h>
 
@@ -278,8 +278,9 @@ static void km_dp_init(struct dpages *dp, void *data)
 /*-----------------------------------------------------------------
  * IO routines that accept a list of pages.
  *---------------------------------------------------------------*/
-static void do_region(int rw, unsigned region, struct dm_io_region *where,
-		      struct dpages *dp, struct io *io)
+static void do_region(int op, int op_flags, unsigned region,
+		      struct dm_io_region *where, struct dpages *dp,
+		      struct io *io)
 {
 	struct bio *bio;
 	struct page *page;
@@ -295,24 +296,25 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 	/*
 	 * Reject unsupported discard and write same requests.
 	 */
-	if (rw & REQ_DISCARD)
+	if (op == REQ_OP_DISCARD)
 		special_cmd_max_sectors = q->limits.max_discard_sectors;
-	else if (rw & REQ_WRITE_SAME)
+	else if (op == REQ_OP_WRITE_SAME)
 		special_cmd_max_sectors = q->limits.max_write_same_sectors;
-	if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) {
+	if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_SAME) &&
+	    special_cmd_max_sectors == 0) {
 		dec_count(io, region, -EOPNOTSUPP);
 		return;
 	}
 
 	/*
-	 * where->count may be zero if rw holds a flush and we need to
+	 * where->count may be zero if op holds a flush and we need to
 	 * send a zero-sized flush.
 	 */
 	do {
 		/*
 		 * Allocate a suitably sized-bio.
 		 */
-		if ((rw & REQ_DISCARD) || (rw & REQ_WRITE_SAME))
+		if ((op == REQ_OP_DISCARD) || (op == REQ_OP_WRITE_SAME))
 			num_bvecs = 1;
 		else
 			num_bvecs = min_t(int, BIO_MAX_PAGES,
@@ -322,13 +324,14 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
 		bio->bi_bdev = where->bdev;
 		bio->bi_end_io = endio;
+		bio_set_op_attrs(bio, op, op_flags);
 		store_io_and_region_in_bio(bio, io, region);
 
-		if (rw & REQ_DISCARD) {
+		if (op == REQ_OP_DISCARD) {
 			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 			remaining -= num_sectors;
-		} else if (rw & REQ_WRITE_SAME) {
+		} else if (op == REQ_OP_WRITE_SAME) {
 			/*
 			 * WRITE SAME only uses a single page.
 			 */
@@ -355,11 +358,11 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		}
 
 		atomic_inc(&io->count);
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	} while (remaining);
 }
 
-static void dispatch_io(int rw, unsigned int num_regions,
+static void dispatch_io(int op, int op_flags, unsigned int num_regions,
 			struct dm_io_region *where, struct dpages *dp,
 			struct io *io, int sync)
 {
@@ -369,7 +372,7 @@ static void dispatch_io(int rw, unsigned int num_regions,
 	BUG_ON(num_regions > DM_IO_MAX_REGIONS);
 
 	if (sync)
-		rw |= REQ_SYNC;
+		op_flags |= REQ_SYNC;
 
 	/*
 	 * For multiple regions we need to be careful to rewind
@@ -377,8 +380,8 @@ static void dispatch_io(int rw, unsigned int num_regions,
 	 */
 	for (i = 0; i < num_regions; i++) {
 		*dp = old_pages;
-		if (where[i].count || (rw & REQ_FLUSH))
-			do_region(rw, i, where + i, dp, io);
+		if (where[i].count || (op_flags & REQ_PREFLUSH))
+			do_region(op, op_flags, i, where + i, dp, io);
 	}
 
 	/*
@@ -402,13 +405,13 @@ static void sync_io_complete(unsigned long error, void *context)
 }
 
 static int sync_io(struct dm_io_client *client, unsigned int num_regions,
-		   struct dm_io_region *where, int rw, struct dpages *dp,
-		   unsigned long *error_bits)
+		   struct dm_io_region *where, int op, int op_flags,
+		   struct dpages *dp, unsigned long *error_bits)
 {
 	struct io *io;
 	struct sync_io sio;
 
-	if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
+	if (num_regions > 1 && !op_is_write(op)) {
 		WARN_ON(1);
 		return -EIO;
 	}
@@ -425,7 +428,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	io->vma_invalidate_address = dp->vma_invalidate_address;
 	io->vma_invalidate_size = dp->vma_invalidate_size;
 
-	dispatch_io(rw, num_regions, where, dp, io, 1);
+	dispatch_io(op, op_flags, num_regions, where, dp, io, 1);
 
 	wait_for_completion_io(&sio.wait);
 
@@ -436,12 +439,12 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 }
 
 static int async_io(struct dm_io_client *client, unsigned int num_regions,
-		    struct dm_io_region *where, int rw, struct dpages *dp,
-		    io_notify_fn fn, void *context)
+		    struct dm_io_region *where, int op, int op_flags,
+		    struct dpages *dp, io_notify_fn fn, void *context)
 {
 	struct io *io;
 
-	if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
+	if (num_regions > 1 && !op_is_write(op)) {
 		WARN_ON(1);
 		fn(1, context);
 		return -EIO;
@@ -457,7 +460,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 	io->vma_invalidate_address = dp->vma_invalidate_address;
 	io->vma_invalidate_size = dp->vma_invalidate_size;
 
-	dispatch_io(rw, num_regions, where, dp, io, 0);
+	dispatch_io(op, op_flags, num_regions, where, dp, io, 0);
 	return 0;
 }
 
@@ -480,7 +483,7 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
 
 	case DM_IO_VMA:
 		flush_kernel_vmap_range(io_req->mem.ptr.vma, size);
-		if ((io_req->bi_rw & RW_MASK) == READ) {
+		if (io_req->bi_op == REQ_OP_READ) {
 			dp->vma_invalidate_address = io_req->mem.ptr.vma;
 			dp->vma_invalidate_size = size;
 		}
@@ -518,10 +521,12 @@ int dm_io(struct dm_io_request *io_req, unsigned num_regions,
 
 	if (!io_req->notify.fn)
 		return sync_io(io_req->client, num_regions, where,
-			       io_req->bi_rw, &dp, sync_error_bits);
+			       io_req->bi_op, io_req->bi_op_flags, &dp,
+			       sync_error_bits);
 
-	return async_io(io_req->client, num_regions, where, io_req->bi_rw,
-			&dp, io_req->notify.fn, io_req->notify.context);
+	return async_io(io_req->client, num_regions, where, io_req->bi_op,
+			io_req->bi_op_flags, &dp, io_req->notify.fn,
+			io_req->notify.context);
 }
 EXPORT_SYMBOL(dm_io);
 
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 2c7ca258c4e4..966eb4b61aed 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -5,7 +5,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/module.h>
 #include <linux/vmalloc.h>
@@ -1267,6 +1267,15 @@ static int populate_table(struct dm_table *table,
 	return dm_table_complete(table);
 }
 
+static bool is_valid_type(unsigned cur, unsigned new)
+{
+	if (cur == new ||
+	    (cur == DM_TYPE_BIO_BASED && new == DM_TYPE_DAX_BIO_BASED))
+		return true;
+
+	return false;
+}
+
 static int table_load(struct dm_ioctl *param, size_t param_size)
 {
 	int r;
@@ -1309,7 +1318,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 			DMWARN("unable to set up device queue for new table.");
 			goto err_unlock_md_type;
 		}
-	} else if (dm_get_md_type(md) != dm_table_get_type(t)) {
+	} else if (!is_valid_type(dm_get_md_type(md), dm_table_get_type(t))) {
 		DMWARN("can't change device type after initial table load.");
 		r = -EINVAL;
 		goto err_unlock_md_type;
@@ -1670,8 +1679,7 @@ static int check_version(unsigned int cmd, struct dm_ioctl __user *user)
 	return r;
 }
 
-#define DM_PARAMS_KMALLOC	0x0001	/* Params alloced with kmalloc */
-#define DM_PARAMS_VMALLOC	0x0002	/* Params alloced with vmalloc */
+#define DM_PARAMS_MALLOC	0x0001	/* Params allocated with kvmalloc() */
 #define DM_WIPE_BUFFER		0x0010	/* Wipe input buffer before returning from ioctl */
 
 static void free_params(struct dm_ioctl *param, size_t param_size, int param_flags)
@@ -1679,10 +1687,8 @@ static void free_params(struct dm_ioctl *param, size_t param_size, int param_fla
 	if (param_flags & DM_WIPE_BUFFER)
 		memset(param, 0, param_size);
 
-	if (param_flags & DM_PARAMS_KMALLOC)
-		kfree(param);
-	if (param_flags & DM_PARAMS_VMALLOC)
-		vfree(param);
+	if (param_flags & DM_PARAMS_MALLOC)
+		kvfree(param);
 }
 
 static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kernel,
@@ -1714,19 +1720,14 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 	 * Use kmalloc() rather than vmalloc() when we can.
 	 */
 	dmi = NULL;
-	if (param_kernel->data_size <= KMALLOC_MAX_SIZE) {
+	if (param_kernel->data_size <= KMALLOC_MAX_SIZE)
 		dmi = kmalloc(param_kernel->data_size, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
-		if (dmi)
-			*param_flags |= DM_PARAMS_KMALLOC;
-	}
 
 	if (!dmi) {
 		unsigned noio_flag;
 		noio_flag = memalloc_noio_save();
 		dmi = __vmalloc(param_kernel->data_size, GFP_NOIO | __GFP_HIGH | __GFP_HIGHMEM, PAGE_KERNEL);
 		memalloc_noio_restore(noio_flag);
-		if (dmi)
-			*param_flags |= DM_PARAMS_VMALLOC;
 	}
 
 	if (!dmi) {
@@ -1735,6 +1736,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 		return -ENOMEM;
 	}
 
+	*param_flags |= DM_PARAMS_MALLOC;
+
 	if (copy_from_user(dmi, user, param_kernel->data_size))
 		goto bad;
 
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 1452ed9aacb4..9e9d04cb7d51 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -26,7 +26,7 @@
 #include <linux/device-mapper.h>
 #include <linux/dm-kcopyd.h>
 
-#include "dm.h"
+#include "dm-core.h"
 
 #define SUB_JOB_SIZE	128
 #define SPLIT_COUNT	8
@@ -465,7 +465,7 @@ static void complete_io(unsigned long error, void *context)
 	io_job_finish(kc->throttle);
 
 	if (error) {
-		if (job->rw & WRITE)
+		if (op_is_write(job->rw))
 			job->write_err |= error;
 		else
 			job->read_err = 1;
@@ -477,7 +477,7 @@ static void complete_io(unsigned long error, void *context)
 		}
 	}
 
-	if (job->rw & WRITE)
+	if (op_is_write(job->rw))
 		push(&kc->complete_jobs, job);
 
 	else {
@@ -496,7 +496,8 @@ static int run_io_job(struct kcopyd_job *job)
 {
 	int r;
 	struct dm_io_request io_req = {
-		.bi_rw = job->rw,
+		.bi_op = job->rw,
+		.bi_op_flags = 0,
 		.mem.type = DM_IO_PAGE_LIST,
 		.mem.ptr.pl = job->pages,
 		.mem.offset = 0,
@@ -550,7 +551,7 @@ static int process_jobs(struct list_head *jobs, struct dm_kcopyd_client *kc,
 
 		if (r < 0) {
 			/* error this rogue job */
-			if (job->rw & WRITE)
+			if (op_is_write(job->rw))
 				job->write_err = (unsigned long) -1L;
 			else
 				job->read_err = 1;
@@ -734,7 +735,7 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 		/*
 		 * Use WRITE SAME to optimize zeroing if all dests support it.
 		 */
-		job->rw = WRITE | REQ_WRITE_SAME;
+		job->rw = REQ_OP_WRITE_SAME;
 		for (i = 0; i < job->num_dests; i++)
 			if (!bdev_write_same(job->dests[i].bdev)) {
 				job->rw = WRITE;
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 05c35aacb3aa..6d35dd4e9efb 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -141,9 +141,27 @@ static int linear_iterate_devices(struct dm_target *ti,
 	return fn(ti, lc->dev, lc->start, ti->len, data);
 }
 
+static long linear_direct_access(struct dm_target *ti, sector_t sector,
+				 void __pmem **kaddr, pfn_t *pfn, long size)
+{
+	struct linear_c *lc = ti->private;
+	struct block_device *bdev = lc->dev->bdev;
+	struct blk_dax_ctl dax = {
+		.sector = linear_map_sector(ti, sector),
+		.size = size,
+	};
+	long ret;
+
+	ret = bdev_direct_access(bdev, &dax);
+	*kaddr = dax.addr;
+	*pfn = dax.pfn;
+
+	return ret;
+}
+
 static struct target_type linear_target = {
 	.name   = "linear",
-	.version = {1, 2, 1},
+	.version = {1, 3, 0},
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,
 	.dtr    = linear_dtr,
@@ -151,6 +169,7 @@ static struct target_type linear_target = {
 	.status = linear_status,
 	.prepare_ioctl = linear_prepare_ioctl,
 	.iterate_devices = linear_iterate_devices,
+	.direct_access = linear_direct_access,
 };
 
 int __init dm_linear_init(void)
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 608302e222af..b5dbf7a0515e 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -205,6 +205,7 @@ static int write_metadata(struct log_writes_c *lc, void *entry,
 	bio->bi_bdev = lc->logdev->bdev;
 	bio->bi_end_io = log_end_io;
 	bio->bi_private = lc;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	page = alloc_page(GFP_KERNEL);
 	if (!page) {
@@ -226,7 +227,7 @@ static int write_metadata(struct log_writes_c *lc, void *entry,
 		DMERR("Couldn't add page to the log block");
 		goto error_bio;
 	}
-	submit_bio(WRITE, bio);
+	submit_bio(bio);
 	return 0;
 error_bio:
 	bio_put(bio);
@@ -269,6 +270,7 @@ static int log_one_block(struct log_writes_c *lc,
 	bio->bi_bdev = lc->logdev->bdev;
 	bio->bi_end_io = log_end_io;
 	bio->bi_private = lc;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	for (i = 0; i < block->vec_cnt; i++) {
 		/*
@@ -279,7 +281,7 @@ static int log_one_block(struct log_writes_c *lc,
 				   block->vecs[i].bv_len, 0);
 		if (ret != block->vecs[i].bv_len) {
 			atomic_inc(&lc->io_blocks);
-			submit_bio(WRITE, bio);
+			submit_bio(bio);
 			bio = bio_alloc(GFP_KERNEL, block->vec_cnt - i);
 			if (!bio) {
 				DMERR("Couldn't alloc log bio");
@@ -290,6 +292,7 @@ static int log_one_block(struct log_writes_c *lc,
 			bio->bi_bdev = lc->logdev->bdev;
 			bio->bi_end_io = log_end_io;
 			bio->bi_private = lc;
+			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 			ret = bio_add_page(bio, block->vecs[i].bv_page,
 					   block->vecs[i].bv_len, 0);
@@ -301,7 +304,7 @@ static int log_one_block(struct log_writes_c *lc,
 		}
 		sector += block->vecs[i].bv_len >> SECTOR_SHIFT;
 	}
-	submit_bio(WRITE, bio);
+	submit_bio(bio);
 out:
 	kfree(block->data);
 	kfree(block);
@@ -552,9 +555,9 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 	struct bio_vec bv;
 	size_t alloc_size;
 	int i = 0;
-	bool flush_bio = (bio->bi_rw & REQ_FLUSH);
+	bool flush_bio = (bio->bi_rw & REQ_PREFLUSH);
 	bool fua_bio = (bio->bi_rw & REQ_FUA);
-	bool discard_bio = (bio->bi_rw & REQ_DISCARD);
+	bool discard_bio = (bio_op(bio) == REQ_OP_DISCARD);
 
 	pb->block = NULL;
 
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 627d19186d5a..4ca2d1df5b44 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -293,7 +293,7 @@ static void header_from_disk(struct log_header_core *core, struct log_header_dis
 
 static int rw_header(struct log_c *lc, int rw)
 {
-	lc->io_req.bi_rw = rw;
+	lc->io_req.bi_op = rw;
 
 	return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
 }
@@ -306,7 +306,8 @@ static int flush_header(struct log_c *lc)
 		.count = 0,
 	};
 
-	lc->io_req.bi_rw = WRITE_FLUSH;
+	lc->io_req.bi_op = REQ_OP_WRITE;
+	lc->io_req.bi_op_flags = WRITE_FLUSH;
 
 	return dm_io(&lc->io_req, 1, &null_location, NULL);
 }
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 52baf8a5b0f4..7eac080fcb18 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -7,7 +7,8 @@
 
 #include <linux/device-mapper.h>
 
-#include "dm.h"
+#include "dm-rq.h"
+#include "dm-bio-record.h"
 #include "dm-path-selector.h"
 #include "dm-uevent.h"
 
@@ -89,6 +90,8 @@ struct multipath {
 	atomic_t pg_init_in_progress;	/* Only one pg_init allowed at once */
 	atomic_t pg_init_count;		/* Number of times pg_init called */
 
+	unsigned queue_mode;
+
 	/*
 	 * We must use a mempool of dm_mpath_io structs so that we
 	 * can resubmit bios on error.
@@ -97,10 +100,13 @@ struct multipath {
 
 	struct mutex work_mutex;
 	struct work_struct trigger_event;
+
+	struct work_struct process_queued_bios;
+	struct bio_list queued_bios;
 };
 
 /*
- * Context information attached to each bio we process.
+ * Context information attached to each io we process.
  */
 struct dm_mpath_io {
 	struct pgpath *pgpath;
@@ -114,6 +120,7 @@ static struct kmem_cache *_mpio_cache;
 static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
 static void trigger_event(struct work_struct *work);
 static void activate_path(struct work_struct *work);
+static void process_queued_bios(struct work_struct *work);
 
 /*-----------------------------------------------
  * Multipath state flags.
@@ -185,7 +192,7 @@ static void free_priority_group(struct priority_group *pg,
 	kfree(pg);
 }
 
-static struct multipath *alloc_multipath(struct dm_target *ti, bool use_blk_mq)
+static struct multipath *alloc_multipath(struct dm_target *ti)
 {
 	struct multipath *m;
 
@@ -203,15 +210,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti, bool use_blk_mq)
 		mutex_init(&m->work_mutex);
 
 		m->mpio_pool = NULL;
-		if (!use_blk_mq) {
-			unsigned min_ios = dm_get_reserved_rq_based_ios();
-
-			m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
-			if (!m->mpio_pool) {
-				kfree(m);
-				return NULL;
-			}
-		}
+		m->queue_mode = DM_TYPE_NONE;
 
 		m->ti = ti;
 		ti->private = m;
@@ -220,6 +219,39 @@ static struct multipath *alloc_multipath(struct dm_target *ti, bool use_blk_mq)
 	return m;
 }
 
+static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m)
+{
+	if (m->queue_mode == DM_TYPE_NONE) {
+		/*
+		 * Default to request-based.
+		 */
+		if (dm_use_blk_mq(dm_table_get_md(ti->table)))
+			m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
+		else
+			m->queue_mode = DM_TYPE_REQUEST_BASED;
+	}
+
+	if (m->queue_mode == DM_TYPE_REQUEST_BASED) {
+		unsigned min_ios = dm_get_reserved_rq_based_ios();
+
+		m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
+		if (!m->mpio_pool)
+			return -ENOMEM;
+	}
+	else if (m->queue_mode == DM_TYPE_BIO_BASED) {
+		INIT_WORK(&m->process_queued_bios, process_queued_bios);
+		/*
+		 * bio-based doesn't support any direct scsi_dh management;
+		 * it just discovers if a scsi_dh is attached.
+		 */
+		set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags);
+	}
+
+	dm_table_set_type(ti->table, m->queue_mode);
+
+	return 0;
+}
+
 static void free_multipath(struct multipath *m)
 {
 	struct priority_group *pg, *tmp;
@@ -272,6 +304,41 @@ static void clear_request_fn_mpio(struct multipath *m, union map_info *info)
 	}
 }
 
+static size_t multipath_per_bio_data_size(void)
+{
+	return sizeof(struct dm_mpath_io) + sizeof(struct dm_bio_details);
+}
+
+static struct dm_mpath_io *get_mpio_from_bio(struct bio *bio)
+{
+	return dm_per_bio_data(bio, multipath_per_bio_data_size());
+}
+
+static struct dm_bio_details *get_bio_details_from_bio(struct bio *bio)
+{
+	/* dm_bio_details is immediately after the dm_mpath_io in bio's per-bio-data */
+	struct dm_mpath_io *mpio = get_mpio_from_bio(bio);
+	void *bio_details = mpio + 1;
+
+	return bio_details;
+}
+
+static void multipath_init_per_bio_data(struct bio *bio, struct dm_mpath_io **mpio_p,
+					struct dm_bio_details **bio_details_p)
+{
+	struct dm_mpath_io *mpio = get_mpio_from_bio(bio);
+	struct dm_bio_details *bio_details = get_bio_details_from_bio(bio);
+
+	memset(mpio, 0, sizeof(*mpio));
+	memset(bio_details, 0, sizeof(*bio_details));
+	dm_bio_record(bio_details, bio);
+
+	if (mpio_p)
+		*mpio_p = mpio;
+	if (bio_details_p)
+		*bio_details_p = bio_details;
+}
+
 /*-----------------------------------------------
  * Path selection
  *-----------------------------------------------*/
@@ -431,16 +498,26 @@ failed:
  * and multipath_resume() calls and we have no need to check
  * for the DMF_NOFLUSH_SUSPENDING flag.
  */
-static int must_push_back(struct multipath *m)
+static bool __must_push_back(struct multipath *m)
+{
+	return ((test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) !=
+		 test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)) &&
+		dm_noflush_suspending(m->ti));
+}
+
+static bool must_push_back_rq(struct multipath *m)
 {
 	return (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) ||
-		((test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) !=
-		  test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)) &&
-		 dm_noflush_suspending(m->ti)));
+		__must_push_back(m));
+}
+
+static bool must_push_back_bio(struct multipath *m)
+{
+	return __must_push_back(m);
 }
 
 /*
- * Map cloned requests
+ * Map cloned requests (request-based multipath)
  */
 static int __multipath_map(struct dm_target *ti, struct request *clone,
 			   union map_info *map_context,
@@ -459,7 +536,7 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 		pgpath = choose_pgpath(m, nr_bytes);
 
 	if (!pgpath) {
-		if (!must_push_back(m))
+		if (!must_push_back_rq(m))
 			r = -EIO;	/* Failed */
 		return r;
 	} else if (test_bit(MPATHF_QUEUE_IO, &m->flags) ||
@@ -530,6 +607,108 @@ static void multipath_release_clone(struct request *clone)
 }
 
 /*
+ * Map cloned bios (bio-based multipath)
+ */
+static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_mpath_io *mpio)
+{
+	size_t nr_bytes = bio->bi_iter.bi_size;
+	struct pgpath *pgpath;
+	unsigned long flags;
+	bool queue_io;
+
+	/* Do we need to select a new pgpath? */
+	pgpath = lockless_dereference(m->current_pgpath);
+	queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
+	if (!pgpath || !queue_io)
+		pgpath = choose_pgpath(m, nr_bytes);
+
+	if ((pgpath && queue_io) ||
+	    (!pgpath && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))) {
+		/* Queue for the daemon to resubmit */
+		spin_lock_irqsave(&m->lock, flags);
+		bio_list_add(&m->queued_bios, bio);
+		spin_unlock_irqrestore(&m->lock, flags);
+		/* PG_INIT_REQUIRED cannot be set without QUEUE_IO */
+		if (queue_io || test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags))
+			pg_init_all_paths(m);
+		else if (!queue_io)
+			queue_work(kmultipathd, &m->process_queued_bios);
+		return DM_MAPIO_SUBMITTED;
+	}
+
+	if (!pgpath) {
+		if (!must_push_back_bio(m))
+			return -EIO;
+		return DM_MAPIO_REQUEUE;
+	}
+
+	mpio->pgpath = pgpath;
+	mpio->nr_bytes = nr_bytes;
+
+	bio->bi_error = 0;
+	bio->bi_bdev = pgpath->path.dev->bdev;
+	bio->bi_rw |= REQ_FAILFAST_TRANSPORT;
+
+	if (pgpath->pg->ps.type->start_io)
+		pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
+					      &pgpath->path,
+					      nr_bytes);
+	return DM_MAPIO_REMAPPED;
+}
+
+static int multipath_map_bio(struct dm_target *ti, struct bio *bio)
+{
+	struct multipath *m = ti->private;
+	struct dm_mpath_io *mpio = NULL;
+
+	multipath_init_per_bio_data(bio, &mpio, NULL);
+
+	return __multipath_map_bio(m, bio, mpio);
+}
+
+static void process_queued_bios_list(struct multipath *m)
+{
+	if (m->queue_mode == DM_TYPE_BIO_BASED)
+		queue_work(kmultipathd, &m->process_queued_bios);
+}
+
+static void process_queued_bios(struct work_struct *work)
+{
+	int r;
+	unsigned long flags;
+	struct bio *bio;
+	struct bio_list bios;
+	struct blk_plug plug;
+	struct multipath *m =
+		container_of(work, struct multipath, process_queued_bios);
+
+	bio_list_init(&bios);
+
+	spin_lock_irqsave(&m->lock, flags);
+
+	if (bio_list_empty(&m->queued_bios)) {
+		spin_unlock_irqrestore(&m->lock, flags);
+		return;
+	}
+
+	bio_list_merge(&bios, &m->queued_bios);
+	bio_list_init(&m->queued_bios);
+
+	spin_unlock_irqrestore(&m->lock, flags);
+
+	blk_start_plug(&plug);
+	while ((bio = bio_list_pop(&bios))) {
+		r = __multipath_map_bio(m, bio, get_mpio_from_bio(bio));
+		if (r < 0 || r == DM_MAPIO_REQUEUE) {
+			bio->bi_error = r;
+			bio_endio(bio);
+		} else if (r == DM_MAPIO_REMAPPED)
+			generic_make_request(bio);
+	}
+	blk_finish_plug(&plug);
+}
+
+/*
  * If we run out of usable paths, should we queue I/O or error it?
  */
 static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
@@ -557,8 +736,10 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
 
 	spin_unlock_irqrestore(&m->lock, flags);
 
-	if (!queue_if_no_path)
+	if (!queue_if_no_path) {
 		dm_table_run_md_queue_async(m->ti->table);
+		process_queued_bios_list(m);
+	}
 
 	return 0;
 }
@@ -798,6 +979,12 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m)
 	if (!hw_argc)
 		return 0;
 
+	if (m->queue_mode == DM_TYPE_BIO_BASED) {
+		dm_consume_args(as, hw_argc);
+		DMERR("bio-based multipath doesn't allow hardware handler args");
+		return 0;
+	}
+
 	m->hw_handler_name = kstrdup(dm_shift_arg(as), GFP_KERNEL);
 
 	if (hw_argc > 1) {
@@ -833,7 +1020,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
 	const char *arg_name;
 
 	static struct dm_arg _args[] = {
-		{0, 6, "invalid number of feature args"},
+		{0, 8, "invalid number of feature args"},
 		{1, 50, "pg_init_retries must be between 1 and 50"},
 		{0, 60000, "pg_init_delay_msecs must be between 0 and 60000"},
 	};
@@ -873,6 +1060,24 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
 			continue;
 		}
 
+		if (!strcasecmp(arg_name, "queue_mode") &&
+		    (argc >= 1)) {
+			const char *queue_mode_name = dm_shift_arg(as);
+
+			if (!strcasecmp(queue_mode_name, "bio"))
+				m->queue_mode = DM_TYPE_BIO_BASED;
+			else if (!strcasecmp(queue_mode_name, "rq"))
+				m->queue_mode = DM_TYPE_REQUEST_BASED;
+			else if (!strcasecmp(queue_mode_name, "mq"))
+				m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
+			else {
+				ti->error = "Unknown 'queue_mode' requested";
+				r = -EINVAL;
+			}
+			argc--;
+			continue;
+		}
+
 		ti->error = "Unrecognised multipath feature request";
 		r = -EINVAL;
 	} while (argc && !r);
@@ -880,8 +1085,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
 	return r;
 }
 
-static int multipath_ctr(struct dm_target *ti, unsigned int argc,
-			 char **argv)
+static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 {
 	/* target arguments */
 	static struct dm_arg _args[] = {
@@ -894,12 +1098,11 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
 	struct dm_arg_set as;
 	unsigned pg_count = 0;
 	unsigned next_pg_num;
-	bool use_blk_mq = dm_use_blk_mq(dm_table_get_md(ti->table));
 
 	as.argc = argc;
 	as.argv = argv;
 
-	m = alloc_multipath(ti, use_blk_mq);
+	m = alloc_multipath(ti);
 	if (!m) {
 		ti->error = "can't allocate multipath";
 		return -EINVAL;
@@ -909,6 +1112,10 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
 	if (r)
 		goto bad;
 
+	r = alloc_multipath_stage2(ti, m);
+	if (r)
+		goto bad;
+
 	r = parse_hw_handler(&as, m);
 	if (r)
 		goto bad;
@@ -958,7 +1165,9 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_same_bios = 1;
-	if (use_blk_mq)
+	if (m->queue_mode == DM_TYPE_BIO_BASED)
+		ti->per_io_data_size = multipath_per_bio_data_size();
+	else if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED)
 		ti->per_io_data_size = sizeof(struct dm_mpath_io);
 
 	return 0;
@@ -1083,8 +1292,10 @@ static int reinstate_path(struct pgpath *pgpath)
 
 out:
 	spin_unlock_irqrestore(&m->lock, flags);
-	if (run_queue)
+	if (run_queue) {
 		dm_table_run_md_queue_async(m->ti->table);
+		process_queued_bios_list(m);
+	}
 
 	return r;
 }
@@ -1281,6 +1492,8 @@ static void pg_init_done(void *data, int errors)
 	}
 	clear_bit(MPATHF_QUEUE_IO, &m->flags);
 
+	process_queued_bios_list(m);
+
 	/*
 	 * Wake up any thread waiting to suspend.
 	 */
@@ -1328,7 +1541,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	 * during end I/O handling, since those clone requests don't have
 	 * bio clones.  If we queue them inside the multipath target,
 	 * we need to make bio clones, that requires memory allocation.
-	 * (See drivers/md/dm.c:end_clone_bio() about why the clone requests
+	 * (See drivers/md/dm-rq.c:end_clone_bio() about why the clone requests
 	 *  don't have bio clones.)
 	 * Instead of queueing the clone request here, we queue the original
 	 * request into dm core, which will remake a clone request and
@@ -1347,7 +1560,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
 
 	if (!atomic_read(&m->nr_valid_paths)) {
 		if (!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
-			if (!must_push_back(m))
+			if (!must_push_back_rq(m))
 				r = -EIO;
 		} else {
 			if (error == -EBADE)
@@ -1381,6 +1594,64 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 	return r;
 }
 
+static int do_end_io_bio(struct multipath *m, struct bio *clone,
+			 int error, struct dm_mpath_io *mpio)
+{
+	unsigned long flags;
+
+	if (!error)
+		return 0;	/* I/O complete */
+
+	if (noretry_error(error))
+		return error;
+
+	if (mpio->pgpath)
+		fail_path(mpio->pgpath);
+
+	if (!atomic_read(&m->nr_valid_paths)) {
+		if (!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+			if (!must_push_back_bio(m))
+				return -EIO;
+			return DM_ENDIO_REQUEUE;
+		} else {
+			if (error == -EBADE)
+				return error;
+		}
+	}
+
+	/* Queue for the daemon to resubmit */
+	dm_bio_restore(get_bio_details_from_bio(clone), clone);
+
+	spin_lock_irqsave(&m->lock, flags);
+	bio_list_add(&m->queued_bios, clone);
+	spin_unlock_irqrestore(&m->lock, flags);
+	if (!test_bit(MPATHF_QUEUE_IO, &m->flags))
+		queue_work(kmultipathd, &m->process_queued_bios);
+
+	return DM_ENDIO_INCOMPLETE;
+}
+
+static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, int error)
+{
+	struct multipath *m = ti->private;
+	struct dm_mpath_io *mpio = get_mpio_from_bio(clone);
+	struct pgpath *pgpath;
+	struct path_selector *ps;
+	int r;
+
+	BUG_ON(!mpio);
+
+	r = do_end_io_bio(m, clone, error, mpio);
+	pgpath = mpio->pgpath;
+	if (pgpath) {
+		ps = &pgpath->pg->ps;
+		if (ps->type->end_io)
+			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
+	}
+
+	return r;
+}
+
 /*
  * Suspend can't complete until all the I/O is processed so if
  * the last path fails we must error any remaining I/O.
@@ -1454,7 +1725,9 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 		DMEMIT("%u ", test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) +
 			      (m->pg_init_retries > 0) * 2 +
 			      (m->pg_init_delay_msecs != DM_PG_INIT_DELAY_DEFAULT) * 2 +
-			      test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags));
+			      test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags) +
+			      (m->queue_mode != DM_TYPE_REQUEST_BASED) * 2);
+
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			DMEMIT("queue_if_no_path ");
 		if (m->pg_init_retries)
@@ -1463,6 +1736,16 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 			DMEMIT("pg_init_delay_msecs %u ", m->pg_init_delay_msecs);
 		if (test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags))
 			DMEMIT("retain_attached_hw_handler ");
+		if (m->queue_mode != DM_TYPE_REQUEST_BASED) {
+			switch(m->queue_mode) {
+			case DM_TYPE_BIO_BASED:
+				DMEMIT("queue_mode bio ");
+				break;
+			case DM_TYPE_MQ_REQUEST_BASED:
+				DMEMIT("queue_mode mq ");
+				break;
+			}
+		}
 	}
 
 	if (!m->hw_handler_name || type == STATUSTYPE_INFO)
@@ -1642,6 +1925,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 		if (test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags))
 			pg_init_all_paths(m);
 		dm_table_run_md_queue_async(m->ti->table);
+		process_queued_bios_list(m);
 	}
 
 	/*
@@ -1748,7 +2032,7 @@ static int multipath_busy(struct dm_target *ti)
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 11, 0},
+	.version = {1, 12, 0},
 	.features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE,
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
@@ -1757,6 +2041,8 @@ static struct target_type multipath_target = {
 	.clone_and_map_rq = multipath_clone_and_map,
 	.release_clone_rq = multipath_release_clone,
 	.rq_end_io = multipath_end_io,
+	.map = multipath_map_bio,
+	.end_io = multipath_end_io_bio,
 	.presuspend = multipath_presuspend,
 	.postsuspend = multipath_postsuspend,
 	.resume = multipath_resume,
@@ -1771,14 +2057,14 @@ static int __init dm_multipath_init(void)
 {
 	int r;
 
-	/* allocate a slab for the dm_ios */
+	/* allocate a slab for the dm_mpath_ios */
 	_mpio_cache = KMEM_CACHE(dm_mpath_io, 0);
 	if (!_mpio_cache)
 		return -ENOMEM;
 
 	r = dm_register_target(&multipath_target);
 	if (r < 0) {
-		DMERR("register failed %d", r);
+		DMERR("request-based register failed %d", r);
 		r = -EINVAL;
 		goto bad_register_target;
 	}
@@ -1804,10 +2090,6 @@ static int __init dm_multipath_init(void)
 		goto bad_alloc_kmpath_handlerd;
 	}
 
-	DMINFO("version %u.%u.%u loaded",
-	       multipath_target.version[0], multipath_target.version[1],
-	       multipath_target.version[2]);
-
 	return 0;
 
 bad_alloc_kmpath_handlerd:
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 52532745a50f..84983549b5e1 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010-2011 Neil Brown
- * Copyright (C) 2010-2015 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2010-2016 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
@@ -17,7 +17,12 @@
 #include <linux/device-mapper.h>
 
 #define DM_MSG_PREFIX "raid"
-#define	MAX_RAID_DEVICES	253 /* raid4/5/6 limit */
+#define	MAX_RAID_DEVICES	253 /* md-raid kernel limit */
+
+/*
+ * Minimum sectors of free reshape space per raid device
+ */
+#define	MIN_FREE_RESHAPE_SPACE to_sector(4*4096)
 
 static bool devices_handle_discard_safely = false;
 
@@ -25,12 +30,12 @@ static bool devices_handle_discard_safely = false;
  * The following flags are used by dm-raid.c to set up the array state.
  * They must be cleared before md_run is called.
  */
-#define FirstUse 10             /* rdev flag */
+#define FirstUse 10		/* rdev flag */
 
 struct raid_dev {
 	/*
 	 * Two DM devices, one to hold metadata and one to hold the
-	 * actual data/parity.  The reason for this is to not confuse
+	 * actual data/parity.	The reason for this is to not confuse
 	 * ti->len and give more flexibility in altering size and
 	 * characteristics.
 	 *
@@ -46,25 +51,175 @@ struct raid_dev {
 };
 
 /*
+ * Bits for establishing rs->ctr_flags
+ *
+ * 1 = no flag value
+ * 2 = flag with value
+ */
+#define __CTR_FLAG_SYNC			0  /* 1 */ /* Not with raid0! */
+#define __CTR_FLAG_NOSYNC		1  /* 1 */ /* Not with raid0! */
+#define __CTR_FLAG_REBUILD		2  /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_DAEMON_SLEEP		3  /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_MIN_RECOVERY_RATE	4  /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_MAX_RECOVERY_RATE	5  /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_MAX_WRITE_BEHIND	6  /* 2 */ /* Only with raid1! */
+#define __CTR_FLAG_WRITE_MOSTLY		7  /* 2 */ /* Only with raid1! */
+#define __CTR_FLAG_STRIPE_CACHE		8  /* 2 */ /* Only with raid4/5/6! */
+#define __CTR_FLAG_REGION_SIZE		9  /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_RAID10_COPIES	10 /* 2 */ /* Only with raid10 */
+#define __CTR_FLAG_RAID10_FORMAT	11 /* 2 */ /* Only with raid10 */
+/* New for v1.9.0 */
+#define __CTR_FLAG_DELTA_DISKS		12 /* 2 */ /* Only with reshapable raid1/4/5/6/10! */
+#define __CTR_FLAG_DATA_OFFSET		13 /* 2 */ /* Only with reshapable raid4/5/6/10! */
+#define __CTR_FLAG_RAID10_USE_NEAR_SETS 14 /* 2 */ /* Only with raid10! */
+
+/*
  * Flags for rs->ctr_flags field.
  */
-#define CTR_FLAG_SYNC              0x1
-#define CTR_FLAG_NOSYNC            0x2
-#define CTR_FLAG_REBUILD           0x4
-#define CTR_FLAG_DAEMON_SLEEP      0x8
-#define CTR_FLAG_MIN_RECOVERY_RATE 0x10
-#define CTR_FLAG_MAX_RECOVERY_RATE 0x20
-#define CTR_FLAG_MAX_WRITE_BEHIND  0x40
-#define CTR_FLAG_STRIPE_CACHE      0x80
-#define CTR_FLAG_REGION_SIZE       0x100
-#define CTR_FLAG_RAID10_COPIES     0x200
-#define CTR_FLAG_RAID10_FORMAT     0x400
+#define CTR_FLAG_SYNC			(1 << __CTR_FLAG_SYNC)
+#define CTR_FLAG_NOSYNC			(1 << __CTR_FLAG_NOSYNC)
+#define CTR_FLAG_REBUILD		(1 << __CTR_FLAG_REBUILD)
+#define CTR_FLAG_DAEMON_SLEEP		(1 << __CTR_FLAG_DAEMON_SLEEP)
+#define CTR_FLAG_MIN_RECOVERY_RATE	(1 << __CTR_FLAG_MIN_RECOVERY_RATE)
+#define CTR_FLAG_MAX_RECOVERY_RATE	(1 << __CTR_FLAG_MAX_RECOVERY_RATE)
+#define CTR_FLAG_MAX_WRITE_BEHIND	(1 << __CTR_FLAG_MAX_WRITE_BEHIND)
+#define CTR_FLAG_WRITE_MOSTLY		(1 << __CTR_FLAG_WRITE_MOSTLY)
+#define CTR_FLAG_STRIPE_CACHE		(1 << __CTR_FLAG_STRIPE_CACHE)
+#define CTR_FLAG_REGION_SIZE		(1 << __CTR_FLAG_REGION_SIZE)
+#define CTR_FLAG_RAID10_COPIES		(1 << __CTR_FLAG_RAID10_COPIES)
+#define CTR_FLAG_RAID10_FORMAT		(1 << __CTR_FLAG_RAID10_FORMAT)
+#define CTR_FLAG_DELTA_DISKS		(1 << __CTR_FLAG_DELTA_DISKS)
+#define CTR_FLAG_DATA_OFFSET		(1 << __CTR_FLAG_DATA_OFFSET)
+#define CTR_FLAG_RAID10_USE_NEAR_SETS	(1 << __CTR_FLAG_RAID10_USE_NEAR_SETS)
+
+/*
+ * Definitions of various constructor flags to
+ * be used in checks of valid / invalid flags
+ * per raid level.
+ */
+/* Define all any sync flags */
+#define	CTR_FLAGS_ANY_SYNC		(CTR_FLAG_SYNC | CTR_FLAG_NOSYNC)
+
+/* Define flags for options without argument (e.g. 'nosync') */
+#define	CTR_FLAG_OPTIONS_NO_ARGS	(CTR_FLAGS_ANY_SYNC | \
+					 CTR_FLAG_RAID10_USE_NEAR_SETS)
+
+/* Define flags for options with one argument (e.g. 'delta_disks +2') */
+#define CTR_FLAG_OPTIONS_ONE_ARG (CTR_FLAG_REBUILD | \
+				  CTR_FLAG_WRITE_MOSTLY | \
+				  CTR_FLAG_DAEMON_SLEEP | \
+				  CTR_FLAG_MIN_RECOVERY_RATE | \
+				  CTR_FLAG_MAX_RECOVERY_RATE | \
+				  CTR_FLAG_MAX_WRITE_BEHIND | \
+				  CTR_FLAG_STRIPE_CACHE | \
+				  CTR_FLAG_REGION_SIZE | \
+				  CTR_FLAG_RAID10_COPIES | \
+				  CTR_FLAG_RAID10_FORMAT | \
+				  CTR_FLAG_DELTA_DISKS | \
+				  CTR_FLAG_DATA_OFFSET)
+
+/* Valid options definitions per raid level... */
+
+/* "raid0" does only accept data offset */
+#define RAID0_VALID_FLAGS	(CTR_FLAG_DATA_OFFSET)
+
+/* "raid1" does not accept stripe cache, data offset, delta_disks or any raid10 options */
+#define RAID1_VALID_FLAGS	(CTR_FLAGS_ANY_SYNC | \
+				 CTR_FLAG_REBUILD | \
+				 CTR_FLAG_WRITE_MOSTLY | \
+				 CTR_FLAG_DAEMON_SLEEP | \
+				 CTR_FLAG_MIN_RECOVERY_RATE | \
+				 CTR_FLAG_MAX_RECOVERY_RATE | \
+				 CTR_FLAG_MAX_WRITE_BEHIND | \
+				 CTR_FLAG_REGION_SIZE | \
+				 CTR_FLAG_DELTA_DISKS | \
+				 CTR_FLAG_DATA_OFFSET)
+
+/* "raid10" does not accept any raid1 or stripe cache options */
+#define RAID10_VALID_FLAGS	(CTR_FLAGS_ANY_SYNC | \
+				 CTR_FLAG_REBUILD | \
+				 CTR_FLAG_DAEMON_SLEEP | \
+				 CTR_FLAG_MIN_RECOVERY_RATE | \
+				 CTR_FLAG_MAX_RECOVERY_RATE | \
+				 CTR_FLAG_REGION_SIZE | \
+				 CTR_FLAG_RAID10_COPIES | \
+				 CTR_FLAG_RAID10_FORMAT | \
+				 CTR_FLAG_DELTA_DISKS | \
+				 CTR_FLAG_DATA_OFFSET | \
+				 CTR_FLAG_RAID10_USE_NEAR_SETS)
+
+/*
+ * "raid4/5/6" do not accept any raid1 or raid10 specific options
+ *
+ * "raid6" does not accept "nosync", because it is not guaranteed
+ * that both parity and q-syndrome are being written properly with
+ * any writes
+ */
+#define RAID45_VALID_FLAGS	(CTR_FLAGS_ANY_SYNC | \
+				 CTR_FLAG_REBUILD | \
+				 CTR_FLAG_DAEMON_SLEEP | \
+				 CTR_FLAG_MIN_RECOVERY_RATE | \
+				 CTR_FLAG_MAX_RECOVERY_RATE | \
+				 CTR_FLAG_MAX_WRITE_BEHIND | \
+				 CTR_FLAG_STRIPE_CACHE | \
+				 CTR_FLAG_REGION_SIZE | \
+				 CTR_FLAG_DELTA_DISKS | \
+				 CTR_FLAG_DATA_OFFSET)
+
+#define RAID6_VALID_FLAGS	(CTR_FLAG_SYNC | \
+				 CTR_FLAG_REBUILD | \
+				 CTR_FLAG_DAEMON_SLEEP | \
+				 CTR_FLAG_MIN_RECOVERY_RATE | \
+				 CTR_FLAG_MAX_RECOVERY_RATE | \
+				 CTR_FLAG_MAX_WRITE_BEHIND | \
+				 CTR_FLAG_STRIPE_CACHE | \
+				 CTR_FLAG_REGION_SIZE | \
+				 CTR_FLAG_DELTA_DISKS | \
+				 CTR_FLAG_DATA_OFFSET)
+/* ...valid options definitions per raid level */
+
+/*
+ * Flags for rs->runtime_flags field
+ * (RT_FLAG prefix meaning "runtime flag")
+ *
+ * These are all internal and used to define runtime state,
+ * e.g. to prevent another resume from preresume processing
+ * the raid set all over again.
+ */
+#define RT_FLAG_RS_PRERESUMED		0
+#define RT_FLAG_RS_RESUMED		1
+#define RT_FLAG_RS_BITMAP_LOADED	2
+#define RT_FLAG_UPDATE_SBS		3
+#define RT_FLAG_RESHAPE_RS		4
+#define RT_FLAG_KEEP_RS_FROZEN		5
+
+/* Array elements of 64 bit needed for rebuild/failed disk bits */
+#define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
+
+/*
+ * raid set level, layout and chunk sectors backup/restore
+ */
+struct rs_layout {
+	int new_level;
+	int new_layout;
+	int new_chunk_sectors;
+};
 
 struct raid_set {
 	struct dm_target *ti;
 
 	uint32_t bitmap_loaded;
-	uint32_t ctr_flags;
+	uint32_t stripe_cache_entries;
+	unsigned long ctr_flags;
+	unsigned long runtime_flags;
+
+	uint64_t rebuild_disks[DISKS_ARRAY_ELEMS];
+
+	int raid_disks;
+	int delta_disks;
+	int data_offset;
+	int raid10_copies;
+	int requested_bitmap_chunk_sectors;
 
 	struct mddev md;
 	struct raid_type *raid_type;
@@ -73,82 +228,446 @@ struct raid_set {
 	struct raid_dev dev[0];
 };
 
+static void rs_config_backup(struct raid_set *rs, struct rs_layout *l)
+{
+	struct mddev *mddev = &rs->md;
+
+	l->new_level = mddev->new_level;
+	l->new_layout = mddev->new_layout;
+	l->new_chunk_sectors = mddev->new_chunk_sectors;
+}
+
+static void rs_config_restore(struct raid_set *rs, struct rs_layout *l)
+{
+	struct mddev *mddev = &rs->md;
+
+	mddev->new_level = l->new_level;
+	mddev->new_layout = l->new_layout;
+	mddev->new_chunk_sectors = l->new_chunk_sectors;
+}
+
+/* raid10 algorithms (i.e. formats) */
+#define	ALGORITHM_RAID10_DEFAULT	0
+#define	ALGORITHM_RAID10_NEAR		1
+#define	ALGORITHM_RAID10_OFFSET		2
+#define	ALGORITHM_RAID10_FAR		3
+
 /* Supported raid types and properties. */
 static struct raid_type {
 	const char *name;		/* RAID algorithm. */
 	const char *descr;		/* Descriptor text for logging. */
-	const unsigned parity_devs;	/* # of parity devices. */
-	const unsigned minimal_devs;	/* minimal # of devices in set. */
-	const unsigned level;		/* RAID level. */
-	const unsigned algorithm;	/* RAID algorithm. */
+	const unsigned int parity_devs;	/* # of parity devices. */
+	const unsigned int minimal_devs;/* minimal # of devices in set. */
+	const unsigned int level;	/* RAID level. */
+	const unsigned int algorithm;	/* RAID algorithm. */
 } raid_types[] = {
-	{"raid0",    "RAID0 (striping)",                0, 2, 0, 0 /* NONE */},
-	{"raid1",    "RAID1 (mirroring)",               0, 2, 1, 0 /* NONE */},
-	{"raid10",   "RAID10 (striped mirrors)",        0, 2, 10, UINT_MAX /* Varies */},
-	{"raid4",    "RAID4 (dedicated parity disk)",	1, 2, 5, ALGORITHM_PARITY_0},
-	{"raid5_la", "RAID5 (left asymmetric)",		1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
-	{"raid5_ra", "RAID5 (right asymmetric)",	1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
-	{"raid5_ls", "RAID5 (left symmetric)",		1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
-	{"raid5_rs", "RAID5 (right symmetric)",		1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
-	{"raid6_zr", "RAID6 (zero restart)",		2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART},
-	{"raid6_nr", "RAID6 (N restart)",		2, 4, 6, ALGORITHM_ROTATING_N_RESTART},
-	{"raid6_nc", "RAID6 (N continue)",		2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
+	{"raid0",	  "raid0 (striping)",			    0, 2, 0,  0 /* NONE */},
+	{"raid1",	  "raid1 (mirroring)",			    0, 2, 1,  0 /* NONE */},
+	{"raid10_far",	  "raid10 far (striped mirrors)",	    0, 2, 10, ALGORITHM_RAID10_FAR},
+	{"raid10_offset", "raid10 offset (striped mirrors)",	    0, 2, 10, ALGORITHM_RAID10_OFFSET},
+	{"raid10_near",	  "raid10 near (striped mirrors)",	    0, 2, 10, ALGORITHM_RAID10_NEAR},
+	{"raid10",	  "raid10 (striped mirrors)",		    0, 2, 10, ALGORITHM_RAID10_DEFAULT},
+	{"raid4",	  "raid4 (dedicated last parity disk)",	    1, 2, 4,  ALGORITHM_PARITY_N}, /* raid4 layout = raid5_n */
+	{"raid5_n",	  "raid5 (dedicated last parity disk)",	    1, 2, 5,  ALGORITHM_PARITY_N},
+	{"raid5_ls",	  "raid5 (left symmetric)",		    1, 2, 5,  ALGORITHM_LEFT_SYMMETRIC},
+	{"raid5_rs",	  "raid5 (right symmetric)",		    1, 2, 5,  ALGORITHM_RIGHT_SYMMETRIC},
+	{"raid5_la",	  "raid5 (left asymmetric)",		    1, 2, 5,  ALGORITHM_LEFT_ASYMMETRIC},
+	{"raid5_ra",	  "raid5 (right asymmetric)",		    1, 2, 5,  ALGORITHM_RIGHT_ASYMMETRIC},
+	{"raid6_zr",	  "raid6 (zero restart)",		    2, 4, 6,  ALGORITHM_ROTATING_ZERO_RESTART},
+	{"raid6_nr",	  "raid6 (N restart)",			    2, 4, 6,  ALGORITHM_ROTATING_N_RESTART},
+	{"raid6_nc",	  "raid6 (N continue)",			    2, 4, 6,  ALGORITHM_ROTATING_N_CONTINUE},
+	{"raid6_n_6",	  "raid6 (dedicated parity/Q n/6)",	    2, 4, 6,  ALGORITHM_PARITY_N_6},
+	{"raid6_ls_6",	  "raid6 (left symmetric dedicated Q 6)",   2, 4, 6,  ALGORITHM_LEFT_SYMMETRIC_6},
+	{"raid6_rs_6",	  "raid6 (right symmetric dedicated Q 6)",  2, 4, 6,  ALGORITHM_RIGHT_SYMMETRIC_6},
+	{"raid6_la_6",	  "raid6 (left asymmetric dedicated Q 6)",  2, 4, 6,  ALGORITHM_LEFT_ASYMMETRIC_6},
+	{"raid6_ra_6",	  "raid6 (right asymmetric dedicated Q 6)", 2, 4, 6,  ALGORITHM_RIGHT_ASYMMETRIC_6}
+};
+
+/* True, if @v is in inclusive range [@min, @max] */
+static bool __within_range(long v, long min, long max)
+{
+	return v >= min && v <= max;
+}
+
+/* All table line arguments are defined here */
+static struct arg_name_flag {
+	const unsigned long flag;
+	const char *name;
+} __arg_name_flags[] = {
+	{ CTR_FLAG_SYNC, "sync"},
+	{ CTR_FLAG_NOSYNC, "nosync"},
+	{ CTR_FLAG_REBUILD, "rebuild"},
+	{ CTR_FLAG_DAEMON_SLEEP, "daemon_sleep"},
+	{ CTR_FLAG_MIN_RECOVERY_RATE, "min_recovery_rate"},
+	{ CTR_FLAG_MAX_RECOVERY_RATE, "max_recovery_rate"},
+	{ CTR_FLAG_MAX_WRITE_BEHIND, "max_write_behind"},
+	{ CTR_FLAG_WRITE_MOSTLY, "write_mostly"},
+	{ CTR_FLAG_STRIPE_CACHE, "stripe_cache"},
+	{ CTR_FLAG_REGION_SIZE, "region_size"},
+	{ CTR_FLAG_RAID10_COPIES, "raid10_copies"},
+	{ CTR_FLAG_RAID10_FORMAT, "raid10_format"},
+	{ CTR_FLAG_DATA_OFFSET, "data_offset"},
+	{ CTR_FLAG_DELTA_DISKS, "delta_disks"},
+	{ CTR_FLAG_RAID10_USE_NEAR_SETS, "raid10_use_near_sets"},
 };
 
-static char *raid10_md_layout_to_format(int layout)
+/* Return argument name string for given @flag */
+static const char *dm_raid_arg_name_by_flag(const uint32_t flag)
+{
+	if (hweight32(flag) == 1) {
+		struct arg_name_flag *anf = __arg_name_flags + ARRAY_SIZE(__arg_name_flags);
+
+		while (anf-- > __arg_name_flags)
+			if (flag & anf->flag)
+				return anf->name;
+
+	} else
+		DMERR("%s called with more than one flag!", __func__);
+
+	return NULL;
+}
+
+/*
+ * Bool helpers to test for various raid levels of a raid set.
+ * It's level as reported by the superblock rather than
+ * the requested raid_type passed to the constructor.
+ */
+/* Return true, if raid set in @rs is raid0 */
+static bool rs_is_raid0(struct raid_set *rs)
+{
+	return !rs->md.level;
+}
+
+/* Return true, if raid set in @rs is raid1 */
+static bool rs_is_raid1(struct raid_set *rs)
+{
+	return rs->md.level == 1;
+}
+
+/* Return true, if raid set in @rs is raid10 */
+static bool rs_is_raid10(struct raid_set *rs)
+{
+	return rs->md.level == 10;
+}
+
+/* Return true, if raid set in @rs is level 6 */
+static bool rs_is_raid6(struct raid_set *rs)
+{
+	return rs->md.level == 6;
+}
+
+/* Return true, if raid set in @rs is level 4, 5 or 6 */
+static bool rs_is_raid456(struct raid_set *rs)
+{
+	return __within_range(rs->md.level, 4, 6);
+}
+
+/* Return true, if raid set in @rs is reshapable */
+static bool __is_raid10_far(int layout);
+static bool rs_is_reshapable(struct raid_set *rs)
+{
+	return rs_is_raid456(rs) ||
+	       (rs_is_raid10(rs) && !__is_raid10_far(rs->md.new_layout));
+}
+
+/* Return true, if raid set in @rs is recovering */
+static bool rs_is_recovering(struct raid_set *rs)
+{
+	return rs->md.recovery_cp < rs->dev[0].rdev.sectors;
+}
+
+/* Return true, if raid set in @rs is reshaping */
+static bool rs_is_reshaping(struct raid_set *rs)
+{
+	return rs->md.reshape_position != MaxSector;
+}
+
+/*
+ * bool helpers to test for various raid levels of a raid type @rt
+ */
+
+/* Return true, if raid type in @rt is raid0 */
+static bool rt_is_raid0(struct raid_type *rt)
+{
+	return !rt->level;
+}
+
+/* Return true, if raid type in @rt is raid1 */
+static bool rt_is_raid1(struct raid_type *rt)
+{
+	return rt->level == 1;
+}
+
+/* Return true, if raid type in @rt is raid10 */
+static bool rt_is_raid10(struct raid_type *rt)
+{
+	return rt->level == 10;
+}
+
+/* Return true, if raid type in @rt is raid4/5 */
+static bool rt_is_raid45(struct raid_type *rt)
+{
+	return __within_range(rt->level, 4, 5);
+}
+
+/* Return true, if raid type in @rt is raid6 */
+static bool rt_is_raid6(struct raid_type *rt)
+{
+	return rt->level == 6;
+}
+
+/* Return true, if raid type in @rt is raid4/5/6 */
+static bool rt_is_raid456(struct raid_type *rt)
+{
+	return __within_range(rt->level, 4, 6);
+}
+/* END: raid level bools */
+
+/* Return valid ctr flags for the raid level of @rs */
+static unsigned long __valid_flags(struct raid_set *rs)
+{
+	if (rt_is_raid0(rs->raid_type))
+		return RAID0_VALID_FLAGS;
+	else if (rt_is_raid1(rs->raid_type))
+		return RAID1_VALID_FLAGS;
+	else if (rt_is_raid10(rs->raid_type))
+		return RAID10_VALID_FLAGS;
+	else if (rt_is_raid45(rs->raid_type))
+		return RAID45_VALID_FLAGS;
+	else if (rt_is_raid6(rs->raid_type))
+		return RAID6_VALID_FLAGS;
+
+	return 0;
+}
+
+/*
+ * Check for valid flags set on @rs
+ *
+ * Has to be called after parsing of the ctr flags!
+ */
+static int rs_check_for_valid_flags(struct raid_set *rs)
+{
+	if (rs->ctr_flags & ~__valid_flags(rs)) {
+		rs->ti->error = "Invalid flags combination";
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* MD raid10 bit definitions and helpers */
+#define RAID10_OFFSET			(1 << 16) /* stripes with data copies area adjacent on devices */
+#define RAID10_BROCKEN_USE_FAR_SETS	(1 << 17) /* Broken in raid10.c: use sets instead of whole stripe rotation */
+#define RAID10_USE_FAR_SETS		(1 << 18) /* Use sets instead of whole stripe rotation */
+#define RAID10_FAR_COPIES_SHIFT		8	  /* raid10 # far copies shift (2nd byte of layout) */
+
+/* Return md raid10 near copies for @layout */
+static unsigned int __raid10_near_copies(int layout)
+{
+	return layout & 0xFF;
+}
+
+/* Return md raid10 far copies for @layout */
+static unsigned int __raid10_far_copies(int layout)
+{
+	return __raid10_near_copies(layout >> RAID10_FAR_COPIES_SHIFT);
+}
+
+/* Return true if md raid10 offset for @layout */
+static bool __is_raid10_offset(int layout)
+{
+	return !!(layout & RAID10_OFFSET);
+}
+
+/* Return true if md raid10 near for @layout */
+static bool __is_raid10_near(int layout)
+{
+	return !__is_raid10_offset(layout) && __raid10_near_copies(layout) > 1;
+}
+
+/* Return true if md raid10 far for @layout */
+static bool __is_raid10_far(int layout)
+{
+	return !__is_raid10_offset(layout) && __raid10_far_copies(layout) > 1;
+}
+
+/* Return md raid10 layout string for @layout */
+static const char *raid10_md_layout_to_format(int layout)
 {
 	/*
-	 * Bit 16 and 17 stand for "offset" and "use_far_sets"
+	 * Bit 16 stands for "offset"
+	 * (i.e. adjacent stripes hold copies)
+	 *
 	 * Refer to MD's raid10.c for details
 	 */
-	if ((layout & 0x10000) && (layout & 0x20000))
+	if (__is_raid10_offset(layout))
 		return "offset";
 
-	if ((layout & 0xFF) > 1)
+	if (__raid10_near_copies(layout) > 1)
 		return "near";
 
+	WARN_ON(__raid10_far_copies(layout) < 2);
+
 	return "far";
 }
 
-static unsigned raid10_md_layout_to_copies(int layout)
+/* Return md raid10 algorithm for @name */
+static int raid10_name_to_format(const char *name)
 {
-	if ((layout & 0xFF) > 1)
-		return layout & 0xFF;
-	return (layout >> 8) & 0xFF;
+	if (!strcasecmp(name, "near"))
+		return ALGORITHM_RAID10_NEAR;
+	else if (!strcasecmp(name, "offset"))
+		return ALGORITHM_RAID10_OFFSET;
+	else if (!strcasecmp(name, "far"))
+		return ALGORITHM_RAID10_FAR;
+
+	return -EINVAL;
 }
 
-static int raid10_format_to_md_layout(char *format, unsigned copies)
+/* Return md raid10 copies for @layout */
+static unsigned int raid10_md_layout_to_copies(int layout)
 {
-	unsigned n = 1, f = 1;
+	return max(__raid10_near_copies(layout), __raid10_far_copies(layout));
+}
 
-	if (!strcasecmp("near", format))
+/* Return md raid10 format id for @format string */
+static int raid10_format_to_md_layout(struct raid_set *rs,
+				      unsigned int algorithm,
+				      unsigned int copies)
+{
+	unsigned int n = 1, f = 1, r = 0;
+
+	/*
+	 * MD resilienece flaw:
+	 *
+	 * enabling use_far_sets for far/offset formats causes copies
+	 * to be colocated on the same devs together with their origins!
+	 *
+	 * -> disable it for now in the definition above
+	 */
+	if (algorithm == ALGORITHM_RAID10_DEFAULT ||
+	    algorithm == ALGORITHM_RAID10_NEAR)
 		n = copies;
-	else
+
+	else if (algorithm == ALGORITHM_RAID10_OFFSET) {
 		f = copies;
+		r = RAID10_OFFSET;
+		if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
+			r |= RAID10_USE_FAR_SETS;
 
-	if (!strcasecmp("offset", format))
-		return 0x30000 | (f << 8) | n;
+	} else if (algorithm == ALGORITHM_RAID10_FAR) {
+		f = copies;
+		r = !RAID10_OFFSET;
+		if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
+			r |= RAID10_USE_FAR_SETS;
 
-	if (!strcasecmp("far", format))
-		return 0x20000 | (f << 8) | n;
+	} else
+		return -EINVAL;
 
-	return (f << 8) | n;
+	return r | (f << RAID10_FAR_COPIES_SHIFT) | n;
 }
+/* END: MD raid10 bit definitions and helpers */
 
-static struct raid_type *get_raid_type(char *name)
+/* Check for any of the raid10 algorithms */
+static bool __got_raid10(struct raid_type *rtp, const int layout)
 {
-	int i;
+	if (rtp->level == 10) {
+		switch (rtp->algorithm) {
+		case ALGORITHM_RAID10_DEFAULT:
+		case ALGORITHM_RAID10_NEAR:
+			return __is_raid10_near(layout);
+		case ALGORITHM_RAID10_OFFSET:
+			return __is_raid10_offset(layout);
+		case ALGORITHM_RAID10_FAR:
+			return __is_raid10_far(layout);
+		default:
+			break;
+		}
+	}
+
+	return false;
+}
 
-	for (i = 0; i < ARRAY_SIZE(raid_types); i++)
-		if (!strcmp(raid_types[i].name, name))
-			return &raid_types[i];
+/* Return raid_type for @name */
+static struct raid_type *get_raid_type(const char *name)
+{
+	struct raid_type *rtp = raid_types + ARRAY_SIZE(raid_types);
+
+	while (rtp-- > raid_types)
+		if (!strcasecmp(rtp->name, name))
+			return rtp;
 
 	return NULL;
 }
 
-static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *raid_type, unsigned raid_devs)
+/* Return raid_type for @name based derived from @level and @layout */
+static struct raid_type *get_raid_type_by_ll(const int level, const int layout)
 {
-	unsigned i;
+	struct raid_type *rtp = raid_types + ARRAY_SIZE(raid_types);
+
+	while (rtp-- > raid_types) {
+		/* RAID10 special checks based on @layout flags/properties */
+		if (rtp->level == level &&
+		    (__got_raid10(rtp, layout) || rtp->algorithm == layout))
+			return rtp;
+	}
+
+	return NULL;
+}
+
+/*
+ * Conditionally change bdev capacity of @rs
+ * in case of a disk add/remove reshape
+ */
+static void rs_set_capacity(struct raid_set *rs)
+{
+	struct mddev *mddev = &rs->md;
+	struct md_rdev *rdev;
+	struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table));
+
+	/*
+	 * raid10 sets rdev->sector to the device size, which
+	 * is unintended in case of out-of-place reshaping
+	 */
+	rdev_for_each(rdev, mddev)
+		rdev->sectors = mddev->dev_sectors;
+
+	set_capacity(gendisk, mddev->array_sectors);
+	revalidate_disk(gendisk);
+}
+
+/*
+ * Set the mddev properties in @rs to the current
+ * ones retrieved from the freshest superblock
+ */
+static void rs_set_cur(struct raid_set *rs)
+{
+	struct mddev *mddev = &rs->md;
+
+	mddev->new_level = mddev->level;
+	mddev->new_layout = mddev->layout;
+	mddev->new_chunk_sectors = mddev->chunk_sectors;
+}
+
+/*
+ * Set the mddev properties in @rs to the new
+ * ones requested by the ctr
+ */
+static void rs_set_new(struct raid_set *rs)
+{
+	struct mddev *mddev = &rs->md;
+
+	mddev->level = mddev->new_level;
+	mddev->layout = mddev->new_layout;
+	mddev->chunk_sectors = mddev->new_chunk_sectors;
+	mddev->raid_disks = rs->raid_disks;
+	mddev->delta_disks = 0;
+}
+
+static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *raid_type,
+				       unsigned int raid_devs)
+{
+	unsigned int i;
 	struct raid_set *rs;
 
 	if (raid_devs <= raid_type->parity_devs) {
@@ -164,15 +683,19 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra
 
 	mddev_init(&rs->md);
 
+	rs->raid_disks = raid_devs;
+	rs->delta_disks = 0;
+
 	rs->ti = ti;
 	rs->raid_type = raid_type;
+	rs->stripe_cache_entries = 256;
 	rs->md.raid_disks = raid_devs;
 	rs->md.level = raid_type->level;
 	rs->md.new_level = rs->md.level;
 	rs->md.layout = raid_type->algorithm;
 	rs->md.new_layout = rs->md.layout;
 	rs->md.delta_disks = 0;
-	rs->md.recovery_cp = 0;
+	rs->md.recovery_cp = MaxSector;
 
 	for (i = 0; i < raid_devs; i++)
 		md_rdev_init(&rs->dev[i].rdev);
@@ -189,11 +712,11 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra
 	return rs;
 }
 
-static void context_free(struct raid_set *rs)
+static void raid_set_free(struct raid_set *rs)
 {
 	int i;
 
-	for (i = 0; i < rs->md.raid_disks; i++) {
+	for (i = 0; i < rs->raid_disks; i++) {
 		if (rs->dev[i].meta_dev)
 			dm_put_device(rs->ti, rs->dev[i].meta_dev);
 		md_rdev_clear(&rs->dev[i].rdev);
@@ -218,16 +741,22 @@ static void context_free(struct raid_set *rs)
  *    <meta_dev> -
  *
  * This code parses those words.  If there is a failure,
- * the caller must use context_free to unwind the operations.
+ * the caller must use raid_set_free() to unwind the operations.
  */
-static int dev_parms(struct raid_set *rs, char **argv)
+static int parse_dev_params(struct raid_set *rs, struct dm_arg_set *as)
 {
 	int i;
 	int rebuild = 0;
 	int metadata_available = 0;
-	int ret = 0;
+	int r = 0;
+	const char *arg;
 
-	for (i = 0; i < rs->md.raid_disks; i++, argv += 2) {
+	/* Put off the number of raid devices argument to get to dev pairs */
+	arg = dm_shift_arg(as);
+	if (!arg)
+		return -EINVAL;
+
+	for (i = 0; i < rs->raid_disks; i++) {
 		rs->dev[i].rdev.raid_disk = i;
 
 		rs->dev[i].meta_dev = NULL;
@@ -240,39 +769,49 @@ static int dev_parms(struct raid_set *rs, char **argv)
 		rs->dev[i].rdev.data_offset = 0;
 		rs->dev[i].rdev.mddev = &rs->md;
 
-		if (strcmp(argv[0], "-")) {
-			ret = dm_get_device(rs->ti, argv[0],
-					    dm_table_get_mode(rs->ti->table),
-					    &rs->dev[i].meta_dev);
-			rs->ti->error = "RAID metadata device lookup failure";
-			if (ret)
-				return ret;
+		arg = dm_shift_arg(as);
+		if (!arg)
+			return -EINVAL;
+
+		if (strcmp(arg, "-")) {
+			r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
+					  &rs->dev[i].meta_dev);
+			if (r) {
+				rs->ti->error = "RAID metadata device lookup failure";
+				return r;
+			}
 
 			rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL);
-			if (!rs->dev[i].rdev.sb_page)
+			if (!rs->dev[i].rdev.sb_page) {
+				rs->ti->error = "Failed to allocate superblock page";
 				return -ENOMEM;
+			}
 		}
 
-		if (!strcmp(argv[1], "-")) {
+		arg = dm_shift_arg(as);
+		if (!arg)
+			return -EINVAL;
+
+		if (!strcmp(arg, "-")) {
 			if (!test_bit(In_sync, &rs->dev[i].rdev.flags) &&
 			    (!rs->dev[i].rdev.recovery_offset)) {
 				rs->ti->error = "Drive designated for rebuild not specified";
 				return -EINVAL;
 			}
 
-			rs->ti->error = "No data device supplied with metadata device";
-			if (rs->dev[i].meta_dev)
+			if (rs->dev[i].meta_dev) {
+				rs->ti->error = "No data device supplied with metadata device";
 				return -EINVAL;
+			}
 
 			continue;
 		}
 
-		ret = dm_get_device(rs->ti, argv[1],
-				    dm_table_get_mode(rs->ti->table),
-				    &rs->dev[i].data_dev);
-		if (ret) {
+		r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
+				  &rs->dev[i].data_dev);
+		if (r) {
 			rs->ti->error = "RAID device lookup failure";
-			return ret;
+			return r;
 		}
 
 		if (rs->dev[i].meta_dev) {
@@ -280,7 +819,7 @@ static int dev_parms(struct raid_set *rs, char **argv)
 			rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev;
 		}
 		rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev;
-		list_add(&rs->dev[i].rdev.same_set, &rs->md.disks);
+		list_add_tail(&rs->dev[i].rdev.same_set, &rs->md.disks);
 		if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
 			rebuild++;
 	}
@@ -301,8 +840,7 @@ static int dev_parms(struct raid_set *rs, char **argv)
 		 *
 		 * User could specify 'nosync' option if desperate.
 		 */
-		DMERR("Unable to rebuild drive while array is not in-sync");
-		rs->ti->error = "RAID device lookup failure";
+		rs->ti->error = "Unable to rebuild drive while array is not in-sync";
 		return -EINVAL;
 	}
 
@@ -325,7 +863,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
 
 	if (!region_size) {
 		/*
-		 * Choose a reasonable default.  All figures in sectors.
+		 * Choose a reasonable default.	 All figures in sectors.
 		 */
 		if (min_region_size > (1 << 13)) {
 			/* If not a power of 2, make it the next power of 2 */
@@ -366,7 +904,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
 	/*
 	 * Convert sectors to bytes.
 	 */
-	rs->md.bitmap_info.chunksize = (region_size << 9);
+	rs->md.bitmap_info.chunksize = to_bytes(region_size);
 
 	return 0;
 }
@@ -382,9 +920,9 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
  */
 static int validate_raid_redundancy(struct raid_set *rs)
 {
-	unsigned i, rebuild_cnt = 0;
-	unsigned rebuilds_per_group = 0, copies, d;
-	unsigned group_size, last_group_start;
+	unsigned int i, rebuild_cnt = 0;
+	unsigned int rebuilds_per_group = 0, copies;
+	unsigned int group_size, last_group_start;
 
 	for (i = 0; i < rs->md.raid_disks; i++)
 		if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
@@ -403,7 +941,7 @@ static int validate_raid_redundancy(struct raid_set *rs)
 			goto too_many;
 		break;
 	case 10:
-		copies = raid10_md_layout_to_copies(rs->md.layout);
+		copies = raid10_md_layout_to_copies(rs->md.new_layout);
 		if (rebuild_cnt < copies)
 			break;
 
@@ -417,17 +955,16 @@ static int validate_raid_redundancy(struct raid_set *rs)
 		 * simple case where the number of devices is a multiple of the
 		 * number of copies, we must also handle cases where the number
 		 * of devices is not a multiple of the number of copies.
-		 * E.g.    dev1 dev2 dev3 dev4 dev5
-		 *          A    A    B    B    C
-		 *          C    D    D    E    E
+		 * E.g.	   dev1 dev2 dev3 dev4 dev5
+		 *	    A	 A    B	   B	C
+		 *	    C	 D    D	   E	E
 		 */
-		if (!strcmp("near", raid10_md_layout_to_format(rs->md.layout))) {
-			for (i = 0; i < rs->md.raid_disks * copies; i++) {
+		if (__is_raid10_near(rs->md.new_layout)) {
+			for (i = 0; i < rs->md.raid_disks; i++) {
 				if (!(i % copies))
 					rebuilds_per_group = 0;
-				d = i % rs->md.raid_disks;
-				if ((!rs->dev[d].rdev.sb_page ||
-				     !test_bit(In_sync, &rs->dev[d].rdev.flags)) &&
+				if ((!rs->dev[i].rdev.sb_page ||
+				    !test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
 				    (++rebuilds_per_group >= copies))
 					goto too_many;
 			}
@@ -442,7 +979,7 @@ static int validate_raid_redundancy(struct raid_set *rs)
 		 * use the 'use_far_sets' variant.)
 		 *
 		 * This check is somewhat complicated by the need to account
-		 * for arrays that are not a multiple of (far) copies.  This
+		 * for arrays that are not a multiple of (far) copies.	This
 		 * results in the need to treat the last (potentially larger)
 		 * set differently.
 		 */
@@ -475,42 +1012,48 @@ too_many:
  *
  * Argument definitions
  *    <chunk_size>			The number of sectors per disk that
- *                                      will form the "stripe"
+ *					will form the "stripe"
  *    [[no]sync]			Force or prevent recovery of the
- *                                      entire array
+ *					entire array
  *    [rebuild <idx>]			Rebuild the drive indicated by the index
  *    [daemon_sleep <ms>]		Time between bitmap daemon work to
- *                                      clear bits
+ *					clear bits
  *    [min_recovery_rate <kB/sec/disk>]	Throttle RAID initialization
  *    [max_recovery_rate <kB/sec/disk>]	Throttle RAID initialization
  *    [write_mostly <idx>]		Indicate a write mostly drive via index
  *    [max_write_behind <sectors>]	See '-write-behind=' (man mdadm)
  *    [stripe_cache <sectors>]		Stripe cache size for higher RAIDs
- *    [region_size <sectors>]           Defines granularity of bitmap
+ *    [region_size <sectors>]		Defines granularity of bitmap
  *
  * RAID10-only options:
- *    [raid10_copies <# copies>]        Number of copies.  (Default: 2)
+ *    [raid10_copies <# copies>]	Number of copies.  (Default: 2)
  *    [raid10_format <near|far|offset>] Layout algorithm.  (Default: near)
  */
-static int parse_raid_params(struct raid_set *rs, char **argv,
-			     unsigned num_raid_params)
-{
-	char *raid10_format = "near";
-	unsigned raid10_copies = 2;
-	unsigned i;
-	unsigned long value, region_size = 0;
-	sector_t sectors_per_dev = rs->ti->len;
+static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
+			     unsigned int num_raid_params)
+{
+	int value, raid10_format = ALGORITHM_RAID10_DEFAULT;
+	unsigned int raid10_copies = 2;
+	unsigned int i, write_mostly = 0;
+	unsigned int region_size = 0;
 	sector_t max_io_len;
-	char *key;
+	const char *arg, *key;
+	struct raid_dev *rd;
+	struct raid_type *rt = rs->raid_type;
+
+	arg = dm_shift_arg(as);
+	num_raid_params--; /* Account for chunk_size argument */
+
+	if (kstrtoint(arg, 10, &value) < 0) {
+		rs->ti->error = "Bad numerical argument given for chunk_size";
+		return -EINVAL;
+	}
 
 	/*
 	 * First, parse the in-order required arguments
 	 * "chunk_size" is the only argument of this type.
 	 */
-	if ((kstrtoul(argv[0], 10, &value) < 0)) {
-		rs->ti->error = "Bad chunk size";
-		return -EINVAL;
-	} else if (rs->raid_type->level == 1) {
+	if (rt_is_raid1(rt)) {
 		if (value)
 			DMERR("Ignoring chunk size parameter for RAID 1");
 		value = 0;
@@ -523,8 +1066,6 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 	}
 
 	rs->md.new_chunk_sectors = rs->md.chunk_sectors = value;
-	argv++;
-	num_raid_params--;
 
 	/*
 	 * We set each individual device as In_sync with a completed
@@ -532,18 +1073,18 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 	 * replacement then one of the following cases applies:
 	 *
 	 *   1) User specifies 'rebuild'.
-	 *      - Device is reset when param is read.
+	 *	- Device is reset when param is read.
 	 *   2) A new device is supplied.
-	 *      - No matching superblock found, resets device.
+	 *	- No matching superblock found, resets device.
 	 *   3) Device failure was transient and returns on reload.
-	 *      - Failure noticed, resets device for bitmap replay.
+	 *	- Failure noticed, resets device for bitmap replay.
 	 *   4) Device hadn't completed recovery after previous failure.
-	 *      - Superblock is read and overrides recovery_offset.
+	 *	- Superblock is read and overrides recovery_offset.
 	 *
 	 * What is found in the superblocks of the devices is always
 	 * authoritative, unless 'rebuild' or '[no]sync' was specified.
 	 */
-	for (i = 0; i < rs->md.raid_disks; i++) {
+	for (i = 0; i < rs->raid_disks; i++) {
 		set_bit(In_sync, &rs->dev[i].rdev.flags);
 		rs->dev[i].rdev.recovery_offset = MaxSector;
 	}
@@ -552,72 +1093,112 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 	 * Second, parse the unordered optional arguments
 	 */
 	for (i = 0; i < num_raid_params; i++) {
-		if (!strcasecmp(argv[i], "nosync")) {
-			rs->md.recovery_cp = MaxSector;
-			rs->ctr_flags |= CTR_FLAG_NOSYNC;
+		key = dm_shift_arg(as);
+		if (!key) {
+			rs->ti->error = "Not enough raid parameters given";
+			return -EINVAL;
+		}
+
+		if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC))) {
+			if (test_and_set_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
+				rs->ti->error = "Only one 'nosync' argument allowed";
+				return -EINVAL;
+			}
 			continue;
 		}
-		if (!strcasecmp(argv[i], "sync")) {
-			rs->md.recovery_cp = 0;
-			rs->ctr_flags |= CTR_FLAG_SYNC;
+		if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_SYNC))) {
+			if (test_and_set_bit(__CTR_FLAG_SYNC, &rs->ctr_flags)) {
+				rs->ti->error = "Only one 'sync' argument allowed";
+				return -EINVAL;
+			}
+			continue;
+		}
+		if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_USE_NEAR_SETS))) {
+			if (test_and_set_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) {
+				rs->ti->error = "Only one 'raid10_use_new_sets' argument allowed";
+				return -EINVAL;
+			}
 			continue;
 		}
 
-		/* The rest of the optional arguments come in key/value pairs */
-		if ((i + 1) >= num_raid_params) {
+		arg = dm_shift_arg(as);
+		i++; /* Account for the argument pairs */
+		if (!arg) {
 			rs->ti->error = "Wrong number of raid parameters given";
 			return -EINVAL;
 		}
 
-		key = argv[i++];
+		/*
+		 * Parameters that take a string value are checked here.
+		 */
 
-		/* Parameters that take a string value are checked here. */
-		if (!strcasecmp(key, "raid10_format")) {
-			if (rs->raid_type->level != 10) {
+		if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_FORMAT))) {
+			if (test_and_set_bit(__CTR_FLAG_RAID10_FORMAT, &rs->ctr_flags)) {
+				rs->ti->error = "Only one 'raid10_format' argument pair allowed";
+				return -EINVAL;
+			}
+			if (!rt_is_raid10(rt)) {
 				rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type";
 				return -EINVAL;
 			}
-			if (strcmp("near", argv[i]) &&
-			    strcmp("far", argv[i]) &&
-			    strcmp("offset", argv[i])) {
+			raid10_format = raid10_name_to_format(arg);
+			if (raid10_format < 0) {
 				rs->ti->error = "Invalid 'raid10_format' value given";
-				return -EINVAL;
+				return raid10_format;
 			}
-			raid10_format = argv[i];
-			rs->ctr_flags |= CTR_FLAG_RAID10_FORMAT;
 			continue;
 		}
 
-		if (kstrtoul(argv[i], 10, &value) < 0) {
+		if (kstrtoint(arg, 10, &value) < 0) {
 			rs->ti->error = "Bad numerical argument given in raid params";
 			return -EINVAL;
 		}
 
-		/* Parameters that take a numeric value are checked here */
-		if (!strcasecmp(key, "rebuild")) {
-			if (value >= rs->md.raid_disks) {
+		if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD))) {
+			/*
+			 * "rebuild" is being passed in by userspace to provide
+			 * indexes of replaced devices and to set up additional
+			 * devices on raid level takeover.
+			 */
+			if (!__within_range(value, 0, rs->raid_disks - 1)) {
 				rs->ti->error = "Invalid rebuild index given";
 				return -EINVAL;
 			}
-			clear_bit(In_sync, &rs->dev[value].rdev.flags);
-			rs->dev[value].rdev.recovery_offset = 0;
-			rs->ctr_flags |= CTR_FLAG_REBUILD;
-		} else if (!strcasecmp(key, "write_mostly")) {
-			if (rs->raid_type->level != 1) {
+
+			if (test_and_set_bit(value, (void *) rs->rebuild_disks)) {
+				rs->ti->error = "rebuild for this index already given";
+				return -EINVAL;
+			}
+
+			rd = rs->dev + value;
+			clear_bit(In_sync, &rd->rdev.flags);
+			clear_bit(Faulty, &rd->rdev.flags);
+			rd->rdev.recovery_offset = 0;
+			set_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags);
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY))) {
+			if (!rt_is_raid1(rt)) {
 				rs->ti->error = "write_mostly option is only valid for RAID1";
 				return -EINVAL;
 			}
-			if (value >= rs->md.raid_disks) {
-				rs->ti->error = "Invalid write_mostly drive index given";
+
+			if (!__within_range(value, 0, rs->md.raid_disks - 1)) {
+				rs->ti->error = "Invalid write_mostly index given";
 				return -EINVAL;
 			}
+
+			write_mostly++;
 			set_bit(WriteMostly, &rs->dev[value].rdev.flags);
-		} else if (!strcasecmp(key, "max_write_behind")) {
-			if (rs->raid_type->level != 1) {
+			set_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags);
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_WRITE_BEHIND))) {
+			if (!rt_is_raid1(rt)) {
 				rs->ti->error = "max_write_behind option is only valid for RAID1";
 				return -EINVAL;
 			}
-			rs->ctr_flags |= CTR_FLAG_MAX_WRITE_BEHIND;
+
+			if (test_and_set_bit(__CTR_FLAG_MAX_WRITE_BEHIND, &rs->ctr_flags)) {
+				rs->ti->error = "Only one max_write_behind argument pair allowed";
+				return -EINVAL;
+			}
 
 			/*
 			 * In device-mapper, we specify things in sectors, but
@@ -628,64 +1209,121 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 				rs->ti->error = "Max write-behind limit out of range";
 				return -EINVAL;
 			}
+
 			rs->md.bitmap_info.max_write_behind = value;
-		} else if (!strcasecmp(key, "daemon_sleep")) {
-			rs->ctr_flags |= CTR_FLAG_DAEMON_SLEEP;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP))) {
+			if (test_and_set_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags)) {
+				rs->ti->error = "Only one daemon_sleep argument pair allowed";
+				return -EINVAL;
+			}
 			if (!value || (value > MAX_SCHEDULE_TIMEOUT)) {
 				rs->ti->error = "daemon sleep period out of range";
 				return -EINVAL;
 			}
 			rs->md.bitmap_info.daemon_sleep = value;
-		} else if (!strcasecmp(key, "stripe_cache")) {
-			rs->ctr_flags |= CTR_FLAG_STRIPE_CACHE;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DATA_OFFSET))) {
+			/* Userspace passes new data_offset after having extended the the data image LV */
+			if (test_and_set_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags)) {
+				rs->ti->error = "Only one data_offset argument pair allowed";
+				return -EINVAL;
+			}
+			/* Ensure sensible data offset */
+			if (value < 0 ||
+			    (value && (value < MIN_FREE_RESHAPE_SPACE || value % to_sector(PAGE_SIZE)))) {
+				rs->ti->error = "Bogus data_offset value";
+				return -EINVAL;
+			}
+			rs->data_offset = value;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DELTA_DISKS))) {
+			/* Define the +/-# of disks to add to/remove from the given raid set */
+			if (test_and_set_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags)) {
+				rs->ti->error = "Only one delta_disks argument pair allowed";
+				return -EINVAL;
+			}
+			/* Ensure MAX_RAID_DEVICES and raid type minimal_devs! */
+			if (!__within_range(abs(value), 1, MAX_RAID_DEVICES - rt->minimal_devs)) {
+				rs->ti->error = "Too many delta_disk requested";
+				return -EINVAL;
+			}
 
-			/*
-			 * In device-mapper, we specify things in sectors, but
-			 * MD records this value in kB
-			 */
-			value /= 2;
+			rs->delta_disks = value;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_STRIPE_CACHE))) {
+			if (test_and_set_bit(__CTR_FLAG_STRIPE_CACHE, &rs->ctr_flags)) {
+				rs->ti->error = "Only one stripe_cache argument pair allowed";
+				return -EINVAL;
+			}
 
-			if ((rs->raid_type->level != 5) &&
-			    (rs->raid_type->level != 6)) {
+			if (!rt_is_raid456(rt)) {
 				rs->ti->error = "Inappropriate argument: stripe_cache";
 				return -EINVAL;
 			}
-			if (raid5_set_cache_size(&rs->md, (int)value)) {
-				rs->ti->error = "Bad stripe_cache size";
+
+			rs->stripe_cache_entries = value;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MIN_RECOVERY_RATE))) {
+			if (test_and_set_bit(__CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags)) {
+				rs->ti->error = "Only one min_recovery_rate argument pair allowed";
 				return -EINVAL;
 			}
-		} else if (!strcasecmp(key, "min_recovery_rate")) {
-			rs->ctr_flags |= CTR_FLAG_MIN_RECOVERY_RATE;
 			if (value > INT_MAX) {
 				rs->ti->error = "min_recovery_rate out of range";
 				return -EINVAL;
 			}
 			rs->md.sync_speed_min = (int)value;
-		} else if (!strcasecmp(key, "max_recovery_rate")) {
-			rs->ctr_flags |= CTR_FLAG_MAX_RECOVERY_RATE;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE))) {
+			if (test_and_set_bit(__CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags)) {
+				rs->ti->error = "Only one max_recovery_rate argument pair allowed";
+				return -EINVAL;
+			}
 			if (value > INT_MAX) {
 				rs->ti->error = "max_recovery_rate out of range";
 				return -EINVAL;
 			}
 			rs->md.sync_speed_max = (int)value;
-		} else if (!strcasecmp(key, "region_size")) {
-			rs->ctr_flags |= CTR_FLAG_REGION_SIZE;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REGION_SIZE))) {
+			if (test_and_set_bit(__CTR_FLAG_REGION_SIZE, &rs->ctr_flags)) {
+				rs->ti->error = "Only one region_size argument pair allowed";
+				return -EINVAL;
+			}
+
 			region_size = value;
-		} else if (!strcasecmp(key, "raid10_copies") &&
-			   (rs->raid_type->level == 10)) {
-			if ((value < 2) || (value > 0xFF)) {
+			rs->requested_bitmap_chunk_sectors = value;
+		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_COPIES))) {
+			if (test_and_set_bit(__CTR_FLAG_RAID10_COPIES, &rs->ctr_flags)) {
+				rs->ti->error = "Only one raid10_copies argument pair allowed";
+				return -EINVAL;
+			}
+
+			if (!__within_range(value, 2, rs->md.raid_disks)) {
 				rs->ti->error = "Bad value for 'raid10_copies'";
 				return -EINVAL;
 			}
-			rs->ctr_flags |= CTR_FLAG_RAID10_COPIES;
+
 			raid10_copies = value;
 		} else {
 			DMERR("Unable to parse RAID parameter: %s", key);
-			rs->ti->error = "Unable to parse RAID parameters";
+			rs->ti->error = "Unable to parse RAID parameter";
 			return -EINVAL;
 		}
 	}
 
+	if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) &&
+	    test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
+		rs->ti->error = "sync and nosync are mutually exclusive";
+		return -EINVAL;
+	}
+
+	if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags) &&
+	    (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ||
+	     test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))) {
+		rs->ti->error = "sync/nosync and rebuild are mutually exclusive";
+		return -EINVAL;
+	}
+
+	if (write_mostly >= rs->md.raid_disks) {
+		rs->ti->error = "Can't set all raid1 devices to write_mostly";
+		return -EINVAL;
+	}
+
 	if (validate_region_size(rs, region_size))
 		return -EINVAL;
 
@@ -697,47 +1335,193 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 	if (dm_set_target_max_io_len(rs->ti, max_io_len))
 		return -EINVAL;
 
-	if (rs->raid_type->level == 10) {
+	if (rt_is_raid10(rt)) {
 		if (raid10_copies > rs->md.raid_disks) {
 			rs->ti->error = "Not enough devices to satisfy specification";
 			return -EINVAL;
 		}
 
-		/*
-		 * If the format is not "near", we only support
-		 * two copies at the moment.
-		 */
-		if (strcmp("near", raid10_format) && (raid10_copies > 2)) {
-			rs->ti->error = "Too many copies for given RAID10 format.";
+		rs->md.new_layout = raid10_format_to_md_layout(rs, raid10_format, raid10_copies);
+		if (rs->md.new_layout < 0) {
+			rs->ti->error = "Error getting raid10 format";
+			return rs->md.new_layout;
+		}
+
+		rt = get_raid_type_by_ll(10, rs->md.new_layout);
+		if (!rt) {
+			rs->ti->error = "Failed to recognize new raid10 layout";
 			return -EINVAL;
 		}
 
-		/* (Len * #mirrors) / #devices */
-		sectors_per_dev = rs->ti->len * raid10_copies;
-		sector_div(sectors_per_dev, rs->md.raid_disks);
-
-		rs->md.layout = raid10_format_to_md_layout(raid10_format,
-							   raid10_copies);
-		rs->md.new_layout = rs->md.layout;
-	} else if ((!rs->raid_type->level || rs->raid_type->level > 1) &&
-		   sector_div(sectors_per_dev,
-			      (rs->md.raid_disks - rs->raid_type->parity_devs))) {
-		rs->ti->error = "Target length not divisible by number of data devices";
-		return -EINVAL;
+		if ((rt->algorithm == ALGORITHM_RAID10_DEFAULT ||
+		     rt->algorithm == ALGORITHM_RAID10_NEAR) &&
+		    test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) {
+			rs->ti->error = "RAID10 format 'near' and 'raid10_use_near_sets' are incompatible";
+			return -EINVAL;
+		}
 	}
-	rs->md.dev_sectors = sectors_per_dev;
+
+	rs->raid10_copies = raid10_copies;
 
 	/* Assume there are no metadata devices until the drives are parsed */
 	rs->md.persistent = 0;
 	rs->md.external = 1;
 
+	/* Check, if any invalid ctr arguments have been passed in for the raid level */
+	return rs_check_for_valid_flags(rs);
+}
+
+/* Set raid4/5/6 cache size */
+static int rs_set_raid456_stripe_cache(struct raid_set *rs)
+{
+	int r;
+	struct r5conf *conf;
+	struct mddev *mddev = &rs->md;
+	uint32_t min_stripes = max(mddev->chunk_sectors, mddev->new_chunk_sectors) / 2;
+	uint32_t nr_stripes = rs->stripe_cache_entries;
+
+	if (!rt_is_raid456(rs->raid_type)) {
+		rs->ti->error = "Inappropriate raid level; cannot change stripe_cache size";
+		return -EINVAL;
+	}
+
+	if (nr_stripes < min_stripes) {
+		DMINFO("Adjusting requested %u stripe cache entries to %u to suit stripe size",
+		       nr_stripes, min_stripes);
+		nr_stripes = min_stripes;
+	}
+
+	conf = mddev->private;
+	if (!conf) {
+		rs->ti->error = "Cannot change stripe_cache size on inactive RAID set";
+		return -EINVAL;
+	}
+
+	/* Try setting number of stripes in raid456 stripe cache */
+	if (conf->min_nr_stripes != nr_stripes) {
+		r = raid5_set_cache_size(mddev, nr_stripes);
+		if (r) {
+			rs->ti->error = "Failed to set raid4/5/6 stripe cache size";
+			return r;
+		}
+
+		DMINFO("%u stripe cache entries", nr_stripes);
+	}
+
 	return 0;
 }
 
+/* Return # of data stripes as kept in mddev as of @rs (i.e. as of superblock) */
+static unsigned int mddev_data_stripes(struct raid_set *rs)
+{
+	return rs->md.raid_disks - rs->raid_type->parity_devs;
+}
+
+/* Return # of data stripes of @rs (i.e. as of ctr) */
+static unsigned int rs_data_stripes(struct raid_set *rs)
+{
+	return rs->raid_disks - rs->raid_type->parity_devs;
+}
+
+/* Calculate the sectors per device and per array used for @rs */
+static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev)
+{
+	int delta_disks;
+	unsigned int data_stripes;
+	struct mddev *mddev = &rs->md;
+	struct md_rdev *rdev;
+	sector_t array_sectors = rs->ti->len, dev_sectors = rs->ti->len;
+
+	if (use_mddev) {
+		delta_disks = mddev->delta_disks;
+		data_stripes = mddev_data_stripes(rs);
+	} else {
+		delta_disks = rs->delta_disks;
+		data_stripes = rs_data_stripes(rs);
+	}
+
+	/* Special raid1 case w/o delta_disks support (yet) */
+	if (rt_is_raid1(rs->raid_type))
+		;
+	else if (rt_is_raid10(rs->raid_type)) {
+		if (rs->raid10_copies < 2 ||
+		    delta_disks < 0) {
+			rs->ti->error = "Bogus raid10 data copies or delta disks";
+			return -EINVAL;
+		}
+
+		dev_sectors *= rs->raid10_copies;
+		if (sector_div(dev_sectors, data_stripes))
+			goto bad;
+
+		array_sectors = (data_stripes + delta_disks) * dev_sectors;
+		if (sector_div(array_sectors, rs->raid10_copies))
+			goto bad;
+
+	} else if (sector_div(dev_sectors, data_stripes))
+		goto bad;
+
+	else
+		/* Striped layouts */
+		array_sectors = (data_stripes + delta_disks) * dev_sectors;
+
+	rdev_for_each(rdev, mddev)
+		rdev->sectors = dev_sectors;
+
+	mddev->array_sectors = array_sectors;
+	mddev->dev_sectors = dev_sectors;
+
+	return 0;
+bad:
+	rs->ti->error = "Target length not divisible by number of data devices";
+	return -EINVAL;
+}
+
+/* Setup recovery on @rs */
+static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
+{
+	/* raid0 does not recover */
+	if (rs_is_raid0(rs))
+		rs->md.recovery_cp = MaxSector;
+	/*
+	 * A raid6 set has to be recovered either
+	 * completely or for the grown part to
+	 * ensure proper parity and Q-Syndrome
+	 */
+	else if (rs_is_raid6(rs))
+		rs->md.recovery_cp = dev_sectors;
+	/*
+	 * Other raid set types may skip recovery
+	 * depending on the 'nosync' flag.
+	 */
+	else
+		rs->md.recovery_cp = test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)
+				     ? MaxSector : dev_sectors;
+}
+
+/* Setup recovery on @rs based on raid type, device size and 'nosync' flag */
+static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
+{
+	if (!dev_sectors)
+		/* New raid set or 'sync' flag provided */
+		__rs_setup_recovery(rs, 0);
+	else if (dev_sectors == MaxSector)
+		/* Prevent recovery */
+		__rs_setup_recovery(rs, MaxSector);
+	else if (rs->dev[0].rdev.sectors < dev_sectors)
+		/* Grown raid set */
+		__rs_setup_recovery(rs, rs->dev[0].rdev.sectors);
+	else
+		__rs_setup_recovery(rs, MaxSector);
+}
+
 static void do_table_event(struct work_struct *ws)
 {
 	struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);
 
+	smp_rmb(); /* Make sure we access most actual mddev properties */
+	if (!rs_is_reshaping(rs))
+		rs_set_capacity(rs);
 	dm_table_event(rs->ti->table);
 }
 
@@ -749,19 +1533,225 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
 }
 
 /*
+ * Make sure a valid takover (level switch) is being requested on @rs
+ *
+ * Conversions of raid sets from one MD personality to another
+ * have to conform to restrictions which are enforced here.
+ */
+static int rs_check_takeover(struct raid_set *rs)
+{
+	struct mddev *mddev = &rs->md;
+	unsigned int near_copies;
+
+	if (rs->md.degraded) {
+		rs->ti->error = "Can't takeover degraded raid set";
+		return -EPERM;
+	}
+
+	if (rs_is_reshaping(rs)) {
+		rs->ti->error = "Can't takeover reshaping raid set";
+		return -EPERM;
+	}
+
+	switch (mddev->level) {
+	case 0:
+		/* raid0 -> raid1/5 with one disk */
+		if ((mddev->new_level == 1 || mddev->new_level == 5) &&
+		    mddev->raid_disks == 1)
+			return 0;
+
+		/* raid0 -> raid10 */
+		if (mddev->new_level == 10 &&
+		    !(rs->raid_disks % mddev->raid_disks))
+			return 0;
+
+		/* raid0 with multiple disks -> raid4/5/6 */
+		if (__within_range(mddev->new_level, 4, 6) &&
+		    mddev->new_layout == ALGORITHM_PARITY_N &&
+		    mddev->raid_disks > 1)
+			return 0;
+
+		break;
+
+	case 10:
+		/* Can't takeover raid10_offset! */
+		if (__is_raid10_offset(mddev->layout))
+			break;
+
+		near_copies = __raid10_near_copies(mddev->layout);
+
+		/* raid10* -> raid0 */
+		if (mddev->new_level == 0) {
+			/* Can takeover raid10_near with raid disks divisable by data copies! */
+			if (near_copies > 1 &&
+			    !(mddev->raid_disks % near_copies)) {
+				mddev->raid_disks /= near_copies;
+				mddev->delta_disks = mddev->raid_disks;
+				return 0;
+			}
+
+			/* Can takeover raid10_far */
+			if (near_copies == 1 &&
+			    __raid10_far_copies(mddev->layout) > 1)
+				return 0;
+
+			break;
+		}
+
+		/* raid10_{near,far} -> raid1 */
+		if (mddev->new_level == 1 &&
+		    max(near_copies, __raid10_far_copies(mddev->layout)) == mddev->raid_disks)
+			return 0;
+
+		/* raid10_{near,far} with 2 disks -> raid4/5 */
+		if (__within_range(mddev->new_level, 4, 5) &&
+		    mddev->raid_disks == 2)
+			return 0;
+		break;
+
+	case 1:
+		/* raid1 with 2 disks -> raid4/5 */
+		if (__within_range(mddev->new_level, 4, 5) &&
+		    mddev->raid_disks == 2) {
+			mddev->degraded = 1;
+			return 0;
+		}
+
+		/* raid1 -> raid0 */
+		if (mddev->new_level == 0 &&
+		    mddev->raid_disks == 1)
+			return 0;
+
+		/* raid1 -> raid10 */
+		if (mddev->new_level == 10)
+			return 0;
+		break;
+
+	case 4:
+		/* raid4 -> raid0 */
+		if (mddev->new_level == 0)
+			return 0;
+
+		/* raid4 -> raid1/5 with 2 disks */
+		if ((mddev->new_level == 1 || mddev->new_level == 5) &&
+		    mddev->raid_disks == 2)
+			return 0;
+
+		/* raid4 -> raid5/6 with parity N */
+		if (__within_range(mddev->new_level, 5, 6) &&
+		    mddev->layout == ALGORITHM_PARITY_N)
+			return 0;
+		break;
+
+	case 5:
+		/* raid5 with parity N -> raid0 */
+		if (mddev->new_level == 0 &&
+		    mddev->layout == ALGORITHM_PARITY_N)
+			return 0;
+
+		/* raid5 with parity N -> raid4 */
+		if (mddev->new_level == 4 &&
+		    mddev->layout == ALGORITHM_PARITY_N)
+			return 0;
+
+		/* raid5 with 2 disks -> raid1/4/10 */
+		if ((mddev->new_level == 1 || mddev->new_level == 4 || mddev->new_level == 10) &&
+		    mddev->raid_disks == 2)
+			return 0;
+
+		/* raid5_* ->  raid6_*_6 with Q-Syndrome N (e.g. raid5_ra -> raid6_ra_6 */
+		if (mddev->new_level == 6 &&
+		    ((mddev->layout == ALGORITHM_PARITY_N && mddev->new_layout == ALGORITHM_PARITY_N) ||
+		      __within_range(mddev->new_layout, ALGORITHM_LEFT_ASYMMETRIC_6, ALGORITHM_RIGHT_SYMMETRIC_6)))
+			return 0;
+		break;
+
+	case 6:
+		/* raid6 with parity N -> raid0 */
+		if (mddev->new_level == 0 &&
+		    mddev->layout == ALGORITHM_PARITY_N)
+			return 0;
+
+		/* raid6 with parity N -> raid4 */
+		if (mddev->new_level == 4 &&
+		    mddev->layout == ALGORITHM_PARITY_N)
+			return 0;
+
+		/* raid6_*_n with Q-Syndrome N -> raid5_* */
+		if (mddev->new_level == 5 &&
+		    ((mddev->layout == ALGORITHM_PARITY_N && mddev->new_layout == ALGORITHM_PARITY_N) ||
+		     __within_range(mddev->new_layout, ALGORITHM_LEFT_ASYMMETRIC, ALGORITHM_RIGHT_SYMMETRIC)))
+			return 0;
+
+	default:
+		break;
+	}
+
+	rs->ti->error = "takeover not possible";
+	return -EINVAL;
+}
+
+/* True if @rs requested to be taken over */
+static bool rs_takeover_requested(struct raid_set *rs)
+{
+	return rs->md.new_level != rs->md.level;
+}
+
+/* True if @rs is requested to reshape by ctr */
+static bool rs_reshape_requested(struct raid_set *rs)
+{
+	bool change;
+	struct mddev *mddev = &rs->md;
+
+	if (rs_takeover_requested(rs))
+		return false;
+
+	if (!mddev->level)
+		return false;
+
+	change = mddev->new_layout != mddev->layout ||
+		 mddev->new_chunk_sectors != mddev->chunk_sectors ||
+		 rs->delta_disks;
+
+	/* Historical case to support raid1 reshape without delta disks */
+	if (mddev->level == 1) {
+		if (rs->delta_disks)
+			return !!rs->delta_disks;
+
+		return !change &&
+		       mddev->raid_disks != rs->raid_disks;
+	}
+
+	if (mddev->level == 10)
+		return change &&
+		       !__is_raid10_far(mddev->new_layout) &&
+		       rs->delta_disks >= 0;
+
+	return change;
+}
+
+/*  Features */
+#define	FEATURE_FLAG_SUPPORTS_V190	0x1 /* Supports extended superblock */
+
+/* State flags for sb->flags */
+#define	SB_FLAG_RESHAPE_ACTIVE		0x1
+#define	SB_FLAG_RESHAPE_BACKWARDS	0x2
+
+/*
  * This structure is never routinely used by userspace, unlike md superblocks.
  * Devices with this superblock should only ever be accessed via device-mapper.
  */
 #define DM_RAID_MAGIC 0x64526D44
 struct dm_raid_superblock {
 	__le32 magic;		/* "DmRd" */
-	__le32 features;	/* Used to indicate possible future changes */
+	__le32 compat_features;	/* Used to indicate compatible features (like 1.9.0 ondisk metadata extension) */
 
-	__le32 num_devices;	/* Number of devices in this array. (Max 64) */
-	__le32 array_position;	/* The position of this drive in the array */
+	__le32 num_devices;	/* Number of devices in this raid set. (Max 64) */
+	__le32 array_position;	/* The position of this drive in the raid set */
 
 	__le64 events;		/* Incremented by md when superblock updated */
-	__le64 failed_devices;	/* Bit field of devices to indicate failures */
+	__le64 failed_devices;	/* Pre 1.9.0 part of bit field of devices to */
+				/* indicate failures (see extension below) */
 
 	/*
 	 * This offset tracks the progress of the repair or replacement of
@@ -770,21 +1760,95 @@ struct dm_raid_superblock {
 	__le64 disk_recovery_offset;
 
 	/*
-	 * This offset tracks the progress of the initial array
+	 * This offset tracks the progress of the initial raid set
 	 * synchronisation/parity calculation.
 	 */
 	__le64 array_resync_offset;
 
 	/*
-	 * RAID characteristics
+	 * raid characteristics
 	 */
 	__le32 level;
 	__le32 layout;
 	__le32 stripe_sectors;
 
-	/* Remainder of a logical block is zero-filled when writing (see super_sync()). */
+	/********************************************************************
+	 * BELOW FOLLOW V1.9.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!!
+	 *
+	 * FEATURE_FLAG_SUPPORTS_V190 in the features member indicates that those exist
+	 */
+
+	__le32 flags; /* Flags defining array states for reshaping */
+
+	/*
+	 * This offset tracks the progress of a raid
+	 * set reshape in order to be able to restart it
+	 */
+	__le64 reshape_position;
+
+	/*
+	 * These define the properties of the array in case of an interrupted reshape
+	 */
+	__le32 new_level;
+	__le32 new_layout;
+	__le32 new_stripe_sectors;
+	__le32 delta_disks;
+
+	__le64 array_sectors; /* Array size in sectors */
+
+	/*
+	 * Sector offsets to data on devices (reshaping).
+	 * Needed to support out of place reshaping, thus
+	 * not writing over any stripes whilst converting
+	 * them from old to new layout
+	 */
+	__le64 data_offset;
+	__le64 new_data_offset;
+
+	__le64 sectors; /* Used device size in sectors */
+
+	/*
+	 * Additonal Bit field of devices indicating failures to support
+	 * up to 256 devices with the 1.9.0 on-disk metadata format
+	 */
+	__le64 extended_failed_devices[DISKS_ARRAY_ELEMS - 1];
+
+	__le32 incompat_features;	/* Used to indicate any incompatible features */
+
+	/* Always set rest up to logical block size to 0 when writing (see get_metadata_device() below). */
 } __packed;
 
+/*
+ * Check for reshape constraints on raid set @rs:
+ *
+ * - reshape function non-existent
+ * - degraded set
+ * - ongoing recovery
+ * - ongoing reshape
+ *
+ * Returns 0 if none or -EPERM if given constraint
+ * and error message reference in @errmsg
+ */
+static int rs_check_reshape(struct raid_set *rs)
+{
+	struct mddev *mddev = &rs->md;
+
+	if (!mddev->pers || !mddev->pers->check_reshape)
+		rs->ti->error = "Reshape not supported";
+	else if (mddev->degraded)
+		rs->ti->error = "Can't reshape degraded raid set";
+	else if (rs_is_recovering(rs))
+		rs->ti->error = "Convert request on recovering raid set prohibited";
+	else if (rs_is_reshaping(rs))
+		rs->ti->error = "raid set already reshaping!";
+	else if (!(rs_is_raid1(rs) || rs_is_raid10(rs) || rs_is_raid456(rs)))
+		rs->ti->error = "Reshaping only supported for raid1/4/5/6/10";
+	else
+		return 0;
+
+	return -EPERM;
+}
+
 static int read_disk_sb(struct md_rdev *rdev, int size)
 {
 	BUG_ON(!rdev->sb_page);
@@ -792,7 +1856,7 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
 	if (rdev->sb_loaded)
 		return 0;
 
-	if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, 1)) {
+	if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, 0, true)) {
 		DMERR("Failed to read superblock of device at position %d",
 		      rdev->raid_disk);
 		md_error(rdev->mddev, rdev);
@@ -804,31 +1868,67 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
 	return 0;
 }
 
+static void sb_retrieve_failed_devices(struct dm_raid_superblock *sb, uint64_t *failed_devices)
+{
+	failed_devices[0] = le64_to_cpu(sb->failed_devices);
+	memset(failed_devices + 1, 0, sizeof(sb->extended_failed_devices));
+
+	if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) {
+		int i = ARRAY_SIZE(sb->extended_failed_devices);
+
+		while (i--)
+			failed_devices[i+1] = le64_to_cpu(sb->extended_failed_devices[i]);
+	}
+}
+
+static void sb_update_failed_devices(struct dm_raid_superblock *sb, uint64_t *failed_devices)
+{
+	int i = ARRAY_SIZE(sb->extended_failed_devices);
+
+	sb->failed_devices = cpu_to_le64(failed_devices[0]);
+	while (i--)
+		sb->extended_failed_devices[i] = cpu_to_le64(failed_devices[i+1]);
+}
+
+/*
+ * Synchronize the superblock members with the raid set properties
+ *
+ * All superblock data is little endian.
+ */
 static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
 {
-	int i;
-	uint64_t failed_devices;
+	bool update_failed_devices = false;
+	unsigned int i;
+	uint64_t failed_devices[DISKS_ARRAY_ELEMS];
 	struct dm_raid_superblock *sb;
 	struct raid_set *rs = container_of(mddev, struct raid_set, md);
 
+	/* No metadata device, no superblock */
+	if (!rdev->meta_bdev)
+		return;
+
+	BUG_ON(!rdev->sb_page);
+
 	sb = page_address(rdev->sb_page);
-	failed_devices = le64_to_cpu(sb->failed_devices);
 
-	for (i = 0; i < mddev->raid_disks; i++)
-		if (!rs->dev[i].data_dev ||
-		    test_bit(Faulty, &(rs->dev[i].rdev.flags)))
-			failed_devices |= (1ULL << i);
+	sb_retrieve_failed_devices(sb, failed_devices);
 
-	memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
+	for (i = 0; i < rs->raid_disks; i++)
+		if (!rs->dev[i].data_dev || test_bit(Faulty, &rs->dev[i].rdev.flags)) {
+			update_failed_devices = true;
+			set_bit(i, (void *) failed_devices);
+		}
+
+	if (update_failed_devices)
+		sb_update_failed_devices(sb, failed_devices);
 
 	sb->magic = cpu_to_le32(DM_RAID_MAGIC);
-	sb->features = cpu_to_le32(0);	/* No features yet */
+	sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
 
 	sb->num_devices = cpu_to_le32(mddev->raid_disks);
 	sb->array_position = cpu_to_le32(rdev->raid_disk);
 
 	sb->events = cpu_to_le64(mddev->events);
-	sb->failed_devices = cpu_to_le64(failed_devices);
 
 	sb->disk_recovery_offset = cpu_to_le64(rdev->recovery_offset);
 	sb->array_resync_offset = cpu_to_le64(mddev->recovery_cp);
@@ -836,6 +1936,33 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
 	sb->level = cpu_to_le32(mddev->level);
 	sb->layout = cpu_to_le32(mddev->layout);
 	sb->stripe_sectors = cpu_to_le32(mddev->chunk_sectors);
+
+	sb->new_level = cpu_to_le32(mddev->new_level);
+	sb->new_layout = cpu_to_le32(mddev->new_layout);
+	sb->new_stripe_sectors = cpu_to_le32(mddev->new_chunk_sectors);
+
+	sb->delta_disks = cpu_to_le32(mddev->delta_disks);
+
+	smp_rmb(); /* Make sure we access most recent reshape position */
+	sb->reshape_position = cpu_to_le64(mddev->reshape_position);
+	if (le64_to_cpu(sb->reshape_position) != MaxSector) {
+		/* Flag ongoing reshape */
+		sb->flags |= cpu_to_le32(SB_FLAG_RESHAPE_ACTIVE);
+
+		if (mddev->delta_disks < 0 || mddev->reshape_backwards)
+			sb->flags |= cpu_to_le32(SB_FLAG_RESHAPE_BACKWARDS);
+	} else {
+		/* Clear reshape flags */
+		sb->flags &= ~(cpu_to_le32(SB_FLAG_RESHAPE_ACTIVE|SB_FLAG_RESHAPE_BACKWARDS));
+	}
+
+	sb->array_sectors = cpu_to_le64(mddev->array_sectors);
+	sb->data_offset = cpu_to_le64(rdev->data_offset);
+	sb->new_data_offset = cpu_to_le64(rdev->new_data_offset);
+	sb->sectors = cpu_to_le64(rdev->sectors);
+
+	/* Zero out the rest of the payload after the size of the superblock */
+	memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
 }
 
 /*
@@ -848,7 +1975,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
  */
 static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 {
-	int ret;
+	int r;
 	struct dm_raid_superblock *sb;
 	struct dm_raid_superblock *refsb;
 	uint64_t events_sb, events_refsb;
@@ -860,9 +1987,9 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 		return -EINVAL;
 	}
 
-	ret = read_disk_sb(rdev, rdev->sb_size);
-	if (ret)
-		return ret;
+	r = read_disk_sb(rdev, rdev->sb_size);
+	if (r)
+		return r;
 
 	sb = page_address(rdev->sb_page);
 
@@ -876,6 +2003,7 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 		super_sync(rdev->mddev, rdev);
 
 		set_bit(FirstUse, &rdev->flags);
+		sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
 
 		/* Force writing of superblocks to disk */
 		set_bit(MD_CHANGE_DEVS, &rdev->mddev->flags);
@@ -895,129 +2023,212 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 	return (events_sb > events_refsb) ? 1 : 0;
 }
 
-static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
+static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 {
 	int role;
-	struct raid_set *rs = container_of(mddev, struct raid_set, md);
+	unsigned int d;
+	struct mddev *mddev = &rs->md;
 	uint64_t events_sb;
-	uint64_t failed_devices;
+	uint64_t failed_devices[DISKS_ARRAY_ELEMS];
 	struct dm_raid_superblock *sb;
-	uint32_t new_devs = 0;
-	uint32_t rebuilds = 0;
+	uint32_t new_devs = 0, rebuild_and_new = 0, rebuilds = 0;
 	struct md_rdev *r;
 	struct dm_raid_superblock *sb2;
 
 	sb = page_address(rdev->sb_page);
 	events_sb = le64_to_cpu(sb->events);
-	failed_devices = le64_to_cpu(sb->failed_devices);
 
 	/*
 	 * Initialise to 1 if this is a new superblock.
 	 */
 	mddev->events = events_sb ? : 1;
 
+	mddev->reshape_position = MaxSector;
+
 	/*
-	 * Reshaping is not currently allowed
+	 * Reshaping is supported, e.g. reshape_position is valid
+	 * in superblock and superblock content is authoritative.
 	 */
-	if (le32_to_cpu(sb->level) != mddev->level) {
-		DMERR("Reshaping arrays not yet supported. (RAID level change)");
-		return -EINVAL;
-	}
-	if (le32_to_cpu(sb->layout) != mddev->layout) {
-		DMERR("Reshaping arrays not yet supported. (RAID layout change)");
-		DMERR("  0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
-		DMERR("  Old layout: %s w/ %d copies",
-		      raid10_md_layout_to_format(le32_to_cpu(sb->layout)),
-		      raid10_md_layout_to_copies(le32_to_cpu(sb->layout)));
-		DMERR("  New layout: %s w/ %d copies",
-		      raid10_md_layout_to_format(mddev->layout),
-		      raid10_md_layout_to_copies(mddev->layout));
-		return -EINVAL;
-	}
-	if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
-		DMERR("Reshaping arrays not yet supported. (stripe sectors change)");
-		return -EINVAL;
-	}
+	if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) {
+		/* Superblock is authoritative wrt given raid set layout! */
+		mddev->raid_disks = le32_to_cpu(sb->num_devices);
+		mddev->level = le32_to_cpu(sb->level);
+		mddev->layout = le32_to_cpu(sb->layout);
+		mddev->chunk_sectors = le32_to_cpu(sb->stripe_sectors);
+		mddev->new_level = le32_to_cpu(sb->new_level);
+		mddev->new_layout = le32_to_cpu(sb->new_layout);
+		mddev->new_chunk_sectors = le32_to_cpu(sb->new_stripe_sectors);
+		mddev->delta_disks = le32_to_cpu(sb->delta_disks);
+		mddev->array_sectors = le64_to_cpu(sb->array_sectors);
+
+		/* raid was reshaping and got interrupted */
+		if (le32_to_cpu(sb->flags) & SB_FLAG_RESHAPE_ACTIVE) {
+			if (test_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags)) {
+				DMERR("Reshape requested but raid set is still reshaping");
+				return -EINVAL;
+			}
 
-	/* We can only change the number of devices in RAID1 right now */
-	if ((rs->raid_type->level != 1) &&
-	    (le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
-		DMERR("Reshaping arrays not yet supported. (device count change)");
-		return -EINVAL;
+			if (mddev->delta_disks < 0 ||
+			    (!mddev->delta_disks && (le32_to_cpu(sb->flags) & SB_FLAG_RESHAPE_BACKWARDS)))
+				mddev->reshape_backwards = 1;
+			else
+				mddev->reshape_backwards = 0;
+
+			mddev->reshape_position = le64_to_cpu(sb->reshape_position);
+			rs->raid_type = get_raid_type_by_ll(mddev->level, mddev->layout);
+		}
+
+	} else {
+		/*
+		 * No takeover/reshaping, because we don't have the extended v1.9.0 metadata
+		 */
+		if (le32_to_cpu(sb->level) != mddev->level) {
+			DMERR("Reshaping/takeover raid sets not yet supported. (raid level/stripes/size change)");
+			return -EINVAL;
+		}
+		if (le32_to_cpu(sb->layout) != mddev->layout) {
+			DMERR("Reshaping raid sets not yet supported. (raid layout change)");
+			DMERR("	 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
+			DMERR("	 Old layout: %s w/ %d copies",
+			      raid10_md_layout_to_format(le32_to_cpu(sb->layout)),
+			      raid10_md_layout_to_copies(le32_to_cpu(sb->layout)));
+			DMERR("	 New layout: %s w/ %d copies",
+			      raid10_md_layout_to_format(mddev->layout),
+			      raid10_md_layout_to_copies(mddev->layout));
+			return -EINVAL;
+		}
+		if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
+			DMERR("Reshaping raid sets not yet supported. (stripe sectors change)");
+			return -EINVAL;
+		}
+
+		/* We can only change the number of devices in raid1 with old (i.e. pre 1.0.7) metadata */
+		if (!rt_is_raid1(rs->raid_type) &&
+		    (le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
+			DMERR("Reshaping raid sets not yet supported. (device count change from %u to %u)",
+			      sb->num_devices, mddev->raid_disks);
+			return -EINVAL;
+		}
+
+		/* Table line is checked vs. authoritative superblock */
+		rs_set_new(rs);
 	}
 
-	if (!(rs->ctr_flags & (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC)))
+	if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))
 		mddev->recovery_cp = le64_to_cpu(sb->array_resync_offset);
 
 	/*
 	 * During load, we set FirstUse if a new superblock was written.
 	 * There are two reasons we might not have a superblock:
-	 * 1) The array is brand new - in which case, all of the
-	 *    devices must have their In_sync bit set.  Also,
+	 * 1) The raid set is brand new - in which case, all of the
+	 *    devices must have their In_sync bit set.	Also,
 	 *    recovery_cp must be 0, unless forced.
-	 * 2) This is a new device being added to an old array
+	 * 2) This is a new device being added to an old raid set
 	 *    and the new device needs to be rebuilt - in which
 	 *    case the In_sync bit will /not/ be set and
 	 *    recovery_cp must be MaxSector.
+	 * 3) This is/are a new device(s) being added to an old
+	 *    raid set during takeover to a higher raid level
+	 *    to provide capacity for redundancy or during reshape
+	 *    to add capacity to grow the raid set.
 	 */
+	d = 0;
 	rdev_for_each(r, mddev) {
+		if (test_bit(FirstUse, &r->flags))
+			new_devs++;
+
 		if (!test_bit(In_sync, &r->flags)) {
-			DMINFO("Device %d specified for rebuild: "
-			       "Clearing superblock", r->raid_disk);
+			DMINFO("Device %d specified for rebuild; clearing superblock",
+				r->raid_disk);
 			rebuilds++;
-		} else if (test_bit(FirstUse, &r->flags))
-			new_devs++;
+
+			if (test_bit(FirstUse, &r->flags))
+				rebuild_and_new++;
+		}
+
+		d++;
 	}
 
-	if (!rebuilds) {
-		if (new_devs == mddev->raid_disks) {
-			DMINFO("Superblocks created for new array");
+	if (new_devs == rs->raid_disks || !rebuilds) {
+		/* Replace a broken device */
+		if (new_devs == 1 && !rs->delta_disks)
+			;
+		if (new_devs == rs->raid_disks) {
+			DMINFO("Superblocks created for new raid set");
 			set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
-		} else if (new_devs) {
-			DMERR("New device injected "
-			      "into existing array without 'rebuild' "
-			      "parameter specified");
+		} else if (new_devs != rebuilds &&
+			   new_devs != rs->delta_disks) {
+			DMERR("New device injected into existing raid set without "
+			      "'delta_disks' or 'rebuild' parameter specified");
 			return -EINVAL;
 		}
-	} else if (new_devs) {
-		DMERR("'rebuild' devices cannot be "
-		      "injected into an array with other first-time devices");
-		return -EINVAL;
-	} else if (mddev->recovery_cp != MaxSector) {
-		DMERR("'rebuild' specified while array is not in-sync");
+	} else if (new_devs && new_devs != rebuilds) {
+		DMERR("%u 'rebuild' devices cannot be injected into"
+		      " a raid set with %u other first-time devices",
+		      rebuilds, new_devs);
 		return -EINVAL;
+	} else if (rebuilds) {
+		if (rebuild_and_new && rebuilds != rebuild_and_new) {
+			DMERR("new device%s provided without 'rebuild'",
+			      new_devs > 1 ? "s" : "");
+			return -EINVAL;
+		} else if (rs_is_recovering(rs)) {
+			DMERR("'rebuild' specified while raid set is not in-sync (recovery_cp=%llu)",
+			      (unsigned long long) mddev->recovery_cp);
+			return -EINVAL;
+		} else if (rs_is_reshaping(rs)) {
+			DMERR("'rebuild' specified while raid set is being reshaped (reshape_position=%llu)",
+			      (unsigned long long) mddev->reshape_position);
+			return -EINVAL;
+		}
 	}
 
 	/*
 	 * Now we set the Faulty bit for those devices that are
 	 * recorded in the superblock as failed.
 	 */
+	sb_retrieve_failed_devices(sb, failed_devices);
 	rdev_for_each(r, mddev) {
 		if (!r->sb_page)
 			continue;
 		sb2 = page_address(r->sb_page);
 		sb2->failed_devices = 0;
+		memset(sb2->extended_failed_devices, 0, sizeof(sb2->extended_failed_devices));
 
 		/*
 		 * Check for any device re-ordering.
 		 */
 		if (!test_bit(FirstUse, &r->flags) && (r->raid_disk >= 0)) {
 			role = le32_to_cpu(sb2->array_position);
+			if (role < 0)
+				continue;
+
 			if (role != r->raid_disk) {
-				if (rs->raid_type->level != 1) {
-					rs->ti->error = "Cannot change device "
-						"positions in RAID array";
+				if (__is_raid10_near(mddev->layout)) {
+					if (mddev->raid_disks % __raid10_near_copies(mddev->layout) ||
+					    rs->raid_disks % rs->raid10_copies) {
+						rs->ti->error =
+							"Cannot change raid10 near set to odd # of devices!";
+						return -EINVAL;
+					}
+
+					sb2->array_position = cpu_to_le32(r->raid_disk);
+
+				} else if (!(rs_is_raid10(rs) && rt_is_raid0(rs->raid_type)) &&
+					   !(rs_is_raid0(rs) && rt_is_raid10(rs->raid_type)) &&
+					   !rt_is_raid1(rs->raid_type)) {
+					rs->ti->error = "Cannot change device positions in raid set";
 					return -EINVAL;
 				}
-				DMINFO("RAID1 device #%d now at position #%d",
-				       role, r->raid_disk);
+
+				DMINFO("raid device #%d now at position #%d", role, r->raid_disk);
 			}
 
 			/*
 			 * Partial recovery is performed on
 			 * returning failed devices.
 			 */
-			if (failed_devices & (1 << role))
+			if (test_bit(role, (void *) failed_devices))
 				set_bit(Faulty, &r->flags);
 		}
 	}
@@ -1028,41 +2239,60 @@ static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
 static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
 {
 	struct mddev *mddev = &rs->md;
-	struct dm_raid_superblock *sb = page_address(rdev->sb_page);
+	struct dm_raid_superblock *sb;
+
+	if (rs_is_raid0(rs) || !rdev->sb_page)
+		return 0;
+
+	sb = page_address(rdev->sb_page);
 
 	/*
 	 * If mddev->events is not set, we know we have not yet initialized
 	 * the array.
 	 */
-	if (!mddev->events && super_init_validation(mddev, rdev))
+	if (!mddev->events && super_init_validation(rs, rdev))
 		return -EINVAL;
 
-	if (le32_to_cpu(sb->features)) {
-		rs->ti->error = "Unable to assemble array: No feature flags supported yet";
+	if (le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
+		rs->ti->error = "Unable to assemble array: Unknown flag(s) in compatible feature flags";
+		return -EINVAL;
+	}
+
+	if (sb->incompat_features) {
+		rs->ti->error = "Unable to assemble array: No incompatible feature flags supported yet";
 		return -EINVAL;
 	}
 
 	/* Enable bitmap creation for RAID levels != 0 */
-	mddev->bitmap_info.offset = (rs->raid_type->level) ? to_sector(4096) : 0;
+	mddev->bitmap_info.offset = rt_is_raid0(rs->raid_type) ? 0 : to_sector(4096);
 	rdev->mddev->bitmap_info.default_offset = mddev->bitmap_info.offset;
 
-	if (!test_bit(FirstUse, &rdev->flags)) {
+	if (!test_and_clear_bit(FirstUse, &rdev->flags)) {
+		/* Retrieve device size stored in superblock to be prepared for shrink */
+		rdev->sectors = le64_to_cpu(sb->sectors);
 		rdev->recovery_offset = le64_to_cpu(sb->disk_recovery_offset);
-		if (rdev->recovery_offset != MaxSector)
-			clear_bit(In_sync, &rdev->flags);
+		if (rdev->recovery_offset == MaxSector)
+			set_bit(In_sync, &rdev->flags);
+		/*
+		 * If no reshape in progress -> we're recovering single
+		 * disk(s) and have to set the device(s) to out-of-sync
+		 */
+		else if (!rs_is_reshaping(rs))
+			clear_bit(In_sync, &rdev->flags); /* Mandatory for recovery */
 	}
 
 	/*
 	 * If a device comes back, set it as not In_sync and no longer faulty.
 	 */
-	if (test_bit(Faulty, &rdev->flags)) {
-		clear_bit(Faulty, &rdev->flags);
+	if (test_and_clear_bit(Faulty, &rdev->flags)) {
+		rdev->recovery_offset = 0;
 		clear_bit(In_sync, &rdev->flags);
 		rdev->saved_raid_disk = rdev->raid_disk;
-		rdev->recovery_offset = 0;
 	}
 
-	clear_bit(FirstUse, &rdev->flags);
+	/* Reshape support -> restore repective data offsets */
+	rdev->data_offset = le64_to_cpu(sb->data_offset);
+	rdev->new_data_offset = le64_to_cpu(sb->new_data_offset);
 
 	return 0;
 }
@@ -1072,7 +2302,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
  */
 static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 {
-	int ret;
+	int r;
 	struct raid_dev *dev;
 	struct md_rdev *rdev, *tmp, *freshest;
 	struct mddev *mddev = &rs->md;
@@ -1082,24 +2312,22 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 		/*
 		 * Skipping super_load due to CTR_FLAG_SYNC will cause
 		 * the array to undergo initialization again as
-		 * though it were new.  This is the intended effect
+		 * though it were new.	This is the intended effect
 		 * of the "sync" directive.
 		 *
 		 * When reshaping capability is added, we must ensure
 		 * that the "sync" directive is disallowed during the
 		 * reshape.
 		 */
-		rdev->sectors = to_sector(i_size_read(rdev->bdev->bd_inode));
-
-		if (rs->ctr_flags & CTR_FLAG_SYNC)
+		if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags))
 			continue;
 
 		if (!rdev->meta_bdev)
 			continue;
 
-		ret = super_load(rdev, freshest);
+		r = super_load(rdev, freshest);
 
-		switch (ret) {
+		switch (r) {
 		case 1:
 			freshest = rdev;
 			break;
@@ -1148,25 +2376,336 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 	 * Validation of the freshest device provides the source of
 	 * validation for the remaining devices.
 	 */
-	ti->error = "Unable to assemble array: Invalid superblocks";
+	rs->ti->error = "Unable to assemble array: Invalid superblocks";
 	if (super_validate(rs, freshest))
 		return -EINVAL;
 
 	rdev_for_each(rdev, mddev)
 		if ((rdev != freshest) && super_validate(rs, rdev))
 			return -EINVAL;
+	return 0;
+}
+
+/*
+ * Adjust data_offset and new_data_offset on all disk members of @rs
+ * for out of place reshaping if requested by contructor
+ *
+ * We need free space at the beginning of each raid disk for forward
+ * and at the end for backward reshapes which userspace has to provide
+ * via remapping/reordering of space.
+ */
+static int rs_adjust_data_offsets(struct raid_set *rs)
+{
+	sector_t data_offset = 0, new_data_offset = 0;
+	struct md_rdev *rdev;
+
+	/* Constructor did not request data offset change */
+	if (!test_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags)) {
+		if (!rs_is_reshapable(rs))
+			goto out;
+
+		return 0;
+	}
+
+	/* HM FIXME: get InSync raid_dev? */
+	rdev = &rs->dev[0].rdev;
+
+	if (rs->delta_disks < 0) {
+		/*
+		 * Removing disks (reshaping backwards):
+		 *
+		 * - before reshape: data is at offset 0 and free space
+		 *		     is at end of each component LV
+		 *
+		 * - after reshape: data is at offset rs->data_offset != 0 on each component LV
+		 */
+		data_offset = 0;
+		new_data_offset = rs->data_offset;
+
+	} else if (rs->delta_disks > 0) {
+		/*
+		 * Adding disks (reshaping forwards):
+		 *
+		 * - before reshape: data is at offset rs->data_offset != 0 and
+		 *		     free space is at begin of each component LV
+		 *
+		 * - after reshape: data is at offset 0 on each component LV
+		 */
+		data_offset = rs->data_offset;
+		new_data_offset = 0;
+
+	} else {
+		/*
+		 * User space passes in 0 for data offset after having removed reshape space
+		 *
+		 * - or - (data offset != 0)
+		 *
+		 * Changing RAID layout or chunk size -> toggle offsets
+		 *
+		 * - before reshape: data is at offset rs->data_offset 0 and
+		 *		     free space is at end of each component LV
+		 *		     -or-
+		 *                   data is at offset rs->data_offset != 0 and
+		 *		     free space is at begin of each component LV
+		 *
+		 * - after reshape: data is at offset 0 if it was at offset != 0
+		 *                  or at offset != 0 if it was at offset 0
+		 *                  on each component LV
+		 *
+		 */
+		data_offset = rs->data_offset ? rdev->data_offset : 0;
+		new_data_offset = data_offset ? 0 : rs->data_offset;
+		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+	}
+
+	/*
+	 * Make sure we got a minimum amount of free sectors per device
+	 */
+	if (rs->data_offset &&
+	    to_sector(i_size_read(rdev->bdev->bd_inode)) - rdev->sectors < MIN_FREE_RESHAPE_SPACE) {
+		rs->ti->error = data_offset ? "No space for forward reshape" :
+					      "No space for backward reshape";
+		return -ENOSPC;
+	}
+out:
+	/* Adjust data offsets on all rdevs */
+	rdev_for_each(rdev, &rs->md) {
+		rdev->data_offset = data_offset;
+		rdev->new_data_offset = new_data_offset;
+	}
+
+	return 0;
+}
+
+/* Userpace reordered disks -> adjust raid_disk indexes in @rs */
+static void __reorder_raid_disk_indexes(struct raid_set *rs)
+{
+	int i = 0;
+	struct md_rdev *rdev;
+
+	rdev_for_each(rdev, &rs->md) {
+		rdev->raid_disk = i++;
+		rdev->saved_raid_disk = rdev->new_raid_disk = -1;
+	}
+}
+
+/*
+ * Setup @rs for takeover by a different raid level
+ */
+static int rs_setup_takeover(struct raid_set *rs)
+{
+	struct mddev *mddev = &rs->md;
+	struct md_rdev *rdev;
+	unsigned int d = mddev->raid_disks = rs->raid_disks;
+	sector_t new_data_offset = rs->dev[0].rdev.data_offset ? 0 : rs->data_offset;
+
+	if (rt_is_raid10(rs->raid_type)) {
+		if (mddev->level == 0) {
+			/* Userpace reordered disks -> adjust raid_disk indexes */
+			__reorder_raid_disk_indexes(rs);
+
+			/* raid0 -> raid10_far layout */
+			mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_FAR,
+								   rs->raid10_copies);
+		} else if (mddev->level == 1)
+			/* raid1 -> raid10_near layout */
+			mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_NEAR,
+								   rs->raid_disks);
+		else
+			return -EINVAL;
+
+	}
+
+	clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
+	mddev->recovery_cp = MaxSector;
+
+	while (d--) {
+		rdev = &rs->dev[d].rdev;
+
+		if (test_bit(d, (void *) rs->rebuild_disks)) {
+			clear_bit(In_sync, &rdev->flags);
+			clear_bit(Faulty, &rdev->flags);
+			mddev->recovery_cp = rdev->recovery_offset = 0;
+			/* Bitmap has to be created when we do an "up" takeover */
+			set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
+		}
+
+		rdev->new_data_offset = new_data_offset;
+	}
+
+	return 0;
+}
+
+/* Prepare @rs for reshape */
+static int rs_prepare_reshape(struct raid_set *rs)
+{
+	bool reshape;
+	struct mddev *mddev = &rs->md;
+
+	if (rs_is_raid10(rs)) {
+		if (rs->raid_disks != mddev->raid_disks &&
+		    __is_raid10_near(mddev->layout) &&
+		    rs->raid10_copies &&
+		    rs->raid10_copies != __raid10_near_copies(mddev->layout)) {
+			/*
+			 * raid disk have to be multiple of data copies to allow this conversion,
+			 *
+			 * This is actually not a reshape it is a
+			 * rebuild of any additional mirrors per group
+			 */
+			if (rs->raid_disks % rs->raid10_copies) {
+				rs->ti->error = "Can't reshape raid10 mirror groups";
+				return -EINVAL;
+			}
+
+			/* Userpace reordered disks to add/remove mirrors -> adjust raid_disk indexes */
+			__reorder_raid_disk_indexes(rs);
+			mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_NEAR,
+								   rs->raid10_copies);
+			mddev->new_layout = mddev->layout;
+			reshape = false;
+		} else
+			reshape = true;
+
+	} else if (rs_is_raid456(rs))
+		reshape = true;
+
+	else if (rs_is_raid1(rs)) {
+		if (rs->delta_disks) {
+			/* Process raid1 via delta_disks */
+			mddev->degraded = rs->delta_disks < 0 ? -rs->delta_disks : rs->delta_disks;
+			reshape = true;
+		} else {
+			/* Process raid1 without delta_disks */
+			mddev->raid_disks = rs->raid_disks;
+			set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags);
+			reshape = false;
+		}
+	} else {
+		rs->ti->error = "Called with bogus raid type";
+		return -EINVAL;
+	}
+
+	if (reshape) {
+		set_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags);
+		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+		set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags);
+	} else if (mddev->raid_disks < rs->raid_disks)
+		/* Create new superblocks and bitmaps, if any new disks */
+		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
 
 	return 0;
 }
 
 /*
+ *
+ * - change raid layout
+ * - change chunk size
+ * - add disks
+ * - remove disks
+ */
+static int rs_setup_reshape(struct raid_set *rs)
+{
+	int r = 0;
+	unsigned int cur_raid_devs, d;
+	struct mddev *mddev = &rs->md;
+	struct md_rdev *rdev;
+
+	mddev->delta_disks = rs->delta_disks;
+	cur_raid_devs = mddev->raid_disks;
+
+	/* Ignore impossible layout change whilst adding/removing disks */
+	if (mddev->delta_disks &&
+	    mddev->layout != mddev->new_layout) {
+		DMINFO("Ignoring invalid layout change with delta_disks=%d", rs->delta_disks);
+		mddev->new_layout = mddev->layout;
+	}
+
+	/*
+	 * Adjust array size:
+	 *
+	 * - in case of adding disks, array size has
+	 *   to grow after the disk adding reshape,
+	 *   which'll hapen in the event handler;
+	 *   reshape will happen forward, so space has to
+	 *   be available at the beginning of each disk
+	 *
+	 * - in case of removing disks, array size
+	 *   has to shrink before starting the reshape,
+	 *   which'll happen here;
+	 *   reshape will happen backward, so space has to
+	 *   be available at the end of each disk
+	 *
+	 * - data_offset and new_data_offset are
+	 *   adjusted for aforementioned out of place
+	 *   reshaping based on userspace passing in
+	 *   the "data_offset <sectors>" key/value
+	 *   pair via the constructor
+	 */
+
+	/* Add disk(s) */
+	if (rs->delta_disks > 0) {
+		/* Prepare disks for check in raid4/5/6/10 {check|start}_reshape */
+		for (d = cur_raid_devs; d < rs->raid_disks; d++) {
+			rdev = &rs->dev[d].rdev;
+			clear_bit(In_sync, &rdev->flags);
+
+			/*
+			 * save_raid_disk needs to be -1, or recovery_offset will be set to 0
+			 * by md, which'll store that erroneously in the superblock on reshape
+			 */
+			rdev->saved_raid_disk = -1;
+			rdev->raid_disk = d;
+
+			rdev->sectors = mddev->dev_sectors;
+			rdev->recovery_offset = rs_is_raid1(rs) ? 0 : MaxSector;
+		}
+
+		mddev->reshape_backwards = 0; /* adding disks -> forward reshape */
+
+	/* Remove disk(s) */
+	} else if (rs->delta_disks < 0) {
+		r = rs_set_dev_and_array_sectors(rs, true);
+		mddev->reshape_backwards = 1; /* removing disk(s) -> backward reshape */
+
+	/* Change layout and/or chunk size */
+	} else {
+		/*
+		 * Reshape layout (e.g. raid5_ls -> raid5_n) and/or chunk size:
+		 *
+		 * keeping number of disks and do layout change ->
+		 *
+		 * toggle reshape_backward depending on data_offset:
+		 *
+		 * - free space upfront -> reshape forward
+		 *
+		 * - free space at the end -> reshape backward
+		 *
+		 *
+		 * This utilizes free reshape space avoiding the need
+		 * for userspace to move (parts of) LV segments in
+		 * case of layout/chunksize change  (for disk
+		 * adding/removing reshape space has to be at
+		 * the proper address (see above with delta_disks):
+		 *
+		 * add disk(s)   -> begin
+		 * remove disk(s)-> end
+		 */
+		mddev->reshape_backwards = rs->dev[0].rdev.data_offset ? 0 : 1;
+	}
+
+	return r;
+}
+
+/*
  * Enable/disable discard support on RAID set depending on
  * RAID level and discard properties of underlying RAID members.
  */
-static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
+static void configure_discard_support(struct raid_set *rs)
 {
 	int i;
 	bool raid456;
+	struct dm_target *ti = rs->ti;
 
 	/* Assume discards not supported until after checks below. */
 	ti->discards_supported = false;
@@ -1174,7 +2713,7 @@ static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
 	/* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
 	raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
 
-	for (i = 0; i < rs->md.raid_disks; i++) {
+	for (i = 0; i < rs->raid_disks; i++) {
 		struct request_queue *q;
 
 		if (!rs->dev[i].rdev.bdev)
@@ -1207,118 +2746,252 @@ static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
 }
 
 /*
- * Construct a RAID4/5/6 mapping:
+ * Construct a RAID0/1/10/4/5/6 mapping:
  * Args:
- *	<raid_type> <#raid_params> <raid_params>		\
- *	<#raid_devs> { <meta_dev1> <dev1> .. <meta_devN> <devN> }
+ *	<raid_type> <#raid_params> <raid_params>{0,}	\
+ *	<#raid_devs> [<meta_dev1> <dev1>]{1,}
  *
- * <raid_params> varies by <raid_type>.  See 'parse_raid_params' for
+ * <raid_params> varies by <raid_type>.	 See 'parse_raid_params' for
  * details on possible <raid_params>.
+ *
+ * Userspace is free to initialize the metadata devices, hence the superblocks to
+ * enforce recreation based on the passed in table parameters.
+ *
  */
-static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
+static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
-	int ret;
+	int r;
+	bool resize;
 	struct raid_type *rt;
-	unsigned long num_raid_params, num_raid_devs;
+	unsigned int num_raid_params, num_raid_devs;
+	sector_t calculated_dev_sectors;
 	struct raid_set *rs = NULL;
-
-	/* Must have at least <raid_type> <#raid_params> */
-	if (argc < 2) {
-		ti->error = "Too few arguments";
+	const char *arg;
+	struct rs_layout rs_layout;
+	struct dm_arg_set as = { argc, argv }, as_nrd;
+	struct dm_arg _args[] = {
+		{ 0, as.argc, "Cannot understand number of raid parameters" },
+		{ 1, 254, "Cannot understand number of raid devices parameters" }
+	};
+
+	/* Must have <raid_type> */
+	arg = dm_shift_arg(&as);
+	if (!arg) {
+		ti->error = "No arguments";
 		return -EINVAL;
 	}
 
-	/* raid type */
-	rt = get_raid_type(argv[0]);
+	rt = get_raid_type(arg);
 	if (!rt) {
 		ti->error = "Unrecognised raid_type";
 		return -EINVAL;
 	}
-	argc--;
-	argv++;
-
-	/* number of RAID parameters */
-	if (kstrtoul(argv[0], 10, &num_raid_params) < 0) {
-		ti->error = "Cannot understand number of RAID parameters";
-		return -EINVAL;
-	}
-	argc--;
-	argv++;
 
-	/* Skip over RAID params for now and find out # of devices */
-	if (num_raid_params >= argc) {
-		ti->error = "Arguments do not agree with counts given";
+	/* Must have <#raid_params> */
+	if (dm_read_arg_group(_args, &as, &num_raid_params, &ti->error))
 		return -EINVAL;
-	}
 
-	if ((kstrtoul(argv[num_raid_params], 10, &num_raid_devs) < 0) ||
-	    (num_raid_devs > MAX_RAID_DEVICES)) {
-		ti->error = "Cannot understand number of raid devices";
+	/* number of raid device tupples <meta_dev data_dev> */
+	as_nrd = as;
+	dm_consume_args(&as_nrd, num_raid_params);
+	_args[1].max = (as_nrd.argc - 1) / 2;
+	if (dm_read_arg(_args + 1, &as_nrd, &num_raid_devs, &ti->error))
 		return -EINVAL;
-	}
 
-	argc -= num_raid_params + 1; /* +1: we already have num_raid_devs */
-	if (argc != (num_raid_devs * 2)) {
-		ti->error = "Supplied RAID devices does not match the count given";
+	if (!__within_range(num_raid_devs, 1, MAX_RAID_DEVICES)) {
+		ti->error = "Invalid number of supplied raid devices";
 		return -EINVAL;
 	}
 
-	rs = context_alloc(ti, rt, (unsigned)num_raid_devs);
+	rs = raid_set_alloc(ti, rt, num_raid_devs);
 	if (IS_ERR(rs))
 		return PTR_ERR(rs);
 
-	ret = parse_raid_params(rs, argv, (unsigned)num_raid_params);
-	if (ret)
+	r = parse_raid_params(rs, &as, num_raid_params);
+	if (r)
 		goto bad;
 
-	argv += num_raid_params + 1;
-
-	ret = dev_parms(rs, argv);
-	if (ret)
+	r = parse_dev_params(rs, &as);
+	if (r)
 		goto bad;
 
 	rs->md.sync_super = super_sync;
-	ret = analyse_superblocks(ti, rs);
-	if (ret)
+
+	/*
+	 * Calculate ctr requested array and device sizes to allow
+	 * for superblock analysis needing device sizes defined.
+	 *
+	 * Any existing superblock will overwrite the array and device sizes
+	 */
+	r = rs_set_dev_and_array_sectors(rs, false);
+	if (r)
+		goto bad;
+
+	calculated_dev_sectors = rs->dev[0].rdev.sectors;
+
+	/*
+	 * Backup any new raid set level, layout, ...
+	 * requested to be able to compare to superblock
+	 * members for conversion decisions.
+	 */
+	rs_config_backup(rs, &rs_layout);
+
+	r = analyse_superblocks(ti, rs);
+	if (r)
 		goto bad;
 
+	resize = calculated_dev_sectors != rs->dev[0].rdev.sectors;
+
 	INIT_WORK(&rs->md.event_work, do_table_event);
 	ti->private = rs;
 	ti->num_flush_bios = 1;
 
+	/* Restore any requested new layout for conversion decision */
+	rs_config_restore(rs, &rs_layout);
+
 	/*
-	 * Disable/enable discard support on RAID set.
+	 * Now that we have any superblock metadata available,
+	 * check for new, recovering, reshaping, to be taken over,
+	 * to be reshaped or an existing, unchanged raid set to
+	 * run in sequence.
 	 */
-	configure_discard_support(ti, rs);
+	if (test_bit(MD_ARRAY_FIRST_USE, &rs->md.flags)) {
+		/* A new raid6 set has to be recovered to ensure proper parity and Q-Syndrome */
+		if (rs_is_raid6(rs) &&
+		    test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
+			ti->error = "'nosync' not allowed for new raid6 set";
+			r = -EINVAL;
+			goto bad;
+		}
+		rs_setup_recovery(rs, 0);
+		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+		rs_set_new(rs);
+	} else if (rs_is_recovering(rs)) {
+		/* A recovering raid set may be resized */
+		; /* skip setup rs */
+	} else if (rs_is_reshaping(rs)) {
+		/* Have to reject size change request during reshape */
+		if (resize) {
+			ti->error = "Can't resize a reshaping raid set";
+			r = -EPERM;
+			goto bad;
+		}
+		/* skip setup rs */
+	} else if (rs_takeover_requested(rs)) {
+		if (rs_is_reshaping(rs)) {
+			ti->error = "Can't takeover a reshaping raid set";
+			r = -EPERM;
+			goto bad;
+		}
+
+		/*
+		 * If a takeover is needed, userspace sets any additional
+		 * devices to rebuild and we can check for a valid request here.
+		 *
+		 * If acceptible, set the level to the new requested
+		 * one, prohibit requesting recovery, allow the raid
+		 * set to run and store superblocks during resume.
+		 */
+		r = rs_check_takeover(rs);
+		if (r)
+			goto bad;
+
+		r = rs_setup_takeover(rs);
+		if (r)
+			goto bad;
+
+		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+		set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags);
+		/* Takeover ain't recovery, so disable recovery */
+		rs_setup_recovery(rs, MaxSector);
+		rs_set_new(rs);
+	} else if (rs_reshape_requested(rs)) {
+		/*
+		  * We can only prepare for a reshape here, because the
+		  * raid set needs to run to provide the repective reshape
+		  * check functions via its MD personality instance.
+		  *
+		  * So do the reshape check after md_run() succeeded.
+		  */
+		r = rs_prepare_reshape(rs);
+		if (r)
+			return r;
+
+		/* Reshaping ain't recovery, so disable recovery */
+		rs_setup_recovery(rs, MaxSector);
+		rs_set_cur(rs);
+	} else {
+		/* May not set recovery when a device rebuild is requested */
+		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
+			rs_setup_recovery(rs, MaxSector);
+			set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+		} else
+			rs_setup_recovery(rs, test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ?
+					      0 : (resize ? calculated_dev_sectors : MaxSector));
+		rs_set_cur(rs);
+	}
+
+	/* If constructor requested it, change data and new_data offsets */
+	r = rs_adjust_data_offsets(rs);
+	if (r)
+		goto bad;
+
+	/* Start raid set read-only and assumed clean to change in raid_resume() */
+	rs->md.ro = 1;
+	rs->md.in_sync = 1;
+	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
 
 	/* Has to be held on running the array */
 	mddev_lock_nointr(&rs->md);
-	ret = md_run(&rs->md);
+	r = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
-	mddev_unlock(&rs->md);
 
-	if (ret) {
-		ti->error = "Fail to run raid array";
+	if (r) {
+		ti->error = "Failed to run raid array";
+		mddev_unlock(&rs->md);
 		goto bad;
 	}
 
-	if (ti->len != rs->md.array_sectors) {
-		ti->error = "Array size does not match requested target length";
-		ret = -EINVAL;
-		goto size_mismatch;
-	}
 	rs->callbacks.congested_fn = raid_is_congested;
 	dm_table_add_target_callbacks(ti->table, &rs->callbacks);
 
 	mddev_suspend(&rs->md);
+
+	/* Try to adjust the raid4/5/6 stripe cache size to the stripe size */
+	if (rs_is_raid456(rs)) {
+		r = rs_set_raid456_stripe_cache(rs);
+		if (r)
+			goto bad_stripe_cache;
+	}
+
+	/* Now do an early reshape check */
+	if (test_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags)) {
+		r = rs_check_reshape(rs);
+		if (r)
+			goto bad_check_reshape;
+
+		/* Restore new, ctr requested layout to perform check */
+		rs_config_restore(rs, &rs_layout);
+
+		if (rs->md.pers->start_reshape) {
+			r = rs->md.pers->check_reshape(&rs->md);
+			if (r) {
+				ti->error = "Reshape check failed";
+				goto bad_check_reshape;
+			}
+		}
+	}
+
+	mddev_unlock(&rs->md);
 	return 0;
 
-size_mismatch:
+bad_stripe_cache:
+bad_check_reshape:
 	md_stop(&rs->md);
 bad:
-	context_free(rs);
+	raid_set_free(rs);
 
-	return ret;
+	return r;
 }
 
 static void raid_dtr(struct dm_target *ti)
@@ -1327,7 +3000,7 @@ static void raid_dtr(struct dm_target *ti)
 
 	list_del_init(&rs->callbacks.list);
 	md_stop(&rs->md);
-	context_free(rs);
+	raid_set_free(rs);
 }
 
 static int raid_map(struct dm_target *ti, struct bio *bio)
@@ -1335,11 +3008,23 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
 
+	/*
+	 * If we're reshaping to add disk(s)), ti->len and
+	 * mddev->array_sectors will differ during the process
+	 * (ti->len > mddev->array_sectors), so we have to requeue
+	 * bios with addresses > mddev->array_sectors here or
+	 * there will occur accesses past EOD of the component
+	 * data images thus erroring the raid set.
+	 */
+	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
+		return DM_MAPIO_REQUEUE;
+
 	mddev->pers->make_request(mddev, bio);
 
 	return DM_MAPIO_SUBMITTED;
 }
 
+/* Return string describing the current sync action of @mddev */
 static const char *decipher_sync_action(struct mddev *mddev)
 {
 	if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
@@ -1365,195 +3050,260 @@ static const char *decipher_sync_action(struct mddev *mddev)
 	return "idle";
 }
 
-static void raid_status(struct dm_target *ti, status_type_t type,
-			unsigned status_flags, char *result, unsigned maxlen)
+/*
+ * Return status string @rdev
+ *
+ * Status characters:
+ *
+ *  'D' = Dead/Failed device
+ *  'a' = Alive but not in-sync
+ *  'A' = Alive and in-sync
+ */
+static const char *__raid_dev_status(struct md_rdev *rdev, bool array_in_sync)
 {
-	struct raid_set *rs = ti->private;
-	unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
-	unsigned sz = 0;
-	int i, array_in_sync = 0;
-	sector_t sync;
+	if (test_bit(Faulty, &rdev->flags))
+		return "D";
+	else if (!array_in_sync || !test_bit(In_sync, &rdev->flags))
+		return "a";
+	else
+		return "A";
+}
 
-	switch (type) {
-	case STATUSTYPE_INFO:
-		DMEMIT("%s %d ", rs->raid_type->name, rs->md.raid_disks);
+/* Helper to return resync/reshape progress for @rs and @array_in_sync */
+static sector_t rs_get_progress(struct raid_set *rs,
+				sector_t resync_max_sectors, bool *array_in_sync)
+{
+	sector_t r, recovery_cp, curr_resync_completed;
+	struct mddev *mddev = &rs->md;
 
-		if (rs->raid_type->level) {
-			if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery))
-				sync = rs->md.curr_resync_completed;
-			else
-				sync = rs->md.recovery_cp;
-
-			if (sync >= rs->md.resync_max_sectors) {
-				/*
-				 * Sync complete.
-				 */
-				array_in_sync = 1;
-				sync = rs->md.resync_max_sectors;
-			} else if (test_bit(MD_RECOVERY_REQUESTED, &rs->md.recovery)) {
-				/*
-				 * If "check" or "repair" is occurring, the array has
-				 * undergone and initial sync and the health characters
-				 * should not be 'a' anymore.
-				 */
-				array_in_sync = 1;
+	curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp;
+	recovery_cp = mddev->recovery_cp;
+	*array_in_sync = false;
+
+	if (rs_is_raid0(rs)) {
+		r = resync_max_sectors;
+		*array_in_sync = true;
+
+	} else {
+		r = mddev->reshape_position;
+
+		/* Reshape is relative to the array size */
+		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ||
+		    r != MaxSector) {
+			if (r == MaxSector) {
+				*array_in_sync = true;
+				r = resync_max_sectors;
 			} else {
-				/*
-				 * The array may be doing an initial sync, or it may
-				 * be rebuilding individual components.  If all the
-				 * devices are In_sync, then it is the array that is
-				 * being initialized.
-				 */
-				for (i = 0; i < rs->md.raid_disks; i++)
-					if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
-						array_in_sync = 1;
+				/* Got to reverse on backward reshape */
+				if (mddev->reshape_backwards)
+					r = mddev->array_sectors - r;
+
+				/* Devide by # of data stripes */
+				sector_div(r, mddev_data_stripes(rs));
 			}
+
+		/* Sync is relative to the component device size */
+		} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+			r = curr_resync_completed;
+		else
+			r = recovery_cp;
+
+		if (r == MaxSector) {
+			/*
+			 * Sync complete.
+			 */
+			*array_in_sync = true;
+			r = resync_max_sectors;
+		} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+			/*
+			 * If "check" or "repair" is occurring, the raid set has
+			 * undergone an initial sync and the health characters
+			 * should not be 'a' anymore.
+			 */
+			*array_in_sync = true;
 		} else {
-			/* RAID0 */
-			array_in_sync = 1;
-			sync = rs->md.resync_max_sectors;
-		}
+			struct md_rdev *rdev;
 
-		/*
-		 * Status characters:
-		 *  'D' = Dead/Failed device
-		 *  'a' = Alive but not in-sync
-		 *  'A' = Alive and in-sync
-		 */
-		for (i = 0; i < rs->md.raid_disks; i++) {
-			if (test_bit(Faulty, &rs->dev[i].rdev.flags))
-				DMEMIT("D");
-			else if (!array_in_sync ||
-				 !test_bit(In_sync, &rs->dev[i].rdev.flags))
-				DMEMIT("a");
-			else
-				DMEMIT("A");
+			/*
+			 * The raid set may be doing an initial sync, or it may
+			 * be rebuilding individual components.	 If all the
+			 * devices are In_sync, then it is the raid set that is
+			 * being initialized.
+			 */
+			rdev_for_each(rdev, mddev)
+				if (!test_bit(In_sync, &rdev->flags))
+					*array_in_sync = true;
+#if 0
+			r = 0; /* HM FIXME: TESTME: https://bugzilla.redhat.com/show_bug.cgi?id=1210637 ? */
+#endif
 		}
+	}
+
+	return r;
+}
+
+/* Helper to return @dev name or "-" if !@dev */
+static const char *__get_dev_name(struct dm_dev *dev)
+{
+	return dev ? dev->name : "-";
+}
+
+static void raid_status(struct dm_target *ti, status_type_t type,
+			unsigned int status_flags, char *result, unsigned int maxlen)
+{
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+	struct r5conf *conf = mddev->private;
+	int i, max_nr_stripes = conf ? conf->max_nr_stripes : 0;
+	bool array_in_sync;
+	unsigned int raid_param_cnt = 1; /* at least 1 for chunksize */
+	unsigned int sz = 0;
+	unsigned int rebuild_disks;
+	unsigned int write_mostly_params = 0;
+	sector_t progress, resync_max_sectors, resync_mismatches;
+	const char *sync_action;
+	struct raid_type *rt;
+	struct md_rdev *rdev;
+
+	switch (type) {
+	case STATUSTYPE_INFO:
+		/* *Should* always succeed */
+		rt = get_raid_type_by_ll(mddev->new_level, mddev->new_layout);
+		if (!rt)
+			return;
+
+		DMEMIT("%s %d ", rt->name, mddev->raid_disks);
+
+		/* Access most recent mddev properties for status output */
+		smp_rmb();
+		/* Get sensible max sectors even if raid set not yet started */
+		resync_max_sectors = test_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags) ?
+				      mddev->resync_max_sectors : mddev->dev_sectors;
+		progress = rs_get_progress(rs, resync_max_sectors, &array_in_sync);
+		resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
+				    atomic64_read(&mddev->resync_mismatches) : 0;
+		sync_action = decipher_sync_action(&rs->md);
+
+		/* HM FIXME: do we want another state char for raid0? It shows 'D' or 'A' now */
+		rdev_for_each(rdev, mddev)
+			DMEMIT(__raid_dev_status(rdev, array_in_sync));
 
 		/*
-		 * In-sync ratio:
+		 * In-sync/Reshape ratio:
 		 *  The in-sync ratio shows the progress of:
-		 *   - Initializing the array
-		 *   - Rebuilding a subset of devices of the array
+		 *   - Initializing the raid set
+		 *   - Rebuilding a subset of devices of the raid set
 		 *  The user can distinguish between the two by referring
 		 *  to the status characters.
+		 *
+		 *  The reshape ratio shows the progress of
+		 *  changing the raid layout or the number of
+		 *  disks of a raid set
 		 */
-		DMEMIT(" %llu/%llu",
-		       (unsigned long long) sync,
-		       (unsigned long long) rs->md.resync_max_sectors);
+		DMEMIT(" %llu/%llu", (unsigned long long) progress,
+				     (unsigned long long) resync_max_sectors);
 
 		/*
+		 * v1.5.0+:
+		 *
 		 * Sync action:
-		 *   See Documentation/device-mapper/dm-raid.c for
+		 *   See Documentation/device-mapper/dm-raid.txt for
 		 *   information on each of these states.
 		 */
-		DMEMIT(" %s", decipher_sync_action(&rs->md));
+		DMEMIT(" %s", sync_action);
 
 		/*
+		 * v1.5.0+:
+		 *
 		 * resync_mismatches/mismatch_cnt
 		 *   This field shows the number of discrepancies found when
-		 *   performing a "check" of the array.
+		 *   performing a "check" of the raid set.
 		 */
-		DMEMIT(" %llu",
-		       (strcmp(rs->md.last_sync_action, "check")) ? 0 :
-		       (unsigned long long)
-		       atomic64_read(&rs->md.resync_mismatches));
-		break;
-	case STATUSTYPE_TABLE:
-		/* The string you would use to construct this array */
-		for (i = 0; i < rs->md.raid_disks; i++) {
-			if ((rs->ctr_flags & CTR_FLAG_REBUILD) &&
-			    rs->dev[i].data_dev &&
-			    !test_bit(In_sync, &rs->dev[i].rdev.flags))
-				raid_param_cnt += 2; /* for rebuilds */
-			if (rs->dev[i].data_dev &&
-			    test_bit(WriteMostly, &rs->dev[i].rdev.flags))
-				raid_param_cnt += 2;
-		}
-
-		raid_param_cnt += (hweight32(rs->ctr_flags & ~CTR_FLAG_REBUILD) * 2);
-		if (rs->ctr_flags & (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC))
-			raid_param_cnt--;
-
-		DMEMIT("%s %u %u", rs->raid_type->name,
-		       raid_param_cnt, rs->md.chunk_sectors);
-
-		if ((rs->ctr_flags & CTR_FLAG_SYNC) &&
-		    (rs->md.recovery_cp == MaxSector))
-			DMEMIT(" sync");
-		if (rs->ctr_flags & CTR_FLAG_NOSYNC)
-			DMEMIT(" nosync");
-
-		for (i = 0; i < rs->md.raid_disks; i++)
-			if ((rs->ctr_flags & CTR_FLAG_REBUILD) &&
-			    rs->dev[i].data_dev &&
-			    !test_bit(In_sync, &rs->dev[i].rdev.flags))
-				DMEMIT(" rebuild %u", i);
-
-		if (rs->ctr_flags & CTR_FLAG_DAEMON_SLEEP)
-			DMEMIT(" daemon_sleep %lu",
-			       rs->md.bitmap_info.daemon_sleep);
-
-		if (rs->ctr_flags & CTR_FLAG_MIN_RECOVERY_RATE)
-			DMEMIT(" min_recovery_rate %d", rs->md.sync_speed_min);
-
-		if (rs->ctr_flags & CTR_FLAG_MAX_RECOVERY_RATE)
-			DMEMIT(" max_recovery_rate %d", rs->md.sync_speed_max);
-
-		for (i = 0; i < rs->md.raid_disks; i++)
-			if (rs->dev[i].data_dev &&
-			    test_bit(WriteMostly, &rs->dev[i].rdev.flags))
-				DMEMIT(" write_mostly %u", i);
-
-		if (rs->ctr_flags & CTR_FLAG_MAX_WRITE_BEHIND)
-			DMEMIT(" max_write_behind %lu",
-			       rs->md.bitmap_info.max_write_behind);
-
-		if (rs->ctr_flags & CTR_FLAG_STRIPE_CACHE) {
-			struct r5conf *conf = rs->md.private;
-
-			/* convert from kiB to sectors */
-			DMEMIT(" stripe_cache %d",
-			       conf ? conf->max_nr_stripes * 2 : 0);
-		}
-
-		if (rs->ctr_flags & CTR_FLAG_REGION_SIZE)
-			DMEMIT(" region_size %lu",
-			       rs->md.bitmap_info.chunksize >> 9);
-
-		if (rs->ctr_flags & CTR_FLAG_RAID10_COPIES)
-			DMEMIT(" raid10_copies %u",
-			       raid10_md_layout_to_copies(rs->md.layout));
-
-		if (rs->ctr_flags & CTR_FLAG_RAID10_FORMAT)
-			DMEMIT(" raid10_format %s",
-			       raid10_md_layout_to_format(rs->md.layout));
+		DMEMIT(" %llu", (unsigned long long) resync_mismatches);
 
-		DMEMIT(" %d", rs->md.raid_disks);
-		for (i = 0; i < rs->md.raid_disks; i++) {
-			if (rs->dev[i].meta_dev)
-				DMEMIT(" %s", rs->dev[i].meta_dev->name);
-			else
-				DMEMIT(" -");
+		/*
+		 * v1.9.0+:
+		 *
+		 * data_offset (needed for out of space reshaping)
+		 *   This field shows the data offset into the data
+		 *   image LV where the first stripes data starts.
+		 *
+		 * We keep data_offset equal on all raid disks of the set,
+		 * so retrieving it from the first raid disk is sufficient.
+		 */
+		DMEMIT(" %llu", (unsigned long long) rs->dev[0].rdev.data_offset);
+		break;
 
-			if (rs->dev[i].data_dev)
-				DMEMIT(" %s", rs->dev[i].data_dev->name);
-			else
-				DMEMIT(" -");
-		}
+	case STATUSTYPE_TABLE:
+		/* Report the table line string you would use to construct this raid set */
+
+		/* Calculate raid parameter count */
+		for (i = 0; i < rs->raid_disks; i++)
+			if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
+				write_mostly_params += 2;
+		rebuild_disks = memweight(rs->rebuild_disks, DISKS_ARRAY_ELEMS * sizeof(*rs->rebuild_disks));
+		raid_param_cnt += rebuild_disks * 2 +
+				  write_mostly_params +
+				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_NO_ARGS) +
+				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_ONE_ARG) * 2;
+		/* Emit table line */
+		DMEMIT("%s %u %u", rs->raid_type->name, raid_param_cnt, mddev->new_chunk_sectors);
+		if (test_bit(__CTR_FLAG_RAID10_FORMAT, &rs->ctr_flags))
+			DMEMIT(" %s %s", dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_FORMAT),
+					 raid10_md_layout_to_format(mddev->layout));
+		if (test_bit(__CTR_FLAG_RAID10_COPIES, &rs->ctr_flags))
+			DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_COPIES),
+					 raid10_md_layout_to_copies(mddev->layout));
+		if (test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))
+			DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC));
+		if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags))
+			DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_SYNC));
+		if (test_bit(__CTR_FLAG_REGION_SIZE, &rs->ctr_flags))
+			DMEMIT(" %s %llu", dm_raid_arg_name_by_flag(CTR_FLAG_REGION_SIZE),
+					   (unsigned long long) to_sector(mddev->bitmap_info.chunksize));
+		if (test_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags))
+			DMEMIT(" %s %llu", dm_raid_arg_name_by_flag(CTR_FLAG_DATA_OFFSET),
+					   (unsigned long long) rs->data_offset);
+		if (test_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags))
+			DMEMIT(" %s %lu", dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP),
+					  mddev->bitmap_info.daemon_sleep);
+		if (test_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags))
+			DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_DELTA_DISKS),
+					 max(rs->delta_disks, mddev->delta_disks));
+		if (test_bit(__CTR_FLAG_STRIPE_CACHE, &rs->ctr_flags))
+			DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_STRIPE_CACHE),
+					 max_nr_stripes);
+		if (rebuild_disks)
+			for (i = 0; i < rs->raid_disks; i++)
+				if (test_bit(rs->dev[i].rdev.raid_disk, (void *) rs->rebuild_disks))
+					DMEMIT(" %s %u", dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD),
+							 rs->dev[i].rdev.raid_disk);
+		if (write_mostly_params)
+			for (i = 0; i < rs->raid_disks; i++)
+				if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
+					DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY),
+					       rs->dev[i].rdev.raid_disk);
+		if (test_bit(__CTR_FLAG_MAX_WRITE_BEHIND, &rs->ctr_flags))
+			DMEMIT(" %s %lu", dm_raid_arg_name_by_flag(CTR_FLAG_MAX_WRITE_BEHIND),
+					  mddev->bitmap_info.max_write_behind);
+		if (test_bit(__CTR_FLAG_MAX_RECOVERY_RATE, &rs->ctr_flags))
+			DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE),
+					 mddev->sync_speed_max);
+		if (test_bit(__CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags))
+			DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_MIN_RECOVERY_RATE),
+					 mddev->sync_speed_min);
+		DMEMIT(" %d", rs->raid_disks);
+		for (i = 0; i < rs->raid_disks; i++)
+			DMEMIT(" %s %s", __get_dev_name(rs->dev[i].meta_dev),
+					 __get_dev_name(rs->dev[i].data_dev));
 	}
 }
 
-static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
+static int raid_message(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
 
-	if (!strcasecmp(argv[0], "reshape")) {
-		DMERR("Reshape not supported.");
-		return -EINVAL;
-	}
-
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
@@ -1571,11 +3321,10 @@ static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
 		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
 		return -EBUSY;
 	else if (!strcasecmp(argv[0], "resync"))
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	else if (!strcasecmp(argv[0], "recover")) {
+		; /* MD_RECOVERY_NEEDED set below */
+	else if (!strcasecmp(argv[0], "recover"))
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	} else {
+	else {
 		if (!strcasecmp(argv[0], "check"))
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		else if (!!strcasecmp(argv[0], "repair"))
@@ -1588,11 +3337,11 @@ static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
 		 * canceling read-auto mode
 		 */
 		mddev->ro = 0;
-		if (!mddev->suspended)
+		if (!mddev->suspended && mddev->sync_thread)
 			md_wakeup_thread(mddev->sync_thread);
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	if (!mddev->suspended)
+	if (!mddev->suspended && mddev->thread)
 		md_wakeup_thread(mddev->thread);
 
 	return 0;
@@ -1602,28 +3351,27 @@ static int raid_iterate_devices(struct dm_target *ti,
 				iterate_devices_callout_fn fn, void *data)
 {
 	struct raid_set *rs = ti->private;
-	unsigned i;
-	int ret = 0;
+	unsigned int i;
+	int r = 0;
 
-	for (i = 0; !ret && i < rs->md.raid_disks; i++)
+	for (i = 0; !r && i < rs->md.raid_disks; i++)
 		if (rs->dev[i].data_dev)
-			ret = fn(ti,
+			r = fn(ti,
 				 rs->dev[i].data_dev,
 				 0, /* No offset on data devs */
 				 rs->md.dev_sectors,
 				 data);
 
-	return ret;
+	return r;
 }
 
 static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct raid_set *rs = ti->private;
-	unsigned chunk_size = rs->md.chunk_sectors << 9;
-	struct r5conf *conf = rs->md.private;
+	unsigned int chunk_size = to_bytes(rs->md.chunk_sectors);
 
 	blk_limits_io_min(limits, chunk_size);
-	blk_limits_io_opt(limits, chunk_size * (conf->raid_disks - conf->max_degraded));
+	blk_limits_io_opt(limits, chunk_size * mddev_data_stripes(rs));
 }
 
 static void raid_presuspend(struct dm_target *ti)
@@ -1637,7 +3385,11 @@ static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
-	mddev_suspend(&rs->md);
+	if (test_and_clear_bit(RT_FLAG_RS_RESUMED, &rs->runtime_flags)) {
+		if (!rs->md.suspended)
+			mddev_suspend(&rs->md);
+		rs->md.ro = 1;
+	}
 }
 
 static void attempt_restore_of_faulty_devices(struct raid_set *rs)
@@ -1651,7 +3403,8 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs)
 	for (i = 0; i < rs->md.raid_disks; i++) {
 		r = &rs->dev[i].rdev;
 		if (test_bit(Faulty, &r->flags) && r->sb_page &&
-		    sync_page_io(r, 0, r->sb_size, r->sb_page, READ, 1)) {
+		    sync_page_io(r, 0, r->sb_size, r->sb_page,
+				 REQ_OP_READ, 0, true)) {
 			DMINFO("Faulty %s device #%d has readable super block."
 			       "  Attempting to revive it.",
 			       rs->raid_type->name, i);
@@ -1660,7 +3413,7 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs)
 			 * Faulty bit may be set, but sometimes the array can
 			 * be suspended before the personalities can respond
 			 * by removing the device from the array (i.e. calling
-			 * 'hot_remove_disk').  If they haven't yet removed
+			 * 'hot_remove_disk').	If they haven't yet removed
 			 * the failed device, its 'raid_disk' number will be
 			 * '>= 0' - meaning we must call this function
 			 * ourselves.
@@ -1696,34 +3449,192 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs)
 	}
 }
 
-static void raid_resume(struct dm_target *ti)
+static int __load_dirty_region_bitmap(struct raid_set *rs)
 {
-	struct raid_set *rs = ti->private;
+	int r = 0;
+
+	/* Try loading the bitmap unless "raid0", which does not have one */
+	if (!rs_is_raid0(rs) &&
+	    !test_and_set_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags)) {
+		r = bitmap_load(&rs->md);
+		if (r)
+			DMERR("Failed to load bitmap");
+	}
 
-	if (rs->raid_type->level) {
-		set_bit(MD_CHANGE_DEVS, &rs->md.flags);
+	return r;
+}
 
-		if (!rs->bitmap_loaded) {
-			bitmap_load(&rs->md);
-			rs->bitmap_loaded = 1;
-		} else {
-			/*
-			 * A secondary resume while the device is active.
-			 * Take this opportunity to check whether any failed
-			 * devices are reachable again.
-			 */
-			attempt_restore_of_faulty_devices(rs);
+/* Enforce updating all superblocks */
+static void rs_update_sbs(struct raid_set *rs)
+{
+	struct mddev *mddev = &rs->md;
+	int ro = mddev->ro;
+
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	mddev->ro = 0;
+	md_update_sb(mddev, 1);
+	mddev->ro = ro;
+}
+
+/*
+ * Reshape changes raid algorithm of @rs to new one within personality
+ * (e.g. raid6_zr -> raid6_nc), changes stripe size, adds/removes
+ * disks from a raid set thus growing/shrinking it or resizes the set
+ *
+ * Call mddev_lock_nointr() before!
+ */
+static int rs_start_reshape(struct raid_set *rs)
+{
+	int r;
+	struct mddev *mddev = &rs->md;
+	struct md_personality *pers = mddev->pers;
+
+	r = rs_setup_reshape(rs);
+	if (r)
+		return r;
+
+	/* Need to be resumed to be able to start reshape, recovery is frozen until raid_resume() though */
+	if (mddev->suspended)
+		mddev_resume(mddev);
+
+	/*
+	 * Check any reshape constraints enforced by the personalility
+	 *
+	 * May as well already kick the reshape off so that * pers->start_reshape() becomes optional.
+	 */
+	r = pers->check_reshape(mddev);
+	if (r) {
+		rs->ti->error = "pers->check_reshape() failed";
+		return r;
+	}
+
+	/*
+	 * Personality may not provide start reshape method in which
+	 * case check_reshape above has already covered everything
+	 */
+	if (pers->start_reshape) {
+		r = pers->start_reshape(mddev);
+		if (r) {
+			rs->ti->error = "pers->start_reshape() failed";
+			return r;
 		}
+	}
+
+	/* Suspend because a resume will happen in raid_resume() */
+	if (!mddev->suspended)
+		mddev_suspend(mddev);
+
+	/*
+	 * Now reshape got set up, update superblocks to
+	 * reflect the fact so that a table reload will
+	 * access proper superblock content in the ctr.
+	 */
+	rs_update_sbs(rs);
+
+	return 0;
+}
+
+static int raid_preresume(struct dm_target *ti)
+{
+	int r;
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+
+	/* This is a resume after a suspend of the set -> it's already started */
+	if (test_and_set_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags))
+		return 0;
+
+	/*
+	 * The superblocks need to be updated on disk if the
+	 * array is new or new devices got added (thus zeroed
+	 * out by userspace) or __load_dirty_region_bitmap
+	 * will overwrite them in core with old data or fail.
+	 */
+	if (test_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags))
+		rs_update_sbs(rs);
 
-		clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
+	/*
+	 * Disable/enable discard support on raid set after any
+	 * conversion, because devices can have been added
+	 */
+	configure_discard_support(rs);
+
+	/* Load the bitmap from disk unless raid0 */
+	r = __load_dirty_region_bitmap(rs);
+	if (r)
+		return r;
+
+	/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
+	if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) &&
+	    mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
+		r = bitmap_resize(mddev->bitmap, mddev->dev_sectors,
+				  to_bytes(rs->requested_bitmap_chunk_sectors), 0);
+		if (r)
+			DMERR("Failed to resize bitmap");
+	}
+
+	/* Check for any resize/reshape on @rs and adjust/initiate */
+	/* Be prepared for mddev_resume() in raid_resume() */
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
+		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		mddev->resync_min = mddev->recovery_cp;
 	}
 
-	mddev_resume(&rs->md);
+	rs_set_capacity(rs);
+
+	/* Check for any reshape request unless new raid set */
+	if (test_and_clear_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags)) {
+		/* Initiate a reshape. */
+		mddev_lock_nointr(mddev);
+		r = rs_start_reshape(rs);
+		mddev_unlock(mddev);
+		if (r)
+			DMWARN("Failed to check/start reshape, continuing without change");
+		r = 0;
+	}
+
+	return r;
+}
+
+static void raid_resume(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+
+	if (test_and_set_bit(RT_FLAG_RS_RESUMED, &rs->runtime_flags)) {
+		/*
+		 * A secondary resume while the device is active.
+		 * Take this opportunity to check whether any failed
+		 * devices are reachable again.
+		 */
+		attempt_restore_of_faulty_devices(rs);
+	} else {
+		mddev->ro = 0;
+		mddev->in_sync = 0;
+
+		/*
+		 * When passing in flags to the ctr, we expect userspace
+		 * to reset them because they made it to the superblocks
+		 * and reload the mapping anyway.
+		 *
+		 * -> only unfreeze recovery in case of a table reload or
+		 *    we'll have a bogus recovery/reshape position
+		 *    retrieved from the superblock by the ctr because
+		 *    the ongoing recovery/reshape will change it after read.
+		 */
+		if (!test_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags))
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+		if (mddev->suspended)
+			mddev_resume(mddev);
+	}
 }
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 8, 0},
+	.version = {1, 9, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
@@ -1734,6 +3645,7 @@ static struct target_type raid_target = {
 	.io_hints = raid_io_hints,
 	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
+	.preresume = raid_preresume,
 	.resume = raid_resume,
 };
 
@@ -1758,11 +3670,13 @@ module_param(devices_handle_discard_safely, bool, 0644);
 MODULE_PARM_DESC(devices_handle_discard_safely,
 		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
 
-MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
+MODULE_DESCRIPTION(DM_NAME " raid0/1/10/4/5/6 target");
+MODULE_ALIAS("dm-raid0");
 MODULE_ALIAS("dm-raid1");
 MODULE_ALIAS("dm-raid10");
 MODULE_ALIAS("dm-raid4");
 MODULE_ALIAS("dm-raid5");
 MODULE_ALIAS("dm-raid6");
 MODULE_AUTHOR("Neil Brown <dm-devel@redhat.com>");
+MODULE_AUTHOR("Heinz Mauelshagen <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index b3ccf1e0d4f2..dac55b254a09 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -260,7 +260,8 @@ static int mirror_flush(struct dm_target *ti)
 	struct dm_io_region io[ms->nr_mirrors];
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE_FLUSH,
+		.bi_op = REQ_OP_WRITE,
+		.bi_op_flags = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = ms->io_client,
@@ -527,7 +528,7 @@ static void read_callback(unsigned long error, void *context)
 		DMWARN_LIMIT("Read failure on mirror device %s.  "
 			     "Trying alternative device.",
 			     m->dev->name);
-		queue_bio(m->ms, bio, bio_rw(bio));
+		queue_bio(m->ms, bio, bio_data_dir(bio));
 		return;
 	}
 
@@ -541,7 +542,8 @@ static void read_async_bio(struct mirror *m, struct bio *bio)
 {
 	struct dm_io_region io;
 	struct dm_io_request io_req = {
-		.bi_rw = READ,
+		.bi_op = REQ_OP_READ,
+		.bi_op_flags = 0,
 		.mem.type = DM_IO_BIO,
 		.mem.ptr.bio = bio,
 		.notify.fn = read_callback,
@@ -624,7 +626,7 @@ static void write_callback(unsigned long error, void *context)
 	 * If the bio is discard, return an error, but do not
 	 * degrade the array.
 	 */
-	if (bio->bi_rw & REQ_DISCARD) {
+	if (bio_op(bio) == REQ_OP_DISCARD) {
 		bio->bi_error = -EOPNOTSUPP;
 		bio_endio(bio);
 		return;
@@ -654,7 +656,8 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	struct dm_io_region io[ms->nr_mirrors], *dest = io;
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
+		.bi_op = REQ_OP_WRITE,
+		.bi_op_flags = bio->bi_rw & WRITE_FLUSH_FUA,
 		.mem.type = DM_IO_BIO,
 		.mem.ptr.bio = bio,
 		.notify.fn = write_callback,
@@ -662,8 +665,8 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 		.client = ms->io_client,
 	};
 
-	if (bio->bi_rw & REQ_DISCARD) {
-		io_req.bi_rw |= REQ_DISCARD;
+	if (bio_op(bio) == REQ_OP_DISCARD) {
+		io_req.bi_op = REQ_OP_DISCARD;
 		io_req.mem.type = DM_IO_KMEM;
 		io_req.mem.ptr.addr = NULL;
 	}
@@ -701,8 +704,8 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		if ((bio->bi_rw & REQ_FLUSH) ||
-		    (bio->bi_rw & REQ_DISCARD)) {
+		if ((bio->bi_rw & REQ_PREFLUSH) ||
+		    (bio_op(bio) == REQ_OP_DISCARD)) {
 			bio_list_add(&sync, bio);
 			continue;
 		}
@@ -1190,7 +1193,7 @@ static void mirror_dtr(struct dm_target *ti)
  */
 static int mirror_map(struct dm_target *ti, struct bio *bio)
 {
-	int r, rw = bio_rw(bio);
+	int r, rw = bio_data_dir(bio);
 	struct mirror *m;
 	struct mirror_set *ms = ti->private;
 	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
@@ -1214,7 +1217,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
 	 * If region is not in-sync queue the bio.
 	 */
 	if (!r || (r == -EWOULDBLOCK)) {
-		if (rw == READA)
+		if (bio->bi_rw & REQ_RAHEAD)
 			return -EWOULDBLOCK;
 
 		queue_bio(ms, bio, rw);
@@ -1239,7 +1242,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
 
 static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 {
-	int rw = bio_rw(bio);
+	int rw = bio_data_dir(bio);
 	struct mirror_set *ms = (struct mirror_set *) ti->private;
 	struct mirror *m = NULL;
 	struct dm_bio_details *bd = NULL;
@@ -1250,7 +1253,8 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)))
+		if (!(bio->bi_rw & REQ_PREFLUSH) &&
+		    bio_op(bio) != REQ_OP_DISCARD)
 			dm_rh_dec(ms->rh, bio_record->write_region);
 		return error;
 	}
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 74cb7b991d41..b11813431f31 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -398,12 +398,12 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
 	region_t region = dm_rh_bio_to_region(rh, bio);
 	int recovering = 0;
 
-	if (bio->bi_rw & REQ_FLUSH) {
+	if (bio->bi_rw & REQ_PREFLUSH) {
 		rh->flush_failure = 1;
 		return;
 	}
 
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		return;
 
 	/* We must inform the log that the sync count has changed. */
@@ -526,7 +526,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
 	struct bio *bio;
 
 	for (bio = bios->head; bio; bio = bio->bi_next) {
-		if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))
+		if (bio->bi_rw & REQ_PREFLUSH || bio_op(bio) == REQ_OP_DISCARD)
 			continue;
 		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
 	}
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
new file mode 100644
index 000000000000..7a9661868496
--- /dev/null
+++ b/drivers/md/dm-rq.c
@@ -0,0 +1,970 @@
+/*
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-core.h"
+#include "dm-rq.h"
+
+#include <linux/elevator.h> /* for rq_end_sector() */
+#include <linux/blk-mq.h>
+
+#define DM_MSG_PREFIX "core-rq"
+
+#define DM_MQ_NR_HW_QUEUES 1
+#define DM_MQ_QUEUE_DEPTH 2048
+static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
+static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
+
+/*
+ * Request-based DM's mempools' reserved IOs set by the user.
+ */
+#define RESERVED_REQUEST_BASED_IOS	256
+static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
+
+#ifdef CONFIG_DM_MQ_DEFAULT
+static bool use_blk_mq = true;
+#else
+static bool use_blk_mq = false;
+#endif
+
+bool dm_use_blk_mq_default(void)
+{
+	return use_blk_mq;
+}
+
+bool dm_use_blk_mq(struct mapped_device *md)
+{
+	return md->use_blk_mq;
+}
+EXPORT_SYMBOL_GPL(dm_use_blk_mq);
+
+unsigned dm_get_reserved_rq_based_ios(void)
+{
+	return __dm_get_module_param(&reserved_rq_based_ios,
+				     RESERVED_REQUEST_BASED_IOS, DM_RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
+
+static unsigned dm_get_blk_mq_nr_hw_queues(void)
+{
+	return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
+}
+
+static unsigned dm_get_blk_mq_queue_depth(void)
+{
+	return __dm_get_module_param(&dm_mq_queue_depth,
+				     DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
+}
+
+int dm_request_based(struct mapped_device *md)
+{
+	return blk_queue_stackable(md->queue);
+}
+
+static void dm_old_start_queue(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (blk_queue_stopped(q))
+		blk_start_queue(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+void dm_start_queue(struct request_queue *q)
+{
+	if (!q->mq_ops)
+		dm_old_start_queue(q);
+	else {
+		blk_mq_start_stopped_hw_queues(q, true);
+		blk_mq_kick_requeue_list(q);
+	}
+}
+
+static void dm_old_stop_queue(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (blk_queue_stopped(q)) {
+		spin_unlock_irqrestore(q->queue_lock, flags);
+		return;
+	}
+
+	blk_stop_queue(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+void dm_stop_queue(struct request_queue *q)
+{
+	if (!q->mq_ops)
+		dm_old_stop_queue(q);
+	else
+		blk_mq_stop_hw_queues(q);
+}
+
+static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
+						gfp_t gfp_mask)
+{
+	return mempool_alloc(md->io_pool, gfp_mask);
+}
+
+static void free_old_rq_tio(struct dm_rq_target_io *tio)
+{
+	mempool_free(tio, tio->md->io_pool);
+}
+
+static struct request *alloc_old_clone_request(struct mapped_device *md,
+					       gfp_t gfp_mask)
+{
+	return mempool_alloc(md->rq_pool, gfp_mask);
+}
+
+static void free_old_clone_request(struct mapped_device *md, struct request *rq)
+{
+	mempool_free(rq, md->rq_pool);
+}
+
+/*
+ * Partial completion handling for request-based dm
+ */
+static void end_clone_bio(struct bio *clone)
+{
+	struct dm_rq_clone_bio_info *info =
+		container_of(clone, struct dm_rq_clone_bio_info, clone);
+	struct dm_rq_target_io *tio = info->tio;
+	struct bio *bio = info->orig;
+	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
+	int error = clone->bi_error;
+
+	bio_put(clone);
+
+	if (tio->error)
+		/*
+		 * An error has already been detected on the request.
+		 * Once error occurred, just let clone->end_io() handle
+		 * the remainder.
+		 */
+		return;
+	else if (error) {
+		/*
+		 * Don't notice the error to the upper layer yet.
+		 * The error handling decision is made by the target driver,
+		 * when the request is completed.
+		 */
+		tio->error = error;
+		return;
+	}
+
+	/*
+	 * I/O for the bio successfully completed.
+	 * Notice the data completion to the upper layer.
+	 */
+
+	/*
+	 * bios are processed from the head of the list.
+	 * So the completing bio should always be rq->bio.
+	 * If it's not, something wrong is happening.
+	 */
+	if (tio->orig->bio != bio)
+		DMERR("bio completion is going in the middle of the request");
+
+	/*
+	 * Update the original request.
+	 * Do not use blk_end_request() here, because it may complete
+	 * the original request before the clone, and break the ordering.
+	 */
+	blk_update_request(tio->orig, 0, nr_bytes);
+}
+
+static struct dm_rq_target_io *tio_from_request(struct request *rq)
+{
+	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
+}
+
+static void rq_end_stats(struct mapped_device *md, struct request *orig)
+{
+	if (unlikely(dm_stats_used(&md->stats))) {
+		struct dm_rq_target_io *tio = tio_from_request(orig);
+		tio->duration_jiffies = jiffies - tio->duration_jiffies;
+		dm_stats_account_io(&md->stats, rq_data_dir(orig),
+				    blk_rq_pos(orig), tio->n_sectors, true,
+				    tio->duration_jiffies, &tio->stats_aux);
+	}
+}
+
+/*
+ * Don't touch any member of the md after calling this function because
+ * the md may be freed in dm_put() at the end of this function.
+ * Or do dm_get() before calling this function and dm_put() later.
+ */
+static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
+{
+	atomic_dec(&md->pending[rw]);
+
+	/* nudge anyone waiting on suspend queue */
+	if (!md_in_flight(md))
+		wake_up(&md->wait);
+
+	/*
+	 * Run this off this callpath, as drivers could invoke end_io while
+	 * inside their request_fn (and holding the queue lock). Calling
+	 * back into ->request_fn() could deadlock attempting to grab the
+	 * queue lock again.
+	 */
+	if (!md->queue->mq_ops && run_queue)
+		blk_run_queue_async(md->queue);
+
+	/*
+	 * dm_put() must be at the end of this function. See the comment above
+	 */
+	dm_put(md);
+}
+
+static void free_rq_clone(struct request *clone)
+{
+	struct dm_rq_target_io *tio = clone->end_io_data;
+	struct mapped_device *md = tio->md;
+
+	blk_rq_unprep_clone(clone);
+
+	/*
+	 * It is possible for a clone_old_rq() allocated clone to
+	 * get passed in -- it may not yet have a request_queue.
+	 * This is known to occur if the error target replaces
+	 * a multipath target that has a request_fn queue stacked
+	 * on blk-mq queue(s).
+	 */
+	if (clone->q && clone->q->mq_ops)
+		/* stacked on blk-mq queue(s) */
+		tio->ti->type->release_clone_rq(clone);
+	else if (!md->queue->mq_ops)
+		/* request_fn queue stacked on request_fn queue(s) */
+		free_old_clone_request(md, clone);
+
+	if (!md->queue->mq_ops)
+		free_old_rq_tio(tio);
+}
+
+/*
+ * Complete the clone and the original request.
+ * Must be called without clone's queue lock held,
+ * see end_clone_request() for more details.
+ */
+static void dm_end_request(struct request *clone, int error)
+{
+	int rw = rq_data_dir(clone);
+	struct dm_rq_target_io *tio = clone->end_io_data;
+	struct mapped_device *md = tio->md;
+	struct request *rq = tio->orig;
+
+	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
+		rq->errors = clone->errors;
+		rq->resid_len = clone->resid_len;
+
+		if (rq->sense)
+			/*
+			 * We are using the sense buffer of the original
+			 * request.
+			 * So setting the length of the sense data is enough.
+			 */
+			rq->sense_len = clone->sense_len;
+	}
+
+	free_rq_clone(clone);
+	rq_end_stats(md, rq);
+	if (!rq->q->mq_ops)
+		blk_end_request_all(rq, error);
+	else
+		blk_mq_end_request(rq, error);
+	rq_completed(md, rw, true);
+}
+
+static void dm_unprep_request(struct request *rq)
+{
+	struct dm_rq_target_io *tio = tio_from_request(rq);
+	struct request *clone = tio->clone;
+
+	if (!rq->q->mq_ops) {
+		rq->special = NULL;
+		rq->cmd_flags &= ~REQ_DONTPREP;
+	}
+
+	if (clone)
+		free_rq_clone(clone);
+	else if (!tio->md->queue->mq_ops)
+		free_old_rq_tio(tio);
+}
+
+/*
+ * Requeue the original request of a clone.
+ */
+static void dm_old_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_requeue_request(q, rq);
+	blk_run_queue_async(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void dm_mq_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	unsigned long flags;
+
+	blk_mq_requeue_request(rq);
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (!blk_queue_stopped(q))
+		blk_mq_kick_requeue_list(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void dm_requeue_original_request(struct mapped_device *md,
+					struct request *rq)
+{
+	int rw = rq_data_dir(rq);
+
+	rq_end_stats(md, rq);
+	dm_unprep_request(rq);
+
+	if (!rq->q->mq_ops)
+		dm_old_requeue_request(rq);
+	else
+		dm_mq_requeue_request(rq);
+
+	rq_completed(md, rw, false);
+}
+
+static void dm_done(struct request *clone, int error, bool mapped)
+{
+	int r = error;
+	struct dm_rq_target_io *tio = clone->end_io_data;
+	dm_request_endio_fn rq_end_io = NULL;
+
+	if (tio->ti) {
+		rq_end_io = tio->ti->type->rq_end_io;
+
+		if (mapped && rq_end_io)
+			r = rq_end_io(tio->ti, clone, error, &tio->info);
+	}
+
+	if (unlikely(r == -EREMOTEIO && (req_op(clone) == REQ_OP_WRITE_SAME) &&
+		     !clone->q->limits.max_write_same_sectors))
+		disable_write_same(tio->md);
+
+	if (r <= 0)
+		/* The target wants to complete the I/O */
+		dm_end_request(clone, r);
+	else if (r == DM_ENDIO_INCOMPLETE)
+		/* The target will handle the I/O */
+		return;
+	else if (r == DM_ENDIO_REQUEUE)
+		/* The target wants to requeue the I/O */
+		dm_requeue_original_request(tio->md, tio->orig);
+	else {
+		DMWARN("unimplemented target endio return value: %d", r);
+		BUG();
+	}
+}
+
+/*
+ * Request completion handler for request-based dm
+ */
+static void dm_softirq_done(struct request *rq)
+{
+	bool mapped = true;
+	struct dm_rq_target_io *tio = tio_from_request(rq);
+	struct request *clone = tio->clone;
+	int rw;
+
+	if (!clone) {
+		rq_end_stats(tio->md, rq);
+		rw = rq_data_dir(rq);
+		if (!rq->q->mq_ops) {
+			blk_end_request_all(rq, tio->error);
+			rq_completed(tio->md, rw, false);
+			free_old_rq_tio(tio);
+		} else {
+			blk_mq_end_request(rq, tio->error);
+			rq_completed(tio->md, rw, false);
+		}
+		return;
+	}
+
+	if (rq->cmd_flags & REQ_FAILED)
+		mapped = false;
+
+	dm_done(clone, tio->error, mapped);
+}
+
+/*
+ * Complete the clone and the original request with the error status
+ * through softirq context.
+ */
+static void dm_complete_request(struct request *rq, int error)
+{
+	struct dm_rq_target_io *tio = tio_from_request(rq);
+
+	tio->error = error;
+	if (!rq->q->mq_ops)
+		blk_complete_request(rq);
+	else
+		blk_mq_complete_request(rq, error);
+}
+
+/*
+ * Complete the not-mapped clone and the original request with the error status
+ * through softirq context.
+ * Target's rq_end_io() function isn't called.
+ * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
+ */
+static void dm_kill_unmapped_request(struct request *rq, int error)
+{
+	rq->cmd_flags |= REQ_FAILED;
+	dm_complete_request(rq, error);
+}
+
+/*
+ * Called with the clone's queue lock held (in the case of .request_fn)
+ */
+static void end_clone_request(struct request *clone, int error)
+{
+	struct dm_rq_target_io *tio = clone->end_io_data;
+
+	if (!clone->q->mq_ops) {
+		/*
+		 * For just cleaning up the information of the queue in which
+		 * the clone was dispatched.
+		 * The clone is *NOT* freed actually here because it is alloced
+		 * from dm own mempool (REQ_ALLOCED isn't set).
+		 */
+		__blk_put_request(clone->q, clone);
+	}
+
+	/*
+	 * Actual request completion is done in a softirq context which doesn't
+	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
+	 *     - another request may be submitted by the upper level driver
+	 *       of the stacking during the completion
+	 *     - the submission which requires queue lock may be done
+	 *       against this clone's queue
+	 */
+	dm_complete_request(tio->orig, error);
+}
+
+static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
+{
+	int r;
+
+	if (blk_queue_io_stat(clone->q))
+		clone->cmd_flags |= REQ_IO_STAT;
+
+	clone->start_time = jiffies;
+	r = blk_insert_cloned_request(clone->q, clone);
+	if (r)
+		/* must complete clone in terms of original request */
+		dm_complete_request(rq, r);
+}
+
+static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
+				 void *data)
+{
+	struct dm_rq_target_io *tio = data;
+	struct dm_rq_clone_bio_info *info =
+		container_of(bio, struct dm_rq_clone_bio_info, clone);
+
+	info->orig = bio_orig;
+	info->tio = tio;
+	bio->bi_end_io = end_clone_bio;
+
+	return 0;
+}
+
+static int setup_clone(struct request *clone, struct request *rq,
+		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
+{
+	int r;
+
+	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
+			      dm_rq_bio_constructor, tio);
+	if (r)
+		return r;
+
+	clone->cmd = rq->cmd;
+	clone->cmd_len = rq->cmd_len;
+	clone->sense = rq->sense;
+	clone->end_io = end_clone_request;
+	clone->end_io_data = tio;
+
+	tio->clone = clone;
+
+	return 0;
+}
+
+static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
+				    struct dm_rq_target_io *tio, gfp_t gfp_mask)
+{
+	/*
+	 * Create clone for use with .request_fn request_queue
+	 */
+	struct request *clone;
+
+	clone = alloc_old_clone_request(md, gfp_mask);
+	if (!clone)
+		return NULL;
+
+	blk_rq_init(NULL, clone);
+	if (setup_clone(clone, rq, tio, gfp_mask)) {
+		/* -ENOMEM */
+		free_old_clone_request(md, clone);
+		return NULL;
+	}
+
+	return clone;
+}
+
+static void map_tio_request(struct kthread_work *work);
+
+static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
+		     struct mapped_device *md)
+{
+	tio->md = md;
+	tio->ti = NULL;
+	tio->clone = NULL;
+	tio->orig = rq;
+	tio->error = 0;
+	/*
+	 * Avoid initializing info for blk-mq; it passes
+	 * target-specific data through info.ptr
+	 * (see: dm_mq_init_request)
+	 */
+	if (!md->init_tio_pdu)
+		memset(&tio->info, 0, sizeof(tio->info));
+	if (md->kworker_task)
+		init_kthread_work(&tio->work, map_tio_request);
+}
+
+static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
+					       struct mapped_device *md,
+					       gfp_t gfp_mask)
+{
+	struct dm_rq_target_io *tio;
+	int srcu_idx;
+	struct dm_table *table;
+
+	tio = alloc_old_rq_tio(md, gfp_mask);
+	if (!tio)
+		return NULL;
+
+	init_tio(tio, rq, md);
+
+	table = dm_get_live_table(md, &srcu_idx);
+	/*
+	 * Must clone a request if this .request_fn DM device
+	 * is stacked on .request_fn device(s).
+	 */
+	if (!dm_table_all_blk_mq_devices(table)) {
+		if (!clone_old_rq(rq, md, tio, gfp_mask)) {
+			dm_put_live_table(md, srcu_idx);
+			free_old_rq_tio(tio);
+			return NULL;
+		}
+	}
+	dm_put_live_table(md, srcu_idx);
+
+	return tio;
+}
+
+/*
+ * Called with the queue lock held.
+ */
+static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
+{
+	struct mapped_device *md = q->queuedata;
+	struct dm_rq_target_io *tio;
+
+	if (unlikely(rq->special)) {
+		DMWARN("Already has something in rq->special.");
+		return BLKPREP_KILL;
+	}
+
+	tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
+	if (!tio)
+		return BLKPREP_DEFER;
+
+	rq->special = tio;
+	rq->cmd_flags |= REQ_DONTPREP;
+
+	return BLKPREP_OK;
+}
+
+/*
+ * Returns:
+ * 0                : the request has been processed
+ * DM_MAPIO_REQUEUE : the original request needs to be requeued
+ * < 0              : the request was completed due to failure
+ */
+static int map_request(struct dm_rq_target_io *tio, struct request *rq,
+		       struct mapped_device *md)
+{
+	int r;
+	struct dm_target *ti = tio->ti;
+	struct request *clone = NULL;
+
+	if (tio->clone) {
+		clone = tio->clone;
+		r = ti->type->map_rq(ti, clone, &tio->info);
+	} else {
+		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
+		if (r < 0) {
+			/* The target wants to complete the I/O */
+			dm_kill_unmapped_request(rq, r);
+			return r;
+		}
+		if (r != DM_MAPIO_REMAPPED)
+			return r;
+		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+			/* -ENOMEM */
+			ti->type->release_clone_rq(clone);
+			return DM_MAPIO_REQUEUE;
+		}
+	}
+
+	switch (r) {
+	case DM_MAPIO_SUBMITTED:
+		/* The target has taken the I/O to submit by itself later */
+		break;
+	case DM_MAPIO_REMAPPED:
+		/* The target has remapped the I/O so dispatch it */
+		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
+				     blk_rq_pos(rq));
+		dm_dispatch_clone_request(clone, rq);
+		break;
+	case DM_MAPIO_REQUEUE:
+		/* The target wants to requeue the I/O */
+		dm_requeue_original_request(md, tio->orig);
+		break;
+	default:
+		if (r > 0) {
+			DMWARN("unimplemented target map return value: %d", r);
+			BUG();
+		}
+
+		/* The target wants to complete the I/O */
+		dm_kill_unmapped_request(rq, r);
+		return r;
+	}
+
+	return 0;
+}
+
+static void dm_start_request(struct mapped_device *md, struct request *orig)
+{
+	if (!orig->q->mq_ops)
+		blk_start_request(orig);
+	else
+		blk_mq_start_request(orig);
+	atomic_inc(&md->pending[rq_data_dir(orig)]);
+
+	if (md->seq_rq_merge_deadline_usecs) {
+		md->last_rq_pos = rq_end_sector(orig);
+		md->last_rq_rw = rq_data_dir(orig);
+		md->last_rq_start_time = ktime_get();
+	}
+
+	if (unlikely(dm_stats_used(&md->stats))) {
+		struct dm_rq_target_io *tio = tio_from_request(orig);
+		tio->duration_jiffies = jiffies;
+		tio->n_sectors = blk_rq_sectors(orig);
+		dm_stats_account_io(&md->stats, rq_data_dir(orig),
+				    blk_rq_pos(orig), tio->n_sectors, false, 0,
+				    &tio->stats_aux);
+	}
+
+	/*
+	 * Hold the md reference here for the in-flight I/O.
+	 * We can't rely on the reference count by device opener,
+	 * because the device may be closed during the request completion
+	 * when all bios are completed.
+	 * See the comment in rq_completed() too.
+	 */
+	dm_get(md);
+}
+
+static void map_tio_request(struct kthread_work *work)
+{
+	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
+	struct request *rq = tio->orig;
+	struct mapped_device *md = tio->md;
+
+	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
+		dm_requeue_original_request(md, rq);
+}
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
+{
+	return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
+}
+
+#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
+						     const char *buf, size_t count)
+{
+	unsigned deadline;
+
+	if (dm_get_md_type(md) != DM_TYPE_REQUEST_BASED)
+		return count;
+
+	if (kstrtouint(buf, 10, &deadline))
+		return -EINVAL;
+
+	if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
+		deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;
+
+	md->seq_rq_merge_deadline_usecs = deadline;
+
+	return count;
+}
+
+static bool dm_old_request_peeked_before_merge_deadline(struct mapped_device *md)
+{
+	ktime_t kt_deadline;
+
+	if (!md->seq_rq_merge_deadline_usecs)
+		return false;
+
+	kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
+	kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);
+
+	return !ktime_after(ktime_get(), kt_deadline);
+}
+
+/*
+ * q->request_fn for old request-based dm.
+ * Called with the queue lock held.
+ */
+static void dm_old_request_fn(struct request_queue *q)
+{
+	struct mapped_device *md = q->queuedata;
+	struct dm_target *ti = md->immutable_target;
+	struct request *rq;
+	struct dm_rq_target_io *tio;
+	sector_t pos = 0;
+
+	if (unlikely(!ti)) {
+		int srcu_idx;
+		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+
+		ti = dm_table_find_target(map, pos);
+		dm_put_live_table(md, srcu_idx);
+	}
+
+	/*
+	 * For suspend, check blk_queue_stopped() and increment
+	 * ->pending within a single queue_lock not to increment the
+	 * number of in-flight I/Os after the queue is stopped in
+	 * dm_suspend().
+	 */
+	while (!blk_queue_stopped(q)) {
+		rq = blk_peek_request(q);
+		if (!rq)
+			return;
+
+		/* always use block 0 to find the target for flushes for now */
+		pos = 0;
+		if (req_op(rq) != REQ_OP_FLUSH)
+			pos = blk_rq_pos(rq);
+
+		if ((dm_old_request_peeked_before_merge_deadline(md) &&
+		     md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
+		     md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
+		    (ti->type->busy && ti->type->busy(ti))) {
+			blk_delay_queue(q, 10);
+			return;
+		}
+
+		dm_start_request(md, rq);
+
+		tio = tio_from_request(rq);
+		/* Establish tio->ti before queuing work (map_tio_request) */
+		tio->ti = ti;
+		queue_kthread_work(&md->kworker, &tio->work);
+		BUG_ON(!irqs_disabled());
+	}
+}
+
+/*
+ * Fully initialize a .request_fn request-based queue.
+ */
+int dm_old_init_request_queue(struct mapped_device *md)
+{
+	/* Fully initialize the queue */
+	if (!blk_init_allocated_queue(md->queue, dm_old_request_fn, NULL))
+		return -EINVAL;
+
+	/* disable dm_old_request_fn's merge heuristic by default */
+	md->seq_rq_merge_deadline_usecs = 0;
+
+	dm_init_normal_md_queue(md);
+	blk_queue_softirq_done(md->queue, dm_softirq_done);
+	blk_queue_prep_rq(md->queue, dm_old_prep_fn);
+
+	/* Initialize the request-based DM worker thread */
+	init_kthread_worker(&md->kworker);
+	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
+				       "kdmwork-%s", dm_device_name(md));
+	if (IS_ERR(md->kworker_task))
+		return PTR_ERR(md->kworker_task);
+
+	elv_register_queue(md->queue);
+
+	return 0;
+}
+
+static int dm_mq_init_request(void *data, struct request *rq,
+		       unsigned int hctx_idx, unsigned int request_idx,
+		       unsigned int numa_node)
+{
+	struct mapped_device *md = data;
+	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+
+	/*
+	 * Must initialize md member of tio, otherwise it won't
+	 * be available in dm_mq_queue_rq.
+	 */
+	tio->md = md;
+
+	if (md->init_tio_pdu) {
+		/* target-specific per-io data is immediately after the tio */
+		tio->info.ptr = tio + 1;
+	}
+
+	return 0;
+}
+
+static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+			  const struct blk_mq_queue_data *bd)
+{
+	struct request *rq = bd->rq;
+	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+	struct mapped_device *md = tio->md;
+	struct dm_target *ti = md->immutable_target;
+
+	if (unlikely(!ti)) {
+		int srcu_idx;
+		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+
+		ti = dm_table_find_target(map, 0);
+		dm_put_live_table(md, srcu_idx);
+	}
+
+	if (ti->type->busy && ti->type->busy(ti))
+		return BLK_MQ_RQ_QUEUE_BUSY;
+
+	dm_start_request(md, rq);
+
+	/* Init tio using md established in .init_request */
+	init_tio(tio, rq, md);
+
+	/*
+	 * Establish tio->ti before calling map_request().
+	 */
+	tio->ti = ti;
+
+	/* Direct call is fine since .queue_rq allows allocations */
+	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+		/* Undo dm_start_request() before requeuing */
+		rq_end_stats(md, rq);
+		rq_completed(md, rq_data_dir(rq), false);
+		return BLK_MQ_RQ_QUEUE_BUSY;
+	}
+
+	return BLK_MQ_RQ_QUEUE_OK;
+}
+
+static struct blk_mq_ops dm_mq_ops = {
+	.queue_rq = dm_mq_queue_rq,
+	.map_queue = blk_mq_map_queue,
+	.complete = dm_softirq_done,
+	.init_request = dm_mq_init_request,
+};
+
+int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
+{
+	struct request_queue *q;
+	struct dm_target *immutable_tgt;
+	int err;
+
+	if (!dm_table_all_blk_mq_devices(t)) {
+		DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
+		return -EINVAL;
+	}
+
+	md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
+	if (!md->tag_set)
+		return -ENOMEM;
+
+	md->tag_set->ops = &dm_mq_ops;
+	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
+	md->tag_set->numa_node = md->numa_node_id;
+	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
+	md->tag_set->driver_data = md;
+
+	md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
+	immutable_tgt = dm_table_get_immutable_target(t);
+	if (immutable_tgt && immutable_tgt->per_io_data_size) {
+		/* any target-specific per-io data is immediately after the tio */
+		md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
+		md->init_tio_pdu = true;
+	}
+
+	err = blk_mq_alloc_tag_set(md->tag_set);
+	if (err)
+		goto out_kfree_tag_set;
+
+	q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
+	if (IS_ERR(q)) {
+		err = PTR_ERR(q);
+		goto out_tag_set;
+	}
+	dm_init_md_queue(md);
+
+	/* backfill 'mq' sysfs registration normally done in blk_register_queue */
+	blk_mq_register_disk(md->disk);
+
+	return 0;
+
+out_tag_set:
+	blk_mq_free_tag_set(md->tag_set);
+out_kfree_tag_set:
+	kfree(md->tag_set);
+
+	return err;
+}
+
+void dm_mq_cleanup_mapped_device(struct mapped_device *md)
+{
+	if (md->tag_set) {
+		blk_mq_free_tag_set(md->tag_set);
+		kfree(md->tag_set);
+	}
+}
+
+module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
+
+module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
+
+module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");
+
+module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");
diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h
new file mode 100644
index 000000000000..9e6f0a3773d4
--- /dev/null
+++ b/drivers/md/dm-rq.h
@@ -0,0 +1,64 @@
+/*
+ * Internal header file for device mapper
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef DM_RQ_INTERNAL_H
+#define DM_RQ_INTERNAL_H
+
+#include <linux/bio.h>
+#include <linux/kthread.h>
+
+#include "dm-stats.h"
+
+struct mapped_device;
+
+/*
+ * One of these is allocated per request.
+ */
+struct dm_rq_target_io {
+	struct mapped_device *md;
+	struct dm_target *ti;
+	struct request *orig, *clone;
+	struct kthread_work work;
+	int error;
+	union map_info info;
+	struct dm_stats_aux stats_aux;
+	unsigned long duration_jiffies;
+	unsigned n_sectors;
+};
+
+/*
+ * For request-based dm - the bio clones we allocate are embedded in these
+ * structs.
+ *
+ * We allocate these with bio_alloc_bioset, using the front_pad parameter when
+ * the bioset is created - this means the bio has to come at the end of the
+ * struct.
+ */
+struct dm_rq_clone_bio_info {
+	struct bio *orig;
+	struct dm_rq_target_io *tio;
+	struct bio clone;
+};
+
+bool dm_use_blk_mq_default(void);
+bool dm_use_blk_mq(struct mapped_device *md);
+
+int dm_old_init_request_queue(struct mapped_device *md);
+int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t);
+void dm_mq_cleanup_mapped_device(struct mapped_device *md);
+
+void dm_start_queue(struct request_queue *q);
+void dm_stop_queue(struct request_queue *q);
+
+unsigned dm_get_reserved_rq_based_ios(void);
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf);
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
+						     const char *buf, size_t count);
+
+#endif
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 4d3909393f2c..b8cf956b577b 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -226,8 +226,8 @@ static void do_metadata(struct work_struct *work)
 /*
  * Read or write a chunk aligned and sized block of data from a device.
  */
-static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
-		    int metadata)
+static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int op,
+		    int op_flags, int metadata)
 {
 	struct dm_io_region where = {
 		.bdev = dm_snap_cow(ps->store->snap)->bdev,
@@ -235,7 +235,8 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
 		.count = ps->store->chunk_size,
 	};
 	struct dm_io_request io_req = {
-		.bi_rw = rw,
+		.bi_op = op,
+		.bi_op_flags = op_flags,
 		.mem.type = DM_IO_VMA,
 		.mem.ptr.vma = area,
 		.client = ps->io_client,
@@ -281,14 +282,14 @@ static void skip_metadata(struct pstore *ps)
  * Read or write a metadata area.  Remembering to skip the first
  * chunk which holds the header.
  */
-static int area_io(struct pstore *ps, int rw)
+static int area_io(struct pstore *ps, int op, int op_flags)
 {
 	int r;
 	chunk_t chunk;
 
 	chunk = area_location(ps, ps->current_area);
 
-	r = chunk_io(ps, ps->area, chunk, rw, 0);
+	r = chunk_io(ps, ps->area, chunk, op, op_flags, 0);
 	if (r)
 		return r;
 
@@ -302,7 +303,8 @@ static void zero_memory_area(struct pstore *ps)
 
 static int zero_disk_area(struct pstore *ps, chunk_t area)
 {
-	return chunk_io(ps, ps->zero_area, area_location(ps, area), WRITE, 0);
+	return chunk_io(ps, ps->zero_area, area_location(ps, area),
+			REQ_OP_WRITE, 0, 0);
 }
 
 static int read_header(struct pstore *ps, int *new_snapshot)
@@ -334,7 +336,7 @@ static int read_header(struct pstore *ps, int *new_snapshot)
 	if (r)
 		return r;
 
-	r = chunk_io(ps, ps->header_area, 0, READ, 1);
+	r = chunk_io(ps, ps->header_area, 0, REQ_OP_READ, 0, 1);
 	if (r)
 		goto bad;
 
@@ -395,7 +397,7 @@ static int write_header(struct pstore *ps)
 	dh->version = cpu_to_le32(ps->version);
 	dh->chunk_size = cpu_to_le32(ps->store->chunk_size);
 
-	return chunk_io(ps, ps->header_area, 0, WRITE, 1);
+	return chunk_io(ps, ps->header_area, 0, REQ_OP_WRITE, 0, 1);
 }
 
 /*
@@ -739,7 +741,7 @@ static void persistent_commit_exception(struct dm_exception_store *store,
 	/*
 	 * Commit exceptions to disk.
 	 */
-	if (ps->valid && area_io(ps, WRITE_FLUSH_FUA))
+	if (ps->valid && area_io(ps, REQ_OP_WRITE, WRITE_FLUSH_FUA))
 		ps->valid = 0;
 
 	/*
@@ -779,7 +781,7 @@ static int persistent_prepare_merge(struct dm_exception_store *store,
 			return 0;
 
 		ps->current_area--;
-		r = area_io(ps, READ);
+		r = area_io(ps, REQ_OP_READ, 0);
 		if (r < 0)
 			return r;
 		ps->current_committed = ps->exceptions_per_area;
@@ -816,7 +818,7 @@ static int persistent_commit_merge(struct dm_exception_store *store,
 	for (i = 0; i < nr_merged; i++)
 		clear_exception(ps, ps->current_committed - 1 - i);
 
-	r = area_io(ps, WRITE_FLUSH_FUA);
+	r = area_io(ps, REQ_OP_WRITE, WRITE_FLUSH_FUA);
 	if (r < 0)
 		return r;
 
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 70bb0e8b62ce..731e1f5bd895 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1680,7 +1680,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 
 	init_tracked_chunk(bio);
 
-	if (bio->bi_rw & REQ_FLUSH) {
+	if (bio->bi_rw & REQ_PREFLUSH) {
 		bio->bi_bdev = s->cow->bdev;
 		return DM_MAPIO_REMAPPED;
 	}
@@ -1696,7 +1696,8 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 	 * to copy an exception */
 	down_write(&s->lock);
 
-	if (!s->valid || (unlikely(s->snapshot_overflowed) && bio_rw(bio) == WRITE)) {
+	if (!s->valid || (unlikely(s->snapshot_overflowed) &&
+	    bio_data_dir(bio) == WRITE)) {
 		r = -EIO;
 		goto out_unlock;
 	}
@@ -1713,7 +1714,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 	 * flags so we should only get this if we are
 	 * writeable.
 	 */
-	if (bio_rw(bio) == WRITE) {
+	if (bio_data_dir(bio) == WRITE) {
 		pe = __lookup_pending_exception(s, chunk);
 		if (!pe) {
 			up_write(&s->lock);
@@ -1799,7 +1800,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
 
 	init_tracked_chunk(bio);
 
-	if (bio->bi_rw & REQ_FLUSH) {
+	if (bio->bi_rw & REQ_PREFLUSH) {
 		if (!dm_bio_get_target_bio_nr(bio))
 			bio->bi_bdev = s->origin->bdev;
 		else
@@ -1819,7 +1820,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
 	e = dm_lookup_exception(&s->complete, chunk);
 	if (e) {
 		/* Queue writes overlapping with chunks being merged */
-		if (bio_rw(bio) == WRITE &&
+		if (bio_data_dir(bio) == WRITE &&
 		    chunk >= s->first_merging_chunk &&
 		    chunk < (s->first_merging_chunk +
 			     s->num_merging_chunks)) {
@@ -1831,7 +1832,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
 
 		remap_exception(s, e, bio, chunk);
 
-		if (bio_rw(bio) == WRITE)
+		if (bio_data_dir(bio) == WRITE)
 			track_chunk(s, bio, chunk);
 		goto out_unlock;
 	}
@@ -1839,7 +1840,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
 redirect_to_origin:
 	bio->bi_bdev = s->origin->bdev;
 
-	if (bio_rw(bio) == WRITE) {
+	if (bio_data_dir(bio) == WRITE) {
 		up_write(&s->lock);
 		return do_origin(s->origin, bio);
 	}
@@ -2285,10 +2286,10 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
 
 	bio->bi_bdev = o->dev->bdev;
 
-	if (unlikely(bio->bi_rw & REQ_FLUSH))
+	if (unlikely(bio->bi_rw & REQ_PREFLUSH))
 		return DM_MAPIO_REMAPPED;
 
-	if (bio_rw(bio) != WRITE)
+	if (bio_data_dir(bio) != WRITE)
 		return DM_MAPIO_REMAPPED;
 
 	available_sectors = o->split_boundary -
@@ -2301,6 +2302,13 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
 	return do_origin(o->dev, bio);
 }
 
+static long origin_direct_access(struct dm_target *ti, sector_t sector,
+		void __pmem **kaddr, pfn_t *pfn, long size)
+{
+	DMWARN("device does not support dax.");
+	return -EIO;
+}
+
 /*
  * Set the target "max_io_len" field to the minimum of all the snapshots'
  * chunk sizes.
@@ -2360,6 +2368,7 @@ static struct target_type origin_target = {
 	.postsuspend = origin_postsuspend,
 	.status  = origin_status,
 	.iterate_devices = origin_iterate_devices,
+	.direct_access = origin_direct_access,
 };
 
 static struct target_type snapshot_target = {
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 8289804ccd99..38b05f23b96c 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/device-mapper.h>
 
-#include "dm.h"
+#include "dm-core.h"
 #include "dm-stats.h"
 
 #define DM_MSG_PREFIX "stats"
@@ -514,11 +514,10 @@ static void dm_stat_round(struct dm_stat *s, struct dm_stat_shared *shared,
 }
 
 static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
-			      unsigned long bi_rw, sector_t len,
+			      int idx, sector_t len,
 			      struct dm_stats_aux *stats_aux, bool end,
 			      unsigned long duration_jiffies)
 {
-	unsigned long idx = bi_rw & REQ_WRITE;
 	struct dm_stat_shared *shared = &s->stat_shared[entry];
 	struct dm_stat_percpu *p;
 
@@ -584,7 +583,7 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
 #endif
 }
 
-static void __dm_stat_bio(struct dm_stat *s, unsigned long bi_rw,
+static void __dm_stat_bio(struct dm_stat *s, int bi_rw,
 			  sector_t bi_sector, sector_t end_sector,
 			  bool end, unsigned long duration_jiffies,
 			  struct dm_stats_aux *stats_aux)
@@ -645,8 +644,8 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw,
 		last = raw_cpu_ptr(stats->last);
 		stats_aux->merged =
 			(bi_sector == (ACCESS_ONCE(last->last_sector) &&
-				       ((bi_rw & (REQ_WRITE | REQ_DISCARD)) ==
-					(ACCESS_ONCE(last->last_rw) & (REQ_WRITE | REQ_DISCARD)))
+				       ((bi_rw == WRITE) ==
+					(ACCESS_ONCE(last->last_rw) == WRITE))
 				       ));
 		ACCESS_ONCE(last->last_sector) = end_sector;
 		ACCESS_ONCE(last->last_rw) = bi_rw;
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 797ddb900b06..01bb9cf2a8c2 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -286,14 +286,14 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 	uint32_t stripe;
 	unsigned target_bio_nr;
 
-	if (bio->bi_rw & REQ_FLUSH) {
+	if (bio->bi_rw & REQ_PREFLUSH) {
 		target_bio_nr = dm_bio_get_target_bio_nr(bio);
 		BUG_ON(target_bio_nr >= sc->stripes);
 		bio->bi_bdev = sc->stripe[target_bio_nr].dev->bdev;
 		return DM_MAPIO_REMAPPED;
 	}
-	if (unlikely(bio->bi_rw & REQ_DISCARD) ||
-	    unlikely(bio->bi_rw & REQ_WRITE_SAME)) {
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD) ||
+	    unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) {
 		target_bio_nr = dm_bio_get_target_bio_nr(bio);
 		BUG_ON(target_bio_nr >= sc->stripes);
 		return stripe_map_range(sc, bio, target_bio_nr);
@@ -308,6 +308,29 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_REMAPPED;
 }
 
+static long stripe_direct_access(struct dm_target *ti, sector_t sector,
+				 void __pmem **kaddr, pfn_t *pfn, long size)
+{
+	struct stripe_c *sc = ti->private;
+	uint32_t stripe;
+	struct block_device *bdev;
+	struct blk_dax_ctl dax = {
+		.size = size,
+	};
+	long ret;
+
+	stripe_map_sector(sc, sector, &stripe, &dax.sector);
+
+	dax.sector += sc->stripe[stripe].physical_start;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	ret = bdev_direct_access(bdev, &dax);
+	*kaddr = dax.addr;
+	*pfn = dax.pfn;
+
+	return ret;
+}
+
 /*
  * Stripe status:
  *
@@ -416,7 +439,7 @@ static void stripe_io_hints(struct dm_target *ti,
 
 static struct target_type stripe_target = {
 	.name   = "striped",
-	.version = {1, 5, 1},
+	.version = {1, 6, 0},
 	.module = THIS_MODULE,
 	.ctr    = stripe_ctr,
 	.dtr    = stripe_dtr,
@@ -425,6 +448,7 @@ static struct target_type stripe_target = {
 	.status = stripe_status,
 	.iterate_devices = stripe_iterate_devices,
 	.io_hints = stripe_io_hints,
+	.direct_access = stripe_direct_access,
 };
 
 int __init dm_stripe_init(void)
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index 7e818f5f1dc4..c209b8a19b84 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -6,7 +6,8 @@
 
 #include <linux/sysfs.h>
 #include <linux/dm-ioctl.h>
-#include "dm.h"
+#include "dm-core.h"
+#include "dm-rq.h"
 
 struct dm_sysfs_attr {
 	struct attribute attr;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 626a5ec04466..3e407a9cde1f 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -5,7 +5,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/module.h>
 #include <linux/vmalloc.h>
@@ -43,8 +43,10 @@ struct dm_table {
 	struct dm_target *targets;
 
 	struct target_type *immutable_target_type;
-	unsigned integrity_supported:1;
-	unsigned singleton:1;
+
+	bool integrity_supported:1;
+	bool singleton:1;
+	bool all_blk_mq:1;
 
 	/*
 	 * Indicates the rw permissions for the new logical
@@ -206,6 +208,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 	}
 
+	t->type = DM_TYPE_NONE;
 	t->mode = mode;
 	t->md = md;
 	*result = t;
@@ -703,7 +706,7 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 			      dm_device_name(t->md), type);
 			return -EINVAL;
 		}
-		t->singleton = 1;
+		t->singleton = true;
 	}
 
 	if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
@@ -824,22 +827,70 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args)
 }
 EXPORT_SYMBOL(dm_consume_args);
 
+static bool __table_type_bio_based(unsigned table_type)
+{
+	return (table_type == DM_TYPE_BIO_BASED ||
+		table_type == DM_TYPE_DAX_BIO_BASED);
+}
+
 static bool __table_type_request_based(unsigned table_type)
 {
 	return (table_type == DM_TYPE_REQUEST_BASED ||
 		table_type == DM_TYPE_MQ_REQUEST_BASED);
 }
 
-static int dm_table_set_type(struct dm_table *t)
+void dm_table_set_type(struct dm_table *t, unsigned type)
+{
+	t->type = type;
+}
+EXPORT_SYMBOL_GPL(dm_table_set_type);
+
+static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+			       sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && blk_queue_dax(q);
+}
+
+static bool dm_table_supports_dax(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	/* Ensure that all targets support DAX. */
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!ti->type->direct_access)
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    !ti->type->iterate_devices(ti, device_supports_dax, NULL))
+			return false;
+	}
+
+	return true;
+}
+
+static int dm_table_determine_type(struct dm_table *t)
 {
 	unsigned i;
 	unsigned bio_based = 0, request_based = 0, hybrid = 0;
-	bool use_blk_mq = false;
+	bool verify_blk_mq = false;
 	struct dm_target *tgt;
 	struct dm_dev_internal *dd;
-	struct list_head *devices;
+	struct list_head *devices = dm_table_get_devices(t);
 	unsigned live_md_type = dm_get_md_type(t->md);
 
+	if (t->type != DM_TYPE_NONE) {
+		/* target already set the table's type */
+		if (t->type == DM_TYPE_BIO_BASED)
+			return 0;
+		BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
+		goto verify_rq_based;
+	}
+
 	for (i = 0; i < t->num_targets; i++) {
 		tgt = t->targets + i;
 		if (dm_target_hybrid(tgt))
@@ -871,11 +922,27 @@ static int dm_table_set_type(struct dm_table *t)
 	if (bio_based) {
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
+		if (dm_table_supports_dax(t) ||
+		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED))
+			t->type = DM_TYPE_DAX_BIO_BASED;
 		return 0;
 	}
 
 	BUG_ON(!request_based); /* No targets in this table */
 
+	if (list_empty(devices) && __table_type_request_based(live_md_type)) {
+		/* inherit live MD type */
+		t->type = live_md_type;
+		return 0;
+	}
+
+	/*
+	 * The only way to establish DM_TYPE_MQ_REQUEST_BASED is by
+	 * having a compatible target use dm_table_set_type.
+	 */
+	t->type = DM_TYPE_REQUEST_BASED;
+
+verify_rq_based:
 	/*
 	 * Request-based dm supports only tables that have a single target now.
 	 * To support multiple targets, request splitting support is needed,
@@ -888,7 +955,6 @@ static int dm_table_set_type(struct dm_table *t)
 	}
 
 	/* Non-request-stackable devices can't be used for request-based dm */
-	devices = dm_table_get_devices(t);
 	list_for_each_entry(dd, devices, list) {
 		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
 
@@ -899,10 +965,10 @@ static int dm_table_set_type(struct dm_table *t)
 		}
 
 		if (q->mq_ops)
-			use_blk_mq = true;
+			verify_blk_mq = true;
 	}
 
-	if (use_blk_mq) {
+	if (verify_blk_mq) {
 		/* verify _all_ devices in the table are blk-mq devices */
 		list_for_each_entry(dd, devices, list)
 			if (!bdev_get_queue(dd->dm_dev->bdev)->mq_ops) {
@@ -910,14 +976,9 @@ static int dm_table_set_type(struct dm_table *t)
 				      " are blk-mq request-stackable");
 				return -EINVAL;
 			}
-		t->type = DM_TYPE_MQ_REQUEST_BASED;
 
-	} else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
-		/* inherit live MD type */
-		t->type = live_md_type;
-
-	} else
-		t->type = DM_TYPE_REQUEST_BASED;
+		t->all_blk_mq = true;
+	}
 
 	return 0;
 }
@@ -956,14 +1017,19 @@ struct dm_target *dm_table_get_wildcard_target(struct dm_table *t)
 	return NULL;
 }
 
+bool dm_table_bio_based(struct dm_table *t)
+{
+	return __table_type_bio_based(dm_table_get_type(t));
+}
+
 bool dm_table_request_based(struct dm_table *t)
 {
 	return __table_type_request_based(dm_table_get_type(t));
 }
 
-bool dm_table_mq_request_based(struct dm_table *t)
+bool dm_table_all_blk_mq_devices(struct dm_table *t)
 {
-	return dm_table_get_type(t) == DM_TYPE_MQ_REQUEST_BASED;
+	return t->all_blk_mq;
 }
 
 static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
@@ -978,7 +1044,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 		return -EINVAL;
 	}
 
-	if (type == DM_TYPE_BIO_BASED)
+	if (__table_type_bio_based(type))
 		for (i = 0; i < t->num_targets; i++) {
 			tgt = t->targets + i;
 			per_io_data_size = max(per_io_data_size, tgt->per_io_data_size);
@@ -1106,7 +1172,7 @@ static int dm_table_register_integrity(struct dm_table *t)
 		return 0;
 
 	if (!integrity_profile_exists(dm_disk(md))) {
-		t->integrity_supported = 1;
+		t->integrity_supported = true;
 		/*
 		 * Register integrity profile during table load; we can do
 		 * this because the final profile must match during resume.
@@ -1129,7 +1195,7 @@ static int dm_table_register_integrity(struct dm_table *t)
 	}
 
 	/* Preserve existing integrity profile */
-	t->integrity_supported = 1;
+	t->integrity_supported = true;
 	return 0;
 }
 
@@ -1141,9 +1207,9 @@ int dm_table_complete(struct dm_table *t)
 {
 	int r;
 
-	r = dm_table_set_type(t);
+	r = dm_table_determine_type(t);
 	if (r) {
-		DMERR("unable to set table type");
+		DMERR("unable to determine table type");
 		return r;
 	}
 
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index a317dd884ba6..6eecd6b36f76 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -4,7 +4,7 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
 
 #include <linux/module.h>
 #include <linux/init.h>
@@ -148,9 +148,15 @@ static void io_err_release_clone_rq(struct request *clone)
 {
 }
 
+static long io_err_direct_access(struct dm_target *ti, sector_t sector,
+				 void __pmem **kaddr, pfn_t *pfn, long size)
+{
+	return -EIO;
+}
+
 static struct target_type error_target = {
 	.name = "error",
-	.version = {1, 4, 0},
+	.version = {1, 5, 0},
 	.features = DM_TARGET_WILDCARD,
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
@@ -158,6 +164,7 @@ static struct target_type error_target = {
 	.map_rq = io_err_map_rq,
 	.clone_and_map_rq = io_err_clone_and_map_rq,
 	.release_clone_rq = io_err_release_clone_rq,
+	.direct_access = io_err_direct_access,
 };
 
 int __init dm_target_init(void)
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 43824d73366d..a15091a0d40c 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1677,6 +1677,36 @@ int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *resu
 	return r;
 }
 
+int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
+{
+	int r = 0;
+
+	down_write(&pmd->root_lock);
+	for (; b != e; b++) {
+		r = dm_sm_inc_block(pmd->data_sm, b);
+		if (r)
+			break;
+	}
+	up_write(&pmd->root_lock);
+
+	return r;
+}
+
+int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
+{
+	int r = 0;
+
+	down_write(&pmd->root_lock);
+	for (; b != e; b++) {
+		r = dm_sm_dec_block(pmd->data_sm, b);
+		if (r)
+			break;
+	}
+	up_write(&pmd->root_lock);
+
+	return r;
+}
+
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
 {
 	int r;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index a938babe4258..35e954ea20a9 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -197,6 +197,9 @@ int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
 
 int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
 
+int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e);
+int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e);
+
 /*
  * Returns -ENOSPC if the new size is too small and already allocated
  * blocks would be lost.
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fc803d50f9f0..197ea2003400 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -253,6 +253,7 @@ struct pool {
 	struct bio_list deferred_flush_bios;
 	struct list_head prepared_mappings;
 	struct list_head prepared_discards;
+	struct list_head prepared_discards_pt2;
 	struct list_head active_thins;
 
 	struct dm_deferred_set *shared_read_ds;
@@ -269,6 +270,7 @@ struct pool {
 
 	process_mapping_fn process_prepared_mapping;
 	process_mapping_fn process_prepared_discard;
+	process_mapping_fn process_prepared_discard_pt2;
 
 	struct dm_bio_prison_cell **cell_sort_array;
 };
@@ -360,7 +362,7 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da
 	sector_t len = block_to_sectors(tc->pool, data_e - data_b);
 
 	return __blkdev_issue_discard(tc->pool_dev->bdev, s, len,
-				      GFP_NOWAIT, REQ_WRITE | REQ_DISCARD, &op->bio);
+				      GFP_NOWAIT, 0, &op->bio);
 }
 
 static void end_discard(struct discard_op *op, int r)
@@ -371,7 +373,8 @@ static void end_discard(struct discard_op *op, int r)
 		 * need to wait for the chain to complete.
 		 */
 		bio_chain(op->bio, op->parent_bio);
-		submit_bio(REQ_WRITE | REQ_DISCARD, op->bio);
+		bio_set_op_attrs(op->bio, REQ_OP_DISCARD, 0);
+		submit_bio(op->bio);
 	}
 
 	blk_finish_plug(&op->plug);
@@ -696,7 +699,7 @@ static void remap_to_origin(struct thin_c *tc, struct bio *bio)
 
 static int bio_triggers_commit(struct thin_c *tc, struct bio *bio)
 {
-	return (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) &&
+	return (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) &&
 		dm_thin_changed_this_transaction(tc->td);
 }
 
@@ -704,7 +707,7 @@ static void inc_all_io_entry(struct pool *pool, struct bio *bio)
 {
 	struct dm_thin_endio_hook *h;
 
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		return;
 
 	h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
@@ -867,7 +870,8 @@ static void __inc_remap_and_issue_cell(void *context,
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(&cell->bios))) {
-		if (bio->bi_rw & (REQ_DISCARD | REQ_FLUSH | REQ_FUA))
+		if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA) ||
+		    bio_op(bio) == REQ_OP_DISCARD)
 			bio_list_add(&info->defer_bios, bio);
 		else {
 			inc_all_io_entry(info->tc->pool, bio);
@@ -999,7 +1003,8 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
 
 /*----------------------------------------------------------------*/
 
-static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m)
+static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m,
+						   struct bio *discard_parent)
 {
 	/*
 	 * We've already unmapped this range of blocks, but before we
@@ -1012,7 +1017,7 @@ static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m
 	dm_block_t b = m->data_block, e, end = m->data_block + m->virt_end - m->virt_begin;
 	struct discard_op op;
 
-	begin_discard(&op, tc, m->bio);
+	begin_discard(&op, tc, discard_parent);
 	while (b != end) {
 		/* find start of unmapped run */
 		for (; b < end; b++) {
@@ -1047,28 +1052,101 @@ out:
 	end_discard(&op, r);
 }
 
-static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
+static void queue_passdown_pt2(struct dm_thin_new_mapping *m)
+{
+	unsigned long flags;
+	struct pool *pool = m->tc->pool;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	list_add_tail(&m->list, &pool->prepared_discards_pt2);
+	spin_unlock_irqrestore(&pool->lock, flags);
+	wake_worker(pool);
+}
+
+static void passdown_endio(struct bio *bio)
+{
+	/*
+	 * It doesn't matter if the passdown discard failed, we still want
+	 * to unmap (we ignore err).
+	 */
+	queue_passdown_pt2(bio->bi_private);
+}
+
+static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
 {
 	int r;
 	struct thin_c *tc = m->tc;
 	struct pool *pool = tc->pool;
+	struct bio *discard_parent;
+	dm_block_t data_end = m->data_block + (m->virt_end - m->virt_begin);
 
+	/*
+	 * Only this thread allocates blocks, so we can be sure that the
+	 * newly unmapped blocks will not be allocated before the end of
+	 * the function.
+	 */
 	r = dm_thin_remove_range(tc->td, m->virt_begin, m->virt_end);
 	if (r) {
 		metadata_operation_failed(pool, "dm_thin_remove_range", r);
 		bio_io_error(m->bio);
+		cell_defer_no_holder(tc, m->cell);
+		mempool_free(m, pool->mapping_pool);
+		return;
+	}
 
-	} else if (m->maybe_shared) {
-		passdown_double_checking_shared_status(m);
+	discard_parent = bio_alloc(GFP_NOIO, 1);
+	if (!discard_parent) {
+		DMWARN("%s: unable to allocate top level discard bio for passdown. Skipping passdown.",
+		       dm_device_name(tc->pool->pool_md));
+		queue_passdown_pt2(m);
 
 	} else {
-		struct discard_op op;
-		begin_discard(&op, tc, m->bio);
-		r = issue_discard(&op, m->data_block,
-				  m->data_block + (m->virt_end - m->virt_begin));
-		end_discard(&op, r);
+		discard_parent->bi_end_io = passdown_endio;
+		discard_parent->bi_private = m;
+
+		if (m->maybe_shared)
+			passdown_double_checking_shared_status(m, discard_parent);
+		else {
+			struct discard_op op;
+
+			begin_discard(&op, tc, discard_parent);
+			r = issue_discard(&op, m->data_block, data_end);
+			end_discard(&op, r);
+		}
 	}
 
+	/*
+	 * Increment the unmapped blocks.  This prevents a race between the
+	 * passdown io and reallocation of freed blocks.
+	 */
+	r = dm_pool_inc_data_range(pool->pmd, m->data_block, data_end);
+	if (r) {
+		metadata_operation_failed(pool, "dm_pool_inc_data_range", r);
+		bio_io_error(m->bio);
+		cell_defer_no_holder(tc, m->cell);
+		mempool_free(m, pool->mapping_pool);
+		return;
+	}
+}
+
+static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m)
+{
+	int r;
+	struct thin_c *tc = m->tc;
+	struct pool *pool = tc->pool;
+
+	/*
+	 * The passdown has completed, so now we can decrement all those
+	 * unmapped blocks.
+	 */
+	r = dm_pool_dec_data_range(pool->pmd, m->data_block,
+				   m->data_block + (m->virt_end - m->virt_begin));
+	if (r) {
+		metadata_operation_failed(pool, "dm_pool_dec_data_range", r);
+		bio_io_error(m->bio);
+	} else
+		bio_endio(m->bio);
+
 	cell_defer_no_holder(tc, m->cell);
 	mempool_free(m, pool->mapping_pool);
 }
@@ -1639,7 +1717,8 @@ static void __remap_and_issue_shared_cell(void *context,
 
 	while ((bio = bio_list_pop(&cell->bios))) {
 		if ((bio_data_dir(bio) == WRITE) ||
-		    (bio->bi_rw & (REQ_DISCARD | REQ_FLUSH | REQ_FUA)))
+		    (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA) ||
+		     bio_op(bio) == REQ_OP_DISCARD))
 			bio_list_add(&info->defer_bios, bio);
 		else {
 			struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));;
@@ -2028,7 +2107,7 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 			break;
 		}
 
-		if (bio->bi_rw & REQ_DISCARD)
+		if (bio_op(bio) == REQ_OP_DISCARD)
 			pool->process_discard(tc, bio);
 		else
 			pool->process_bio(tc, bio);
@@ -2115,7 +2194,7 @@ static void process_thin_deferred_cells(struct thin_c *tc)
 				return;
 			}
 
-			if (cell->holder->bi_rw & REQ_DISCARD)
+			if (bio_op(cell->holder) == REQ_OP_DISCARD)
 				pool->process_discard_cell(tc, cell);
 			else
 				pool->process_cell(tc, cell);
@@ -2212,6 +2291,8 @@ static void do_worker(struct work_struct *ws)
 	throttle_work_update(&pool->throttle);
 	process_prepared(pool, &pool->prepared_discards, &pool->process_prepared_discard);
 	throttle_work_update(&pool->throttle);
+	process_prepared(pool, &pool->prepared_discards_pt2, &pool->process_prepared_discard_pt2);
+	throttle_work_update(&pool->throttle);
 	process_deferred_bios(pool);
 	throttle_work_complete(&pool->throttle);
 }
@@ -2340,7 +2421,8 @@ static void set_discard_callbacks(struct pool *pool)
 
 	if (passdown_enabled(pt)) {
 		pool->process_discard_cell = process_discard_cell_passdown;
-		pool->process_prepared_discard = process_prepared_discard_passdown;
+		pool->process_prepared_discard = process_prepared_discard_passdown_pt1;
+		pool->process_prepared_discard_pt2 = process_prepared_discard_passdown_pt2;
 	} else {
 		pool->process_discard_cell = process_discard_cell_no_passdown;
 		pool->process_prepared_discard = process_prepared_discard_no_passdown;
@@ -2553,7 +2635,8 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_SUBMITTED;
 	}
 
-	if (bio->bi_rw & (REQ_DISCARD | REQ_FLUSH | REQ_FUA)) {
+	if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA) ||
+	    bio_op(bio) == REQ_OP_DISCARD) {
 		thin_defer_bio_with_throttle(tc, bio);
 		return DM_MAPIO_SUBMITTED;
 	}
@@ -2826,6 +2909,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	bio_list_init(&pool->deferred_flush_bios);
 	INIT_LIST_HEAD(&pool->prepared_mappings);
 	INIT_LIST_HEAD(&pool->prepared_discards);
+	INIT_LIST_HEAD(&pool->prepared_discards_pt2);
 	INIT_LIST_HEAD(&pool->active_thins);
 	pool->low_water_triggered = false;
 	pool->suspended = true;
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 459a9f8905ed..0f0eb8a3d922 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -453,9 +453,7 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
 	 */
 
 	offset = block << v->data_dev_block_bits;
-
-	res = offset;
-	div64_u64(res, v->fec->rounds << v->data_dev_block_bits);
+	res = div64_u64(offset, v->fec->rounds << v->data_dev_block_bits);
 
 	/*
 	 * The base RS block we can feed to the interleaver to find out all
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index 766bc93006e6..618b8752dcf1 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -35,16 +35,19 @@ static int zero_ctr(struct dm_target *ti, unsigned int argc, char **argv)
  */
 static int zero_map(struct dm_target *ti, struct bio *bio)
 {
-	switch(bio_rw(bio)) {
-	case READ:
+	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+		if (bio->bi_rw & REQ_RAHEAD) {
+			/* readahead of null bytes only wastes buffer cache */
+			return -EIO;
+		}
 		zero_fill_bio(bio);
 		break;
-	case READA:
-		/* readahead of null bytes only wastes buffer cache */
-		return -EIO;
-	case WRITE:
+	case REQ_OP_WRITE:
 		/* writes get silently dropped */
 		break;
+	default:
+		return -EIO;
 	}
 
 	bio_endio(bio);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1b2f96205361..ceb69fc0b10b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -5,13 +5,13 @@
  * This file is released under the GPL.
  */
 
-#include "dm.h"
+#include "dm-core.h"
+#include "dm-rq.h"
 #include "dm-uevent.h"
 
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/moduleparam.h>
 #include <linux/blkpg.h>
 #include <linux/bio.h>
 #include <linux/mempool.h>
@@ -20,14 +20,8 @@
 #include <linux/hdreg.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
-#include <linux/kthread.h>
-#include <linux/ktime.h>
-#include <linux/elevator.h> /* for rq_end_sector() */
-#include <linux/blk-mq.h>
 #include <linux/pr.h>
 
-#include <trace/events/block.h>
-
 #define DM_MSG_PREFIX "core"
 
 #ifdef CONFIG_PRINTK
@@ -63,7 +57,6 @@ static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
 static struct workqueue_struct *deferred_remove_workqueue;
 
 /*
- * For bio-based dm.
  * One of these is allocated per bio.
  */
 struct dm_io {
@@ -76,36 +69,6 @@ struct dm_io {
 	struct dm_stats_aux stats_aux;
 };
 
-/*
- * For request-based dm.
- * One of these is allocated per request.
- */
-struct dm_rq_target_io {
-	struct mapped_device *md;
-	struct dm_target *ti;
-	struct request *orig, *clone;
-	struct kthread_work work;
-	int error;
-	union map_info info;
-	struct dm_stats_aux stats_aux;
-	unsigned long duration_jiffies;
-	unsigned n_sectors;
-};
-
-/*
- * For request-based dm - the bio clones we allocate are embedded in these
- * structs.
- *
- * We allocate these with bio_alloc_bioset, using the front_pad parameter when
- * the bioset is created - this means the bio has to come at the end of the
- * struct.
- */
-struct dm_rq_clone_bio_info {
-	struct bio *orig;
-	struct dm_rq_target_io *tio;
-	struct bio clone;
-};
-
 #define MINOR_ALLOCED ((void *)-1)
 
 /*
@@ -120,130 +83,9 @@ struct dm_rq_clone_bio_info {
 #define DMF_DEFERRED_REMOVE 6
 #define DMF_SUSPENDED_INTERNALLY 7
 
-/*
- * Work processed by per-device workqueue.
- */
-struct mapped_device {
-	struct srcu_struct io_barrier;
-	struct mutex suspend_lock;
-
-	/*
-	 * The current mapping (struct dm_table *).
-	 * Use dm_get_live_table{_fast} or take suspend_lock for
-	 * dereference.
-	 */
-	void __rcu *map;
-
-	struct list_head table_devices;
-	struct mutex table_devices_lock;
-
-	unsigned long flags;
-
-	struct request_queue *queue;
-	int numa_node_id;
-
-	unsigned type;
-	/* Protect queue and type against concurrent access. */
-	struct mutex type_lock;
-
-	atomic_t holders;
-	atomic_t open_count;
-
-	struct dm_target *immutable_target;
-	struct target_type *immutable_target_type;
-
-	struct gendisk *disk;
-	char name[16];
-
-	void *interface_ptr;
-
-	/*
-	 * A list of ios that arrived while we were suspended.
-	 */
-	atomic_t pending[2];
-	wait_queue_head_t wait;
-	struct work_struct work;
-	spinlock_t deferred_lock;
-	struct bio_list deferred;
-
-	/*
-	 * Event handling.
-	 */
-	wait_queue_head_t eventq;
-	atomic_t event_nr;
-	atomic_t uevent_seq;
-	struct list_head uevent_list;
-	spinlock_t uevent_lock; /* Protect access to uevent_list */
-
-	/* the number of internal suspends */
-	unsigned internal_suspend_count;
-
-	/*
-	 * Processing queue (flush)
-	 */
-	struct workqueue_struct *wq;
-
-	/*
-	 * io objects are allocated from here.
-	 */
-	mempool_t *io_pool;
-	mempool_t *rq_pool;
-
-	struct bio_set *bs;
-
-	/*
-	 * freeze/thaw support require holding onto a super block
-	 */
-	struct super_block *frozen_sb;
-
-	/* forced geometry settings */
-	struct hd_geometry geometry;
-
-	struct block_device *bdev;
-
-	/* kobject and completion */
-	struct dm_kobject_holder kobj_holder;
-
-	/* zero-length flush that will be cloned and submitted to targets */
-	struct bio flush_bio;
-
-	struct dm_stats stats;
-
-	struct kthread_worker kworker;
-	struct task_struct *kworker_task;
-
-	/* for request-based merge heuristic in dm_request_fn() */
-	unsigned seq_rq_merge_deadline_usecs;
-	int last_rq_rw;
-	sector_t last_rq_pos;
-	ktime_t last_rq_start_time;
-
-	/* for blk-mq request-based DM support */
-	struct blk_mq_tag_set *tag_set;
-	bool use_blk_mq:1;
-	bool init_tio_pdu:1;
-};
-
-#ifdef CONFIG_DM_MQ_DEFAULT
-static bool use_blk_mq = true;
-#else
-static bool use_blk_mq = false;
-#endif
-
-#define DM_MQ_NR_HW_QUEUES 1
-#define DM_MQ_QUEUE_DEPTH 2048
 #define DM_NUMA_NODE NUMA_NO_NODE
-
-static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
-static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
 static int dm_numa_node = DM_NUMA_NODE;
 
-bool dm_use_blk_mq(struct mapped_device *md)
-{
-	return md->use_blk_mq;
-}
-EXPORT_SYMBOL_GPL(dm_use_blk_mq);
-
 /*
  * For mempools pre-allocation at the table loading time.
  */
@@ -259,9 +101,6 @@ struct table_device {
 	struct dm_dev dm_dev;
 };
 
-#define RESERVED_BIO_BASED_IOS		16
-#define RESERVED_REQUEST_BASED_IOS	256
-#define RESERVED_MAX_IOS		1024
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_rq_tio_cache;
 static struct kmem_cache *_rq_cache;
@@ -269,13 +108,9 @@ static struct kmem_cache *_rq_cache;
 /*
  * Bio-based DM's mempools' reserved IOs set by the user.
  */
+#define RESERVED_BIO_BASED_IOS		16
 static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
 
-/*
- * Request-based DM's mempools' reserved IOs set by the user.
- */
-static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
-
 static int __dm_get_module_param_int(int *module_param, int min, int max)
 {
 	int param = ACCESS_ONCE(*module_param);
@@ -297,8 +132,8 @@ static int __dm_get_module_param_int(int *module_param, int min, int max)
 	return param;
 }
 
-static unsigned __dm_get_module_param(unsigned *module_param,
-				      unsigned def, unsigned max)
+unsigned __dm_get_module_param(unsigned *module_param,
+			       unsigned def, unsigned max)
 {
 	unsigned param = ACCESS_ONCE(*module_param);
 	unsigned modified_param = 0;
@@ -319,28 +154,10 @@ static unsigned __dm_get_module_param(unsigned *module_param,
 unsigned dm_get_reserved_bio_based_ios(void)
 {
 	return __dm_get_module_param(&reserved_bio_based_ios,
-				     RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS);
+				     RESERVED_BIO_BASED_IOS, DM_RESERVED_MAX_IOS);
 }
 EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios);
 
-unsigned dm_get_reserved_rq_based_ios(void)
-{
-	return __dm_get_module_param(&reserved_rq_based_ios,
-				     RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS);
-}
-EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
-
-static unsigned dm_get_blk_mq_nr_hw_queues(void)
-{
-	return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
-}
-
-static unsigned dm_get_blk_mq_queue_depth(void)
-{
-	return __dm_get_module_param(&dm_mq_queue_depth,
-				     DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
-}
-
 static unsigned dm_get_numa_node(void)
 {
 	return __dm_get_module_param_int(&dm_numa_node,
@@ -679,29 +496,7 @@ static void free_tio(struct dm_target_io *tio)
 	bio_put(&tio->clone);
 }
 
-static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
-						gfp_t gfp_mask)
-{
-	return mempool_alloc(md->io_pool, gfp_mask);
-}
-
-static void free_old_rq_tio(struct dm_rq_target_io *tio)
-{
-	mempool_free(tio, tio->md->io_pool);
-}
-
-static struct request *alloc_old_clone_request(struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	return mempool_alloc(md->rq_pool, gfp_mask);
-}
-
-static void free_old_clone_request(struct mapped_device *md, struct request *rq)
-{
-	mempool_free(rq, md->rq_pool);
-}
-
-static int md_in_flight(struct mapped_device *md)
+int md_in_flight(struct mapped_device *md)
 {
 	return atomic_read(&md->pending[READ]) +
 	       atomic_read(&md->pending[WRITE]);
@@ -723,8 +518,9 @@ static void start_io_acct(struct dm_io *io)
 		atomic_inc_return(&md->pending[rw]));
 
 	if (unlikely(dm_stats_used(&md->stats)))
-		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
-				    bio_sectors(bio), false, 0, &io->stats_aux);
+		dm_stats_account_io(&md->stats, bio_data_dir(bio),
+				    bio->bi_iter.bi_sector, bio_sectors(bio),
+				    false, 0, &io->stats_aux);
 }
 
 static void end_io_acct(struct dm_io *io)
@@ -738,8 +534,9 @@ static void end_io_acct(struct dm_io *io)
 	generic_end_io_acct(rw, &dm_disk(md)->part0, io->start_time);
 
 	if (unlikely(dm_stats_used(&md->stats)))
-		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
-				    bio_sectors(bio), true, duration, &io->stats_aux);
+		dm_stats_account_io(&md->stats, bio_data_dir(bio),
+				    bio->bi_iter.bi_sector, bio_sectors(bio),
+				    true, duration, &io->stats_aux);
 
 	/*
 	 * After this is decremented the bio must not be touched if it is
@@ -1001,12 +798,12 @@ static void dec_pending(struct dm_io *io, int error)
 		if (io_error == DM_ENDIO_REQUEUE)
 			return;
 
-		if ((bio->bi_rw & REQ_FLUSH) && bio->bi_iter.bi_size) {
+		if ((bio->bi_rw & REQ_PREFLUSH) && bio->bi_iter.bi_size) {
 			/*
 			 * Preflush done for flush with data, reissue
-			 * without REQ_FLUSH.
+			 * without REQ_PREFLUSH.
 			 */
-			bio->bi_rw &= ~REQ_FLUSH;
+			bio->bi_rw &= ~REQ_PREFLUSH;
 			queue_io(md, bio);
 		} else {
 			/* done with normal IO or empty flush */
@@ -1017,7 +814,7 @@ static void dec_pending(struct dm_io *io, int error)
 	}
 }
 
-static void disable_write_same(struct mapped_device *md)
+void disable_write_same(struct mapped_device *md)
 {
 	struct queue_limits *limits = dm_get_queue_limits(md);
 
@@ -1051,7 +848,7 @@ static void clone_endio(struct bio *bio)
 		}
 	}
 
-	if (unlikely(r == -EREMOTEIO && (bio->bi_rw & REQ_WRITE_SAME) &&
+	if (unlikely(r == -EREMOTEIO && (bio_op(bio) == REQ_OP_WRITE_SAME) &&
 		     !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
 		disable_write_same(md);
 
@@ -1060,371 +857,6 @@ static void clone_endio(struct bio *bio)
 }
 
 /*
- * Partial completion handling for request-based dm
- */
-static void end_clone_bio(struct bio *clone)
-{
-	struct dm_rq_clone_bio_info *info =
-		container_of(clone, struct dm_rq_clone_bio_info, clone);
-	struct dm_rq_target_io *tio = info->tio;
-	struct bio *bio = info->orig;
-	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
-	int error = clone->bi_error;
-
-	bio_put(clone);
-
-	if (tio->error)
-		/*
-		 * An error has already been detected on the request.
-		 * Once error occurred, just let clone->end_io() handle
-		 * the remainder.
-		 */
-		return;
-	else if (error) {
-		/*
-		 * Don't notice the error to the upper layer yet.
-		 * The error handling decision is made by the target driver,
-		 * when the request is completed.
-		 */
-		tio->error = error;
-		return;
-	}
-
-	/*
-	 * I/O for the bio successfully completed.
-	 * Notice the data completion to the upper layer.
-	 */
-
-	/*
-	 * bios are processed from the head of the list.
-	 * So the completing bio should always be rq->bio.
-	 * If it's not, something wrong is happening.
-	 */
-	if (tio->orig->bio != bio)
-		DMERR("bio completion is going in the middle of the request");
-
-	/*
-	 * Update the original request.
-	 * Do not use blk_end_request() here, because it may complete
-	 * the original request before the clone, and break the ordering.
-	 */
-	blk_update_request(tio->orig, 0, nr_bytes);
-}
-
-static struct dm_rq_target_io *tio_from_request(struct request *rq)
-{
-	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
-}
-
-static void rq_end_stats(struct mapped_device *md, struct request *orig)
-{
-	if (unlikely(dm_stats_used(&md->stats))) {
-		struct dm_rq_target_io *tio = tio_from_request(orig);
-		tio->duration_jiffies = jiffies - tio->duration_jiffies;
-		dm_stats_account_io(&md->stats, orig->cmd_flags, blk_rq_pos(orig),
-				    tio->n_sectors, true, tio->duration_jiffies,
-				    &tio->stats_aux);
-	}
-}
-
-/*
- * Don't touch any member of the md after calling this function because
- * the md may be freed in dm_put() at the end of this function.
- * Or do dm_get() before calling this function and dm_put() later.
- */
-static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
-{
-	atomic_dec(&md->pending[rw]);
-
-	/* nudge anyone waiting on suspend queue */
-	if (!md_in_flight(md))
-		wake_up(&md->wait);
-
-	/*
-	 * Run this off this callpath, as drivers could invoke end_io while
-	 * inside their request_fn (and holding the queue lock). Calling
-	 * back into ->request_fn() could deadlock attempting to grab the
-	 * queue lock again.
-	 */
-	if (!md->queue->mq_ops && run_queue)
-		blk_run_queue_async(md->queue);
-
-	/*
-	 * dm_put() must be at the end of this function. See the comment above
-	 */
-	dm_put(md);
-}
-
-static void free_rq_clone(struct request *clone)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct mapped_device *md = tio->md;
-
-	blk_rq_unprep_clone(clone);
-
-	if (md->type == DM_TYPE_MQ_REQUEST_BASED)
-		/* stacked on blk-mq queue(s) */
-		tio->ti->type->release_clone_rq(clone);
-	else if (!md->queue->mq_ops)
-		/* request_fn queue stacked on request_fn queue(s) */
-		free_old_clone_request(md, clone);
-
-	if (!md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
-/*
- * Complete the clone and the original request.
- * Must be called without clone's queue lock held,
- * see end_clone_request() for more details.
- */
-static void dm_end_request(struct request *clone, int error)
-{
-	int rw = rq_data_dir(clone);
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct mapped_device *md = tio->md;
-	struct request *rq = tio->orig;
-
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		rq->errors = clone->errors;
-		rq->resid_len = clone->resid_len;
-
-		if (rq->sense)
-			/*
-			 * We are using the sense buffer of the original
-			 * request.
-			 * So setting the length of the sense data is enough.
-			 */
-			rq->sense_len = clone->sense_len;
-	}
-
-	free_rq_clone(clone);
-	rq_end_stats(md, rq);
-	if (!rq->q->mq_ops)
-		blk_end_request_all(rq, error);
-	else
-		blk_mq_end_request(rq, error);
-	rq_completed(md, rw, true);
-}
-
-static void dm_unprep_request(struct request *rq)
-{
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-	struct request *clone = tio->clone;
-
-	if (!rq->q->mq_ops) {
-		rq->special = NULL;
-		rq->cmd_flags &= ~REQ_DONTPREP;
-	}
-
-	if (clone)
-		free_rq_clone(clone);
-	else if (!tio->md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
-/*
- * Requeue the original request of a clone.
- */
-static void dm_old_requeue_request(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	blk_requeue_request(q, rq);
-	blk_run_queue_async(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_mq_requeue_request(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-	unsigned long flags;
-
-	blk_mq_requeue_request(rq);
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (!blk_queue_stopped(q))
-		blk_mq_kick_requeue_list(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_requeue_original_request(struct mapped_device *md,
-					struct request *rq)
-{
-	int rw = rq_data_dir(rq);
-
-	rq_end_stats(md, rq);
-	dm_unprep_request(rq);
-
-	if (!rq->q->mq_ops)
-		dm_old_requeue_request(rq);
-	else
-		dm_mq_requeue_request(rq);
-
-	rq_completed(md, rw, false);
-}
-
-static void dm_old_stop_queue(struct request_queue *q)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (blk_queue_stopped(q)) {
-		spin_unlock_irqrestore(q->queue_lock, flags);
-		return;
-	}
-
-	blk_stop_queue(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_stop_queue(struct request_queue *q)
-{
-	if (!q->mq_ops)
-		dm_old_stop_queue(q);
-	else
-		blk_mq_stop_hw_queues(q);
-}
-
-static void dm_old_start_queue(struct request_queue *q)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	if (blk_queue_stopped(q))
-		blk_start_queue(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_start_queue(struct request_queue *q)
-{
-	if (!q->mq_ops)
-		dm_old_start_queue(q);
-	else {
-		blk_mq_start_stopped_hw_queues(q, true);
-		blk_mq_kick_requeue_list(q);
-	}
-}
-
-static void dm_done(struct request *clone, int error, bool mapped)
-{
-	int r = error;
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	dm_request_endio_fn rq_end_io = NULL;
-
-	if (tio->ti) {
-		rq_end_io = tio->ti->type->rq_end_io;
-
-		if (mapped && rq_end_io)
-			r = rq_end_io(tio->ti, clone, error, &tio->info);
-	}
-
-	if (unlikely(r == -EREMOTEIO && (clone->cmd_flags & REQ_WRITE_SAME) &&
-		     !clone->q->limits.max_write_same_sectors))
-		disable_write_same(tio->md);
-
-	if (r <= 0)
-		/* The target wants to complete the I/O */
-		dm_end_request(clone, r);
-	else if (r == DM_ENDIO_INCOMPLETE)
-		/* The target will handle the I/O */
-		return;
-	else if (r == DM_ENDIO_REQUEUE)
-		/* The target wants to requeue the I/O */
-		dm_requeue_original_request(tio->md, tio->orig);
-	else {
-		DMWARN("unimplemented target endio return value: %d", r);
-		BUG();
-	}
-}
-
-/*
- * Request completion handler for request-based dm
- */
-static void dm_softirq_done(struct request *rq)
-{
-	bool mapped = true;
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-	struct request *clone = tio->clone;
-	int rw;
-
-	if (!clone) {
-		rq_end_stats(tio->md, rq);
-		rw = rq_data_dir(rq);
-		if (!rq->q->mq_ops) {
-			blk_end_request_all(rq, tio->error);
-			rq_completed(tio->md, rw, false);
-			free_old_rq_tio(tio);
-		} else {
-			blk_mq_end_request(rq, tio->error);
-			rq_completed(tio->md, rw, false);
-		}
-		return;
-	}
-
-	if (rq->cmd_flags & REQ_FAILED)
-		mapped = false;
-
-	dm_done(clone, tio->error, mapped);
-}
-
-/*
- * Complete the clone and the original request with the error status
- * through softirq context.
- */
-static void dm_complete_request(struct request *rq, int error)
-{
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-
-	tio->error = error;
-	if (!rq->q->mq_ops)
-		blk_complete_request(rq);
-	else
-		blk_mq_complete_request(rq, error);
-}
-
-/*
- * Complete the not-mapped clone and the original request with the error status
- * through softirq context.
- * Target's rq_end_io() function isn't called.
- * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
- */
-static void dm_kill_unmapped_request(struct request *rq, int error)
-{
-	rq->cmd_flags |= REQ_FAILED;
-	dm_complete_request(rq, error);
-}
-
-/*
- * Called with the clone's queue lock held (in the case of .request_fn)
- */
-static void end_clone_request(struct request *clone, int error)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-
-	if (!clone->q->mq_ops) {
-		/*
-		 * For just cleaning up the information of the queue in which
-		 * the clone was dispatched.
-		 * The clone is *NOT* freed actually here because it is alloced
-		 * from dm own mempool (REQ_ALLOCED isn't set).
-		 */
-		__blk_put_request(clone->q, clone);
-	}
-
-	/*
-	 * Actual request completion is done in a softirq context which doesn't
-	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
-	 *     - another request may be submitted by the upper level driver
-	 *       of the stacking during the completion
-	 *     - the submission which requires queue lock may be done
-	 *       against this clone's queue
-	 */
-	dm_complete_request(tio->orig, error);
-}
-
-/*
  * Return maximum size of I/O possible at the supplied sector up to the current
  * target boundary.
  */
@@ -1473,9 +905,36 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
 }
 EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
 
+static long dm_blk_direct_access(struct block_device *bdev, sector_t sector,
+				 void __pmem **kaddr, pfn_t *pfn, long size)
+{
+	struct mapped_device *md = bdev->bd_disk->private_data;
+	struct dm_table *map;
+	struct dm_target *ti;
+	int srcu_idx;
+	long len, ret = -EIO;
+
+	map = dm_get_live_table(md, &srcu_idx);
+	if (!map)
+		goto out;
+
+	ti = dm_table_find_target(map, sector);
+	if (!dm_target_is_valid(ti))
+		goto out;
+
+	len = max_io_len(sector, ti) << SECTOR_SHIFT;
+	size = min(len, size);
+
+	if (ti->type->direct_access)
+		ret = ti->type->direct_access(ti, sector, kaddr, pfn, size);
+out:
+	dm_put_live_table(md, srcu_idx);
+	return min(ret, size);
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
- * allowed for all bio types except REQ_FLUSH.
+ * allowed for all bio types except REQ_PREFLUSH.
  *
  * dm_accept_partial_bio informs the dm that the target only wants to process
  * additional n_sectors sectors of the bio and the rest of the data should be
@@ -1505,7 +964,7 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 {
 	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
 	unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT;
-	BUG_ON(bio->bi_rw & REQ_FLUSH);
+	BUG_ON(bio->bi_rw & REQ_PREFLUSH);
 	BUG_ON(bi_size > *tio->len_ptr);
 	BUG_ON(n_sectors > bi_size);
 	*tio->len_ptr -= bi_size - n_sectors;
@@ -1746,9 +1205,9 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 	unsigned len;
 	int r;
 
-	if (unlikely(bio->bi_rw & REQ_DISCARD))
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
 		return __send_discard(ci);
-	else if (unlikely(bio->bi_rw & REQ_WRITE_SAME))
+	else if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
 		return __send_write_same(ci);
 
 	ti = dm_table_find_target(ci->map, ci->sector);
@@ -1793,7 +1252,7 @@ static void __split_and_process_bio(struct mapped_device *md,
 
 	start_io_acct(ci.io);
 
-	if (bio->bi_rw & REQ_FLUSH) {
+	if (bio->bi_rw & REQ_PREFLUSH) {
 		ci.bio = &ci.md->flush_bio;
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
@@ -1831,7 +1290,7 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
 	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
 		dm_put_live_table(md, srcu_idx);
 
-		if (bio_rw(bio) != READA)
+		if (!(bio->bi_rw & REQ_RAHEAD))
 			queue_io(md, bio);
 		else
 			bio_io_error(bio);
@@ -1843,352 +1302,6 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
-int dm_request_based(struct mapped_device *md)
-{
-	return blk_queue_stackable(md->queue);
-}
-
-static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
-{
-	int r;
-
-	if (blk_queue_io_stat(clone->q))
-		clone->cmd_flags |= REQ_IO_STAT;
-
-	clone->start_time = jiffies;
-	r = blk_insert_cloned_request(clone->q, clone);
-	if (r)
-		/* must complete clone in terms of original request */
-		dm_complete_request(rq, r);
-}
-
-static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
-				 void *data)
-{
-	struct dm_rq_target_io *tio = data;
-	struct dm_rq_clone_bio_info *info =
-		container_of(bio, struct dm_rq_clone_bio_info, clone);
-
-	info->orig = bio_orig;
-	info->tio = tio;
-	bio->bi_end_io = end_clone_bio;
-
-	return 0;
-}
-
-static int setup_clone(struct request *clone, struct request *rq,
-		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	int r;
-
-	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
-			      dm_rq_bio_constructor, tio);
-	if (r)
-		return r;
-
-	clone->cmd = rq->cmd;
-	clone->cmd_len = rq->cmd_len;
-	clone->sense = rq->sense;
-	clone->end_io = end_clone_request;
-	clone->end_io_data = tio;
-
-	tio->clone = clone;
-
-	return 0;
-}
-
-static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
-				    struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	/*
-	 * Create clone for use with .request_fn request_queue
-	 */
-	struct request *clone;
-
-	clone = alloc_old_clone_request(md, gfp_mask);
-	if (!clone)
-		return NULL;
-
-	blk_rq_init(NULL, clone);
-	if (setup_clone(clone, rq, tio, gfp_mask)) {
-		/* -ENOMEM */
-		free_old_clone_request(md, clone);
-		return NULL;
-	}
-
-	return clone;
-}
-
-static void map_tio_request(struct kthread_work *work);
-
-static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
-		     struct mapped_device *md)
-{
-	tio->md = md;
-	tio->ti = NULL;
-	tio->clone = NULL;
-	tio->orig = rq;
-	tio->error = 0;
-	/*
-	 * Avoid initializing info for blk-mq; it passes
-	 * target-specific data through info.ptr
-	 * (see: dm_mq_init_request)
-	 */
-	if (!md->init_tio_pdu)
-		memset(&tio->info, 0, sizeof(tio->info));
-	if (md->kworker_task)
-		init_kthread_work(&tio->work, map_tio_request);
-}
-
-static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
-					       struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	struct dm_rq_target_io *tio;
-	int srcu_idx;
-	struct dm_table *table;
-
-	tio = alloc_old_rq_tio(md, gfp_mask);
-	if (!tio)
-		return NULL;
-
-	init_tio(tio, rq, md);
-
-	table = dm_get_live_table(md, &srcu_idx);
-	/*
-	 * Must clone a request if this .request_fn DM device
-	 * is stacked on .request_fn device(s).
-	 */
-	if (!dm_table_mq_request_based(table)) {
-		if (!clone_old_rq(rq, md, tio, gfp_mask)) {
-			dm_put_live_table(md, srcu_idx);
-			free_old_rq_tio(tio);
-			return NULL;
-		}
-	}
-	dm_put_live_table(md, srcu_idx);
-
-	return tio;
-}
-
-/*
- * Called with the queue lock held.
- */
-static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_rq_target_io *tio;
-
-	if (unlikely(rq->special)) {
-		DMWARN("Already has something in rq->special.");
-		return BLKPREP_KILL;
-	}
-
-	tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
-	if (!tio)
-		return BLKPREP_DEFER;
-
-	rq->special = tio;
-	rq->cmd_flags |= REQ_DONTPREP;
-
-	return BLKPREP_OK;
-}
-
-/*
- * Returns:
- * 0                : the request has been processed
- * DM_MAPIO_REQUEUE : the original request needs to be requeued
- * < 0              : the request was completed due to failure
- */
-static int map_request(struct dm_rq_target_io *tio, struct request *rq,
-		       struct mapped_device *md)
-{
-	int r;
-	struct dm_target *ti = tio->ti;
-	struct request *clone = NULL;
-
-	if (tio->clone) {
-		clone = tio->clone;
-		r = ti->type->map_rq(ti, clone, &tio->info);
-	} else {
-		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
-		if (r < 0) {
-			/* The target wants to complete the I/O */
-			dm_kill_unmapped_request(rq, r);
-			return r;
-		}
-		if (r != DM_MAPIO_REMAPPED)
-			return r;
-		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
-			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
-			return DM_MAPIO_REQUEUE;
-		}
-	}
-
-	switch (r) {
-	case DM_MAPIO_SUBMITTED:
-		/* The target has taken the I/O to submit by itself later */
-		break;
-	case DM_MAPIO_REMAPPED:
-		/* The target has remapped the I/O so dispatch it */
-		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
-				     blk_rq_pos(rq));
-		dm_dispatch_clone_request(clone, rq);
-		break;
-	case DM_MAPIO_REQUEUE:
-		/* The target wants to requeue the I/O */
-		dm_requeue_original_request(md, tio->orig);
-		break;
-	default:
-		if (r > 0) {
-			DMWARN("unimplemented target map return value: %d", r);
-			BUG();
-		}
-
-		/* The target wants to complete the I/O */
-		dm_kill_unmapped_request(rq, r);
-		return r;
-	}
-
-	return 0;
-}
-
-static void map_tio_request(struct kthread_work *work)
-{
-	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
-	struct request *rq = tio->orig;
-	struct mapped_device *md = tio->md;
-
-	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
-		dm_requeue_original_request(md, rq);
-}
-
-static void dm_start_request(struct mapped_device *md, struct request *orig)
-{
-	if (!orig->q->mq_ops)
-		blk_start_request(orig);
-	else
-		blk_mq_start_request(orig);
-	atomic_inc(&md->pending[rq_data_dir(orig)]);
-
-	if (md->seq_rq_merge_deadline_usecs) {
-		md->last_rq_pos = rq_end_sector(orig);
-		md->last_rq_rw = rq_data_dir(orig);
-		md->last_rq_start_time = ktime_get();
-	}
-
-	if (unlikely(dm_stats_used(&md->stats))) {
-		struct dm_rq_target_io *tio = tio_from_request(orig);
-		tio->duration_jiffies = jiffies;
-		tio->n_sectors = blk_rq_sectors(orig);
-		dm_stats_account_io(&md->stats, orig->cmd_flags, blk_rq_pos(orig),
-				    tio->n_sectors, false, 0, &tio->stats_aux);
-	}
-
-	/*
-	 * Hold the md reference here for the in-flight I/O.
-	 * We can't rely on the reference count by device opener,
-	 * because the device may be closed during the request completion
-	 * when all bios are completed.
-	 * See the comment in rq_completed() too.
-	 */
-	dm_get(md);
-}
-
-#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
-{
-	return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
-}
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
-						     const char *buf, size_t count)
-{
-	unsigned deadline;
-
-	if (!dm_request_based(md) || md->use_blk_mq)
-		return count;
-
-	if (kstrtouint(buf, 10, &deadline))
-		return -EINVAL;
-
-	if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
-		deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;
-
-	md->seq_rq_merge_deadline_usecs = deadline;
-
-	return count;
-}
-
-static bool dm_request_peeked_before_merge_deadline(struct mapped_device *md)
-{
-	ktime_t kt_deadline;
-
-	if (!md->seq_rq_merge_deadline_usecs)
-		return false;
-
-	kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
-	kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);
-
-	return !ktime_after(ktime_get(), kt_deadline);
-}
-
-/*
- * q->request_fn for request-based dm.
- * Called with the queue lock held.
- */
-static void dm_request_fn(struct request_queue *q)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_target *ti = md->immutable_target;
-	struct request *rq;
-	struct dm_rq_target_io *tio;
-	sector_t pos = 0;
-
-	if (unlikely(!ti)) {
-		int srcu_idx;
-		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-
-		ti = dm_table_find_target(map, pos);
-		dm_put_live_table(md, srcu_idx);
-	}
-
-	/*
-	 * For suspend, check blk_queue_stopped() and increment
-	 * ->pending within a single queue_lock not to increment the
-	 * number of in-flight I/Os after the queue is stopped in
-	 * dm_suspend().
-	 */
-	while (!blk_queue_stopped(q)) {
-		rq = blk_peek_request(q);
-		if (!rq)
-			return;
-
-		/* always use block 0 to find the target for flushes for now */
-		pos = 0;
-		if (!(rq->cmd_flags & REQ_FLUSH))
-			pos = blk_rq_pos(rq);
-
-		if ((dm_request_peeked_before_merge_deadline(md) &&
-		     md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
-		     md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
-		    (ti->type->busy && ti->type->busy(ti))) {
-			blk_delay_queue(q, HZ / 100);
-			return;
-		}
-
-		dm_start_request(md, rq);
-
-		tio = tio_from_request(rq);
-		/* Establish tio->ti before queuing work (map_tio_request) */
-		tio->ti = ti;
-		queue_kthread_work(&md->kworker, &tio->work);
-		BUG_ON(!irqs_disabled());
-	}
-}
-
 static int dm_any_congested(void *congested_data, int bdi_bits)
 {
 	int r = bdi_bits;
@@ -2266,7 +1379,7 @@ static const struct block_device_operations dm_blk_dops;
 
 static void dm_wq_work(struct work_struct *work);
 
-static void dm_init_md_queue(struct mapped_device *md)
+void dm_init_md_queue(struct mapped_device *md)
 {
 	/*
 	 * Request-based dm devices cannot be stacked on top of bio-based dm
@@ -2287,7 +1400,7 @@ static void dm_init_md_queue(struct mapped_device *md)
 	md->queue->backing_dev_info.congested_data = md;
 }
 
-static void dm_init_normal_md_queue(struct mapped_device *md)
+void dm_init_normal_md_queue(struct mapped_device *md)
 {
 	md->use_blk_mq = false;
 	dm_init_md_queue(md);
@@ -2327,6 +1440,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		bdput(md->bdev);
 		md->bdev = NULL;
 	}
+
+	dm_mq_cleanup_mapped_device(md);
 }
 
 /*
@@ -2360,7 +1475,7 @@ static struct mapped_device *alloc_dev(int minor)
 		goto bad_io_barrier;
 
 	md->numa_node_id = numa_node_id;
-	md->use_blk_mq = use_blk_mq;
+	md->use_blk_mq = dm_use_blk_mq_default();
 	md->init_tio_pdu = false;
 	md->type = DM_TYPE_NONE;
 	mutex_init(&md->suspend_lock);
@@ -2412,7 +1527,7 @@ static struct mapped_device *alloc_dev(int minor)
 
 	bio_init(&md->flush_bio);
 	md->flush_bio.bi_bdev = md->bdev;
-	md->flush_bio.bi_rw = WRITE_FLUSH;
+	bio_set_op_attrs(&md->flush_bio, REQ_OP_WRITE, WRITE_FLUSH);
 
 	dm_stats_init(&md->stats);
 
@@ -2445,10 +1560,6 @@ static void free_dev(struct mapped_device *md)
 	unlock_fs(md);
 
 	cleanup_mapped_device(md);
-	if (md->tag_set) {
-		blk_mq_free_tag_set(md->tag_set);
-		kfree(md->tag_set);
-	}
 
 	free_table_devices(&md->table_devices);
 	dm_stats_cleanup(&md->stats);
@@ -2464,7 +1575,7 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 
 	if (md->bs) {
 		/* The md already has necessary mempools. */
-		if (dm_table_get_type(t) == DM_TYPE_BIO_BASED) {
+		if (dm_table_bio_based(t)) {
 			/*
 			 * Reload bioset because front_pad may have changed
 			 * because a different table was loaded.
@@ -2654,176 +1765,15 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_get_queue_limits);
 
-static void dm_old_init_rq_based_worker_thread(struct mapped_device *md)
-{
-	/* Initialize the request-based DM worker thread */
-	init_kthread_worker(&md->kworker);
-	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
-				       "kdmwork-%s", dm_device_name(md));
-}
-
-/*
- * Fully initialize a .request_fn request-based queue.
- */
-static int dm_old_init_request_queue(struct mapped_device *md)
-{
-	/* Fully initialize the queue */
-	if (!blk_init_allocated_queue(md->queue, dm_request_fn, NULL))
-		return -EINVAL;
-
-	/* disable dm_request_fn's merge heuristic by default */
-	md->seq_rq_merge_deadline_usecs = 0;
-
-	dm_init_normal_md_queue(md);
-	blk_queue_softirq_done(md->queue, dm_softirq_done);
-	blk_queue_prep_rq(md->queue, dm_old_prep_fn);
-
-	dm_old_init_rq_based_worker_thread(md);
-
-	elv_register_queue(md->queue);
-
-	return 0;
-}
-
-static int dm_mq_init_request(void *data, struct request *rq,
-			      unsigned int hctx_idx, unsigned int request_idx,
-			      unsigned int numa_node)
-{
-	struct mapped_device *md = data;
-	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-
-	/*
-	 * Must initialize md member of tio, otherwise it won't
-	 * be available in dm_mq_queue_rq.
-	 */
-	tio->md = md;
-
-	if (md->init_tio_pdu) {
-		/* target-specific per-io data is immediately after the tio */
-		tio->info.ptr = tio + 1;
-	}
-
-	return 0;
-}
-
-static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
-			  const struct blk_mq_queue_data *bd)
-{
-	struct request *rq = bd->rq;
-	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-	struct mapped_device *md = tio->md;
-	struct dm_target *ti = md->immutable_target;
-
-	if (unlikely(!ti)) {
-		int srcu_idx;
-		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-
-		ti = dm_table_find_target(map, 0);
-		dm_put_live_table(md, srcu_idx);
-	}
-
-	if (ti->type->busy && ti->type->busy(ti))
-		return BLK_MQ_RQ_QUEUE_BUSY;
-
-	dm_start_request(md, rq);
-
-	/* Init tio using md established in .init_request */
-	init_tio(tio, rq, md);
-
-	/*
-	 * Establish tio->ti before queuing work (map_tio_request)
-	 * or making direct call to map_request().
-	 */
-	tio->ti = ti;
-
-	/* Direct call is fine since .queue_rq allows allocations */
-	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
-		/* Undo dm_start_request() before requeuing */
-		rq_end_stats(md, rq);
-		rq_completed(md, rq_data_dir(rq), false);
-		return BLK_MQ_RQ_QUEUE_BUSY;
-	}
-
-	return BLK_MQ_RQ_QUEUE_OK;
-}
-
-static struct blk_mq_ops dm_mq_ops = {
-	.queue_rq = dm_mq_queue_rq,
-	.map_queue = blk_mq_map_queue,
-	.complete = dm_softirq_done,
-	.init_request = dm_mq_init_request,
-};
-
-static int dm_mq_init_request_queue(struct mapped_device *md,
-				    struct dm_target *immutable_tgt)
-{
-	struct request_queue *q;
-	int err;
-
-	if (dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) {
-		DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
-		return -EINVAL;
-	}
-
-	md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
-	if (!md->tag_set)
-		return -ENOMEM;
-
-	md->tag_set->ops = &dm_mq_ops;
-	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
-	md->tag_set->numa_node = md->numa_node_id;
-	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
-	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
-	md->tag_set->driver_data = md;
-
-	md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
-	if (immutable_tgt && immutable_tgt->per_io_data_size) {
-		/* any target-specific per-io data is immediately after the tio */
-		md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
-		md->init_tio_pdu = true;
-	}
-
-	err = blk_mq_alloc_tag_set(md->tag_set);
-	if (err)
-		goto out_kfree_tag_set;
-
-	q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
-	if (IS_ERR(q)) {
-		err = PTR_ERR(q);
-		goto out_tag_set;
-	}
-	dm_init_md_queue(md);
-
-	/* backfill 'mq' sysfs registration normally done in blk_register_queue */
-	blk_mq_register_disk(md->disk);
-
-	return 0;
-
-out_tag_set:
-	blk_mq_free_tag_set(md->tag_set);
-out_kfree_tag_set:
-	kfree(md->tag_set);
-
-	return err;
-}
-
-static unsigned filter_md_type(unsigned type, struct mapped_device *md)
-{
-	if (type == DM_TYPE_BIO_BASED)
-		return type;
-
-	return !md->use_blk_mq ? DM_TYPE_REQUEST_BASED : DM_TYPE_MQ_REQUEST_BASED;
-}
-
 /*
  * Setup the DM device's queue based on md's type
  */
 int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 {
 	int r;
-	unsigned md_type = filter_md_type(dm_get_md_type(md), md);
+	unsigned type = dm_get_md_type(md);
 
-	switch (md_type) {
+	switch (type) {
 	case DM_TYPE_REQUEST_BASED:
 		r = dm_old_init_request_queue(md);
 		if (r) {
@@ -2832,13 +1782,14 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 		}
 		break;
 	case DM_TYPE_MQ_REQUEST_BASED:
-		r = dm_mq_init_request_queue(md, dm_table_get_immutable_target(t));
+		r = dm_mq_init_request_queue(md, t);
 		if (r) {
 			DMERR("Cannot initialize queue for request-based dm-mq mapped device");
 			return r;
 		}
 		break;
 	case DM_TYPE_BIO_BASED:
+	case DM_TYPE_DAX_BIO_BASED:
 		dm_init_normal_md_queue(md);
 		blk_queue_make_request(md->queue, dm_make_request);
 		/*
@@ -2847,6 +1798,9 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 		 */
 		bioset_free(md->queue->bio_split);
 		md->queue->bio_split = NULL;
+
+		if (type == DM_TYPE_DAX_BIO_BASED)
+			queue_flag_set_unlocked(QUEUE_FLAG_DAX, md->queue);
 		break;
 	}
 
@@ -3541,10 +2495,9 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 	if (!pools)
 		return NULL;
 
-	type = filter_md_type(type, md);
-
 	switch (type) {
 	case DM_TYPE_BIO_BASED:
+	case DM_TYPE_DAX_BIO_BASED:
 		cachep = _io_cache;
 		pool_size = dm_get_reserved_bio_based_ios();
 		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
@@ -3601,26 +2554,76 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
 	kfree(pools);
 }
 
-static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
-			  u32 flags)
+struct dm_pr {
+	u64	old_key;
+	u64	new_key;
+	u32	flags;
+	bool	fail_early;
+};
+
+static int dm_call_pr(struct block_device *bdev, iterate_devices_callout_fn fn,
+		      void *data)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
-	const struct pr_ops *ops;
-	fmode_t mode;
-	int r;
+	struct dm_table *table;
+	struct dm_target *ti;
+	int ret = -ENOTTY, srcu_idx;
 
-	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
-	if (r < 0)
-		return r;
+	table = dm_get_live_table(md, &srcu_idx);
+	if (!table || !dm_table_get_size(table))
+		goto out;
 
-	ops = bdev->bd_disk->fops->pr_ops;
-	if (ops && ops->pr_register)
-		r = ops->pr_register(bdev, old_key, new_key, flags);
-	else
-		r = -EOPNOTSUPP;
+	/* We only support devices that have a single target */
+	if (dm_table_get_num_targets(table) != 1)
+		goto out;
+	ti = dm_table_get_target(table, 0);
 
-	bdput(bdev);
-	return r;
+	ret = -EINVAL;
+	if (!ti->type->iterate_devices)
+		goto out;
+
+	ret = ti->type->iterate_devices(ti, fn, data);
+out:
+	dm_put_live_table(md, srcu_idx);
+	return ret;
+}
+
+/*
+ * For register / unregister we need to manually call out to every path.
+ */
+static int __dm_pr_register(struct dm_target *ti, struct dm_dev *dev,
+			    sector_t start, sector_t len, void *data)
+{
+	struct dm_pr *pr = data;
+	const struct pr_ops *ops = dev->bdev->bd_disk->fops->pr_ops;
+
+	if (!ops || !ops->pr_register)
+		return -EOPNOTSUPP;
+	return ops->pr_register(dev->bdev, pr->old_key, pr->new_key, pr->flags);
+}
+
+static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+			  u32 flags)
+{
+	struct dm_pr pr = {
+		.old_key	= old_key,
+		.new_key	= new_key,
+		.flags		= flags,
+		.fail_early	= true,
+	};
+	int ret;
+
+	ret = dm_call_pr(bdev, __dm_pr_register, &pr);
+	if (ret && new_key) {
+		/* unregister all paths if we failed to register any path */
+		pr.old_key = new_key;
+		pr.new_key = 0;
+		pr.flags = 0;
+		pr.fail_early = false;
+		dm_call_pr(bdev, __dm_pr_register, &pr);
+	}
+
+	return ret;
 }
 
 static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
@@ -3721,6 +2724,7 @@ static const struct block_device_operations dm_blk_dops = {
 	.open = dm_blk_open,
 	.release = dm_blk_close,
 	.ioctl = dm_blk_ioctl,
+	.direct_access = dm_blk_direct_access,
 	.getgeo = dm_blk_getgeo,
 	.pr_ops = &dm_pr_ops,
 	.owner = THIS_MODULE
@@ -3738,18 +2742,6 @@ MODULE_PARM_DESC(major, "The major number of the device mapper");
 module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");
 
-module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
-
-module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
-
-module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");
-
-module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");
-
 module_param(dm_numa_node, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(dm_numa_node, "NUMA node for DM device memory allocations");
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 13a758ec0f88..f0aad08b9654 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -13,6 +13,7 @@
 #include <linux/fs.h>
 #include <linux/device-mapper.h>
 #include <linux/list.h>
+#include <linux/moduleparam.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/hdreg.h>
@@ -33,14 +34,6 @@
 #define DM_STATUS_NOFLUSH_FLAG		(1 << 0)
 
 /*
- * Type of table and mapped_device's mempool
- */
-#define DM_TYPE_NONE			0
-#define DM_TYPE_BIO_BASED		1
-#define DM_TYPE_REQUEST_BASED		2
-#define DM_TYPE_MQ_REQUEST_BASED	3
-
-/*
  * List of devices that a metadevice uses and should open/close.
  */
 struct dm_dev_internal {
@@ -75,8 +68,9 @@ unsigned dm_table_get_type(struct dm_table *t);
 struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
 struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
 struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
+bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
-bool dm_table_mq_request_based(struct dm_table *t);
+bool dm_table_all_blk_mq_devices(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
 
@@ -161,16 +155,6 @@ void dm_interface_exit(void);
 /*
  * sysfs interface
  */
-struct dm_kobject_holder {
-	struct kobject kobj;
-	struct completion completion;
-};
-
-static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
-{
-	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
-}
-
 int dm_sysfs_init(struct mapped_device *md);
 void dm_sysfs_exit(struct mapped_device *md);
 struct kobject *dm_kobject(struct mapped_device *md);
@@ -212,8 +196,6 @@ int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
 void dm_internal_suspend(struct mapped_device *md);
 void dm_internal_resume(struct mapped_device *md);
 
-bool dm_use_blk_mq(struct mapped_device *md);
-
 int dm_io_init(void);
 void dm_io_exit(void);
 
@@ -228,18 +210,8 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
 /*
- * Helpers that are used by DM core
+ * Various helpers
  */
 unsigned dm_get_reserved_bio_based_ios(void);
-unsigned dm_get_reserved_rq_based_ios(void);
-
-static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
-{
-	return !maxlen || strlen(result) + 1 >= maxlen;
-}
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf);
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
-						     const char *buf, size_t count);
 
 #endif
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index b7fe7e9fc777..70ff888d25d0 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -221,7 +221,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 	struct bio *split;
 	sector_t start_sector, end_sector, data_offset;
 
-	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+	if (unlikely(bio->bi_rw & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
@@ -252,7 +252,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 		split->bi_iter.bi_sector = split->bi_iter.bi_sector -
 			start_sector + data_offset;
 
-		if (unlikely((split->bi_rw & REQ_DISCARD) &&
+		if (unlikely((bio_op(split) == REQ_OP_DISCARD) &&
 			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
 			/* Just ignore it */
 			bio_endio(split);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 866825f10b4c..1f123f5a29da 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -394,8 +394,9 @@ static void submit_flushes(struct work_struct *ws)
 			bi->bi_end_io = md_end_flush;
 			bi->bi_private = rdev;
 			bi->bi_bdev = rdev->bdev;
+			bio_set_op_attrs(bi, REQ_OP_WRITE, WRITE_FLUSH);
 			atomic_inc(&mddev->flush_pending);
-			submit_bio(WRITE_FLUSH, bi);
+			submit_bio(bi);
 			rcu_read_lock();
 			rdev_dec_pending(rdev, mddev);
 		}
@@ -413,7 +414,7 @@ static void md_submit_flush_data(struct work_struct *ws)
 		/* an empty barrier - all done */
 		bio_endio(bio);
 	else {
-		bio->bi_rw &= ~REQ_FLUSH;
+		bio->bi_rw &= ~REQ_PREFLUSH;
 		mddev->pers->make_request(mddev, bio);
 	}
 
@@ -742,9 +743,10 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 	bio_add_page(bio, page, size, 0);
 	bio->bi_private = rdev;
 	bio->bi_end_io = super_written;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH_FUA);
 
 	atomic_inc(&mddev->pending_writes);
-	submit_bio(WRITE_FLUSH_FUA, bio);
+	submit_bio(bio);
 }
 
 void md_super_wait(struct mddev *mddev)
@@ -754,13 +756,14 @@ void md_super_wait(struct mddev *mddev)
 }
 
 int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
-		 struct page *page, int rw, bool metadata_op)
+		 struct page *page, int op, int op_flags, bool metadata_op)
 {
 	struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, rdev->mddev);
 	int ret;
 
 	bio->bi_bdev = (metadata_op && rdev->meta_bdev) ?
 		rdev->meta_bdev : rdev->bdev;
+	bio_set_op_attrs(bio, op, op_flags);
 	if (metadata_op)
 		bio->bi_iter.bi_sector = sector + rdev->sb_start;
 	else if (rdev->mddev->reshape_position != MaxSector &&
@@ -770,7 +773,8 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 	else
 		bio->bi_iter.bi_sector = sector + rdev->data_offset;
 	bio_add_page(bio, page, size, 0);
-	submit_bio_wait(rw, bio);
+
+	submit_bio_wait(bio);
 
 	ret = !bio->bi_error;
 	bio_put(bio);
@@ -785,7 +789,7 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
 	if (rdev->sb_loaded)
 		return 0;
 
-	if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, true))
+	if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, 0, true))
 		goto fail;
 	rdev->sb_loaded = 1;
 	return 0;
@@ -1471,7 +1475,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 			return -EINVAL;
 		bb_sector = (long long)offset;
 		if (!sync_page_io(rdev, bb_sector, sectors << 9,
-				  rdev->bb_page, READ, true))
+				  rdev->bb_page, REQ_OP_READ, 0, true))
 			return -EIO;
 		bbp = (u64 *)page_address(rdev->bb_page);
 		rdev->badblocks.shift = sb->bblog_shift;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b5c4be73e6e4..b4f335245bd6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -424,7 +424,7 @@ struct mddev {
 
 	/* Generic flush handling.
 	 * The last to finish preflush schedules a worker to submit
-	 * the rest of the request (without the REQ_FLUSH flag).
+	 * the rest of the request (without the REQ_PREFLUSH flag).
 	 */
 	struct bio *flush_bio;
 	atomic_t flush_pending;
@@ -618,7 +618,8 @@ extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
 extern void md_super_wait(struct mddev *mddev);
 extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
-			struct page *page, int rw, bool metadata_op);
+			struct page *page, int op, int op_flags,
+			bool metadata_op);
 extern void md_do_sync(struct md_thread *thread);
 extern void md_new_event(struct mddev *mddev);
 extern int md_allow_write(struct mddev *mddev);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index dd483bb2e111..72ea98e89e57 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -111,7 +111,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
-	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+	if (unlikely(bio->bi_rw & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index ea3d3b656fd0..2cc1877804c2 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -429,7 +429,14 @@ static int dm_btree_lookup_next_single(struct dm_btree_info *info, dm_block_t ro
 
 	if (flags & INTERNAL_NODE) {
 		i = lower_bound(n, key);
-		if (i < 0 || i >= nr_entries) {
+		if (i < 0) {
+			/*
+			 * avoid early -ENODATA return when all entries are
+			 * higher than the search @key.
+			 */
+			i = 0;
+		}
+		if (i >= nr_entries) {
 			r = -ENODATA;
 			goto out;
 		}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 34783a3c8b3c..c3d439083212 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -458,7 +458,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 	struct md_rdev *tmp_dev;
 	struct bio *split;
 
-	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+	if (unlikely(bio->bi_rw & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
@@ -488,7 +488,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 		split->bi_iter.bi_sector = sector + zone->dev_start +
 			tmp_dev->data_offset;
 
-		if (unlikely((split->bi_rw & REQ_DISCARD) &&
+		if (unlikely((bio_op(split) == REQ_OP_DISCARD) &&
 			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
 			/* Just ignore it */
 			bio_endio(split);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index c7c8cde0ab21..4e6da4497553 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -759,7 +759,7 @@ static void flush_pending_writes(struct r1conf *conf)
 		while (bio) { /* submit pending writes */
 			struct bio *next = bio->bi_next;
 			bio->bi_next = NULL;
-			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+			if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
 				bio_endio(bio);
@@ -1033,7 +1033,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
 		bio->bi_next = NULL;
-		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+		if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
 			bio_endio(bio);
@@ -1053,12 +1053,11 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio)
 	int i, disks;
 	struct bitmap *bitmap;
 	unsigned long flags;
+	const int op = bio_op(bio);
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
-	const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
-	const unsigned long do_discard = (bio->bi_rw
-					  & (REQ_DISCARD | REQ_SECURE));
-	const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
+	const unsigned long do_flush_fua = (bio->bi_rw &
+						(REQ_PREFLUSH | REQ_FUA));
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
 	struct raid1_plug_cb *plug = NULL;
@@ -1106,7 +1105,7 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio)
 	bitmap = mddev->bitmap;
 
 	/*
-	 * make_request() can abort the operation when READA is being
+	 * make_request() can abort the operation when read-ahead is being
 	 * used and no empty request is available.
 	 *
 	 */
@@ -1166,7 +1165,7 @@ read_again:
 			mirror->rdev->data_offset;
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = raid1_end_read_request;
-		read_bio->bi_rw = READ | do_sync;
+		bio_set_op_attrs(read_bio, op, do_sync);
 		read_bio->bi_private = r1_bio;
 
 		if (max_sectors < r1_bio->sectors) {
@@ -1376,8 +1375,7 @@ read_again:
 				   conf->mirrors[i].rdev->data_offset);
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		mbio->bi_rw =
-			WRITE | do_flush_fua | do_sync | do_discard | do_same;
+		bio_set_op_attrs(mbio, op, do_flush_fua | do_sync);
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
@@ -1771,7 +1769,7 @@ static void end_sync_write(struct bio *bio)
 static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
 			    int sectors, struct page *page, int rw)
 {
-	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
+	if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
 		/* success */
 		return 1;
 	if (rw == WRITE) {
@@ -1825,7 +1823,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 				rdev = conf->mirrors[d].rdev;
 				if (sync_page_io(rdev, sect, s<<9,
 						 bio->bi_io_vec[idx].bv_page,
-						 READ, false)) {
+						 REQ_OP_READ, 0, false)) {
 					success = 1;
 					break;
 				}
@@ -2030,7 +2028,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 		      !test_bit(MD_RECOVERY_SYNC, &mddev->recovery))))
 			continue;
 
-		wbio->bi_rw = WRITE;
+		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
 		wbio->bi_end_io = end_sync_write;
 		atomic_inc(&r1_bio->remaining);
 		md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
@@ -2090,7 +2088,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			    is_badblock(rdev, sect, s,
 					&first_bad, &bad_sectors) == 0 &&
 			    sync_page_io(rdev, sect, s<<9,
-					 conf->tmppage, READ, false))
+					 conf->tmppage, REQ_OP_READ, 0, false))
 				success = 1;
 			else {
 				d++;
@@ -2201,14 +2199,15 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 			wbio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
 		}
 
-		wbio->bi_rw = WRITE;
+		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
 		wbio->bi_iter.bi_sector = r1_bio->sector;
 		wbio->bi_iter.bi_size = r1_bio->sectors << 9;
 
 		bio_trim(wbio, sector - r1_bio->sector, sectors);
 		wbio->bi_iter.bi_sector += rdev->data_offset;
 		wbio->bi_bdev = rdev->bdev;
-		if (submit_bio_wait(WRITE, wbio) < 0)
+
+		if (submit_bio_wait(wbio) < 0)
 			/* failure! */
 			ok = rdev_set_badblocks(rdev, sector,
 						sectors, 0)
@@ -2343,7 +2342,7 @@ read_more:
 		bio->bi_iter.bi_sector = r1_bio->sector + rdev->data_offset;
 		bio->bi_bdev = rdev->bdev;
 		bio->bi_end_io = raid1_end_read_request;
-		bio->bi_rw = READ | do_sync;
+		bio_set_op_attrs(bio, REQ_OP_READ, do_sync);
 		bio->bi_private = r1_bio;
 		if (max_sectors < r1_bio->sectors) {
 			/* Drat - have to split this up more */
@@ -2571,7 +2570,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (i < conf->raid_disks)
 				still_degraded = 1;
 		} else if (!test_bit(In_sync, &rdev->flags)) {
-			bio->bi_rw = WRITE;
+			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			bio->bi_end_io = end_sync_write;
 			write_targets ++;
 		} else {
@@ -2598,7 +2597,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 					if (disk < 0)
 						disk = i;
 				}
-				bio->bi_rw = READ;
+				bio_set_op_attrs(bio, REQ_OP_READ, 0);
 				bio->bi_end_io = end_sync_read;
 				read_targets++;
 			} else if (!test_bit(WriteErrorSeen, &rdev->flags) &&
@@ -2610,7 +2609,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 				 * if we are doing resync or repair. Otherwise, leave
 				 * this device alone for this sync request.
 				 */
-				bio->bi_rw = WRITE;
+				bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 				bio->bi_end_io = end_sync_write;
 				write_targets++;
 			}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c7de2a53e625..26ae74fd0d01 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -865,7 +865,7 @@ static void flush_pending_writes(struct r10conf *conf)
 		while (bio) { /* submit pending writes */
 			struct bio *next = bio->bi_next;
 			bio->bi_next = NULL;
-			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+			if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
 				bio_endio(bio);
@@ -1041,7 +1041,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
 		bio->bi_next = NULL;
-		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+		if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
 			bio_endio(bio);
@@ -1058,12 +1058,10 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	struct r10bio *r10_bio;
 	struct bio *read_bio;
 	int i;
+	const int op = bio_op(bio);
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
 	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
-	const unsigned long do_discard = (bio->bi_rw
-					  & (REQ_DISCARD | REQ_SECURE));
-	const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
@@ -1156,7 +1154,7 @@ read_again:
 			choose_data_offset(r10_bio, rdev);
 		read_bio->bi_bdev = rdev->bdev;
 		read_bio->bi_end_io = raid10_end_read_request;
-		read_bio->bi_rw = READ | do_sync;
+		bio_set_op_attrs(read_bio, op, do_sync);
 		read_bio->bi_private = r10_bio;
 
 		if (max_sectors < r10_bio->sectors) {
@@ -1363,8 +1361,7 @@ retry_write:
 							      rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
-			mbio->bi_rw =
-				WRITE | do_sync | do_fua | do_discard | do_same;
+			bio_set_op_attrs(mbio, op, do_sync | do_fua);
 			mbio->bi_private = r10_bio;
 
 			atomic_inc(&r10_bio->remaining);
@@ -1406,8 +1403,7 @@ retry_write:
 						   r10_bio, rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
-			mbio->bi_rw =
-				WRITE | do_sync | do_fua | do_discard | do_same;
+			bio_set_op_attrs(mbio, op, do_sync | do_fua);
 			mbio->bi_private = r10_bio;
 
 			atomic_inc(&r10_bio->remaining);
@@ -1450,7 +1446,7 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
 
 	struct bio *split;
 
-	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+	if (unlikely(bio->bi_rw & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
@@ -1992,10 +1988,10 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 
 		tbio->bi_vcnt = vcnt;
 		tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
-		tbio->bi_rw = WRITE;
 		tbio->bi_private = r10_bio;
 		tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
 		tbio->bi_end_io = end_sync_write;
+		bio_set_op_attrs(tbio, REQ_OP_WRITE, 0);
 
 		bio_copy_data(tbio, fbio);
 
@@ -2078,7 +2074,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
 				  addr,
 				  s << 9,
 				  bio->bi_io_vec[idx].bv_page,
-				  READ, false);
+				  REQ_OP_READ, 0, false);
 		if (ok) {
 			rdev = conf->mirrors[dw].rdev;
 			addr = r10_bio->devs[1].addr + sect;
@@ -2086,7 +2082,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
 					  addr,
 					  s << 9,
 					  bio->bi_io_vec[idx].bv_page,
-					  WRITE, false);
+					  REQ_OP_WRITE, 0, false);
 			if (!ok) {
 				set_bit(WriteErrorSeen, &rdev->flags);
 				if (!test_and_set_bit(WantReplacement,
@@ -2213,7 +2209,7 @@ static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
 	    && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags)))
 		return -1;
-	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
+	if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
 		/* success */
 		return 1;
 	if (rw == WRITE) {
@@ -2299,7 +2295,8 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 						       r10_bio->devs[sl].addr +
 						       sect,
 						       s<<9,
-						       conf->tmppage, READ, false);
+						       conf->tmppage,
+						       REQ_OP_READ, 0, false);
 				rdev_dec_pending(rdev, mddev);
 				rcu_read_lock();
 				if (success)
@@ -2474,7 +2471,9 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 				   choose_data_offset(r10_bio, rdev) +
 				   (sector - r10_bio->sector));
 		wbio->bi_bdev = rdev->bdev;
-		if (submit_bio_wait(WRITE, wbio) < 0)
+		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
+
+		if (submit_bio_wait(wbio) < 0)
 			/* Failure! */
 			ok = rdev_set_badblocks(rdev, sector,
 						sectors, 0)
@@ -2548,7 +2547,7 @@ read_more:
 	bio->bi_iter.bi_sector = r10_bio->devs[slot].addr
 		+ choose_data_offset(r10_bio, rdev);
 	bio->bi_bdev = rdev->bdev;
-	bio->bi_rw = READ | do_sync;
+	bio_set_op_attrs(bio, REQ_OP_READ, do_sync);
 	bio->bi_private = r10_bio;
 	bio->bi_end_io = raid10_end_read_request;
 	if (max_sectors < r10_bio->sectors) {
@@ -3038,7 +3037,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				biolist = bio;
 				bio->bi_private = r10_bio;
 				bio->bi_end_io = end_sync_read;
-				bio->bi_rw = READ;
+				bio_set_op_attrs(bio, REQ_OP_READ, 0);
 				from_addr = r10_bio->devs[j].addr;
 				bio->bi_iter.bi_sector = from_addr +
 					rdev->data_offset;
@@ -3064,7 +3063,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 					biolist = bio;
 					bio->bi_private = r10_bio;
 					bio->bi_end_io = end_sync_write;
-					bio->bi_rw = WRITE;
+					bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 					bio->bi_iter.bi_sector = to_addr
 						+ rdev->data_offset;
 					bio->bi_bdev = rdev->bdev;
@@ -3093,7 +3092,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				biolist = bio;
 				bio->bi_private = r10_bio;
 				bio->bi_end_io = end_sync_write;
-				bio->bi_rw = WRITE;
+				bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 				bio->bi_iter.bi_sector = to_addr +
 					rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
@@ -3213,7 +3212,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			biolist = bio;
 			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_read;
-			bio->bi_rw = READ;
+			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 			bio->bi_iter.bi_sector = sector +
 				conf->mirrors[d].rdev->data_offset;
 			bio->bi_bdev = conf->mirrors[d].rdev->bdev;
@@ -3235,7 +3234,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			biolist = bio;
 			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_write;
-			bio->bi_rw = WRITE;
+			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			bio->bi_iter.bi_sector = sector +
 				conf->mirrors[d].replacement->data_offset;
 			bio->bi_bdev = conf->mirrors[d].replacement->bdev;
@@ -4320,7 +4319,7 @@ read_more:
 			       + rdev->data_offset);
 	read_bio->bi_private = r10_bio;
 	read_bio->bi_end_io = end_sync_read;
-	read_bio->bi_rw = READ;
+	bio_set_op_attrs(read_bio, REQ_OP_READ, 0);
 	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
 	read_bio->bi_error = 0;
 	read_bio->bi_vcnt = 0;
@@ -4354,7 +4353,7 @@ read_more:
 			rdev2->new_data_offset;
 		b->bi_private = r10_bio;
 		b->bi_end_io = end_reshape_write;
-		b->bi_rw = WRITE;
+		bio_set_op_attrs(b, REQ_OP_WRITE, 0);
 		b->bi_next = blist;
 		blist = b;
 	}
@@ -4522,7 +4521,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
 					       addr,
 					       s << 9,
 					       bvec[idx].bv_page,
-					       READ, false);
+					       REQ_OP_READ, 0, false);
 			if (success)
 				break;
 		failed:
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index e889e2deb7b3..5504ce2bac06 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -254,14 +254,14 @@ static void r5l_submit_current_io(struct r5l_log *log)
 	__r5l_set_io_unit_state(io, IO_UNIT_IO_START);
 	spin_unlock_irqrestore(&log->io_list_lock, flags);
 
-	submit_bio(WRITE, io->current_bio);
+	submit_bio(io->current_bio);
 }
 
 static struct bio *r5l_bio_alloc(struct r5l_log *log)
 {
 	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, log->bs);
 
-	bio->bi_rw = WRITE;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	bio->bi_bdev = log->rdev->bdev;
 	bio->bi_iter.bi_sector = log->rdev->data_offset + log->log_start;
 
@@ -373,7 +373,7 @@ static void r5l_append_payload_page(struct r5l_log *log, struct page *page)
 		io->current_bio = r5l_bio_alloc(log);
 		bio_chain(io->current_bio, prev);
 
-		submit_bio(WRITE, prev);
+		submit_bio(prev);
 	}
 
 	if (!bio_add_page(io->current_bio, page, PAGE_SIZE, 0))
@@ -536,7 +536,7 @@ int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio)
 		bio_endio(bio);
 		return 0;
 	}
-	bio->bi_rw &= ~REQ_FLUSH;
+	bio->bi_rw &= ~REQ_PREFLUSH;
 	return -EAGAIN;
 }
 
@@ -686,7 +686,8 @@ void r5l_flush_stripe_to_raid(struct r5l_log *log)
 	bio_reset(&log->flush_bio);
 	log->flush_bio.bi_bdev = log->rdev->bdev;
 	log->flush_bio.bi_end_io = r5l_log_flush_endio;
-	submit_bio(WRITE_FLUSH, &log->flush_bio);
+	bio_set_op_attrs(&log->flush_bio, REQ_OP_WRITE, WRITE_FLUSH);
+	submit_bio(&log->flush_bio);
 }
 
 static void r5l_write_super(struct r5l_log *log, sector_t cp);
@@ -881,7 +882,8 @@ static int r5l_read_meta_block(struct r5l_log *log,
 	struct r5l_meta_block *mb;
 	u32 crc, stored_crc;
 
-	if (!sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, READ, false))
+	if (!sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, REQ_OP_READ, 0,
+			  false))
 		return -EIO;
 
 	mb = page_address(page);
@@ -926,7 +928,8 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
 					     &disk_index, sh);
 
 			sync_page_io(log->rdev, *log_offset, PAGE_SIZE,
-				     sh->dev[disk_index].page, READ, false);
+				     sh->dev[disk_index].page, REQ_OP_READ, 0,
+				     false);
 			sh->dev[disk_index].log_checksum =
 				le32_to_cpu(payload->checksum[0]);
 			set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
@@ -934,7 +937,8 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
 		} else {
 			disk_index = sh->pd_idx;
 			sync_page_io(log->rdev, *log_offset, PAGE_SIZE,
-				     sh->dev[disk_index].page, READ, false);
+				     sh->dev[disk_index].page, REQ_OP_READ, 0,
+				     false);
 			sh->dev[disk_index].log_checksum =
 				le32_to_cpu(payload->checksum[0]);
 			set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
@@ -944,7 +948,7 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
 				sync_page_io(log->rdev,
 					     r5l_ring_add(log, *log_offset, BLOCK_SECTORS),
 					     PAGE_SIZE, sh->dev[disk_index].page,
-					     READ, false);
+					     REQ_OP_READ, 0, false);
 				sh->dev[disk_index].log_checksum =
 					le32_to_cpu(payload->checksum[1]);
 				set_bit(R5_Wantwrite,
@@ -986,11 +990,13 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
 		rdev = rcu_dereference(conf->disks[disk_index].rdev);
 		if (rdev)
 			sync_page_io(rdev, stripe_sect, PAGE_SIZE,
-				     sh->dev[disk_index].page, WRITE, false);
+				     sh->dev[disk_index].page, REQ_OP_WRITE, 0,
+				     false);
 		rrdev = rcu_dereference(conf->disks[disk_index].replacement);
 		if (rrdev)
 			sync_page_io(rrdev, stripe_sect, PAGE_SIZE,
-				     sh->dev[disk_index].page, WRITE, false);
+				     sh->dev[disk_index].page, REQ_OP_WRITE, 0,
+				     false);
 	}
 	raid5_release_stripe(sh);
 	return 0;
@@ -1062,7 +1068,8 @@ static int r5l_log_write_empty_meta_block(struct r5l_log *log, sector_t pos,
 	crc = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
 	mb->checksum = cpu_to_le32(crc);
 
-	if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, WRITE_FUA, false)) {
+	if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE,
+			  WRITE_FUA, false)) {
 		__free_page(page);
 		return -EIO;
 	}
@@ -1137,7 +1144,7 @@ static int r5l_load_log(struct r5l_log *log)
 	if (!page)
 		return -ENOMEM;
 
-	if (!sync_page_io(rdev, cp, PAGE_SIZE, page, READ, false)) {
+	if (!sync_page_io(rdev, cp, PAGE_SIZE, page, REQ_OP_READ, 0, false)) {
 		ret = -EIO;
 		goto ioerr;
 	}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8959e6dd31dd..6953d78297b0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -806,7 +806,8 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 	dd_idx = 0;
 	while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
 		dd_idx++;
-	if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw)
+	if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw ||
+	    bio_op(head->dev[dd_idx].towrite) != bio_op(sh->dev[dd_idx].towrite))
 		goto unlock_out;
 
 	if (head->batch_head) {
@@ -891,29 +892,28 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 	if (r5l_write_stripe(conf->log, sh) == 0)
 		return;
 	for (i = disks; i--; ) {
-		int rw;
+		int op, op_flags = 0;
 		int replace_only = 0;
 		struct bio *bi, *rbi;
 		struct md_rdev *rdev, *rrdev = NULL;
 
 		sh = head_sh;
 		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
+			op = REQ_OP_WRITE;
 			if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
-				rw = WRITE_FUA;
-			else
-				rw = WRITE;
+				op_flags = WRITE_FUA;
 			if (test_bit(R5_Discard, &sh->dev[i].flags))
-				rw |= REQ_DISCARD;
+				op = REQ_OP_DISCARD;
 		} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
-			rw = READ;
+			op = REQ_OP_READ;
 		else if (test_and_clear_bit(R5_WantReplace,
 					    &sh->dev[i].flags)) {
-			rw = WRITE;
+			op = REQ_OP_WRITE;
 			replace_only = 1;
 		} else
 			continue;
 		if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags))
-			rw |= REQ_SYNC;
+			op_flags |= REQ_SYNC;
 
 again:
 		bi = &sh->dev[i].req;
@@ -927,7 +927,7 @@ again:
 			rdev = rrdev;
 			rrdev = NULL;
 		}
-		if (rw & WRITE) {
+		if (op_is_write(op)) {
 			if (replace_only)
 				rdev = NULL;
 			if (rdev == rrdev)
@@ -953,7 +953,7 @@ again:
 		 * need to check for writes.  We never accept write errors
 		 * on the replacement, so we don't to check rrdev.
 		 */
-		while ((rw & WRITE) && rdev &&
+		while (op_is_write(op) && rdev &&
 		       test_bit(WriteErrorSeen, &rdev->flags)) {
 			sector_t first_bad;
 			int bad_sectors;
@@ -995,13 +995,13 @@ again:
 
 			bio_reset(bi);
 			bi->bi_bdev = rdev->bdev;
-			bi->bi_rw = rw;
-			bi->bi_end_io = (rw & WRITE)
+			bio_set_op_attrs(bi, op, op_flags);
+			bi->bi_end_io = op_is_write(op)
 				? raid5_end_write_request
 				: raid5_end_read_request;
 			bi->bi_private = sh;
 
-			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
+			pr_debug("%s: for %llu schedule op %d on disc %d\n",
 				__func__, (unsigned long long)sh->sector,
 				bi->bi_rw, i);
 			atomic_inc(&sh->count);
@@ -1027,7 +1027,7 @@ again:
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
 			 */
-			if (rw & REQ_DISCARD)
+			if (op == REQ_OP_DISCARD)
 				bi->bi_vcnt = 0;
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
@@ -1047,12 +1047,12 @@ again:
 
 			bio_reset(rbi);
 			rbi->bi_bdev = rrdev->bdev;
-			rbi->bi_rw = rw;
-			BUG_ON(!(rw & WRITE));
+			bio_set_op_attrs(rbi, op, op_flags);
+			BUG_ON(!op_is_write(op));
 			rbi->bi_end_io = raid5_end_write_request;
 			rbi->bi_private = sh;
 
-			pr_debug("%s: for %llu schedule op %ld on "
+			pr_debug("%s: for %llu schedule op %d on "
 				 "replacement disc %d\n",
 				__func__, (unsigned long long)sh->sector,
 				rbi->bi_rw, i);
@@ -1076,7 +1076,7 @@ again:
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
 			 */
-			if (rw & REQ_DISCARD)
+			if (op == REQ_OP_DISCARD)
 				rbi->bi_vcnt = 0;
 			if (conf->mddev->gendisk)
 				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
@@ -1085,9 +1085,9 @@ again:
 			generic_make_request(rbi);
 		}
 		if (!rdev && !rrdev) {
-			if (rw & WRITE)
+			if (op_is_write(op))
 				set_bit(STRIPE_DEGRADED, &sh->state);
-			pr_debug("skip op %ld on disc %d for sector %llu\n",
+			pr_debug("skip op %d on disc %d for sector %llu\n",
 				bi->bi_rw, i, (unsigned long long)sh->sector);
 			clear_bit(R5_LOCKED, &sh->dev[i].flags);
 			set_bit(STRIPE_HANDLE, &sh->state);
@@ -1623,7 +1623,7 @@ again:
 					set_bit(R5_WantFUA, &dev->flags);
 				if (wbi->bi_rw & REQ_SYNC)
 					set_bit(R5_SyncIO, &dev->flags);
-				if (wbi->bi_rw & REQ_DISCARD)
+				if (bio_op(wbi) == REQ_OP_DISCARD)
 					set_bit(R5_Discard, &dev->flags);
 				else {
 					tx = async_copy_data(1, wbi, &dev->page,
@@ -5150,7 +5150,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	DEFINE_WAIT(w);
 	bool do_prepare;
 
-	if (unlikely(bi->bi_rw & REQ_FLUSH)) {
+	if (unlikely(bi->bi_rw & REQ_PREFLUSH)) {
 		int ret = r5l_handle_flush_request(conf->log, bi);
 
 		if (ret == 0)
@@ -5176,7 +5176,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 			return;
 	}
 
-	if (unlikely(bi->bi_rw & REQ_DISCARD)) {
+	if (unlikely(bio_op(bi) == REQ_OP_DISCARD)) {
 		make_discard_request(mddev, bi);
 		return;
 	}
@@ -5233,7 +5233,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 			(unsigned long long)logical_sector);
 
 		sh = raid5_get_active_stripe(conf, new_sector, previous,
-				       (bi->bi_rw&RWA_MASK), 0);
+				       (bi->bi_rw & REQ_RAHEAD), 0);
 		if (sh) {
 			if (unlikely(previous)) {
 				/* expansion might have moved on while waiting for a
diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig
index a8518fb3bca7..962f2a9a6614 100644
--- a/drivers/media/Kconfig
+++ b/drivers/media/Kconfig
@@ -80,6 +80,9 @@ config MEDIA_RC_SUPPORT
 
 	  Say Y when you have a TV or an IR device.
 
+config MEDIA_CEC_EDID
+	bool
+
 #
 # Media controller
 #	Selectable only for webcam/grabbers, as other drivers don't use it
diff --git a/drivers/media/Makefile b/drivers/media/Makefile
index e608bbce0c35..081a7866fd44 100644
--- a/drivers/media/Makefile
+++ b/drivers/media/Makefile
@@ -2,6 +2,10 @@
 # Makefile for the kernel multimedia device drivers.
 #
 
+ifeq ($(CONFIG_MEDIA_CEC_EDID),y)
+  obj-$(CONFIG_MEDIA_SUPPORT) += cec-edid.o
+endif
+
 media-objs	:= media-device.o media-devnode.o media-entity.o
 
 #
diff --git a/drivers/media/cec-edid.c b/drivers/media/cec-edid.c
new file mode 100644
index 000000000000..70018247bdda
--- /dev/null
+++ b/drivers/media/cec-edid.c
@@ -0,0 +1,168 @@
+/*
+ * cec-edid - HDMI Consumer Electronics Control EDID & CEC helper functions
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <media/cec-edid.h>
+
+/*
+ * This EDID is expected to be a CEA-861 compliant, which means that there are
+ * at least two blocks and one or more of the extensions blocks are CEA-861
+ * blocks.
+ *
+ * The returned location is guaranteed to be < size - 1.
+ */
+static unsigned int cec_get_edid_spa_location(const u8 *edid, unsigned int size)
+{
+	unsigned int blocks = size / 128;
+	unsigned int block;
+	u8 d;
+
+	/* Sanity check: at least 2 blocks and a multiple of the block size */
+	if (blocks < 2 || size % 128)
+		return 0;
+
+	/*
+	 * If there are fewer extension blocks than the size, then update
+	 * 'blocks'. It is allowed to have more extension blocks than the size,
+	 * since some hardware can only read e.g. 256 bytes of the EDID, even
+	 * though more blocks are present. The first CEA-861 extension block
+	 * should normally be in block 1 anyway.
+	 */
+	if (edid[0x7e] + 1 < blocks)
+		blocks = edid[0x7e] + 1;
+
+	for (block = 1; block < blocks; block++) {
+		unsigned int offset = block * 128;
+
+		/* Skip any non-CEA-861 extension blocks */
+		if (edid[offset] != 0x02 || edid[offset + 1] != 0x03)
+			continue;
+
+		/* search Vendor Specific Data Block (tag 3) */
+		d = edid[offset + 2] & 0x7f;
+		/* Check if there are Data Blocks */
+		if (d <= 4)
+			continue;
+		if (d > 4) {
+			unsigned int i = offset + 4;
+			unsigned int end = offset + d;
+
+			/* Note: 'end' is always < 'size' */
+			do {
+				u8 tag = edid[i] >> 5;
+				u8 len = edid[i] & 0x1f;
+
+				if (tag == 3 && len >= 5 && i + len <= end)
+					return i + 4;
+				i += len + 1;
+			} while (i < end);
+		}
+	}
+	return 0;
+}
+
+u16 cec_get_edid_phys_addr(const u8 *edid, unsigned int size,
+			   unsigned int *offset)
+{
+	unsigned int loc = cec_get_edid_spa_location(edid, size);
+
+	if (offset)
+		*offset = loc;
+	if (loc == 0)
+		return CEC_PHYS_ADDR_INVALID;
+	return (edid[loc] << 8) | edid[loc + 1];
+}
+EXPORT_SYMBOL_GPL(cec_get_edid_phys_addr);
+
+void cec_set_edid_phys_addr(u8 *edid, unsigned int size, u16 phys_addr)
+{
+	unsigned int loc = cec_get_edid_spa_location(edid, size);
+	u8 sum = 0;
+	unsigned int i;
+
+	if (loc == 0)
+		return;
+	edid[loc] = phys_addr >> 8;
+	edid[loc + 1] = phys_addr & 0xff;
+	loc &= ~0x7f;
+
+	/* update the checksum */
+	for (i = loc; i < loc + 127; i++)
+		sum += edid[i];
+	edid[i] = 256 - sum;
+}
+EXPORT_SYMBOL_GPL(cec_set_edid_phys_addr);
+
+u16 cec_phys_addr_for_input(u16 phys_addr, u8 input)
+{
+	/* Check if input is sane */
+	if (WARN_ON(input == 0 || input > 0xf))
+		return CEC_PHYS_ADDR_INVALID;
+
+	if (phys_addr == 0)
+		return input << 12;
+
+	if ((phys_addr & 0x0fff) == 0)
+		return phys_addr | (input << 8);
+
+	if ((phys_addr & 0x00ff) == 0)
+		return phys_addr | (input << 4);
+
+	if ((phys_addr & 0x000f) == 0)
+		return phys_addr | input;
+
+	/*
+	 * All nibbles are used so no valid physical addresses can be assigned
+	 * to the input.
+	 */
+	return CEC_PHYS_ADDR_INVALID;
+}
+EXPORT_SYMBOL_GPL(cec_phys_addr_for_input);
+
+int cec_phys_addr_validate(u16 phys_addr, u16 *parent, u16 *port)
+{
+	int i;
+
+	if (parent)
+		*parent = phys_addr;
+	if (port)
+		*port = 0;
+	if (phys_addr == CEC_PHYS_ADDR_INVALID)
+		return 0;
+	for (i = 0; i < 16; i += 4)
+		if (phys_addr & (0xf << i))
+			break;
+	if (i == 16)
+		return 0;
+	if (parent)
+		*parent = phys_addr & (0xfff0 << i);
+	if (port)
+		*port = (phys_addr >> i) & 0xf;
+	for (i += 4; i < 16; i += 4)
+		if ((phys_addr & (0xf << i)) == 0)
+			return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cec_phys_addr_validate);
+
+MODULE_AUTHOR("Hans Verkuil <hans.verkuil@cisco.com>");
+MODULE_DESCRIPTION("CEC EDID helper functions");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c
index cf1dadd0be9e..3ec3cebe62b9 100644
--- a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c
+++ b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c
@@ -777,7 +777,7 @@ static void precalculate_color(struct tpg_data *tpg, int k)
 	 * Remember that r, g and b are still in the 0 - 0xff0 range.
 	 */
 	if (tpg->real_rgb_range == V4L2_DV_RGB_RANGE_LIMITED &&
-	    tpg->rgb_range == V4L2_DV_RGB_RANGE_FULL) {
+	    tpg->rgb_range == V4L2_DV_RGB_RANGE_FULL && !tpg->is_yuv) {
 		/*
 		 * Convert from full range (which is what r, g and b are)
 		 * to limited range (which is the 'real' RGB range), which
@@ -787,7 +787,7 @@ static void precalculate_color(struct tpg_data *tpg, int k)
 		g = (g * 219) / 255 + (16 << 4);
 		b = (b * 219) / 255 + (16 << 4);
 	} else if (tpg->real_rgb_range != V4L2_DV_RGB_RANGE_LIMITED &&
-		   tpg->rgb_range == V4L2_DV_RGB_RANGE_LIMITED) {
+		   tpg->rgb_range == V4L2_DV_RGB_RANGE_LIMITED && !tpg->is_yuv) {
 		/*
 		 * Clamp r, g and b to the limited range and convert to full
 		 * range since that's what we deliver.
diff --git a/drivers/media/dvb-core/demux.h b/drivers/media/dvb-core/demux.h
index 6d3b95b8939d..7f1dffef4353 100644
--- a/drivers/media/dvb-core/demux.h
+++ b/drivers/media/dvb-core/demux.h
@@ -143,7 +143,7 @@ struct dmx_ts_feed {
 		   int type,
 		   enum dmx_ts_pes pes_type,
 		   size_t circular_buffer_size,
-		   struct timespec timeout);
+		   ktime_t timeout);
 	int (*start_filtering)(struct dmx_ts_feed *feed);
 	int (*stop_filtering)(struct dmx_ts_feed *feed);
 };
diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c
index a168cbe1c998..7b67e1dd97fd 100644
--- a/drivers/media/dvb-core/dmxdev.c
+++ b/drivers/media/dvb-core/dmxdev.c
@@ -556,7 +556,7 @@ static int dvb_dmxdev_start_feed(struct dmxdev *dmxdev,
 				 struct dmxdev_filter *filter,
 				 struct dmxdev_feed *feed)
 {
-	struct timespec timeout = { 0 };
+	ktime_t timeout = ktime_set(0, 0);
 	struct dmx_pes_filter_params *para = &filter->params.pes;
 	dmx_output_t otype;
 	int ret;
diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c
index f82cd1ff4f3a..b5b5b195ea7f 100644
--- a/drivers/media/dvb-core/dvb_ca_en50221.c
+++ b/drivers/media/dvb-core/dvb_ca_en50221.c
@@ -123,6 +123,7 @@ struct dvb_ca_slot {
 
 /* Private CA-interface information */
 struct dvb_ca_private {
+	struct kref refcount;
 
 	/* pointer back to the public data structure */
 	struct dvb_ca_en50221 *pub;
@@ -161,6 +162,34 @@ struct dvb_ca_private {
 	struct mutex ioctl_mutex;
 };
 
+static void dvb_ca_private_free(struct dvb_ca_private *ca)
+{
+	unsigned int i;
+
+	dvb_unregister_device(ca->dvbdev);
+	for (i = 0; i < ca->slot_count; i++)
+		vfree(ca->slot_info[i].rx_buffer.data);
+
+	kfree(ca->slot_info);
+	kfree(ca);
+}
+
+static void dvb_ca_private_release(struct kref *ref)
+{
+	struct dvb_ca_private *ca = container_of(ref, struct dvb_ca_private, refcount);
+	dvb_ca_private_free(ca);
+}
+
+static void dvb_ca_private_get(struct dvb_ca_private *ca)
+{
+	kref_get(&ca->refcount);
+}
+
+static void dvb_ca_private_put(struct dvb_ca_private *ca)
+{
+	kref_put(&ca->refcount, dvb_ca_private_release);
+}
+
 static void dvb_ca_en50221_thread_wakeup(struct dvb_ca_private *ca);
 static int dvb_ca_en50221_read_data(struct dvb_ca_private *ca, int slot, u8 * ebuf, int ecount);
 static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, u8 * ebuf, int ecount);
@@ -1558,6 +1587,8 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file)
 	dvb_ca_en50221_thread_update_delay(ca);
 	dvb_ca_en50221_thread_wakeup(ca);
 
+	dvb_ca_private_get(ca);
+
 	return 0;
 }
 
@@ -1586,6 +1617,8 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file)
 
 	module_put(ca->pub->owner);
 
+	dvb_ca_private_put(ca);
+
 	return err;
 }
 
@@ -1681,6 +1714,7 @@ int dvb_ca_en50221_init(struct dvb_adapter *dvb_adapter,
 		ret = -ENOMEM;
 		goto exit;
 	}
+	kref_init(&ca->refcount);
 	ca->pub = pubca;
 	ca->flags = flags;
 	ca->slot_count = slot_count;
@@ -1759,10 +1793,7 @@ void dvb_ca_en50221_release(struct dvb_ca_en50221 *pubca)
 
 	for (i = 0; i < ca->slot_count; i++) {
 		dvb_ca_en50221_slot_shutdown(ca, i);
-		vfree(ca->slot_info[i].rx_buffer.data);
 	}
-	kfree(ca->slot_info);
-	dvb_unregister_device(ca->dvbdev);
-	kfree(ca);
+	dvb_ca_private_put(ca);
 	pubca->private = NULL;
 }
diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c
index 0cc5e935166c..a0cf7b0d03e8 100644
--- a/drivers/media/dvb-core/dvb_demux.c
+++ b/drivers/media/dvb-core/dvb_demux.c
@@ -398,28 +398,23 @@ static void dvb_dmx_swfilter_packet(struct dvb_demux *demux, const u8 *buf)
 	int dvr_done = 0;
 
 	if (dvb_demux_speedcheck) {
-		struct timespec cur_time, delta_time;
+		ktime_t cur_time;
 		u64 speed_bytes, speed_timedelta;
 
 		demux->speed_pkts_cnt++;
 
 		/* show speed every SPEED_PKTS_INTERVAL packets */
 		if (!(demux->speed_pkts_cnt % SPEED_PKTS_INTERVAL)) {
-			cur_time = current_kernel_time();
+			cur_time = ktime_get();
 
-			if (demux->speed_last_time.tv_sec != 0 &&
-					demux->speed_last_time.tv_nsec != 0) {
-				delta_time = timespec_sub(cur_time,
-						demux->speed_last_time);
+			if (ktime_to_ns(demux->speed_last_time) != 0) {
 				speed_bytes = (u64)demux->speed_pkts_cnt
 					* 188 * 8;
 				/* convert to 1024 basis */
 				speed_bytes = 1000 * div64_u64(speed_bytes,
 						1024);
-				speed_timedelta =
-					(u64)timespec_to_ns(&delta_time);
-				speed_timedelta = div64_u64(speed_timedelta,
-						1000000); /* nsec -> usec */
+				speed_timedelta = ktime_ms_delta(cur_time,
+							demux->speed_last_time);
 				printk(KERN_INFO "TS speed %llu Kbits/sec \n",
 						div64_u64(speed_bytes,
 							speed_timedelta));
@@ -666,7 +661,7 @@ out:
 
 static int dmx_ts_feed_set(struct dmx_ts_feed *ts_feed, u16 pid, int ts_type,
 			   enum dmx_ts_pes pes_type,
-			   size_t circular_buffer_size, struct timespec timeout)
+			   size_t circular_buffer_size, ktime_t timeout)
 {
 	struct dvb_demux_feed *feed = (struct dvb_demux_feed *)ts_feed;
 	struct dvb_demux *demux = feed->demux;
diff --git a/drivers/media/dvb-core/dvb_demux.h b/drivers/media/dvb-core/dvb_demux.h
index ae7fc33c3231..5ed3cab4ad28 100644
--- a/drivers/media/dvb-core/dvb_demux.h
+++ b/drivers/media/dvb-core/dvb_demux.h
@@ -83,7 +83,7 @@ struct dvb_demux_feed {
 	u8 *buffer;
 	int buffer_size;
 
-	struct timespec timeout;
+	ktime_t timeout;
 	struct dvb_demux_filter *filter;
 
 	int ts_type;
@@ -134,7 +134,7 @@ struct dvb_demux {
 
 	uint8_t *cnt_storage; /* for TS continuity check */
 
-	struct timespec speed_last_time; /* for TS speed check */
+	ktime_t speed_last_time; /* for TS speed check */
 	uint32_t speed_pkts_cnt; /* for TS speed check */
 };
 
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index c0142614c408..be99c8dbc5f8 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -99,6 +99,7 @@ MODULE_PARM_DESC(dvb_mfe_wait_time, "Wait up to <mfe_wait_time> seconds on open(
 static DEFINE_MUTEX(frontend_mutex);
 
 struct dvb_frontend_private {
+	struct kref refcount;
 
 	/* thread/frontend values */
 	struct dvb_device *dvbdev;
@@ -137,6 +138,23 @@ struct dvb_frontend_private {
 #endif
 };
 
+static void dvb_frontend_private_free(struct kref *ref)
+{
+	struct dvb_frontend_private *fepriv =
+		container_of(ref, struct dvb_frontend_private, refcount);
+	kfree(fepriv);
+}
+
+static void dvb_frontend_private_put(struct dvb_frontend_private *fepriv)
+{
+	kref_put(&fepriv->refcount, dvb_frontend_private_free);
+}
+
+static void dvb_frontend_private_get(struct dvb_frontend_private *fepriv)
+{
+	kref_get(&fepriv->refcount);
+}
+
 static void dvb_frontend_wakeup(struct dvb_frontend *fe);
 static int dtv_get_frontend(struct dvb_frontend *fe,
 			    struct dtv_frontend_properties *c,
@@ -2543,6 +2561,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file)
 		fepriv->events.eventr = fepriv->events.eventw = 0;
 	}
 
+	dvb_frontend_private_get(fepriv);
+
 	if (adapter->mfe_shared)
 		mutex_unlock (&adapter->mfe_lock);
 	return ret;
@@ -2591,6 +2611,8 @@ static int dvb_frontend_release(struct inode *inode, struct file *file)
 			fe->ops.ts_bus_ctrl(fe, 0);
 	}
 
+	dvb_frontend_private_put(fepriv);
+
 	return ret;
 }
 
@@ -2679,6 +2701,8 @@ int dvb_register_frontend(struct dvb_adapter* dvb,
 	}
 	fepriv = fe->frontend_priv;
 
+	kref_init(&fepriv->refcount);
+
 	sema_init(&fepriv->sem, 1);
 	init_waitqueue_head (&fepriv->wait_queue);
 	init_waitqueue_head (&fepriv->events.wait_queue);
@@ -2713,18 +2737,11 @@ int dvb_unregister_frontend(struct dvb_frontend* fe)
 
 	mutex_lock(&frontend_mutex);
 	dvb_frontend_stop (fe);
-	mutex_unlock(&frontend_mutex);
-
-	if (fepriv->dvbdev->users < -1)
-		wait_event(fepriv->dvbdev->wait_queue,
-				fepriv->dvbdev->users==-1);
-
-	mutex_lock(&frontend_mutex);
 	dvb_unregister_device (fepriv->dvbdev);
 
 	/* fe is invalid now */
-	kfree(fepriv);
 	mutex_unlock(&frontend_mutex);
+	dvb_frontend_private_put(fepriv);
 	return 0;
 }
 EXPORT_SYMBOL(dvb_unregister_frontend);
diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c
index ce6a711b42d4..9914f69a4a02 100644
--- a/drivers/media/dvb-core/dvb_net.c
+++ b/drivers/media/dvb-core/dvb_net.c
@@ -997,7 +997,7 @@ static int dvb_net_feed_start(struct net_device *dev)
 		netdev_dbg(dev, "start filtering\n");
 		priv->secfeed->start_filtering(priv->secfeed);
 	} else if (priv->feedtype == DVB_NET_FEEDTYPE_ULE) {
-		struct timespec timeout = { 0, 10000000 }; // 10 msec
+		ktime_t timeout = ns_to_ktime(10 * NSEC_PER_MSEC);
 
 		/* we have payloads encapsulated in TS */
 		netdev_dbg(dev, "alloc tsfeed\n");
diff --git a/drivers/media/dvb-core/dvb_ringbuffer.c b/drivers/media/dvb-core/dvb_ringbuffer.c
index 1100e98a7b1d..7df7fb3738a0 100644
--- a/drivers/media/dvb-core/dvb_ringbuffer.c
+++ b/drivers/media/dvb-core/dvb_ringbuffer.c
@@ -55,7 +55,13 @@ void dvb_ringbuffer_init(struct dvb_ringbuffer *rbuf, void *data, size_t len)
 
 int dvb_ringbuffer_empty(struct dvb_ringbuffer *rbuf)
 {
-	return (rbuf->pread==rbuf->pwrite);
+	/* smp_load_acquire() to load write pointer on reader side
+	 * this pairs with smp_store_release() in dvb_ringbuffer_write(),
+	 * dvb_ringbuffer_write_user(), or dvb_ringbuffer_reset()
+	 *
+	 * for memory barriers also see Documentation/circular-buffers.txt
+	 */
+	return (rbuf->pread == smp_load_acquire(&rbuf->pwrite));
 }
 
 
@@ -64,7 +70,12 @@ ssize_t dvb_ringbuffer_free(struct dvb_ringbuffer *rbuf)
 {
 	ssize_t free;
 
-	free = rbuf->pread - rbuf->pwrite;
+	/* ACCESS_ONCE() to load read pointer on writer side
+	 * this pairs with smp_store_release() in dvb_ringbuffer_read(),
+	 * dvb_ringbuffer_read_user(), dvb_ringbuffer_flush(),
+	 * or dvb_ringbuffer_reset()
+	 */
+	free = ACCESS_ONCE(rbuf->pread) - rbuf->pwrite;
 	if (free <= 0)
 		free += rbuf->size;
 	return free-1;
@@ -76,7 +87,11 @@ ssize_t dvb_ringbuffer_avail(struct dvb_ringbuffer *rbuf)
 {
 	ssize_t avail;
 
-	avail = rbuf->pwrite - rbuf->pread;
+	/* smp_load_acquire() to load write pointer on reader side
+	 * this pairs with smp_store_release() in dvb_ringbuffer_write(),
+	 * dvb_ringbuffer_write_user(), or dvb_ringbuffer_reset()
+	 */
+	avail = smp_load_acquire(&rbuf->pwrite) - rbuf->pread;
 	if (avail < 0)
 		avail += rbuf->size;
 	return avail;
@@ -86,14 +101,25 @@ ssize_t dvb_ringbuffer_avail(struct dvb_ringbuffer *rbuf)
 
 void dvb_ringbuffer_flush(struct dvb_ringbuffer *rbuf)
 {
-	rbuf->pread = rbuf->pwrite;
+	/* dvb_ringbuffer_flush() counts as read operation
+	 * smp_load_acquire() to load write pointer
+	 * smp_store_release() to update read pointer, this ensures that the
+	 * correct pointer is visible for subsequent dvb_ringbuffer_free()
+	 * calls on other cpu cores
+	 */
+	smp_store_release(&rbuf->pread, smp_load_acquire(&rbuf->pwrite));
 	rbuf->error = 0;
 }
 EXPORT_SYMBOL(dvb_ringbuffer_flush);
 
 void dvb_ringbuffer_reset(struct dvb_ringbuffer *rbuf)
 {
-	rbuf->pread = rbuf->pwrite = 0;
+	/* dvb_ringbuffer_reset() counts as read and write operation
+	 * smp_store_release() to update read pointer
+	 */
+	smp_store_release(&rbuf->pread, 0);
+	/* smp_store_release() to update write pointer */
+	smp_store_release(&rbuf->pwrite, 0);
 	rbuf->error = 0;
 }
 
@@ -119,12 +145,17 @@ ssize_t dvb_ringbuffer_read_user(struct dvb_ringbuffer *rbuf, u8 __user *buf, si
 			return -EFAULT;
 		buf += split;
 		todo -= split;
-		rbuf->pread = 0;
+		/* smp_store_release() for read pointer update to ensure
+		 * that buf is not overwritten until read is complete,
+		 * this pairs with ACCESS_ONCE() in dvb_ringbuffer_free()
+		 */
+		smp_store_release(&rbuf->pread, 0);
 	}
 	if (copy_to_user(buf, rbuf->data+rbuf->pread, todo))
 		return -EFAULT;
 
-	rbuf->pread = (rbuf->pread + todo) % rbuf->size;
+	/* smp_store_release() to update read pointer, see above */
+	smp_store_release(&rbuf->pread, (rbuf->pread + todo) % rbuf->size);
 
 	return len;
 }
@@ -139,11 +170,16 @@ void dvb_ringbuffer_read(struct dvb_ringbuffer *rbuf, u8 *buf, size_t len)
 		memcpy(buf, rbuf->data+rbuf->pread, split);
 		buf += split;
 		todo -= split;
-		rbuf->pread = 0;
+		/* smp_store_release() for read pointer update to ensure
+		 * that buf is not overwritten until read is complete,
+		 * this pairs with ACCESS_ONCE() in dvb_ringbuffer_free()
+		 */
+		smp_store_release(&rbuf->pread, 0);
 	}
 	memcpy(buf, rbuf->data+rbuf->pread, todo);
 
-	rbuf->pread = (rbuf->pread + todo) % rbuf->size;
+	/* smp_store_release() to update read pointer, see above */
+	smp_store_release(&rbuf->pread, (rbuf->pread + todo) % rbuf->size);
 }
 
 
@@ -158,10 +194,16 @@ ssize_t dvb_ringbuffer_write(struct dvb_ringbuffer *rbuf, const u8 *buf, size_t
 		memcpy(rbuf->data+rbuf->pwrite, buf, split);
 		buf += split;
 		todo -= split;
-		rbuf->pwrite = 0;
+		/* smp_store_release() for write pointer update to ensure that
+		 * written data is visible on other cpu cores before the pointer
+		 * update, this pairs with smp_load_acquire() in
+		 * dvb_ringbuffer_empty() or dvb_ringbuffer_avail()
+		 */
+		smp_store_release(&rbuf->pwrite, 0);
 	}
 	memcpy(rbuf->data+rbuf->pwrite, buf, todo);
-	rbuf->pwrite = (rbuf->pwrite + todo) % rbuf->size;
+	/* smp_store_release() for write pointer update, see above */
+	smp_store_release(&rbuf->pwrite, (rbuf->pwrite + todo) % rbuf->size);
 
 	return len;
 }
@@ -181,12 +223,18 @@ ssize_t dvb_ringbuffer_write_user(struct dvb_ringbuffer *rbuf,
 			return len - todo;
 		buf += split;
 		todo -= split;
-		rbuf->pwrite = 0;
+		/* smp_store_release() for write pointer update to ensure that
+		 * written data is visible on other cpu cores before the pointer
+		 * update, this pairs with smp_load_acquire() in
+		 * dvb_ringbuffer_empty() or dvb_ringbuffer_avail()
+		 */
+		smp_store_release(&rbuf->pwrite, 0);
 	}
 	status = copy_from_user(rbuf->data+rbuf->pwrite, buf, todo);
 	if (status)
 		return len - todo;
-	rbuf->pwrite = (rbuf->pwrite + todo) % rbuf->size;
+	/* smp_store_release() for write pointer update, see above */
+	smp_store_release(&rbuf->pwrite, (rbuf->pwrite + todo) % rbuf->size);
 
 	return len;
 }
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index a82f77c49bd5..c645aa81f423 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -73,6 +73,14 @@ config DVB_SI2165
 
 	  Say Y when you want to support this frontend.
 
+config DVB_MN88472
+	tristate "Panasonic MN88472"
+	depends on DVB_CORE && I2C
+	select REGMAP_I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  Say Y when you want to support this frontend.
+
 config DVB_MN88473
 	tristate "Panasonic MN88473"
 	depends on DVB_CORE && I2C
@@ -853,6 +861,13 @@ config DVB_ASCOT2E
 	help
 	  Say Y when you want to support this frontend.
 
+config DVB_HELENE
+	tristate "Sony HELENE Sat/Ter tuner (CXD2858ER)"
+	depends on DVB_CORE && I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	Say Y when you want to support this frontend.
+
 comment "Tools to develop new frontends"
 
 config DVB_DUMMY_FE
diff --git a/drivers/media/dvb-frontends/Makefile b/drivers/media/dvb-frontends/Makefile
index eb7191f4219d..e90165ad361b 100644
--- a/drivers/media/dvb-frontends/Makefile
+++ b/drivers/media/dvb-frontends/Makefile
@@ -95,6 +95,7 @@ obj-$(CONFIG_DVB_STV0900) += stv0900.o
 obj-$(CONFIG_DVB_STV090x) += stv090x.o
 obj-$(CONFIG_DVB_STV6110x) += stv6110x.o
 obj-$(CONFIG_DVB_M88DS3103) += m88ds3103.o
+obj-$(CONFIG_DVB_MN88472) += mn88472.o
 obj-$(CONFIG_DVB_MN88473) += mn88473.o
 obj-$(CONFIG_DVB_ISL6423) += isl6423.o
 obj-$(CONFIG_DVB_EC100) += ec100.o
@@ -123,3 +124,4 @@ obj-$(CONFIG_DVB_AS102_FE) += as102_fe.o
 obj-$(CONFIG_DVB_TC90522) += tc90522.o
 obj-$(CONFIG_DVB_HORUS3A) += horus3a.o
 obj-$(CONFIG_DVB_ASCOT2E) += ascot2e.o
+obj-$(CONFIG_DVB_HELENE) += helene.o
diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c
index efebe5ce2429..9a8157a5f49d 100644
--- a/drivers/media/dvb-frontends/af9033.c
+++ b/drivers/media/dvb-frontends/af9033.c
@@ -41,7 +41,6 @@ struct af9033_dev {
 	u64 post_bit_count;
 	u64 error_block_count;
 	u64 total_block_count;
-	struct delayed_work stat_work;
 };
 
 /* write multiple registers */
@@ -468,8 +467,6 @@ static int af9033_init(struct dvb_frontend *fe)
 	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	c->post_bit_error.len = 1;
 	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	/* start statistics polling */
-	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
 
 	return 0;
 
@@ -485,9 +482,6 @@ static int af9033_sleep(struct dvb_frontend *fe)
 	int ret, i;
 	u8 tmp;
 
-	/* stop statistics polling */
-	cancel_delayed_work_sync(&dev->stat_work);
-
 	ret = af9033_wr_reg(dev, 0x80004c, 1);
 	if (ret < 0)
 		goto err;
@@ -821,36 +815,39 @@ err:
 static int af9033_read_status(struct dvb_frontend *fe, enum fe_status *status)
 {
 	struct af9033_dev *dev = fe->demodulator_priv;
-	int ret;
-	u8 tmp;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	int ret, i, tmp = 0;
+	u8 u8tmp, buf[7];
+
+	dev_dbg(&dev->client->dev, "\n");
 
 	*status = 0;
 
 	/* radio channel status, 0=no result, 1=has signal, 2=no signal */
-	ret = af9033_rd_reg(dev, 0x800047, &tmp);
+	ret = af9033_rd_reg(dev, 0x800047, &u8tmp);
 	if (ret < 0)
 		goto err;
 
 	/* has signal */
-	if (tmp == 0x01)
+	if (u8tmp == 0x01)
 		*status |= FE_HAS_SIGNAL;
 
-	if (tmp != 0x02) {
+	if (u8tmp != 0x02) {
 		/* TPS lock */
-		ret = af9033_rd_reg_mask(dev, 0x80f5a9, &tmp, 0x01);
+		ret = af9033_rd_reg_mask(dev, 0x80f5a9, &u8tmp, 0x01);
 		if (ret < 0)
 			goto err;
 
-		if (tmp)
+		if (u8tmp)
 			*status |= FE_HAS_SIGNAL | FE_HAS_CARRIER |
 					FE_HAS_VITERBI;
 
 		/* full lock */
-		ret = af9033_rd_reg_mask(dev, 0x80f999, &tmp, 0x01);
+		ret = af9033_rd_reg_mask(dev, 0x80f999, &u8tmp, 0x01);
 		if (ret < 0)
 			goto err;
 
-		if (tmp)
+		if (u8tmp)
 			*status |= FE_HAS_SIGNAL | FE_HAS_CARRIER |
 					FE_HAS_VITERBI | FE_HAS_SYNC |
 					FE_HAS_LOCK;
@@ -858,6 +855,148 @@ static int af9033_read_status(struct dvb_frontend *fe, enum fe_status *status)
 
 	dev->fe_status = *status;
 
+	/* signal strength */
+	if (dev->fe_status & FE_HAS_SIGNAL) {
+		if (dev->is_af9035) {
+			ret = af9033_rd_reg(dev, 0x80004a, &u8tmp);
+			if (ret)
+				goto err;
+			tmp = -u8tmp * 1000;
+		} else {
+			ret = af9033_rd_reg(dev, 0x8000f7, &u8tmp);
+			if (ret)
+				goto err;
+			tmp = (u8tmp - 100) * 1000;
+		}
+
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_DECIBEL;
+		c->strength.stat[0].svalue = tmp;
+	} else {
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	}
+
+	/* CNR */
+	if (dev->fe_status & FE_HAS_VITERBI) {
+		u32 snr_val, snr_lut_size;
+		const struct val_snr *snr_lut = NULL;
+
+		/* read value */
+		ret = af9033_rd_regs(dev, 0x80002c, buf, 3);
+		if (ret)
+			goto err;
+
+		snr_val = (buf[2] << 16) | (buf[1] << 8) | (buf[0] << 0);
+
+		/* read superframe number */
+		ret = af9033_rd_reg(dev, 0x80f78b, &u8tmp);
+		if (ret)
+			goto err;
+
+		if (u8tmp)
+			snr_val /= u8tmp;
+
+		/* read current transmission mode */
+		ret = af9033_rd_reg(dev, 0x80f900, &u8tmp);
+		if (ret)
+			goto err;
+
+		switch ((u8tmp >> 0) & 3) {
+		case 0:
+			snr_val *= 4;
+			break;
+		case 1:
+			snr_val *= 1;
+			break;
+		case 2:
+			snr_val *= 2;
+			break;
+		default:
+			snr_val *= 0;
+			break;
+		}
+
+		/* read current modulation */
+		ret = af9033_rd_reg(dev, 0x80f903, &u8tmp);
+		if (ret)
+			goto err;
+
+		switch ((u8tmp >> 0) & 3) {
+		case 0:
+			snr_lut_size = ARRAY_SIZE(qpsk_snr_lut);
+			snr_lut = qpsk_snr_lut;
+			break;
+		case 1:
+			snr_lut_size = ARRAY_SIZE(qam16_snr_lut);
+			snr_lut = qam16_snr_lut;
+			break;
+		case 2:
+			snr_lut_size = ARRAY_SIZE(qam64_snr_lut);
+			snr_lut = qam64_snr_lut;
+			break;
+		default:
+			snr_lut_size = 0;
+			tmp = 0;
+			break;
+		}
+
+		for (i = 0; i < snr_lut_size; i++) {
+			tmp = snr_lut[i].snr * 1000;
+			if (snr_val < snr_lut[i].val)
+				break;
+		}
+
+		c->cnr.len = 1;
+		c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+		c->cnr.stat[0].svalue = tmp;
+	} else {
+		c->cnr.len = 1;
+		c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	}
+
+	/* UCB/PER/BER */
+	if (dev->fe_status & FE_HAS_LOCK) {
+		/* outer FEC, 204 byte packets */
+		u16 abort_packet_count, rsd_packet_count;
+		/* inner FEC, bits */
+		u32 rsd_bit_err_count;
+
+		/*
+		 * Packet count used for measurement is 10000
+		 * (rsd_packet_count). Maybe it should be increased?
+		 */
+
+		ret = af9033_rd_regs(dev, 0x800032, buf, 7);
+		if (ret)
+			goto err;
+
+		abort_packet_count = (buf[1] << 8) | (buf[0] << 0);
+		rsd_bit_err_count = (buf[4] << 16) | (buf[3] << 8) | buf[2];
+		rsd_packet_count = (buf[6] << 8) | (buf[5] << 0);
+
+		dev->error_block_count += abort_packet_count;
+		dev->total_block_count += rsd_packet_count;
+		dev->post_bit_error += rsd_bit_err_count;
+		dev->post_bit_count += rsd_packet_count * 204 * 8;
+
+		c->block_count.len = 1;
+		c->block_count.stat[0].scale = FE_SCALE_COUNTER;
+		c->block_count.stat[0].uvalue = dev->total_block_count;
+
+		c->block_error.len = 1;
+		c->block_error.stat[0].scale = FE_SCALE_COUNTER;
+		c->block_error.stat[0].uvalue = dev->error_block_count;
+
+		c->post_bit_count.len = 1;
+		c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+		c->post_bit_count.stat[0].uvalue = dev->post_bit_count;
+
+		c->post_bit_error.len = 1;
+		c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+		c->post_bit_error.stat[0].uvalue = dev->post_bit_error;
+	}
+
 	return 0;
 
 err:
@@ -1059,159 +1198,6 @@ err:
 	return ret;
 }
 
-static void af9033_stat_work(struct work_struct *work)
-{
-	struct af9033_dev *dev = container_of(work, struct af9033_dev, stat_work.work);
-	struct dtv_frontend_properties *c = &dev->fe.dtv_property_cache;
-	int ret, tmp, i, len;
-	u8 u8tmp, buf[7];
-
-	dev_dbg(&dev->client->dev, "\n");
-
-	/* signal strength */
-	if (dev->fe_status & FE_HAS_SIGNAL) {
-		if (dev->is_af9035) {
-			ret = af9033_rd_reg(dev, 0x80004a, &u8tmp);
-			tmp = -u8tmp * 1000;
-		} else {
-			ret = af9033_rd_reg(dev, 0x8000f7, &u8tmp);
-			tmp = (u8tmp - 100) * 1000;
-		}
-		if (ret)
-			goto err;
-
-		c->strength.len = 1;
-		c->strength.stat[0].scale = FE_SCALE_DECIBEL;
-		c->strength.stat[0].svalue = tmp;
-	} else {
-		c->strength.len = 1;
-		c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	}
-
-	/* CNR */
-	if (dev->fe_status & FE_HAS_VITERBI) {
-		u32 snr_val;
-		const struct val_snr *snr_lut;
-
-		/* read value */
-		ret = af9033_rd_regs(dev, 0x80002c, buf, 3);
-		if (ret)
-			goto err;
-
-		snr_val = (buf[2] << 16) | (buf[1] << 8) | (buf[0] << 0);
-
-		/* read superframe number */
-		ret = af9033_rd_reg(dev, 0x80f78b, &u8tmp);
-		if (ret)
-			goto err;
-
-		if (u8tmp)
-			snr_val /= u8tmp;
-
-		/* read current transmission mode */
-		ret = af9033_rd_reg(dev, 0x80f900, &u8tmp);
-		if (ret)
-			goto err;
-
-		switch ((u8tmp >> 0) & 3) {
-		case 0:
-			snr_val *= 4;
-			break;
-		case 1:
-			snr_val *= 1;
-			break;
-		case 2:
-			snr_val *= 2;
-			break;
-		default:
-			goto err_schedule_delayed_work;
-		}
-
-		/* read current modulation */
-		ret = af9033_rd_reg(dev, 0x80f903, &u8tmp);
-		if (ret)
-			goto err;
-
-		switch ((u8tmp >> 0) & 3) {
-		case 0:
-			len = ARRAY_SIZE(qpsk_snr_lut);
-			snr_lut = qpsk_snr_lut;
-			break;
-		case 1:
-			len = ARRAY_SIZE(qam16_snr_lut);
-			snr_lut = qam16_snr_lut;
-			break;
-		case 2:
-			len = ARRAY_SIZE(qam64_snr_lut);
-			snr_lut = qam64_snr_lut;
-			break;
-		default:
-			goto err_schedule_delayed_work;
-		}
-
-		for (i = 0; i < len; i++) {
-			tmp = snr_lut[i].snr * 1000;
-			if (snr_val < snr_lut[i].val)
-				break;
-		}
-
-		c->cnr.len = 1;
-		c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
-		c->cnr.stat[0].svalue = tmp;
-	} else {
-		c->cnr.len = 1;
-		c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	}
-
-	/* UCB/PER/BER */
-	if (dev->fe_status & FE_HAS_LOCK) {
-		/* outer FEC, 204 byte packets */
-		u16 abort_packet_count, rsd_packet_count;
-		/* inner FEC, bits */
-		u32 rsd_bit_err_count;
-
-		/*
-		 * Packet count used for measurement is 10000
-		 * (rsd_packet_count). Maybe it should be increased?
-		 */
-
-		ret = af9033_rd_regs(dev, 0x800032, buf, 7);
-		if (ret)
-			goto err;
-
-		abort_packet_count = (buf[1] << 8) | (buf[0] << 0);
-		rsd_bit_err_count = (buf[4] << 16) | (buf[3] << 8) | buf[2];
-		rsd_packet_count = (buf[6] << 8) | (buf[5] << 0);
-
-		dev->error_block_count += abort_packet_count;
-		dev->total_block_count += rsd_packet_count;
-		dev->post_bit_error += rsd_bit_err_count;
-		dev->post_bit_count += rsd_packet_count * 204 * 8;
-
-		c->block_count.len = 1;
-		c->block_count.stat[0].scale = FE_SCALE_COUNTER;
-		c->block_count.stat[0].uvalue = dev->total_block_count;
-
-		c->block_error.len = 1;
-		c->block_error.stat[0].scale = FE_SCALE_COUNTER;
-		c->block_error.stat[0].uvalue = dev->error_block_count;
-
-		c->post_bit_count.len = 1;
-		c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
-		c->post_bit_count.stat[0].uvalue = dev->post_bit_count;
-
-		c->post_bit_error.len = 1;
-		c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
-		c->post_bit_error.stat[0].uvalue = dev->post_bit_error;
-	}
-
-err_schedule_delayed_work:
-	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
-	return;
-err:
-	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
-}
-
 static struct dvb_frontend_ops af9033_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
@@ -1272,7 +1258,6 @@ static int af9033_probe(struct i2c_client *client,
 
 	/* setup the state */
 	dev->client = client;
-	INIT_DELAYED_WORK(&dev->stat_work, af9033_stat_work);
 	memcpy(&dev->cfg, cfg, sizeof(struct af9033_config));
 
 	if (dev->cfg.clock != 12000000) {
@@ -1372,9 +1357,6 @@ static int af9033_remove(struct i2c_client *client)
 
 	dev_dbg(&dev->client->dev, "\n");
 
-	/* stop statistics polling */
-	cancel_delayed_work_sync(&dev->stat_work);
-
 	dev->fe.ops.release = NULL;
 	dev->fe.demodulator_priv = NULL;
 	kfree(dev);
@@ -1391,6 +1373,7 @@ MODULE_DEVICE_TABLE(i2c, af9033_id_table);
 static struct i2c_driver af9033_driver = {
 	.driver = {
 		.name	= "af9033",
+		.suppress_bind_attrs	= true,
 	},
 	.probe		= af9033_probe,
 	.remove		= af9033_remove,
diff --git a/drivers/media/dvb-frontends/ascot2e.c b/drivers/media/dvb-frontends/ascot2e.c
index f770f6a2c987..8cc8c4597b6a 100644
--- a/drivers/media/dvb-frontends/ascot2e.c
+++ b/drivers/media/dvb-frontends/ascot2e.c
@@ -132,7 +132,7 @@ static int ascot2e_write_regs(struct ascot2e_priv *priv,
 		}
 	};
 
-	if (len + 1 >= sizeof(buf)) {
+	if (len + 1 > sizeof(buf)) {
 		dev_warn(&priv->i2c->dev,"wr reg=%04x: len=%d is too big!\n",
 			 reg, len + 1);
 		return -E2BIG;
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index 900186ba8e62..09c39346167f 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -1,7 +1,9 @@
 /*
  * cxd2841er.c
  *
- * Sony CXD2441ER digital demodulator driver
+ * Sony digital demodulator driver for
+ *	CXD2841ER - DVB-S/S2/T/T2/C/C2
+ *	CXD2854ER - DVB-S/S2/T/T2/C/C2, ISDB-T/S
  *
  * Copyright 2012 Sony Corporation
  * Copyright (C) 2014 NetUP Inc.
@@ -34,6 +36,16 @@
 #include "cxd2841er_priv.h"
 
 #define MAX_WRITE_REGSIZE	16
+#define LOG2_E_100X 144
+
+/* DVB-C constellation */
+enum sony_dvbc_constellation_t {
+	SONY_DVBC_CONSTELLATION_16QAM,
+	SONY_DVBC_CONSTELLATION_32QAM,
+	SONY_DVBC_CONSTELLATION_64QAM,
+	SONY_DVBC_CONSTELLATION_128QAM,
+	SONY_DVBC_CONSTELLATION_256QAM
+};
 
 enum cxd2841er_state {
 	STATE_SHUTDOWN = 0,
@@ -51,6 +63,8 @@ struct cxd2841er_priv {
 	const struct cxd2841er_config	*config;
 	enum cxd2841er_state		state;
 	u8				system;
+	enum cxd2841er_xtal		xtal;
+	enum fe_caps caps;
 };
 
 static const struct cxd2841er_cnr_data s_cn_data[] = {
@@ -188,6 +202,9 @@ static const struct cxd2841er_cnr_data s2_cn_data[] = {
 };
 
 #define MAKE_IFFREQ_CONFIG(iffreq) ((u32)(((iffreq)/41.0)*16777216.0 + 0.5))
+#define MAKE_IFFREQ_CONFIG_XTAL(xtal, iffreq) ((xtal == SONY_XTAL_24000) ? \
+		(u32)(((iffreq)/48.0)*16777216.0 + 0.5) : \
+		(u32)(((iffreq)/41.0)*16777216.0 + 0.5))
 
 static void cxd2841er_i2c_debug(struct cxd2841er_priv *priv,
 				u8 addr, u8 reg, u8 write,
@@ -217,7 +234,7 @@ static int cxd2841er_write_regs(struct cxd2841er_priv *priv,
 	};
 
 	if (len + 1 >= sizeof(buf)) {
-		dev_warn(&priv->i2c->dev,"wr reg=%04x: len=%d is too big!\n",
+		dev_warn(&priv->i2c->dev, "wr reg=%04x: len=%d is too big!\n",
 			 reg, len + 1);
 		return -E2BIG;
 	}
@@ -282,6 +299,7 @@ static int cxd2841er_read_regs(struct cxd2841er_priv *priv,
 			KBUILD_MODNAME, ret, i2c_addr, reg);
 		return ret;
 	}
+	cxd2841er_i2c_debug(priv, i2c_addr, reg, 0, val, len);
 	return 0;
 }
 
@@ -427,6 +445,15 @@ static int cxd2841er_sleep_tc_to_active_t2_band(struct cxd2841er_priv *priv,
 static int cxd2841er_sleep_tc_to_active_c_band(struct cxd2841er_priv *priv,
 					       u32 bandwidth);
 
+static int cxd2841er_sleep_tc_to_active_i(struct cxd2841er_priv *priv,
+		u32 bandwidth);
+
+static int cxd2841er_active_i_to_sleep_tc(struct cxd2841er_priv *priv);
+
+static int cxd2841er_sleep_tc_to_shutdown(struct cxd2841er_priv *priv);
+
+static int cxd2841er_shutdown_to_sleep_tc(struct cxd2841er_priv *priv);
+
 static int cxd2841er_retune_active(struct cxd2841er_priv *priv,
 				   struct dtv_frontend_properties *p)
 {
@@ -454,7 +481,13 @@ static int cxd2841er_retune_active(struct cxd2841er_priv *priv,
 					priv, p->bandwidth_hz);
 		case SYS_DVBC_ANNEX_A:
 			return cxd2841er_sleep_tc_to_active_c_band(
-					priv, 8000000);
+					priv, p->bandwidth_hz);
+		case SYS_ISDBT:
+			cxd2841er_active_i_to_sleep_tc(priv);
+			cxd2841er_sleep_tc_to_shutdown(priv);
+			cxd2841er_shutdown_to_sleep_tc(priv);
+			return cxd2841er_sleep_tc_to_active_i(
+					priv, p->bandwidth_hz);
 		}
 	}
 	dev_dbg(&priv->i2c->dev, "%s(): invalid delivery system %d\n",
@@ -669,6 +702,45 @@ static int cxd2841er_active_c_to_sleep_tc(struct cxd2841er_priv *priv)
 	return 0;
 }
 
+static int cxd2841er_active_i_to_sleep_tc(struct cxd2841er_priv *priv)
+{
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_err(&priv->i2c->dev, "%s(): invalid state %d\n",
+				__func__, priv->state);
+		return -EINVAL;
+	}
+	/* Set SLV-T Bank : 0x00 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
+	/* disable TS output */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0xc3, 0x01);
+	/* enable Hi-Z setting 1 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x80, 0x3f);
+	/* enable Hi-Z setting 2 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x81, 0xff);
+
+	/* TODO: Cancel demod parameter */
+
+	/* Set SLV-X Bank : 0x00 */
+	cxd2841er_write_reg(priv, I2C_SLVX, 0x00, 0x00);
+	/* disable ADC 1 */
+	cxd2841er_write_reg(priv, I2C_SLVX, 0x18, 0x01);
+	/* Set SLV-T Bank : 0x00 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
+	/* Disable ADC 2 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x43, 0x0a);
+	/* Disable ADC 3 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x41, 0x0a);
+	/* Disable ADC clock */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x30, 0x00);
+	/* Disable RF level monitor */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x2f, 0x00);
+	/* Disable demod clock */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x2c, 0x00);
+	priv->state = STATE_SLEEP_TC;
+	return 0;
+}
+
 static int cxd2841er_shutdown_to_sleep_s(struct cxd2841er_priv *priv)
 {
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
@@ -686,8 +758,25 @@ static int cxd2841er_shutdown_to_sleep_s(struct cxd2841er_priv *priv)
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x00, 0x00);
 	/* Set demod SW reset */
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x10, 0x01);
-	/* Set X'tal clock to 20.5Mhz */
-	cxd2841er_write_reg(priv, I2C_SLVX, 0x14, 0x00);
+
+	switch (priv->xtal) {
+	case SONY_XTAL_20500:
+		cxd2841er_write_reg(priv, I2C_SLVX, 0x14, 0x00);
+		break;
+	case SONY_XTAL_24000:
+		/* Select demod frequency */
+		cxd2841er_write_reg(priv, I2C_SLVX, 0x12, 0x00);
+		cxd2841er_write_reg(priv, I2C_SLVX, 0x14, 0x03);
+		break;
+	case SONY_XTAL_41000:
+		cxd2841er_write_reg(priv, I2C_SLVX, 0x14, 0x01);
+		break;
+	default:
+		dev_dbg(&priv->i2c->dev, "%s(): invalid demod xtal %d\n",
+				__func__, priv->xtal);
+		return -EINVAL;
+	}
+
 	/* Set demod mode */
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x17, 0x0a);
 	/* Clear demod SW reset */
@@ -712,6 +801,8 @@ static int cxd2841er_shutdown_to_sleep_s(struct cxd2841er_priv *priv)
 
 static int cxd2841er_shutdown_to_sleep_tc(struct cxd2841er_priv *priv)
 {
+	u8 data = 0;
+
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	if (priv->state != STATE_SHUTDOWN) {
 		dev_dbg(&priv->i2c->dev, "%s(): invalid demod state %d\n",
@@ -727,9 +818,24 @@ static int cxd2841er_shutdown_to_sleep_tc(struct cxd2841er_priv *priv)
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x00, 0x00);
 	/* Set demod SW reset */
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x10, 0x01);
-	/* Set X'tal clock to 20.5Mhz */
+  /* Select ADC clock mode */
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x13, 0x00);
-	cxd2841er_write_reg(priv, I2C_SLVX, 0x14, 0x00);
+
+	switch (priv->xtal) {
+	case SONY_XTAL_20500:
+		data = 0x0;
+		break;
+	case SONY_XTAL_24000:
+		/* Select demod frequency */
+		cxd2841er_write_reg(priv, I2C_SLVX, 0x12, 0x00);
+		data = 0x3;
+		break;
+	case SONY_XTAL_41000:
+		cxd2841er_write_reg(priv, I2C_SLVX, 0x12, 0x00);
+		data = 0x1;
+		break;
+	}
+	cxd2841er_write_reg(priv, I2C_SLVX, 0x14, data);
 	/* Clear demod SW reset */
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x10, 0x00);
 	usleep_range(1000, 2000);
@@ -809,11 +915,14 @@ static void cxd2841er_set_ts_clock_mode(struct cxd2841er_priv *priv,
 
 static u8 cxd2841er_chip_id(struct cxd2841er_priv *priv)
 {
-	u8 chip_id;
+	u8 chip_id = 0;
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
-	cxd2841er_write_reg(priv, I2C_SLVT, 0, 0);
-	cxd2841er_read_reg(priv, I2C_SLVT, 0xfd, &chip_id);
+	if (cxd2841er_write_reg(priv, I2C_SLVT, 0, 0) == 0)
+		cxd2841er_read_reg(priv, I2C_SLVT, 0xfd, &chip_id);
+	else if (cxd2841er_write_reg(priv, I2C_SLVX, 0, 0) == 0)
+		cxd2841er_read_reg(priv, I2C_SLVX, 0xfd, &chip_id);
+
 	return chip_id;
 }
 
@@ -896,6 +1005,25 @@ static int cxd2841er_read_status_c(struct cxd2841er_priv *priv, u8 *tslock)
 	return 0;
 }
 
+static int cxd2841er_read_status_i(struct cxd2841er_priv *priv,
+		u8 *sync, u8 *tslock, u8 *unlock)
+{
+	u8 data = 0;
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	if (priv->state != STATE_ACTIVE_TC)
+		return -EINVAL;
+	/* Set SLV-T Bank : 0x60 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x60);
+	cxd2841er_read_reg(priv, I2C_SLVT, 0x10, &data);
+	dev_dbg(&priv->i2c->dev,
+			"%s(): lock=0x%x\n", __func__, data);
+	*sync = ((data & 0x02) ? 1 : 0);
+	*tslock = ((data & 0x01) ? 1 : 0);
+	*unlock = ((data & 0x10) ? 1 : 0);
+	return 0;
+}
+
 static int cxd2841er_read_status_tc(struct dvb_frontend *fe,
 				    enum fe_status *status)
 {
@@ -921,6 +1049,20 @@ static int cxd2841er_read_status_tc(struct dvb_frontend *fe,
 					FE_HAS_SYNC;
 			if (tslock)
 				*status |= FE_HAS_LOCK;
+		} else if (priv->system == SYS_ISDBT) {
+			ret = cxd2841er_read_status_i(
+					priv, &sync, &tslock, &unlock);
+			if (ret)
+				goto done;
+			if (unlock)
+				goto done;
+			if (sync)
+				*status = FE_HAS_SIGNAL |
+					FE_HAS_CARRIER |
+					FE_HAS_VITERBI |
+					FE_HAS_SYNC;
+			if (tslock)
+				*status |= FE_HAS_LOCK;
 		} else if (priv->system == SYS_DVBC_ANNEX_A) {
 			ret = cxd2841er_read_status_c(priv, &tslock);
 			if (ret)
@@ -997,6 +1139,76 @@ static int cxd2841er_get_carrier_offset_s_s2(struct cxd2841er_priv *priv,
 	return 0;
 }
 
+static int cxd2841er_get_carrier_offset_i(struct cxd2841er_priv *priv,
+					   u32 bandwidth, int *offset)
+{
+	u8 data[4];
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_dbg(&priv->i2c->dev, "%s(): invalid state %d\n",
+			__func__, priv->state);
+		return -EINVAL;
+	}
+	if (priv->system != SYS_ISDBT) {
+		dev_dbg(&priv->i2c->dev, "%s(): invalid delivery system %d\n",
+			__func__, priv->system);
+		return -EINVAL;
+	}
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x60);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x4c, data, sizeof(data));
+	*offset = -1 * sign_extend32(
+		((u32)(data[0] & 0x1F) << 24) | ((u32)data[1] << 16) |
+		((u32)data[2] << 8) | (u32)data[3], 29);
+
+	switch (bandwidth) {
+	case 6000000:
+		*offset = -1 * ((*offset) * 8/264);
+		break;
+	case 7000000:
+		*offset = -1 * ((*offset) * 8/231);
+		break;
+	case 8000000:
+		*offset = -1 * ((*offset) * 8/198);
+		break;
+	default:
+		dev_dbg(&priv->i2c->dev, "%s(): invalid bandwidth %d\n",
+				__func__, bandwidth);
+		return -EINVAL;
+	}
+
+	dev_dbg(&priv->i2c->dev, "%s(): bandwidth %d offset %d\n",
+			__func__, bandwidth, *offset);
+
+	return 0;
+}
+
+static int cxd2841er_get_carrier_offset_t(struct cxd2841er_priv *priv,
+					   u32 bandwidth, int *offset)
+{
+	u8 data[4];
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_dbg(&priv->i2c->dev, "%s(): invalid state %d\n",
+			__func__, priv->state);
+		return -EINVAL;
+	}
+	if (priv->system != SYS_DVBT) {
+		dev_dbg(&priv->i2c->dev, "%s(): invalid delivery system %d\n",
+			__func__, priv->system);
+		return -EINVAL;
+	}
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x4c, data, sizeof(data));
+	*offset = -1 * sign_extend32(
+		((u32)(data[0] & 0x1F) << 24) | ((u32)data[1] << 16) |
+		((u32)data[2] << 8) | (u32)data[3], 29);
+	*offset *= (bandwidth / 1000000);
+	*offset /= 235;
+	return 0;
+}
+
 static int cxd2841er_get_carrier_offset_t2(struct cxd2841er_priv *priv,
 					   u32 bandwidth, int *offset)
 {
@@ -1060,6 +1272,24 @@ static int cxd2841er_get_carrier_offset_c(struct cxd2841er_priv *priv,
 	return 0;
 }
 
+static int cxd2841er_read_packet_errors_c(
+		struct cxd2841er_priv *priv, u32 *penum)
+{
+	u8 data[3];
+
+	*penum = 0;
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_dbg(&priv->i2c->dev, "%s(): invalid state %d\n",
+				__func__, priv->state);
+		return -EINVAL;
+	}
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x40);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0xea, data, sizeof(data));
+	if (data[2] & 0x01)
+		*penum = ((u32)data[0] << 8) | (u32)data[1];
+	return 0;
+}
+
 static int cxd2841er_read_packet_errors_t(
 		struct cxd2841er_priv *priv, u32 *penum)
 {
@@ -1096,11 +1326,85 @@ static int cxd2841er_read_packet_errors_t2(
 	return 0;
 }
 
-static u32 cxd2841er_mon_read_ber_s(struct cxd2841er_priv *priv)
+static int cxd2841er_read_packet_errors_i(
+		struct cxd2841er_priv *priv, u32 *penum)
+{
+	u8 data[2];
+
+	*penum = 0;
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_dbg(&priv->i2c->dev, "%s(): invalid state %d\n",
+				__func__, priv->state);
+		return -EINVAL;
+	}
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x60);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0xA1, data, 1);
+
+	if (!(data[0] & 0x01))
+		return 0;
+
+	/* Layer A */
+	cxd2841er_read_regs(priv, I2C_SLVT, 0xA2, data, sizeof(data));
+	*penum = ((u32)data[0] << 8) | (u32)data[1];
+
+	/* Layer B */
+	cxd2841er_read_regs(priv, I2C_SLVT, 0xA4, data, sizeof(data));
+	*penum += ((u32)data[0] << 8) | (u32)data[1];
+
+	/* Layer C */
+	cxd2841er_read_regs(priv, I2C_SLVT, 0xA6, data, sizeof(data));
+	*penum += ((u32)data[0] << 8) | (u32)data[1];
+
+	return 0;
+}
+
+static int cxd2841er_read_ber_c(struct cxd2841er_priv *priv,
+		u32 *bit_error, u32 *bit_count)
+{
+	u8 data[3];
+	u32 bit_err, period_exp;
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_dbg(&priv->i2c->dev, "%s(): invalid state %d\n",
+				__func__, priv->state);
+		return -EINVAL;
+	}
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x40);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x62, data, sizeof(data));
+	if (!(data[0] & 0x80)) {
+		dev_dbg(&priv->i2c->dev,
+				"%s(): no valid BER data\n", __func__);
+		return -EINVAL;
+	}
+	bit_err = ((u32)(data[0] & 0x3f) << 16) |
+		((u32)data[1] << 8) |
+		(u32)data[2];
+	cxd2841er_read_reg(priv, I2C_SLVT, 0x60, data);
+	period_exp = data[0] & 0x1f;
+
+	if ((period_exp <= 11) && (bit_err > (1 << period_exp) * 204 * 8)) {
+		dev_dbg(&priv->i2c->dev,
+				"%s(): period_exp(%u) or bit_err(%u)  not in range. no valid BER data\n",
+				__func__, period_exp, bit_err);
+		return -EINVAL;
+	}
+
+	dev_dbg(&priv->i2c->dev,
+			"%s(): period_exp(%u) or bit_err(%u) count=%d\n",
+			__func__, period_exp, bit_err,
+			((1 << period_exp) * 204 * 8));
+
+	*bit_error = bit_err;
+	*bit_count = ((1 << period_exp) * 204 * 8);
+
+	return 0;
+}
+
+static int cxd2841er_mon_read_ber_s(struct cxd2841er_priv *priv,
+				    u32 *bit_error, u32 *bit_count)
 {
 	u8 data[11];
-	u32 bit_error, bit_count;
-	u32 temp_q, temp_r;
 
 	/* Set SLV-T Bank : 0xA0 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0xa0);
@@ -1116,40 +1420,30 @@ static u32 cxd2841er_mon_read_ber_s(struct cxd2841er_priv *priv)
 	 */
 	cxd2841er_read_regs(priv, I2C_SLVT, 0x35, data, 11);
 	if (data[0] & 0x01) {
-		bit_error = ((u32)(data[1]  & 0x3F) << 16) |
-			((u32)(data[2]  & 0xFF) <<  8) |
-			(u32)(data[3]  & 0xFF);
-		bit_count = ((u32)(data[8]  & 0x3F) << 16) |
-			((u32)(data[9]  & 0xFF) <<  8) |
-			(u32)(data[10] & 0xFF);
-		/*
-		 *	BER = bitError / bitCount
-		 *	= (bitError * 10^7) / bitCount
-		 *	= ((bitError * 625 * 125 * 128) / bitCount
-		 */
-		if ((bit_count == 0) || (bit_error > bit_count)) {
+		*bit_error = ((u32)(data[1]  & 0x3F) << 16) |
+			     ((u32)(data[2]  & 0xFF) <<  8) |
+			     (u32)(data[3]  & 0xFF);
+		*bit_count = ((u32)(data[8]  & 0x3F) << 16) |
+			     ((u32)(data[9]  & 0xFF) <<  8) |
+			     (u32)(data[10] & 0xFF);
+		if ((*bit_count == 0) || (*bit_error > *bit_count)) {
 			dev_dbg(&priv->i2c->dev,
 				"%s(): invalid bit_error %d, bit_count %d\n",
-				__func__, bit_error, bit_count);
-			return 0;
+				__func__, *bit_error, *bit_count);
+			return -EINVAL;
 		}
-		temp_q = div_u64_rem(10000000ULL * bit_error,
-						bit_count, &temp_r);
-		if (bit_count != 1 && temp_r >= bit_count / 2)
-			temp_q++;
-		return temp_q;
+		return 0;
 	}
 	dev_dbg(&priv->i2c->dev, "%s(): no data available\n", __func__);
-	return 0;
+	return -EINVAL;
 }
 
 
-static u32 cxd2841er_mon_read_ber_s2(struct cxd2841er_priv *priv)
+static int cxd2841er_mon_read_ber_s2(struct cxd2841er_priv *priv,
+				     u32 *bit_error, u32 *bit_count)
 {
 	u8 data[5];
-	u32 bit_error, period;
-	u32 temp_q, temp_r;
-	u32 result = 0;
+	u32 period;
 
 	/* Set SLV-T Bank : 0xB2 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0xb2);
@@ -1164,10 +1458,10 @@ static u32 cxd2841er_mon_read_ber_s2(struct cxd2841er_priv *priv)
 	cxd2841er_read_regs(priv, I2C_SLVT, 0x30, data, 5);
 	if (data[0] & 0x01) {
 		/* Bit error count */
-		bit_error = ((u32)(data[1] & 0x0F) << 24) |
-			((u32)(data[2] & 0xFF) << 16) |
-			((u32)(data[3] & 0xFF) <<  8) |
-			(u32)(data[4] & 0xFF);
+		*bit_error = ((u32)(data[1] & 0x0F) << 24) |
+			     ((u32)(data[2] & 0xFF) << 16) |
+			     ((u32)(data[3] & 0xFF) <<  8) |
+			     (u32)(data[4] & 0xFF);
 
 		/* Set SLV-T Bank : 0xA0 */
 		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0xa0);
@@ -1177,40 +1471,30 @@ static u32 cxd2841er_mon_read_ber_s2(struct cxd2841er_priv *priv)
 		if (period == 0) {
 			dev_dbg(&priv->i2c->dev,
 				"%s(): period is 0\n", __func__);
-			return 0;
+			return -EINVAL;
 		}
-		if (bit_error > (period * 64800)) {
+		if (*bit_error > (period * 64800)) {
 			dev_dbg(&priv->i2c->dev,
 				"%s(): invalid bit_err 0x%x period 0x%x\n",
-				__func__, bit_error, period);
-			return 0;
+				__func__, *bit_error, period);
+			return -EINVAL;
 		}
-		/*
-		 * BER = bitError / (period * 64800)
-		 *	= (bitError * 10^7) / (period * 64800)
-		 *	= (bitError * 10^5) / (period * 648)
-		 *	= (bitError * 12500) / (period * 81)
-		 *	= (bitError * 10) * 1250 / (period * 81)
-		 */
-		temp_q = div_u64_rem(12500ULL * bit_error,
-					period * 81, &temp_r);
-		if (temp_r >= period * 40)
-			temp_q++;
-		result = temp_q;
+		*bit_count = period * 64800;
+
+		return 0;
 	} else {
 		dev_dbg(&priv->i2c->dev,
 			"%s(): no data available\n", __func__);
 	}
-	return result;
+	return -EINVAL;
 }
 
-static int cxd2841er_read_ber_t2(struct cxd2841er_priv *priv, u32 *ber)
+static int cxd2841er_read_ber_t2(struct cxd2841er_priv *priv,
+				 u32 *bit_error, u32 *bit_count)
 {
 	u8 data[4];
-	u32 div, q, r;
-	u32 bit_err, period_exp, n_ldpc;
+	u32 period_exp, n_ldpc;
 
-	*ber = 0;
 	if (priv->state != STATE_ACTIVE_TC) {
 		dev_dbg(&priv->i2c->dev,
 			"%s(): invalid state %d\n", __func__, priv->state);
@@ -1221,40 +1505,44 @@ static int cxd2841er_read_ber_t2(struct cxd2841er_priv *priv, u32 *ber)
 	if (!(data[0] & 0x10)) {
 		dev_dbg(&priv->i2c->dev,
 			"%s(): no valid BER data\n", __func__);
-		return 0;
+		return -EINVAL;
 	}
-	bit_err = ((u32)(data[0] & 0x0f) << 24) |
-		((u32)data[1] << 16) |
-		((u32)data[2] << 8) |
-		(u32)data[3];
+	*bit_error = ((u32)(data[0] & 0x0f) << 24) |
+		     ((u32)data[1] << 16) |
+		     ((u32)data[2] << 8) |
+		     (u32)data[3];
 	cxd2841er_read_reg(priv, I2C_SLVT, 0x6f, data);
 	period_exp = data[0] & 0x0f;
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x22);
 	cxd2841er_read_reg(priv, I2C_SLVT, 0x5e, data);
 	n_ldpc = ((data[0] & 0x03) == 0 ? 16200 : 64800);
-	if (bit_err > ((1U << period_exp) * n_ldpc)) {
+	if (*bit_error > ((1U << period_exp) * n_ldpc)) {
 		dev_dbg(&priv->i2c->dev,
 			"%s(): invalid BER value\n", __func__);
 		return -EINVAL;
 	}
+
+	/*
+	 * FIXME: the right thing would be to return bit_error untouched,
+	 * but, as we don't know the scale returned by the counters, let's
+	 * at least preserver BER = bit_error/bit_count.
+	 */
 	if (period_exp >= 4) {
-		div = (1U << (period_exp - 4)) * (n_ldpc / 200);
-		q = div_u64_rem(3125ULL * bit_err, div, &r);
+		*bit_count = (1U << (period_exp - 4)) * (n_ldpc / 200);
+		*bit_error *= 3125ULL;
 	} else {
-		div = (1U << period_exp) * (n_ldpc / 200);
-		q = div_u64_rem(50000ULL * bit_err, div, &r);
+		*bit_count = (1U << period_exp) * (n_ldpc / 200);
+		*bit_error *= 50000ULL;
 	}
-	*ber = (r >= div / 2) ? q + 1 : q;
 	return 0;
 }
 
-static int cxd2841er_read_ber_t(struct cxd2841er_priv *priv, u32 *ber)
+static int cxd2841er_read_ber_t(struct cxd2841er_priv *priv,
+				u32 *bit_error, u32 *bit_count)
 {
 	u8 data[2];
-	u32 div, q, r;
-	u32 bit_err, period;
+	u32 period;
 
-	*ber = 0;
 	if (priv->state != STATE_ACTIVE_TC) {
 		dev_dbg(&priv->i2c->dev,
 			"%s(): invalid state %d\n", __func__, priv->state);
@@ -1268,16 +1556,22 @@ static int cxd2841er_read_ber_t(struct cxd2841er_priv *priv, u32 *ber)
 		return 0;
 	}
 	cxd2841er_read_regs(priv, I2C_SLVT, 0x22, data, sizeof(data));
-	bit_err = ((u32)data[0] << 8) | (u32)data[1];
+	*bit_error = ((u32)data[0] << 8) | (u32)data[1];
 	cxd2841er_read_reg(priv, I2C_SLVT, 0x6f, data);
 	period = ((data[0] & 0x07) == 0) ? 256 : (4096 << (data[0] & 0x07));
-	div = period / 128;
-	q = div_u64_rem(78125ULL * bit_err, div, &r);
-	*ber = (r >= div / 2) ? q + 1 : q;
+
+	/*
+	 * FIXME: the right thing would be to return bit_error untouched,
+	 * but, as we don't know the scale returned by the counters, let's
+	 * at least preserver BER = bit_error/bit_count.
+	 */
+	*bit_count = period / 128;
+	*bit_error *= 78125ULL;
 	return 0;
 }
 
-static u32 cxd2841er_dvbs_read_snr(struct cxd2841er_priv *priv, u8 delsys)
+static u32 cxd2841er_dvbs_read_snr(struct cxd2841er_priv *priv,
+		u8 delsys, u32 *snr)
 {
 	u8 data[3];
 	u32 res = 0, value;
@@ -1335,9 +1629,71 @@ static u32 cxd2841er_dvbs_read_snr(struct cxd2841er_priv *priv, u8 delsys)
 	} else {
 		dev_dbg(&priv->i2c->dev,
 			"%s(): no data available\n", __func__);
+		return -EINVAL;
 	}
 done:
-	return res;
+	*snr = res;
+	return 0;
+}
+
+static uint32_t sony_log(uint32_t x)
+{
+	return (((10000>>8)*(intlog2(x)>>16) + LOG2_E_100X/2)/LOG2_E_100X);
+}
+
+static int cxd2841er_read_snr_c(struct cxd2841er_priv *priv, u32 *snr)
+{
+	u32 reg;
+	u8 data[2];
+	enum sony_dvbc_constellation_t qam = SONY_DVBC_CONSTELLATION_16QAM;
+
+	*snr = 0;
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_dbg(&priv->i2c->dev,
+				"%s(): invalid state %d\n",
+				__func__, priv->state);
+		return -EINVAL;
+	}
+
+	/*
+	 * Freeze registers: ensure multiple separate register reads
+	 * are from the same snapshot
+	 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x01, 0x01);
+
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x40);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x19, data, 1);
+	qam = (enum sony_dvbc_constellation_t) (data[0] & 0x07);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x4C, data, 2);
+
+	reg = ((u32)(data[0]&0x1f) << 8) | (u32)data[1];
+	if (reg == 0) {
+		dev_dbg(&priv->i2c->dev,
+				"%s(): reg value out of range\n", __func__);
+		return 0;
+	}
+
+	switch (qam) {
+	case SONY_DVBC_CONSTELLATION_16QAM:
+	case SONY_DVBC_CONSTELLATION_64QAM:
+	case SONY_DVBC_CONSTELLATION_256QAM:
+		/* SNR(dB) = -9.50 * ln(IREG_SNR_ESTIMATE / (24320)) */
+		if (reg < 126)
+			reg = 126;
+		*snr = -95 * (int32_t)sony_log(reg) + 95941;
+		break;
+	case SONY_DVBC_CONSTELLATION_32QAM:
+	case SONY_DVBC_CONSTELLATION_128QAM:
+		/* SNR(dB) = -8.75 * ln(IREG_SNR_ESTIMATE / (20800)) */
+		if (reg < 69)
+			reg = 69;
+		*snr = -88 * (int32_t)sony_log(reg) + 86999;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static int cxd2841er_read_snr_t(struct cxd2841er_priv *priv, u32 *snr)
@@ -1391,6 +1747,52 @@ static int cxd2841er_read_snr_t2(struct cxd2841er_priv *priv, u32 *snr)
 	return 0;
 }
 
+static int cxd2841er_read_snr_i(struct cxd2841er_priv *priv, u32 *snr)
+{
+	u32 reg;
+	u8 data[2];
+
+	*snr = 0;
+	if (priv->state != STATE_ACTIVE_TC) {
+		dev_dbg(&priv->i2c->dev,
+				"%s(): invalid state %d\n", __func__,
+				priv->state);
+		return -EINVAL;
+	}
+
+	/* Freeze all registers */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x01, 0x01);
+
+
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x60);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x28, data, sizeof(data));
+	reg = ((u32)data[0] << 8) | (u32)data[1];
+	if (reg == 0) {
+		dev_dbg(&priv->i2c->dev,
+				"%s(): reg value out of range\n", __func__);
+		return 0;
+	}
+	if (reg > 4996)
+		reg = 4996;
+	*snr = 100 * intlog10(reg) - 9031;
+	return 0;
+}
+
+static u16 cxd2841er_read_agc_gain_c(struct cxd2841er_priv *priv,
+					u8 delsys)
+{
+	u8 data[2];
+
+	cxd2841er_write_reg(
+		priv, I2C_SLVT, 0x00, 0x40);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x49, data, 2);
+	dev_dbg(&priv->i2c->dev,
+			"%s(): AGC value=%u\n",
+			__func__, (((u16)data[0] & 0x0F) << 8) |
+			(u16)(data[1] & 0xFF));
+	return ((((u16)data[0] & 0x0F) << 8) | (u16)(data[1] & 0xFF)) << 4;
+}
+
 static u16 cxd2841er_read_agc_gain_t_t2(struct cxd2841er_priv *priv,
 					u8 delsys)
 {
@@ -1399,6 +1801,26 @@ static u16 cxd2841er_read_agc_gain_t_t2(struct cxd2841er_priv *priv,
 	cxd2841er_write_reg(
 		priv, I2C_SLVT, 0x00, (delsys == SYS_DVBT ? 0x10 : 0x20));
 	cxd2841er_read_regs(priv, I2C_SLVT, 0x26, data, 2);
+	dev_dbg(&priv->i2c->dev,
+			"%s(): AGC value=%u\n",
+			__func__, (((u16)data[0] & 0x0F) << 8) |
+			(u16)(data[1] & 0xFF));
+	return ((((u16)data[0] & 0x0F) << 8) | (u16)(data[1] & 0xFF)) << 4;
+}
+
+static u16 cxd2841er_read_agc_gain_i(struct cxd2841er_priv *priv,
+		u8 delsys)
+{
+	u8 data[2];
+
+	cxd2841er_write_reg(
+			priv, I2C_SLVT, 0x00, 0x60);
+	cxd2841er_read_regs(priv, I2C_SLVT, 0x26, data, 2);
+
+	dev_dbg(&priv->i2c->dev,
+			"%s(): AGC value=%u\n",
+			__func__, (((u16)data[0] & 0x0F) << 8) |
+			(u16)(data[1] & 0xFF));
 	return ((((u16)data[0] & 0x0F) << 8) | (u16)(data[1] & 0xFF)) << 4;
 }
 
@@ -1417,101 +1839,170 @@ static u16 cxd2841er_read_agc_gain_s(struct cxd2841er_priv *priv)
 	return ((((u16)data[0] & 0x1F) << 8) | (u16)(data[1] & 0xFF)) << 3;
 }
 
-static int cxd2841er_read_ber(struct dvb_frontend *fe, u32 *ber)
+static void cxd2841er_read_ber(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
+	u32 ret, bit_error = 0, bit_count = 0;
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
-	*ber = 0;
 	switch (p->delivery_system) {
+	case SYS_DVBC_ANNEX_A:
+	case SYS_DVBC_ANNEX_B:
+	case SYS_DVBC_ANNEX_C:
+		ret = cxd2841er_read_ber_c(priv, &bit_error, &bit_count);
+		break;
 	case SYS_DVBS:
-		*ber = cxd2841er_mon_read_ber_s(priv);
+		ret = cxd2841er_mon_read_ber_s(priv, &bit_error, &bit_count);
 		break;
 	case SYS_DVBS2:
-		*ber = cxd2841er_mon_read_ber_s2(priv);
+		ret = cxd2841er_mon_read_ber_s2(priv, &bit_error, &bit_count);
 		break;
 	case SYS_DVBT:
-		return cxd2841er_read_ber_t(priv, ber);
+		ret = cxd2841er_read_ber_t(priv, &bit_error, &bit_count);
+		break;
 	case SYS_DVBT2:
-		return cxd2841er_read_ber_t2(priv, ber);
-	default:
-		*ber = 0;
+		ret = cxd2841er_read_ber_t2(priv, &bit_error, &bit_count);
 		break;
+	default:
+		p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+		p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+		return;
+	}
+
+	if (!ret) {
+		p->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+		p->post_bit_error.stat[0].uvalue += bit_error;
+		p->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+		p->post_bit_count.stat[0].uvalue += bit_count;
+	} else {
+		p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+		p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	}
-	return 0;
 }
 
-static int cxd2841er_read_signal_strength(struct dvb_frontend *fe,
-					  u16 *strength)
+static void cxd2841er_read_signal_strength(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
+	s32 strength;
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	switch (p->delivery_system) {
 	case SYS_DVBT:
 	case SYS_DVBT2:
-		*strength = 65535 - cxd2841er_read_agc_gain_t_t2(
-			priv, p->delivery_system);
+		strength = cxd2841er_read_agc_gain_t_t2(priv,
+							p->delivery_system);
+		p->strength.stat[0].scale = FE_SCALE_DECIBEL;
+		/* Formula was empirically determinated @ 410 MHz */
+		p->strength.stat[0].uvalue = strength * 366 / 100 - 89520;
+		break;	/* Code moved out of the function */
+	case SYS_DVBC_ANNEX_A:
+	case SYS_DVBC_ANNEX_B:
+	case SYS_DVBC_ANNEX_C:
+		strength = cxd2841er_read_agc_gain_c(priv,
+							p->delivery_system);
+		p->strength.stat[0].scale = FE_SCALE_DECIBEL;
+		/*
+		 * Formula was empirically determinated via linear regression,
+		 * using frequencies: 175 MHz, 410 MHz and 800 MHz, and a
+		 * stream modulated with QAM64
+		 */
+		p->strength.stat[0].uvalue = strength * 4045 / 1000 - 85224;
+		break;
+	case SYS_ISDBT:
+		strength = cxd2841er_read_agc_gain_i(priv, p->delivery_system);
+		p->strength.stat[0].scale = FE_SCALE_DECIBEL;
+		/*
+		 * Formula was empirically determinated via linear regression,
+		 * using frequencies: 175 MHz, 410 MHz and 800 MHz.
+		 */
+		p->strength.stat[0].uvalue = strength * 3775 / 1000 - 90185;
 		break;
 	case SYS_DVBS:
 	case SYS_DVBS2:
-		*strength = 65535 - cxd2841er_read_agc_gain_s(priv);
+		strength = 65535 - cxd2841er_read_agc_gain_s(priv);
+		p->strength.stat[0].scale = FE_SCALE_RELATIVE;
+		p->strength.stat[0].uvalue = strength;
 		break;
 	default:
-		*strength = 0;
+		p->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 		break;
 	}
-	return 0;
 }
 
-static int cxd2841er_read_snr(struct dvb_frontend *fe, u16 *snr)
+static void cxd2841er_read_snr(struct dvb_frontend *fe)
 {
 	u32 tmp = 0;
+	int ret = 0;
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	switch (p->delivery_system) {
+	case SYS_DVBC_ANNEX_A:
+	case SYS_DVBC_ANNEX_B:
+	case SYS_DVBC_ANNEX_C:
+		ret = cxd2841er_read_snr_c(priv, &tmp);
+		break;
 	case SYS_DVBT:
-		cxd2841er_read_snr_t(priv, &tmp);
+		ret = cxd2841er_read_snr_t(priv, &tmp);
 		break;
 	case SYS_DVBT2:
-		cxd2841er_read_snr_t2(priv, &tmp);
+		ret = cxd2841er_read_snr_t2(priv, &tmp);
+		break;
+	case SYS_ISDBT:
+		ret = cxd2841er_read_snr_i(priv, &tmp);
 		break;
 	case SYS_DVBS:
 	case SYS_DVBS2:
-		tmp = cxd2841er_dvbs_read_snr(priv, p->delivery_system);
+		ret = cxd2841er_dvbs_read_snr(priv, p->delivery_system, &tmp);
 		break;
 	default:
 		dev_dbg(&priv->i2c->dev, "%s(): unknown delivery system %d\n",
 			__func__, p->delivery_system);
-		break;
+		p->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+		return;
+	}
+
+	if (!ret) {
+		p->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+		p->cnr.stat[0].svalue = tmp;
+	} else {
+		p->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	}
-	*snr = tmp & 0xffff;
-	return 0;
 }
 
-static int cxd2841er_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
+static void cxd2841er_read_ucblocks(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
+	u32 ucblocks;
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	switch (p->delivery_system) {
+	case SYS_DVBC_ANNEX_A:
+	case SYS_DVBC_ANNEX_B:
+	case SYS_DVBC_ANNEX_C:
+		cxd2841er_read_packet_errors_c(priv, &ucblocks);
+		break;
 	case SYS_DVBT:
-		cxd2841er_read_packet_errors_t(priv, ucblocks);
+		cxd2841er_read_packet_errors_t(priv, &ucblocks);
 		break;
 	case SYS_DVBT2:
-		cxd2841er_read_packet_errors_t2(priv, ucblocks);
+		cxd2841er_read_packet_errors_t2(priv, &ucblocks);
 		break;
-	default:
-		*ucblocks = 0;
+	case SYS_ISDBT:
+		cxd2841er_read_packet_errors_i(priv, &ucblocks);
 		break;
+	default:
+		p->block_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+		return;
 	}
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
-	return 0;
+
+	p->block_error.stat[0].scale = FE_SCALE_COUNTER;
+	p->block_error.stat[0].uvalue = ucblocks;
 }
 
 static int cxd2841er_dvbt2_set_profile(
@@ -1524,15 +2015,18 @@ static int cxd2841er_dvbt2_set_profile(
 	switch (profile) {
 	case DVBT2_PROFILE_BASE:
 		tune_mode = 0x01;
-		seq_not2d_time = 12;
+		/* Set early unlock time */
+		seq_not2d_time = (priv->xtal == SONY_XTAL_24000)?0x0E:0x0C;
 		break;
 	case DVBT2_PROFILE_LITE:
 		tune_mode = 0x05;
-		seq_not2d_time = 40;
+		/* Set early unlock time */
+		seq_not2d_time = (priv->xtal == SONY_XTAL_24000)?0x2E:0x28;
 		break;
 	case DVBT2_PROFILE_ANY:
 		tune_mode = 0x00;
-		seq_not2d_time = 40;
+		/* Set early unlock time */
+		seq_not2d_time = (priv->xtal == SONY_XTAL_24000)?0x2E:0x28;
 		break;
 	default:
 		return -EINVAL;
@@ -1574,254 +2068,617 @@ static int cxd2841er_sleep_tc_to_active_t2_band(struct cxd2841er_priv *priv,
 						u32 bandwidth)
 {
 	u32 iffreq;
-	u8 b20_9f[5];
-	u8 b10_a6[14];
-	u8 b10_b6[3];
-	u8 b10_d7;
+	u8 data[MAX_WRITE_REGSIZE];
+
+	const uint8_t nominalRate8bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x11, 0xF0, 0x00, 0x00, 0x00}, /* 20.5MHz XTal */
+		{0x15, 0x00, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x11, 0xF0, 0x00, 0x00, 0x00}  /* 41MHz XTal */
+	};
+
+	const uint8_t nominalRate7bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x14, 0x80, 0x00, 0x00, 0x00}, /* 20.5MHz XTal */
+		{0x18, 0x00, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x14, 0x80, 0x00, 0x00, 0x00}  /* 41MHz XTal */
+	};
+
+	const uint8_t nominalRate6bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x17, 0xEA, 0xAA, 0xAA, 0xAA}, /* 20.5MHz XTal */
+		{0x1C, 0x00, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x17, 0xEA, 0xAA, 0xAA, 0xAA}  /* 41MHz XTal */
+	};
+
+	const uint8_t nominalRate5bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x1C, 0xB3, 0x33, 0x33, 0x33}, /* 20.5MHz XTal */
+		{0x21, 0x99, 0x99, 0x99, 0x99}, /* 24MHz XTal */
+		{0x1C, 0xB3, 0x33, 0x33, 0x33}  /* 41MHz XTal */
+	};
+
+	const uint8_t nominalRate17bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x58, 0xE2, 0xAF, 0xE0, 0xBC}, /* 20.5MHz XTal */
+		{0x68, 0x0F, 0xA2, 0x32, 0xD0}, /* 24MHz XTal */
+		{0x58, 0xE2, 0xAF, 0xE0, 0xBC}  /* 41MHz XTal */
+	};
+
+	const uint8_t itbCoef8bw[3][14] = {
+		{0x26, 0xAF, 0x06, 0xCD, 0x13, 0xBB, 0x28, 0xBA,
+			0x23, 0xA9, 0x1F, 0xA8, 0x2C, 0xC8}, /* 20.5MHz XTal */
+		{0x2F, 0xBA, 0x28, 0x9B, 0x28, 0x9D, 0x28, 0xA1,
+			0x29, 0xA5, 0x2A, 0xAC, 0x29, 0xB5}, /* 24MHz XTal   */
+		{0x26, 0xAF, 0x06, 0xCD, 0x13, 0xBB, 0x28, 0xBA,
+			0x23, 0xA9, 0x1F, 0xA8, 0x2C, 0xC8}  /* 41MHz XTal   */
+	};
+
+	const uint8_t itbCoef7bw[3][14] = {
+		{0x2C, 0xBD, 0x02, 0xCF, 0x04, 0xF8, 0x23, 0xA6,
+			0x29, 0xB0, 0x26, 0xA9, 0x21, 0xA5}, /* 20.5MHz XTal */
+		{0x30, 0xB1, 0x29, 0x9A, 0x28, 0x9C, 0x28, 0xA0,
+			0x29, 0xA2, 0x2B, 0xA6, 0x2B, 0xAD}, /* 24MHz XTal   */
+		{0x2C, 0xBD, 0x02, 0xCF, 0x04, 0xF8, 0x23, 0xA6,
+			0x29, 0xB0, 0x26, 0xA9, 0x21, 0xA5}  /* 41MHz XTal   */
+	};
+
+	const uint8_t itbCoef6bw[3][14] = {
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8,
+			0x00, 0xCF, 0x00, 0xE6, 0x23, 0xA4}, /* 20.5MHz XTal */
+		{0x31, 0xA8, 0x29, 0x9B, 0x27, 0x9C, 0x28, 0x9E,
+			0x29, 0xA4, 0x29, 0xA2, 0x29, 0xA8}, /* 24MHz XTal   */
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8,
+			0x00, 0xCF, 0x00, 0xE6, 0x23, 0xA4}  /* 41MHz XTal   */
+	};
+
+	const uint8_t itbCoef5bw[3][14] = {
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8,
+			0x00, 0xCF, 0x00, 0xE6, 0x23, 0xA4}, /* 20.5MHz XTal */
+		{0x31, 0xA8, 0x29, 0x9B, 0x27, 0x9C, 0x28, 0x9E,
+			0x29, 0xA4, 0x29, 0xA2, 0x29, 0xA8}, /* 24MHz XTal   */
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8,
+			0x00, 0xCF, 0x00, 0xE6, 0x23, 0xA4}  /* 41MHz XTal   */
+	};
+
+	const uint8_t itbCoef17bw[3][14] = {
+		{0x25, 0xA0, 0x36, 0x8D, 0x2E, 0x94, 0x28, 0x9B,
+			0x32, 0x90, 0x2C, 0x9D, 0x29, 0x99}, /* 20.5MHz XTal */
+		{0x33, 0x8E, 0x2B, 0x97, 0x2D, 0x95, 0x37, 0x8B,
+			0x30, 0x97, 0x2D, 0x9A, 0x21, 0xA4}, /* 24MHz XTal   */
+		{0x25, 0xA0, 0x36, 0x8D, 0x2E, 0x94, 0x28, 0x9B,
+			0x32, 0x90, 0x2C, 0x9D, 0x29, 0x99}  /* 41MHz XTal   */
+	};
+
+	/* Set SLV-T Bank : 0x20 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x20);
 
-	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	switch (bandwidth) {
 	case 8000000:
-		/* bank 0x20, reg 0x9f */
-		b20_9f[0] = 0x11;
-		b20_9f[1] = 0xf0;
-		b20_9f[2] = 0x00;
-		b20_9f[3] = 0x00;
-		b20_9f[4] = 0x00;
-		/* bank 0x10, reg 0xa6 */
-		b10_a6[0] = 0x26;
-		b10_a6[1] = 0xaf;
-		b10_a6[2] = 0x06;
-		b10_a6[3] = 0xcd;
-		b10_a6[4] = 0x13;
-		b10_a6[5] = 0xbb;
-		b10_a6[6] = 0x28;
-		b10_a6[7] = 0xba;
-		b10_a6[8] = 0x23;
-		b10_a6[9] = 0xa9;
-		b10_a6[10] = 0x1f;
-		b10_a6[11] = 0xa8;
-		b10_a6[12] = 0x2c;
-		b10_a6[13] = 0xc8;
-		iffreq = MAKE_IFFREQ_CONFIG(4.80);
-		b10_d7 = 0x00;
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate8bw[priv->xtal], 5);
+
+		/* Set SLV-T Bank : 0x27 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x27);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT,
+				0x7a, 0x00, 0x0f);
+
+		/* Set SLV-T Bank : 0x10 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		 */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef8bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 4.80);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+				priv, I2C_SLVT, 0xD7, 0x00, 0x07);
 		break;
 	case 7000000:
-		/* bank 0x20, reg 0x9f */
-		b20_9f[0] = 0x14;
-		b20_9f[1] = 0x80;
-		b20_9f[2] = 0x00;
-		b20_9f[3] = 0x00;
-		b20_9f[4] = 0x00;
-		/* bank 0x10, reg 0xa6 */
-		b10_a6[0] = 0x2C;
-		b10_a6[1] = 0xBD;
-		b10_a6[2] = 0x02;
-		b10_a6[3] = 0xCF;
-		b10_a6[4] = 0x04;
-		b10_a6[5] = 0xF8;
-		b10_a6[6] = 0x23;
-		b10_a6[7] = 0xA6;
-		b10_a6[8] = 0x29;
-		b10_a6[9] = 0xB0;
-		b10_a6[10] = 0x26;
-		b10_a6[11] = 0xA9;
-		b10_a6[12] = 0x21;
-		b10_a6[13] = 0xA5;
-		iffreq = MAKE_IFFREQ_CONFIG(4.2);
-		b10_d7 = 0x02;
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate7bw[priv->xtal], 5);
+
+		/* Set SLV-T Bank : 0x27 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x27);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT,
+				0x7a, 0x00, 0x0f);
+
+		/* Set SLV-T Bank : 0x10 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		 */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef7bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 4.20);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+				priv, I2C_SLVT, 0xD7, 0x02, 0x07);
 		break;
 	case 6000000:
-		/* bank 0x20, reg 0x9f */
-		b20_9f[0] = 0x17;
-		b20_9f[1] = 0xEA;
-		b20_9f[2] = 0xAA;
-		b20_9f[3] = 0xAA;
-		b20_9f[4] = 0xAA;
-		/* bank 0x10, reg 0xa6 */
-		b10_a6[0] = 0x27;
-		b10_a6[1] = 0xA7;
-		b10_a6[2] = 0x28;
-		b10_a6[3] = 0xB3;
-		b10_a6[4] = 0x02;
-		b10_a6[5] = 0xF0;
-		b10_a6[6] = 0x01;
-		b10_a6[7] = 0xE8;
-		b10_a6[8] = 0x00;
-		b10_a6[9] = 0xCF;
-		b10_a6[10] = 0x00;
-		b10_a6[11] = 0xE6;
-		b10_a6[12] = 0x23;
-		b10_a6[13] = 0xA4;
-		iffreq = MAKE_IFFREQ_CONFIG(3.6);
-		b10_d7 = 0x04;
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate6bw[priv->xtal], 5);
+
+		/* Set SLV-T Bank : 0x27 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x27);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT,
+				0x7a, 0x00, 0x0f);
+
+		/* Set SLV-T Bank : 0x10 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		 */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef6bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 3.60);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+				priv, I2C_SLVT, 0xD7, 0x04, 0x07);
 		break;
 	case 5000000:
-		/* bank 0x20, reg 0x9f */
-		b20_9f[0] = 0x1C;
-		b20_9f[1] = 0xB3;
-		b20_9f[2] = 0x33;
-		b20_9f[3] = 0x33;
-		b20_9f[4] = 0x33;
-		/* bank 0x10, reg 0xa6 */
-		b10_a6[0] = 0x27;
-		b10_a6[1] = 0xA7;
-		b10_a6[2] = 0x28;
-		b10_a6[3] = 0xB3;
-		b10_a6[4] = 0x02;
-		b10_a6[5] = 0xF0;
-		b10_a6[6] = 0x01;
-		b10_a6[7] = 0xE8;
-		b10_a6[8] = 0x00;
-		b10_a6[9] = 0xCF;
-		b10_a6[10] = 0x00;
-		b10_a6[11] = 0xE6;
-		b10_a6[12] = 0x23;
-		b10_a6[13] = 0xA4;
-		iffreq = MAKE_IFFREQ_CONFIG(3.6);
-		b10_d7 = 0x06;
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate5bw[priv->xtal], 5);
+
+		/* Set SLV-T Bank : 0x27 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x27);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT,
+				0x7a, 0x00, 0x0f);
+
+		/* Set SLV-T Bank : 0x10 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		 */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef5bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 3.60);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+				priv, I2C_SLVT, 0xD7, 0x06, 0x07);
 		break;
 	case 1712000:
-		/* bank 0x20, reg 0x9f */
-		b20_9f[0] = 0x58;
-		b20_9f[1] = 0xE2;
-		b20_9f[2] = 0xAF;
-		b20_9f[3] = 0xE0;
-		b20_9f[4] = 0xBC;
-		/* bank 0x10, reg 0xa6 */
-		b10_a6[0] = 0x25;
-		b10_a6[1] = 0xA0;
-		b10_a6[2] = 0x36;
-		b10_a6[3] = 0x8D;
-		b10_a6[4] = 0x2E;
-		b10_a6[5] = 0x94;
-		b10_a6[6] = 0x28;
-		b10_a6[7] = 0x9B;
-		b10_a6[8] = 0x32;
-		b10_a6[9] = 0x90;
-		b10_a6[10] = 0x2C;
-		b10_a6[11] = 0x9D;
-		b10_a6[12] = 0x29;
-		b10_a6[13] = 0x99;
-		iffreq = MAKE_IFFREQ_CONFIG(3.5);
-		b10_d7 = 0x03;
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate17bw[priv->xtal], 5);
+
+		/* Set SLV-T Bank : 0x27 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x27);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT,
+				0x7a, 0x03, 0x0f);
+
+		/* Set SLV-T Bank : 0x10 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		 */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef17bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 3.50);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+				priv, I2C_SLVT, 0xD7, 0x03, 0x07);
 		break;
 	default:
 		return -EINVAL;
 	}
-	/* Set SLV-T Bank : 0x20 */
-	cxd2841er_write_reg(priv, I2C_SLVX, 0x00, 0x20);
-	cxd2841er_write_regs(priv, I2C_SLVT, 0x9f, b20_9f, sizeof(b20_9f));
-	/* Set SLV-T Bank : 0x27 */
-	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x27);
-	cxd2841er_set_reg_bits(
-		priv, I2C_SLVT, 0x7a,
-		(bandwidth == 1712000 ? 0x03 : 0x00), 0x0f);
-	/* Set SLV-T Bank : 0x10 */
-	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
-	/* Group delay equaliser sett. for ASCOT2E */
-	cxd2841er_write_regs(priv, I2C_SLVT, 0xa6, b10_a6, sizeof(b10_a6));
-	/* <IF freq setting> */
-	b10_b6[0] = (u8) ((iffreq >> 16) & 0xff);
-	b10_b6[1] = (u8)((iffreq >> 8) & 0xff);
-	b10_b6[2] = (u8)(iffreq & 0xff);
-	cxd2841er_write_regs(priv, I2C_SLVT, 0xb6, b10_b6, sizeof(b10_b6));
-	/* System bandwidth setting */
-	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xd7, b10_d7, 0x07);
 	return 0;
 }
 
 static int cxd2841er_sleep_tc_to_active_t_band(
 		struct cxd2841er_priv *priv, u32 bandwidth)
 {
-	u8 b13_9c[2] = { 0x01, 0x14 };
-	u8 bw8mhz_b10_9f[] = { 0x11, 0xF0, 0x00, 0x00, 0x00 };
-	u8 bw8mhz_b10_a6[] = { 0x26, 0xAF, 0x06, 0xCD, 0x13, 0xBB,
-			0x28, 0xBA, 0x23, 0xA9, 0x1F, 0xA8, 0x2C, 0xC8 };
-	u8 bw8mhz_b10_d9[] = { 0x01, 0xE0 };
-	u8 bw8mhz_b17_38[] = { 0x01, 0x02 };
-	u8 bw7mhz_b10_9f[] = { 0x14, 0x80, 0x00, 0x00, 0x00 };
-	u8 bw7mhz_b10_a6[] = { 0x2C, 0xBD, 0x02, 0xCF, 0x04, 0xF8,
-			0x23, 0xA6, 0x29, 0xB0, 0x26, 0xA9, 0x21, 0xA5 };
-	u8 bw7mhz_b10_d9[] = { 0x12, 0xF8 };
-	u8 bw7mhz_b17_38[] = { 0x00, 0x03 };
-	u8 bw6mhz_b10_9f[] = { 0x17, 0xEA, 0xAA, 0xAA, 0xAA };
-	u8 bw6mhz_b10_a6[] = { 0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0,
-			0x01, 0xE8, 0x00, 0xCF, 0x00, 0xE6, 0x23, 0xA4 };
-	u8 bw6mhz_b10_d9[] = { 0x1F, 0xDC };
-	u8 bw6mhz_b17_38[] = { 0x00, 0x03 };
-	u8 bw5mhz_b10_9f[] = { 0x1C, 0xB3, 0x33, 0x33, 0x33 };
-	u8 bw5mhz_b10_a6[] = { 0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0,
-			0x01, 0xE8, 0x00, 0xCF, 0x00, 0xE6, 0x23, 0xA4 };
-	u8 bw5mhz_b10_d9[] = { 0x26, 0x3C };
-	u8 bw5mhz_b17_38[] = { 0x00, 0x03 };
-	u8 b10_b6[3];
-	u8 d7val;
+	u8 data[MAX_WRITE_REGSIZE];
 	u32 iffreq;
-	u8 *b10_9f;
-	u8 *b10_a6;
-	u8 *b10_d9;
-	u8 *b17_38;
+	u8 nominalRate8bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x11, 0xF0, 0x00, 0x00, 0x00}, /* 20.5MHz XTal */
+		{0x15, 0x00, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x11, 0xF0, 0x00, 0x00, 0x00}  /* 41MHz XTal */
+	};
+	u8 nominalRate7bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x14, 0x80, 0x00, 0x00, 0x00}, /* 20.5MHz XTal */
+		{0x18, 0x00, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x14, 0x80, 0x00, 0x00, 0x00}  /* 41MHz XTal */
+	};
+	u8 nominalRate6bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x17, 0xEA, 0xAA, 0xAA, 0xAA}, /* 20.5MHz XTal */
+		{0x1C, 0x00, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x17, 0xEA, 0xAA, 0xAA, 0xAA}  /* 41MHz XTal */
+	};
+	u8 nominalRate5bw[3][5] = {
+		/* TRCG Nominal Rate [37:0] */
+		{0x1C, 0xB3, 0x33, 0x33, 0x33}, /* 20.5MHz XTal */
+		{0x21, 0x99, 0x99, 0x99, 0x99}, /* 24MHz XTal */
+		{0x1C, 0xB3, 0x33, 0x33, 0x33}  /* 41MHz XTal */
+	};
 
-	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	u8 itbCoef8bw[3][14] = {
+		{0x26, 0xAF, 0x06, 0xCD, 0x13, 0xBB, 0x28, 0xBA, 0x23, 0xA9,
+			0x1F, 0xA8, 0x2C, 0xC8}, /* 20.5MHz XTal */
+		{0x2F, 0xBA, 0x28, 0x9B, 0x28, 0x9D, 0x28, 0xA1, 0x29, 0xA5,
+			0x2A, 0xAC, 0x29, 0xB5}, /* 24MHz XTal   */
+		{0x26, 0xAF, 0x06, 0xCD, 0x13, 0xBB, 0x28, 0xBA, 0x23, 0xA9,
+			0x1F, 0xA8, 0x2C, 0xC8}  /* 41MHz XTal   */
+	};
+	u8 itbCoef7bw[3][14] = {
+		{0x2C, 0xBD, 0x02, 0xCF, 0x04, 0xF8, 0x23, 0xA6, 0x29, 0xB0,
+			0x26, 0xA9, 0x21, 0xA5}, /* 20.5MHz XTal */
+		{0x30, 0xB1, 0x29, 0x9A, 0x28, 0x9C, 0x28, 0xA0, 0x29, 0xA2,
+			0x2B, 0xA6, 0x2B, 0xAD}, /* 24MHz XTal   */
+		{0x2C, 0xBD, 0x02, 0xCF, 0x04, 0xF8, 0x23, 0xA6, 0x29, 0xB0,
+			0x26, 0xA9, 0x21, 0xA5}  /* 41MHz XTal   */
+	};
+	u8 itbCoef6bw[3][14] = {
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8, 0x00, 0xCF,
+			0x00, 0xE6, 0x23, 0xA4}, /* 20.5MHz XTal */
+		{0x31, 0xA8, 0x29, 0x9B, 0x27, 0x9C, 0x28, 0x9E, 0x29, 0xA4,
+			0x29, 0xA2, 0x29, 0xA8}, /* 24MHz XTal   */
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8, 0x00, 0xCF,
+			0x00, 0xE6, 0x23, 0xA4}  /* 41MHz XTal   */
+	};
+	u8 itbCoef5bw[3][14] = {
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8, 0x00, 0xCF,
+			0x00, 0xE6, 0x23, 0xA4}, /* 20.5MHz XTal */
+		{0x31, 0xA8, 0x29, 0x9B, 0x27, 0x9C, 0x28, 0x9E, 0x29, 0xA4,
+			0x29, 0xA2, 0x29, 0xA8}, /* 24MHz XTal   */
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8, 0x00, 0xCF,
+			0x00, 0xE6, 0x23, 0xA4}  /* 41MHz XTal   */
+	};
+
+	/* Set SLV-T Bank : 0x13 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x13);
 	/* Echo performance optimization setting */
-	cxd2841er_write_regs(priv, I2C_SLVT, 0x9c, b13_9c, sizeof(b13_9c));
+	data[0] = 0x01;
+	data[1] = 0x14;
+	cxd2841er_write_regs(priv, I2C_SLVT, 0x9C, data, 2);
+
+	/* Set SLV-T Bank : 0x10 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
 
 	switch (bandwidth) {
 	case 8000000:
-		b10_9f = bw8mhz_b10_9f;
-		b10_a6 = bw8mhz_b10_a6;
-		b10_d9 = bw8mhz_b10_d9;
-		b17_38 = bw8mhz_b17_38;
-		d7val = 0;
-		iffreq = MAKE_IFFREQ_CONFIG(4.80);
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate8bw[priv->xtal], 5);
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		*/
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef8bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 4.80);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+			priv, I2C_SLVT, 0xD7, 0x00, 0x07);
+
+		/* Demod core latency setting */
+		if (priv->xtal == SONY_XTAL_24000) {
+			data[0] = 0x15;
+			data[1] = 0x28;
+		} else {
+			data[0] = 0x01;
+			data[1] = 0xE0;
+		}
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Notch filter setting */
+		data[0] = 0x01;
+		data[1] = 0x02;
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x17);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x38, data, 2);
 		break;
 	case 7000000:
-		b10_9f = bw7mhz_b10_9f;
-		b10_a6 = bw7mhz_b10_a6;
-		b10_d9 = bw7mhz_b10_d9;
-		b17_38 = bw7mhz_b17_38;
-		d7val = 2;
-		iffreq = MAKE_IFFREQ_CONFIG(4.20);
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate7bw[priv->xtal], 5);
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		*/
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef7bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 4.20);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+			priv, I2C_SLVT, 0xD7, 0x02, 0x07);
+
+		/* Demod core latency setting */
+		if (priv->xtal == SONY_XTAL_24000) {
+			data[0] = 0x1F;
+			data[1] = 0xF8;
+		} else {
+			data[0] = 0x12;
+			data[1] = 0xF8;
+		}
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Notch filter setting */
+		data[0] = 0x00;
+		data[1] = 0x03;
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x17);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x38, data, 2);
 		break;
 	case 6000000:
-		b10_9f = bw6mhz_b10_9f;
-		b10_a6 = bw6mhz_b10_a6;
-		b10_d9 = bw6mhz_b10_d9;
-		b17_38 = bw6mhz_b17_38;
-		d7val = 4;
-		iffreq = MAKE_IFFREQ_CONFIG(3.60);
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate6bw[priv->xtal], 5);
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		*/
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef6bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 3.60);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+			priv, I2C_SLVT, 0xD7, 0x04, 0x07);
+
+		/* Demod core latency setting */
+		if (priv->xtal == SONY_XTAL_24000) {
+			data[0] = 0x25;
+			data[1] = 0x4C;
+		} else {
+			data[0] = 0x1F;
+			data[1] = 0xDC;
+		}
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Notch filter setting */
+		data[0] = 0x00;
+		data[1] = 0x03;
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x17);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x38, data, 2);
 		break;
 	case 5000000:
-		b10_9f = bw5mhz_b10_9f;
-		b10_a6 = bw5mhz_b10_a6;
-		b10_d9 = bw5mhz_b10_d9;
-		b17_38 = bw5mhz_b17_38;
-		d7val = 6;
-		iffreq = MAKE_IFFREQ_CONFIG(3.60);
+		/* <Timing Recovery setting> */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate5bw[priv->xtal], 5);
+		/* Group delay equaliser settings for
+		 * ASCOT2D, ASCOT2E and ASCOT3 tuners
+		*/
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef5bw[priv->xtal], 14);
+		/* <IF freq setting> */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 3.60);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(
+			priv, I2C_SLVT, 0xD7, 0x06, 0x07);
+
+		/* Demod core latency setting */
+		if (priv->xtal == SONY_XTAL_24000) {
+			data[0] = 0x2C;
+			data[1] = 0xC2;
+		} else {
+			data[0] = 0x26;
+			data[1] = 0x3C;
+		}
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Notch filter setting */
+		data[0] = 0x00;
+		data[1] = 0x03;
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x17);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x38, data, 2);
+		break;
+	}
+
+	return 0;
+}
+
+static int cxd2841er_sleep_tc_to_active_i_band(
+		struct cxd2841er_priv *priv, u32 bandwidth)
+{
+	u32 iffreq;
+	u8 data[3];
+
+	/* TRCG Nominal Rate */
+	u8 nominalRate8bw[3][5] = {
+		{0x00, 0x00, 0x00, 0x00, 0x00}, /* 20.5MHz XTal */
+		{0x11, 0xB8, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x00, 0x00, 0x00, 0x00, 0x00}  /* 41MHz XTal */
+	};
+
+	u8 nominalRate7bw[3][5] = {
+		{0x00, 0x00, 0x00, 0x00, 0x00}, /* 20.5MHz XTal */
+		{0x14, 0x40, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x00, 0x00, 0x00, 0x00, 0x00}  /* 41MHz XTal */
+	};
+
+	u8 nominalRate6bw[3][5] = {
+		{0x14, 0x2E, 0x00, 0x00, 0x00}, /* 20.5MHz XTal */
+		{0x17, 0xA0, 0x00, 0x00, 0x00}, /* 24MHz XTal */
+		{0x14, 0x2E, 0x00, 0x00, 0x00}  /* 41MHz XTal */
+	};
+
+	u8 itbCoef8bw[3][14] = {
+		{0x00}, /* 20.5MHz XTal */
+		{0x2F, 0xBA, 0x28, 0x9B, 0x28, 0x9D, 0x28, 0xA1, 0x29,
+			0xA5, 0x2A, 0xAC, 0x29, 0xB5}, /* 24MHz Xtal */
+		{0x0}, /* 41MHz XTal   */
+	};
+
+	u8 itbCoef7bw[3][14] = {
+		{0x00}, /* 20.5MHz XTal */
+		{0x30, 0xB1, 0x29, 0x9A, 0x28, 0x9C, 0x28, 0xA0, 0x29,
+			0xA2, 0x2B, 0xA6, 0x2B, 0xAD}, /* 24MHz Xtal */
+		{0x00}, /* 41MHz XTal   */
+	};
+
+	u8 itbCoef6bw[3][14] = {
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8, 0x00,
+			0xCF, 0x00, 0xE6, 0x23, 0xA4}, /* 20.5MHz XTal */
+		{0x31, 0xA8, 0x29, 0x9B, 0x27, 0x9C, 0x28, 0x9E, 0x29,
+			0xA4, 0x29, 0xA2, 0x29, 0xA8}, /* 24MHz Xtal   */
+		{0x27, 0xA7, 0x28, 0xB3, 0x02, 0xF0, 0x01, 0xE8, 0x00,
+			0xCF, 0x00, 0xE6, 0x23, 0xA4}, /* 41MHz XTal   */
+	};
+
+	dev_dbg(&priv->i2c->dev, "%s() bandwidth=%u\n", __func__, bandwidth);
+	/* Set SLV-T Bank : 0x10 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+
+	/*  20.5/41MHz Xtal support is not available
+	 *  on ISDB-T 7MHzBW and 8MHzBW
+	*/
+	if (priv->xtal != SONY_XTAL_24000 && bandwidth > 6000000) {
+		dev_err(&priv->i2c->dev,
+			"%s(): bandwidth %d supported only for 24MHz xtal\n",
+			__func__, bandwidth);
+		return -EINVAL;
+	}
+
+	switch (bandwidth) {
+	case 8000000:
+		/* TRCG Nominal Rate */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate8bw[priv->xtal], 5);
+		/*  Group delay equaliser settings for ASCOT tuners optimized */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef8bw[priv->xtal], 14);
+
+		/* IF freq setting */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 4.75);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xd7, 0x0, 0x7);
+
+		/* Demod core latency setting */
+		data[0] = 0x13;
+		data[1] = 0xFC;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Acquisition optimization setting */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x12);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x71, 0x03, 0x07);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x15);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0xBE, 0x03);
+		break;
+	case 7000000:
+		/* TRCG Nominal Rate */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate7bw[priv->xtal], 5);
+		/*  Group delay equaliser settings for ASCOT tuners optimized */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef7bw[priv->xtal], 14);
+
+		/* IF freq setting */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 4.15);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xd7, 0x02, 0x7);
+
+		/* Demod core latency setting */
+		data[0] = 0x1A;
+		data[1] = 0xFA;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Acquisition optimization setting */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x12);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x71, 0x03, 0x07);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x15);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0xBE, 0x02);
+		break;
+	case 6000000:
+		/* TRCG Nominal Rate */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0x9F, nominalRate6bw[priv->xtal], 5);
+		/*  Group delay equaliser settings for ASCOT tuners optimized */
+		cxd2841er_write_regs(priv, I2C_SLVT,
+				0xA6, itbCoef6bw[priv->xtal], 14);
+
+		/* IF freq setting */
+		iffreq = MAKE_IFFREQ_CONFIG_XTAL(priv->xtal, 3.55);
+		data[0] = (u8) ((iffreq >> 16) & 0xff);
+		data[1] = (u8)((iffreq >> 8) & 0xff);
+		data[2] = (u8)(iffreq & 0xff);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xB6, data, 3);
+
+		/* System bandwidth setting */
+		cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xd7, 0x04, 0x7);
+
+		/* Demod core latency setting */
+		if (priv->xtal == SONY_XTAL_24000) {
+			data[0] = 0x1F;
+			data[1] = 0x79;
+		} else {
+			data[0] = 0x1A;
+			data[1] = 0xE2;
+		}
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Acquisition optimization setting */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x12);
+		cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x71, 0x07, 0x07);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x15);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0xBE, 0x02);
 		break;
 	default:
 		dev_dbg(&priv->i2c->dev, "%s(): invalid bandwidth %d\n",
-			__func__, bandwidth);
+				__func__, bandwidth);
 		return -EINVAL;
 	}
-	/* <IF freq setting> */
-	b10_b6[0] = (u8) ((iffreq >> 16) & 0xff);
-	b10_b6[1] = (u8)((iffreq >> 8) & 0xff);
-	b10_b6[2] = (u8)(iffreq & 0xff);
-	cxd2841er_write_regs(
-		priv, I2C_SLVT, 0x9f, b10_9f, sizeof(bw8mhz_b10_9f));
-	cxd2841er_write_regs(
-		priv, I2C_SLVT, 0xa6, b10_a6, sizeof(bw8mhz_b10_a6));
-	cxd2841er_write_regs(priv, I2C_SLVT, 0xb6, b10_b6, sizeof(b10_b6));
-	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xd7, d7val, 0x7);
-	cxd2841er_write_regs(
-		priv, I2C_SLVT, 0xd9, b10_d9, sizeof(bw8mhz_b10_d9));
-	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x17);
-	cxd2841er_write_regs(
-		priv, I2C_SLVT, 0x38, b17_38, sizeof(bw8mhz_b17_38));
 	return 0;
 }
 
@@ -1837,7 +2694,7 @@ static int cxd2841er_sleep_tc_to_active_c_band(struct cxd2841er_priv *priv,
 	u8 b10_b6[3];
 	u32 iffreq;
 
-	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	dev_dbg(&priv->i2c->dev, "%s() bw=%d\n", __func__, bandwidth);
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
 	switch (bandwidth) {
 	case 8000000:
@@ -1854,7 +2711,7 @@ static int cxd2841er_sleep_tc_to_active_c_band(struct cxd2841er_priv *priv,
 		iffreq = MAKE_IFFREQ_CONFIG(3.7);
 		break;
 	default:
-		dev_dbg(&priv->i2c->dev, "%s(): unsupported bandwidth %d\n",
+		dev_err(&priv->i2c->dev, "%s(): unsupported bandwidth %d\n",
 			__func__, bandwidth);
 		return -EINVAL;
 	}
@@ -1902,6 +2759,7 @@ static int cxd2841er_sleep_tc_to_active_t(struct cxd2841er_priv *priv,
 					  u32 bandwidth)
 {
 	u8 data[2] = { 0x09, 0x54 };
+	u8 data24m[3] = {0xDC, 0x6C, 0x00};
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	cxd2841er_set_ts_clock_mode(priv, SYS_DVBT);
@@ -1919,7 +2777,11 @@ static int cxd2841er_sleep_tc_to_active_t(struct cxd2841er_priv *priv,
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x30, 0x00);
 	/* Enable ADC 1 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x41, 0x1a);
-	/* xtal freq 20.5MHz */
+	/* Enable ADC 2 & 3 */
+	if (priv->xtal == SONY_XTAL_41000) {
+		data[0] = 0x0A;
+		data[1] = 0xD4;
+	}
 	cxd2841er_write_regs(priv, I2C_SLVT, 0x43, data, 2);
 	/* Enable ADC 4 */
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x18, 0x00);
@@ -1947,6 +2809,15 @@ static int cxd2841er_sleep_tc_to_active_t(struct cxd2841er_priv *priv,
 	/* TSIF setting */
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xce, 0x01, 0x01);
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xcf, 0x01, 0x01);
+
+	if (priv->xtal == SONY_XTAL_24000) {
+		/* Set SLV-T Bank : 0x10 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0xBF, 0x60);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x18);
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x24, data24m, 3);
+	}
+
 	cxd2841er_sleep_tc_to_active_t_band(priv, bandwidth);
 	/* Set SLV-T Bank : 0x00 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
@@ -1961,7 +2832,7 @@ static int cxd2841er_sleep_tc_to_active_t(struct cxd2841er_priv *priv,
 static int cxd2841er_sleep_tc_to_active_t2(struct cxd2841er_priv *priv,
 					   u32 bandwidth)
 {
-	u8 data[2] = { 0x09, 0x54 };
+	u8 data[MAX_WRITE_REGSIZE];
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	cxd2841er_set_ts_clock_mode(priv, SYS_DVBT2);
@@ -1974,12 +2845,21 @@ static int cxd2841er_sleep_tc_to_active_t2(struct cxd2841er_priv *priv,
 	/* Enable demod clock */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x2c, 0x01);
 	/* Disable RF level monitor */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x59, 0x00);
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x2f, 0x00);
 	/* Enable ADC clock */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x30, 0x00);
 	/* Enable ADC 1 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x41, 0x1a);
-	/* xtal freq 20.5MHz */
+
+	if (priv->xtal == SONY_XTAL_41000) {
+		data[0] = 0x0A;
+		data[1] = 0xD4;
+	} else {
+		data[0] = 0x09;
+		data[1] = 0x54;
+	}
+
 	cxd2841er_write_regs(priv, I2C_SLVT, 0x43, data, 2);
 	/* Enable ADC 4 */
 	cxd2841er_write_reg(priv, I2C_SLVX, 0x18, 0x00);
@@ -2002,6 +2882,10 @@ static int cxd2841er_sleep_tc_to_active_t2(struct cxd2841er_priv *priv,
 	/* Set SLV-T Bank : 0x2b */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x2b);
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x76, 0x20, 0x70);
+	/* Set SLV-T Bank : 0x23 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x23);
+	/* L1 Control setting */
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xE6, 0x00, 0x03);
 	/* Set SLV-T Bank : 0x00 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
 	/* TSIF setting */
@@ -2020,6 +2904,72 @@ static int cxd2841er_sleep_tc_to_active_t2(struct cxd2841er_priv *priv,
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x2b);
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x11, 0x20, 0x3f);
 
+	/* 24MHz Xtal setting */
+	if (priv->xtal == SONY_XTAL_24000) {
+		/* Set SLV-T Bank : 0x11 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x11);
+		data[0] = 0xEB;
+		data[1] = 0x03;
+		data[2] = 0x3B;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x33, data, 3);
+
+		/* Set SLV-T Bank : 0x20 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x20);
+		data[0] = 0x5E;
+		data[1] = 0x5E;
+		data[2] = 0x47;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x95, data, 3);
+
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x99, 0x18);
+
+		data[0] = 0x3F;
+		data[1] = 0xFF;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD9, data, 2);
+
+		/* Set SLV-T Bank : 0x24 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x24);
+		data[0] = 0x0B;
+		data[1] = 0x72;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x34, data, 2);
+
+		data[0] = 0x93;
+		data[1] = 0xF3;
+		data[2] = 0x00;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xD2, data, 3);
+
+		data[0] = 0x05;
+		data[1] = 0xB8;
+		data[2] = 0xD8;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0xDD, data, 3);
+
+		cxd2841er_write_reg(priv, I2C_SLVT, 0xE0, 0x00);
+
+		/* Set SLV-T Bank : 0x25 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x25);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0xED, 0x60);
+
+		/* Set SLV-T Bank : 0x27 */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x27);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0xFA, 0x34);
+
+		/* Set SLV-T Bank : 0x2B */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x2B);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x4B, 0x2F);
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x9E, 0x0E);
+
+		/* Set SLV-T Bank : 0x2D */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x2D);
+		data[0] = 0x89;
+		data[1] = 0x89;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x24, data, 2);
+
+		/* Set SLV-T Bank : 0x5E */
+		cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x5E);
+		data[0] = 0x24;
+		data[1] = 0x95;
+		cxd2841er_write_regs(priv, I2C_SLVT, 0x8C, data, 2);
+	}
+
 	cxd2841er_sleep_tc_to_active_t2_band(priv, bandwidth);
 
 	/* Set SLV-T Bank : 0x00 */
@@ -2032,6 +2982,84 @@ static int cxd2841er_sleep_tc_to_active_t2(struct cxd2841er_priv *priv,
 	return 0;
 }
 
+/* ISDB-Tb part */
+static int cxd2841er_sleep_tc_to_active_i(struct cxd2841er_priv *priv,
+		u32 bandwidth)
+{
+	u8 data[2] = { 0x09, 0x54 };
+	u8 data24m[2] = {0x60, 0x00};
+	u8 data24m2[3] = {0xB7, 0x1B, 0x00};
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	cxd2841er_set_ts_clock_mode(priv, SYS_DVBT);
+	/* Set SLV-X Bank : 0x00 */
+	cxd2841er_write_reg(priv, I2C_SLVX, 0x00, 0x00);
+	/* Set demod mode */
+	cxd2841er_write_reg(priv, I2C_SLVX, 0x17, 0x06);
+	/* Set SLV-T Bank : 0x00 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
+	/* Enable demod clock */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x2c, 0x01);
+	/* Enable RF level monitor */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x2f, 0x01);
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x59, 0x01);
+	/* Enable ADC clock */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x30, 0x00);
+	/* Enable ADC 1 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x41, 0x1a);
+	/* xtal freq 20.5MHz or 24M */
+	cxd2841er_write_regs(priv, I2C_SLVT, 0x43, data, 2);
+	/* Enable ADC 4 */
+	cxd2841er_write_reg(priv, I2C_SLVX, 0x18, 0x00);
+	/* ASCOT setting ON */
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xa5, 0x01, 0x01);
+	/* FEC Auto Recovery setting */
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x30, 0x01, 0x01);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x31, 0x00, 0x01);
+	/* ISDB-T initial setting */
+	/* Set SLV-T Bank : 0x00 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xce, 0x00, 0x01);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xcf, 0x00, 0x01);
+	/* Set SLV-T Bank : 0x10 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x69, 0x04, 0x07);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x6B, 0x03, 0x07);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x9D, 0x50, 0xFF);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xD3, 0x06, 0x1F);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xED, 0x00, 0x01);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xE2, 0xCE, 0x80);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xF2, 0x13, 0x10);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xDE, 0x2E, 0x3F);
+	/* Set SLV-T Bank : 0x15 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x15);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xDE, 0x02, 0x03);
+	/* Set SLV-T Bank : 0x1E */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x1E);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x73, 0x68, 0xFF);
+	/* Set SLV-T Bank : 0x63 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x63);
+	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0x81, 0x00, 0x01);
+
+	/* for xtal 24MHz */
+	/* Set SLV-T Bank : 0x10 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
+	cxd2841er_write_regs(priv, I2C_SLVT, 0xBF, data24m, 2);
+	/* Set SLV-T Bank : 0x60 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x60);
+	cxd2841er_write_regs(priv, I2C_SLVT, 0xA8, data24m2, 3);
+
+	cxd2841er_sleep_tc_to_active_i_band(priv, bandwidth);
+	/* Set SLV-T Bank : 0x00 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
+	/* Disable HiZ Setting 1 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x80, 0x28);
+	/* Disable HiZ Setting 2 */
+	cxd2841er_write_reg(priv, I2C_SLVT, 0x81, 0x00);
+	priv->state = STATE_ACTIVE_TC;
+	return 0;
+}
+
 static int cxd2841er_sleep_tc_to_active_c(struct cxd2841er_priv *priv,
 					  u32 bandwidth)
 {
@@ -2079,7 +3107,7 @@ static int cxd2841er_sleep_tc_to_active_c(struct cxd2841er_priv *priv,
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xce, 0x01, 0x01);
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xcf, 0x01, 0x01);
 
-	cxd2841er_sleep_tc_to_active_c_band(priv, 8000000);
+	cxd2841er_sleep_tc_to_active_c_band(priv, bandwidth);
 	/* Set SLV-T Bank : 0x00 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
 	/* Disable HiZ Setting 1 */
@@ -2094,8 +3122,6 @@ static int cxd2841er_get_frontend(struct dvb_frontend *fe,
 				  struct dtv_frontend_properties *p)
 {
 	enum fe_status status = 0;
-	u16 strength = 0, snr = 0;
-	u32 errors = 0, ber = 0;
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
@@ -2104,32 +3130,18 @@ static int cxd2841er_get_frontend(struct dvb_frontend *fe,
 	else if (priv->state == STATE_ACTIVE_TC)
 		cxd2841er_read_status_tc(fe, &status);
 
+	cxd2841er_read_signal_strength(fe);
+
 	if (status & FE_HAS_LOCK) {
-		cxd2841er_read_signal_strength(fe, &strength);
-		p->strength.len = 1;
-		p->strength.stat[0].scale = FE_SCALE_RELATIVE;
-		p->strength.stat[0].uvalue = strength;
-		cxd2841er_read_snr(fe, &snr);
-		p->cnr.len = 1;
-		p->cnr.stat[0].scale = FE_SCALE_DECIBEL;
-		p->cnr.stat[0].svalue = snr;
-		cxd2841er_read_ucblocks(fe, &errors);
-		p->block_error.len = 1;
-		p->block_error.stat[0].scale = FE_SCALE_COUNTER;
-		p->block_error.stat[0].uvalue = errors;
-		cxd2841er_read_ber(fe, &ber);
-		p->post_bit_error.len = 1;
-		p->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
-		p->post_bit_error.stat[0].uvalue = ber;
+		cxd2841er_read_snr(fe);
+		cxd2841er_read_ucblocks(fe);
+
+		cxd2841er_read_ber(fe);
 	} else {
-		p->strength.len = 1;
-		p->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-		p->cnr.len = 1;
 		p->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-		p->block_error.len = 1;
 		p->block_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-		p->post_bit_error.len = 1;
 		p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+		p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	}
 	return 0;
 }
@@ -2142,10 +3154,10 @@ static int cxd2841er_set_frontend_s(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	u32 symbol_rate = p->symbol_rate/1000;
 
-	dev_dbg(&priv->i2c->dev, "%s(): %s frequency=%d symbol_rate=%d\n",
+	dev_dbg(&priv->i2c->dev, "%s(): %s frequency=%d symbol_rate=%d xtal=%d\n",
 		__func__,
 		(p->delivery_system == SYS_DVBS ? "DVB-S" : "DVB-S2"),
-		 p->frequency, symbol_rate);
+		 p->frequency, symbol_rate, priv->xtal);
 	switch (priv->state) {
 	case STATE_SLEEP_S:
 		ret = cxd2841er_sleep_s_to_active_s(
@@ -2189,6 +3201,13 @@ static int cxd2841er_set_frontend_s(struct dvb_frontend *fe)
 			__func__, carr_offset);
 	}
 done:
+	/* Reset stats */
+	p->strength.stat[0].scale = FE_SCALE_RELATIVE;
+	p->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	p->block_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
 	return ret;
 }
 
@@ -2199,7 +3218,8 @@ static int cxd2841er_set_frontend_tc(struct dvb_frontend *fe)
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 
-	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	dev_dbg(&priv->i2c->dev, "%s() delivery_system=%d bandwidth_hz=%d\n",
+		 __func__, p->delivery_system, p->bandwidth_hz);
 	if (p->delivery_system == SYS_DVBT) {
 		priv->system = SYS_DVBT;
 		switch (priv->state) {
@@ -2233,9 +3253,33 @@ static int cxd2841er_set_frontend_tc(struct dvb_frontend *fe)
 				__func__, priv->state);
 			ret = -EINVAL;
 		}
+	} else if (p->delivery_system == SYS_ISDBT) {
+		priv->system = SYS_ISDBT;
+		switch (priv->state) {
+		case STATE_SLEEP_TC:
+			ret = cxd2841er_sleep_tc_to_active_i(
+					priv, p->bandwidth_hz);
+			break;
+		case STATE_ACTIVE_TC:
+			ret = cxd2841er_retune_active(priv, p);
+			break;
+		default:
+			dev_dbg(&priv->i2c->dev, "%s(): invalid state %d\n",
+					__func__, priv->state);
+			ret = -EINVAL;
+		}
 	} else if (p->delivery_system == SYS_DVBC_ANNEX_A ||
 			p->delivery_system == SYS_DVBC_ANNEX_C) {
 		priv->system = SYS_DVBC_ANNEX_A;
+		/* correct bandwidth */
+		if (p->bandwidth_hz != 6000000 &&
+				p->bandwidth_hz != 7000000 &&
+				p->bandwidth_hz != 8000000) {
+			p->bandwidth_hz = 8000000;
+			dev_dbg(&priv->i2c->dev, "%s(): forcing bandwidth to %d\n",
+					__func__, p->bandwidth_hz);
+		}
+
 		switch (priv->state) {
 		case STATE_SLEEP_TC:
 			ret = cxd2841er_sleep_tc_to_active_c(
@@ -2321,7 +3365,8 @@ static int cxd2841er_tune_tc(struct dvb_frontend *fe,
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 
-	dev_dbg(&priv->i2c->dev, "%s(): re_tune %d\n", __func__, re_tune);
+	dev_dbg(&priv->i2c->dev, "%s(): re_tune %d bandwidth=%d\n", __func__,
+			re_tune, p->bandwidth_hz);
 	if (re_tune) {
 		ret = cxd2841er_set_frontend_tc(fe);
 		if (ret)
@@ -2329,7 +3374,16 @@ static int cxd2841er_tune_tc(struct dvb_frontend *fe,
 		cxd2841er_read_status_tc(fe, status);
 		if (*status & FE_HAS_LOCK) {
 			switch (priv->system) {
+			case SYS_ISDBT:
+				ret = cxd2841er_get_carrier_offset_i(
+						priv, p->bandwidth_hz,
+						&carrier_offset);
+				break;
 			case SYS_DVBT:
+				ret = cxd2841er_get_carrier_offset_t(
+					priv, p->bandwidth_hz,
+					&carrier_offset);
+				break;
 			case SYS_DVBT2:
 				ret = cxd2841er_get_carrier_offset_t2(
 					priv, p->bandwidth_hz,
@@ -2382,6 +3436,9 @@ static int cxd2841er_sleep_tc(struct dvb_frontend *fe)
 		case SYS_DVBT2:
 			cxd2841er_active_t2_to_sleep_tc(priv);
 			break;
+		case SYS_ISDBT:
+			cxd2841er_active_i_to_sleep_tc(priv);
+			break;
 		case SYS_DVBC_ANNEX_A:
 			cxd2841er_active_c_to_sleep_tc(priv);
 			break;
@@ -2512,23 +3569,57 @@ static enum dvbfe_algo cxd2841er_get_algo(struct dvb_frontend *fe)
 	return DVBFE_ALGO_HW;
 }
 
+static void cxd2841er_init_stats(struct dvb_frontend *fe)
+{
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+
+	p->strength.len = 1;
+	p->strength.stat[0].scale = FE_SCALE_RELATIVE;
+	p->cnr.len = 1;
+	p->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	p->block_error.len = 1;
+	p->block_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	p->post_bit_error.len = 1;
+	p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	p->post_bit_count.len = 1;
+	p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+}
+
+
 static int cxd2841er_init_s(struct dvb_frontend *fe)
 {
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
 
+	/* sanity. force demod to SHUTDOWN state */
+	if (priv->state == STATE_SLEEP_S) {
+		dev_dbg(&priv->i2c->dev, "%s() forcing sleep->shutdown\n",
+				__func__);
+		cxd2841er_sleep_s_to_shutdown(priv);
+	} else if (priv->state == STATE_ACTIVE_S) {
+		dev_dbg(&priv->i2c->dev, "%s() forcing active->sleep->shutdown\n",
+				__func__);
+		cxd2841er_active_s_to_sleep_s(priv);
+		cxd2841er_sleep_s_to_shutdown(priv);
+	}
+
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	cxd2841er_shutdown_to_sleep_s(priv);
 	/* SONY_DEMOD_CONFIG_SAT_IFAGCNEG set to 1 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0xa0);
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xb9, 0x01, 0x01);
+
+	cxd2841er_init_stats(fe);
+
 	return 0;
 }
 
 static int cxd2841er_init_tc(struct dvb_frontend *fe)
 {
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 
-	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	dev_dbg(&priv->i2c->dev, "%s() bandwidth_hz=%d\n",
+			__func__, p->bandwidth_hz);
 	cxd2841er_shutdown_to_sleep_tc(priv);
 	/* SONY_DEMOD_CONFIG_IFAGCNEG = 1 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x10);
@@ -2538,12 +3629,14 @@ static int cxd2841er_init_tc(struct dvb_frontend *fe)
 	/* SONY_DEMOD_CONFIG_PARALLEL_SEL = 1 */
 	cxd2841er_write_reg(priv, I2C_SLVT, 0x00, 0x00);
 	cxd2841er_set_reg_bits(priv, I2C_SLVT, 0xc4, 0x00, 0x80);
+
+	cxd2841er_init_stats(fe);
+
 	return 0;
 }
 
 static struct dvb_frontend_ops cxd2841er_dvbs_s2_ops;
-static struct dvb_frontend_ops cxd2841er_dvbt_t2_ops;
-static struct dvb_frontend_ops cxd2841er_dvbc_ops;
+static struct dvb_frontend_ops cxd2841er_t_c_ops;
 
 static struct dvb_frontend *cxd2841er_attach(struct cxd2841er_config *cfg,
 					     struct i2c_adapter *i2c,
@@ -2551,6 +3644,7 @@ static struct dvb_frontend *cxd2841er_attach(struct cxd2841er_config *cfg,
 {
 	u8 chip_id = 0;
 	const char *type;
+	const char *name;
 	struct cxd2841er_priv *priv = NULL;
 
 	/* allocate memory for the internal state */
@@ -2561,46 +3655,49 @@ static struct dvb_frontend *cxd2841er_attach(struct cxd2841er_config *cfg,
 	priv->config = cfg;
 	priv->i2c_addr_slvx = (cfg->i2c_addr + 4) >> 1;
 	priv->i2c_addr_slvt = (cfg->i2c_addr) >> 1;
-	/* create dvb_frontend */
-	switch (system) {
-	case SYS_DVBS:
-		memcpy(&priv->frontend.ops,
-			&cxd2841er_dvbs_s2_ops,
-			sizeof(struct dvb_frontend_ops));
-		type = "S/S2";
-		break;
-	case SYS_DVBT:
-		memcpy(&priv->frontend.ops,
-			&cxd2841er_dvbt_t2_ops,
-			sizeof(struct dvb_frontend_ops));
-		type = "T/T2";
-		break;
-	case SYS_DVBC_ANNEX_A:
-		memcpy(&priv->frontend.ops,
-			&cxd2841er_dvbc_ops,
-			sizeof(struct dvb_frontend_ops));
-		type = "C/C2";
-		break;
-	default:
-		kfree(priv);
-		return NULL;
-	}
+	priv->xtal = cfg->xtal;
 	priv->frontend.demodulator_priv = priv;
 	dev_info(&priv->i2c->dev,
-		"%s(): attaching CXD2841ER DVB-%s frontend\n",
-		__func__, type);
-	dev_info(&priv->i2c->dev,
 		"%s(): I2C adapter %p SLVX addr %x SLVT addr %x\n",
 		__func__, priv->i2c,
 		priv->i2c_addr_slvx, priv->i2c_addr_slvt);
 	chip_id = cxd2841er_chip_id(priv);
-	if (chip_id != CXD2841ER_CHIP_ID) {
+	switch (chip_id) {
+	case CXD2841ER_CHIP_ID:
+		snprintf(cxd2841er_t_c_ops.info.name, 128,
+				"Sony CXD2841ER DVB-T/T2/C demodulator");
+		name = "CXD2841ER";
+		break;
+	case CXD2854ER_CHIP_ID:
+		snprintf(cxd2841er_t_c_ops.info.name, 128,
+				"Sony CXD2854ER DVB-T/T2/C and ISDB-T demodulator");
+		cxd2841er_t_c_ops.delsys[3] = SYS_ISDBT;
+		name = "CXD2854ER";
+		break;
+	default:
 		dev_err(&priv->i2c->dev, "%s(): invalid chip ID 0x%02x\n",
-			__func__, chip_id);
+				__func__, chip_id);
 		priv->frontend.demodulator_priv = NULL;
 		kfree(priv);
 		return NULL;
 	}
+
+	/* create dvb_frontend */
+	if (system == SYS_DVBS) {
+		memcpy(&priv->frontend.ops,
+			&cxd2841er_dvbs_s2_ops,
+			sizeof(struct dvb_frontend_ops));
+		type = "S/S2";
+	} else {
+		memcpy(&priv->frontend.ops,
+			&cxd2841er_t_c_ops,
+			sizeof(struct dvb_frontend_ops));
+		type = "T/T2/C/ISDB-T";
+	}
+
+	dev_info(&priv->i2c->dev,
+		"%s(): attaching %s DVB-%s frontend\n",
+		__func__, name, type);
 	dev_info(&priv->i2c->dev, "%s(): chip ID 0x%02x OK.\n",
 		__func__, chip_id);
 	return &priv->frontend;
@@ -2613,19 +3710,12 @@ struct dvb_frontend *cxd2841er_attach_s(struct cxd2841er_config *cfg,
 }
 EXPORT_SYMBOL(cxd2841er_attach_s);
 
-struct dvb_frontend *cxd2841er_attach_t(struct cxd2841er_config *cfg,
+struct dvb_frontend *cxd2841er_attach_t_c(struct cxd2841er_config *cfg,
 					struct i2c_adapter *i2c)
 {
-	return cxd2841er_attach(cfg, i2c, SYS_DVBT);
+	return cxd2841er_attach(cfg, i2c, 0);
 }
-EXPORT_SYMBOL(cxd2841er_attach_t);
-
-struct dvb_frontend *cxd2841er_attach_c(struct cxd2841er_config *cfg,
-					struct i2c_adapter *i2c)
-{
-	return cxd2841er_attach(cfg, i2c, SYS_DVBC_ANNEX_A);
-}
-EXPORT_SYMBOL(cxd2841er_attach_c);
+EXPORT_SYMBOL(cxd2841er_attach_t_c);
 
 static struct dvb_frontend_ops cxd2841er_dvbs_s2_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
@@ -2655,10 +3745,10 @@ static struct dvb_frontend_ops cxd2841er_dvbs_s2_ops = {
 	.tune = cxd2841er_tune_s
 };
 
-static struct  dvb_frontend_ops cxd2841er_dvbt_t2_ops = {
-	.delsys = { SYS_DVBT, SYS_DVBT2 },
+static struct  dvb_frontend_ops cxd2841er_t_c_ops = {
+	.delsys = { SYS_DVBT, SYS_DVBT2, SYS_DVBC_ANNEX_A },
 	.info = {
-		.name	= "Sony CXD2841ER DVB-T/T2 demodulator",
+		.name	= "", /* will set in attach function */
 		.caps = FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
@@ -2691,37 +3781,6 @@ static struct  dvb_frontend_ops cxd2841er_dvbt_t2_ops = {
 	.get_frontend_algo = cxd2841er_get_algo
 };
 
-static struct  dvb_frontend_ops cxd2841er_dvbc_ops = {
-	.delsys = { SYS_DVBC_ANNEX_A },
-	.info = {
-		.name	= "Sony CXD2841ER DVB-C demodulator",
-		.caps = FE_CAN_FEC_1_2 |
-			FE_CAN_FEC_2_3 |
-			FE_CAN_FEC_3_4 |
-			FE_CAN_FEC_5_6 |
-			FE_CAN_FEC_7_8 |
-			FE_CAN_FEC_AUTO |
-			FE_CAN_QAM_16 |
-			FE_CAN_QAM_32 |
-			FE_CAN_QAM_64 |
-			FE_CAN_QAM_128 |
-			FE_CAN_QAM_256 |
-			FE_CAN_QAM_AUTO |
-			FE_CAN_INVERSION_AUTO,
-		.frequency_min = 42000000,
-		.frequency_max = 1002000000
-	},
-	.init = cxd2841er_init_tc,
-	.sleep = cxd2841er_sleep_tc,
-	.release = cxd2841er_release,
-	.set_frontend = cxd2841er_set_frontend_tc,
-	.get_frontend = cxd2841er_get_frontend,
-	.read_status = cxd2841er_read_status_tc,
-	.tune = cxd2841er_tune_tc,
-	.i2c_gate_ctrl = cxd2841er_i2c_gate_ctrl,
-	.get_frontend_algo = cxd2841er_get_algo,
-};
-
-MODULE_DESCRIPTION("Sony CXD2841ER DVB-C/C2/T/T2/S/S2 demodulator driver");
-MODULE_AUTHOR("Sergey Kozlov <serjk@netup.ru>");
+MODULE_DESCRIPTION("Sony CXD2841ER/CXD2854ER DVB-C/C2/T/T2/S/S2 demodulator driver");
+MODULE_AUTHOR("Sergey Kozlov <serjk@netup.ru>, Abylay Ospan <aospan@netup.ru>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/cxd2841er.h b/drivers/media/dvb-frontends/cxd2841er.h
index 3472bdd58949..62ad5f07390b 100644
--- a/drivers/media/dvb-frontends/cxd2841er.h
+++ b/drivers/media/dvb-frontends/cxd2841er.h
@@ -25,41 +25,39 @@
 #include <linux/kconfig.h>
 #include <linux/dvb/frontend.h>
 
+enum cxd2841er_xtal {
+	SONY_XTAL_20500, /* 20.5 MHz */
+	SONY_XTAL_24000, /* 24 MHz */
+	SONY_XTAL_41000 /* 41 MHz */
+};
+
 struct cxd2841er_config {
 	u8	i2c_addr;
+	enum cxd2841er_xtal	xtal;
 };
 
 #if IS_REACHABLE(CONFIG_DVB_CXD2841ER)
 extern struct dvb_frontend *cxd2841er_attach_s(struct cxd2841er_config *cfg,
 					       struct i2c_adapter *i2c);
 
-extern struct dvb_frontend *cxd2841er_attach_t(struct cxd2841er_config *cfg,
-					       struct i2c_adapter *i2c);
-
-extern struct dvb_frontend *cxd2841er_attach_c(struct cxd2841er_config *cfg,
+extern struct dvb_frontend *cxd2841er_attach_t_c(struct cxd2841er_config *cfg,
 					       struct i2c_adapter *i2c);
 #else
 static inline struct dvb_frontend *cxd2841er_attach_s(
 					struct cxd2841er_config *cfg,
 					struct i2c_adapter *i2c)
 {
-	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
+	pr_warn("%s: driver disabled by Kconfig\n", __func__);
 	return NULL;
 }
 
-static inline struct dvb_frontend *cxd2841er_attach_t(
+static inline struct dvb_frontend *cxd2841er_attach_t_c(
 		struct cxd2841er_config *cfg, struct i2c_adapter *i2c)
 {
-	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
+	pr_warn("%s: driver disabled by Kconfig\n", __func__);
 	return NULL;
 }
 
-static inline struct dvb_frontend *cxd2841er_attach_c(
-		struct cxd2841er_config *cfg, struct i2c_adapter *i2c)
-{
-	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
-	return NULL;
-}
 #endif
 
 #endif
diff --git a/drivers/media/dvb-frontends/cxd2841er_priv.h b/drivers/media/dvb-frontends/cxd2841er_priv.h
index 33e2f495277b..0bbce451149f 100644
--- a/drivers/media/dvb-frontends/cxd2841er_priv.h
+++ b/drivers/media/dvb-frontends/cxd2841er_priv.h
@@ -26,6 +26,7 @@
 #define I2C_SLVT			1
 
 #define CXD2841ER_CHIP_ID		0xa7
+#define CXD2854ER_CHIP_ID		0xc1
 
 #define CXD2841ER_DVBS_POLLING_INVL	10
 
diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c
index d879dc0607f4..14c403254fe0 100644
--- a/drivers/media/dvb-frontends/dib0090.c
+++ b/drivers/media/dvb-frontends/dib0090.c
@@ -797,6 +797,8 @@ static const u16 bb_ramp_pwm_normal[] = {
 	(0  << 9) | 400, /* BB_RAMP6 */
 };
 
+#if 0
+/* Currently unused */
 static const u16 bb_ramp_pwm_boost[] = {
 	550, /* max BB gain in 10th of dB */
 	8, /* ramp_slope = 1dB of gain -> clock_ticks_per_db = clk_khz / ramp_slope -> BB_RAMP2 */
@@ -806,6 +808,7 @@ static const u16 bb_ramp_pwm_boost[] = {
 	(2  << 9) | 208, /* BB_RAMP5 = 29dB */
 	(0  << 9) | 440, /* BB_RAMP6 */
 };
+#endif
 
 static const u16 rf_ramp_pwm_cband[] = {
 	314, /* max RF gain in 10th of dB */
@@ -849,6 +852,8 @@ static const u16 rf_ramp_pwm_uhf[] = {
 	(0  << 10) | 580, /* GAIN_4_2, LNA 4 */
 };
 
+#if 0
+/* Currently unused */
 static const u16 rf_ramp_pwm_sband[] = {
 	253, /* max RF gain in 10th of dB */
 	38, /* ramp_slope = 1dB of gain -> clock_ticks_per_db = clk_khz / ramp_slope -> RF_RAMP2 */
@@ -862,6 +867,7 @@ static const u16 rf_ramp_pwm_sband[] = {
 	(0  << 10) | 0, /* GAIN_4_1, LNA 4 = 0dB */
 	(0  << 10) | 0, /* GAIN_4_2, LNA 4 */
 };
+#endif
 
 struct slope {
 	s16 range;
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index e48b741d439e..bd6d2ee0f7c9 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -1240,12 +1240,15 @@ static u32 frac_times1e6(u32 N, u32 D)
 *        and rounded. For calc used formula: 16*10^(prescaleGain[dB]/20).
 *
 */
+#if 0
+/* Currently, unused as we lack support for analog TV */
 static const u16 nicam_presc_table_val[43] = {
 	1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 4, 4,
 	5, 5, 6, 6, 7, 8, 9, 10, 11, 13, 14, 16,
 	18, 20, 23, 25, 28, 32, 36, 40, 45,
 	51, 57, 64, 71, 80, 90, 101, 113, 127
 };
+#endif
 
 /*============================================================================*/
 /*==                        END HELPER FUNCTIONS                            ==*/
diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c
index addffc33993a..447b518e287a 100644
--- a/drivers/media/dvb-frontends/ds3000.c
+++ b/drivers/media/dvb-frontends/ds3000.c
@@ -959,6 +959,15 @@ static int ds3000_set_frontend(struct dvb_frontend *fe)
 	/* enable ac coupling */
 	ds3000_writereg(state, 0x25, 0x8a);
 
+	if ((c->symbol_rate < ds3000_ops.info.symbol_rate_min) ||
+			(c->symbol_rate > ds3000_ops.info.symbol_rate_max)) {
+		dprintk("%s() symbol_rate %u out of range (%u ... %u)\n",
+				__func__, c->symbol_rate,
+				ds3000_ops.info.symbol_rate_min,
+				ds3000_ops.info.symbol_rate_max);
+		return -EINVAL;
+	}
+
 	/* enhance symbol rate performance */
 	if ((c->symbol_rate / 1000) <= 5000) {
 		value = 29777 / (c->symbol_rate / 1000) + 1;
diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c
new file mode 100644
index 000000000000..97a8982740a6
--- /dev/null
+++ b/drivers/media/dvb-frontends/helene.c
@@ -0,0 +1,1042 @@
+/*
+ * helene.c
+ *
+ * Sony HELENE DVB-S/S2 DVB-T/T2 DVB-C/C2 ISDB-T/S tuner driver (CXD2858ER)
+ *
+ * Copyright 2012 Sony Corporation
+ * Copyright (C) 2014 NetUP Inc.
+ * Copyright (C) 2014 Abylay Ospan <aospan@netup.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+  */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/dvb/frontend.h>
+#include <linux/types.h>
+#include "helene.h"
+#include "dvb_frontend.h"
+
+#define MAX_WRITE_REGSIZE 20
+
+enum helene_state {
+	STATE_UNKNOWN,
+	STATE_SLEEP,
+	STATE_ACTIVE
+};
+
+struct helene_priv {
+	u32			frequency;
+	u8			i2c_address;
+	struct i2c_adapter	*i2c;
+	enum helene_state	state;
+	void			*set_tuner_data;
+	int			(*set_tuner)(void *, int);
+	enum helene_xtal xtal;
+};
+
+#define TERR_INTERNAL_LOOPFILTER_AVAILABLE(tv_system) \
+	(((tv_system) != SONY_HELENE_DTV_DVBC_6) && \
+	 ((tv_system) != SONY_HELENE_DTV_DVBC_8)\
+	 && ((tv_system) != SONY_HELENE_DTV_DVBC2_6) && \
+	 ((tv_system) != SONY_HELENE_DTV_DVBC2_8))
+
+#define HELENE_AUTO		0xff
+#define HELENE_OFFSET(ofs)	((u8)(ofs) & 0x1F)
+#define HELENE_BW_6		0x00
+#define HELENE_BW_7		0x01
+#define HELENE_BW_8		0x02
+#define HELENE_BW_1_7		0x03
+
+enum helene_tv_system_t {
+	SONY_HELENE_TV_SYSTEM_UNKNOWN,
+	/* Terrestrial Analog */
+	SONY_HELENE_ATV_MN_EIAJ,
+	/**< System-M (Japan) (IF: Fp=5.75MHz in default) */
+	SONY_HELENE_ATV_MN_SAP,
+	/**< System-M (US)    (IF: Fp=5.75MHz in default) */
+	SONY_HELENE_ATV_MN_A2,
+	/**< System-M (Korea) (IF: Fp=5.9MHz in default) */
+	SONY_HELENE_ATV_BG,
+	/**< System-B/G       (IF: Fp=7.3MHz in default) */
+	SONY_HELENE_ATV_I,
+	/**< System-I         (IF: Fp=7.85MHz in default) */
+	SONY_HELENE_ATV_DK,
+	/**< System-D/K       (IF: Fp=7.85MHz in default) */
+	SONY_HELENE_ATV_L,
+	/**< System-L         (IF: Fp=7.85MHz in default) */
+	SONY_HELENE_ATV_L_DASH,
+	/**< System-L DASH    (IF: Fp=2.2MHz in default) */
+	/* Terrestrial/Cable Digital */
+	SONY_HELENE_DTV_8VSB,
+	/**< ATSC 8VSB        (IF: Fc=3.7MHz in default) */
+	SONY_HELENE_DTV_QAM,
+	/**< US QAM           (IF: Fc=3.7MHz in default) */
+	SONY_HELENE_DTV_ISDBT_6,
+	/**< ISDB-T 6MHzBW    (IF: Fc=3.55MHz in default) */
+	SONY_HELENE_DTV_ISDBT_7,
+	/**< ISDB-T 7MHzBW    (IF: Fc=4.15MHz in default) */
+	SONY_HELENE_DTV_ISDBT_8,
+	/**< ISDB-T 8MHzBW    (IF: Fc=4.75MHz in default) */
+	SONY_HELENE_DTV_DVBT_5,
+	/**< DVB-T 5MHzBW     (IF: Fc=3.6MHz in default) */
+	SONY_HELENE_DTV_DVBT_6,
+	/**< DVB-T 6MHzBW     (IF: Fc=3.6MHz in default) */
+	SONY_HELENE_DTV_DVBT_7,
+	/**< DVB-T 7MHzBW     (IF: Fc=4.2MHz in default) */
+	SONY_HELENE_DTV_DVBT_8,
+	/**< DVB-T 8MHzBW     (IF: Fc=4.8MHz in default) */
+	SONY_HELENE_DTV_DVBT2_1_7,
+	/**< DVB-T2 1.7MHzBW  (IF: Fc=3.5MHz in default) */
+	SONY_HELENE_DTV_DVBT2_5,
+	/**< DVB-T2 5MHzBW    (IF: Fc=3.6MHz in default) */
+	SONY_HELENE_DTV_DVBT2_6,
+	/**< DVB-T2 6MHzBW    (IF: Fc=3.6MHz in default) */
+	SONY_HELENE_DTV_DVBT2_7,
+	/**< DVB-T2 7MHzBW    (IF: Fc=4.2MHz in default) */
+	SONY_HELENE_DTV_DVBT2_8,
+	/**< DVB-T2 8MHzBW    (IF: Fc=4.8MHz in default) */
+	SONY_HELENE_DTV_DVBC_6,
+	/**< DVB-C 6MHzBW     (IF: Fc=3.7MHz in default) */
+	SONY_HELENE_DTV_DVBC_8,
+	/**< DVB-C 8MHzBW     (IF: Fc=4.9MHz in default) */
+	SONY_HELENE_DTV_DVBC2_6,
+	/**< DVB-C2 6MHzBW    (IF: Fc=3.7MHz in default) */
+	SONY_HELENE_DTV_DVBC2_8,
+	/**< DVB-C2 8MHzBW    (IF: Fc=4.9MHz in default) */
+	SONY_HELENE_DTV_DTMB,
+	/**< DTMB             (IF: Fc=5.1MHz in default) */
+	/* Satellite */
+	SONY_HELENE_STV_ISDBS,
+	/**< ISDB-S */
+	SONY_HELENE_STV_DVBS,
+	/**< DVB-S */
+	SONY_HELENE_STV_DVBS2,
+	/**< DVB-S2 */
+
+	SONY_HELENE_ATV_MIN = SONY_HELENE_ATV_MN_EIAJ,
+	/**< Minimum analog terrestrial system */
+	SONY_HELENE_ATV_MAX = SONY_HELENE_ATV_L_DASH,
+	/**< Maximum analog terrestrial system */
+	SONY_HELENE_DTV_MIN = SONY_HELENE_DTV_8VSB,
+	/**< Minimum digital terrestrial system */
+	SONY_HELENE_DTV_MAX = SONY_HELENE_DTV_DTMB,
+	/**< Maximum digital terrestrial system */
+	SONY_HELENE_TERR_TV_SYSTEM_NUM,
+	/**< Number of supported terrestrial broadcasting system */
+	SONY_HELENE_STV_MIN = SONY_HELENE_STV_ISDBS,
+	/**< Minimum satellite system */
+	SONY_HELENE_STV_MAX = SONY_HELENE_STV_DVBS2
+	/**< Maximum satellite system */
+};
+
+struct helene_terr_adjust_param_t {
+	/* < Addr:0x69 Bit[6:4] : RFVGA gain.
+	 * 0xFF means Auto. (RF_GAIN_SEL = 1)
+	 */
+	uint8_t RF_GAIN;
+	/* < Addr:0x69 Bit[3:0] : IF_BPF gain.
+	*/
+	uint8_t IF_BPF_GC;
+	/* < Addr:0x6B Bit[3:0] : RF overload
+	 * RF input detect level. (FRF <= 172MHz)
+	*/
+	uint8_t RFOVLD_DET_LV1_VL;
+	/* < Addr:0x6B Bit[3:0] : RF overload
+	 * RF input detect level. (172MHz < FRF <= 464MHz)
+	*/
+	uint8_t RFOVLD_DET_LV1_VH;
+	/* < Addr:0x6B Bit[3:0] : RF overload
+	 * RF input detect level. (FRF > 464MHz)
+	*/
+	uint8_t RFOVLD_DET_LV1_U;
+	/* < Addr:0x6C Bit[2:0] :
+	 * Internal RFAGC detect level. (FRF <= 172MHz)
+	*/
+	uint8_t IFOVLD_DET_LV_VL;
+	/* < Addr:0x6C Bit[2:0] :
+	 * Internal RFAGC detect level. (172MHz < FRF <= 464MHz)
+	*/
+	uint8_t IFOVLD_DET_LV_VH;
+	/* < Addr:0x6C Bit[2:0] :
+	 * Internal RFAGC detect level. (FRF > 464MHz)
+	*/
+	uint8_t IFOVLD_DET_LV_U;
+	/* < Addr:0x6D Bit[5:4] :
+	 * IF filter center offset.
+	*/
+	uint8_t IF_BPF_F0;
+	/* < Addr:0x6D Bit[1:0] :
+	 * 6MHzBW(0x00) or 7MHzBW(0x01)
+	 * or 8MHzBW(0x02) or 1.7MHzBW(0x03)
+	*/
+	uint8_t BW;
+	/* < Addr:0x6E Bit[4:0] :
+	 * 5bit signed. IF offset (kHz) = FIF_OFFSET x 50
+	*/
+	uint8_t FIF_OFFSET;
+	/* < Addr:0x6F Bit[4:0] :
+	 * 5bit signed. BW offset (kHz) =
+	 * BW_OFFSET x 50 (BW_OFFSET x 10 in 1.7MHzBW)
+	*/
+	uint8_t BW_OFFSET;
+	/* < Addr:0x9C Bit[0]   :
+	 * Local polarity. (0: Upper Local, 1: Lower Local)
+	*/
+	uint8_t IS_LOWERLOCAL;
+};
+
+static const struct helene_terr_adjust_param_t
+terr_params[SONY_HELENE_TERR_TV_SYSTEM_NUM] = {
+	/*< SONY_HELENE_TV_SYSTEM_UNKNOWN */
+	{HELENE_AUTO, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		HELENE_BW_6, HELENE_OFFSET(0),  HELENE_OFFSET(0),  0x00},
+	/* Analog */
+	/**< SONY_HELENE_ATV_MN_EIAJ   (System-M (Japan)) */
+	{HELENE_AUTO, 0x05, 0x03, 0x06, 0x03, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(0),  HELENE_OFFSET(1),  0x00},
+	/**< SONY_HELENE_ATV_MN_SAP    (System-M (US)) */
+	{HELENE_AUTO, 0x05, 0x03, 0x06, 0x03, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(0),  HELENE_OFFSET(1),  0x00},
+	{HELENE_AUTO, 0x05, 0x03, 0x06, 0x03, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(3),  HELENE_OFFSET(1),  0x00},
+	/**< SONY_HELENE_ATV_MN_A2     (System-M (Korea)) */
+	{HELENE_AUTO, 0x05, 0x03, 0x06, 0x03, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_7,  HELENE_OFFSET(11), HELENE_OFFSET(5),  0x00},
+	/**< SONY_HELENE_ATV_BG        (System-B/G) */
+	{HELENE_AUTO, 0x05, 0x03, 0x06, 0x03, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(2),  HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_ATV_I         (System-I) */
+	{HELENE_AUTO, 0x05, 0x03, 0x06, 0x03, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(2),  HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_ATV_DK        (System-D/K) */
+	{HELENE_AUTO, 0x03, 0x04, 0x0A, 0x04, 0x04, 0x04, 0x04, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(2),  HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_ATV_L         (System-L) */
+	{HELENE_AUTO, 0x03, 0x04, 0x0A, 0x04, 0x04, 0x04, 0x04, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(-1), HELENE_OFFSET(4),  0x00},
+	/**< SONY_HELENE_ATV_L_DASH    (System-L DASH) */
+	/* Digital */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x03, 0x03, 0x03, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-6), HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_DTV_8VSB      (ATSC 8VSB) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-6), HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_DTV_QAM       (US QAM) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-9), HELENE_OFFSET(-5), 0x00},
+	/**< SONY_HELENE_DTV_ISDBT_6   (ISDB-T 6MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_7,  HELENE_OFFSET(-7), HELENE_OFFSET(-6), 0x00},
+	/**< SONY_HELENE_DTV_ISDBT_7   (ISDB-T 7MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(-5), HELENE_OFFSET(-7), 0x00},
+	/**< SONY_HELENE_DTV_ISDBT_8   (ISDB-T 8MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-8), HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_DTV_DVBT_5    (DVB-T 5MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-8), HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_DTV_DVBT_6    (DVB-T 6MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_7,  HELENE_OFFSET(-6), HELENE_OFFSET(-5), 0x00},
+	/**< SONY_HELENE_DTV_DVBT_7    (DVB-T 7MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(-4), HELENE_OFFSET(-6), 0x00},
+	/**< SONY_HELENE_DTV_DVBT_8    (DVB-T 8MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_1_7, HELENE_OFFSET(-10), HELENE_OFFSET(-10), 0x00},
+	/**< SONY_HELENE_DTV_DVBT2_1_7 (DVB-T2 1.7MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-8), HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_DTV_DVBT2_5   (DVB-T2 5MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-8), HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_DTV_DVBT2_6   (DVB-T2 6MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_7,  HELENE_OFFSET(-6), HELENE_OFFSET(-5), 0x00},
+	/**< SONY_HELENE_DTV_DVBT2_7   (DVB-T2 7MHzBW) */
+	{HELENE_AUTO, 0x09, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(-4), HELENE_OFFSET(-6), 0x00},
+	/**< SONY_HELENE_DTV_DVBT2_8   (DVB-T2 8MHzBW) */
+	{HELENE_AUTO, 0x05, 0x02, 0x02, 0x02, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-6), HELENE_OFFSET(-4), 0x00},
+	/**< SONY_HELENE_DTV_DVBC_6    (DVB-C 6MHzBW) */
+	{HELENE_AUTO, 0x05, 0x02, 0x02, 0x02, 0x01, 0x01, 0x01, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(-2), HELENE_OFFSET(-3), 0x00},
+	/**< SONY_HELENE_DTV_DVBC_8    (DVB-C 8MHzBW) */
+	{HELENE_AUTO, 0x03, 0x09, 0x09, 0x09, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_6,  HELENE_OFFSET(-6), HELENE_OFFSET(-2), 0x00},
+	/**< SONY_HELENE_DTV_DVBC2_6   (DVB-C2 6MHzBW) */
+	{HELENE_AUTO, 0x03, 0x09, 0x09, 0x09, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(-2), HELENE_OFFSET(0),  0x00},
+	/**< SONY_HELENE_DTV_DVBC2_8   (DVB-C2 8MHzBW) */
+	{HELENE_AUTO, 0x04, 0x0B, 0x0B, 0x0B, 0x02, 0x02, 0x02, 0x00,
+		HELENE_BW_8,  HELENE_OFFSET(2),  HELENE_OFFSET(1),  0x00}
+	/**< SONY_HELENE_DTV_DTMB      (DTMB) */
+};
+
+static void helene_i2c_debug(struct helene_priv *priv,
+		u8 reg, u8 write, const u8 *data, u32 len)
+{
+	dev_dbg(&priv->i2c->dev, "helene: I2C %s reg 0x%02x size %d\n",
+			(write == 0 ? "read" : "write"), reg, len);
+	print_hex_dump_bytes("helene: I2C data: ",
+			DUMP_PREFIX_OFFSET, data, len);
+}
+
+static int helene_write_regs(struct helene_priv *priv,
+		u8 reg, const u8 *data, u32 len)
+{
+	int ret;
+	u8 buf[MAX_WRITE_REGSIZE + 1];
+	struct i2c_msg msg[1] = {
+		{
+			.addr = priv->i2c_address,
+			.flags = 0,
+			.len = len + 1,
+			.buf = buf,
+		}
+	};
+
+	if (len + 1 > sizeof(buf)) {
+		dev_warn(&priv->i2c->dev,
+				"wr reg=%04x: len=%d vs %Zu is too big!\n",
+				reg, len + 1, sizeof(buf));
+		return -E2BIG;
+	}
+
+	helene_i2c_debug(priv, reg, 1, data, len);
+	buf[0] = reg;
+	memcpy(&buf[1], data, len);
+	ret = i2c_transfer(priv->i2c, msg, 1);
+	if (ret >= 0 && ret != 1)
+		ret = -EREMOTEIO;
+	if (ret < 0) {
+		dev_warn(&priv->i2c->dev,
+				"%s: i2c wr failed=%d reg=%02x len=%d\n",
+				KBUILD_MODNAME, ret, reg, len);
+		return ret;
+	}
+	return 0;
+}
+
+static int helene_write_reg(struct helene_priv *priv, u8 reg, u8 val)
+{
+	return helene_write_regs(priv, reg, &val, 1);
+}
+
+static int helene_read_regs(struct helene_priv *priv,
+		u8 reg, u8 *val, u32 len)
+{
+	int ret;
+	struct i2c_msg msg[2] = {
+		{
+			.addr = priv->i2c_address,
+			.flags = 0,
+			.len = 1,
+			.buf = &reg,
+		}, {
+			.addr = priv->i2c_address,
+			.flags = I2C_M_RD,
+			.len = len,
+			.buf = val,
+		}
+	};
+
+	ret = i2c_transfer(priv->i2c, &msg[0], 1);
+	if (ret >= 0 && ret != 1)
+		ret = -EREMOTEIO;
+	if (ret < 0) {
+		dev_warn(&priv->i2c->dev,
+				"%s: I2C rw failed=%d addr=%02x reg=%02x\n",
+				KBUILD_MODNAME, ret, priv->i2c_address, reg);
+		return ret;
+	}
+	ret = i2c_transfer(priv->i2c, &msg[1], 1);
+	if (ret >= 0 && ret != 1)
+		ret = -EREMOTEIO;
+	if (ret < 0) {
+		dev_warn(&priv->i2c->dev,
+				"%s: i2c rd failed=%d addr=%02x reg=%02x\n",
+				KBUILD_MODNAME, ret, priv->i2c_address, reg);
+		return ret;
+	}
+	helene_i2c_debug(priv, reg, 0, val, len);
+	return 0;
+}
+
+static int helene_read_reg(struct helene_priv *priv, u8 reg, u8 *val)
+{
+	return helene_read_regs(priv, reg, val, 1);
+}
+
+static int helene_set_reg_bits(struct helene_priv *priv,
+		u8 reg, u8 data, u8 mask)
+{
+	int res;
+	u8 rdata;
+
+	if (mask != 0xff) {
+		res = helene_read_reg(priv, reg, &rdata);
+		if (res != 0)
+			return res;
+		data = ((data & mask) | (rdata & (mask ^ 0xFF)));
+	}
+	return helene_write_reg(priv, reg, data);
+}
+
+static int helene_enter_power_save(struct helene_priv *priv)
+{
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	if (priv->state == STATE_SLEEP)
+		return 0;
+
+	/* Standby setting for CPU */
+	helene_write_reg(priv, 0x88, 0x0);
+
+	/* Standby setting for internal logic block */
+	helene_write_reg(priv, 0x87, 0xC0);
+
+	priv->state = STATE_SLEEP;
+	return 0;
+}
+
+static int helene_leave_power_save(struct helene_priv *priv)
+{
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	if (priv->state == STATE_ACTIVE)
+		return 0;
+
+	/* Standby setting for internal logic block */
+	helene_write_reg(priv, 0x87, 0xC4);
+
+	/* Standby setting for CPU */
+	helene_write_reg(priv, 0x88, 0x40);
+
+	priv->state = STATE_ACTIVE;
+	return 0;
+}
+
+static int helene_init(struct dvb_frontend *fe)
+{
+	struct helene_priv *priv = fe->tuner_priv;
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	return helene_leave_power_save(priv);
+}
+
+static int helene_release(struct dvb_frontend *fe)
+{
+	struct helene_priv *priv = fe->tuner_priv;
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	kfree(fe->tuner_priv);
+	fe->tuner_priv = NULL;
+	return 0;
+}
+
+static int helene_sleep(struct dvb_frontend *fe)
+{
+	struct helene_priv *priv = fe->tuner_priv;
+
+	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
+	helene_enter_power_save(priv);
+	return 0;
+}
+
+static enum helene_tv_system_t helene_get_tv_system(struct dvb_frontend *fe)
+{
+	enum helene_tv_system_t system = SONY_HELENE_TV_SYSTEM_UNKNOWN;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	struct helene_priv *priv = fe->tuner_priv;
+
+	if (p->delivery_system == SYS_DVBT) {
+		if (p->bandwidth_hz <= 5000000)
+			system = SONY_HELENE_DTV_DVBT_5;
+		else if (p->bandwidth_hz <= 6000000)
+			system = SONY_HELENE_DTV_DVBT_6;
+		else if (p->bandwidth_hz <= 7000000)
+			system = SONY_HELENE_DTV_DVBT_7;
+		else if (p->bandwidth_hz <= 8000000)
+			system = SONY_HELENE_DTV_DVBT_8;
+		else {
+			system = SONY_HELENE_DTV_DVBT_8;
+			p->bandwidth_hz = 8000000;
+		}
+	} else if (p->delivery_system == SYS_DVBT2) {
+		if (p->bandwidth_hz <= 5000000)
+			system = SONY_HELENE_DTV_DVBT2_5;
+		else if (p->bandwidth_hz <= 6000000)
+			system = SONY_HELENE_DTV_DVBT2_6;
+		else if (p->bandwidth_hz <= 7000000)
+			system = SONY_HELENE_DTV_DVBT2_7;
+		else if (p->bandwidth_hz <= 8000000)
+			system = SONY_HELENE_DTV_DVBT2_8;
+		else {
+			system = SONY_HELENE_DTV_DVBT2_8;
+			p->bandwidth_hz = 8000000;
+		}
+	} else if (p->delivery_system == SYS_DVBS) {
+		system = SONY_HELENE_STV_DVBS;
+	} else if (p->delivery_system == SYS_DVBS2) {
+		system = SONY_HELENE_STV_DVBS2;
+	} else if (p->delivery_system == SYS_ISDBS) {
+		system = SONY_HELENE_STV_ISDBS;
+	} else if (p->delivery_system == SYS_ISDBT) {
+		if (p->bandwidth_hz <= 6000000)
+			system = SONY_HELENE_DTV_ISDBT_6;
+		else if (p->bandwidth_hz <= 7000000)
+			system = SONY_HELENE_DTV_ISDBT_7;
+		else if (p->bandwidth_hz <= 8000000)
+			system = SONY_HELENE_DTV_ISDBT_8;
+		else {
+			system = SONY_HELENE_DTV_ISDBT_8;
+			p->bandwidth_hz = 8000000;
+		}
+	} else if (p->delivery_system == SYS_DVBC_ANNEX_A) {
+		if (p->bandwidth_hz <= 6000000)
+			system = SONY_HELENE_DTV_DVBC_6;
+		else if (p->bandwidth_hz <= 8000000)
+			system = SONY_HELENE_DTV_DVBC_8;
+	}
+	dev_dbg(&priv->i2c->dev,
+			"%s(): HELENE DTV system %d (delsys %d, bandwidth %d)\n",
+			__func__, (int)system, p->delivery_system,
+			p->bandwidth_hz);
+	return system;
+}
+
+static int helene_set_params_s(struct dvb_frontend *fe)
+{
+	u8 data[MAX_WRITE_REGSIZE];
+	u32 frequency;
+	enum helene_tv_system_t tv_system;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	struct helene_priv *priv = fe->tuner_priv;
+	int frequencykHz = p->frequency;
+	uint32_t frequency4kHz = 0;
+	u32 symbol_rate = p->symbol_rate/1000;
+
+	dev_dbg(&priv->i2c->dev, "%s(): tune frequency %dkHz sr=%uKsps\n",
+			__func__, frequencykHz, symbol_rate);
+	tv_system = helene_get_tv_system(fe);
+
+	if (tv_system == SONY_HELENE_TV_SYSTEM_UNKNOWN) {
+		dev_err(&priv->i2c->dev, "%s(): unknown DTV system\n",
+				__func__);
+		return -EINVAL;
+	}
+	/* RF switch turn to satellite */
+	if (priv->set_tuner)
+		priv->set_tuner(priv->set_tuner_data, 0);
+	frequency = roundup(p->frequency / 1000, 1);
+
+	/* Disable IF signal output */
+	helene_write_reg(priv, 0x15, 0x02);
+
+	/* RFIN matching in power save (Sat) reset */
+	helene_write_reg(priv, 0x43, 0x06);
+
+	/* Analog block setting (0x6A, 0x6B) */
+	data[0] = 0x00;
+	data[1] = 0x00;
+	helene_write_regs(priv, 0x6A, data, 2);
+	helene_write_reg(priv, 0x75, 0x99);
+	helene_write_reg(priv, 0x9D, 0x00);
+
+	/* Tuning setting for CPU (0x61) */
+	helene_write_reg(priv, 0x61, 0x07);
+
+	/* Satellite mode select (0x01) */
+	helene_write_reg(priv, 0x01, 0x01);
+
+	/* Clock enable for internal logic block, CPU wake-up (0x04, 0x05) */
+	data[0] = 0xC4;
+	data[1] = 0x40;
+
+	switch (priv->xtal) {
+	case SONY_HELENE_XTAL_16000:
+		data[2] = 0x02;
+		break;
+	case SONY_HELENE_XTAL_20500:
+		data[2] = 0x02;
+		break;
+	case SONY_HELENE_XTAL_24000:
+		data[2] = 0x03;
+		break;
+	case SONY_HELENE_XTAL_41000:
+		data[2] = 0x05;
+		break;
+	default:
+		dev_err(&priv->i2c->dev, "%s(): unknown xtal %d\n",
+				__func__, priv->xtal);
+		return -EINVAL;
+	}
+
+	/* Setting for analog block (0x07). LOOPFILTER INTERNAL */
+	data[3] = 0x80;
+
+	/* Tuning setting for analog block
+	 * (0x08, 0x09, 0x0A, 0x0B). LOOPFILTER INTERNAL
+	*/
+	if (priv->xtal == SONY_HELENE_XTAL_20500)
+		data[4] = 0x58;
+	else
+		data[4] = 0x70;
+
+	data[5] = 0x1E;
+	data[6] = 0x02;
+	data[7] = 0x24;
+
+	/* Enable for analog block (0x0C, 0x0D, 0x0E). SAT LNA ON */
+	data[8] = 0x0F;
+	data[8] |= 0xE0; /* POWERSAVE_TERR_RF_ACTIVE */
+	data[9]  = 0x02;
+	data[10] = 0x1E;
+
+	/* Setting for LPF cutoff frequency (0x0F) */
+	switch (tv_system) {
+	case SONY_HELENE_STV_ISDBS:
+		data[11] = 0x22; /* 22MHz */
+		break;
+	case SONY_HELENE_STV_DVBS:
+		if (symbol_rate <= 4000)
+			data[11] = 0x05;
+		else if (symbol_rate <= 10000)
+			data[11] = (uint8_t)((symbol_rate * 47
+						+ (40000-1)) / 40000);
+		else
+			data[11] = (uint8_t)((symbol_rate * 27
+						+ (40000-1)) / 40000 + 5);
+
+		if (data[11] > 36)
+			data[11] = 36; /* 5 <= lpf_cutoff <= 36 is valid */
+		break;
+	case SONY_HELENE_STV_DVBS2:
+		if (symbol_rate <= 4000)
+			data[11] = 0x05;
+		else if (symbol_rate <= 10000)
+			data[11] = (uint8_t)((symbol_rate * 11
+						+ (10000-1)) / 10000);
+		else
+			data[11] = (uint8_t)((symbol_rate * 3
+						+ (5000-1)) / 5000 + 5);
+
+		if (data[11] > 36)
+			data[11] = 36; /* 5 <= lpf_cutoff <= 36 is valid */
+		break;
+	default:
+		dev_err(&priv->i2c->dev, "%s(): unknown standard %d\n",
+				__func__, tv_system);
+		return -EINVAL;
+	}
+
+	/* RF tuning frequency setting (0x10, 0x11, 0x12) */
+	frequency4kHz = (frequencykHz + 2) / 4;
+	data[12] = (uint8_t)(frequency4kHz & 0xFF);         /* FRF_L */
+	data[13] = (uint8_t)((frequency4kHz >> 8) & 0xFF);  /* FRF_M */
+	/* FRF_H (bit[3:0]) */
+	data[14] = (uint8_t)((frequency4kHz >> 16) & 0x0F);
+
+	/* Tuning command (0x13) */
+	data[15] = 0xFF;
+
+	/* Setting for IQOUT_LIMIT (0x14) 0.75Vpp */
+	data[16] = 0x00;
+
+	/* Enable IQ output (0x15) */
+	data[17] = 0x01;
+
+	helene_write_regs(priv, 0x04, data, 18);
+
+	dev_dbg(&priv->i2c->dev, "%s(): tune done\n",
+			__func__);
+
+	priv->frequency = frequency;
+	return 0;
+}
+
+static int helene_set_params(struct dvb_frontend *fe)
+{
+	u8 data[MAX_WRITE_REGSIZE];
+	u32 frequency;
+	enum helene_tv_system_t tv_system;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	struct helene_priv *priv = fe->tuner_priv;
+	int frequencykHz = p->frequency / 1000;
+
+	dev_dbg(&priv->i2c->dev, "%s(): tune frequency %dkHz\n",
+			__func__, frequencykHz);
+	tv_system = helene_get_tv_system(fe);
+
+	if (tv_system == SONY_HELENE_TV_SYSTEM_UNKNOWN) {
+		dev_dbg(&priv->i2c->dev, "%s(): unknown DTV system\n",
+				__func__);
+		return -EINVAL;
+	}
+	if (priv->set_tuner)
+		priv->set_tuner(priv->set_tuner_data, 1);
+	frequency = roundup(p->frequency / 1000, 25);
+
+	/* mode select */
+	helene_write_reg(priv, 0x01, 0x00);
+
+	/* Disable IF signal output */
+	helene_write_reg(priv, 0x74, 0x02);
+
+	if (priv->state == STATE_SLEEP)
+		helene_leave_power_save(priv);
+
+	/* Initial setting for internal analog block (0x91, 0x92) */
+	if ((tv_system == SONY_HELENE_DTV_DVBC_6) ||
+			(tv_system == SONY_HELENE_DTV_DVBC_8)) {
+		data[0] = 0x16;
+		data[1] = 0x26;
+	} else {
+		data[0] = 0x10;
+		data[1] = 0x20;
+	}
+	helene_write_regs(priv, 0x91, data, 2);
+
+	/* Setting for analog block */
+	if (TERR_INTERNAL_LOOPFILTER_AVAILABLE(tv_system))
+		data[0] = 0x90;
+	else
+		data[0] = 0x00;
+
+	/* Setting for local polarity (0x9D) */
+	data[1] = (uint8_t)(terr_params[tv_system].IS_LOWERLOCAL & 0x01);
+	helene_write_regs(priv, 0x9C, data, 2);
+
+	/* Enable for analog block */
+	data[0] = 0xEE;
+	data[1] = 0x02;
+	data[2] = 0x1E;
+	data[3] = 0x67; /* Tuning setting for CPU */
+
+	/* Setting for PLL reference divider for xtal=24MHz */
+	if ((tv_system == SONY_HELENE_DTV_DVBC_6) ||
+			(tv_system == SONY_HELENE_DTV_DVBC_8))
+		data[4] = 0x18;
+	else
+		data[4] = 0x03;
+
+	/* Tuning setting for analog block */
+	if (TERR_INTERNAL_LOOPFILTER_AVAILABLE(tv_system)) {
+		data[5] = 0x38;
+		data[6] = 0x1E;
+		data[7] = 0x02;
+		data[8] = 0x24;
+	} else if ((tv_system == SONY_HELENE_DTV_DVBC_6) ||
+			(tv_system == SONY_HELENE_DTV_DVBC_8)) {
+		data[5] = 0x1C;
+		data[6] = 0x78;
+		data[7] = 0x08;
+		data[8] = 0x1C;
+	} else {
+		data[5] = 0xB4;
+		data[6] = 0x78;
+		data[7] = 0x08;
+		data[8] = 0x30;
+	}
+	helene_write_regs(priv, 0x5E, data, 9);
+
+	/* LT_AMP_EN should be 0 */
+	helene_set_reg_bits(priv, 0x67, 0x0, 0x02);
+
+	/* Setting for IFOUT_LIMIT */
+	data[0] = 0x00; /* 1.5Vpp */
+
+	/* RF_GAIN setting */
+	if (terr_params[tv_system].RF_GAIN == HELENE_AUTO)
+		data[1] = 0x80; /* RF_GAIN_SEL = 1 */
+	else
+		data[1] = (uint8_t)((terr_params[tv_system].RF_GAIN
+					<< 4) & 0x70);
+
+	/* IF_BPF_GC setting */
+	data[1] |= (uint8_t)(terr_params[tv_system].IF_BPF_GC & 0x0F);
+
+	/* Setting for internal RFAGC (0x6A, 0x6B, 0x6C) */
+	data[2] = 0x00;
+	if (frequencykHz <= 172000) {
+		data[3] = (uint8_t)(terr_params[tv_system].RFOVLD_DET_LV1_VL
+				& 0x0F);
+		data[4] = (uint8_t)(terr_params[tv_system].IFOVLD_DET_LV_VL
+				& 0x07);
+	} else if (frequencykHz <= 464000) {
+		data[3] = (uint8_t)(terr_params[tv_system].RFOVLD_DET_LV1_VH
+				& 0x0F);
+		data[4] = (uint8_t)(terr_params[tv_system].IFOVLD_DET_LV_VH
+				& 0x07);
+	} else {
+		data[3] = (uint8_t)(terr_params[tv_system].RFOVLD_DET_LV1_U
+				& 0x0F);
+		data[4] = (uint8_t)(terr_params[tv_system].IFOVLD_DET_LV_U
+				& 0x07);
+	}
+	data[4] |= 0x20;
+
+	/* Setting for IF frequency and bandwidth */
+
+	/* IF filter center frequency offset (IF_BPF_F0) (0x6D) */
+	data[5] = (uint8_t)((terr_params[tv_system].IF_BPF_F0 << 4) & 0x30);
+
+	/* IF filter band width (BW) (0x6D) */
+	data[5] |= (uint8_t)(terr_params[tv_system].BW & 0x03);
+
+	/* IF frequency offset value (FIF_OFFSET) (0x6E) */
+	data[6] = (uint8_t)(terr_params[tv_system].FIF_OFFSET & 0x1F);
+
+	/* IF band width offset value (BW_OFFSET) (0x6F) */
+	data[7] = (uint8_t)(terr_params[tv_system].BW_OFFSET & 0x1F);
+
+	/* RF tuning frequency setting (0x70, 0x71, 0x72) */
+	data[8]  = (uint8_t)(frequencykHz & 0xFF);         /* FRF_L */
+	data[9]  = (uint8_t)((frequencykHz >> 8) & 0xFF);  /* FRF_M */
+	data[10] = (uint8_t)((frequencykHz >> 16)
+			& 0x0F); /* FRF_H (bit[3:0]) */
+
+	/* Tuning command */
+	data[11] = 0xFF;
+
+	/* Enable IF output, AGC and IFOUT pin selection (0x74) */
+	data[12] = 0x01;
+
+	if ((tv_system == SONY_HELENE_DTV_DVBC_6) ||
+			(tv_system == SONY_HELENE_DTV_DVBC_8)) {
+		data[13] = 0xD9;
+		data[14] = 0x0F;
+		data[15] = 0x24;
+		data[16] = 0x87;
+	} else {
+		data[13] = 0x99;
+		data[14] = 0x00;
+		data[15] = 0x24;
+		data[16] = 0x87;
+	}
+
+	helene_write_regs(priv, 0x68, data, 17);
+
+	dev_dbg(&priv->i2c->dev, "%s(): tune done\n",
+			__func__);
+
+	priv->frequency = frequency;
+	return 0;
+}
+
+static int helene_get_frequency(struct dvb_frontend *fe, u32 *frequency)
+{
+	struct helene_priv *priv = fe->tuner_priv;
+
+	*frequency = priv->frequency * 1000;
+	return 0;
+}
+
+static struct dvb_tuner_ops helene_tuner_ops = {
+	.info = {
+		.name = "Sony HELENE Ter tuner",
+		.frequency_min = 1000000,
+		.frequency_max = 1200000000,
+		.frequency_step = 25000,
+	},
+	.init = helene_init,
+	.release = helene_release,
+	.sleep = helene_sleep,
+	.set_params = helene_set_params,
+	.get_frequency = helene_get_frequency,
+};
+
+static struct dvb_tuner_ops helene_tuner_ops_s = {
+	.info = {
+		.name = "Sony HELENE Sat tuner",
+		.frequency_min = 500000,
+		.frequency_max = 2500000,
+		.frequency_step = 1000,
+	},
+	.init = helene_init,
+	.release = helene_release,
+	.sleep = helene_sleep,
+	.set_params = helene_set_params_s,
+	.get_frequency = helene_get_frequency,
+};
+
+/* power-on tuner
+ * call once after reset
+ */
+static int helene_x_pon(struct helene_priv *priv)
+{
+	/* RFIN matching in power save (terrestrial) = ACTIVE */
+	/* RFIN matching in power save (satellite) = ACTIVE */
+	u8 dataT[] = { 0x06, 0x00, 0x02, 0x00 };
+	/* SAT_RF_ACTIVE = true, lnaOff = false, terrRfActive = true */
+	u8 dataS[] = { 0x05, 0x06 };
+	u8 cdata[] = {0x7A, 0x01};
+	u8 data[20];
+	u8 rdata[2];
+
+	/* mode select */
+	helene_write_reg(priv, 0x01, 0x00);
+
+	helene_write_reg(priv, 0x67, dataT[3]);
+	helene_write_reg(priv, 0x43, dataS[1]);
+	helene_write_regs(priv, 0x5E, dataT, 3);
+	helene_write_reg(priv, 0x0C, dataS[0]);
+
+	/* Initial setting for internal logic block */
+	helene_write_regs(priv, 0x99, cdata, sizeof(cdata));
+
+	/* 0x81 - 0x94 */
+	data[0] = 0x18; /* xtal 24 MHz */
+	data[1] = (uint8_t)(0x80 | (0x04 & 0x1F)); /* 4 x 25 = 100uA */
+	data[2] = (uint8_t)(0x80 | (0x26 & 0x7F)); /* 38 x 0.25 = 9.5pF */
+	data[3] = 0x80; /* REFOUT signal output 500mVpp */
+	data[4] = 0x00; /* GPIO settings */
+	data[5] = 0x00; /* GPIO settings */
+	data[6] = 0xC4; /* Clock enable for internal logic block */
+	data[7] = 0x40; /* Start CPU boot-up */
+	data[8] = 0x10; /* For burst-write */
+
+	/* Setting for internal RFAGC */
+	data[9] = 0x00;
+	data[10] = 0x45;
+	data[11] = 0x75;
+
+	data[12] = 0x07; /* Setting for analog block */
+
+	/* Initial setting for internal analog block */
+	data[13] = 0x1C;
+	data[14] = 0x3F;
+	data[15] = 0x02;
+	data[16] = 0x10;
+	data[17] = 0x20;
+	data[18] = 0x0A;
+	data[19] = 0x00;
+
+	helene_write_regs(priv, 0x81, data, sizeof(data));
+
+	/* Setting for internal RFAGC */
+	helene_write_reg(priv, 0x9B, 0x00);
+
+	msleep(20);
+
+	/* Check CPU_STT/CPU_ERR */
+	helene_read_regs(priv, 0x1A, rdata, sizeof(rdata));
+
+	if (rdata[0] != 0x00) {
+		dev_err(&priv->i2c->dev,
+				"HELENE tuner CPU error 0x%x\n", rdata[0]);
+		return -EIO;
+	}
+
+	/* VCO current setting */
+	cdata[0] = 0x90;
+	cdata[1] = 0x06;
+	helene_write_regs(priv, 0x17, cdata, sizeof(cdata));
+	msleep(20);
+	helene_read_reg(priv, 0x19, data);
+	helene_write_reg(priv, 0x95, (uint8_t)((data[0] >> 4) & 0x0F));
+
+	/* Disable IF signal output */
+	helene_write_reg(priv, 0x74, 0x02);
+
+	/* Standby setting for CPU */
+	helene_write_reg(priv, 0x88, 0x00);
+
+	/* Standby setting for internal logic block */
+	helene_write_reg(priv, 0x87, 0xC0);
+
+	/* Load capacitance control setting for crystal oscillator */
+	helene_write_reg(priv, 0x80, 0x01);
+
+	/* Satellite initial setting */
+	cdata[0] = 0x07;
+	cdata[1] = 0x00;
+	helene_write_regs(priv, 0x41, cdata, sizeof(cdata));
+
+	dev_info(&priv->i2c->dev,
+			"HELENE tuner x_pon done\n");
+
+	return 0;
+}
+
+struct dvb_frontend *helene_attach_s(struct dvb_frontend *fe,
+		const struct helene_config *config,
+		struct i2c_adapter *i2c)
+{
+	struct helene_priv *priv = NULL;
+
+	priv = kzalloc(sizeof(struct helene_priv), GFP_KERNEL);
+	if (priv == NULL)
+		return NULL;
+	priv->i2c_address = (config->i2c_address >> 1);
+	priv->i2c = i2c;
+	priv->set_tuner_data = config->set_tuner_priv;
+	priv->set_tuner = config->set_tuner_callback;
+	priv->xtal = config->xtal;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 1);
+
+	if (helene_x_pon(priv) != 0)
+		return NULL;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 0);
+
+	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops_s,
+			sizeof(struct dvb_tuner_ops));
+	fe->tuner_priv = priv;
+	dev_info(&priv->i2c->dev,
+			"Sony HELENE Sat attached on addr=%x at I2C adapter %p\n",
+			priv->i2c_address, priv->i2c);
+	return fe;
+}
+EXPORT_SYMBOL(helene_attach_s);
+
+struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
+		const struct helene_config *config,
+		struct i2c_adapter *i2c)
+{
+	struct helene_priv *priv = NULL;
+
+	priv = kzalloc(sizeof(struct helene_priv), GFP_KERNEL);
+	if (priv == NULL)
+		return NULL;
+	priv->i2c_address = (config->i2c_address >> 1);
+	priv->i2c = i2c;
+	priv->set_tuner_data = config->set_tuner_priv;
+	priv->set_tuner = config->set_tuner_callback;
+	priv->xtal = config->xtal;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 1);
+
+	if (helene_x_pon(priv) != 0)
+		return NULL;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 0);
+
+	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops,
+			sizeof(struct dvb_tuner_ops));
+	fe->tuner_priv = priv;
+	dev_info(&priv->i2c->dev,
+			"Sony HELENE Ter attached on addr=%x at I2C adapter %p\n",
+			priv->i2c_address, priv->i2c);
+	return fe;
+}
+EXPORT_SYMBOL(helene_attach);
+
+MODULE_DESCRIPTION("Sony HELENE Sat/Ter tuner driver");
+MODULE_AUTHOR("Abylay Ospan <aospan@netup.ru>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/helene.h b/drivers/media/dvb-frontends/helene.h
new file mode 100644
index 000000000000..e1b9224cfc55
--- /dev/null
+++ b/drivers/media/dvb-frontends/helene.h
@@ -0,0 +1,79 @@
+/*
+ * helene.h
+ *
+ * Sony HELENE DVB-S/S2/T/T2/C/C2/ISDB-T/S tuner driver (CXD2858ER)
+ *
+ * Copyright 2012 Sony Corporation
+ * Copyright (C) 2014 NetUP Inc.
+ * Copyright (C) 2014 Abylay Ospan <aospan@netup.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+  */
+
+#ifndef __DVB_HELENE_H__
+#define __DVB_HELENE_H__
+
+#include <linux/kconfig.h>
+#include <linux/dvb/frontend.h>
+#include <linux/i2c.h>
+
+enum helene_xtal {
+	SONY_HELENE_XTAL_16000, /* 16 MHz */
+	SONY_HELENE_XTAL_20500, /* 20.5 MHz */
+	SONY_HELENE_XTAL_24000, /* 24 MHz */
+	SONY_HELENE_XTAL_41000 /* 41 MHz */
+};
+
+/**
+ * struct helene_config - the configuration of 'Helene' tuner driver
+ * @i2c_address:	I2C address of the tuner
+ * @xtal_freq_mhz:	Oscillator frequency, MHz
+ * @set_tuner_priv:	Callback function private context
+ * @set_tuner_callback:	Callback function that notifies the parent driver
+ *			which tuner is active now
+ */
+struct helene_config {
+	u8	i2c_address;
+	u8	xtal_freq_mhz;
+	void	*set_tuner_priv;
+	int	(*set_tuner_callback)(void *, int);
+	enum helene_xtal xtal;
+};
+
+#if IS_REACHABLE(CONFIG_DVB_HELENE)
+extern struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
+					const struct helene_config *config,
+					struct i2c_adapter *i2c);
+#else
+static inline struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
+					const struct helene_config *config,
+					struct i2c_adapter *i2c)
+{
+	pr_warn("%s: driver disabled by Kconfig\n", __func__);
+	return NULL;
+}
+#endif
+
+#if IS_REACHABLE(CONFIG_DVB_HELENE)
+extern struct dvb_frontend *helene_attach_s(struct dvb_frontend *fe,
+					const struct helene_config *config,
+					struct i2c_adapter *i2c);
+#else
+static inline struct dvb_frontend *helene_attach_s(struct dvb_frontend *fe,
+					const struct helene_config *config,
+					struct i2c_adapter *i2c)
+{
+	pr_warn("%s: driver disabled by Kconfig\n", __func__);
+	return NULL;
+}
+#endif
+
+#endif
diff --git a/drivers/media/dvb-frontends/horus3a.c b/drivers/media/dvb-frontends/horus3a.c
index 000606af70f7..a98bca5270d9 100644
--- a/drivers/media/dvb-frontends/horus3a.c
+++ b/drivers/media/dvb-frontends/horus3a.c
@@ -66,7 +66,7 @@ static int horus3a_write_regs(struct horus3a_priv *priv,
 		}
 	};
 
-	if (len + 1 >= sizeof(buf)) {
+	if (len + 1 > sizeof(buf)) {
 		dev_warn(&priv->i2c->dev,"wr reg=%04x: len=%d is too big!\n",
 			 reg, len + 1);
 		return -E2BIG;
@@ -272,24 +272,6 @@ static int horus3a_set_params(struct dvb_frontend *fe)
 		if (fc_lpf > 36)
 			fc_lpf = 36;
 	} else if (p->delivery_system == SYS_DVBS2) {
-		int rolloff;
-
-		switch (p->rolloff) {
-		case ROLLOFF_35:
-			rolloff = 35;
-			break;
-		case ROLLOFF_25:
-			rolloff = 25;
-			break;
-		case ROLLOFF_20:
-			rolloff = 20;
-			break;
-		case ROLLOFF_AUTO:
-		default:
-			dev_err(&priv->i2c->dev,
-				"horus3a: auto roll-off is not supported\n");
-			return -EINVAL;
-		}
 		/*
 		 * SR <= 4.5:
 		 * fc_lpf = 5
@@ -302,11 +284,9 @@ static int horus3a_set_params(struct dvb_frontend *fe)
 		if (symbol_rate <= 4500)
 			fc_lpf = 5;
 		else if (symbol_rate <= 10000)
-			fc_lpf = (u8)DIV_ROUND_UP(
-				symbol_rate * (200 + rolloff), 200000);
+			fc_lpf = (u8)((symbol_rate * 11 + (10000-1)) / 10000);
 		else
-			fc_lpf = (u8)DIV_ROUND_UP(
-				symbol_rate * (100 + rolloff), 200000) + 5;
+			fc_lpf = (u8)((symbol_rate * 3 + (5000-1)) / 5000 + 5);
 		/* 5 <= fc_lpf <= 36 is valid */
 		if (fc_lpf > 36)
 			fc_lpf = 36;
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index 5557ef8fc704..e0fe5bc9dbce 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -306,8 +306,8 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 	const struct m88ds3103_reg_val *init;
 	u8 u8tmp, u8tmp1 = 0, u8tmp2 = 0; /* silence compiler warning */
 	u8 buf[3];
-	u16 u16tmp, divide_ratio = 0;
-	u32 tuner_frequency, target_mclk;
+	u16 u16tmp;
+	u32 tuner_frequency_khz, target_mclk;
 	s32 s32tmp;
 
 	dev_dbg(&client->dev,
@@ -344,7 +344,7 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 	}
 
 	if (fe->ops.tuner_ops.get_frequency) {
-		ret = fe->ops.tuner_ops.get_frequency(fe, &tuner_frequency);
+		ret = fe->ops.tuner_ops.get_frequency(fe, &tuner_frequency_khz);
 		if (ret)
 			goto err;
 	} else {
@@ -353,20 +353,20 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 		 * actual frequency used. Carrier offset calculation is not
 		 * valid.
 		 */
-		tuner_frequency = c->frequency;
+		tuner_frequency_khz = c->frequency;
 	}
 
 	/* select M88RS6000 demod main mclk and ts mclk from tuner die. */
 	if (dev->chip_id == M88RS6000_CHIP_ID) {
 		if (c->symbol_rate > 45010000)
-			dev->mclk_khz = 110250;
+			dev->mclk = 110250000;
 		else
-			dev->mclk_khz = 96000;
+			dev->mclk = 96000000;
 
 		if (c->delivery_system == SYS_DVBS)
-			target_mclk = 96000;
+			target_mclk = 96000000;
 		else
-			target_mclk = 144000;
+			target_mclk = 144000000;
 
 		/* Enable demod clock path */
 		ret = regmap_write(dev->regmap, 0x06, 0x00);
@@ -375,7 +375,7 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 		usleep_range(10000, 20000);
 	} else {
 	/* set M88DS3103 mclk and ts mclk. */
-		dev->mclk_khz = 96000;
+		dev->mclk = 96000000;
 
 		switch (dev->cfg->ts_mode) {
 		case M88DS3103_TS_SERIAL:
@@ -385,14 +385,14 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 		case M88DS3103_TS_PARALLEL:
 		case M88DS3103_TS_CI:
 			if (c->delivery_system == SYS_DVBS)
-				target_mclk = 96000;
+				target_mclk = 96000000;
 			else {
 				if (c->symbol_rate < 18000000)
-					target_mclk = 96000;
+					target_mclk = 96000000;
 				else if (c->symbol_rate < 28000000)
-					target_mclk = 144000;
+					target_mclk = 144000000;
 				else
-					target_mclk = 192000;
+					target_mclk = 192000000;
 			}
 			break;
 		default:
@@ -402,15 +402,15 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 		}
 
 		switch (target_mclk) {
-		case 96000:
+		case 96000000:
 			u8tmp1 = 0x02; /* 0b10 */
 			u8tmp2 = 0x01; /* 0b01 */
 			break;
-		case 144000:
+		case 144000000:
 			u8tmp1 = 0x00; /* 0b00 */
 			u8tmp2 = 0x01; /* 0b01 */
 			break;
-		case 192000:
+		case 192000000:
 			u8tmp1 = 0x03; /* 0b11 */
 			u8tmp2 = 0x00; /* 0b00 */
 			break;
@@ -464,8 +464,8 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 	}
 
 	if (dev->chip_id == M88RS6000_CHIP_ID) {
-		if ((c->delivery_system == SYS_DVBS2)
-			&& ((c->symbol_rate / 1000) <= 5000)) {
+		if (c->delivery_system == SYS_DVBS2 &&
+		    c->symbol_rate <= 5000000) {
 			ret = regmap_write(dev->regmap, 0xc0, 0x04);
 			if (ret)
 				goto err;
@@ -522,37 +522,25 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 		ret = m88ds3103_update_bits(dev, 0x29, 0x20, u8tmp1);
 		if (ret)
 			goto err;
-		u8tmp1 = 0;
-		u8tmp2 = 0;
+		u16tmp = 0;
+		u8tmp1 = 0x3f;
+		u8tmp2 = 0x3f;
 		break;
 	default:
-		if (dev->cfg->ts_clk) {
-			divide_ratio = DIV_ROUND_UP(target_mclk, dev->cfg->ts_clk);
-			u8tmp1 = divide_ratio / 2;
-			u8tmp2 = DIV_ROUND_UP(divide_ratio, 2);
-		}
+		u16tmp = DIV_ROUND_UP(target_mclk, dev->cfg->ts_clk);
+		u8tmp1 = u16tmp / 2 - 1;
+		u8tmp2 = DIV_ROUND_UP(u16tmp, 2) - 1;
 	}
 
-	dev_dbg(&client->dev,
-		"target_mclk=%d ts_clk=%d divide_ratio=%d\n",
-		target_mclk, dev->cfg->ts_clk, divide_ratio);
+	dev_dbg(&client->dev, "target_mclk=%u ts_clk=%u ts_clk_divide_ratio=%u\n",
+		target_mclk, dev->cfg->ts_clk, u16tmp);
 
-	u8tmp1--;
-	u8tmp2--;
 	/* u8tmp1[5:2] => fe[3:0], u8tmp1[1:0] => ea[7:6] */
-	u8tmp1 &= 0x3f;
 	/* u8tmp2[5:0] => ea[5:0] */
-	u8tmp2 &= 0x3f;
-
-	ret = regmap_bulk_read(dev->regmap, 0xfe, &u8tmp, 1);
+	u8tmp = (u8tmp1 >> 2) & 0x0f;
+	ret = regmap_update_bits(dev->regmap, 0xfe, 0x0f, u8tmp);
 	if (ret)
 		goto err;
-
-	u8tmp = ((u8tmp  & 0xf0) << 0) | u8tmp1 >> 2;
-	ret = regmap_write(dev->regmap, 0xfe, u8tmp);
-	if (ret)
-		goto err;
-
 	u8tmp = ((u8tmp1 & 0x03) << 6) | u8tmp2 >> 0;
 	ret = regmap_write(dev->regmap, 0xea, u8tmp);
 	if (ret)
@@ -581,7 +569,7 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	u16tmp = DIV_ROUND_CLOSEST((c->symbol_rate / 1000) << 15, dev->mclk_khz / 2);
+	u16tmp = DIV_ROUND_CLOSEST_ULL((u64)c->symbol_rate * 0x10000, dev->mclk);
 	buf[0] = (u16tmp >> 0) & 0xff;
 	buf[1] = (u16tmp >> 8) & 0xff;
 	ret = regmap_bulk_write(dev->regmap, 0x61, buf, 2);
@@ -601,13 +589,11 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 		goto err;
 
 	dev_dbg(&client->dev, "carrier offset=%d\n",
-		(tuner_frequency - c->frequency));
-
-	s32tmp = 0x10000 * (tuner_frequency - c->frequency);
-	s32tmp = DIV_ROUND_CLOSEST(s32tmp, dev->mclk_khz);
-	if (s32tmp < 0)
-		s32tmp += 0x10000;
+		(tuner_frequency_khz - c->frequency));
 
+	/* Use 32-bit calc as there is no s64 version of DIV_ROUND_CLOSEST() */
+	s32tmp = 0x10000 * (tuner_frequency_khz - c->frequency);
+	s32tmp = DIV_ROUND_CLOSEST(s32tmp, dev->mclk / 1000);
 	buf[0] = (s32tmp >> 0) & 0xff;
 	buf[1] = (s32tmp >> 8) & 0xff;
 	ret = regmap_bulk_write(dev->regmap, 0x5e, buf, 2);
@@ -635,10 +621,10 @@ static int m88ds3103_init(struct dvb_frontend *fe)
 	struct m88ds3103_dev *dev = fe->demodulator_priv;
 	struct i2c_client *client = dev->client;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	int ret, len, remaining;
+	int ret, len, rem;
 	unsigned int utmp;
-	const struct firmware *fw = NULL;
-	u8 *fw_file;
+	const struct firmware *firmware;
+	const char *name;
 
 	dev_dbg(&client->dev, "\n");
 
@@ -664,7 +650,7 @@ static int m88ds3103_init(struct dvb_frontend *fe)
 	dev_dbg(&client->dev, "firmware=%02x\n", utmp);
 
 	if (utmp)
-		goto skip_fw_download;
+		goto warm;
 
 	/* global reset, global diseqc reset, golbal fec reset */
 	ret = regmap_write(dev->regmap, 0x07, 0xe0);
@@ -679,52 +665,47 @@ static int m88ds3103_init(struct dvb_frontend *fe)
 		 m88ds3103_ops.info.name);
 
 	if (dev->chip_id == M88RS6000_CHIP_ID)
-		fw_file = M88RS6000_FIRMWARE;
+		name = M88RS6000_FIRMWARE;
 	else
-		fw_file = M88DS3103_FIRMWARE;
+		name = M88DS3103_FIRMWARE;
 	/* request the firmware, this will block and timeout */
-	ret = request_firmware(&fw, fw_file, &client->dev);
+	ret = request_firmware(&firmware, name, &client->dev);
 	if (ret) {
-		dev_err(&client->dev, "firmware file '%s' not found\n", fw_file);
+		dev_err(&client->dev, "firmware file '%s' not found\n", name);
 		goto err;
 	}
 
-	dev_info(&client->dev, "downloading firmware from file '%s'\n",
-		 fw_file);
+	dev_info(&client->dev, "downloading firmware from file '%s'\n", name);
 
 	ret = regmap_write(dev->regmap, 0xb2, 0x01);
 	if (ret)
-		goto error_fw_release;
-
-	for (remaining = fw->size; remaining > 0;
-			remaining -= (dev->cfg->i2c_wr_max - 1)) {
-		len = remaining;
-		if (len > (dev->cfg->i2c_wr_max - 1))
-			len = (dev->cfg->i2c_wr_max - 1);
+		goto err_release_firmware;
 
+	for (rem = firmware->size; rem > 0; rem -= (dev->cfg->i2c_wr_max - 1)) {
+		len = min(dev->cfg->i2c_wr_max - 1, rem);
 		ret = regmap_bulk_write(dev->regmap, 0xb0,
-				&fw->data[fw->size - remaining], len);
+					&firmware->data[firmware->size - rem],
+					len);
 		if (ret) {
-			dev_err(&client->dev, "firmware download failed=%d\n",
+			dev_err(&client->dev, "firmware download failed %d\n",
 				ret);
-			goto error_fw_release;
+			goto err_release_firmware;
 		}
 	}
 
 	ret = regmap_write(dev->regmap, 0xb2, 0x00);
 	if (ret)
-		goto error_fw_release;
+		goto err_release_firmware;
 
-	release_firmware(fw);
-	fw = NULL;
+	release_firmware(firmware);
 
 	ret = regmap_read(dev->regmap, 0xb9, &utmp);
 	if (ret)
 		goto err;
 
 	if (!utmp) {
+		ret = -EINVAL;
 		dev_info(&client->dev, "firmware did not run\n");
-		ret = -EFAULT;
 		goto err;
 	}
 
@@ -733,7 +714,7 @@ static int m88ds3103_init(struct dvb_frontend *fe)
 	dev_info(&client->dev, "firmware version: %X.%X\n",
 		 (utmp >> 4) & 0xf, (utmp >> 0 & 0xf));
 
-skip_fw_download:
+warm:
 	/* warm state */
 	dev->warm = true;
 
@@ -746,8 +727,8 @@ skip_fw_download:
 	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 
 	return 0;
-error_fw_release:
-	release_firmware(fw);
+err_release_firmware:
+	release_firmware(firmware);
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
 	return ret;
@@ -952,8 +933,7 @@ static int m88ds3103_get_frontend(struct dvb_frontend *fe,
 	if (ret)
 		goto err;
 
-	c->symbol_rate = 1ull * ((buf[1] << 8) | (buf[0] << 0)) *
-			dev->mclk_khz * 1000 / 0x10000;
+	c->symbol_rate = DIV_ROUND_CLOSEST_ULL((u64)(buf[1] << 8 | buf[0] << 0) * dev->mclk, 0x10000);
 
 	return 0;
 err:
@@ -1119,8 +1099,9 @@ static int m88ds3103_diseqc_send_master_cmd(struct dvb_frontend *fe,
 	#define SEND_MASTER_CMD_TIMEOUT 120
 	timeout = jiffies + msecs_to_jiffies(SEND_MASTER_CMD_TIMEOUT);
 
-	/* DiSEqC message typical period is 54 ms */
-	usleep_range(50000, 54000);
+	/* DiSEqC message period is 13.5 ms per byte */
+	utmp = diseqc_cmd->msg_len * 13500;
+	usleep_range(utmp - 4000, utmp);
 
 	for (utmp = 1; !time_after(jiffies, timeout) && utmp;) {
 		ret = regmap_read(dev->regmap, 0xa1, &utmp);
@@ -1395,7 +1376,7 @@ static int m88ds3103_probe(struct i2c_client *client,
 	dev->config.clock = pdata->clk;
 	dev->config.i2c_wr_max = pdata->i2c_wr_max;
 	dev->config.ts_mode = pdata->ts_mode;
-	dev->config.ts_clk = pdata->ts_clk;
+	dev->config.ts_clk = pdata->ts_clk * 1000;
 	dev->config.ts_clk_pol = pdata->ts_clk_pol;
 	dev->config.spec_inv = pdata->spec_inv;
 	dev->config.agc_inv = pdata->agc_inv;
@@ -1446,6 +1427,11 @@ static int m88ds3103_probe(struct i2c_client *client,
 		goto err_kfree;
 	}
 
+	if (!pdata->ts_clk) {
+		ret = -EINVAL;
+		goto err_kfree;
+	}
+
 	/* 0x29 register is defined differently for m88rs6000. */
 	/* set internal tuner address to 0x21 */
 	if (dev->chip_id == M88RS6000_CHIP_ID)
diff --git a/drivers/media/dvb-frontends/m88ds3103_priv.h b/drivers/media/dvb-frontends/m88ds3103_priv.h
index d78e467295d2..07f20c269c67 100644
--- a/drivers/media/dvb-frontends/m88ds3103_priv.h
+++ b/drivers/media/dvb-frontends/m88ds3103_priv.h
@@ -27,7 +27,6 @@
 
 #define M88DS3103_FIRMWARE "dvb-demod-m88ds3103.fw"
 #define M88RS6000_FIRMWARE "dvb-demod-m88rs6000.fw"
-#define M88DS3103_MCLK_KHZ 96000
 #define M88RS6000_CHIP_ID 0x74
 #define M88DS3103_CHIP_ID 0x70
 
@@ -46,7 +45,7 @@ struct m88ds3103_dev {
 	/* auto detect chip id to do different config */
 	u8 chip_id;
 	/* main mclk is calculated for M88RS6000 dynamically */
-	s32 mclk_khz;
+	s32 mclk;
 	u64 post_bit_error;
 	u64 post_bit_count;
 };
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index a09b12313a73..ef79a4ec31e2 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -609,7 +609,7 @@ static int m88rs2000_set_frontend(struct dvb_frontend *fe)
 {
 	struct m88rs2000_state *state = fe->demodulator_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	enum fe_status status;
+	enum fe_status status = 0;
 	int i, ret = 0;
 	u32 tuner_freq;
 	s16 offset = 0;
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index fb88dddaf3a3..41325328a22e 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -301,10 +301,11 @@ static int mb86a20s_read_status(struct dvb_frontend *fe, enum fe_status *status)
 
 	*status = 0;
 
-	val = mb86a20s_readreg(state, 0x0a) & 0xf;
+	val = mb86a20s_readreg(state, 0x0a);
 	if (val < 0)
 		return val;
 
+	val &= 0xf;
 	if (val >= 2)
 		*status |= FE_HAS_SIGNAL;
 
diff --git a/drivers/staging/media/mn88472/mn88472.c b/drivers/media/dvb-frontends/mn88472.c
index 7ea749cf19f9..18fb2df1e2bd 100644
--- a/drivers/staging/media/mn88472/mn88472.c
+++ b/drivers/media/dvb-frontends/mn88472.c
@@ -17,28 +17,90 @@
 #include "mn88472_priv.h"
 
 static int mn88472_get_tune_settings(struct dvb_frontend *fe,
-	struct dvb_frontend_tune_settings *s)
+				     struct dvb_frontend_tune_settings *s)
 {
-	s->min_delay_ms = 800;
+	s->min_delay_ms = 1000;
 	return 0;
 }
 
+static int mn88472_read_status(struct dvb_frontend *fe, enum fe_status *status)
+{
+	struct i2c_client *client = fe->demodulator_priv;
+	struct mn88472_dev *dev = i2c_get_clientdata(client);
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	int ret;
+	unsigned int utmp;
+
+	if (!dev->active) {
+		ret = -EAGAIN;
+		goto err;
+	}
+
+	switch (c->delivery_system) {
+	case SYS_DVBT:
+		ret = regmap_read(dev->regmap[0], 0x7f, &utmp);
+		if (ret)
+			goto err;
+		if ((utmp & 0x0f) >= 0x09)
+			*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+				  FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+		else
+			*status = 0;
+		break;
+	case SYS_DVBT2:
+		ret = regmap_read(dev->regmap[2], 0x92, &utmp);
+		if (ret)
+			goto err;
+		if ((utmp & 0x0f) >= 0x0d)
+			*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+				  FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+		else if ((utmp & 0x0f) >= 0x0a)
+			*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+				  FE_HAS_VITERBI;
+		else if ((utmp & 0x0f) >= 0x07)
+			*status = FE_HAS_SIGNAL | FE_HAS_CARRIER;
+		else
+			*status = 0;
+		break;
+	case SYS_DVBC_ANNEX_A:
+		ret = regmap_read(dev->regmap[1], 0x84, &utmp);
+		if (ret)
+			goto err;
+		if ((utmp & 0x0f) >= 0x08)
+			*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+				  FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+		else
+			*status = 0;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err;
+	}
+
+	return 0;
+err:
+	dev_dbg(&client->dev, "failed=%d\n", ret);
+	return ret;
+}
+
 static int mn88472_set_frontend(struct dvb_frontend *fe)
 {
 	struct i2c_client *client = fe->demodulator_priv;
 	struct mn88472_dev *dev = i2c_get_clientdata(client);
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i;
-	u32 if_frequency = 0;
-	u64 tmp;
-	u8 delivery_system_val, if_val[3], bw_val[7], bw_val2;
+	unsigned int utmp;
+	u32 if_frequency;
+	u8 buf[3], delivery_system_val, bandwidth_val, *bandwidth_vals_ptr;
+	u8 reg_bank0_b4_val, reg_bank0_cd_val, reg_bank0_d4_val;
+	u8 reg_bank0_d6_val;
 
 	dev_dbg(&client->dev,
-			"delivery_system=%d modulation=%d frequency=%d symbol_rate=%d inversion=%d\n",
-			c->delivery_system, c->modulation,
-			c->frequency, c->symbol_rate, c->inversion);
+		"delivery_system=%u modulation=%u frequency=%u bandwidth_hz=%u symbol_rate=%u inversion=%d stream_id=%d\n",
+		c->delivery_system, c->modulation, c->frequency,
+		c->bandwidth_hz, c->symbol_rate, c->inversion, c->stream_id);
 
-	if (!dev->warm) {
+	if (!dev->active) {
 		ret = -EAGAIN;
 		goto err;
 	}
@@ -46,39 +108,64 @@ static int mn88472_set_frontend(struct dvb_frontend *fe)
 	switch (c->delivery_system) {
 	case SYS_DVBT:
 		delivery_system_val = 0x02;
+		reg_bank0_b4_val = 0x00;
+		reg_bank0_cd_val = 0x1f;
+		reg_bank0_d4_val = 0x0a;
+		reg_bank0_d6_val = 0x48;
 		break;
 	case SYS_DVBT2:
 		delivery_system_val = 0x03;
+		reg_bank0_b4_val = 0xf6;
+		reg_bank0_cd_val = 0x01;
+		reg_bank0_d4_val = 0x09;
+		reg_bank0_d6_val = 0x46;
 		break;
 	case SYS_DVBC_ANNEX_A:
 		delivery_system_val = 0x04;
+		reg_bank0_b4_val = 0x00;
+		reg_bank0_cd_val = 0x17;
+		reg_bank0_d4_val = 0x09;
+		reg_bank0_d6_val = 0x48;
 		break;
 	default:
 		ret = -EINVAL;
 		goto err;
 	}
 
-	if (c->bandwidth_hz <= 5000000) {
-		memcpy(bw_val, "\xe5\x99\x9a\x1b\xa9\x1b\xa9", 7);
-		bw_val2 = 0x03;
-	} else if (c->bandwidth_hz <= 6000000) {
-		/* IF 3570000 Hz, BW 6000000 Hz */
-		memcpy(bw_val, "\xbf\x55\x55\x15\x6b\x15\x6b", 7);
-		bw_val2 = 0x02;
-	} else if (c->bandwidth_hz <= 7000000) {
-		/* IF 4570000 Hz, BW 7000000 Hz */
-		memcpy(bw_val, "\xa4\x00\x00\x0f\x2c\x0f\x2c", 7);
-		bw_val2 = 0x01;
-	} else if (c->bandwidth_hz <= 8000000) {
-		/* IF 4570000 Hz, BW 8000000 Hz */
-		memcpy(bw_val, "\x8f\x80\x00\x08\xee\x08\xee", 7);
-		bw_val2 = 0x00;
-	} else {
-		ret = -EINVAL;
-		goto err;
+	switch (c->delivery_system) {
+	case SYS_DVBT:
+	case SYS_DVBT2:
+		switch (c->bandwidth_hz) {
+		case 5000000:
+			bandwidth_vals_ptr = "\xe5\x99\x9a\x1b\xa9\x1b\xa9";
+			bandwidth_val = 0x03;
+			break;
+		case 6000000:
+			bandwidth_vals_ptr = "\xbf\x55\x55\x15\x6b\x15\x6b";
+			bandwidth_val = 0x02;
+			break;
+		case 7000000:
+			bandwidth_vals_ptr = "\xa4\x00\x00\x0f\x2c\x0f\x2c";
+			bandwidth_val = 0x01;
+			break;
+		case 8000000:
+			bandwidth_vals_ptr = "\x8f\x80\x00\x08\xee\x08\xee";
+			bandwidth_val = 0x00;
+			break;
+		default:
+			ret = -EINVAL;
+			goto err;
+		}
+		break;
+	case SYS_DVBC_ANNEX_A:
+		bandwidth_vals_ptr = NULL;
+		bandwidth_val = 0x00;
+		break;
+	default:
+		break;
 	}
 
-	/* program tuner */
+	/* Program tuner */
 	if (fe->ops.tuner_ops.set_params) {
 		ret = fe->ops.tuner_ops.set_params(fe);
 		if (ret)
@@ -91,20 +178,10 @@ static int mn88472_set_frontend(struct dvb_frontend *fe)
 			goto err;
 
 		dev_dbg(&client->dev, "get_if_frequency=%d\n", if_frequency);
-	}
-
-	/* Calculate IF registers ( (1<<24)*IF / Xtal ) */
-	tmp =  div_u64(if_frequency * (u64)(1<<24) + (dev->xtal / 2),
-				   dev->xtal);
-	if_val[0] = (tmp >> 16) & 0xff;
-	if_val[1] = (tmp >>  8) & 0xff;
-	if_val[2] = (tmp >>  0) & 0xff;
-
-	ret = regmap_write(dev->regmap[2], 0xfb, 0x13);
-	ret = regmap_write(dev->regmap[2], 0xef, 0x13);
-	ret = regmap_write(dev->regmap[2], 0xf9, 0x13);
-	if (ret)
+	} else {
+		ret = -EINVAL;
 		goto err;
+	}
 
 	ret = regmap_write(dev->regmap[2], 0x00, 0x66);
 	if (ret)
@@ -118,157 +195,81 @@ static int mn88472_set_frontend(struct dvb_frontend *fe)
 	ret = regmap_write(dev->regmap[2], 0x03, delivery_system_val);
 	if (ret)
 		goto err;
-	ret = regmap_write(dev->regmap[2], 0x04, bw_val2);
+	ret = regmap_write(dev->regmap[2], 0x04, bandwidth_val);
 	if (ret)
 		goto err;
 
-	for (i = 0; i < sizeof(if_val); i++) {
-		ret = regmap_write(dev->regmap[2], 0x10 + i, if_val[i]);
+	/* IF */
+	utmp = DIV_ROUND_CLOSEST_ULL((u64)if_frequency * 0x1000000, dev->clk);
+	buf[0] = (utmp >> 16) & 0xff;
+	buf[1] = (utmp >>  8) & 0xff;
+	buf[2] = (utmp >>  0) & 0xff;
+	for (i = 0; i < 3; i++) {
+		ret = regmap_write(dev->regmap[2], 0x10 + i, buf[i]);
 		if (ret)
 			goto err;
 	}
 
-	for (i = 0; i < sizeof(bw_val); i++) {
-		ret = regmap_write(dev->regmap[2], 0x13 + i, bw_val[i]);
-		if (ret)
-			goto err;
+	/* Bandwidth */
+	if (bandwidth_vals_ptr) {
+		for (i = 0; i < 7; i++) {
+			ret = regmap_write(dev->regmap[2], 0x13 + i,
+					   bandwidth_vals_ptr[i]);
+			if (ret)
+				goto err;
+		}
 	}
 
+	ret = regmap_write(dev->regmap[0], 0xb4, reg_bank0_b4_val);
+	if (ret)
+		goto err;
+	ret = regmap_write(dev->regmap[0], 0xcd, reg_bank0_cd_val);
+	if (ret)
+		goto err;
+	ret = regmap_write(dev->regmap[0], 0xd4, reg_bank0_d4_val);
+	if (ret)
+		goto err;
+	ret = regmap_write(dev->regmap[0], 0xd6, reg_bank0_d6_val);
+	if (ret)
+		goto err;
+
 	switch (c->delivery_system) {
 	case SYS_DVBT:
 		ret = regmap_write(dev->regmap[0], 0x07, 0x26);
-		ret = regmap_write(dev->regmap[0], 0xb0, 0x0a);
-		ret = regmap_write(dev->regmap[0], 0xb4, 0x00);
-		ret = regmap_write(dev->regmap[0], 0xcd, 0x1f);
-		ret = regmap_write(dev->regmap[0], 0xd4, 0x0a);
-		ret = regmap_write(dev->regmap[0], 0xd6, 0x48);
+		if (ret)
+			goto err;
 		ret = regmap_write(dev->regmap[0], 0x00, 0xba);
+		if (ret)
+			goto err;
 		ret = regmap_write(dev->regmap[0], 0x01, 0x13);
 		if (ret)
 			goto err;
 		break;
 	case SYS_DVBT2:
 		ret = regmap_write(dev->regmap[2], 0x2b, 0x13);
+		if (ret)
+			goto err;
 		ret = regmap_write(dev->regmap[2], 0x4f, 0x05);
+		if (ret)
+			goto err;
 		ret = regmap_write(dev->regmap[1], 0xf6, 0x05);
-		ret = regmap_write(dev->regmap[0], 0xb0, 0x0a);
-		ret = regmap_write(dev->regmap[0], 0xb4, 0xf6);
-		ret = regmap_write(dev->regmap[0], 0xcd, 0x01);
-		ret = regmap_write(dev->regmap[0], 0xd4, 0x09);
-		ret = regmap_write(dev->regmap[0], 0xd6, 0x46);
-		ret = regmap_write(dev->regmap[2], 0x30, 0x80);
-		ret = regmap_write(dev->regmap[2], 0x32, 0x00);
 		if (ret)
 			goto err;
-		break;
-	case SYS_DVBC_ANNEX_A:
-		ret = regmap_write(dev->regmap[0], 0xb0, 0x0b);
-		ret = regmap_write(dev->regmap[0], 0xb4, 0x00);
-		ret = regmap_write(dev->regmap[0], 0xcd, 0x17);
-		ret = regmap_write(dev->regmap[0], 0xd4, 0x09);
-		ret = regmap_write(dev->regmap[0], 0xd6, 0x48);
-		ret = regmap_write(dev->regmap[1], 0x00, 0xb0);
+		ret = regmap_write(dev->regmap[2], 0x32, c->stream_id);
 		if (ret)
 			goto err;
 		break;
-	default:
-		ret = -EINVAL;
-		goto err;
-	}
-
-	ret = regmap_write(dev->regmap[0], 0x46, 0x00);
-	ret = regmap_write(dev->regmap[0], 0xae, 0x00);
-
-	switch (dev->ts_mode) {
-	case SERIAL_TS_MODE:
-		ret = regmap_write(dev->regmap[2], 0x08, 0x1d);
-		break;
-	case PARALLEL_TS_MODE:
-		ret = regmap_write(dev->regmap[2], 0x08, 0x00);
+	case SYS_DVBC_ANNEX_A:
 		break;
 	default:
-		dev_dbg(&client->dev, "ts_mode error: %d\n", dev->ts_mode);
-		ret = -EINVAL;
-		goto err;
-	}
-
-	switch (dev->ts_clock) {
-	case VARIABLE_TS_CLOCK:
-		ret = regmap_write(dev->regmap[0], 0xd9, 0xe3);
 		break;
-	case FIXED_TS_CLOCK:
-		ret = regmap_write(dev->regmap[0], 0xd9, 0xe1);
-		break;
-	default:
-		dev_dbg(&client->dev, "ts_clock error: %d\n", dev->ts_clock);
-		ret = -EINVAL;
-		goto err;
 	}
 
-	/* Reset demod */
+	/* Reset FSM */
 	ret = regmap_write(dev->regmap[2], 0xf8, 0x9f);
 	if (ret)
 		goto err;
 
-	dev->delivery_system = c->delivery_system;
-
-	return 0;
-err:
-	dev_dbg(&client->dev, "failed=%d\n", ret);
-	return ret;
-}
-
-static int mn88472_read_status(struct dvb_frontend *fe, enum fe_status *status)
-{
-	struct i2c_client *client = fe->demodulator_priv;
-	struct mn88472_dev *dev = i2c_get_clientdata(client);
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	int ret;
-	unsigned int utmp;
-	int lock = 0;
-
-	*status = 0;
-
-	if (!dev->warm) {
-		ret = -EAGAIN;
-		goto err;
-	}
-
-	switch (c->delivery_system) {
-	case SYS_DVBT:
-		ret = regmap_read(dev->regmap[0], 0x7F, &utmp);
-		if (ret)
-			goto err;
-		if ((utmp & 0xF) >= 0x09)
-			lock = 1;
-		break;
-	case SYS_DVBT2:
-		ret = regmap_read(dev->regmap[2], 0x92, &utmp);
-		if (ret)
-			goto err;
-		if ((utmp & 0xF) >= 0x07)
-			*status |= FE_HAS_SIGNAL;
-		if ((utmp & 0xF) >= 0x0a)
-			*status |= FE_HAS_CARRIER;
-		if ((utmp & 0xF) >= 0x0d)
-			*status |= FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
-		break;
-	case SYS_DVBC_ANNEX_A:
-		ret = regmap_read(dev->regmap[1], 0x84, &utmp);
-		if (ret)
-			goto err;
-		if ((utmp & 0xF) >= 0x08)
-			lock = 1;
-		break;
-	default:
-		ret = -EINVAL;
-		goto err;
-	}
-
-	if (lock)
-		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_VITERBI |
-				FE_HAS_SYNC | FE_HAS_LOCK;
-
 	return 0;
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
@@ -279,93 +280,107 @@ static int mn88472_init(struct dvb_frontend *fe)
 {
 	struct i2c_client *client = fe->demodulator_priv;
 	struct mn88472_dev *dev = i2c_get_clientdata(client);
-	int ret, len, remaining;
-	const struct firmware *fw = NULL;
-	u8 *fw_file = MN88472_FIRMWARE;
-	unsigned int tmp;
+	int ret, len, rem;
+	unsigned int utmp;
+	const struct firmware *firmware;
+	const char *name = MN88472_FIRMWARE;
 
 	dev_dbg(&client->dev, "\n");
 
-	/* set cold state by default */
-	dev->warm = false;
-
-	/* power on */
+	/* Power up */
 	ret = regmap_write(dev->regmap[2], 0x05, 0x00);
 	if (ret)
 		goto err;
-
-	ret = regmap_bulk_write(dev->regmap[2], 0x0b, "\x00\x00", 2);
+	ret = regmap_write(dev->regmap[2], 0x0b, 0x00);
 	if (ret)
 		goto err;
-
-	/* check if firmware is already running */
-	ret = regmap_read(dev->regmap[0], 0xf5, &tmp);
+	ret = regmap_write(dev->regmap[2], 0x0c, 0x00);
 	if (ret)
 		goto err;
 
-	if (!(tmp & 0x1)) {
-		dev_info(&client->dev, "firmware already running\n");
-		dev->warm = true;
-		return 0;
-	}
+	/* Check if firmware is already running */
+	ret = regmap_read(dev->regmap[0], 0xf5, &utmp);
+	if (ret)
+		goto err;
+	if (!(utmp & 0x01))
+		goto warm;
 
-	/* request the firmware, this will block and timeout */
-	ret = request_firmware(&fw, fw_file, &client->dev);
+	ret = request_firmware(&firmware, name, &client->dev);
 	if (ret) {
-		dev_err(&client->dev, "firmare file '%s' not found\n",
-				fw_file);
+		dev_err(&client->dev, "firmware file '%s' not found\n", name);
 		goto err;
 	}
 
-	dev_info(&client->dev, "downloading firmware from file '%s'\n",
-			fw_file);
+	dev_info(&client->dev, "downloading firmware from file '%s'\n", name);
 
 	ret = regmap_write(dev->regmap[0], 0xf5, 0x03);
 	if (ret)
-		goto firmware_release;
-
-	for (remaining = fw->size; remaining > 0;
-			remaining -= (dev->i2c_wr_max - 1)) {
-		len = remaining;
-		if (len > (dev->i2c_wr_max - 1))
-			len = dev->i2c_wr_max - 1;
+		goto err_release_firmware;
 
+	for (rem = firmware->size; rem > 0; rem -= (dev->i2c_write_max - 1)) {
+		len = min(dev->i2c_write_max - 1, rem);
 		ret = regmap_bulk_write(dev->regmap[0], 0xf6,
-				&fw->data[fw->size - remaining], len);
+					&firmware->data[firmware->size - rem],
+					len);
 		if (ret) {
-			dev_err(&client->dev,
-					"firmware download failed=%d\n", ret);
-			goto firmware_release;
+			dev_err(&client->dev, "firmware download failed %d\n",
+				ret);
+			goto err_release_firmware;
 		}
 	}
 
-	/* parity check of firmware */
-	ret = regmap_read(dev->regmap[0], 0xf8, &tmp);
-	if (ret) {
-		dev_err(&client->dev,
-				"parity reg read failed=%d\n", ret);
-		goto firmware_release;
-	}
-	if (tmp & 0x10) {
-		dev_err(&client->dev,
-				"firmware parity check failed=0x%x\n", tmp);
-		goto firmware_release;
+	/* Parity check of firmware */
+	ret = regmap_read(dev->regmap[0], 0xf8, &utmp);
+	if (ret)
+		goto err_release_firmware;
+	if (utmp & 0x10) {
+		ret = -EINVAL;
+		dev_err(&client->dev, "firmware did not run\n");
+		goto err_release_firmware;
 	}
-	dev_err(&client->dev, "firmware parity check succeeded=0x%x\n", tmp);
 
 	ret = regmap_write(dev->regmap[0], 0xf5, 0x00);
 	if (ret)
-		goto firmware_release;
+		goto err_release_firmware;
+
+	release_firmware(firmware);
+warm:
+	/* TS config */
+	switch (dev->ts_mode) {
+	case SERIAL_TS_MODE:
+		utmp = 0x1d;
+		break;
+	case PARALLEL_TS_MODE:
+		utmp = 0x00;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err;
+	}
+	ret = regmap_write(dev->regmap[2], 0x08, utmp);
+	if (ret)
+		goto err;
 
-	release_firmware(fw);
-	fw = NULL;
+	switch (dev->ts_clk) {
+	case VARIABLE_TS_CLOCK:
+		utmp = 0xe3;
+		break;
+	case FIXED_TS_CLOCK:
+		utmp = 0xe1;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err;
+	}
+	ret = regmap_write(dev->regmap[0], 0xd9, utmp);
+	if (ret)
+		goto err;
 
-	/* warm state */
-	dev->warm = true;
+	dev->active = true;
 
 	return 0;
-firmware_release:
-	release_firmware(fw);
+err_release_firmware:
+	release_firmware(firmware);
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
 	return ret;
@@ -379,18 +394,17 @@ static int mn88472_sleep(struct dvb_frontend *fe)
 
 	dev_dbg(&client->dev, "\n");
 
-	/* power off */
+	/* Power down */
+	ret = regmap_write(dev->regmap[2], 0x0c, 0x30);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x0b, 0x30);
-
 	if (ret)
 		goto err;
-
 	ret = regmap_write(dev->regmap[2], 0x05, 0x3e);
 	if (ret)
 		goto err;
 
-	dev->delivery_system = SYS_UNDEFINED;
-
 	return 0;
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
@@ -434,10 +448,19 @@ static struct dvb_frontend_ops mn88472_ops = {
 	.read_status = mn88472_read_status,
 };
 
+static struct dvb_frontend *mn88472_get_dvb_frontend(struct i2c_client *client)
+{
+	struct mn88472_dev *dev = i2c_get_clientdata(client);
+
+	dev_dbg(&client->dev, "\n");
+
+	return &dev->fe;
+}
+
 static int mn88472_probe(struct i2c_client *client,
-		const struct i2c_device_id *id)
+			 const struct i2c_device_id *id)
 {
-	struct mn88472_config *config = client->dev.platform_data;
+	struct mn88472_config *pdata = client->dev.platform_data;
 	struct mn88472_dev *dev;
 	int ret;
 	unsigned int utmp;
@@ -448,23 +471,16 @@ static int mn88472_probe(struct i2c_client *client,
 
 	dev_dbg(&client->dev, "\n");
 
-	/* Caller really need to provide pointer for frontend we create. */
-	if (config->fe == NULL) {
-		dev_err(&client->dev, "frontend pointer not defined\n");
-		ret = -EINVAL;
-		goto err;
-	}
-
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev) {
 		ret = -ENOMEM;
 		goto err;
 	}
 
-	dev->i2c_wr_max = config->i2c_wr_max;
-	dev->xtal = config->xtal;
-	dev->ts_mode = config->ts_mode;
-	dev->ts_clock = config->ts_clock;
+	dev->i2c_write_max = pdata->i2c_wr_max ? pdata->i2c_wr_max : ~0;
+	dev->clk = pdata->xtal;
+	dev->ts_mode = pdata->ts_mode;
+	dev->ts_clk = pdata->ts_clock;
 	dev->client[0] = client;
 	dev->regmap[0] = regmap_init_i2c(dev->client[0], &regmap_config);
 	if (IS_ERR(dev->regmap[0])) {
@@ -472,15 +488,25 @@ static int mn88472_probe(struct i2c_client *client,
 		goto err_kfree;
 	}
 
-	/* check demod answers to I2C */
-	ret = regmap_read(dev->regmap[0], 0x00, &utmp);
+	/* Check demod answers with correct chip id */
+	ret = regmap_read(dev->regmap[0], 0xff, &utmp);
 	if (ret)
 		goto err_regmap_0_regmap_exit;
 
+	dev_dbg(&client->dev, "chip id=%02x\n", utmp);
+
+	if (utmp != 0x02) {
+		ret = -ENODEV;
+		goto err_regmap_0_regmap_exit;
+	}
+
 	/*
-	 * Chip has three I2C addresses for different register pages. Used
+	 * Chip has three I2C addresses for different register banks. Used
 	 * addresses are 0x18, 0x1a and 0x1c. We register two dummy clients,
-	 * 0x1a and 0x1c, in order to get own I2C client for each register page.
+	 * 0x1a and 0x1c, in order to get own I2C client for each register bank.
+	 *
+	 * Also, register bank 2 do not support sequential I/O. Only single
+	 * register write or read is allowed to that bank.
 	 */
 	dev->client[1] = i2c_new_dummy(client->adapter, 0x1a);
 	if (!dev->client[1]) {
@@ -510,15 +536,25 @@ static int mn88472_probe(struct i2c_client *client,
 	}
 	i2c_set_clientdata(dev->client[2], dev);
 
-	/* create dvb_frontend */
+	/* Sleep because chip is active by default */
+	ret = regmap_write(dev->regmap[2], 0x05, 0x3e);
+	if (ret)
+		goto err_regmap_2_regmap_exit;
+
+	/* Create dvb frontend */
 	memcpy(&dev->fe.ops, &mn88472_ops, sizeof(struct dvb_frontend_ops));
 	dev->fe.demodulator_priv = client;
-	*config->fe = &dev->fe;
+	*pdata->fe = &dev->fe;
 	i2c_set_clientdata(client, dev);
 
-	dev_info(&client->dev, "Panasonic MN88472 successfully attached\n");
-	return 0;
+	/* Setup callbacks */
+	pdata->get_dvb_frontend = mn88472_get_dvb_frontend;
 
+	dev_info(&client->dev, "Panasonic MN88472 successfully identified\n");
+
+	return 0;
+err_regmap_2_regmap_exit:
+	regmap_exit(dev->regmap[2]);
 err_client_2_i2c_unregister_device:
 	i2c_unregister_device(dev->client[2]);
 err_regmap_1_regmap_exit:
@@ -561,11 +597,12 @@ MODULE_DEVICE_TABLE(i2c, mn88472_id_table);
 
 static struct i2c_driver mn88472_driver = {
 	.driver = {
-		.name	= "mn88472",
+		.name = "mn88472",
+		.suppress_bind_attrs = true,
 	},
-	.probe		= mn88472_probe,
-	.remove		= mn88472_remove,
-	.id_table	= mn88472_id_table,
+	.probe    = mn88472_probe,
+	.remove   = mn88472_remove,
+	.id_table = mn88472_id_table,
 };
 
 module_i2c_driver(mn88472_driver);
diff --git a/drivers/media/dvb-frontends/mn88472.h b/drivers/media/dvb-frontends/mn88472.h
index 095294d292f3..323632523876 100644
--- a/drivers/media/dvb-frontends/mn88472.h
+++ b/drivers/media/dvb-frontends/mn88472.h
@@ -19,23 +19,33 @@
 
 #include <linux/dvb/frontend.h>
 
-enum ts_clock {
-	VARIABLE_TS_CLOCK,
-	FIXED_TS_CLOCK,
-};
+/**
+ * struct mn88472_config - Platform data for the mn88472 driver
+ * @xtal: Clock frequency.
+ * @ts_mode: TS mode.
+ * @ts_clock: TS clock config.
+ * @i2c_wr_max: Max number of bytes driver writes to I2C at once.
+ * @get_dvb_frontend: Get DVB frontend.
+ */
 
-enum ts_mode {
-	SERIAL_TS_MODE,
-	PARALLEL_TS_MODE,
-};
+/* Define old names for backward compatibility */
+#define VARIABLE_TS_CLOCK   MN88472_TS_CLK_VARIABLE
+#define FIXED_TS_CLOCK      MN88472_TS_CLK_FIXED
+#define SERIAL_TS_MODE      MN88472_TS_MODE_SERIAL
+#define PARALLEL_TS_MODE    MN88472_TS_MODE_PARALLEL
 
 struct mn88472_config {
-	/*
-	 * Max num of bytes given I2C adapter could write at once.
-	 * Default: none
-	 */
-	u16 i2c_wr_max;
+	unsigned int xtal;
+
+#define MN88472_TS_MODE_SERIAL      0
+#define MN88472_TS_MODE_PARALLEL    1
+	int ts_mode;
 
+#define MN88472_TS_CLK_FIXED        0
+#define MN88472_TS_CLK_VARIABLE     1
+	int ts_clock;
+
+	u16 i2c_wr_max;
 
 	/* Everything after that is returned by the driver. */
 
@@ -43,14 +53,7 @@ struct mn88472_config {
 	 * DVB frontend.
 	 */
 	struct dvb_frontend **fe;
-
-	/*
-	 * Xtal frequency.
-	 * Hz
-	 */
-	u32 xtal;
-	int ts_mode;
-	int ts_clock;
+	struct dvb_frontend* (*get_dvb_frontend)(struct i2c_client *);
 };
 
 #endif
diff --git a/drivers/staging/media/mn88472/mn88472_priv.h b/drivers/media/dvb-frontends/mn88472_priv.h
index 1a0de9e46b66..cdf2597a25d1 100644
--- a/drivers/staging/media/mn88472/mn88472_priv.h
+++ b/drivers/media/dvb-frontends/mn88472_priv.h
@@ -28,12 +28,11 @@ struct mn88472_dev {
 	struct i2c_client *client[3];
 	struct regmap *regmap[3];
 	struct dvb_frontend fe;
-	u16 i2c_wr_max;
-	enum fe_delivery_system delivery_system;
-	bool warm; /* FW running */
-	u32 xtal;
-	int ts_mode;
-	int ts_clock;
+	u16 i2c_write_max;
+	unsigned int clk;
+	unsigned int active:1;
+	unsigned int ts_mode:1;
+	unsigned int ts_clk:1;
 };
 
 #endif
diff --git a/drivers/media/dvb-frontends/mn88473.c b/drivers/media/dvb-frontends/mn88473.c
index 6c5d592161d4..451974a1d7ed 100644
--- a/drivers/media/dvb-frontends/mn88473.c
+++ b/drivers/media/dvb-frontends/mn88473.c
@@ -330,7 +330,7 @@ static int mn88473_init(struct dvb_frontend *fe)
 	/* Request the firmware, this will block and timeout */
 	ret = request_firmware(&fw, name, &client->dev);
 	if (ret) {
-		dev_err(&client->dev, "firmare file '%s' not found\n", name);
+		dev_err(&client->dev, "firmware file '%s' not found\n", name);
 		goto err;
 	}
 
@@ -536,7 +536,7 @@ static int mn88473_probe(struct i2c_client *client,
 	/* Sleep because chip is active by default */
 	ret = regmap_write(dev->regmap[2], 0x05, 0x3e);
 	if (ret)
-		goto err_client_2_i2c_unregister_device;
+		goto err_regmap_2_regmap_exit;
 
 	/* Create dvb frontend */
 	memcpy(&dev->frontend.ops, &mn88473_ops, sizeof(dev->frontend.ops));
@@ -547,7 +547,8 @@ static int mn88473_probe(struct i2c_client *client,
 	dev_info(&client->dev, "Panasonic MN88473 successfully identified\n");
 
 	return 0;
-
+err_regmap_2_regmap_exit:
+	regmap_exit(dev->regmap[2]);
 err_client_2_i2c_unregister_device:
 	i2c_unregister_device(dev->client[2]);
 err_regmap_1_regmap_exit:
diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c
index d25d1e0cd4ca..87226056f226 100644
--- a/drivers/media/dvb-frontends/rtl2830.c
+++ b/drivers/media/dvb-frontends/rtl2830.c
@@ -135,8 +135,6 @@ static int rtl2830_init(struct dvb_frontend *fe)
 	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	c->post_bit_count.len = 1;
 	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	/* start statistics polling */
-	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
 
 	dev->sleeping = false;
 
@@ -152,8 +150,6 @@ static int rtl2830_sleep(struct dvb_frontend *fe)
 	struct rtl2830_dev *dev = i2c_get_clientdata(client);
 
 	dev->sleeping = true;
-	/* stop statistics polling */
-	cancel_delayed_work_sync(&dev->stat_work);
 	dev->fe_status = 0;
 
 	return 0;
@@ -396,8 +392,10 @@ static int rtl2830_read_status(struct dvb_frontend *fe, enum fe_status *status)
 {
 	struct i2c_client *client = fe->demodulator_priv;
 	struct rtl2830_dev *dev = i2c_get_clientdata(client);
-	int ret;
-	u8 u8tmp;
+	struct dtv_frontend_properties *c = &dev->fe.dtv_property_cache;
+	int ret, stmp;
+	unsigned int utmp;
+	u8 u8tmp, buf[2];
 
 	*status = 0;
 
@@ -419,6 +417,89 @@ static int rtl2830_read_status(struct dvb_frontend *fe, enum fe_status *status)
 
 	dev->fe_status = *status;
 
+	/* Signal strength */
+	if (dev->fe_status & FE_HAS_SIGNAL) {
+		/* Read IF AGC */
+		ret = rtl2830_bulk_read(client, 0x359, buf, 2);
+		if (ret)
+			goto err;
+
+		stmp = buf[0] << 8 | buf[1] << 0;
+		stmp = sign_extend32(stmp, 13);
+		utmp = clamp_val(-4 * stmp + 32767, 0x0000, 0xffff);
+
+		dev_dbg(&client->dev, "IF AGC=%d\n", stmp);
+
+		c->strength.stat[0].scale = FE_SCALE_RELATIVE;
+		c->strength.stat[0].uvalue = utmp;
+	} else {
+		c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	}
+
+	/* CNR */
+	if (dev->fe_status & FE_HAS_VITERBI) {
+		unsigned int hierarchy, constellation;
+		#define CONSTELLATION_NUM 3
+		#define HIERARCHY_NUM 4
+		static const u32 constant[CONSTELLATION_NUM][HIERARCHY_NUM] = {
+			{70705899, 70705899, 70705899, 70705899},
+			{82433173, 82433173, 87483115, 94445660},
+			{92888734, 92888734, 95487525, 99770748},
+		};
+
+		ret = rtl2830_bulk_read(client, 0x33c, &u8tmp, 1);
+		if (ret)
+			goto err;
+
+		constellation = (u8tmp >> 2) & 0x03; /* [3:2] */
+		if (constellation > CONSTELLATION_NUM - 1)
+			goto err;
+
+		hierarchy = (u8tmp >> 4) & 0x07; /* [6:4] */
+		if (hierarchy > HIERARCHY_NUM - 1)
+			goto err;
+
+		ret = rtl2830_bulk_read(client, 0x40c, buf, 2);
+		if (ret)
+			goto err;
+
+		utmp = buf[0] << 8 | buf[1] << 0;
+		if (utmp)
+			stmp = (constant[constellation][hierarchy] -
+			       intlog10(utmp)) / ((1 << 24) / 10000);
+		else
+			stmp = 0;
+
+		dev_dbg(&client->dev, "CNR raw=%u\n", utmp);
+
+		c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+		c->cnr.stat[0].svalue = stmp;
+	} else {
+		c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	}
+
+	/* BER */
+	if (dev->fe_status & FE_HAS_LOCK) {
+		ret = rtl2830_bulk_read(client, 0x34e, buf, 2);
+		if (ret)
+			goto err;
+
+		utmp = buf[0] << 8 | buf[1] << 0;
+		dev->post_bit_error += utmp;
+		dev->post_bit_count += 1000000;
+
+		dev_dbg(&client->dev, "BER errors=%u total=1000000\n", utmp);
+
+		c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+		c->post_bit_error.stat[0].uvalue = dev->post_bit_error;
+		c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+		c->post_bit_count.stat[0].uvalue = dev->post_bit_count;
+	} else {
+		c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+		c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	}
+
+
 	return ret;
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
@@ -503,109 +584,6 @@ static struct dvb_frontend_ops rtl2830_ops = {
 	.read_signal_strength = rtl2830_read_signal_strength,
 };
 
-static void rtl2830_stat_work(struct work_struct *work)
-{
-	struct rtl2830_dev *dev = container_of(work, struct rtl2830_dev, stat_work.work);
-	struct i2c_client *client = dev->client;
-	struct dtv_frontend_properties *c = &dev->fe.dtv_property_cache;
-	int ret, tmp;
-	u8 u8tmp, buf[2];
-	u16 u16tmp;
-
-	dev_dbg(&client->dev, "\n");
-
-	/* signal strength */
-	if (dev->fe_status & FE_HAS_SIGNAL) {
-		struct {signed int x:14; } s;
-
-		/* read IF AGC */
-		ret = rtl2830_bulk_read(client, 0x359, buf, 2);
-		if (ret)
-			goto err;
-
-		u16tmp = buf[0] << 8 | buf[1] << 0;
-		u16tmp &= 0x3fff; /* [13:0] */
-		tmp = s.x = u16tmp; /* 14-bit bin to 2 complement */
-		u16tmp = clamp_val(-4 * tmp + 32767, 0x0000, 0xffff);
-
-		dev_dbg(&client->dev, "IF AGC=%d\n", tmp);
-
-		c->strength.stat[0].scale = FE_SCALE_RELATIVE;
-		c->strength.stat[0].uvalue = u16tmp;
-	} else {
-		c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	}
-
-	/* CNR */
-	if (dev->fe_status & FE_HAS_VITERBI) {
-		unsigned hierarchy, constellation;
-		#define CONSTELLATION_NUM 3
-		#define HIERARCHY_NUM 4
-		static const u32 constant[CONSTELLATION_NUM][HIERARCHY_NUM] = {
-			{70705899, 70705899, 70705899, 70705899},
-			{82433173, 82433173, 87483115, 94445660},
-			{92888734, 92888734, 95487525, 99770748},
-		};
-
-		ret = rtl2830_bulk_read(client, 0x33c, &u8tmp, 1);
-		if (ret)
-			goto err;
-
-		constellation = (u8tmp >> 2) & 0x03; /* [3:2] */
-		if (constellation > CONSTELLATION_NUM - 1)
-			goto err_schedule_delayed_work;
-
-		hierarchy = (u8tmp >> 4) & 0x07; /* [6:4] */
-		if (hierarchy > HIERARCHY_NUM - 1)
-			goto err_schedule_delayed_work;
-
-		ret = rtl2830_bulk_read(client, 0x40c, buf, 2);
-		if (ret)
-			goto err;
-
-		u16tmp = buf[0] << 8 | buf[1] << 0;
-		if (u16tmp)
-			tmp = (constant[constellation][hierarchy] -
-			       intlog10(u16tmp)) / ((1 << 24) / 10000);
-		else
-			tmp = 0;
-
-		dev_dbg(&client->dev, "CNR raw=%u\n", u16tmp);
-
-		c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
-		c->cnr.stat[0].svalue = tmp;
-	} else {
-		c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	}
-
-	/* BER */
-	if (dev->fe_status & FE_HAS_LOCK) {
-		ret = rtl2830_bulk_read(client, 0x34e, buf, 2);
-		if (ret)
-			goto err;
-
-		u16tmp = buf[0] << 8 | buf[1] << 0;
-		dev->post_bit_error += u16tmp;
-		dev->post_bit_count += 1000000;
-
-		dev_dbg(&client->dev, "BER errors=%u total=1000000\n", u16tmp);
-
-		c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
-		c->post_bit_error.stat[0].uvalue = dev->post_bit_error;
-		c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
-		c->post_bit_count.stat[0].uvalue = dev->post_bit_count;
-	} else {
-		c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-		c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	}
-
-err_schedule_delayed_work:
-	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
-	return;
-err:
-	dev_dbg(&client->dev, "failed=%d\n", ret);
-}
-
 static int rtl2830_pid_filter_ctrl(struct dvb_frontend *fe, int onoff)
 {
 	struct i2c_client *client = fe->demodulator_priv;
@@ -851,7 +829,6 @@ static int rtl2830_probe(struct i2c_client *client,
 	dev->client = client;
 	dev->pdata = client->dev.platform_data;
 	dev->sleeping = true;
-	INIT_DELAYED_WORK(&dev->stat_work, rtl2830_stat_work);
 	dev->regmap = regmap_init(&client->dev, &regmap_bus, client,
 				  &regmap_config);
 	if (IS_ERR(dev->regmap)) {
@@ -904,9 +881,6 @@ static int rtl2830_remove(struct i2c_client *client)
 
 	dev_dbg(&client->dev, "\n");
 
-	/* stop statistics polling */
-	cancel_delayed_work_sync(&dev->stat_work);
-
 	i2c_mux_del_adapters(dev->muxc);
 	regmap_exit(dev->regmap);
 	kfree(dev);
@@ -922,7 +896,8 @@ MODULE_DEVICE_TABLE(i2c, rtl2830_id_table);
 
 static struct i2c_driver rtl2830_driver = {
 	.driver = {
-		.name	= "rtl2830",
+		.name			= "rtl2830",
+		.suppress_bind_attrs	= true,
 	},
 	.probe		= rtl2830_probe,
 	.remove		= rtl2830_remove,
diff --git a/drivers/media/dvb-frontends/rtl2830_priv.h b/drivers/media/dvb-frontends/rtl2830_priv.h
index da4909543da2..8ec4721d79ac 100644
--- a/drivers/media/dvb-frontends/rtl2830_priv.h
+++ b/drivers/media/dvb-frontends/rtl2830_priv.h
@@ -24,6 +24,7 @@
 #include <linux/i2c-mux.h>
 #include <linux/math64.h>
 #include <linux/regmap.h>
+#include <linux/bitops.h>
 
 struct rtl2830_dev {
 	struct rtl2830_platform_data *pdata;
@@ -33,7 +34,6 @@ struct rtl2830_dev {
 	struct dvb_frontend fe;
 	bool sleeping;
 	unsigned long filters;
-	struct delayed_work stat_work;
 	enum fe_status fe_status;
 	u64 post_bit_error_prev; /* for old DVBv3 read_ber() calculation */
 	u64 post_bit_error;
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index bfb6beedd40b..0ced01f1012e 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -947,6 +947,8 @@ static int rtl2832_slave_ts_ctrl(struct i2c_client *client, bool enable)
 			goto err;
 	}
 
+	dev->slave_ts = enable;
+
 	return 0;
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
@@ -960,7 +962,7 @@ static int rtl2832_pid_filter_ctrl(struct dvb_frontend *fe, int onoff)
 	int ret;
 	u8 u8tmp;
 
-	dev_dbg(&client->dev, "onoff=%d\n", onoff);
+	dev_dbg(&client->dev, "onoff=%d, slave_ts=%d\n", onoff, dev->slave_ts);
 
 	/* enable / disable PID filter */
 	if (onoff)
@@ -968,7 +970,10 @@ static int rtl2832_pid_filter_ctrl(struct dvb_frontend *fe, int onoff)
 	else
 		u8tmp = 0x00;
 
-	ret = regmap_update_bits(dev->regmap, 0x061, 0xc0, u8tmp);
+	if (dev->slave_ts)
+		ret = regmap_update_bits(dev->regmap, 0x021, 0xc0, u8tmp);
+	else
+		ret = regmap_update_bits(dev->regmap, 0x061, 0xc0, u8tmp);
 	if (ret)
 		goto err;
 
@@ -986,8 +991,8 @@ static int rtl2832_pid_filter(struct dvb_frontend *fe, u8 index, u16 pid,
 	int ret;
 	u8 buf[4];
 
-	dev_dbg(&client->dev, "index=%d pid=%04x onoff=%d\n",
-		index, pid, onoff);
+	dev_dbg(&client->dev, "index=%d pid=%04x onoff=%d slave_ts=%d\n",
+		index, pid, onoff, dev->slave_ts);
 
 	/* skip invalid PIDs (0x2000) */
 	if (pid > 0x1fff || index > 32)
@@ -1003,14 +1008,22 @@ static int rtl2832_pid_filter(struct dvb_frontend *fe, u8 index, u16 pid,
 	buf[1] = (dev->filters >>  8) & 0xff;
 	buf[2] = (dev->filters >> 16) & 0xff;
 	buf[3] = (dev->filters >> 24) & 0xff;
-	ret = regmap_bulk_write(dev->regmap, 0x062, buf, 4);
+
+	if (dev->slave_ts)
+		ret = regmap_bulk_write(dev->regmap, 0x022, buf, 4);
+	else
+		ret = regmap_bulk_write(dev->regmap, 0x062, buf, 4);
 	if (ret)
 		goto err;
 
 	/* add PID */
 	buf[0] = (pid >> 8) & 0xff;
 	buf[1] = (pid >> 0) & 0xff;
-	ret = regmap_bulk_write(dev->regmap, 0x066 + 2 * index, buf, 2);
+
+	if (dev->slave_ts)
+		ret = regmap_bulk_write(dev->regmap, 0x026 + 2 * index, buf, 2);
+	else
+		ret = regmap_bulk_write(dev->regmap, 0x066 + 2 * index, buf, 2);
 	if (ret)
 		goto err;
 
@@ -1135,6 +1148,7 @@ MODULE_DEVICE_TABLE(i2c, rtl2832_id_table);
 static struct i2c_driver rtl2832_driver = {
 	.driver = {
 		.name	= "rtl2832",
+		.suppress_bind_attrs	= true,
 	},
 	.probe		= rtl2832_probe,
 	.remove		= rtl2832_remove,
diff --git a/drivers/media/dvb-frontends/rtl2832_priv.h b/drivers/media/dvb-frontends/rtl2832_priv.h
index c1a8a69e9015..9a6d01a9c690 100644
--- a/drivers/media/dvb-frontends/rtl2832_priv.h
+++ b/drivers/media/dvb-frontends/rtl2832_priv.h
@@ -44,6 +44,7 @@ struct rtl2832_dev {
 	bool sleeping;
 	struct delayed_work i2c_gate_work;
 	unsigned long filters; /* PID filter */
+	bool slave_ts;
 };
 
 struct rtl2832_reg_entry {
diff --git a/drivers/media/dvb-frontends/rtl2832_sdr.c b/drivers/media/dvb-frontends/rtl2832_sdr.c
index 47a480a7d46c..6e22af36b637 100644
--- a/drivers/media/dvb-frontends/rtl2832_sdr.c
+++ b/drivers/media/dvb-frontends/rtl2832_sdr.c
@@ -452,7 +452,7 @@ static int rtl2832_sdr_querycap(struct file *file, void *fh,
 /* Videobuf2 operations */
 static int rtl2832_sdr_queue_setup(struct vb2_queue *vq,
 		unsigned int *nbuffers,
-		unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
+		unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct rtl2832_sdr_dev *dev = vb2_get_drv_priv(vq);
 	struct platform_device *pdev = dev->pdev;
diff --git a/drivers/media/dvb-frontends/si2168.c b/drivers/media/dvb-frontends/si2168.c
index 108a069fa1ae..20b4a659e2e4 100644
--- a/drivers/media/dvb-frontends/si2168.c
+++ b/drivers/media/dvb-frontends/si2168.c
@@ -357,9 +357,7 @@ static int si2168_init(struct dvb_frontend *fe)
 	struct si2168_dev *dev = i2c_get_clientdata(client);
 	int ret, len, remaining;
 	const struct firmware *fw;
-	const char *fw_name;
 	struct si2168_cmd cmd;
-	unsigned int chip_id;
 
 	dev_dbg(&client->dev, "\n");
 
@@ -371,7 +369,7 @@ static int si2168_init(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	if (dev->fw_loaded) {
+	if (dev->warm) {
 		/* resume */
 		memcpy(cmd.args, "\xc0\x06\x08\x0f\x00\x20\x21\x01", 8);
 		cmd.wlen = 8;
@@ -398,49 +396,14 @@ static int si2168_init(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	/* query chip revision */
-	memcpy(cmd.args, "\x02", 1);
-	cmd.wlen = 1;
-	cmd.rlen = 13;
-	ret = si2168_cmd_execute(client, &cmd);
-	if (ret)
-		goto err;
-
-	chip_id = cmd.args[1] << 24 | cmd.args[2] << 16 | cmd.args[3] << 8 |
-			cmd.args[4] << 0;
-
-	#define SI2168_A20 ('A' << 24 | 68 << 16 | '2' << 8 | '0' << 0)
-	#define SI2168_A30 ('A' << 24 | 68 << 16 | '3' << 8 | '0' << 0)
-	#define SI2168_B40 ('B' << 24 | 68 << 16 | '4' << 8 | '0' << 0)
-
-	switch (chip_id) {
-	case SI2168_A20:
-		fw_name = SI2168_A20_FIRMWARE;
-		break;
-	case SI2168_A30:
-		fw_name = SI2168_A30_FIRMWARE;
-		break;
-	case SI2168_B40:
-		fw_name = SI2168_B40_FIRMWARE;
-		break;
-	default:
-		dev_err(&client->dev, "unknown chip version Si21%d-%c%c%c\n",
-				cmd.args[2], cmd.args[1],
-				cmd.args[3], cmd.args[4]);
-		ret = -EINVAL;
-		goto err;
-	}
-
-	dev_info(&client->dev, "found a 'Silicon Labs Si21%d-%c%c%c'\n",
-			cmd.args[2], cmd.args[1], cmd.args[3], cmd.args[4]);
-
 	/* request the firmware, this will block and timeout */
-	ret = request_firmware(&fw, fw_name, &client->dev);
+	ret = request_firmware(&fw, dev->firmware_name, &client->dev);
 	if (ret) {
 		/* fallback mechanism to handle old name for Si2168 B40 fw */
-		if (chip_id == SI2168_B40) {
-			fw_name = SI2168_B40_FIRMWARE_FALLBACK;
-			ret = request_firmware(&fw, fw_name, &client->dev);
+		if (dev->chip_id == SI2168_CHIP_ID_B40) {
+			dev->firmware_name = SI2168_B40_FIRMWARE_FALLBACK;
+			ret = request_firmware(&fw, dev->firmware_name,
+					       &client->dev);
 		}
 
 		if (ret == 0) {
@@ -450,13 +413,13 @@ static int si2168_init(struct dvb_frontend *fe)
 		} else {
 			dev_err(&client->dev,
 					"firmware file '%s' not found\n",
-					fw_name);
+					dev->firmware_name);
 			goto err_release_firmware;
 		}
 	}
 
 	dev_info(&client->dev, "downloading firmware from file '%s'\n",
-			fw_name);
+			dev->firmware_name);
 
 	if ((fw->size % 17 == 0) && (fw->data[0] > 5)) {
 		/* firmware is in the new format */
@@ -511,8 +474,11 @@ static int si2168_init(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	dev_info(&client->dev, "firmware version: %c.%c.%d\n",
-			cmd.args[6], cmd.args[7], cmd.args[8]);
+	dev->version = (cmd.args[9] + '@') << 24 | (cmd.args[6] - '0') << 16 |
+		       (cmd.args[7] - '0') << 8 | (cmd.args[8]) << 0;
+	dev_info(&client->dev, "firmware version: %c %d.%d.%d\n",
+		 dev->version >> 24 & 0xff, dev->version >> 16 & 0xff,
+		 dev->version >> 8 & 0xff, dev->version >> 0 & 0xff);
 
 	/* set ts mode */
 	memcpy(cmd.args, "\x14\x00\x01\x10\x10\x00", 6);
@@ -525,7 +491,7 @@ static int si2168_init(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	dev->fw_loaded = true;
+	dev->warm = true;
 warm:
 	dev->active = true;
 
@@ -549,6 +515,10 @@ static int si2168_sleep(struct dvb_frontend *fe)
 
 	dev->active = false;
 
+	/* Firmware B 4.0-11 or later loses warm state during sleep */
+	if (dev->version > ('B' << 24 | 4 << 16 | 0 << 8 | 11 << 0))
+		dev->warm = false;
+
 	memcpy(cmd.args, "\x13", 1);
 	cmd.wlen = 1;
 	cmd.rlen = 0;
@@ -653,6 +623,7 @@ static int si2168_probe(struct i2c_client *client,
 	struct si2168_config *config = client->dev.platform_data;
 	struct si2168_dev *dev;
 	int ret;
+	struct si2168_cmd cmd;
 
 	dev_dbg(&client->dev, "\n");
 
@@ -663,8 +634,56 @@ static int si2168_probe(struct i2c_client *client,
 		goto err;
 	}
 
+	i2c_set_clientdata(client, dev);
 	mutex_init(&dev->i2c_mutex);
 
+	/* Initialize */
+	memcpy(cmd.args, "\xc0\x12\x00\x0c\x00\x0d\x16\x00\x00\x00\x00\x00\x00", 13);
+	cmd.wlen = 13;
+	cmd.rlen = 0;
+	ret = si2168_cmd_execute(client, &cmd);
+	if (ret)
+		goto err_kfree;
+
+	/* Power up */
+	memcpy(cmd.args, "\xc0\x06\x01\x0f\x00\x20\x20\x01", 8);
+	cmd.wlen = 8;
+	cmd.rlen = 1;
+	ret = si2168_cmd_execute(client, &cmd);
+	if (ret)
+		goto err_kfree;
+
+	/* Query chip revision */
+	memcpy(cmd.args, "\x02", 1);
+	cmd.wlen = 1;
+	cmd.rlen = 13;
+	ret = si2168_cmd_execute(client, &cmd);
+	if (ret)
+		goto err_kfree;
+
+	dev->chip_id = cmd.args[1] << 24 | cmd.args[2] << 16 |
+		       cmd.args[3] << 8 | cmd.args[4] << 0;
+
+	switch (dev->chip_id) {
+	case SI2168_CHIP_ID_A20:
+		dev->firmware_name = SI2168_A20_FIRMWARE;
+		break;
+	case SI2168_CHIP_ID_A30:
+		dev->firmware_name = SI2168_A30_FIRMWARE;
+		break;
+	case SI2168_CHIP_ID_B40:
+		dev->firmware_name = SI2168_B40_FIRMWARE;
+		break;
+	default:
+		dev_dbg(&client->dev, "unknown chip version Si21%d-%c%c%c\n",
+			cmd.args[2], cmd.args[1], cmd.args[3], cmd.args[4]);
+		ret = -ENODEV;
+		goto err_kfree;
+	}
+
+	dev->version = (cmd.args[1]) << 24 | (cmd.args[3] - '0') << 16 |
+		       (cmd.args[4] - '0') << 8 | (cmd.args[5]) << 0;
+
 	/* create mux i2c adapter for tuner */
 	dev->muxc = i2c_mux_alloc(client->adapter, &client->dev,
 				  1, 0, I2C_MUX_LOCKED,
@@ -686,11 +705,14 @@ static int si2168_probe(struct i2c_client *client,
 	dev->ts_mode = config->ts_mode;
 	dev->ts_clock_inv = config->ts_clock_inv;
 	dev->ts_clock_gapped = config->ts_clock_gapped;
-	dev->fw_loaded = false;
 
-	i2c_set_clientdata(client, dev);
+	dev_info(&client->dev, "Silicon Labs Si2168-%c%d%d successfully identified\n",
+		 dev->version >> 24 & 0xff, dev->version >> 16 & 0xff,
+		 dev->version >> 8 & 0xff);
+	dev_info(&client->dev, "firmware version: %c %d.%d.%d\n",
+		 dev->version >> 24 & 0xff, dev->version >> 16 & 0xff,
+		 dev->version >> 8 & 0xff, dev->version >> 0 & 0xff);
 
-	dev_info(&client->dev, "Silicon Labs Si2168 successfully attached\n");
 	return 0;
 err_kfree:
 	kfree(dev);
@@ -723,7 +745,8 @@ MODULE_DEVICE_TABLE(i2c, si2168_id_table);
 
 static struct i2c_driver si2168_driver = {
 	.driver = {
-		.name	= "si2168",
+		.name                = "si2168",
+		.suppress_bind_attrs = true,
 	},
 	.probe		= si2168_probe,
 	.remove		= si2168_remove,
diff --git a/drivers/media/dvb-frontends/si2168_priv.h b/drivers/media/dvb-frontends/si2168_priv.h
index 8a1f36d2014d..7843ccb448a0 100644
--- a/drivers/media/dvb-frontends/si2168_priv.h
+++ b/drivers/media/dvb-frontends/si2168_priv.h
@@ -34,8 +34,14 @@ struct si2168_dev {
 	struct dvb_frontend fe;
 	enum fe_delivery_system delivery_system;
 	enum fe_status fe_status;
+	#define SI2168_CHIP_ID_A20 ('A' << 24 | 68 << 16 | '2' << 8 | '0' << 0)
+	#define SI2168_CHIP_ID_A30 ('A' << 24 | 68 << 16 | '3' << 8 | '0' << 0)
+	#define SI2168_CHIP_ID_B40 ('B' << 24 | 68 << 16 | '4' << 8 | '0' << 0)
+	unsigned int chip_id;
+	unsigned int version;
+	const char *firmware_name;
 	bool active;
-	bool fw_loaded;
+	bool warm;
 	u8 ts_mode;
 	bool ts_clock_inv;
 	bool ts_clock_gapped;
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 993dc50c12db..ce9006e10a30 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -209,6 +209,7 @@ config VIDEO_ADV7604
 	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API
 	depends on GPIOLIB || COMPILE_TEST
 	select HDMI
+	select MEDIA_CEC_EDID
 	---help---
 	  Support for the Analog Devices ADV7604 video decoder.
 
@@ -218,10 +219,18 @@ config VIDEO_ADV7604
 	  To compile this driver as a module, choose M here: the
 	  module will be called adv7604.
 
+config VIDEO_ADV7604_CEC
+	bool "Enable Analog Devices ADV7604 CEC support"
+	depends on VIDEO_ADV7604 && MEDIA_CEC
+	---help---
+	  When selected the adv7604 will support the optional
+	  HDMI CEC feature.
+
 config VIDEO_ADV7842
 	tristate "Analog Devices ADV7842 decoder"
 	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API
 	select HDMI
+	select MEDIA_CEC_EDID
 	---help---
 	  Support for the Analog Devices ADV7842 video decoder.
 
@@ -231,6 +240,13 @@ config VIDEO_ADV7842
 	  To compile this driver as a module, choose M here: the
 	  module will be called adv7842.
 
+config VIDEO_ADV7842_CEC
+	bool "Enable Analog Devices ADV7842 CEC support"
+	depends on VIDEO_ADV7842 && MEDIA_CEC
+	---help---
+	  When selected the adv7842 will support the optional
+	  HDMI CEC feature.
+
 config VIDEO_BT819
 	tristate "BT819A VideoStream decoder"
 	depends on VIDEO_V4L2 && I2C
@@ -447,6 +463,7 @@ config VIDEO_ADV7511
 	tristate "Analog Devices ADV7511 encoder"
 	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API
 	select HDMI
+	select MEDIA_CEC_EDID
 	---help---
 	  Support for the Analog Devices ADV7511 video encoder.
 
@@ -455,6 +472,13 @@ config VIDEO_ADV7511
 	  To compile this driver as a module, choose M here: the
 	  module will be called adv7511.
 
+config VIDEO_ADV7511_CEC
+	bool "Enable Analog Devices ADV7511 CEC support"
+	depends on VIDEO_ADV7511 && MEDIA_CEC
+	---help---
+	  When selected the adv7511 will support the optional
+	  HDMI CEC feature.
+
 config VIDEO_AD9389B
 	tristate "Analog Devices AD9389B encoder"
 	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API
diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c
index 39271c35da48..6d7cad54a65d 100644
--- a/drivers/media/i2c/adv7511.c
+++ b/drivers/media/i2c/adv7511.c
@@ -33,6 +33,7 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-dv-timings.h>
 #include <media/i2c/adv7511.h>
+#include <media/cec.h>
 
 static int debug;
 module_param(debug, int, 0644);
@@ -59,6 +60,8 @@ MODULE_LICENSE("GPL v2");
 #define ADV7511_MIN_PIXELCLOCK 20000000
 #define ADV7511_MAX_PIXELCLOCK 225000000
 
+#define ADV7511_MAX_ADDRS (3)
+
 /*
 **********************************************************************
 *
@@ -90,12 +93,20 @@ struct adv7511_state {
 	struct v4l2_ctrl_handler hdl;
 	int chip_revision;
 	u8 i2c_edid_addr;
-	u8 i2c_cec_addr;
 	u8 i2c_pktmem_addr;
+	u8 i2c_cec_addr;
+
+	struct i2c_client *i2c_cec;
+	struct cec_adapter *cec_adap;
+	u8   cec_addr[ADV7511_MAX_ADDRS];
+	u8   cec_valid_addrs;
+	bool cec_enabled_adap;
+
 	/* Is the adv7511 powered on? */
 	bool power_on;
 	/* Did we receive hotplug and rx-sense signals? */
 	bool have_monitor;
+	bool enabled_irq;
 	/* timings from s_dv_timings */
 	struct v4l2_dv_timings dv_timings;
 	u32 fmt_code;
@@ -227,7 +238,7 @@ static int adv_smbus_read_i2c_block_data(struct i2c_client *client,
 	return ret;
 }
 
-static inline void adv7511_edid_rd(struct v4l2_subdev *sd, u16 len, u8 *buf)
+static void adv7511_edid_rd(struct v4l2_subdev *sd, uint16_t len, uint8_t *buf)
 {
 	struct adv7511_state *state = get_adv7511_state(sd);
 	int i;
@@ -242,6 +253,34 @@ static inline void adv7511_edid_rd(struct v4l2_subdev *sd, u16 len, u8 *buf)
 		v4l2_err(sd, "%s: i2c read error\n", __func__);
 }
 
+static inline int adv7511_cec_read(struct v4l2_subdev *sd, u8 reg)
+{
+	struct adv7511_state *state = get_adv7511_state(sd);
+
+	return i2c_smbus_read_byte_data(state->i2c_cec, reg);
+}
+
+static int adv7511_cec_write(struct v4l2_subdev *sd, u8 reg, u8 val)
+{
+	struct adv7511_state *state = get_adv7511_state(sd);
+	int ret;
+	int i;
+
+	for (i = 0; i < 3; i++) {
+		ret = i2c_smbus_write_byte_data(state->i2c_cec, reg, val);
+		if (ret == 0)
+			return 0;
+	}
+	v4l2_err(sd, "%s: I2C Write Problem\n", __func__);
+	return ret;
+}
+
+static inline int adv7511_cec_write_and_or(struct v4l2_subdev *sd, u8 reg, u8 mask,
+				   u8 val)
+{
+	return adv7511_cec_write(sd, reg, (adv7511_cec_read(sd, reg) & mask) | val);
+}
+
 static int adv7511_pktmem_rd(struct v4l2_subdev *sd, u8 reg)
 {
 	struct adv7511_state *state = get_adv7511_state(sd);
@@ -343,28 +382,20 @@ static void adv7511_csc_rgb_full2limit(struct v4l2_subdev *sd, bool enable)
 	}
 }
 
-static void adv7511_set_IT_content_AVI_InfoFrame(struct v4l2_subdev *sd)
+static void adv7511_set_rgb_quantization_mode(struct v4l2_subdev *sd, struct v4l2_ctrl *ctrl)
 {
 	struct adv7511_state *state = get_adv7511_state(sd);
-	if (state->dv_timings.bt.flags & V4L2_DV_FL_IS_CE_VIDEO) {
-		/* CE format, not IT  */
-		adv7511_wr_and_or(sd, 0x57, 0x7f, 0x00);
-	} else {
-		/* IT format */
-		adv7511_wr_and_or(sd, 0x57, 0x7f, 0x80);
+
+	/* Only makes sense for RGB formats */
+	if (state->fmt_code != MEDIA_BUS_FMT_RGB888_1X24) {
+		/* so just keep quantization */
+		adv7511_csc_rgb_full2limit(sd, false);
+		return;
 	}
-}
 
-static int adv7511_set_rgb_quantization_mode(struct v4l2_subdev *sd, struct v4l2_ctrl *ctrl)
-{
 	switch (ctrl->val) {
-	default:
-		return -EINVAL;
-		break;
-	case V4L2_DV_RGB_RANGE_AUTO: {
+	case V4L2_DV_RGB_RANGE_AUTO:
 		/* automatic */
-		struct adv7511_state *state = get_adv7511_state(sd);
-
 		if (state->dv_timings.bt.flags & V4L2_DV_FL_IS_CE_VIDEO) {
 			/* CE format, RGB limited range (16-235) */
 			adv7511_csc_rgb_full2limit(sd, true);
@@ -372,7 +403,6 @@ static int adv7511_set_rgb_quantization_mode(struct v4l2_subdev *sd, struct v4l2
 			/* not CE format, RGB full range (0-255) */
 			adv7511_csc_rgb_full2limit(sd, false);
 		}
-	}
 		break;
 	case V4L2_DV_RGB_RANGE_LIMITED:
 		/* RGB limited range (16-235) */
@@ -383,7 +413,6 @@ static int adv7511_set_rgb_quantization_mode(struct v4l2_subdev *sd, struct v4l2
 		adv7511_csc_rgb_full2limit(sd, false);
 		break;
 	}
-	return 0;
 }
 
 /* ------------------------------ CTRL OPS ------------------------------ */
@@ -400,8 +429,10 @@ static int adv7511_s_ctrl(struct v4l2_ctrl *ctrl)
 		adv7511_wr_and_or(sd, 0xaf, 0xfd, ctrl->val == V4L2_DV_TX_MODE_HDMI ? 0x02 : 0x00);
 		return 0;
 	}
-	if (state->rgb_quantization_range_ctrl == ctrl)
-		return adv7511_set_rgb_quantization_mode(sd, ctrl);
+	if (state->rgb_quantization_range_ctrl == ctrl) {
+		adv7511_set_rgb_quantization_mode(sd, ctrl);
+		return 0;
+	}
 	if (state->content_type_ctrl == ctrl) {
 		u8 itc, cn;
 
@@ -425,16 +456,28 @@ static const struct v4l2_ctrl_ops adv7511_ctrl_ops = {
 #ifdef CONFIG_VIDEO_ADV_DEBUG
 static void adv7511_inv_register(struct v4l2_subdev *sd)
 {
+	struct adv7511_state *state = get_adv7511_state(sd);
+
 	v4l2_info(sd, "0x000-0x0ff: Main Map\n");
+	if (state->i2c_cec)
+		v4l2_info(sd, "0x100-0x1ff: CEC Map\n");
 }
 
 static int adv7511_g_register(struct v4l2_subdev *sd, struct v4l2_dbg_register *reg)
 {
+	struct adv7511_state *state = get_adv7511_state(sd);
+
 	reg->size = 1;
 	switch (reg->reg >> 8) {
 	case 0:
 		reg->val = adv7511_rd(sd, reg->reg & 0xff);
 		break;
+	case 1:
+		if (state->i2c_cec) {
+			reg->val = adv7511_cec_read(sd, reg->reg & 0xff);
+			break;
+		}
+		/* fall through */
 	default:
 		v4l2_info(sd, "Register %03llx not supported\n", reg->reg);
 		adv7511_inv_register(sd);
@@ -445,10 +488,18 @@ static int adv7511_g_register(struct v4l2_subdev *sd, struct v4l2_dbg_register *
 
 static int adv7511_s_register(struct v4l2_subdev *sd, const struct v4l2_dbg_register *reg)
 {
+	struct adv7511_state *state = get_adv7511_state(sd);
+
 	switch (reg->reg >> 8) {
 	case 0:
 		adv7511_wr(sd, reg->reg & 0xff, reg->val & 0xff);
 		break;
+	case 1:
+		if (state->i2c_cec) {
+			adv7511_cec_write(sd, reg->reg & 0xff, reg->val & 0xff);
+			break;
+		}
+		/* fall through */
 	default:
 		v4l2_info(sd, "Register %03llx not supported\n", reg->reg);
 		adv7511_inv_register(sd);
@@ -536,6 +587,7 @@ static int adv7511_log_status(struct v4l2_subdev *sd)
 {
 	struct adv7511_state *state = get_adv7511_state(sd);
 	struct adv7511_state_edid *edid = &state->edid;
+	int i;
 
 	static const char * const states[] = {
 		"in reset",
@@ -605,7 +657,23 @@ static int adv7511_log_status(struct v4l2_subdev *sd)
 	else
 		v4l2_info(sd, "no timings set\n");
 	v4l2_info(sd, "i2c edid addr: 0x%x\n", state->i2c_edid_addr);
+
+	if (state->i2c_cec == NULL)
+		return 0;
+
 	v4l2_info(sd, "i2c cec addr: 0x%x\n", state->i2c_cec_addr);
+
+	v4l2_info(sd, "CEC: %s\n", state->cec_enabled_adap ?
+			"enabled" : "disabled");
+	if (state->cec_enabled_adap) {
+		for (i = 0; i < ADV7511_MAX_ADDRS; i++) {
+			bool is_valid = state->cec_valid_addrs & (1 << i);
+
+			if (is_valid)
+				v4l2_info(sd, "CEC Logical Address: 0x%x\n",
+					  state->cec_addr[i]);
+		}
+	}
 	v4l2_info(sd, "i2c pktmem addr: 0x%x\n", state->i2c_pktmem_addr);
 	return 0;
 }
@@ -663,15 +731,197 @@ static int adv7511_s_power(struct v4l2_subdev *sd, int on)
 	return true;
 }
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7511_CEC)
+static int adv7511_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct adv7511_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+
+	if (state->i2c_cec == NULL)
+		return -EIO;
+
+	if (!state->cec_enabled_adap && enable) {
+		/* power up cec section */
+		adv7511_cec_write_and_or(sd, 0x4e, 0xfc, 0x01);
+		/* legacy mode and clear all rx buffers */
+		adv7511_cec_write(sd, 0x4a, 0x07);
+		adv7511_cec_write(sd, 0x4a, 0);
+		adv7511_cec_write_and_or(sd, 0x11, 0xfe, 0); /* initially disable tx */
+		/* enabled irqs: */
+		/* tx: ready */
+		/* tx: arbitration lost */
+		/* tx: retry timeout */
+		/* rx: ready 1 */
+		if (state->enabled_irq)
+			adv7511_wr_and_or(sd, 0x95, 0xc0, 0x39);
+	} else if (state->cec_enabled_adap && !enable) {
+		if (state->enabled_irq)
+			adv7511_wr_and_or(sd, 0x95, 0xc0, 0x00);
+		/* disable address mask 1-3 */
+		adv7511_cec_write_and_or(sd, 0x4b, 0x8f, 0x00);
+		/* power down cec section */
+		adv7511_cec_write_and_or(sd, 0x4e, 0xfc, 0x00);
+		state->cec_valid_addrs = 0;
+	}
+	state->cec_enabled_adap = enable;
+	return 0;
+}
+
+static int adv7511_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct adv7511_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+	unsigned int i, free_idx = ADV7511_MAX_ADDRS;
+
+	if (!state->cec_enabled_adap)
+		return addr == CEC_LOG_ADDR_INVALID ? 0 : -EIO;
+
+	if (addr == CEC_LOG_ADDR_INVALID) {
+		adv7511_cec_write_and_or(sd, 0x4b, 0x8f, 0);
+		state->cec_valid_addrs = 0;
+		return 0;
+	}
+
+	for (i = 0; i < ADV7511_MAX_ADDRS; i++) {
+		bool is_valid = state->cec_valid_addrs & (1 << i);
+
+		if (free_idx == ADV7511_MAX_ADDRS && !is_valid)
+			free_idx = i;
+		if (is_valid && state->cec_addr[i] == addr)
+			return 0;
+	}
+	if (i == ADV7511_MAX_ADDRS) {
+		i = free_idx;
+		if (i == ADV7511_MAX_ADDRS)
+			return -ENXIO;
+	}
+	state->cec_addr[i] = addr;
+	state->cec_valid_addrs |= 1 << i;
+
+	switch (i) {
+	case 0:
+		/* enable address mask 0 */
+		adv7511_cec_write_and_or(sd, 0x4b, 0xef, 0x10);
+		/* set address for mask 0 */
+		adv7511_cec_write_and_or(sd, 0x4c, 0xf0, addr);
+		break;
+	case 1:
+		/* enable address mask 1 */
+		adv7511_cec_write_and_or(sd, 0x4b, 0xdf, 0x20);
+		/* set address for mask 1 */
+		adv7511_cec_write_and_or(sd, 0x4c, 0x0f, addr << 4);
+		break;
+	case 2:
+		/* enable address mask 2 */
+		adv7511_cec_write_and_or(sd, 0x4b, 0xbf, 0x40);
+		/* set address for mask 1 */
+		adv7511_cec_write_and_or(sd, 0x4d, 0xf0, addr);
+		break;
+	}
+	return 0;
+}
+
+static int adv7511_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				     u32 signal_free_time, struct cec_msg *msg)
+{
+	struct adv7511_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+	u8 len = msg->len;
+	unsigned int i;
+
+	v4l2_dbg(1, debug, sd, "%s: len %d\n", __func__, len);
+
+	if (len > 16) {
+		v4l2_err(sd, "%s: len exceeded 16 (%d)\n", __func__, len);
+		return -EINVAL;
+	}
+
+	/*
+	 * The number of retries is the number of attempts - 1, but retry
+	 * at least once. It's not clear if a value of 0 is allowed, so
+	 * let's do at least one retry.
+	 */
+	adv7511_cec_write_and_or(sd, 0x12, ~0x70, max(1, attempts - 1) << 4);
+
+	/* blocking, clear cec tx irq status */
+	adv7511_wr_and_or(sd, 0x97, 0xc7, 0x38);
+
+	/* write data */
+	for (i = 0; i < len; i++)
+		adv7511_cec_write(sd, i, msg->msg[i]);
+
+	/* set length (data + header) */
+	adv7511_cec_write(sd, 0x10, len);
+	/* start transmit, enable tx */
+	adv7511_cec_write(sd, 0x11, 0x01);
+	return 0;
+}
+
+static void adv_cec_tx_raw_status(struct v4l2_subdev *sd, u8 tx_raw_status)
+{
+	struct adv7511_state *state = get_adv7511_state(sd);
+
+	if ((adv7511_cec_read(sd, 0x11) & 0x01) == 0) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: tx disabled\n", __func__);
+		return;
+	}
+
+	if (tx_raw_status & 0x10) {
+		v4l2_dbg(1, debug, sd,
+			 "%s: tx raw: arbitration lost\n", __func__);
+		cec_transmit_done(state->cec_adap, CEC_TX_STATUS_ARB_LOST,
+				  1, 0, 0, 0);
+		return;
+	}
+	if (tx_raw_status & 0x08) {
+		u8 status;
+		u8 nack_cnt;
+		u8 low_drive_cnt;
+
+		v4l2_dbg(1, debug, sd, "%s: tx raw: retry failed\n", __func__);
+		/*
+		 * We set this status bit since this hardware performs
+		 * retransmissions.
+		 */
+		status = CEC_TX_STATUS_MAX_RETRIES;
+		nack_cnt = adv7511_cec_read(sd, 0x14) & 0xf;
+		if (nack_cnt)
+			status |= CEC_TX_STATUS_NACK;
+		low_drive_cnt = adv7511_cec_read(sd, 0x14) >> 4;
+		if (low_drive_cnt)
+			status |= CEC_TX_STATUS_LOW_DRIVE;
+		cec_transmit_done(state->cec_adap, status,
+				  0, nack_cnt, low_drive_cnt, 0);
+		return;
+	}
+	if (tx_raw_status & 0x20) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: ready ok\n", __func__);
+		cec_transmit_done(state->cec_adap, CEC_TX_STATUS_OK, 0, 0, 0, 0);
+		return;
+	}
+}
+
+static const struct cec_adap_ops adv7511_cec_adap_ops = {
+	.adap_enable = adv7511_cec_adap_enable,
+	.adap_log_addr = adv7511_cec_adap_log_addr,
+	.adap_transmit = adv7511_cec_adap_transmit,
+};
+#endif
+
 /* Enable interrupts */
 static void adv7511_set_isr(struct v4l2_subdev *sd, bool enable)
 {
+	struct adv7511_state *state = get_adv7511_state(sd);
 	u8 irqs = MASK_ADV7511_HPD_INT | MASK_ADV7511_MSEN_INT;
 	u8 irqs_rd;
 	int retries = 100;
 
 	v4l2_dbg(2, debug, sd, "%s: %s\n", __func__, enable ? "enable" : "disable");
 
+	if (state->enabled_irq == enable)
+		return;
+	state->enabled_irq = enable;
+
 	/* The datasheet says that the EDID ready interrupt should be
 	   disabled if there is no hotplug. */
 	if (!enable)
@@ -679,6 +929,9 @@ static void adv7511_set_isr(struct v4l2_subdev *sd, bool enable)
 	else if (adv7511_have_hotplug(sd))
 		irqs |= MASK_ADV7511_EDID_RDY_INT;
 
+	adv7511_wr_and_or(sd, 0x95, 0xc0,
+			  (state->cec_enabled_adap && enable) ? 0x39 : 0x00);
+
 	/*
 	 * This i2c write can fail (approx. 1 in 1000 writes). But it
 	 * is essential that this register is correct, so retry it
@@ -701,20 +954,53 @@ static void adv7511_set_isr(struct v4l2_subdev *sd, bool enable)
 static int adv7511_isr(struct v4l2_subdev *sd, u32 status, bool *handled)
 {
 	u8 irq_status;
+	u8 cec_irq;
 
 	/* disable interrupts to prevent a race condition */
 	adv7511_set_isr(sd, false);
 	irq_status = adv7511_rd(sd, 0x96);
+	cec_irq = adv7511_rd(sd, 0x97);
 	/* clear detected interrupts */
 	adv7511_wr(sd, 0x96, irq_status);
+	adv7511_wr(sd, 0x97, cec_irq);
 
-	v4l2_dbg(1, debug, sd, "%s: irq 0x%x\n", __func__, irq_status);
+	v4l2_dbg(1, debug, sd, "%s: irq 0x%x, cec-irq 0x%x\n", __func__,
+		 irq_status, cec_irq);
 
 	if (irq_status & (MASK_ADV7511_HPD_INT | MASK_ADV7511_MSEN_INT))
 		adv7511_check_monitor_present_status(sd);
 	if (irq_status & MASK_ADV7511_EDID_RDY_INT)
 		adv7511_check_edid_status(sd);
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7511_CEC)
+	if (cec_irq & 0x38)
+		adv_cec_tx_raw_status(sd, cec_irq);
+
+	if (cec_irq & 1) {
+		struct adv7511_state *state = get_adv7511_state(sd);
+		struct cec_msg msg;
+
+		msg.len = adv7511_cec_read(sd, 0x25) & 0x1f;
+
+		v4l2_dbg(1, debug, sd, "%s: cec msg len %d\n", __func__,
+			 msg.len);
+
+		if (msg.len > 16)
+			msg.len = 16;
+
+		if (msg.len) {
+			u8 i;
+
+			for (i = 0; i < msg.len; i++)
+				msg.msg[i] = adv7511_cec_read(sd, i + 0x15);
+
+			adv7511_cec_write(sd, 0x4a, 1); /* toggle to re-enable rx 1 */
+			adv7511_cec_write(sd, 0x4a, 0);
+			cec_received_msg(state->cec_adap, &msg);
+		}
+	}
+#endif
+
 	/* enable interrupts */
 	adv7511_set_isr(sd, true);
 
@@ -771,12 +1057,14 @@ static int adv7511_s_dv_timings(struct v4l2_subdev *sd,
 	/* save timings */
 	state->dv_timings = *timings;
 
+	/* set h/vsync polarities */
+	adv7511_wr_and_or(sd, 0x17, 0x9f,
+		((timings->bt.polarities & V4L2_DV_VSYNC_POS_POL) ? 0 : 0x40) |
+		((timings->bt.polarities & V4L2_DV_HSYNC_POS_POL) ? 0 : 0x20));
+
 	/* update quantization range based on new dv_timings */
 	adv7511_set_rgb_quantization_mode(sd, state->rgb_quantization_range_ctrl);
 
-	/* update AVI infoframe */
-	adv7511_set_IT_content_AVI_InfoFrame(sd);
-
 	return 0;
 }
 
@@ -956,8 +1244,6 @@ static int adv7511_enum_mbus_code(struct v4l2_subdev *sd,
 static void adv7511_fill_format(struct adv7511_state *state,
 				struct v4l2_mbus_framefmt *format)
 {
-	memset(format, 0, sizeof(*format));
-
 	format->width = state->dv_timings.bt.width;
 	format->height = state->dv_timings.bt.height;
 	format->field = V4L2_FIELD_NONE;
@@ -972,6 +1258,7 @@ static int adv7511_get_fmt(struct v4l2_subdev *sd,
 	if (format->pad != 0)
 		return -EINVAL;
 
+	memset(&format->format, 0, sizeof(format->format));
 	adv7511_fill_format(state, &format->format);
 
 	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
@@ -1132,6 +1419,7 @@ static int adv7511_set_fmt(struct v4l2_subdev *sd,
 	adv7511_wr_and_or(sd, 0x57, 0x83, (ec << 4) | (q << 2) | (itc << 7));
 	adv7511_wr_and_or(sd, 0x59, 0x0f, (yq << 6) | (cn << 4));
 	adv7511_wr_and_or(sd, 0x4a, 0xff, 1);
+	adv7511_set_rgb_quantization_mode(sd, state->rgb_quantization_range_ctrl);
 
 	return 0;
 }
@@ -1183,6 +1471,8 @@ static void adv7511_notify_no_edid(struct v4l2_subdev *sd)
 	/* We failed to read the EDID, so send an event for this. */
 	ed.present = false;
 	ed.segment = adv7511_rd(sd, 0xc4);
+	ed.phys_addr = CEC_PHYS_ADDR_INVALID;
+	cec_s_phys_addr(state->cec_adap, ed.phys_addr, false);
 	v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
 	v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, 0x0);
 }
@@ -1406,13 +1696,16 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd)
 
 		v4l2_dbg(1, debug, sd, "%s: edid complete with %d segment(s)\n", __func__, state->edid.segments);
 		state->edid.complete = true;
-
+		ed.phys_addr = cec_get_edid_phys_addr(state->edid.data,
+						      state->edid.segments * 256,
+						      NULL);
 		/* report when we have all segments
 		   but report only for segment 0
 		 */
 		ed.present = true;
 		ed.segment = 0;
 		state->edid_detect_counter++;
+		cec_s_phys_addr(state->cec_adap, ed.phys_addr, false);
 		v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
 		return ed.present;
 	}
@@ -1420,17 +1713,43 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd)
 	return false;
 }
 
+static int adv7511_registered(struct v4l2_subdev *sd)
+{
+	struct adv7511_state *state = get_adv7511_state(sd);
+	int err;
+
+	err = cec_register_adapter(state->cec_adap);
+	if (err)
+		cec_delete_adapter(state->cec_adap);
+	return err;
+}
+
+static void adv7511_unregistered(struct v4l2_subdev *sd)
+{
+	struct adv7511_state *state = get_adv7511_state(sd);
+
+	cec_unregister_adapter(state->cec_adap);
+}
+
+static const struct v4l2_subdev_internal_ops adv7511_int_ops = {
+	.registered = adv7511_registered,
+	.unregistered = adv7511_unregistered,
+};
+
 /* ----------------------------------------------------------------------- */
 /* Setup ADV7511 */
 static void adv7511_init_setup(struct v4l2_subdev *sd)
 {
 	struct adv7511_state *state = get_adv7511_state(sd);
 	struct adv7511_state_edid *edid = &state->edid;
+	u32 cec_clk = state->pdata.cec_clk;
+	u8 ratio;
 
 	v4l2_dbg(1, debug, sd, "%s\n", __func__);
 
 	/* clear all interrupts */
 	adv7511_wr(sd, 0x96, 0xff);
+	adv7511_wr(sd, 0x97, 0xff);
 	/*
 	 * Stop HPD from resetting a lot of registers.
 	 * It might leave the chip in a partly un-initialized state,
@@ -1442,6 +1761,25 @@ static void adv7511_init_setup(struct v4l2_subdev *sd)
 	adv7511_set_isr(sd, false);
 	adv7511_s_stream(sd, false);
 	adv7511_s_audio_stream(sd, false);
+
+	if (state->i2c_cec == NULL)
+		return;
+
+	v4l2_dbg(1, debug, sd, "%s: cec_clk %d\n", __func__, cec_clk);
+
+	/* cec soft reset */
+	adv7511_cec_write(sd, 0x50, 0x01);
+	adv7511_cec_write(sd, 0x50, 0x00);
+
+	/* legacy mode */
+	adv7511_cec_write(sd, 0x4a, 0x00);
+
+	if (cec_clk % 750000 != 0)
+		v4l2_err(sd, "%s: cec_clk %d, not multiple of 750 Khz\n",
+			 __func__, cec_clk);
+
+	ratio = (cec_clk / 750000) - 1;
+	adv7511_cec_write(sd, 0x4e, ratio << 2);
 }
 
 static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *id)
@@ -1476,6 +1814,7 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *
 			 client->addr << 1);
 
 	v4l2_i2c_subdev_init(sd, client, &adv7511_ops);
+	sd->internal_ops = &adv7511_int_ops;
 
 	hdl = &state->hdl;
 	v4l2_ctrl_handler_init(hdl, 10);
@@ -1516,26 +1855,47 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *
 	chip_id[0] = adv7511_rd(sd, 0xf5);
 	chip_id[1] = adv7511_rd(sd, 0xf6);
 	if (chip_id[0] != 0x75 || chip_id[1] != 0x11) {
-		v4l2_err(sd, "chip_id != 0x7511, read 0x%02x%02x\n", chip_id[0], chip_id[1]);
+		v4l2_err(sd, "chip_id != 0x7511, read 0x%02x%02x\n", chip_id[0],
+			 chip_id[1]);
 		err = -EIO;
 		goto err_entity;
 	}
 
-	state->i2c_edid = i2c_new_dummy(client->adapter, state->i2c_edid_addr >> 1);
+	state->i2c_edid = i2c_new_dummy(client->adapter,
+					state->i2c_edid_addr >> 1);
 	if (state->i2c_edid == NULL) {
 		v4l2_err(sd, "failed to register edid i2c client\n");
 		err = -ENOMEM;
 		goto err_entity;
 	}
 
+	adv7511_wr(sd, 0xe1, state->i2c_cec_addr);
+	if (state->pdata.cec_clk < 3000000 ||
+	    state->pdata.cec_clk > 100000000) {
+		v4l2_err(sd, "%s: cec_clk %u outside range, disabling cec\n",
+				__func__, state->pdata.cec_clk);
+		state->pdata.cec_clk = 0;
+	}
+
+	if (state->pdata.cec_clk) {
+		state->i2c_cec = i2c_new_dummy(client->adapter,
+					       state->i2c_cec_addr >> 1);
+		if (state->i2c_cec == NULL) {
+			v4l2_err(sd, "failed to register cec i2c client\n");
+			goto err_unreg_edid;
+		}
+		adv7511_wr(sd, 0xe2, 0x00); /* power up cec section */
+	} else {
+		adv7511_wr(sd, 0xe2, 0x01); /* power down cec section */
+	}
+
 	state->i2c_pktmem = i2c_new_dummy(client->adapter, state->i2c_pktmem_addr >> 1);
 	if (state->i2c_pktmem == NULL) {
 		v4l2_err(sd, "failed to register pktmem i2c client\n");
 		err = -ENOMEM;
-		goto err_unreg_edid;
+		goto err_unreg_cec;
 	}
 
-	adv7511_wr(sd, 0xe2, 0x01); /* power down cec section */
 	state->work_queue = create_singlethread_workqueue(sd->name);
 	if (state->work_queue == NULL) {
 		v4l2_err(sd, "could not create workqueue\n");
@@ -1546,6 +1906,19 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *
 	INIT_DELAYED_WORK(&state->edid_handler, adv7511_edid_handler);
 
 	adv7511_init_setup(sd);
+
+#if IS_ENABLED(CONFIG_VIDEO_ADV7511_CEC)
+	state->cec_adap = cec_allocate_adapter(&adv7511_cec_adap_ops,
+		state, dev_name(&client->dev), CEC_CAP_TRANSMIT |
+		CEC_CAP_LOG_ADDRS | CEC_CAP_PASSTHROUGH | CEC_CAP_RC,
+		ADV7511_MAX_ADDRS, &client->dev);
+	err = PTR_ERR_OR_ZERO(state->cec_adap);
+	if (err) {
+		destroy_workqueue(state->work_queue);
+		goto err_unreg_pktmem;
+	}
+#endif
+
 	adv7511_set_isr(sd, true);
 	adv7511_check_monitor_present_status(sd);
 
@@ -1555,6 +1928,9 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *
 
 err_unreg_pktmem:
 	i2c_unregister_device(state->i2c_pktmem);
+err_unreg_cec:
+	if (state->i2c_cec)
+		i2c_unregister_device(state->i2c_cec);
 err_unreg_edid:
 	i2c_unregister_device(state->i2c_edid);
 err_entity:
@@ -1576,9 +1952,12 @@ static int adv7511_remove(struct i2c_client *client)
 	v4l2_dbg(1, debug, sd, "%s removed @ 0x%x (%s)\n", client->name,
 		 client->addr << 1, client->adapter->name);
 
+	adv7511_set_isr(sd, false);
 	adv7511_init_setup(sd);
 	cancel_delayed_work(&state->edid_handler);
 	i2c_unregister_device(state->i2c_edid);
+	if (state->i2c_cec)
+		i2c_unregister_device(state->i2c_cec);
 	i2c_unregister_device(state->i2c_pktmem);
 	destroy_workqueue(state->work_queue);
 	v4l2_device_unregister_subdev(sd);
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index 3f1ab4986cfc..4003831de712 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -40,6 +40,7 @@
 #include <linux/regmap.h>
 
 #include <media/i2c/adv7604.h>
+#include <media/cec.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-event.h>
@@ -80,6 +81,8 @@ MODULE_LICENSE("GPL");
 
 #define ADV76XX_OP_SWAP_CB_CR				(1 << 0)
 
+#define ADV76XX_MAX_ADDRS (3)
+
 enum adv76xx_type {
 	ADV7604,
 	ADV7611,
@@ -164,6 +167,7 @@ struct adv76xx_state {
 	struct adv76xx_platform_data pdata;
 
 	struct gpio_desc *hpd_gpio[4];
+	struct gpio_desc *reset_gpio;
 
 	struct v4l2_subdev sd;
 	struct media_pad pads[ADV76XX_PAD_MAX];
@@ -184,10 +188,15 @@ struct adv76xx_state {
 	u16 spa_port_a[2];
 	struct v4l2_fract aspect_ratio;
 	u32 rgb_quantization_range;
-	struct workqueue_struct *work_queues;
 	struct delayed_work delayed_work_enable_hotplug;
 	bool restart_stdi_once;
 
+	/* CEC */
+	struct cec_adapter *cec_adap;
+	u8   cec_addr[ADV76XX_MAX_ADDRS];
+	u8   cec_valid_addrs;
+	bool cec_enabled_adap;
+
 	/* i2c clients */
 	struct i2c_client *i2c_clients[ADV76XX_PAGE_MAX];
 
@@ -381,7 +390,8 @@ static inline int io_write(struct v4l2_subdev *sd, u8 reg, u8 val)
 	return regmap_write(state->regmap[ADV76XX_PAGE_IO], reg, val);
 }
 
-static inline int io_write_clr_set(struct v4l2_subdev *sd, u8 reg, u8 mask, u8 val)
+static inline int io_write_clr_set(struct v4l2_subdev *sd, u8 reg, u8 mask,
+				   u8 val)
 {
 	return io_write(sd, reg, (io_read(sd, reg) & ~mask) | val);
 }
@@ -414,6 +424,12 @@ static inline int cec_write(struct v4l2_subdev *sd, u8 reg, u8 val)
 	return regmap_write(state->regmap[ADV76XX_PAGE_CEC], reg, val);
 }
 
+static inline int cec_write_clr_set(struct v4l2_subdev *sd, u8 reg, u8 mask,
+				   u8 val)
+{
+	return cec_write(sd, reg, (cec_read(sd, reg) & ~mask) | val);
+}
+
 static inline int infoframe_read(struct v4l2_subdev *sd, u8 reg)
 {
 	struct adv76xx_state *state = to_state(sd);
@@ -892,9 +908,9 @@ static int adv76xx_s_detect_tx_5v_ctrl(struct v4l2_subdev *sd)
 {
 	struct adv76xx_state *state = to_state(sd);
 	const struct adv76xx_chip_info *info = state->info;
+	u16 cable_det = info->read_cable_det(sd);
 
-	return v4l2_ctrl_s_ctrl(state->detect_tx_5v_ctrl,
-				info->read_cable_det(sd));
+	return v4l2_ctrl_s_ctrl(state->detect_tx_5v_ctrl, cable_det);
 }
 
 static int find_and_set_predefined_video_timings(struct v4l2_subdev *sd,
@@ -1086,6 +1102,10 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 	struct adv76xx_state *state = to_state(sd);
 	bool rgb_output = io_read(sd, 0x02) & 0x02;
 	bool hdmi_signal = hdmi_read(sd, 0x05) & 0x80;
+	u8 y = HDMI_COLORSPACE_RGB;
+
+	if (hdmi_signal && (io_read(sd, 0x60) & 1))
+		y = infoframe_read(sd, 0x01) >> 5;
 
 	v4l2_dbg(2, debug, sd, "%s: RGB quantization range: %d, RGB out: %d, HDMI: %d\n",
 			__func__, state->rgb_quantization_range,
@@ -1093,6 +1113,7 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 
 	adv76xx_set_gain(sd, true, 0x0, 0x0, 0x0);
 	adv76xx_set_offset(sd, true, 0x0, 0x0, 0x0);
+	io_write_clr_set(sd, 0x02, 0x04, rgb_output ? 0 : 4);
 
 	switch (state->rgb_quantization_range) {
 	case V4L2_DV_RGB_RANGE_AUTO:
@@ -1142,6 +1163,9 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 			break;
 		}
 
+		if (y != HDMI_COLORSPACE_RGB)
+			break;
+
 		/* RGB limited range (16-235) */
 		io_write_clr_set(sd, 0x02, 0xf0, 0x00);
 
@@ -1153,6 +1177,9 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 			break;
 		}
 
+		if (y != HDMI_COLORSPACE_RGB)
+			break;
+
 		/* RGB full range (0-255) */
 		io_write_clr_set(sd, 0x02, 0xf0, 0x10);
 
@@ -1849,6 +1876,7 @@ static void adv76xx_setup_format(struct adv76xx_state *state)
 	io_write_clr_set(sd, 0x04, 0xe0, adv76xx_op_ch_sel(state));
 	io_write_clr_set(sd, 0x05, 0x01,
 			state->format->swap_cb_cr ? ADV76XX_OP_SWAP_CB_CR : 0);
+	set_rgb_quantization_range(sd);
 }
 
 static int adv76xx_get_format(struct v4l2_subdev *sd,
@@ -1924,6 +1952,210 @@ static int adv76xx_set_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7604_CEC)
+static void adv76xx_cec_tx_raw_status(struct v4l2_subdev *sd, u8 tx_raw_status)
+{
+	struct adv76xx_state *state = to_state(sd);
+
+	if ((cec_read(sd, 0x11) & 0x01) == 0) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: tx disabled\n", __func__);
+		return;
+	}
+
+	if (tx_raw_status & 0x02) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: arbitration lost\n",
+			 __func__);
+		cec_transmit_done(state->cec_adap, CEC_TX_STATUS_ARB_LOST,
+				  1, 0, 0, 0);
+	}
+	if (tx_raw_status & 0x04) {
+		u8 status;
+		u8 nack_cnt;
+		u8 low_drive_cnt;
+
+		v4l2_dbg(1, debug, sd, "%s: tx raw: retry failed\n", __func__);
+		/*
+		 * We set this status bit since this hardware performs
+		 * retransmissions.
+		 */
+		status = CEC_TX_STATUS_MAX_RETRIES;
+		nack_cnt = cec_read(sd, 0x14) & 0xf;
+		if (nack_cnt)
+			status |= CEC_TX_STATUS_NACK;
+		low_drive_cnt = cec_read(sd, 0x14) >> 4;
+		if (low_drive_cnt)
+			status |= CEC_TX_STATUS_LOW_DRIVE;
+		cec_transmit_done(state->cec_adap, status,
+				  0, nack_cnt, low_drive_cnt, 0);
+		return;
+	}
+	if (tx_raw_status & 0x01) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: ready ok\n", __func__);
+		cec_transmit_done(state->cec_adap, CEC_TX_STATUS_OK, 0, 0, 0, 0);
+		return;
+	}
+}
+
+static void adv76xx_cec_isr(struct v4l2_subdev *sd, bool *handled)
+{
+	struct adv76xx_state *state = to_state(sd);
+	u8 cec_irq;
+
+	/* cec controller */
+	cec_irq = io_read(sd, 0x4d) & 0x0f;
+	if (!cec_irq)
+		return;
+
+	v4l2_dbg(1, debug, sd, "%s: cec: irq 0x%x\n", __func__, cec_irq);
+	adv76xx_cec_tx_raw_status(sd, cec_irq);
+	if (cec_irq & 0x08) {
+		struct cec_msg msg;
+
+		msg.len = cec_read(sd, 0x25) & 0x1f;
+		if (msg.len > 16)
+			msg.len = 16;
+
+		if (msg.len) {
+			u8 i;
+
+			for (i = 0; i < msg.len; i++)
+				msg.msg[i] = cec_read(sd, i + 0x15);
+			cec_write(sd, 0x26, 0x01); /* re-enable rx */
+			cec_received_msg(state->cec_adap, &msg);
+		}
+	}
+
+	/* note: the bit order is swapped between 0x4d and 0x4e */
+	cec_irq = ((cec_irq & 0x08) >> 3) | ((cec_irq & 0x04) >> 1) |
+		  ((cec_irq & 0x02) << 1) | ((cec_irq & 0x01) << 3);
+	io_write(sd, 0x4e, cec_irq);
+
+	if (handled)
+		*handled = true;
+}
+
+static int adv76xx_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct adv76xx_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+
+	if (!state->cec_enabled_adap && enable) {
+		cec_write_clr_set(sd, 0x2a, 0x01, 0x01); /* power up cec */
+		cec_write(sd, 0x2c, 0x01);	/* cec soft reset */
+		cec_write_clr_set(sd, 0x11, 0x01, 0); /* initially disable tx */
+		/* enabled irqs: */
+		/* tx: ready */
+		/* tx: arbitration lost */
+		/* tx: retry timeout */
+		/* rx: ready */
+		io_write_clr_set(sd, 0x50, 0x0f, 0x0f);
+		cec_write(sd, 0x26, 0x01);            /* enable rx */
+	} else if (state->cec_enabled_adap && !enable) {
+		/* disable cec interrupts */
+		io_write_clr_set(sd, 0x50, 0x0f, 0x00);
+		/* disable address mask 1-3 */
+		cec_write_clr_set(sd, 0x27, 0x70, 0x00);
+		/* power down cec section */
+		cec_write_clr_set(sd, 0x2a, 0x01, 0x00);
+		state->cec_valid_addrs = 0;
+	}
+	state->cec_enabled_adap = enable;
+	adv76xx_s_detect_tx_5v_ctrl(sd);
+	return 0;
+}
+
+static int adv76xx_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct adv76xx_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+	unsigned int i, free_idx = ADV76XX_MAX_ADDRS;
+
+	if (!state->cec_enabled_adap)
+		return addr == CEC_LOG_ADDR_INVALID ? 0 : -EIO;
+
+	if (addr == CEC_LOG_ADDR_INVALID) {
+		cec_write_clr_set(sd, 0x27, 0x70, 0);
+		state->cec_valid_addrs = 0;
+		return 0;
+	}
+
+	for (i = 0; i < ADV76XX_MAX_ADDRS; i++) {
+		bool is_valid = state->cec_valid_addrs & (1 << i);
+
+		if (free_idx == ADV76XX_MAX_ADDRS && !is_valid)
+			free_idx = i;
+		if (is_valid && state->cec_addr[i] == addr)
+			return 0;
+	}
+	if (i == ADV76XX_MAX_ADDRS) {
+		i = free_idx;
+		if (i == ADV76XX_MAX_ADDRS)
+			return -ENXIO;
+	}
+	state->cec_addr[i] = addr;
+	state->cec_valid_addrs |= 1 << i;
+
+	switch (i) {
+	case 0:
+		/* enable address mask 0 */
+		cec_write_clr_set(sd, 0x27, 0x10, 0x10);
+		/* set address for mask 0 */
+		cec_write_clr_set(sd, 0x28, 0x0f, addr);
+		break;
+	case 1:
+		/* enable address mask 1 */
+		cec_write_clr_set(sd, 0x27, 0x20, 0x20);
+		/* set address for mask 1 */
+		cec_write_clr_set(sd, 0x28, 0xf0, addr << 4);
+		break;
+	case 2:
+		/* enable address mask 2 */
+		cec_write_clr_set(sd, 0x27, 0x40, 0x40);
+		/* set address for mask 1 */
+		cec_write_clr_set(sd, 0x29, 0x0f, addr);
+		break;
+	}
+	return 0;
+}
+
+static int adv76xx_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				     u32 signal_free_time, struct cec_msg *msg)
+{
+	struct adv76xx_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+	u8 len = msg->len;
+	unsigned int i;
+
+	/*
+	 * The number of retries is the number of attempts - 1, but retry
+	 * at least once. It's not clear if a value of 0 is allowed, so
+	 * let's do at least one retry.
+	 */
+	cec_write_clr_set(sd, 0x12, 0x70, max(1, attempts - 1) << 4);
+
+	if (len > 16) {
+		v4l2_err(sd, "%s: len exceeded 16 (%d)\n", __func__, len);
+		return -EINVAL;
+	}
+
+	/* write data */
+	for (i = 0; i < len; i++)
+		cec_write(sd, i, msg->msg[i]);
+
+	/* set length (data + header) */
+	cec_write(sd, 0x10, len);
+	/* start transmit, enable tx */
+	cec_write(sd, 0x11, 0x01);
+	return 0;
+}
+
+static const struct cec_adap_ops adv76xx_cec_adap_ops = {
+	.adap_enable = adv76xx_cec_adap_enable,
+	.adap_log_addr = adv76xx_cec_adap_log_addr,
+	.adap_transmit = adv76xx_cec_adap_transmit,
+};
+#endif
+
 static int adv76xx_isr(struct v4l2_subdev *sd, u32 status, bool *handled)
 {
 	struct adv76xx_state *state = to_state(sd);
@@ -1969,6 +2201,11 @@ static int adv76xx_isr(struct v4l2_subdev *sd, u32 status, bool *handled)
 			*handled = true;
 	}
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7604_CEC)
+	/* cec */
+	adv76xx_cec_isr(sd, handled);
+#endif
+
 	/* tx 5v detect */
 	tx_5v = irq_reg_0x70 & info->cable_det_mask;
 	if (tx_5v) {
@@ -2018,39 +2255,12 @@ static int adv76xx_get_edid(struct v4l2_subdev *sd, struct v4l2_edid *edid)
 	return 0;
 }
 
-static int get_edid_spa_location(const u8 *edid)
-{
-	u8 d;
-
-	if ((edid[0x7e] != 1) ||
-	    (edid[0x80] != 0x02) ||
-	    (edid[0x81] != 0x03)) {
-		return -1;
-	}
-
-	/* search Vendor Specific Data Block (tag 3) */
-	d = edid[0x82] & 0x7f;
-	if (d > 4) {
-		int i = 0x84;
-		int end = 0x80 + d;
-
-		do {
-			u8 tag = edid[i] >> 5;
-			u8 len = edid[i] & 0x1f;
-
-			if ((tag == 3) && (len >= 5))
-				return i + 4;
-			i += len + 1;
-		} while (i < end);
-	}
-	return -1;
-}
-
 static int adv76xx_set_edid(struct v4l2_subdev *sd, struct v4l2_edid *edid)
 {
 	struct adv76xx_state *state = to_state(sd);
 	const struct adv76xx_chip_info *info = state->info;
-	int spa_loc;
+	unsigned int spa_loc;
+	u16 pa;
 	int err;
 	int i;
 
@@ -2081,6 +2291,10 @@ static int adv76xx_set_edid(struct v4l2_subdev *sd, struct v4l2_edid *edid)
 		edid->blocks = 2;
 		return -E2BIG;
 	}
+	pa = cec_get_edid_phys_addr(edid->edid, edid->blocks * 128, &spa_loc);
+	err = cec_phys_addr_validate(pa, &pa, NULL);
+	if (err)
+		return err;
 
 	v4l2_dbg(2, debug, sd, "%s: write EDID pad %d, edid.present = 0x%x\n",
 			__func__, edid->pad, state->edid.present);
@@ -2090,9 +2304,12 @@ static int adv76xx_set_edid(struct v4l2_subdev *sd, struct v4l2_edid *edid)
 	adv76xx_set_hpd(state, 0);
 	rep_write_clr_set(sd, info->edid_enable_reg, 0x0f, 0x00);
 
-	spa_loc = get_edid_spa_location(edid->edid);
-	if (spa_loc < 0)
-		spa_loc = 0xc0; /* Default value [REF_02, p. 116] */
+	/*
+	 * Return an error if no location of the source physical address
+	 * was found.
+	 */
+	if (spa_loc == 0)
+		return -EINVAL;
 
 	switch (edid->pad) {
 	case ADV76XX_PAD_HDMI_PORT_A:
@@ -2152,10 +2369,10 @@ static int adv76xx_set_edid(struct v4l2_subdev *sd, struct v4l2_edid *edid)
 		v4l2_err(sd, "error enabling edid (0x%x)\n", state->edid.present);
 		return -EIO;
 	}
+	cec_s_phys_addr(state->cec_adap, pa, false);
 
 	/* enable hotplug after 100 ms */
-	queue_delayed_work(state->work_queues,
-			&state->delayed_work_enable_hotplug, HZ / 10);
+	schedule_delayed_work(&state->delayed_work_enable_hotplug, HZ / 10);
 	return 0;
 }
 
@@ -2276,8 +2493,19 @@ static int adv76xx_log_status(struct v4l2_subdev *sd)
 			((edid_enabled & 0x02) ? "Yes" : "No"),
 			((edid_enabled & 0x04) ? "Yes" : "No"),
 			((edid_enabled & 0x08) ? "Yes" : "No"));
-	v4l2_info(sd, "CEC: %s\n", !!(cec_read(sd, 0x2a) & 0x01) ?
+	v4l2_info(sd, "CEC: %s\n", state->cec_enabled_adap ?
 			"enabled" : "disabled");
+	if (state->cec_enabled_adap) {
+		int i;
+
+		for (i = 0; i < ADV76XX_MAX_ADDRS; i++) {
+			bool is_valid = state->cec_valid_addrs & (1 << i);
+
+			if (is_valid)
+				v4l2_info(sd, "CEC Logical Address: 0x%x\n",
+					  state->cec_addr[i]);
+		}
+	}
 
 	v4l2_info(sd, "-----Signal status-----\n");
 	cable_det = info->read_cable_det(sd);
@@ -2323,11 +2551,10 @@ static int adv76xx_log_status(struct v4l2_subdev *sd)
 			rgb_quantization_range_txt[state->rgb_quantization_range]);
 	v4l2_info(sd, "Input color space: %s\n",
 			input_color_space_txt[reg_io_0x02 >> 4]);
-	v4l2_info(sd, "Output color space: %s %s, saturator %s, alt-gamma %s\n",
+	v4l2_info(sd, "Output color space: %s %s, alt-gamma %s\n",
 			(reg_io_0x02 & 0x02) ? "RGB" : "YCbCr",
-			(reg_io_0x02 & 0x04) ? "(16-235)" : "(0-255)",
 			(((reg_io_0x02 >> 2) & 0x01) ^ (reg_io_0x02 & 0x01)) ?
-				"enabled" : "disabled",
+				"(16-235)" : "(0-255)",
 			(reg_io_0x02 & 0x08) ? "enabled" : "disabled");
 	v4l2_info(sd, "Color space conversion: %s\n",
 			csc_coeff_sel_rb[cp_read(sd, info->cp_csc) >> 4]);
@@ -2387,6 +2614,24 @@ static int adv76xx_subscribe_event(struct v4l2_subdev *sd,
 	}
 }
 
+static int adv76xx_registered(struct v4l2_subdev *sd)
+{
+	struct adv76xx_state *state = to_state(sd);
+	int err;
+
+	err = cec_register_adapter(state->cec_adap);
+	if (err)
+		cec_delete_adapter(state->cec_adap);
+	return err;
+}
+
+static void adv76xx_unregistered(struct v4l2_subdev *sd)
+{
+	struct adv76xx_state *state = to_state(sd);
+
+	cec_unregister_adapter(state->cec_adap);
+}
+
 /* ----------------------------------------------------------------------- */
 
 static const struct v4l2_ctrl_ops adv76xx_ctrl_ops = {
@@ -2430,6 +2675,11 @@ static const struct v4l2_subdev_ops adv76xx_ops = {
 	.pad = &adv76xx_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops adv76xx_int_ops = {
+	.registered = adv76xx_registered,
+	.unregistered = adv76xx_unregistered,
+};
+
 /* -------------------------- custom ctrls ---------------------------------- */
 
 static const struct v4l2_ctrl_config adv7604_ctrl_analog_sampling_phase = {
@@ -2492,10 +2742,7 @@ static int adv76xx_core_init(struct v4l2_subdev *sd)
 	cp_write(sd, 0xcf, 0x01);   /* Power down macrovision */
 
 	/* video format */
-	io_write_clr_set(sd, 0x02, 0x0f,
-			pdata->alt_gamma << 3 |
-			pdata->op_656_range << 2 |
-			pdata->alt_data_sat << 0);
+	io_write_clr_set(sd, 0x02, 0x0f, pdata->alt_gamma << 3);
 	io_write_clr_set(sd, 0x05, 0x0e, pdata->blank_data << 3 |
 			pdata->insert_av_codes << 2 |
 			pdata->replicate_av_codes << 1);
@@ -2845,10 +3092,8 @@ static int adv76xx_parse_dt(struct adv76xx_state *state)
 	if (flags & V4L2_MBUS_PCLK_SAMPLE_RISING)
 		state->pdata.inv_llc_pol = 1;
 
-	if (bus_cfg.bus_type == V4L2_MBUS_BT656) {
+	if (bus_cfg.bus_type == V4L2_MBUS_BT656)
 		state->pdata.insert_av_codes = 1;
-		state->pdata.op_656_range = 1;
-	}
 
 	/* Disable the interrupt for now as no DT-based board uses it. */
 	state->pdata.int1_config = ADV76XX_INT1_CONFIG_DISABLED;
@@ -2871,7 +3116,6 @@ static int adv76xx_parse_dt(struct adv76xx_state *state)
 	state->pdata.disable_pwrdnb = 0;
 	state->pdata.disable_cable_det_rst = 0;
 	state->pdata.blank_data = 1;
-	state->pdata.alt_data_sat = 1;
 	state->pdata.op_format_mode_sel = ADV7604_OP_FORMAT_MODE0;
 	state->pdata.bus_order = ADV7604_BUS_ORDER_RGB;
 
@@ -3020,6 +3264,19 @@ static int configure_regmaps(struct adv76xx_state *state)
 	return 0;
 }
 
+static void adv76xx_reset(struct adv76xx_state *state)
+{
+	if (state->reset_gpio) {
+		/* ADV76XX can be reset by a low reset pulse of minimum 5 ms. */
+		gpiod_set_value_cansleep(state->reset_gpio, 0);
+		usleep_range(5000, 10000);
+		gpiod_set_value_cansleep(state->reset_gpio, 1);
+		/* It is recommended to wait 5 ms after the low pulse before */
+		/* an I2C write is performed to the ADV76XX. */
+		usleep_range(5000, 10000);
+	}
+}
+
 static int adv76xx_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -3083,6 +3340,12 @@ static int adv76xx_probe(struct i2c_client *client,
 		if (state->hpd_gpio[i])
 			v4l_info(client, "Handling HPD %u GPIO\n", i);
 	}
+	state->reset_gpio = devm_gpiod_get_optional(&client->dev, "reset",
+								GPIOD_OUT_HIGH);
+	if (IS_ERR(state->reset_gpio))
+		return PTR_ERR(state->reset_gpio);
+
+	adv76xx_reset(state);
 
 	state->timings = cea640x480;
 	state->format = adv76xx_format_info(state, MEDIA_BUS_FMT_YUYV8_2X8);
@@ -3093,6 +3356,7 @@ static int adv76xx_probe(struct i2c_client *client,
 		id->name, i2c_adapter_id(client->adapter),
 		client->addr);
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
+	sd->internal_ops = &adv76xx_int_ops;
 
 	/* Configure IO Regmap region */
 	err = configure_regmap(state, ADV76XX_PAGE_IO);
@@ -3206,14 +3470,6 @@ static int adv76xx_probe(struct i2c_client *client,
 		}
 	}
 
-	/* work queues */
-	state->work_queues = create_singlethread_workqueue(client->name);
-	if (!state->work_queues) {
-		v4l2_err(sd, "Could not create work queue\n");
-		err = -ENOMEM;
-		goto err_i2c;
-	}
-
 	INIT_DELAYED_WORK(&state->delayed_work_enable_hotplug,
 			adv76xx_delayed_work_enable_hotplug);
 
@@ -3236,6 +3492,18 @@ static int adv76xx_probe(struct i2c_client *client,
 	err = adv76xx_core_init(sd);
 	if (err)
 		goto err_entity;
+
+#if IS_ENABLED(CONFIG_VIDEO_ADV7604_CEC)
+	state->cec_adap = cec_allocate_adapter(&adv76xx_cec_adap_ops,
+		state, dev_name(&client->dev),
+		CEC_CAP_TRANSMIT | CEC_CAP_LOG_ADDRS |
+		CEC_CAP_PASSTHROUGH | CEC_CAP_RC, ADV76XX_MAX_ADDRS,
+		&client->dev);
+	err = PTR_ERR_OR_ZERO(state->cec_adap);
+	if (err)
+		goto err_entity;
+#endif
+
 	v4l2_info(sd, "%s found @ 0x%x (%s)\n", client->name,
 			client->addr << 1, client->adapter->name);
 
@@ -3249,7 +3517,6 @@ err_entity:
 	media_entity_cleanup(&sd->entity);
 err_work_queues:
 	cancel_delayed_work(&state->delayed_work_enable_hotplug);
-	destroy_workqueue(state->work_queues);
 err_i2c:
 	adv76xx_unregister_clients(state);
 err_hdl:
@@ -3264,8 +3531,14 @@ static int adv76xx_remove(struct i2c_client *client)
 	struct v4l2_subdev *sd = i2c_get_clientdata(client);
 	struct adv76xx_state *state = to_state(sd);
 
+	/* disable interrupts */
+	io_write(sd, 0x40, 0);
+	io_write(sd, 0x41, 0);
+	io_write(sd, 0x46, 0);
+	io_write(sd, 0x6e, 0);
+	io_write(sd, 0x73, 0);
+
 	cancel_delayed_work(&state->delayed_work_enable_hotplug);
-	destroy_workqueue(state->work_queues);
 	v4l2_async_unregister_subdev(sd);
 	media_entity_cleanup(&sd->entity);
 	adv76xx_unregister_clients(to_state(sd));
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index ecaacb0a6fa1..8c2a52e280af 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -39,6 +39,7 @@
 #include <linux/workqueue.h>
 #include <linux/v4l2-dv-timings.h>
 #include <linux/hdmi.h>
+#include <media/cec.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-ctrls.h>
@@ -79,6 +80,8 @@ MODULE_LICENSE("GPL");
 
 #define ADV7842_OP_SWAP_CB_CR				(1 << 0)
 
+#define ADV7842_MAX_ADDRS (3)
+
 /*
 **********************************************************************
 *
@@ -118,7 +121,6 @@ struct adv7842_state {
 	struct v4l2_fract aspect_ratio;
 	u32 rgb_quantization_range;
 	bool is_cea_format;
-	struct workqueue_struct *work_queues;
 	struct delayed_work delayed_work_enable_hotplug;
 	bool restart_stdi_once;
 	bool hdmi_port_a;
@@ -142,6 +144,11 @@ struct adv7842_state {
 	struct v4l2_ctrl *free_run_color_ctrl_manual;
 	struct v4l2_ctrl *free_run_color_ctrl;
 	struct v4l2_ctrl *rgb_quantization_range_ctrl;
+
+	struct cec_adapter *cec_adap;
+	u8   cec_addr[ADV7842_MAX_ADDRS];
+	u8   cec_valid_addrs;
+	bool cec_enabled_adap;
 };
 
 /* Unsupported timings. This device cannot support 720p30. */
@@ -418,9 +425,9 @@ static inline int cec_write(struct v4l2_subdev *sd, u8 reg, u8 val)
 	return adv_smbus_write_byte_data(state->i2c_cec, reg, val);
 }
 
-static inline int cec_write_and_or(struct v4l2_subdev *sd, u8 reg, u8 mask, u8 val)
+static inline int cec_write_clr_set(struct v4l2_subdev *sd, u8 reg, u8 mask, u8 val)
 {
-	return cec_write(sd, reg, (cec_read(sd, reg) & mask) | val);
+	return cec_write(sd, reg, (cec_read(sd, reg) & ~mask) | val);
 }
 
 static inline int infoframe_read(struct v4l2_subdev *sd, u8 reg)
@@ -696,6 +703,18 @@ adv7842_get_dv_timings_cap(struct v4l2_subdev *sd)
 
 /* ----------------------------------------------------------------------- */
 
+static u16 adv7842_read_cable_det(struct v4l2_subdev *sd)
+{
+	u8 reg = io_read(sd, 0x6f);
+	u16 val = 0;
+
+	if (reg & 0x02)
+		val |= 1; /* port A */
+	if (reg & 0x01)
+		val |= 2; /* port B */
+	return val;
+}
+
 static void adv7842_delayed_work_enable_hotplug(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
@@ -756,56 +775,23 @@ static int edid_write_vga_segment(struct v4l2_subdev *sd)
 	}
 
 	/* enable hotplug after 200 ms */
-	queue_delayed_work(state->work_queues,
-			&state->delayed_work_enable_hotplug, HZ / 5);
+	schedule_delayed_work(&state->delayed_work_enable_hotplug, HZ / 5);
 
 	return 0;
 }
 
-static int edid_spa_location(const u8 *edid)
-{
-	u8 d;
-
-	/*
-	 * TODO, improve and update for other CEA extensions
-	 * currently only for 1 segment (256 bytes),
-	 * i.e. 1 extension block and CEA revision 3.
-	 */
-	if ((edid[0x7e] != 1) ||
-	    (edid[0x80] != 0x02) ||
-	    (edid[0x81] != 0x03)) {
-		return -EINVAL;
-	}
-	/*
-	 * search Vendor Specific Data Block (tag 3)
-	 */
-	d = edid[0x82] & 0x7f;
-	if (d > 4) {
-		int i = 0x84;
-		int end = 0x80 + d;
-		do {
-			u8 tag = edid[i]>>5;
-			u8 len = edid[i] & 0x1f;
-
-			if ((tag == 3) && (len >= 5))
-				return i + 4;
-			i += len + 1;
-		} while (i < end);
-	}
-	return -EINVAL;
-}
-
 static int edid_write_hdmi_segment(struct v4l2_subdev *sd, u8 port)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct adv7842_state *state = to_state(sd);
-	const u8 *val = state->hdmi_edid.edid;
-	int spa_loc = edid_spa_location(val);
+	const u8 *edid = state->hdmi_edid.edid;
+	int spa_loc;
+	u16 pa;
 	int err = 0;
 	int i;
 
-	v4l2_dbg(2, debug, sd, "%s: write EDID on port %c (spa at 0x%x)\n",
-			__func__, (port == ADV7842_EDID_PORT_A) ? 'A' : 'B', spa_loc);
+	v4l2_dbg(2, debug, sd, "%s: write EDID on port %c\n",
+			__func__, (port == ADV7842_EDID_PORT_A) ? 'A' : 'B');
 
 	/* HPA disable on port A and B */
 	io_write_and_or(sd, 0x20, 0xcf, 0x00);
@@ -816,24 +802,33 @@ static int edid_write_hdmi_segment(struct v4l2_subdev *sd, u8 port)
 	if (!state->hdmi_edid.present)
 		return 0;
 
+	pa = cec_get_edid_phys_addr(edid, 256, &spa_loc);
+	err = cec_phys_addr_validate(pa, &pa, NULL);
+	if (err)
+		return err;
+
+	/*
+	 * Return an error if no location of the source physical address
+	 * was found.
+	 */
+	if (spa_loc == 0)
+		return -EINVAL;
+
 	/* edid segment pointer '0' for HDMI ports */
 	rep_write_and_or(sd, 0x77, 0xef, 0x00);
 
 	for (i = 0; !err && i < 256; i += I2C_SMBUS_BLOCK_MAX)
 		err = adv_smbus_write_i2c_block_data(state->i2c_edid, i,
-						     I2C_SMBUS_BLOCK_MAX, val + i);
+						     I2C_SMBUS_BLOCK_MAX, edid + i);
 	if (err)
 		return err;
 
-	if (spa_loc < 0)
-		spa_loc = 0xc0; /* Default value [REF_02, p. 199] */
-
 	if (port == ADV7842_EDID_PORT_A) {
-		rep_write(sd, 0x72, val[spa_loc]);
-		rep_write(sd, 0x73, val[spa_loc + 1]);
+		rep_write(sd, 0x72, edid[spa_loc]);
+		rep_write(sd, 0x73, edid[spa_loc + 1]);
 	} else {
-		rep_write(sd, 0x74, val[spa_loc]);
-		rep_write(sd, 0x75, val[spa_loc + 1]);
+		rep_write(sd, 0x74, edid[spa_loc]);
+		rep_write(sd, 0x75, edid[spa_loc + 1]);
 	}
 	rep_write(sd, 0x76, spa_loc & 0xff);
 	rep_write_and_or(sd, 0x77, 0xbf, (spa_loc >> 2) & 0x40);
@@ -853,10 +848,10 @@ static int edid_write_hdmi_segment(struct v4l2_subdev *sd, u8 port)
 				(port == ADV7842_EDID_PORT_A) ? 'A' : 'B');
 		return -EIO;
 	}
+	cec_s_phys_addr(state->cec_adap, pa, false);
 
 	/* enable hotplug after 200 ms */
-	queue_delayed_work(state->work_queues,
-			&state->delayed_work_enable_hotplug, HZ / 5);
+	schedule_delayed_work(&state->delayed_work_enable_hotplug, HZ / 5);
 
 	return 0;
 }
@@ -983,20 +978,11 @@ static int adv7842_s_register(struct v4l2_subdev *sd,
 static int adv7842_s_detect_tx_5v_ctrl(struct v4l2_subdev *sd)
 {
 	struct adv7842_state *state = to_state(sd);
-	int prev = v4l2_ctrl_g_ctrl(state->detect_tx_5v_ctrl);
-	u8 reg_io_6f = io_read(sd, 0x6f);
-	int val = 0;
+	u16 cable_det = adv7842_read_cable_det(sd);
 
-	if (reg_io_6f & 0x02)
-		val |= 1; /* port A */
-	if (reg_io_6f & 0x01)
-		val |= 2; /* port B */
-
-	v4l2_dbg(1, debug, sd, "%s: 0x%x -> 0x%x\n", __func__, prev, val);
+	v4l2_dbg(1, debug, sd, "%s: 0x%x\n", __func__, cable_det);
 
-	if (val != prev)
-		return v4l2_ctrl_s_ctrl(state->detect_tx_5v_ctrl, val);
-	return 0;
+	return v4l2_ctrl_s_ctrl(state->detect_tx_5v_ctrl, cable_det);
 }
 
 static int find_and_set_predefined_video_timings(struct v4l2_subdev *sd,
@@ -1198,6 +1184,10 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 	struct adv7842_state *state = to_state(sd);
 	bool rgb_output = io_read(sd, 0x02) & 0x02;
 	bool hdmi_signal = hdmi_read(sd, 0x05) & 0x80;
+	u8 y = HDMI_COLORSPACE_RGB;
+
+	if (hdmi_signal && (io_read(sd, 0x60) & 1))
+		y = infoframe_read(sd, 0x01) >> 5;
 
 	v4l2_dbg(2, debug, sd, "%s: RGB quantization range: %d, RGB out: %d, HDMI: %d\n",
 			__func__, state->rgb_quantization_range,
@@ -1205,6 +1195,7 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 
 	adv7842_set_gain(sd, true, 0x0, 0x0, 0x0);
 	adv7842_set_offset(sd, true, 0x0, 0x0, 0x0);
+	io_write_clr_set(sd, 0x02, 0x04, rgb_output ? 0 : 4);
 
 	switch (state->rgb_quantization_range) {
 	case V4L2_DV_RGB_RANGE_AUTO:
@@ -1254,6 +1245,9 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 			break;
 		}
 
+		if (y != HDMI_COLORSPACE_RGB)
+			break;
+
 		/* RGB limited range (16-235) */
 		io_write_and_or(sd, 0x02, 0x0f, 0x00);
 
@@ -1265,6 +1259,9 @@ static void set_rgb_quantization_range(struct v4l2_subdev *sd)
 			break;
 		}
 
+		if (y != HDMI_COLORSPACE_RGB)
+			break;
+
 		/* RGB full range (0-255) */
 		io_write_and_or(sd, 0x02, 0x0f, 0x10);
 
@@ -2072,6 +2069,7 @@ static void adv7842_setup_format(struct adv7842_state *state)
 	io_write_clr_set(sd, 0x04, 0xe0, adv7842_op_ch_sel(state));
 	io_write_clr_set(sd, 0x05, 0x01,
 			state->format->swap_cb_cr ? ADV7842_OP_SWAP_CB_CR : 0);
+	set_rgb_quantization_range(sd);
 }
 
 static int adv7842_get_format(struct v4l2_subdev *sd,
@@ -2170,6 +2168,207 @@ static void adv7842_irq_enable(struct v4l2_subdev *sd, bool enable)
 	}
 }
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7842_CEC)
+static void adv7842_cec_tx_raw_status(struct v4l2_subdev *sd, u8 tx_raw_status)
+{
+	struct adv7842_state *state = to_state(sd);
+
+	if ((cec_read(sd, 0x11) & 0x01) == 0) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: tx disabled\n", __func__);
+		return;
+	}
+
+	if (tx_raw_status & 0x02) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: arbitration lost\n",
+			 __func__);
+		cec_transmit_done(state->cec_adap, CEC_TX_STATUS_ARB_LOST,
+				  1, 0, 0, 0);
+		return;
+	}
+	if (tx_raw_status & 0x04) {
+		u8 status;
+		u8 nack_cnt;
+		u8 low_drive_cnt;
+
+		v4l2_dbg(1, debug, sd, "%s: tx raw: retry failed\n", __func__);
+		/*
+		 * We set this status bit since this hardware performs
+		 * retransmissions.
+		 */
+		status = CEC_TX_STATUS_MAX_RETRIES;
+		nack_cnt = cec_read(sd, 0x14) & 0xf;
+		if (nack_cnt)
+			status |= CEC_TX_STATUS_NACK;
+		low_drive_cnt = cec_read(sd, 0x14) >> 4;
+		if (low_drive_cnt)
+			status |= CEC_TX_STATUS_LOW_DRIVE;
+		cec_transmit_done(state->cec_adap, status,
+				  0, nack_cnt, low_drive_cnt, 0);
+		return;
+	}
+	if (tx_raw_status & 0x01) {
+		v4l2_dbg(1, debug, sd, "%s: tx raw: ready ok\n", __func__);
+		cec_transmit_done(state->cec_adap, CEC_TX_STATUS_OK, 0, 0, 0, 0);
+		return;
+	}
+}
+
+static void adv7842_cec_isr(struct v4l2_subdev *sd, bool *handled)
+{
+	u8 cec_irq;
+
+	/* cec controller */
+	cec_irq = io_read(sd, 0x93) & 0x0f;
+	if (!cec_irq)
+		return;
+
+	v4l2_dbg(1, debug, sd, "%s: cec: irq 0x%x\n", __func__, cec_irq);
+	adv7842_cec_tx_raw_status(sd, cec_irq);
+	if (cec_irq & 0x08) {
+		struct adv7842_state *state = to_state(sd);
+		struct cec_msg msg;
+
+		msg.len = cec_read(sd, 0x25) & 0x1f;
+		if (msg.len > 16)
+			msg.len = 16;
+
+		if (msg.len) {
+			u8 i;
+
+			for (i = 0; i < msg.len; i++)
+				msg.msg[i] = cec_read(sd, i + 0x15);
+			cec_write(sd, 0x26, 0x01); /* re-enable rx */
+			cec_received_msg(state->cec_adap, &msg);
+		}
+	}
+
+	io_write(sd, 0x94, cec_irq);
+
+	if (handled)
+		*handled = true;
+}
+
+static int adv7842_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct adv7842_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+
+	if (!state->cec_enabled_adap && enable) {
+		cec_write_clr_set(sd, 0x2a, 0x01, 0x01); /* power up cec */
+		cec_write(sd, 0x2c, 0x01);	/* cec soft reset */
+		cec_write_clr_set(sd, 0x11, 0x01, 0); /* initially disable tx */
+		/* enabled irqs: */
+		/* tx: ready */
+		/* tx: arbitration lost */
+		/* tx: retry timeout */
+		/* rx: ready */
+		io_write_clr_set(sd, 0x96, 0x0f, 0x0f);
+		cec_write(sd, 0x26, 0x01);            /* enable rx */
+	} else if (state->cec_enabled_adap && !enable) {
+		/* disable cec interrupts */
+		io_write_clr_set(sd, 0x96, 0x0f, 0x00);
+		/* disable address mask 1-3 */
+		cec_write_clr_set(sd, 0x27, 0x70, 0x00);
+		/* power down cec section */
+		cec_write_clr_set(sd, 0x2a, 0x01, 0x00);
+		state->cec_valid_addrs = 0;
+	}
+	state->cec_enabled_adap = enable;
+	return 0;
+}
+
+static int adv7842_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct adv7842_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+	unsigned int i, free_idx = ADV7842_MAX_ADDRS;
+
+	if (!state->cec_enabled_adap)
+		return addr == CEC_LOG_ADDR_INVALID ? 0 : -EIO;
+
+	if (addr == CEC_LOG_ADDR_INVALID) {
+		cec_write_clr_set(sd, 0x27, 0x70, 0);
+		state->cec_valid_addrs = 0;
+		return 0;
+	}
+
+	for (i = 0; i < ADV7842_MAX_ADDRS; i++) {
+		bool is_valid = state->cec_valid_addrs & (1 << i);
+
+		if (free_idx == ADV7842_MAX_ADDRS && !is_valid)
+			free_idx = i;
+		if (is_valid && state->cec_addr[i] == addr)
+			return 0;
+	}
+	if (i == ADV7842_MAX_ADDRS) {
+		i = free_idx;
+		if (i == ADV7842_MAX_ADDRS)
+			return -ENXIO;
+	}
+	state->cec_addr[i] = addr;
+	state->cec_valid_addrs |= 1 << i;
+
+	switch (i) {
+	case 0:
+		/* enable address mask 0 */
+		cec_write_clr_set(sd, 0x27, 0x10, 0x10);
+		/* set address for mask 0 */
+		cec_write_clr_set(sd, 0x28, 0x0f, addr);
+		break;
+	case 1:
+		/* enable address mask 1 */
+		cec_write_clr_set(sd, 0x27, 0x20, 0x20);
+		/* set address for mask 1 */
+		cec_write_clr_set(sd, 0x28, 0xf0, addr << 4);
+		break;
+	case 2:
+		/* enable address mask 2 */
+		cec_write_clr_set(sd, 0x27, 0x40, 0x40);
+		/* set address for mask 1 */
+		cec_write_clr_set(sd, 0x29, 0x0f, addr);
+		break;
+	}
+	return 0;
+}
+
+static int adv7842_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				     u32 signal_free_time, struct cec_msg *msg)
+{
+	struct adv7842_state *state = adap->priv;
+	struct v4l2_subdev *sd = &state->sd;
+	u8 len = msg->len;
+	unsigned int i;
+
+	/*
+	 * The number of retries is the number of attempts - 1, but retry
+	 * at least once. It's not clear if a value of 0 is allowed, so
+	 * let's do at least one retry.
+	 */
+	cec_write_clr_set(sd, 0x12, 0x70, max(1, attempts - 1) << 4);
+
+	if (len > 16) {
+		v4l2_err(sd, "%s: len exceeded 16 (%d)\n", __func__, len);
+		return -EINVAL;
+	}
+
+	/* write data */
+	for (i = 0; i < len; i++)
+		cec_write(sd, i, msg->msg[i]);
+
+	/* set length (data + header) */
+	cec_write(sd, 0x10, len);
+	/* start transmit, enable tx */
+	cec_write(sd, 0x11, 0x01);
+	return 0;
+}
+
+static const struct cec_adap_ops adv7842_cec_adap_ops = {
+	.adap_enable = adv7842_cec_adap_enable,
+	.adap_log_addr = adv7842_cec_adap_log_addr,
+	.adap_transmit = adv7842_cec_adap_transmit,
+};
+#endif
+
 static int adv7842_isr(struct v4l2_subdev *sd, u32 status, bool *handled)
 {
 	struct adv7842_state *state = to_state(sd);
@@ -2241,6 +2440,11 @@ static int adv7842_isr(struct v4l2_subdev *sd, u32 status, bool *handled)
 			*handled = true;
 	}
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7842_CEC)
+	/* cec */
+	adv7842_cec_isr(sd, handled);
+#endif
+
 	/* tx 5v detect */
 	if (irq_status[2] & 0x3) {
 		v4l2_dbg(1, debug, sd, "%s: irq tx_5v\n", __func__);
@@ -2321,10 +2525,12 @@ static int adv7842_set_edid(struct v4l2_subdev *sd, struct v4l2_edid *e)
 	case ADV7842_EDID_PORT_A:
 	case ADV7842_EDID_PORT_B:
 		memset(&state->hdmi_edid.edid, 0, 256);
-		if (e->blocks)
+		if (e->blocks) {
 			state->hdmi_edid.present |= 0x04 << e->pad;
-		else
+		} else {
 			state->hdmi_edid.present &= ~(0x04 << e->pad);
+			adv7842_s_detect_tx_5v_ctrl(sd);
+		}
 		memcpy(&state->hdmi_edid.edid, e->edid, 128 * e->blocks);
 		err = edid_write_hdmi_segment(sd, e->pad);
 		break;
@@ -2397,6 +2603,8 @@ static void adv7842_log_infoframes(struct v4l2_subdev *sd)
 		log_infoframe(sd, &cri[i]);
 }
 
+#if 0
+/* Let's keep it here for now, as it could be useful for debug */
 static const char * const prim_mode_txt[] = {
 	"SDP",
 	"Component",
@@ -2415,6 +2623,7 @@ static const char * const prim_mode_txt[] = {
 	"Reserved",
 	"Reserved",
 };
+#endif
 
 static int adv7842_sdp_log_status(struct v4l2_subdev *sd)
 {
@@ -2509,8 +2718,19 @@ static int adv7842_cp_log_status(struct v4l2_subdev *sd)
 	v4l2_info(sd, "HPD A %s, B %s\n",
 		  reg_io_0x21 & 0x02 ? "enabled" : "disabled",
 		  reg_io_0x21 & 0x01 ? "enabled" : "disabled");
-	v4l2_info(sd, "CEC %s\n", !!(cec_read(sd, 0x2a) & 0x01) ?
+	v4l2_info(sd, "CEC: %s\n", state->cec_enabled_adap ?
 			"enabled" : "disabled");
+	if (state->cec_enabled_adap) {
+		int i;
+
+		for (i = 0; i < ADV7842_MAX_ADDRS; i++) {
+			bool is_valid = state->cec_valid_addrs & (1 << i);
+
+			if (is_valid)
+				v4l2_info(sd, "CEC Logical Address: 0x%x\n",
+					  state->cec_addr[i]);
+		}
+	}
 
 	v4l2_info(sd, "-----Signal status-----\n");
 	if (state->hdmi_port_a) {
@@ -2569,11 +2789,11 @@ static int adv7842_cp_log_status(struct v4l2_subdev *sd)
 		  rgb_quantization_range_txt[state->rgb_quantization_range]);
 	v4l2_info(sd, "Input color space: %s\n",
 		  input_color_space_txt[reg_io_0x02 >> 4]);
-	v4l2_info(sd, "Output color space: %s %s, saturator %s\n",
+	v4l2_info(sd, "Output color space: %s %s, alt-gamma %s\n",
 		  (reg_io_0x02 & 0x02) ? "RGB" : "YCbCr",
-		  (reg_io_0x02 & 0x04) ? "(16-235)" : "(0-255)",
-		  ((reg_io_0x02 & 0x04) ^ (reg_io_0x02 & 0x01)) ?
-					"enabled" : "disabled");
+		  (((reg_io_0x02 >> 2) & 0x01) ^ (reg_io_0x02 & 0x01)) ?
+			"(16-235)" : "(0-255)",
+		  (reg_io_0x02 & 0x08) ? "enabled" : "disabled");
 	v4l2_info(sd, "Color space conversion: %s\n",
 		  csc_coeff_sel_rb[cp_read(sd, 0xf4) >> 4]);
 
@@ -2777,11 +2997,7 @@ static int adv7842_core_init(struct v4l2_subdev *sd)
 	io_write(sd, 0x15, 0x80);   /* Power up pads */
 
 	/* video format */
-	io_write(sd, 0x02,
-		 0xf0 |
-		 pdata->alt_gamma << 3 |
-		 pdata->op_656_range << 2 |
-		 pdata->alt_data_sat << 0);
+	io_write(sd, 0x02, 0xf0 | pdata->alt_gamma << 3);
 	io_write_and_or(sd, 0x05, 0xf0, pdata->blank_data << 3 |
 			pdata->insert_av_codes << 2 |
 			pdata->replicate_av_codes << 1);
@@ -3031,6 +3247,24 @@ static int adv7842_subscribe_event(struct v4l2_subdev *sd,
 	}
 }
 
+static int adv7842_registered(struct v4l2_subdev *sd)
+{
+	struct adv7842_state *state = to_state(sd);
+	int err;
+
+	err = cec_register_adapter(state->cec_adap);
+	if (err)
+		cec_delete_adapter(state->cec_adap);
+	return err;
+}
+
+static void adv7842_unregistered(struct v4l2_subdev *sd)
+{
+	struct adv7842_state *state = to_state(sd);
+
+	cec_unregister_adapter(state->cec_adap);
+}
+
 /* ----------------------------------------------------------------------- */
 
 static const struct v4l2_ctrl_ops adv7842_ctrl_ops = {
@@ -3077,6 +3311,11 @@ static const struct v4l2_subdev_ops adv7842_ops = {
 	.pad = &adv7842_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops adv7842_int_ops = {
+	.registered = adv7842_registered,
+	.unregistered = adv7842_unregistered,
+};
+
 /* -------------------------- custom ctrls ---------------------------------- */
 
 static const struct v4l2_ctrl_config adv7842_ctrl_analog_sampling_phase = {
@@ -3241,6 +3480,7 @@ static int adv7842_probe(struct i2c_client *client,
 	sd = &state->sd;
 	v4l2_i2c_subdev_init(sd, client, &adv7842_ops);
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
+	sd->internal_ops = &adv7842_int_ops;
 	state->mode = pdata->mode;
 
 	state->hdmi_port_a = pdata->input == ADV7842_SELECT_HDMI_PORT_A;
@@ -3311,13 +3551,6 @@ static int adv7842_probe(struct i2c_client *client,
 		goto err_i2c;
 	}
 
-	/* work queues */
-	state->work_queues = create_singlethread_workqueue(client->name);
-	if (!state->work_queues) {
-		v4l2_err(sd, "Could not create work queue\n");
-		err = -ENOMEM;
-		goto err_i2c;
-	}
 
 	INIT_DELAYED_WORK(&state->delayed_work_enable_hotplug,
 			adv7842_delayed_work_enable_hotplug);
@@ -3331,6 +3564,17 @@ static int adv7842_probe(struct i2c_client *client,
 	if (err)
 		goto err_entity;
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7842_CEC)
+	state->cec_adap = cec_allocate_adapter(&adv7842_cec_adap_ops,
+		state, dev_name(&client->dev),
+		CEC_CAP_TRANSMIT | CEC_CAP_LOG_ADDRS |
+		CEC_CAP_PASSTHROUGH | CEC_CAP_RC, ADV7842_MAX_ADDRS,
+		&client->dev);
+	err = PTR_ERR_OR_ZERO(state->cec_adap);
+	if (err)
+		goto err_entity;
+#endif
+
 	v4l2_info(sd, "%s found @ 0x%x (%s)\n", client->name,
 		  client->addr << 1, client->adapter->name);
 	return 0;
@@ -3339,7 +3583,6 @@ err_entity:
 	media_entity_cleanup(&sd->entity);
 err_work_queues:
 	cancel_delayed_work(&state->delayed_work_enable_hotplug);
-	destroy_workqueue(state->work_queues);
 err_i2c:
 	adv7842_unregister_clients(sd);
 err_hdl:
@@ -3355,9 +3598,7 @@ static int adv7842_remove(struct i2c_client *client)
 	struct adv7842_state *state = to_state(sd);
 
 	adv7842_irq_enable(sd, false);
-
 	cancel_delayed_work(&state->delayed_work_enable_hotplug);
-	destroy_workqueue(state->work_queues);
 	v4l2_device_unregister_subdev(sd);
 	media_entity_cleanup(&sd->entity);
 	adv7842_unregister_clients(sd);
diff --git a/drivers/media/i2c/cs53l32a.c b/drivers/media/i2c/cs53l32a.c
index b7e87e38642a..e4b3cf49dd38 100644
--- a/drivers/media/i2c/cs53l32a.c
+++ b/drivers/media/i2c/cs53l32a.c
@@ -121,13 +121,6 @@ static const struct v4l2_ctrl_ops cs53l32a_ctrl_ops = {
 
 static const struct v4l2_subdev_core_ops cs53l32a_core_ops = {
 	.log_status = cs53l32a_log_status,
-	.g_ext_ctrls = v4l2_subdev_g_ext_ctrls,
-	.try_ext_ctrls = v4l2_subdev_try_ext_ctrls,
-	.s_ext_ctrls = v4l2_subdev_s_ext_ctrls,
-	.g_ctrl = v4l2_subdev_g_ctrl,
-	.s_ctrl = v4l2_subdev_s_ctrl,
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
 };
 
 static const struct v4l2_subdev_audio_ops cs53l32a_audio_ops = {
diff --git a/drivers/media/i2c/cx25840/cx25840-core.c b/drivers/media/i2c/cx25840/cx25840-core.c
index 07a3e7173144..142ae28803bb 100644
--- a/drivers/media/i2c/cx25840/cx25840-core.c
+++ b/drivers/media/i2c/cx25840/cx25840-core.c
@@ -5042,13 +5042,6 @@ static const struct v4l2_ctrl_ops cx25840_ctrl_ops = {
 
 static const struct v4l2_subdev_core_ops cx25840_core_ops = {
 	.log_status = cx25840_log_status,
-	.g_ctrl = v4l2_subdev_g_ctrl,
-	.s_ctrl = v4l2_subdev_s_ctrl,
-	.s_ext_ctrls = v4l2_subdev_s_ext_ctrls,
-	.try_ext_ctrls = v4l2_subdev_try_ext_ctrls,
-	.g_ext_ctrls = v4l2_subdev_g_ext_ctrls,
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
 	.reset = cx25840_reset,
 	.load_fw = cx25840_load_fw,
 	.s_io_pin_config = common_s_io_pin_config,
diff --git a/drivers/media/i2c/msp3400-driver.c b/drivers/media/i2c/msp3400-driver.c
index e016626ebf89..503b7c4f0a9b 100644
--- a/drivers/media/i2c/msp3400-driver.c
+++ b/drivers/media/i2c/msp3400-driver.c
@@ -642,13 +642,6 @@ static const struct v4l2_ctrl_ops msp_ctrl_ops = {
 
 static const struct v4l2_subdev_core_ops msp_core_ops = {
 	.log_status = msp_log_status,
-	.g_ext_ctrls = v4l2_subdev_g_ext_ctrls,
-	.try_ext_ctrls = v4l2_subdev_try_ext_ctrls,
-	.s_ext_ctrls = v4l2_subdev_s_ext_ctrls,
-	.g_ctrl = v4l2_subdev_g_ctrl,
-	.s_ctrl = v4l2_subdev_s_ctrl,
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
 };
 
 static const struct v4l2_subdev_video_ops msp_video_ops = {
diff --git a/drivers/media/i2c/mt9t001.c b/drivers/media/i2c/mt9t001.c
index 702d562f8e39..842017fa4aab 100644
--- a/drivers/media/i2c/mt9t001.c
+++ b/drivers/media/i2c/mt9t001.c
@@ -233,10 +233,21 @@ static int __mt9t001_set_power(struct mt9t001 *mt9t001, bool on)
 	ret = mt9t001_reset(mt9t001);
 	if (ret < 0) {
 		dev_err(&client->dev, "Failed to reset the camera\n");
-		return ret;
+		goto e_power;
 	}
 
-	return v4l2_ctrl_handler_setup(&mt9t001->ctrls);
+	ret = v4l2_ctrl_handler_setup(&mt9t001->ctrls);
+	if (ret < 0) {
+		dev_err(&client->dev, "Failed to set up control handlers\n");
+		goto e_power;
+	}
+
+	return 0;
+
+e_power:
+	mt9t001_power_off(mt9t001);
+
+	return ret;
 }
 
 /* -----------------------------------------------------------------------------
@@ -834,7 +845,7 @@ static struct v4l2_subdev_ops mt9t001_subdev_ops = {
 	.pad = &mt9t001_subdev_pad_ops,
 };
 
-static struct v4l2_subdev_internal_ops mt9t001_subdev_internal_ops = {
+static const struct v4l2_subdev_internal_ops mt9t001_subdev_internal_ops = {
 	.registered = mt9t001_registered,
 	.open = mt9t001_open,
 	.close = mt9t001_close,
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index 501b37039449..58eb62f1ba21 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -19,7 +19,6 @@
 #include <linux/log2.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
@@ -133,9 +132,16 @@
 #define		MT9V032_TEST_PATTERN_GRAY_DIAGONAL	(3 << 11)
 #define		MT9V032_TEST_PATTERN_ENABLE		(1 << 13)
 #define		MT9V032_TEST_PATTERN_FLIP		(1 << 14)
+#define MT9V032_AEGC_DESIRED_BIN			0xa5
+#define MT9V032_AEC_UPDATE_FREQUENCY			0xa6
+#define MT9V032_AEC_LPF					0xa8
+#define MT9V032_AGC_UPDATE_FREQUENCY			0xa9
+#define MT9V032_AGC_LPF					0xaa
 #define MT9V032_AEC_AGC_ENABLE				0xaf
 #define		MT9V032_AEC_ENABLE			(1 << 0)
 #define		MT9V032_AGC_ENABLE			(1 << 1)
+#define MT9V034_AEC_MAX_SHUTTER_WIDTH			0xad
+#define MT9V032_AEC_MAX_SHUTTER_WIDTH			0xbd
 #define MT9V032_THERMAL_INFO				0xc1
 
 enum mt9v032_model {
@@ -162,6 +168,8 @@ struct mt9v032_model_data {
 	unsigned int min_shutter;
 	unsigned int max_shutter;
 	unsigned int pclk_reg;
+	unsigned int aec_max_shutter_reg;
+	const struct v4l2_ctrl_config * const aec_max_shutter_v4l2_ctrl;
 };
 
 struct mt9v032_model_info {
@@ -175,63 +183,6 @@ static const struct mt9v032_model_version mt9v032_versions[] = {
 	{ MT9V034_CHIP_ID_REV1, "MT9V024/MT9V034 rev1" },
 };
 
-static const struct mt9v032_model_data mt9v032_model_data[] = {
-	{
-		/* MT9V022, MT9V032 revisions 1/2/3 */
-		.min_row_time = 660,
-		.min_hblank = MT9V032_HORIZONTAL_BLANKING_MIN,
-		.min_vblank = MT9V032_VERTICAL_BLANKING_MIN,
-		.max_vblank = MT9V032_VERTICAL_BLANKING_MAX,
-		.min_shutter = MT9V032_TOTAL_SHUTTER_WIDTH_MIN,
-		.max_shutter = MT9V032_TOTAL_SHUTTER_WIDTH_MAX,
-		.pclk_reg = MT9V032_PIXEL_CLOCK,
-	}, {
-		/* MT9V024, MT9V034 */
-		.min_row_time = 690,
-		.min_hblank = MT9V034_HORIZONTAL_BLANKING_MIN,
-		.min_vblank = MT9V034_VERTICAL_BLANKING_MIN,
-		.max_vblank = MT9V034_VERTICAL_BLANKING_MAX,
-		.min_shutter = MT9V034_TOTAL_SHUTTER_WIDTH_MIN,
-		.max_shutter = MT9V034_TOTAL_SHUTTER_WIDTH_MAX,
-		.pclk_reg = MT9V034_PIXEL_CLOCK,
-	},
-};
-
-static const struct mt9v032_model_info mt9v032_models[] = {
-	[MT9V032_MODEL_V022_COLOR] = {
-		.data = &mt9v032_model_data[0],
-		.color = true,
-	},
-	[MT9V032_MODEL_V022_MONO] = {
-		.data = &mt9v032_model_data[0],
-		.color = false,
-	},
-	[MT9V032_MODEL_V024_COLOR] = {
-		.data = &mt9v032_model_data[1],
-		.color = true,
-	},
-	[MT9V032_MODEL_V024_MONO] = {
-		.data = &mt9v032_model_data[1],
-		.color = false,
-	},
-	[MT9V032_MODEL_V032_COLOR] = {
-		.data = &mt9v032_model_data[0],
-		.color = true,
-	},
-	[MT9V032_MODEL_V032_MONO] = {
-		.data = &mt9v032_model_data[0],
-		.color = false,
-	},
-	[MT9V032_MODEL_V034_COLOR] = {
-		.data = &mt9v032_model_data[1],
-		.color = true,
-	},
-	[MT9V032_MODEL_V034_MONO] = {
-		.data = &mt9v032_model_data[1],
-		.color = false,
-	},
-};
-
 struct mt9v032 {
 	struct v4l2_subdev subdev;
 	struct media_pad pad;
@@ -349,7 +300,8 @@ static int mt9v032_power_on(struct mt9v032 *mt9v032)
 	if (ret < 0)
 		return ret;
 
-	return regmap_write(map, MT9V032_CHIP_CONTROL, 0);
+	return regmap_write(map, MT9V032_CHIP_CONTROL,
+			    MT9V032_CHIP_CONTROL_MASTER_MODE);
 }
 
 static void mt9v032_power_off(struct mt9v032 *mt9v032)
@@ -421,8 +373,7 @@ __mt9v032_get_pad_crop(struct mt9v032 *mt9v032, struct v4l2_subdev_pad_config *c
 
 static int mt9v032_s_stream(struct v4l2_subdev *subdev, int enable)
 {
-	const u16 mode = MT9V032_CHIP_CONTROL_MASTER_MODE
-		       | MT9V032_CHIP_CONTROL_DOUT_ENABLE
+	const u16 mode = MT9V032_CHIP_CONTROL_DOUT_ENABLE
 		       | MT9V032_CHIP_CONTROL_SEQUENTIAL;
 	struct mt9v032 *mt9v032 = to_mt9v032(subdev);
 	struct v4l2_rect *crop = &mt9v032->crop;
@@ -647,6 +598,34 @@ static int mt9v032_set_selection(struct v4l2_subdev *subdev,
  */
 
 #define V4L2_CID_TEST_PATTERN_COLOR	(V4L2_CID_USER_BASE | 0x1001)
+/*
+ * Value between 1 and 64 to set the desired bin. This is effectively a measure
+ * of how bright the image is supposed to be. Both AGC and AEC try to reach
+ * this.
+ */
+#define V4L2_CID_AEGC_DESIRED_BIN	(V4L2_CID_USER_BASE | 0x1002)
+/*
+ * LPF is the low pass filter capability of the chip. Both AEC and AGC have
+ * this setting. This limits the speed in which AGC/AEC adjust their settings.
+ * Possible values are 0-2. 0 means no LPF. For 1 and 2 this equation is used:
+ *
+ * if |(calculated new exp - current exp)| > (current exp / 4)
+ *	next exp = calculated new exp
+ * else
+ *	next exp = current exp + ((calculated new exp - current exp) / 2^LPF)
+ */
+#define V4L2_CID_AEC_LPF		(V4L2_CID_USER_BASE | 0x1003)
+#define V4L2_CID_AGC_LPF		(V4L2_CID_USER_BASE | 0x1004)
+/*
+ * Value between 0 and 15. This is the number of frames being skipped before
+ * updating the auto exposure/gain.
+ */
+#define V4L2_CID_AEC_UPDATE_INTERVAL	(V4L2_CID_USER_BASE | 0x1005)
+#define V4L2_CID_AGC_UPDATE_INTERVAL	(V4L2_CID_USER_BASE | 0x1006)
+/*
+ * Maximum shutter width used for AEC.
+ */
+#define V4L2_CID_AEC_MAX_SHUTTER_WIDTH	(V4L2_CID_USER_BASE | 0x1007)
 
 static int mt9v032_s_ctrl(struct v4l2_ctrl *ctrl)
 {
@@ -716,6 +695,28 @@ static int mt9v032_s_ctrl(struct v4l2_ctrl *ctrl)
 			break;
 		}
 		return regmap_write(map, MT9V032_TEST_PATTERN, data);
+
+	case V4L2_CID_AEGC_DESIRED_BIN:
+		return regmap_write(map, MT9V032_AEGC_DESIRED_BIN, ctrl->val);
+
+	case V4L2_CID_AEC_LPF:
+		return regmap_write(map, MT9V032_AEC_LPF, ctrl->val);
+
+	case V4L2_CID_AGC_LPF:
+		return regmap_write(map, MT9V032_AGC_LPF, ctrl->val);
+
+	case V4L2_CID_AEC_UPDATE_INTERVAL:
+		return regmap_write(map, MT9V032_AEC_UPDATE_FREQUENCY,
+				    ctrl->val);
+
+	case V4L2_CID_AGC_UPDATE_INTERVAL:
+		return regmap_write(map, MT9V032_AGC_UPDATE_FREQUENCY,
+				    ctrl->val);
+
+	case V4L2_CID_AEC_MAX_SHUTTER_WIDTH:
+		return regmap_write(map,
+				    mt9v032->model->data->aec_max_shutter_reg,
+				    ctrl->val);
 	}
 
 	return 0;
@@ -745,6 +746,84 @@ static const struct v4l2_ctrl_config mt9v032_test_pattern_color = {
 	.flags		= 0,
 };
 
+static const struct v4l2_ctrl_config mt9v032_aegc_controls[] = {
+	{
+		.ops		= &mt9v032_ctrl_ops,
+		.id		= V4L2_CID_AEGC_DESIRED_BIN,
+		.type		= V4L2_CTRL_TYPE_INTEGER,
+		.name		= "AEC/AGC Desired Bin",
+		.min		= 1,
+		.max		= 64,
+		.step		= 1,
+		.def		= 58,
+		.flags		= 0,
+	}, {
+		.ops		= &mt9v032_ctrl_ops,
+		.id		= V4L2_CID_AEC_LPF,
+		.type		= V4L2_CTRL_TYPE_INTEGER,
+		.name		= "AEC Low Pass Filter",
+		.min		= 0,
+		.max		= 2,
+		.step		= 1,
+		.def		= 0,
+		.flags		= 0,
+	}, {
+		.ops		= &mt9v032_ctrl_ops,
+		.id		= V4L2_CID_AGC_LPF,
+		.type		= V4L2_CTRL_TYPE_INTEGER,
+		.name		= "AGC Low Pass Filter",
+		.min		= 0,
+		.max		= 2,
+		.step		= 1,
+		.def		= 2,
+		.flags		= 0,
+	}, {
+		.ops		= &mt9v032_ctrl_ops,
+		.id		= V4L2_CID_AEC_UPDATE_INTERVAL,
+		.type		= V4L2_CTRL_TYPE_INTEGER,
+		.name		= "AEC Update Interval",
+		.min		= 0,
+		.max		= 16,
+		.step		= 1,
+		.def		= 2,
+		.flags		= 0,
+	}, {
+		.ops		= &mt9v032_ctrl_ops,
+		.id		= V4L2_CID_AGC_UPDATE_INTERVAL,
+		.type		= V4L2_CTRL_TYPE_INTEGER,
+		.name		= "AGC Update Interval",
+		.min		= 0,
+		.max		= 16,
+		.step		= 1,
+		.def		= 2,
+		.flags		= 0,
+	}
+};
+
+static const struct v4l2_ctrl_config mt9v032_aec_max_shutter_width = {
+	.ops		= &mt9v032_ctrl_ops,
+	.id		= V4L2_CID_AEC_MAX_SHUTTER_WIDTH,
+	.type		= V4L2_CTRL_TYPE_INTEGER,
+	.name		= "AEC Max Shutter Width",
+	.min		= 1,
+	.max		= 2047,
+	.step		= 1,
+	.def		= 480,
+	.flags		= 0,
+};
+
+static const struct v4l2_ctrl_config mt9v034_aec_max_shutter_width = {
+	.ops		= &mt9v032_ctrl_ops,
+	.id		= V4L2_CID_AEC_MAX_SHUTTER_WIDTH,
+	.type		= V4L2_CTRL_TYPE_INTEGER,
+	.name		= "AEC Max Shutter Width",
+	.min		= 1,
+	.max		= 32765,
+	.step		= 1,
+	.def		= 480,
+	.flags		= 0,
+};
+
 /* -----------------------------------------------------------------------------
  * V4L2 subdev core operations
  */
@@ -953,13 +1032,6 @@ static int mt9v032_probe(struct i2c_client *client,
 	unsigned int i;
 	int ret;
 
-	if (!i2c_check_functionality(client->adapter,
-				     I2C_FUNC_SMBUS_WORD_DATA)) {
-		dev_warn(&client->adapter->dev,
-			 "I2C-Adapter doesn't support I2C_FUNC_SMBUS_WORD\n");
-		return -EIO;
-	}
-
 	mt9v032 = devm_kzalloc(&client->dev, sizeof(*mt9v032), GFP_KERNEL);
 	if (!mt9v032)
 		return -ENOMEM;
@@ -986,7 +1058,8 @@ static int mt9v032_probe(struct i2c_client *client,
 	mt9v032->pdata = pdata;
 	mt9v032->model = (const void *)did->driver_data;
 
-	v4l2_ctrl_handler_init(&mt9v032->ctrls, 10);
+	v4l2_ctrl_handler_init(&mt9v032->ctrls, 11 +
+			       ARRAY_SIZE(mt9v032_aegc_controls));
 
 	v4l2_ctrl_new_std(&mt9v032->ctrls, &mt9v032_ctrl_ops,
 			  V4L2_CID_AUTOGAIN, 0, 1, 1, 1);
@@ -1015,6 +1088,13 @@ static int mt9v032_probe(struct i2c_client *client,
 	mt9v032->test_pattern_color = v4l2_ctrl_new_custom(&mt9v032->ctrls,
 				      &mt9v032_test_pattern_color, NULL);
 
+	v4l2_ctrl_new_custom(&mt9v032->ctrls,
+			     mt9v032->model->data->aec_max_shutter_v4l2_ctrl,
+			     NULL);
+	for (i = 0; i < ARRAY_SIZE(mt9v032_aegc_controls); ++i)
+		v4l2_ctrl_new_custom(&mt9v032->ctrls, &mt9v032_aegc_controls[i],
+				     NULL);
+
 	v4l2_ctrl_cluster(2, &mt9v032->test_pattern);
 
 	mt9v032->pixel_rate =
@@ -1103,6 +1183,67 @@ static int mt9v032_remove(struct i2c_client *client)
 	return 0;
 }
 
+static const struct mt9v032_model_data mt9v032_model_data[] = {
+	{
+		/* MT9V022, MT9V032 revisions 1/2/3 */
+		.min_row_time = 660,
+		.min_hblank = MT9V032_HORIZONTAL_BLANKING_MIN,
+		.min_vblank = MT9V032_VERTICAL_BLANKING_MIN,
+		.max_vblank = MT9V032_VERTICAL_BLANKING_MAX,
+		.min_shutter = MT9V032_TOTAL_SHUTTER_WIDTH_MIN,
+		.max_shutter = MT9V032_TOTAL_SHUTTER_WIDTH_MAX,
+		.pclk_reg = MT9V032_PIXEL_CLOCK,
+		.aec_max_shutter_reg = MT9V032_AEC_MAX_SHUTTER_WIDTH,
+		.aec_max_shutter_v4l2_ctrl = &mt9v032_aec_max_shutter_width,
+	}, {
+		/* MT9V024, MT9V034 */
+		.min_row_time = 690,
+		.min_hblank = MT9V034_HORIZONTAL_BLANKING_MIN,
+		.min_vblank = MT9V034_VERTICAL_BLANKING_MIN,
+		.max_vblank = MT9V034_VERTICAL_BLANKING_MAX,
+		.min_shutter = MT9V034_TOTAL_SHUTTER_WIDTH_MIN,
+		.max_shutter = MT9V034_TOTAL_SHUTTER_WIDTH_MAX,
+		.pclk_reg = MT9V034_PIXEL_CLOCK,
+		.aec_max_shutter_reg = MT9V034_AEC_MAX_SHUTTER_WIDTH,
+		.aec_max_shutter_v4l2_ctrl = &mt9v034_aec_max_shutter_width,
+	},
+};
+
+static const struct mt9v032_model_info mt9v032_models[] = {
+	[MT9V032_MODEL_V022_COLOR] = {
+		.data = &mt9v032_model_data[0],
+		.color = true,
+	},
+	[MT9V032_MODEL_V022_MONO] = {
+		.data = &mt9v032_model_data[0],
+		.color = false,
+	},
+	[MT9V032_MODEL_V024_COLOR] = {
+		.data = &mt9v032_model_data[1],
+		.color = true,
+	},
+	[MT9V032_MODEL_V024_MONO] = {
+		.data = &mt9v032_model_data[1],
+		.color = false,
+	},
+	[MT9V032_MODEL_V032_COLOR] = {
+		.data = &mt9v032_model_data[0],
+		.color = true,
+	},
+	[MT9V032_MODEL_V032_MONO] = {
+		.data = &mt9v032_model_data[0],
+		.color = false,
+	},
+	[MT9V032_MODEL_V034_COLOR] = {
+		.data = &mt9v032_model_data[1],
+		.color = true,
+	},
+	[MT9V032_MODEL_V034_MONO] = {
+		.data = &mt9v032_model_data[1],
+		.color = false,
+	},
+};
+
 static const struct i2c_device_id mt9v032_id[] = {
 	{ "mt9v022", (kernel_ulong_t)&mt9v032_models[MT9V032_MODEL_V022_COLOR] },
 	{ "mt9v022m", (kernel_ulong_t)&mt9v032_models[MT9V032_MODEL_V022_MONO] },
diff --git a/drivers/media/i2c/saa7115.c b/drivers/media/i2c/saa7115.c
index bd3526bdd539..58062b41c923 100644
--- a/drivers/media/i2c/saa7115.c
+++ b/drivers/media/i2c/saa7115.c
@@ -1585,13 +1585,6 @@ static const struct v4l2_ctrl_ops saa711x_ctrl_ops = {
 
 static const struct v4l2_subdev_core_ops saa711x_core_ops = {
 	.log_status = saa711x_log_status,
-	.g_ext_ctrls = v4l2_subdev_g_ext_ctrls,
-	.try_ext_ctrls = v4l2_subdev_try_ext_ctrls,
-	.s_ext_ctrls = v4l2_subdev_s_ext_ctrls,
-	.g_ctrl = v4l2_subdev_g_ctrl,
-	.s_ctrl = v4l2_subdev_s_ctrl,
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
 	.reset = saa711x_reset,
 	.s_gpio = saa711x_s_gpio,
 #ifdef CONFIG_VIDEO_ADV_DEBUG
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 3dfe387abf6e..d08ab6c8357c 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -3044,10 +3044,8 @@ static struct smiapp_platform_data *smiapp_get_pdata(struct device *dev)
 	pdata->op_sys_clock = devm_kcalloc(
 		dev, bus_cfg->nr_of_link_frequencies + 1 /* guardian */,
 		sizeof(*pdata->op_sys_clock), GFP_KERNEL);
-	if (!pdata->op_sys_clock) {
-		rval = -ENOMEM;
+	if (!pdata->op_sys_clock)
 		goto out_err;
-	}
 
 	for (i = 0; i < bus_cfg->nr_of_link_frequencies; i++) {
 		pdata->op_sys_clock[i] = bus_cfg->link_frequencies[i];
diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c
index 6cf6d06737a5..1e3a0dd2238c 100644
--- a/drivers/media/i2c/tc358743.c
+++ b/drivers/media/i2c/tc358743.c
@@ -89,8 +89,6 @@ struct tc358743_state {
 	struct v4l2_ctrl *audio_sampling_rate_ctrl;
 	struct v4l2_ctrl *audio_present_ctrl;
 
-	/* work queues */
-	struct workqueue_struct *work_queues;
 	struct delayed_work delayed_work_enable_hotplug;
 
 	/* edid  */
@@ -425,8 +423,7 @@ static void tc358743_enable_edid(struct v4l2_subdev *sd)
 
 	/* Enable hotplug after 100 ms. DDC access to EDID is also enabled when
 	 * hotplug is enabled. See register DDC_CTL */
-	queue_delayed_work(state->work_queues,
-			   &state->delayed_work_enable_hotplug, HZ / 10);
+	schedule_delayed_work(&state->delayed_work_enable_hotplug, HZ / 10);
 
 	tc358743_enable_interrupts(sd, true);
 	tc358743_s_ctrl_detect_tx_5v(sd);
@@ -1884,14 +1881,6 @@ static int tc358743_probe(struct i2c_client *client,
 		goto err_hdl;
 	}
 
-	/* work queues */
-	state->work_queues = create_singlethread_workqueue(client->name);
-	if (!state->work_queues) {
-		v4l2_err(sd, "Could not create work queue\n");
-		err = -ENOMEM;
-		goto err_hdl;
-	}
-
 	state->pad.flags = MEDIA_PAD_FL_SOURCE;
 	err = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (err < 0)
@@ -1940,7 +1929,6 @@ static int tc358743_probe(struct i2c_client *client,
 
 err_work_queues:
 	cancel_delayed_work(&state->delayed_work_enable_hotplug);
-	destroy_workqueue(state->work_queues);
 	mutex_destroy(&state->confctl_mutex);
 err_hdl:
 	media_entity_cleanup(&sd->entity);
@@ -1954,7 +1942,6 @@ static int tc358743_remove(struct i2c_client *client)
 	struct tc358743_state *state = to_state(sd);
 
 	cancel_delayed_work(&state->delayed_work_enable_hotplug);
-	destroy_workqueue(state->work_queues);
 	v4l2_async_unregister_subdev(sd);
 	v4l2_device_unregister_subdev(sd);
 	mutex_destroy(&state->confctl_mutex);
diff --git a/drivers/media/i2c/tvaudio.c b/drivers/media/i2c/tvaudio.c
index fece2a4339a1..42d1e26e581c 100644
--- a/drivers/media/i2c/tvaudio.c
+++ b/drivers/media/i2c/tvaudio.c
@@ -1855,13 +1855,6 @@ static const struct v4l2_ctrl_ops tvaudio_ctrl_ops = {
 
 static const struct v4l2_subdev_core_ops tvaudio_core_ops = {
 	.log_status = tvaudio_log_status,
-	.g_ext_ctrls = v4l2_subdev_g_ext_ctrls,
-	.try_ext_ctrls = v4l2_subdev_try_ext_ctrls,
-	.s_ext_ctrls = v4l2_subdev_s_ext_ctrls,
-	.g_ctrl = v4l2_subdev_g_ctrl,
-	.s_ctrl = v4l2_subdev_s_ctrl,
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
 };
 
 static const struct v4l2_subdev_tuner_ops tvaudio_tuner_ops = {
diff --git a/drivers/media/i2c/wm8775.c b/drivers/media/i2c/wm8775.c
index 6e00f145b948..5581f4db02af 100644
--- a/drivers/media/i2c/wm8775.c
+++ b/drivers/media/i2c/wm8775.c
@@ -178,13 +178,6 @@ static const struct v4l2_ctrl_ops wm8775_ctrl_ops = {
 
 static const struct v4l2_subdev_core_ops wm8775_core_ops = {
 	.log_status = wm8775_log_status,
-	.g_ext_ctrls = v4l2_subdev_g_ext_ctrls,
-	.try_ext_ctrls = v4l2_subdev_try_ext_ctrls,
-	.s_ext_ctrls = v4l2_subdev_s_ext_ctrls,
-	.g_ctrl = v4l2_subdev_g_ctrl,
-	.s_ctrl = v4l2_subdev_s_ctrl,
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
 };
 
 static const struct v4l2_subdev_tuner_ops wm8775_tuner_ops = {
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index a1cd50f331f1..1795abeda658 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -423,7 +423,7 @@ static long media_device_ioctl(struct file *filp, unsigned int cmd,
 			       unsigned long arg)
 {
 	struct media_devnode *devnode = media_devnode_data(filp);
-	struct media_device *dev = to_media_device(devnode);
+	struct media_device *dev = devnode->media_dev;
 	long ret;
 
 	mutex_lock(&dev->graph_mutex);
@@ -495,7 +495,7 @@ static long media_device_compat_ioctl(struct file *filp, unsigned int cmd,
 				      unsigned long arg)
 {
 	struct media_devnode *devnode = media_devnode_data(filp);
-	struct media_device *dev = to_media_device(devnode);
+	struct media_device *dev = devnode->media_dev;
 	long ret;
 
 	switch (cmd) {
@@ -531,7 +531,8 @@ static const struct media_file_operations media_device_fops = {
 static ssize_t show_model(struct device *cd,
 			  struct device_attribute *attr, char *buf)
 {
-	struct media_device *mdev = to_media_device(to_media_devnode(cd));
+	struct media_devnode *devnode = to_media_devnode(cd);
+	struct media_device *mdev = devnode->media_dev;
 
 	return sprintf(buf, "%.*s\n", (int)sizeof(mdev->model), mdev->model);
 }
@@ -704,23 +705,35 @@ EXPORT_SYMBOL_GPL(media_device_cleanup);
 int __must_check __media_device_register(struct media_device *mdev,
 					 struct module *owner)
 {
+	struct media_devnode *devnode;
 	int ret;
 
+	devnode = kzalloc(sizeof(*devnode), GFP_KERNEL);
+	if (!devnode)
+		return -ENOMEM;
+
 	/* Register the device node. */
-	mdev->devnode.fops = &media_device_fops;
-	mdev->devnode.parent = mdev->dev;
-	mdev->devnode.release = media_device_release;
+	mdev->devnode = devnode;
+	devnode->fops = &media_device_fops;
+	devnode->parent = mdev->dev;
+	devnode->release = media_device_release;
 
 	/* Set version 0 to indicate user-space that the graph is static */
 	mdev->topology_version = 0;
 
-	ret = media_devnode_register(&mdev->devnode, owner);
-	if (ret < 0)
+	ret = media_devnode_register(mdev, devnode, owner);
+	if (ret < 0) {
+		/* devnode free is handled in media_devnode_*() */
+		mdev->devnode = NULL;
 		return ret;
+	}
 
-	ret = device_create_file(&mdev->devnode.dev, &dev_attr_model);
+	ret = device_create_file(&devnode->dev, &dev_attr_model);
 	if (ret < 0) {
-		media_devnode_unregister(&mdev->devnode);
+		/* devnode free is handled in media_devnode_*() */
+		mdev->devnode = NULL;
+		media_devnode_unregister_prepare(devnode);
+		media_devnode_unregister(devnode);
 		return ret;
 	}
 
@@ -771,11 +784,14 @@ void media_device_unregister(struct media_device *mdev)
 	mutex_lock(&mdev->graph_mutex);
 
 	/* Check if mdev was ever registered at all */
-	if (!media_devnode_is_registered(&mdev->devnode)) {
+	if (!media_devnode_is_registered(mdev->devnode)) {
 		mutex_unlock(&mdev->graph_mutex);
 		return;
 	}
 
+	/* Clear the devnode register bit to avoid races with media dev open */
+	media_devnode_unregister_prepare(mdev->devnode);
+
 	/* Remove all entities from the media device */
 	list_for_each_entry_safe(entity, next, &mdev->entities, graph_obj.list)
 		__media_device_unregister_entity(entity);
@@ -794,9 +810,12 @@ void media_device_unregister(struct media_device *mdev)
 
 	mutex_unlock(&mdev->graph_mutex);
 
-	device_remove_file(&mdev->devnode.dev, &dev_attr_model);
-	dev_dbg(mdev->dev, "Media device unregistering\n");
-	media_devnode_unregister(&mdev->devnode);
+	dev_dbg(mdev->dev, "Media device unregistered\n");
+
+	device_remove_file(&mdev->devnode->dev, &dev_attr_model);
+	media_devnode_unregister(mdev->devnode);
+	/* devnode free is handled in media_devnode_*() */
+	mdev->devnode = NULL;
 }
 EXPORT_SYMBOL_GPL(media_device_unregister);
 
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index b66dc9d0766b..f2772ba6f611 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -44,6 +44,7 @@
 #include <linux/uaccess.h>
 
 #include <media/media-devnode.h>
+#include <media/media-device.h>
 
 #define MEDIA_NUM_DEVICES	256
 #define MEDIA_NAME		"media"
@@ -59,21 +60,19 @@ static DECLARE_BITMAP(media_devnode_nums, MEDIA_NUM_DEVICES);
 /* Called when the last user of the media device exits. */
 static void media_devnode_release(struct device *cd)
 {
-	struct media_devnode *mdev = to_media_devnode(cd);
+	struct media_devnode *devnode = to_media_devnode(cd);
 
 	mutex_lock(&media_devnode_lock);
-
-	/* Delete the cdev on this minor as well */
-	cdev_del(&mdev->cdev);
-
 	/* Mark device node number as free */
-	clear_bit(mdev->minor, media_devnode_nums);
-
+	clear_bit(devnode->minor, media_devnode_nums);
 	mutex_unlock(&media_devnode_lock);
 
 	/* Release media_devnode and perform other cleanups as needed. */
-	if (mdev->release)
-		mdev->release(mdev);
+	if (devnode->release)
+		devnode->release(devnode);
+
+	kfree(devnode);
+	pr_debug("%s: Media Devnode Deallocated\n", __func__);
 }
 
 static struct bus_type media_bus_type = {
@@ -83,37 +82,37 @@ static struct bus_type media_bus_type = {
 static ssize_t media_read(struct file *filp, char __user *buf,
 		size_t sz, loff_t *off)
 {
-	struct media_devnode *mdev = media_devnode_data(filp);
+	struct media_devnode *devnode = media_devnode_data(filp);
 
-	if (!mdev->fops->read)
+	if (!devnode->fops->read)
 		return -EINVAL;
-	if (!media_devnode_is_registered(mdev))
+	if (!media_devnode_is_registered(devnode))
 		return -EIO;
-	return mdev->fops->read(filp, buf, sz, off);
+	return devnode->fops->read(filp, buf, sz, off);
 }
 
 static ssize_t media_write(struct file *filp, const char __user *buf,
 		size_t sz, loff_t *off)
 {
-	struct media_devnode *mdev = media_devnode_data(filp);
+	struct media_devnode *devnode = media_devnode_data(filp);
 
-	if (!mdev->fops->write)
+	if (!devnode->fops->write)
 		return -EINVAL;
-	if (!media_devnode_is_registered(mdev))
+	if (!media_devnode_is_registered(devnode))
 		return -EIO;
-	return mdev->fops->write(filp, buf, sz, off);
+	return devnode->fops->write(filp, buf, sz, off);
 }
 
 static unsigned int media_poll(struct file *filp,
 			       struct poll_table_struct *poll)
 {
-	struct media_devnode *mdev = media_devnode_data(filp);
+	struct media_devnode *devnode = media_devnode_data(filp);
 
-	if (!media_devnode_is_registered(mdev))
+	if (!media_devnode_is_registered(devnode))
 		return POLLERR | POLLHUP;
-	if (!mdev->fops->poll)
+	if (!devnode->fops->poll)
 		return DEFAULT_POLLMASK;
-	return mdev->fops->poll(filp, poll);
+	return devnode->fops->poll(filp, poll);
 }
 
 static long
@@ -121,12 +120,12 @@ __media_ioctl(struct file *filp, unsigned int cmd, unsigned long arg,
 	      long (*ioctl_func)(struct file *filp, unsigned int cmd,
 				 unsigned long arg))
 {
-	struct media_devnode *mdev = media_devnode_data(filp);
+	struct media_devnode *devnode = media_devnode_data(filp);
 
 	if (!ioctl_func)
 		return -ENOTTY;
 
-	if (!media_devnode_is_registered(mdev))
+	if (!media_devnode_is_registered(devnode))
 		return -EIO;
 
 	return ioctl_func(filp, cmd, arg);
@@ -134,9 +133,9 @@ __media_ioctl(struct file *filp, unsigned int cmd, unsigned long arg,
 
 static long media_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
-	struct media_devnode *mdev = media_devnode_data(filp);
+	struct media_devnode *devnode = media_devnode_data(filp);
 
-	return __media_ioctl(filp, cmd, arg, mdev->fops->ioctl);
+	return __media_ioctl(filp, cmd, arg, devnode->fops->ioctl);
 }
 
 #ifdef CONFIG_COMPAT
@@ -144,9 +143,9 @@ static long media_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 static long media_compat_ioctl(struct file *filp, unsigned int cmd,
 			       unsigned long arg)
 {
-	struct media_devnode *mdev = media_devnode_data(filp);
+	struct media_devnode *devnode = media_devnode_data(filp);
 
-	return __media_ioctl(filp, cmd, arg, mdev->fops->compat_ioctl);
+	return __media_ioctl(filp, cmd, arg, devnode->fops->compat_ioctl);
 }
 
 #endif /* CONFIG_COMPAT */
@@ -154,7 +153,7 @@ static long media_compat_ioctl(struct file *filp, unsigned int cmd,
 /* Override for the open function */
 static int media_open(struct inode *inode, struct file *filp)
 {
-	struct media_devnode *mdev;
+	struct media_devnode *devnode;
 	int ret;
 
 	/* Check if the media device is available. This needs to be done with
@@ -164,23 +163,23 @@ static int media_open(struct inode *inode, struct file *filp)
 	 * a crash.
 	 */
 	mutex_lock(&media_devnode_lock);
-	mdev = container_of(inode->i_cdev, struct media_devnode, cdev);
+	devnode = container_of(inode->i_cdev, struct media_devnode, cdev);
 	/* return ENXIO if the media device has been removed
 	   already or if it is not registered anymore. */
-	if (!media_devnode_is_registered(mdev)) {
+	if (!media_devnode_is_registered(devnode)) {
 		mutex_unlock(&media_devnode_lock);
 		return -ENXIO;
 	}
 	/* and increase the device refcount */
-	get_device(&mdev->dev);
+	get_device(&devnode->dev);
 	mutex_unlock(&media_devnode_lock);
 
-	filp->private_data = mdev;
+	filp->private_data = devnode;
 
-	if (mdev->fops->open) {
-		ret = mdev->fops->open(filp);
+	if (devnode->fops->open) {
+		ret = devnode->fops->open(filp);
 		if (ret) {
-			put_device(&mdev->dev);
+			put_device(&devnode->dev);
 			filp->private_data = NULL;
 			return ret;
 		}
@@ -192,16 +191,18 @@ static int media_open(struct inode *inode, struct file *filp)
 /* Override for the release function */
 static int media_release(struct inode *inode, struct file *filp)
 {
-	struct media_devnode *mdev = media_devnode_data(filp);
+	struct media_devnode *devnode = media_devnode_data(filp);
 
-	if (mdev->fops->release)
-		mdev->fops->release(filp);
+	if (devnode->fops->release)
+		devnode->fops->release(filp);
 
 	filp->private_data = NULL;
 
 	/* decrease the refcount unconditionally since the release()
 	   return value is ignored. */
-	put_device(&mdev->dev);
+	put_device(&devnode->dev);
+
+	pr_debug("%s: Media Release\n", __func__);
 	return 0;
 }
 
@@ -219,7 +220,8 @@ static const struct file_operations media_devnode_fops = {
 	.llseek = no_llseek,
 };
 
-int __must_check media_devnode_register(struct media_devnode *mdev,
+int __must_check media_devnode_register(struct media_device *mdev,
+					struct media_devnode *devnode,
 					struct module *owner)
 {
 	int minor;
@@ -231,61 +233,80 @@ int __must_check media_devnode_register(struct media_devnode *mdev,
 	if (minor == MEDIA_NUM_DEVICES) {
 		mutex_unlock(&media_devnode_lock);
 		pr_err("could not get a free minor\n");
+		kfree(devnode);
 		return -ENFILE;
 	}
 
 	set_bit(minor, media_devnode_nums);
 	mutex_unlock(&media_devnode_lock);
 
-	mdev->minor = minor;
+	devnode->minor = minor;
+	devnode->media_dev = mdev;
+
+	/* Part 1: Initialize dev now to use dev.kobj for cdev.kobj.parent */
+	devnode->dev.bus = &media_bus_type;
+	devnode->dev.devt = MKDEV(MAJOR(media_dev_t), devnode->minor);
+	devnode->dev.release = media_devnode_release;
+	if (devnode->parent)
+		devnode->dev.parent = devnode->parent;
+	dev_set_name(&devnode->dev, "media%d", devnode->minor);
+	device_initialize(&devnode->dev);
 
 	/* Part 2: Initialize and register the character device */
-	cdev_init(&mdev->cdev, &media_devnode_fops);
-	mdev->cdev.owner = owner;
+	cdev_init(&devnode->cdev, &media_devnode_fops);
+	devnode->cdev.owner = owner;
+	devnode->cdev.kobj.parent = &devnode->dev.kobj;
 
-	ret = cdev_add(&mdev->cdev, MKDEV(MAJOR(media_dev_t), mdev->minor), 1);
+	ret = cdev_add(&devnode->cdev, MKDEV(MAJOR(media_dev_t), devnode->minor), 1);
 	if (ret < 0) {
 		pr_err("%s: cdev_add failed\n", __func__);
-		goto error;
+		goto cdev_add_error;
 	}
 
-	/* Part 3: Register the media device */
-	mdev->dev.bus = &media_bus_type;
-	mdev->dev.devt = MKDEV(MAJOR(media_dev_t), mdev->minor);
-	mdev->dev.release = media_devnode_release;
-	if (mdev->parent)
-		mdev->dev.parent = mdev->parent;
-	dev_set_name(&mdev->dev, "media%d", mdev->minor);
-	ret = device_register(&mdev->dev);
+	/* Part 3: Add the media device */
+	ret = device_add(&devnode->dev);
 	if (ret < 0) {
-		pr_err("%s: device_register failed\n", __func__);
-		goto error;
+		pr_err("%s: device_add failed\n", __func__);
+		goto device_add_error;
 	}
 
 	/* Part 4: Activate this minor. The char device can now be used. */
-	set_bit(MEDIA_FLAG_REGISTERED, &mdev->flags);
+	set_bit(MEDIA_FLAG_REGISTERED, &devnode->flags);
 
 	return 0;
 
-error:
+device_add_error:
+	cdev_del(&devnode->cdev);
+cdev_add_error:
 	mutex_lock(&media_devnode_lock);
-	cdev_del(&mdev->cdev);
-	clear_bit(mdev->minor, media_devnode_nums);
+	clear_bit(devnode->minor, media_devnode_nums);
+	devnode->media_dev = NULL;
 	mutex_unlock(&media_devnode_lock);
 
+	put_device(&devnode->dev);
 	return ret;
 }
 
-void media_devnode_unregister(struct media_devnode *mdev)
+void media_devnode_unregister_prepare(struct media_devnode *devnode)
 {
-	/* Check if mdev was ever registered at all */
-	if (!media_devnode_is_registered(mdev))
+	/* Check if devnode was ever registered at all */
+	if (!media_devnode_is_registered(devnode))
 		return;
 
 	mutex_lock(&media_devnode_lock);
-	clear_bit(MEDIA_FLAG_REGISTERED, &mdev->flags);
+	clear_bit(MEDIA_FLAG_REGISTERED, &devnode->flags);
+	mutex_unlock(&media_devnode_lock);
+}
+
+void media_devnode_unregister(struct media_devnode *devnode)
+{
+	mutex_lock(&media_devnode_lock);
+	/* Delete the cdev on this minor as well */
+	cdev_del(&devnode->cdev);
 	mutex_unlock(&media_devnode_lock);
-	device_unregister(&mdev->dev);
+	device_del(&devnode->dev);
+	devnode->media_dev = NULL;
+	put_device(&devnode->dev);
 }
 
 /*
diff --git a/drivers/media/pci/bt8xx/dst_ca.c b/drivers/media/pci/bt8xx/dst_ca.c
index da8b414fd824..8681b9143a35 100644
--- a/drivers/media/pci/bt8xx/dst_ca.c
+++ b/drivers/media/pci/bt8xx/dst_ca.c
@@ -655,7 +655,6 @@ static long dst_ca_ioctl(struct file *file, unsigned int cmd, unsigned long ioct
 static int dst_ca_open(struct inode *inode, struct file *file)
 {
 	dprintk(verbose, DST_CA_DEBUG, 1, " Device opened [%p] ", file);
-	try_module_get(THIS_MODULE);
 
 	return 0;
 }
@@ -663,7 +662,6 @@ static int dst_ca_open(struct inode *inode, struct file *file)
 static int dst_ca_release(struct inode *inode, struct file *file)
 {
 	dprintk(verbose, DST_CA_DEBUG, 1, " Device closed.");
-	module_put(THIS_MODULE);
 
 	return 0;
 }
diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c
index 8d6f04fc8013..476f7f0dcf81 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.c
+++ b/drivers/media/pci/cobalt/cobalt-driver.c
@@ -492,7 +492,6 @@ static int cobalt_subdevs_init(struct cobalt *cobalt)
 		.ain_sel = ADV7604_AIN7_8_9_NC_SYNC_3_1,
 		.bus_order = ADV7604_BUS_ORDER_BRG,
 		.blank_data = 1,
-		.op_656_range = 1,
 		.op_format_mode_sel = ADV7604_OP_FORMAT_MODE0,
 		.int1_config = ADV76XX_INT1_CONFIG_ACTIVE_HIGH,
 		.dr_str_data = ADV76XX_DR_STR_HIGH,
@@ -571,7 +570,6 @@ static int cobalt_subdevs_hsma_init(struct cobalt *cobalt)
 		.bus_order = ADV7842_BUS_ORDER_RBG,
 		.op_format_mode_sel = ADV7842_OP_FORMAT_MODE0,
 		.blank_data = 1,
-		.op_656_range = 1,
 		.dr_str_data = 3,
 		.dr_str_clk = 3,
 		.dr_str_sync = 3,
@@ -691,17 +689,10 @@ static int cobalt_probe(struct pci_dev *pci_dev,
 	cobalt->pci_dev = pci_dev;
 	cobalt->instance = i;
 
-	cobalt->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
-	if (IS_ERR(cobalt->alloc_ctx)) {
-		kfree(cobalt);
-		return -ENOMEM;
-	}
-
 	retval = v4l2_device_register(&pci_dev->dev, &cobalt->v4l2_dev);
 	if (retval) {
 		pr_err("cobalt: v4l2_device_register of card %d failed\n",
 				cobalt->instance);
-		vb2_dma_sg_cleanup_ctx(cobalt->alloc_ctx);
 		kfree(cobalt);
 		return retval;
 	}
@@ -782,7 +773,6 @@ err:
 	cobalt_err("error %d on initialization\n", retval);
 
 	v4l2_device_unregister(&cobalt->v4l2_dev);
-	vb2_dma_sg_cleanup_ctx(cobalt->alloc_ctx);
 	kfree(cobalt);
 	return retval;
 }
@@ -818,7 +808,6 @@ static void cobalt_remove(struct pci_dev *pci_dev)
 	cobalt_info("removed cobalt card\n");
 
 	v4l2_device_unregister(v4l2_dev);
-	vb2_dma_sg_cleanup_ctx(cobalt->alloc_ctx);
 	kfree(cobalt);
 }
 
diff --git a/drivers/media/pci/cobalt/cobalt-driver.h b/drivers/media/pci/cobalt/cobalt-driver.h
index b2f08e4a68bf..ed00dc9d9399 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.h
+++ b/drivers/media/pci/cobalt/cobalt-driver.h
@@ -262,7 +262,6 @@ struct cobalt {
 	int instance;
 	struct pci_dev *pci_dev;
 	struct v4l2_device v4l2_dev;
-	void *alloc_ctx;
 
 	void __iomem *bar0, *bar1;
 
diff --git a/drivers/media/pci/cobalt/cobalt-v4l2.c b/drivers/media/pci/cobalt/cobalt-v4l2.c
index c0ba458f6cf3..d05672fe9ff9 100644
--- a/drivers/media/pci/cobalt/cobalt-v4l2.c
+++ b/drivers/media/pci/cobalt/cobalt-v4l2.c
@@ -45,7 +45,7 @@ static const struct v4l2_dv_timings cea1080p60 = V4L2_DV_BT_CEA_1920X1080P60;
 
 static int cobalt_queue_setup(struct vb2_queue *q,
 			unsigned int *num_buffers, unsigned int *num_planes,
-			unsigned int sizes[], void *alloc_ctxs[])
+			unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cobalt_stream *s = q->drv_priv;
 	unsigned size = s->stride * s->height;
@@ -54,7 +54,6 @@ static int cobalt_queue_setup(struct vb2_queue *q,
 		*num_buffers = 3;
 	if (*num_buffers > NR_BUFS)
 		*num_buffers = NR_BUFS;
-	alloc_ctxs[0] = s->cobalt->alloc_ctx;
 	if (*num_planes)
 		return sizes[0] < size ? -EINVAL : 0;
 	*num_planes = 1;
@@ -1224,6 +1223,7 @@ static int cobalt_node_register(struct cobalt *cobalt, int node)
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->min_buffers_needed = 2;
 	q->lock = &s->lock;
+	q->dev = &cobalt->pci_dev->dev;
 	vdev->queue = q;
 
 	video_set_drvdata(vdev, s);
diff --git a/drivers/media/pci/cx18/cx18-alsa-mixer.c b/drivers/media/pci/cx18/cx18-alsa-mixer.c
index 341bddc00b77..284275270f1b 100644
--- a/drivers/media/pci/cx18/cx18-alsa-mixer.c
+++ b/drivers/media/pci/cx18/cx18-alsa-mixer.c
@@ -93,7 +93,7 @@ static int snd_cx18_mixer_tv_vol_get(struct snd_kcontrol *kctl,
 	vctrl.value = dB_to_cx18_av_vol(uctl->value.integer.value[0]);
 
 	snd_cx18_lock(cxsc);
-	ret = v4l2_subdev_call(cx->sd_av, core, g_ctrl, &vctrl);
+	ret = v4l2_g_ctrl(cx->sd_av->ctrl_handler, &vctrl);
 	snd_cx18_unlock(cxsc);
 
 	if (!ret)
@@ -115,14 +115,14 @@ static int snd_cx18_mixer_tv_vol_put(struct snd_kcontrol *kctl,
 	snd_cx18_lock(cxsc);
 
 	/* Fetch current state */
-	ret = v4l2_subdev_call(cx->sd_av, core, g_ctrl, &vctrl);
+	ret = v4l2_g_ctrl(cx->sd_av->ctrl_handler, &vctrl);
 
 	if (ret ||
 	    (cx18_av_vol_to_dB(vctrl.value) != uctl->value.integer.value[0])) {
 
 		/* Set, if needed */
 		vctrl.value = dB_to_cx18_av_vol(uctl->value.integer.value[0]);
-		ret = v4l2_subdev_call(cx->sd_av, core, s_ctrl, &vctrl);
+		ret = v4l2_s_ctrl(cx->sd_av->ctrl_handler, &vctrl);
 		if (!ret)
 			ret = 1; /* Indicate control was changed w/o error */
 	}
diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 260e462d91b4..2f23b26b16c0 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -560,7 +560,7 @@ static void cx18_process_options(struct cx18 *cx)
 	cx->stream_buf_size[CX18_ENC_STREAM_TYPE_MPG] = enc_mpg_bufsize;
 	cx->stream_buf_size[CX18_ENC_STREAM_TYPE_IDX] = enc_idx_bufsize;
 	cx->stream_buf_size[CX18_ENC_STREAM_TYPE_YUV] = enc_yuv_bufsize;
-	cx->stream_buf_size[CX18_ENC_STREAM_TYPE_VBI] = vbi_active_samples * 36;
+	cx->stream_buf_size[CX18_ENC_STREAM_TYPE_VBI] = VBI_ACTIVE_SAMPLES * 36;
 	cx->stream_buf_size[CX18_ENC_STREAM_TYPE_PCM] = enc_pcm_bufsize;
 	cx->stream_buf_size[CX18_ENC_STREAM_TYPE_RAD] = 0; /* control no data */
 
diff --git a/drivers/media/pci/cx18/cx18-driver.h b/drivers/media/pci/cx18/cx18-driver.h
index 47ce80fa73b9..ef308a10e870 100644
--- a/drivers/media/pci/cx18/cx18-driver.h
+++ b/drivers/media/pci/cx18/cx18-driver.h
@@ -492,9 +492,9 @@ struct cx18_card;
  *  (1/15.625 kHz) * 2 * 13.5 MHz = 1728 samples/line =
  *  4 bytes SAV + 280 bytes anc data + 4 bytes SAV + 1440 active samples
  */
-static const u32 vbi_active_samples = 1444; /* 4 byte SAV + 720 Y + 720 U/V */
-static const u32 vbi_hblank_samples_60Hz = 272; /* 4 byte EAV + 268 anc/fill */
-static const u32 vbi_hblank_samples_50Hz = 284; /* 4 byte EAV + 280 anc/fill */
+#define VBI_ACTIVE_SAMPLES	1444 /* 4 byte SAV + 720 Y + 720 U/V */
+#define VBI_HBLANK_SAMPLES_60HZ	272 /* 4 byte EAV + 268 anc/fill */
+#define VBI_HBLANK_SAMPLES_50HZ	284 /* 4 byte EAV + 280 anc/fill */
 
 #define CX18_VBI_FRAMES 32
 
diff --git a/drivers/media/pci/cx18/cx18-ioctl.c b/drivers/media/pci/cx18/cx18-ioctl.c
index eeb741c7db1b..fecca2a63891 100644
--- a/drivers/media/pci/cx18/cx18-ioctl.c
+++ b/drivers/media/pci/cx18/cx18-ioctl.c
@@ -177,7 +177,7 @@ static int cx18_g_fmt_vbi_cap(struct file *file, void *fh,
 
 	vbifmt->sampling_rate = 27000000;
 	vbifmt->offset = 248; /* FIXME - slightly wrong for both 50 & 60 Hz */
-	vbifmt->samples_per_line = vbi_active_samples - 4;
+	vbifmt->samples_per_line = VBI_ACTIVE_SAMPLES - 4;
 	vbifmt->sample_format = V4L2_PIX_FMT_GREY;
 	vbifmt->start[0] = cx->vbi.start[0];
 	vbifmt->start[1] = cx->vbi.start[1];
diff --git a/drivers/media/pci/cx18/cx18-streams.c b/drivers/media/pci/cx18/cx18-streams.c
index c9860845264f..f3802ec1b383 100644
--- a/drivers/media/pci/cx18/cx18-streams.c
+++ b/drivers/media/pci/cx18/cx18-streams.c
@@ -605,9 +605,9 @@ static void cx18_vbi_setup(struct cx18_stream *s)
 	/* Lines per field */
 	data[1] = (lines / 2) | ((lines / 2) << 16);
 	/* bytes per line */
-	data[2] = (raw ? vbi_active_samples
-		       : (cx->is_60hz ? vbi_hblank_samples_60Hz
-				      : vbi_hblank_samples_50Hz));
+	data[2] = (raw ? VBI_ACTIVE_SAMPLES
+		       : (cx->is_60hz ? VBI_HBLANK_SAMPLES_60HZ
+				      : VBI_HBLANK_SAMPLES_50HZ));
 	/* Every X number of frames a VBI interrupt arrives
 	   (frames as in 25 or 30 fps) */
 	data[3] = 1;
@@ -761,7 +761,7 @@ static void cx18_stream_configure_mdls(struct cx18_stream *s)
 		s->bufs_per_mdl = 1;
 		if  (cx18_raw_vbi(s->cx)) {
 			s->mdl_size = (s->cx->is_60hz ? 12 : 18)
-						       * 2 * vbi_active_samples;
+						       * 2 * VBI_ACTIVE_SAMPLES;
 		} else {
 			/*
 			 * See comment in cx18_vbi_setup() below about the
@@ -769,8 +769,8 @@ static void cx18_stream_configure_mdls(struct cx18_stream *s)
 			 * the lines on which EAV RP codes toggle.
 			*/
 			s->mdl_size = s->cx->is_60hz
-				   ? (21 - 4 + 1) * 2 * vbi_hblank_samples_60Hz
-				   : (23 - 2 + 1) * 2 * vbi_hblank_samples_50Hz;
+				   ? (21 - 4 + 1) * 2 * VBI_HBLANK_SAMPLES_60HZ
+				   : (23 - 2 + 1) * 2 * VBI_HBLANK_SAMPLES_50HZ;
 		}
 		break;
 	default:
diff --git a/drivers/media/pci/cx18/cx18-vbi.c b/drivers/media/pci/cx18/cx18-vbi.c
index add99642f1e2..43360cbcf24b 100644
--- a/drivers/media/pci/cx18/cx18-vbi.c
+++ b/drivers/media/pci/cx18/cx18-vbi.c
@@ -108,7 +108,7 @@ static void copy_vbi_data(struct cx18 *cx, int lines, u32 pts_stamp)
 /* FIXME - this function ignores the input size. */
 static u32 compress_raw_buf(struct cx18 *cx, u8 *buf, u32 size, u32 hdr_size)
 {
-	u32 line_size = vbi_active_samples;
+	u32 line_size = VBI_ACTIVE_SAMPLES;
 	u32 lines = cx->vbi.count * 2;
 	u8 *q = buf;
 	u8 *p;
@@ -145,8 +145,8 @@ static u32 compress_sliced_buf(struct cx18 *cx, u8 *buf, u32 size,
 	struct v4l2_decode_vbi_line vbi;
 	int i;
 	u32 line = 0;
-	u32 line_size = cx->is_60hz ? vbi_hblank_samples_60Hz
-				    : vbi_hblank_samples_50Hz;
+	u32 line_size = cx->is_60hz ? VBI_HBLANK_SAMPLES_60HZ
+				    : VBI_HBLANK_SAMPLES_50HZ;
 
 	/* find the first valid line */
 	for (i = hdr_size, buf += hdr_size; i < size; i++, buf++) {
diff --git a/drivers/media/pci/cx23885/cx23885-417.c b/drivers/media/pci/cx23885/cx23885-417.c
index bd333875a1f7..efec2d1a7afd 100644
--- a/drivers/media/pci/cx23885/cx23885-417.c
+++ b/drivers/media/pci/cx23885/cx23885-417.c
@@ -1140,7 +1140,7 @@ static int cx23885_initialize_codec(struct cx23885_dev *dev, int startencoder)
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx23885_dev *dev = q->drv_priv;
 
@@ -1148,7 +1148,6 @@ static int queue_setup(struct vb2_queue *q,
 	dev->ts1.ts_packet_count = mpeglines;
 	*num_planes = 1;
 	sizes[0] = mpeglinesize * mpeglines;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	*num_buffers = mpegbufs;
 	return 0;
 }
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index 310ee769aed4..4abf50f2694f 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -765,6 +765,11 @@ struct cx23885_board cx23885_boards[] = {
 			.amux   = CX25840_AUDIO7,
 		} },
 	},
+	[CX23885_BOARD_HAUPPAUGE_QUADHD_DVB] = {
+		.name        = "Hauppauge WinTV-QuadHD-DVB",
+		.portb        = CX23885_MPEG_DVB,
+		.portc        = CX23885_MPEG_DVB,
+	},
 };
 const unsigned int cx23885_bcount = ARRAY_SIZE(cx23885_boards);
 
@@ -1060,6 +1065,14 @@ struct cx23885_subid cx23885_subids[] = {
 		.subvendor = 0x1576,
 		.subdevice = 0x0460,
 		.card      = CX23885_BOARD_VIEWCAST_460E,
+	}, {
+		.subvendor = 0x0070,
+		.subdevice = 0x6a28,
+		.card      = CX23885_BOARD_HAUPPAUGE_QUADHD_DVB, /* Tuner Pair 1 */
+	}, {
+		.subvendor = 0x0070,
+		.subdevice = 0x6b28,
+		.card      = CX23885_BOARD_HAUPPAUGE_QUADHD_DVB, /* Tuner Pair 2 */
 	},
 };
 const unsigned int cx23885_idcount = ARRAY_SIZE(cx23885_subids);
@@ -1257,6 +1270,14 @@ static void hauppauge_eeprom(struct cx23885_dev *dev, u8 *eeprom_data)
 	case 150329:
 		/* WinTV-HVR5525 (PCIe, DVB-S/S2, DVB-T/T2/C) */
 		break;
+	case 166100:
+		/* WinTV-QuadHD (DVB) Tuner Pair 1 (PCIe, IR, half height,
+		   DVB-T/T2/C, DVB-T/T2/C */
+		break;
+	case 166101:
+		/* WinTV-QuadHD (DVB) Tuner Pair 2 (PCIe, IR, half height,
+		   DVB-T/T2/C, DVB-T/T2/C */
+		break;
 	default:
 		printk(KERN_WARNING "%s: warning: "
 			"unknown hauppauge model #%d\n",
@@ -1729,20 +1750,22 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx23885_gpio_set(dev, GPIO_2);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR5525:
+	case CX23885_BOARD_HAUPPAUGE_QUADHD_DVB:
 		/*
-		 * GPIO-00 IR_WIDE
-		 * GPIO-02 wake#
-		 * GPIO-03 VAUX Pres.
-		 * GPIO-07 PROG#
-		 * GPIO-08 SAT_RESN
-		 * GPIO-09 TER_RESN
-		 * GPIO-10 B2_SENSE
-		 * GPIO-11 B1_SENSE
-		 * GPIO-15 IR_LED_STATUS
-		 * GPIO-19 IR_NARROW
-		 * GPIO-20 Blauster1
-		 * ALTGPIO VAUX_SWITCH
-		 * AUX_PLL_CLK : Blaster2
+		 * HVR5525 GPIO Details:
+		 *  GPIO-00 IR_WIDE
+		 *  GPIO-02 wake#
+		 *  GPIO-03 VAUX Pres.
+		 *  GPIO-07 PROG#
+		 *  GPIO-08 SAT_RESN
+		 *  GPIO-09 TER_RESN
+		 *  GPIO-10 B2_SENSE
+		 *  GPIO-11 B1_SENSE
+		 *  GPIO-15 IR_LED_STATUS
+		 *  GPIO-19 IR_NARROW
+		 *  GPIO-20 Blauster1
+		 *  ALTGPIO VAUX_SWITCH
+		 *  AUX_PLL_CLK : Blaster2
 		 */
 		/* Put the parts into reset and back */
 		cx23885_gpio_enable(dev, GPIO_8 | GPIO_9, 1);
@@ -1802,6 +1825,7 @@ int cx23885_ir_init(struct cx23885_dev *dev)
 	case CX23885_BOARD_HAUPPAUGE_HVR1255:
 	case CX23885_BOARD_HAUPPAUGE_HVR1255_22111:
 	case CX23885_BOARD_HAUPPAUGE_HVR1210:
+	case CX23885_BOARD_HAUPPAUGE_QUADHD_DVB:
 		/* FIXME: Implement me */
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1270:
@@ -2000,6 +2024,7 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 	case CX23885_BOARD_HAUPPAUGE_STARBURST:
 	case CX23885_BOARD_HAUPPAUGE_IMPACTVCBE:
 	case CX23885_BOARD_HAUPPAUGE_HVR5525:
+	case CX23885_BOARD_HAUPPAUGE_QUADHD_DVB:
 		if (dev->i2c_bus[0].i2c_rc == 0)
 			hauppauge_eeprom(dev, eeprom+0xc0);
 		break;
@@ -2145,6 +2170,14 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 		ts2->ts_clk_en_val = 0x1; /* Enable TS_CLK */
 		ts2->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
 		break;
+	case CX23885_BOARD_HAUPPAUGE_QUADHD_DVB:
+		ts1->gen_ctrl_val  = 0xc; /* Serial bus + punctured clock */
+		ts1->ts_clk_en_val = 0x1; /* Enable TS_CLK */
+		ts1->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
+		ts2->gen_ctrl_val  = 0xc; /* Serial bus + punctured clock */
+		ts2->ts_clk_en_val = 0x1; /* Enable TS_CLK */
+		ts2->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
+		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1250:
 	case CX23885_BOARD_HAUPPAUGE_HVR1500:
 	case CX23885_BOARD_HAUPPAUGE_HVR1500Q:
diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index 813c217b5e1a..c86b1093ab99 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -2005,14 +2005,9 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 	err = pci_set_dma_mask(pci_dev, 0xffffffff);
 	if (err) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
-		goto fail_context;
+		goto fail_ctrl;
 	}
 
-	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		err = PTR_ERR(dev->alloc_ctx);
-		goto fail_context;
-	}
 	err = request_irq(pci_dev->irq, cx23885_irq,
 			  IRQF_SHARED, dev->name, dev);
 	if (err < 0) {
@@ -2041,8 +2036,6 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 	return 0;
 
 fail_irq:
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
-fail_context:
 	cx23885_dev_unregister(dev);
 fail_ctrl:
 	v4l2_ctrl_handler_free(hdl);
@@ -2068,7 +2061,6 @@ static void cx23885_finidev(struct pci_dev *pci_dev)
 	pci_disable_device(pci_dev);
 
 	cx23885_dev_unregister(dev);
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	v4l2_ctrl_handler_free(&dev->ctrl_handler);
 	v4l2_device_unregister(v4l2_dev);
 	kfree(dev);
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index f041b6931ba8..e5748a93c479 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -94,7 +94,7 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx23885_tsport *port = q->drv_priv;
 
@@ -102,7 +102,6 @@ static int queue_setup(struct vb2_queue *q,
 	port->ts_packet_count = 32;
 	*num_planes = 1;
 	sizes[0] = port->ts_packet_size * port->ts_packet_count;
-	alloc_ctxs[0] = port->dev->alloc_ctx;
 	*num_buffers = 32;
 	return 0;
 }
@@ -2269,9 +2268,107 @@ static int dvb_register(struct cx23885_tsport *port)
 		}
 		break;
 	}
+	case CX23885_BOARD_HAUPPAUGE_QUADHD_DVB:
+		switch (port->nr) {
+		/* port b - Terrestrial/cable */
+		case 1:
+			/* attach frontend */
+			memset(&si2168_config, 0, sizeof(si2168_config));
+			si2168_config.i2c_adapter = &adapter;
+			si2168_config.fe = &fe0->dvb.frontend;
+			si2168_config.ts_mode = SI2168_TS_SERIAL;
+			memset(&info, 0, sizeof(struct i2c_board_info));
+			strlcpy(info.type, "si2168", I2C_NAME_SIZE);
+			info.addr = 0x64;
+			info.platform_data = &si2168_config;
+			request_module("%s", info.type);
+			client_demod = i2c_new_device(&dev->i2c_bus[0].i2c_adap, &info);
+			if (!client_demod || !client_demod->dev.driver)
+				goto frontend_detach;
+			if (!try_module_get(client_demod->dev.driver->owner)) {
+				i2c_unregister_device(client_demod);
+				goto frontend_detach;
+			}
+			port->i2c_client_demod = client_demod;
+
+			/* attach tuner */
+			memset(&si2157_config, 0, sizeof(si2157_config));
+			si2157_config.fe = fe0->dvb.frontend;
+			si2157_config.if_port = 1;
+			memset(&info, 0, sizeof(struct i2c_board_info));
+			strlcpy(info.type, "si2157", I2C_NAME_SIZE);
+			info.addr = 0x60;
+			info.platform_data = &si2157_config;
+			request_module("%s", info.type);
+			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!client_tuner || !client_tuner->dev.driver) {
+				module_put(client_demod->dev.driver->owner);
+				i2c_unregister_device(client_demod);
+				port->i2c_client_demod = NULL;
+				goto frontend_detach;
+			}
+			if (!try_module_get(client_tuner->dev.driver->owner)) {
+				i2c_unregister_device(client_tuner);
+				module_put(client_demod->dev.driver->owner);
+				i2c_unregister_device(client_demod);
+				port->i2c_client_demod = NULL;
+				goto frontend_detach;
+			}
+			port->i2c_client_tuner = client_tuner;
+			break;
+
+		/* port c - terrestrial/cable */
+		case 2:
+			/* attach frontend */
+			memset(&si2168_config, 0, sizeof(si2168_config));
+			si2168_config.i2c_adapter = &adapter;
+			si2168_config.fe = &fe0->dvb.frontend;
+			si2168_config.ts_mode = SI2168_TS_SERIAL;
+			memset(&info, 0, sizeof(struct i2c_board_info));
+			strlcpy(info.type, "si2168", I2C_NAME_SIZE);
+			info.addr = 0x66;
+			info.platform_data = &si2168_config;
+			request_module("%s", info.type);
+			client_demod = i2c_new_device(&dev->i2c_bus[0].i2c_adap, &info);
+			if (!client_demod || !client_demod->dev.driver)
+				goto frontend_detach;
+			if (!try_module_get(client_demod->dev.driver->owner)) {
+				i2c_unregister_device(client_demod);
+				goto frontend_detach;
+			}
+			port->i2c_client_demod = client_demod;
+
+			/* attach tuner */
+			memset(&si2157_config, 0, sizeof(si2157_config));
+			si2157_config.fe = fe0->dvb.frontend;
+			si2157_config.if_port = 1;
+			memset(&info, 0, sizeof(struct i2c_board_info));
+			strlcpy(info.type, "si2157", I2C_NAME_SIZE);
+			info.addr = 0x62;
+			info.platform_data = &si2157_config;
+			request_module("%s", info.type);
+			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!client_tuner || !client_tuner->dev.driver) {
+				module_put(client_demod->dev.driver->owner);
+				i2c_unregister_device(client_demod);
+				port->i2c_client_demod = NULL;
+				goto frontend_detach;
+			}
+			if (!try_module_get(client_tuner->dev.driver->owner)) {
+				i2c_unregister_device(client_tuner);
+				module_put(client_demod->dev.driver->owner);
+				i2c_unregister_device(client_demod);
+				port->i2c_client_demod = NULL;
+				goto frontend_detach;
+			}
+			port->i2c_client_tuner = client_tuner;
+			break;
+		}
+		break;
+
 	default:
 		printk(KERN_INFO "%s: The frontend of your DVB/ATSC card "
-			" isn't supported yet\n",
+		       " isn't supported yet\n",
 		       dev->name);
 		break;
 	}
@@ -2397,6 +2494,7 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 		q->mem_ops = &vb2_dma_sg_memops;
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		q->lock = &dev->lock;
+		q->dev = &dev->pci->dev;
 
 		err = vb2_queue_init(q);
 		if (err < 0)
diff --git a/drivers/media/pci/cx23885/cx23885-vbi.c b/drivers/media/pci/cx23885/cx23885-vbi.c
index 39750ebcc04c..75e7fa7b1121 100644
--- a/drivers/media/pci/cx23885/cx23885-vbi.c
+++ b/drivers/media/pci/cx23885/cx23885-vbi.c
@@ -122,7 +122,7 @@ static int cx23885_start_vbi_dma(struct cx23885_dev    *dev,
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx23885_dev *dev = q->drv_priv;
 	unsigned lines = VBI_PAL_LINE_COUNT;
@@ -131,7 +131,6 @@ static int queue_setup(struct vb2_queue *q,
 		lines = VBI_NTSC_LINE_COUNT;
 	*num_planes = 1;
 	sizes[0] = lines * VBI_LINE_LENGTH * 2;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c
index e1d7d0847167..6d735222a958 100644
--- a/drivers/media/pci/cx23885/cx23885-video.c
+++ b/drivers/media/pci/cx23885/cx23885-video.c
@@ -335,13 +335,12 @@ static int cx23885_start_video_dma(struct cx23885_dev *dev,
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx23885_dev *dev = q->drv_priv;
 
 	*num_planes = 1;
 	sizes[0] = (dev->fmt->depth * dev->width * dev->height) >> 3;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
@@ -1268,6 +1267,7 @@ int cx23885_video_register(struct cx23885_dev *dev)
 	q->mem_ops = &vb2_dma_sg_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &dev->lock;
+	q->dev = &dev->pci->dev;
 
 	err = vb2_queue_init(q);
 	if (err < 0)
@@ -1284,6 +1284,7 @@ int cx23885_video_register(struct cx23885_dev *dev)
 	q->mem_ops = &vb2_dma_sg_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &dev->lock;
+	q->dev = &dev->pci->dev;
 
 	err = vb2_queue_init(q);
 	if (err < 0)
diff --git a/drivers/media/pci/cx23885/cx23885.h b/drivers/media/pci/cx23885/cx23885.h
index b1a5409408c7..24a0a6c5b501 100644
--- a/drivers/media/pci/cx23885/cx23885.h
+++ b/drivers/media/pci/cx23885/cx23885.h
@@ -103,6 +103,7 @@
 #define CX23885_BOARD_HAUPPAUGE_STARBURST      53
 #define CX23885_BOARD_VIEWCAST_260E            54
 #define CX23885_BOARD_VIEWCAST_460E            55
+#define CX23885_BOARD_HAUPPAUGE_QUADHD_DVB    56
 
 #define GPIO_0 0x00000001
 #define GPIO_1 0x00000002
@@ -430,7 +431,6 @@ struct cx23885_dev {
 	struct vb2_queue           vb2_vidq;
 	struct cx23885_dmaqueue    vbiq;
 	struct vb2_queue           vb2_vbiq;
-	void			   *alloc_ctx;
 
 	spinlock_t                 slock;
 
diff --git a/drivers/media/pci/cx25821/cx25821-alsa.c b/drivers/media/pci/cx25821/cx25821-alsa.c
index b602eba2b601..df189b16af12 100644
--- a/drivers/media/pci/cx25821/cx25821-alsa.c
+++ b/drivers/media/pci/cx25821/cx25821-alsa.c
@@ -693,7 +693,7 @@ static int snd_cx25821_pcm(struct cx25821_audio_dev *chip, int device,
  * Only boards with eeprom and byte 1 at eeprom=1 have it
  */
 
-static const struct pci_device_id cx25821_audio_pci_tbl[] = {
+static const struct pci_device_id __maybe_unused cx25821_audio_pci_tbl[] = {
 	{0x14f1, 0x0920, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{0,}
 };
diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c
index 0042803a9de7..9a5f912ca859 100644
--- a/drivers/media/pci/cx25821/cx25821-core.c
+++ b/drivers/media/pci/cx25821/cx25821-core.c
@@ -1301,15 +1301,10 @@ static int cx25821_initdev(struct pci_dev *pci_dev,
 
 		goto fail_unregister_device;
 	}
-	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		err = PTR_ERR(dev->alloc_ctx);
-		goto fail_unregister_pci;
-	}
 
 	err = cx25821_dev_setup(dev);
 	if (err)
-		goto fail_free_ctx;
+		goto fail_unregister_pci;
 
 	/* print pci info */
 	pci_read_config_byte(pci_dev, PCI_CLASS_REVISION, &dev->pci_rev);
@@ -1340,8 +1335,6 @@ fail_irq:
 	pr_info("cx25821_initdev() can't get IRQ !\n");
 	cx25821_dev_unregister(dev);
 
-fail_free_ctx:
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 fail_unregister_pci:
 	pci_disable_device(pci_dev);
 fail_unregister_device:
@@ -1365,7 +1358,6 @@ static void cx25821_finidev(struct pci_dev *pci_dev)
 		free_irq(pci_dev->irq, dev);
 
 	cx25821_dev_unregister(dev);
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	v4l2_device_unregister(v4l2_dev);
 	kfree(dev);
 }
diff --git a/drivers/media/pci/cx25821/cx25821-video.c b/drivers/media/pci/cx25821/cx25821-video.c
index c48bba9daf1f..adcd09be347d 100644
--- a/drivers/media/pci/cx25821/cx25821-video.c
+++ b/drivers/media/pci/cx25821/cx25821-video.c
@@ -143,13 +143,11 @@ int cx25821_video_irq(struct cx25821_dev *dev, int chan_num, u32 status)
 
 static int cx25821_queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx25821_channel *chan = q->drv_priv;
 	unsigned size = (chan->fmt->depth * chan->width * chan->height) >> 3;
 
-	alloc_ctxs[0] = chan->dev->alloc_ctx;
-
 	if (*num_planes)
 		return sizes[0] < size ? -EINVAL : 0;
 
@@ -759,6 +757,7 @@ int cx25821_video_register(struct cx25821_dev *dev)
 		q->mem_ops = &vb2_dma_sg_memops;
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		q->lock = &dev->lock;
+		q->dev = &dev->pci->dev;
 
 		if (!is_output) {
 			err = vb2_queue_init(q);
diff --git a/drivers/media/pci/cx25821/cx25821.h b/drivers/media/pci/cx25821/cx25821.h
index a513b68be0fa..35c7375e4617 100644
--- a/drivers/media/pci/cx25821/cx25821.h
+++ b/drivers/media/pci/cx25821/cx25821.h
@@ -249,7 +249,6 @@ struct cx25821_dev {
 	int hwrevision;
 	/* used by cx25821-alsa */
 	struct snd_card *card;
-	void *alloc_ctx;
 
 	u32 clk_freq;
 
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index e158a1da1d41..f3f13eb0c16e 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -799,13 +799,9 @@ static int snd_cx88_alc_put(struct snd_kcontrol *kcontrol,
 {
 	snd_cx88_card_t *chip = snd_kcontrol_chip(kcontrol);
 	struct cx88_core *core = chip->core;
-	struct v4l2_control client_ctl;
-
-	memset(&client_ctl, 0, sizeof(client_ctl));
-	client_ctl.value = 0 != value->value.integer.value[0];
-	client_ctl.id = V4L2_CID_AUDIO_LOUDNESS;
-	call_hw(core, WM8775_GID, core, s_ctrl, &client_ctl);
 
+	wm8775_s_ctrl(core, V4L2_CID_AUDIO_LOUDNESS,
+		      value->value.integer.value[0] != 0);
 	return 0;
 }
 
diff --git a/drivers/media/pci/cx88/cx88-blackbird.c b/drivers/media/pci/cx88/cx88-blackbird.c
index 3233d45d1e5b..04fe9af2a802 100644
--- a/drivers/media/pci/cx88/cx88-blackbird.c
+++ b/drivers/media/pci/cx88/cx88-blackbird.c
@@ -639,7 +639,7 @@ static int blackbird_stop_codec(struct cx8802_dev *dev)
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx8802_dev *dev = q->drv_priv;
 
@@ -647,7 +647,6 @@ static int queue_setup(struct vb2_queue *q,
 	dev->ts_packet_size  = 188 * 4;
 	dev->ts_packet_count  = 32;
 	sizes[0] = dev->ts_packet_size * dev->ts_packet_count;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
@@ -1183,6 +1182,7 @@ static int cx8802_blackbird_probe(struct cx8802_driver *drv)
 	q->mem_ops = &vb2_dma_sg_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &core->lock;
+	q->dev = &dev->pci->dev;
 
 	err = vb2_queue_init(q);
 	if (err < 0)
diff --git a/drivers/media/pci/cx88/cx88-dvb.c b/drivers/media/pci/cx88/cx88-dvb.c
index 851d2a9caed3..5bb63e7a5691 100644
--- a/drivers/media/pci/cx88/cx88-dvb.c
+++ b/drivers/media/pci/cx88/cx88-dvb.c
@@ -84,7 +84,7 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx8802_dev *dev = q->drv_priv;
 
@@ -92,7 +92,6 @@ static int queue_setup(struct vb2_queue *q,
 	dev->ts_packet_size  = 188 * 4;
 	dev->ts_packet_count = dvb_buf_tscnt;
 	sizes[0] = dev->ts_packet_size * dev->ts_packet_count;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	*num_buffers = dvb_buf_tscnt;
 	return 0;
 }
@@ -1793,6 +1792,7 @@ static int cx8802_dvb_probe(struct cx8802_driver *drv)
 		q->mem_ops = &vb2_dma_sg_memops;
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		q->lock = &core->lock;
+		q->dev = &dev->pci->dev;
 
 		err = vb2_queue_init(q);
 		if (err < 0)
diff --git a/drivers/media/pci/cx88/cx88-mpeg.c b/drivers/media/pci/cx88/cx88-mpeg.c
index f34c229f9b37..245357adbc25 100644
--- a/drivers/media/pci/cx88/cx88-mpeg.c
+++ b/drivers/media/pci/cx88/cx88-mpeg.c
@@ -726,11 +726,6 @@ static int cx8802_probe(struct pci_dev *pci_dev,
 	if (NULL == dev)
 		goto fail_core;
 	dev->pci = pci_dev;
-	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		err = PTR_ERR(dev->alloc_ctx);
-		goto fail_dev;
-	}
 	dev->core = core;
 
 	/* Maintain a reference so cx88-video can query the 8802 device. */
@@ -738,7 +733,7 @@ static int cx8802_probe(struct pci_dev *pci_dev,
 
 	err = cx8802_init_common(dev);
 	if (err != 0)
-		goto fail_free;
+		goto fail_dev;
 
 	INIT_LIST_HEAD(&dev->drvlist);
 	mutex_lock(&cx8802_mutex);
@@ -749,8 +744,6 @@ static int cx8802_probe(struct pci_dev *pci_dev,
 	request_modules(dev);
 	return 0;
 
- fail_free:
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
  fail_dev:
 	kfree(dev);
  fail_core:
@@ -798,7 +791,6 @@ static void cx8802_remove(struct pci_dev *pci_dev)
 	/* common */
 	cx8802_fini_common(dev);
 	cx88_core_put(dev->core,dev->pci);
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	kfree(dev);
 }
 
diff --git a/drivers/media/pci/cx88/cx88-vbi.c b/drivers/media/pci/cx88/cx88-vbi.c
index ccc646d819f2..d3237cf8ffa3 100644
--- a/drivers/media/pci/cx88/cx88-vbi.c
+++ b/drivers/media/pci/cx88/cx88-vbi.c
@@ -109,7 +109,7 @@ int cx8800_restart_vbi_queue(struct cx8800_dev    *dev,
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx8800_dev *dev = q->drv_priv;
 
@@ -118,7 +118,6 @@ static int queue_setup(struct vb2_queue *q,
 		sizes[0] = VBI_LINE_NTSC_COUNT * VBI_LINE_LENGTH * 2;
 	else
 		sizes[0] = VBI_LINE_PAL_COUNT * VBI_LINE_LENGTH * 2;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index 5f331df65fb9..5dc1e3f08d50 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -431,14 +431,13 @@ static int restart_video_queue(struct cx8800_dev    *dev,
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cx8800_dev *dev = q->drv_priv;
 	struct cx88_core *core = dev->core;
 
 	*num_planes = 1;
 	sizes[0] = (dev->fmt->depth * core->width * core->height) >> 3;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
@@ -1319,12 +1318,6 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n",core->name);
 		goto fail_core;
 	}
-	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		err = PTR_ERR(dev->alloc_ctx);
-		goto fail_core;
-	}
-
 
 	/* initialize driver struct */
 	spin_lock_init(&dev->slock);
@@ -1445,6 +1438,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 	q->mem_ops = &vb2_dma_sg_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &core->lock;
+	q->dev = &dev->pci->dev;
 
 	err = vb2_queue_init(q);
 	if (err < 0)
@@ -1461,6 +1455,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 	q->mem_ops = &vb2_dma_sg_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &core->lock;
+	q->dev = &dev->pci->dev;
 
 	err = vb2_queue_init(q);
 	if (err < 0)
@@ -1530,7 +1525,6 @@ fail_unreg:
 	free_irq(pci_dev->irq, dev);
 	mutex_unlock(&core->lock);
 fail_core:
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	core->v4ldev = NULL;
 	cx88_core_put(core,dev->pci);
 fail_free:
@@ -1564,7 +1558,6 @@ static void cx8800_finidev(struct pci_dev *pci_dev)
 
 	/* free memory */
 	cx88_core_put(core,dev->pci);
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	kfree(dev);
 }
 
diff --git a/drivers/media/pci/cx88/cx88.h b/drivers/media/pci/cx88/cx88.h
index 78f817ee7e41..ecd4b7bece99 100644
--- a/drivers/media/pci/cx88/cx88.h
+++ b/drivers/media/pci/cx88/cx88.h
@@ -485,7 +485,6 @@ struct cx8800_dev {
 	/* pci i/o */
 	struct pci_dev             *pci;
 	unsigned char              pci_rev,pci_lat;
-	void			   *alloc_ctx;
 
 	const struct cx8800_fmt    *fmt;
 
@@ -549,7 +548,6 @@ struct cx8802_dev {
 	/* pci i/o */
 	struct pci_dev             *pci;
 	unsigned char              pci_rev,pci_lat;
-	void			   *alloc_ctx;
 
 	/* dma queues */
 	struct cx88_dmaqueue       mpegq;
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 6e995ef8c37e..47def73b3502 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1569,10 +1569,9 @@ static int ddb_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (pci_enable_device(pdev) < 0)
 		return -ENODEV;
 
-	dev = vmalloc(sizeof(struct ddb));
+	dev = vzalloc(sizeof(struct ddb));
 	if (dev == NULL)
 		return -ENOMEM;
-	memset(dev, 0, sizeof(struct ddb));
 
 	dev->pdev = pdev;
 	pci_set_drvdata(pdev, dev);
diff --git a/drivers/media/pci/dt3155/dt3155.c b/drivers/media/pci/dt3155/dt3155.c
index 568c0c8fb2dc..6a219694b225 100644
--- a/drivers/media/pci/dt3155/dt3155.c
+++ b/drivers/media/pci/dt3155/dt3155.c
@@ -133,7 +133,7 @@ static int wait_i2c_reg(void __iomem *addr)
 static int
 dt3155_queue_setup(struct vb2_queue *vq,
 		unsigned int *nbuffers, unsigned int *num_planes,
-		unsigned int sizes[], void *alloc_ctxs[])
+		unsigned int sizes[], struct device *alloc_devs[])
 
 {
 	struct dt3155_priv *pd = vb2_get_drv_priv(vq);
@@ -141,7 +141,6 @@ dt3155_queue_setup(struct vb2_queue *vq,
 
 	if (vq->num_buffers + *nbuffers < 2)
 		*nbuffers = 2 - vq->num_buffers;
-	alloc_ctxs[0] = pd->alloc_ctx;
 	if (*num_planes)
 		return sizes[0] < size ? -EINVAL : 0;
 	*num_planes = 1;
@@ -544,21 +543,16 @@ static int dt3155_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pd->vidq.min_buffers_needed = 2;
 	pd->vidq.gfp_flags = GFP_DMA32;
 	pd->vidq.lock = &pd->mux; /* for locking v4l2_file_operations */
+	pd->vidq.dev = &pdev->dev;
 	pd->vdev.queue = &pd->vidq;
 	err = vb2_queue_init(&pd->vidq);
 	if (err < 0)
 		goto err_v4l2_dev_unreg;
-	pd->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(pd->alloc_ctx)) {
-		dev_err(&pdev->dev, "Can't allocate buffer context");
-		err = PTR_ERR(pd->alloc_ctx);
-		goto err_v4l2_dev_unreg;
-	}
 	spin_lock_init(&pd->lock);
 	pd->config = ACQ_MODE_EVEN;
 	err = pci_enable_device(pdev);
 	if (err)
-		goto err_free_ctx;
+		goto err_v4l2_dev_unreg;
 	err = pci_request_region(pdev, 0, pci_name(pdev));
 	if (err)
 		goto err_pci_disable;
@@ -588,8 +582,6 @@ err_free_reg:
 	pci_release_region(pdev, 0);
 err_pci_disable:
 	pci_disable_device(pdev);
-err_free_ctx:
-	vb2_dma_contig_cleanup_ctx(pd->alloc_ctx);
 err_v4l2_dev_unreg:
 	v4l2_device_unregister(&pd->v4l2_dev);
 	return err;
@@ -608,7 +600,6 @@ static void dt3155_remove(struct pci_dev *pdev)
 	pci_iounmap(pdev, pd->regs);
 	pci_release_region(pdev, 0);
 	pci_disable_device(pdev);
-	vb2_dma_contig_cleanup_ctx(pd->alloc_ctx);
 }
 
 static const struct pci_device_id pci_ids[] = {
diff --git a/drivers/media/pci/dt3155/dt3155.h b/drivers/media/pci/dt3155/dt3155.h
index b3531e0bc733..39442e58919d 100644
--- a/drivers/media/pci/dt3155/dt3155.h
+++ b/drivers/media/pci/dt3155/dt3155.h
@@ -161,7 +161,6 @@
  * @vdev:		video_device structure
  * @pdev:		pointer to pci_dev structure
  * @vidq:		vb2_queue structure
- * @alloc_ctx:		dma_contig allocation context
  * @curr_buf:		pointer to curren buffer
  * @mux:		mutex to protect the instance
  * @dmaq:		queue for dma buffers
@@ -181,7 +180,6 @@ struct dt3155_priv {
 	struct video_device vdev;
 	struct pci_dev *pdev;
 	struct vb2_queue vidq;
-	struct vb2_alloc_ctx *alloc_ctx;
 	struct vb2_v4l2_buffer *curr_buf;
 	struct mutex mux;
 	struct list_head dmaq;
diff --git a/drivers/media/pci/ivtv/ivtv-alsa-mixer.c b/drivers/media/pci/ivtv/ivtv-alsa-mixer.c
index 33ec05b09af3..79b24bde4a39 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-mixer.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-mixer.c
@@ -93,7 +93,7 @@ static int snd_ivtv_mixer_tv_vol_get(struct snd_kcontrol *kctl,
 	vctrl.value = dB_to_cx25840_vol(uctl->value.integer.value[0]);
 
 	snd_ivtv_lock(itvsc);
-	ret = v4l2_subdev_call(itv->sd_audio, core, g_ctrl, &vctrl);
+	ret = v4l2_g_ctrl(itv->sd_audio->ctrl_handler, &vctrl);
 	snd_ivtv_unlock(itvsc);
 
 	if (!ret)
@@ -115,14 +115,14 @@ static int snd_ivtv_mixer_tv_vol_put(struct snd_kcontrol *kctl,
 	snd_ivtv_lock(itvsc);
 
 	/* Fetch current state */
-	ret = v4l2_subdev_call(itv->sd_audio, core, g_ctrl, &vctrl);
+	ret = v4l2_g_ctrl(itv->sd_audio->ctrl_handler, &vctrl);
 
 	if (ret ||
 	    (cx25840_vol_to_dB(vctrl.value) != uctl->value.integer.value[0])) {
 
 		/* Set, if needed */
 		vctrl.value = dB_to_cx25840_vol(uctl->value.integer.value[0]);
-		ret = v4l2_subdev_call(itv->sd_audio, core, s_ctrl, &vctrl);
+		ret = v4l2_s_ctrl(itv->sd_audio->ctrl_handler, &vctrl);
 		if (!ret)
 			ret = 1; /* Indicate control was changed w/o error */
 	}
diff --git a/drivers/media/pci/netup_unidvb/Kconfig b/drivers/media/pci/netup_unidvb/Kconfig
index f277b0b10c2d..0ad37714c7fd 100644
--- a/drivers/media/pci/netup_unidvb/Kconfig
+++ b/drivers/media/pci/netup_unidvb/Kconfig
@@ -5,8 +5,13 @@ config DVB_NETUP_UNIDVB
     select VIDEOBUF2_VMALLOC
 	select DVB_HORUS3A if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_ASCOT2E if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_HELENE if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_LNBH25 if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_CXD2841ER if MEDIA_SUBDRV_AUTOSELECT
 	---help---
 	  Support for NetUP PCI express Universal DVB card.
-
+     help
+	Say Y when you want to support NetUP Dual Universal DVB card
+	Card can receive two independent streams in following standards:
+		DVB-S/S2, T/T2, C/C2
+	Two CI slots available for CAM modules.
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb.h b/drivers/media/pci/netup_unidvb/netup_unidvb.h
index a67b28111905..39b08ecda1fc 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb.h
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb.h
@@ -50,6 +50,15 @@
 #define NETUP_UNIDVB_IRQ_CAM0	(1 << 11)
 #define NETUP_UNIDVB_IRQ_CAM1	(1 << 12)
 
+/* NetUP Universal DVB card hardware revisions and it's PCI device id's:
+ * 1.3 - CXD2841ER demod, ASCOT2E and HORUS3A tuners
+ * 1.4 - CXD2854ER demod, HELENE tuner
+*/
+enum netup_hw_rev {
+	NETUP_HW_REV_1_3 = 0x18F6,
+	NETUP_HW_REV_1_4 = 0x18F7
+};
+
 struct netup_dma {
 	u8			num;
 	spinlock_t		lock;
@@ -119,6 +128,7 @@ struct netup_unidvb_dev {
 	struct netup_dma		dma[2];
 	struct netup_ci_state		ci[2];
 	struct netup_spi		*spi;
+	enum netup_hw_rev		rev;
 };
 
 int netup_i2c_register(struct netup_unidvb_dev *ndev);
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_ci.c b/drivers/media/pci/netup_unidvb/netup_unidvb_ci.c
index f46ffac66ee9..f535270c2116 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_ci.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_ci.c
@@ -147,7 +147,7 @@ static int netup_unidvb_ci_read_attribute_mem(struct dvb_ca_en50221 *en50221,
 {
 	struct netup_ci_state *state = en50221->data;
 	struct netup_unidvb_dev *dev = state->dev;
-	u8 val = *((u8 __force *)state->membase8_io + addr);
+	u8 val = *((u8 __force *)state->membase8_config + addr);
 
 	dev_dbg(&dev->pci_dev->dev,
 		"%s(): addr=0x%x val=0x%x\n", __func__, addr, val);
@@ -162,7 +162,7 @@ static int netup_unidvb_ci_write_attribute_mem(struct dvb_ca_en50221 *en50221,
 
 	dev_dbg(&dev->pci_dev->dev,
 		"%s(): addr=0x%x data=0x%x\n", __func__, addr, data);
-	*((u8 __force *)state->membase8_io + addr) = data;
+	*((u8 __force *)state->membase8_config + addr) = data;
 	return 0;
 }
 
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
index 2b667b315913..ac547cb84de8 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
@@ -34,6 +34,7 @@
 #include "cxd2841er.h"
 #include "horus3a.h"
 #include "ascot2e.h"
+#include "helene.h"
 #include "lnbh25.h"
 
 static int spi_enable;
@@ -120,7 +121,8 @@ static int netup_unidvb_tuner_ctrl(void *priv, int is_dvb_tc);
 static void netup_unidvb_queue_cleanup(struct netup_dma *dma);
 
 static struct cxd2841er_config demod_config = {
-	.i2c_addr = 0xc8
+	.i2c_addr = 0xc8,
+	.xtal = SONY_XTAL_24000
 };
 
 static struct horus3a_config horus3a_conf = {
@@ -134,6 +136,12 @@ static struct ascot2e_config ascot2e_conf = {
 	.set_tuner_callback = netup_unidvb_tuner_ctrl
 };
 
+static struct helene_config helene_conf = {
+	.i2c_address = 0xc0,
+	.xtal = SONY_HELENE_XTAL_24000,
+	.set_tuner_callback = netup_unidvb_tuner_ctrl
+};
+
 static struct lnbh25_config lnbh25_conf = {
 	.i2c_address = 0x10,
 	.data2_config = LNBH25_TEN | LNBH25_EXTM
@@ -152,6 +160,11 @@ static int netup_unidvb_tuner_ctrl(void *priv, int is_dvb_tc)
 		__func__, dma->num, is_dvb_tc);
 	reg = readb(ndev->bmmio0 + GPIO_REG_IO);
 	mask = (dma->num == 0) ? GPIO_RFA_CTL : GPIO_RFB_CTL;
+
+	/* inverted tuner control in hw rev. 1.4 */
+	if (ndev->rev == NETUP_HW_REV_1_4)
+		is_dvb_tc = !is_dvb_tc;
+
 	if (!is_dvb_tc)
 		reg |= mask;
 	else
@@ -280,7 +293,7 @@ static int netup_unidvb_queue_setup(struct vb2_queue *vq,
 				    unsigned int *nbuffers,
 				    unsigned int *nplanes,
 				    unsigned int sizes[],
-				    void *alloc_ctxs[])
+				    struct device *alloc_devs[])
 {
 	struct netup_dma *dma = vb2_get_drv_priv(vq);
 
@@ -372,7 +385,15 @@ static int netup_unidvb_queue_init(struct netup_dma *dma,
 static int netup_unidvb_dvb_init(struct netup_unidvb_dev *ndev,
 				 int num)
 {
-	struct vb2_dvb_frontend *fe0, *fe1, *fe2;
+	int fe_count = 2;
+	int i = 0;
+	struct vb2_dvb_frontend *fes[2];
+	u8 fe_name[32];
+
+	if (ndev->rev == NETUP_HW_REV_1_3)
+		demod_config.xtal = SONY_XTAL_20500;
+	else
+		demod_config.xtal = SONY_XTAL_24000;
 
 	if (num < 0 || num > 1) {
 		dev_dbg(&ndev->pci_dev->dev,
@@ -381,84 +402,96 @@ static int netup_unidvb_dvb_init(struct netup_unidvb_dev *ndev,
 	}
 	mutex_init(&ndev->frontends[num].lock);
 	INIT_LIST_HEAD(&ndev->frontends[num].felist);
-	if (vb2_dvb_alloc_frontend(&ndev->frontends[num], 1) == NULL ||
-		vb2_dvb_alloc_frontend(
-			&ndev->frontends[num], 2) == NULL ||
-		vb2_dvb_alloc_frontend(
-			&ndev->frontends[num], 3) == NULL) {
-		dev_dbg(&ndev->pci_dev->dev,
-			"%s(): unable to allocate vb2_dvb_frontend\n",
-			__func__);
-		return -ENOMEM;
+
+	for (i = 0; i < fe_count; i++) {
+		if (vb2_dvb_alloc_frontend(&ndev->frontends[num], i+1)
+				== NULL) {
+			dev_err(&ndev->pci_dev->dev,
+					"%s(): unable to allocate vb2_dvb_frontend\n",
+					__func__);
+			return -ENOMEM;
+		}
 	}
-	fe0 = vb2_dvb_get_frontend(&ndev->frontends[num], 1);
-	fe1 = vb2_dvb_get_frontend(&ndev->frontends[num], 2);
-	fe2 = vb2_dvb_get_frontend(&ndev->frontends[num], 3);
-	if (fe0 == NULL || fe1 == NULL || fe2 == NULL) {
-		dev_dbg(&ndev->pci_dev->dev,
-			"%s(): frontends has not been allocated\n", __func__);
-		return -EINVAL;
+
+	for (i = 0; i < fe_count; i++) {
+		fes[i] = vb2_dvb_get_frontend(&ndev->frontends[num], i+1);
+		if (fes[i] == NULL) {
+			dev_err(&ndev->pci_dev->dev,
+				"%s(): frontends has not been allocated\n",
+				__func__);
+			return -EINVAL;
+		}
+	}
+
+	for (i = 0; i < fe_count; i++) {
+		netup_unidvb_queue_init(&ndev->dma[num], &fes[i]->dvb.dvbq);
+		snprintf(fe_name, sizeof(fe_name), "netup_fe%d", i);
+		fes[i]->dvb.name = fe_name;
 	}
-	netup_unidvb_queue_init(&ndev->dma[num], &fe0->dvb.dvbq);
-	netup_unidvb_queue_init(&ndev->dma[num], &fe1->dvb.dvbq);
-	netup_unidvb_queue_init(&ndev->dma[num], &fe2->dvb.dvbq);
-	fe0->dvb.name = "netup_fe0";
-	fe1->dvb.name = "netup_fe1";
-	fe2->dvb.name = "netup_fe2";
-	fe0->dvb.frontend = dvb_attach(cxd2841er_attach_s,
+
+	fes[0]->dvb.frontend = dvb_attach(cxd2841er_attach_s,
 		&demod_config, &ndev->i2c[num].adap);
-	if (fe0->dvb.frontend == NULL) {
+	if (fes[0]->dvb.frontend == NULL) {
 		dev_dbg(&ndev->pci_dev->dev,
 			"%s(): unable to attach DVB-S/S2 frontend\n",
 			__func__);
 		goto frontend_detach;
 	}
-	horus3a_conf.set_tuner_priv = &ndev->dma[num];
-	if (!dvb_attach(horus3a_attach, fe0->dvb.frontend,
-			&horus3a_conf, &ndev->i2c[num].adap)) {
-		dev_dbg(&ndev->pci_dev->dev,
-			"%s(): unable to attach DVB-S/S2 tuner frontend\n",
-			__func__);
-		goto frontend_detach;
+
+	if (ndev->rev == NETUP_HW_REV_1_3) {
+		horus3a_conf.set_tuner_priv = &ndev->dma[num];
+		if (!dvb_attach(horus3a_attach, fes[0]->dvb.frontend,
+					&horus3a_conf, &ndev->i2c[num].adap)) {
+			dev_dbg(&ndev->pci_dev->dev,
+					"%s(): unable to attach HORUS3A DVB-S/S2 tuner frontend\n",
+					__func__);
+			goto frontend_detach;
+		}
+	} else {
+		helene_conf.set_tuner_priv = &ndev->dma[num];
+		if (!dvb_attach(helene_attach_s, fes[0]->dvb.frontend,
+					&helene_conf, &ndev->i2c[num].adap)) {
+			dev_err(&ndev->pci_dev->dev,
+					"%s(): unable to attach HELENE DVB-S/S2 tuner frontend\n",
+					__func__);
+			goto frontend_detach;
+		}
 	}
-	if (!dvb_attach(lnbh25_attach, fe0->dvb.frontend,
+
+	if (!dvb_attach(lnbh25_attach, fes[0]->dvb.frontend,
 			&lnbh25_conf, &ndev->i2c[num].adap)) {
 		dev_dbg(&ndev->pci_dev->dev,
 			"%s(): unable to attach SEC frontend\n", __func__);
 		goto frontend_detach;
 	}
+
 	/* DVB-T/T2 frontend */
-	fe1->dvb.frontend = dvb_attach(cxd2841er_attach_t,
+	fes[1]->dvb.frontend = dvb_attach(cxd2841er_attach_t_c,
 		&demod_config, &ndev->i2c[num].adap);
-	if (fe1->dvb.frontend == NULL) {
-		dev_dbg(&ndev->pci_dev->dev,
-			"%s(): unable to attach DVB-T frontend\n", __func__);
-		goto frontend_detach;
-	}
-	fe1->dvb.frontend->id = 1;
-	ascot2e_conf.set_tuner_priv = &ndev->dma[num];
-	if (!dvb_attach(ascot2e_attach, fe1->dvb.frontend,
-			&ascot2e_conf, &ndev->i2c[num].adap)) {
-		dev_dbg(&ndev->pci_dev->dev,
-			"%s(): unable to attach DVB-T tuner frontend\n",
-			__func__);
-		goto frontend_detach;
-	}
-	/* DVB-C/C2 frontend */
-	fe2->dvb.frontend = dvb_attach(cxd2841er_attach_c,
-				&demod_config, &ndev->i2c[num].adap);
-	if (fe2->dvb.frontend == NULL) {
+	if (fes[1]->dvb.frontend == NULL) {
 		dev_dbg(&ndev->pci_dev->dev,
-			"%s(): unable to attach DVB-C frontend\n", __func__);
+			"%s(): unable to attach Ter frontend\n", __func__);
 		goto frontend_detach;
 	}
-	fe2->dvb.frontend->id = 2;
-	if (!dvb_attach(ascot2e_attach, fe2->dvb.frontend,
-			&ascot2e_conf, &ndev->i2c[num].adap)) {
-		dev_dbg(&ndev->pci_dev->dev,
-			"%s(): unable to attach DVB-T/C tuner frontend\n",
-			__func__);
-		goto frontend_detach;
+	fes[1]->dvb.frontend->id = 1;
+	if (ndev->rev == NETUP_HW_REV_1_3) {
+		ascot2e_conf.set_tuner_priv = &ndev->dma[num];
+		if (!dvb_attach(ascot2e_attach, fes[1]->dvb.frontend,
+					&ascot2e_conf, &ndev->i2c[num].adap)) {
+			dev_dbg(&ndev->pci_dev->dev,
+					"%s(): unable to attach Ter tuner frontend\n",
+					__func__);
+			goto frontend_detach;
+		}
+	} else {
+		helene_conf.set_tuner_priv = &ndev->dma[num];
+		if (!dvb_attach(helene_attach, fes[1]->dvb.frontend,
+					&helene_conf, &ndev->i2c[num].adap)) {
+			dev_err(&ndev->pci_dev->dev,
+					"%s(): unable to attach HELENE Ter tuner frontend\n",
+					__func__);
+			goto frontend_detach;
+		}
 	}
 
 	if (vb2_dvb_register_bus(&ndev->frontends[num],
@@ -730,7 +763,7 @@ static int netup_unidvb_request_mmio(struct pci_dev *pci_dev)
 static int netup_unidvb_request_modules(struct device *dev)
 {
 	static const char * const modules[] = {
-		"lnbh25", "ascot2e", "horus3a", "cxd2841er", NULL
+		"lnbh25", "ascot2e", "horus3a", "cxd2841er", "helene", NULL
 	};
 	const char * const *curr_mod = modules;
 	int err;
@@ -774,6 +807,16 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev,
 	if (!ndev)
 		goto dev_alloc_err;
 
+	/* detect hardware revision */
+	if (pci_dev->device == NETUP_HW_REV_1_3)
+		ndev->rev = NETUP_HW_REV_1_3;
+	else
+		ndev->rev = NETUP_HW_REV_1_4;
+
+	dev_info(&pci_dev->dev,
+		"%s(): board (0x%x) hardware revision 0x%x\n",
+		__func__, pci_dev->device, ndev->rev);
+
 	ndev->old_fw = old_firmware;
 	ndev->wq = create_singlethread_workqueue(NETUP_UNIDVB_NAME);
 	if (!ndev->wq) {
@@ -932,7 +975,7 @@ wq_create_err:
 	kfree(ndev);
 dev_alloc_err:
 	dev_err(&pci_dev->dev,
-		"%s(): failed to initizalize device\n", __func__);
+		"%s(): failed to initialize device\n", __func__);
 	return -EIO;
 }
 
@@ -972,7 +1015,8 @@ static void netup_unidvb_finidev(struct pci_dev *pci_dev)
 
 
 static struct pci_device_id netup_unidvb_pci_tbl[] = {
-	{ PCI_DEVICE(0x1b55, 0x18f6) },
+	{ PCI_DEVICE(0x1b55, 0x18f6) }, /* hw rev. 1.3 */
+	{ PCI_DEVICE(0x1b55, 0x18f7) }, /* hw rev. 1.4 */
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, netup_unidvb_pci_tbl);
diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c
index c0e1780ec831..ffb66a9ae23e 100644
--- a/drivers/media/pci/saa7134/saa7134-core.c
+++ b/drivers/media/pci/saa7134/saa7134-core.c
@@ -1164,18 +1164,13 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	saa7134_board_init1(dev);
 	saa7134_hwinit1(dev);
 
-	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		err = PTR_ERR(dev->alloc_ctx);
-		goto fail3;
-	}
 	/* get irq */
 	err = request_irq(pci_dev->irq, saa7134_irq,
 			  IRQF_SHARED, dev->name, dev);
 	if (err < 0) {
 		pr_err("%s: can't get IRQ %d\n",
 		       dev->name,pci_dev->irq);
-		goto fail4;
+		goto fail3;
 	}
 
 	/* wait a bit, register i2c bus */
@@ -1233,7 +1228,7 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	if (err < 0) {
 		pr_info("%s: can't register video device\n",
 		       dev->name);
-		goto fail5;
+		goto fail4;
 	}
 	pr_info("%s: registered device %s [v4l2]\n",
 	       dev->name, video_device_node_name(dev->video_dev));
@@ -1246,7 +1241,7 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	err = video_register_device(dev->vbi_dev,VFL_TYPE_VBI,
 				    vbi_nr[dev->nr]);
 	if (err < 0)
-		goto fail5;
+		goto fail4;
 	pr_info("%s: registered device %s\n",
 	       dev->name, video_device_node_name(dev->vbi_dev));
 
@@ -1257,7 +1252,7 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 		err = video_register_device(dev->radio_dev,VFL_TYPE_RADIO,
 					    radio_nr[dev->nr]);
 		if (err < 0)
-			goto fail5;
+			goto fail4;
 		pr_info("%s: registered device %s\n",
 		       dev->name, video_device_node_name(dev->radio_dev));
 	}
@@ -1268,7 +1263,7 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	err = v4l2_mc_create_media_graph(dev->media_dev);
 	if (err) {
 		pr_err("failed to create media graph\n");
-		goto fail5;
+		goto fail4;
 	}
 #endif
 	/* everything worked */
@@ -1287,17 +1282,15 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 #ifdef CONFIG_MEDIA_CONTROLLER
 	err = media_device_register(dev->media_dev);
 	if (err)
-		goto fail5;
+		goto fail4;
 #endif
 
 	return 0;
 
- fail5:
+ fail4:
 	saa7134_unregister_video(dev);
 	saa7134_i2c_unregister(dev);
 	free_irq(pci_dev->irq, dev);
- fail4:
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
  fail3:
 	saa7134_hwfini(dev);
 	iounmap(dev->lmmio);
@@ -1367,7 +1360,6 @@ static void saa7134_finidev(struct pci_dev *pci_dev)
 
 	/* release resources */
 	free_irq(pci_dev->irq, dev);
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	iounmap(dev->lmmio);
 	release_mem_region(pci_resource_start(pci_dev,0),
 			   pci_resource_len(pci_dev,0));
diff --git a/drivers/media/pci/saa7134/saa7134-ts.c b/drivers/media/pci/saa7134/saa7134-ts.c
index 0584a2adbe99..7eaf36a41db9 100644
--- a/drivers/media/pci/saa7134/saa7134-ts.c
+++ b/drivers/media/pci/saa7134/saa7134-ts.c
@@ -118,7 +118,7 @@ EXPORT_SYMBOL_GPL(saa7134_ts_buffer_prepare);
 
 int saa7134_ts_queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct saa7134_dmaqueue *dmaq = q->drv_priv;
 	struct saa7134_dev *dev = dmaq->dev;
@@ -131,7 +131,6 @@ int saa7134_ts_queue_setup(struct vb2_queue *q,
 		*nbuffers = 3;
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(saa7134_ts_queue_setup);
diff --git a/drivers/media/pci/saa7134/saa7134-vbi.c b/drivers/media/pci/saa7134/saa7134-vbi.c
index e76da37c4a8a..cf9a31e0a390 100644
--- a/drivers/media/pci/saa7134/saa7134-vbi.c
+++ b/drivers/media/pci/saa7134/saa7134-vbi.c
@@ -140,7 +140,7 @@ static int buffer_prepare(struct vb2_buffer *vb2)
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct saa7134_dmaqueue *dmaq = q->drv_priv;
 	struct saa7134_dev *dev = dmaq->dev;
@@ -155,7 +155,6 @@ static int queue_setup(struct vb2_queue *q,
 	*nbuffers = saa7134_buffer_count(size, *nbuffers);
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c
index ffa39543eb65..8a6ebd087889 100644
--- a/drivers/media/pci/saa7134/saa7134-video.c
+++ b/drivers/media/pci/saa7134/saa7134-video.c
@@ -963,7 +963,7 @@ static int buffer_prepare(struct vb2_buffer *vb2)
 
 static int queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct saa7134_dmaqueue *dmaq = q->drv_priv;
 	struct saa7134_dev *dev = dmaq->dev;
@@ -980,7 +980,6 @@ static int queue_setup(struct vb2_queue *q,
 	*nbuffers = saa7134_buffer_count(size, *nbuffers);
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = dev->alloc_ctx;
 
 	saa7134_enable_analog_tuner(dev);
 
@@ -2173,6 +2172,7 @@ int saa7134_video_init1(struct saa7134_dev *dev)
 	q->buf_struct_size = sizeof(struct saa7134_buf);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &dev->lock;
+	q->dev = &dev->pci->dev;
 	ret = vb2_queue_init(q);
 	if (ret)
 		return ret;
@@ -2191,6 +2191,7 @@ int saa7134_video_init1(struct saa7134_dev *dev)
 	q->buf_struct_size = sizeof(struct saa7134_buf);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &dev->lock;
+	q->dev = &dev->pci->dev;
 	ret = vb2_queue_init(q);
 	if (ret)
 		return ret;
diff --git a/drivers/media/pci/saa7134/saa7134.h b/drivers/media/pci/saa7134/saa7134.h
index 69a9bbf22d4d..3849083526a7 100644
--- a/drivers/media/pci/saa7134/saa7134.h
+++ b/drivers/media/pci/saa7134/saa7134.h
@@ -610,7 +610,6 @@ struct saa7134_dev {
 
 
 	/* video+ts+vbi capture */
-	void			   *alloc_ctx;
 	struct saa7134_dmaqueue    video_q;
 	struct vb2_queue           video_vbq;
 	struct saa7134_dmaqueue    vbi_q;
@@ -854,7 +853,7 @@ int saa7134_ts_buffer_init(struct vb2_buffer *vb2);
 int saa7134_ts_buffer_prepare(struct vb2_buffer *vb2);
 int saa7134_ts_queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[]);
+			   unsigned int sizes[], struct device *alloc_devs[]);
 int saa7134_ts_start_streaming(struct vb2_queue *vq, unsigned int count);
 void saa7134_ts_stop_streaming(struct vb2_queue *vq);
 
diff --git a/drivers/media/pci/saa7164/saa7164-encoder.c b/drivers/media/pci/saa7164/saa7164-encoder.c
index 1b184c39ba97..32a353d162e7 100644
--- a/drivers/media/pci/saa7164/saa7164-encoder.c
+++ b/drivers/media/pci/saa7164/saa7164-encoder.c
@@ -1022,8 +1022,7 @@ int saa7164_encoder_register(struct saa7164_port *port)
 
 	dprintk(DBGLVL_ENC, "%s()\n", __func__);
 
-	if (port->type != SAA7164_MPEG_ENCODER)
-		BUG();
+	BUG_ON(port->type != SAA7164_MPEG_ENCODER);
 
 	/* Sanity check that the PCI configuration space is active */
 	if (port->hwcfg.BARLocation == 0) {
@@ -1151,8 +1150,7 @@ void saa7164_encoder_unregister(struct saa7164_port *port)
 
 	dprintk(DBGLVL_ENC, "%s(port=%d)\n", __func__, port->nr);
 
-	if (port->type != SAA7164_MPEG_ENCODER)
-		BUG();
+	BUG_ON(port->type != SAA7164_MPEG_ENCODER);
 
 	if (port->v4l_device) {
 		if (port->v4l_device->minor != -1)
diff --git a/drivers/media/pci/saa7164/saa7164.h b/drivers/media/pci/saa7164/saa7164.h
index 8337524bfb8c..97411b0384c1 100644
--- a/drivers/media/pci/saa7164/saa7164.h
+++ b/drivers/media/pci/saa7164/saa7164.h
@@ -263,10 +263,6 @@ struct saa7164_i2c {
 	u32				i2c_rc;
 };
 
-struct saa7164_ctrl {
-	struct v4l2_queryctrl v;
-};
-
 struct saa7164_tvnorm {
 	char		*name;
 	v4l2_std_id	id;
diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
index 67a14c41c227..399164314c28 100644
--- a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
+++ b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
@@ -33,7 +33,7 @@
 #include "solo6x10-jpeg.h"
 
 #define MIN_VID_BUFFERS		2
-#define FRAME_BUF_SIZE		(196 * 1024)
+#define FRAME_BUF_SIZE		(400 * 1024)
 #define MP4_QS			16
 #define DMA_ALIGN		4096
 
@@ -664,12 +664,9 @@ static int solo_ring_thread(void *data)
 static int solo_enc_queue_setup(struct vb2_queue *q,
 				unsigned int *num_buffers,
 				unsigned int *num_planes, unsigned int sizes[],
-				void *alloc_ctxs[])
+				struct device *alloc_devs[])
 {
-	struct solo_enc_dev *solo_enc = vb2_get_drv_priv(q);
-
 	sizes[0] = FRAME_BUF_SIZE;
-	alloc_ctxs[0] = solo_enc->alloc_ctx;
 	*num_planes = 1;
 
 	if (*num_buffers < MIN_VID_BUFFERS)
@@ -1239,11 +1236,6 @@ static struct solo_enc_dev *solo_enc_alloc(struct solo_dev *solo_dev,
 		return ERR_PTR(-ENOMEM);
 
 	hdl = &solo_enc->hdl;
-	solo_enc->alloc_ctx = vb2_dma_sg_init_ctx(&solo_dev->pdev->dev);
-	if (IS_ERR(solo_enc->alloc_ctx)) {
-		ret = PTR_ERR(solo_enc->alloc_ctx);
-		goto hdl_free;
-	}
 	v4l2_ctrl_handler_init(hdl, 10);
 	v4l2_ctrl_new_std(hdl, &solo_ctrl_ops,
 			V4L2_CID_BRIGHTNESS, 0, 255, 1, 128);
@@ -1299,6 +1291,7 @@ static struct solo_enc_dev *solo_enc_alloc(struct solo_dev *solo_dev,
 	solo_enc->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	solo_enc->vidq.buf_struct_size = sizeof(struct solo_vb2_buf);
 	solo_enc->vidq.lock = &solo_enc->lock;
+	solo_enc->vidq.dev = &solo_dev->pdev->dev;
 	ret = vb2_queue_init(&solo_enc->vidq);
 	if (ret)
 		goto hdl_free;
@@ -1347,7 +1340,6 @@ pci_free:
 			solo_enc->desc_items, solo_enc->desc_dma);
 hdl_free:
 	v4l2_ctrl_handler_free(hdl);
-	vb2_dma_sg_cleanup_ctx(solo_enc->alloc_ctx);
 	kfree(solo_enc);
 	return ERR_PTR(ret);
 }
@@ -1362,7 +1354,6 @@ static void solo_enc_free(struct solo_enc_dev *solo_enc)
 			solo_enc->desc_items, solo_enc->desc_dma);
 	video_unregister_device(solo_enc->vfd);
 	v4l2_ctrl_handler_free(&solo_enc->hdl);
-	vb2_dma_sg_cleanup_ctx(solo_enc->alloc_ctx);
 	kfree(solo_enc);
 }
 
diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2.c b/drivers/media/pci/solo6x10/solo6x10-v4l2.c
index 721ff5320de7..b4be47969b6b 100644
--- a/drivers/media/pci/solo6x10/solo6x10-v4l2.c
+++ b/drivers/media/pci/solo6x10/solo6x10-v4l2.c
@@ -315,12 +315,11 @@ static void solo_stop_thread(struct solo_dev *solo_dev)
 
 static int solo_queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct solo_dev *solo_dev = vb2_get_drv_priv(q);
 
 	sizes[0] = solo_image_size(solo_dev);
-	alloc_ctxs[0] = solo_dev->alloc_ctx;
 	*num_planes = 1;
 
 	if (*num_buffers < MIN_VID_BUFFERS)
@@ -386,26 +385,24 @@ static int solo_querycap(struct file *file, void  *priv,
 static int solo_enum_ext_input(struct solo_dev *solo_dev,
 			       struct v4l2_input *input)
 {
-	static const char * const dispnames_1[] = { "4UP" };
-	static const char * const dispnames_2[] = { "4UP-1", "4UP-2" };
-	static const char * const dispnames_5[] = {
-		"4UP-1", "4UP-2", "4UP-3", "4UP-4", "16UP"
-	};
-	const char * const *dispnames;
+	int ext = input->index - solo_dev->nr_chans;
+	unsigned int nup, first;
 
-	if (input->index >= (solo_dev->nr_chans + solo_dev->nr_ext))
+	if (ext >= solo_dev->nr_ext)
 		return -EINVAL;
 
-	if (solo_dev->nr_ext == 5)
-		dispnames = dispnames_5;
-	else if (solo_dev->nr_ext == 2)
-		dispnames = dispnames_2;
-	else
-		dispnames = dispnames_1;
-
-	snprintf(input->name, sizeof(input->name), "Multi %s",
-		 dispnames[input->index - solo_dev->nr_chans]);
-
+	nup   = (ext == 4) ? 16 : 4;
+	first = (ext & 3) << 2; /* first channel in the n-up */
+	snprintf(input->name, sizeof(input->name),
+		 "Multi %d-up (cameras %d-%d)",
+		 nup, first + 1, first + nup);
+	/* Possible outputs:
+	 *  Multi 4-up (cameras 1-4)
+	 *  Multi 4-up (cameras 5-8)
+	 *  Multi 4-up (cameras 9-12)
+	 *  Multi 4-up (cameras 13-16)
+	 *  Multi 16-up (cameras 1-16)
+	 */
 	return 0;
 }
 
@@ -681,16 +678,11 @@ int solo_v4l2_init(struct solo_dev *solo_dev, unsigned nr)
 	solo_dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM;
 	solo_dev->vidq.buf_struct_size = sizeof(struct solo_vb2_buf);
 	solo_dev->vidq.lock = &solo_dev->lock;
+	solo_dev->vidq.dev = &solo_dev->pdev->dev;
 	ret = vb2_queue_init(&solo_dev->vidq);
 	if (ret < 0)
 		goto fail;
 
-	solo_dev->alloc_ctx = vb2_dma_contig_init_ctx(&solo_dev->pdev->dev);
-	if (IS_ERR(solo_dev->alloc_ctx)) {
-		dev_err(&solo_dev->pdev->dev, "Can't allocate buffer context");
-		return PTR_ERR(solo_dev->alloc_ctx);
-	}
-
 	/* Cycle all the channels and clear */
 	for (i = 0; i < solo_dev->nr_chans; i++) {
 		solo_v4l2_set_ch(solo_dev, i);
@@ -718,7 +710,6 @@ int solo_v4l2_init(struct solo_dev *solo_dev, unsigned nr)
 
 fail:
 	video_device_release(solo_dev->vfd);
-	vb2_dma_contig_cleanup_ctx(solo_dev->alloc_ctx);
 	v4l2_ctrl_handler_free(&solo_dev->disp_hdl);
 	solo_dev->vfd = NULL;
 	return ret;
@@ -730,7 +721,6 @@ void solo_v4l2_exit(struct solo_dev *solo_dev)
 		return;
 
 	video_unregister_device(solo_dev->vfd);
-	vb2_dma_contig_cleanup_ctx(solo_dev->alloc_ctx);
 	v4l2_ctrl_handler_free(&solo_dev->disp_hdl);
 	solo_dev->vfd = NULL;
 }
diff --git a/drivers/media/pci/solo6x10/solo6x10.h b/drivers/media/pci/solo6x10/solo6x10.h
index 4ab6586c0467..5bd498735a66 100644
--- a/drivers/media/pci/solo6x10/solo6x10.h
+++ b/drivers/media/pci/solo6x10/solo6x10.h
@@ -178,7 +178,6 @@ struct solo_enc_dev {
 	u32			sequence;
 	struct vb2_queue	vidq;
 	struct list_head	vidq_active;
-	void			*alloc_ctx;
 	int			desc_count;
 	int			desc_nelts;
 	struct solo_p2m_desc	*desc_items;
@@ -269,7 +268,6 @@ struct solo_dev {
 
 	/* Buffer handling */
 	struct vb2_queue	vidq;
-	struct vb2_alloc_ctx	*alloc_ctx;
 	u32			sequence;
 	struct task_struct      *kthread;
 	struct mutex		lock;
diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c
index 1fc195f89686..aeb2b4e2db35 100644
--- a/drivers/media/pci/sta2x11/sta2x11_vip.c
+++ b/drivers/media/pci/sta2x11/sta2x11_vip.c
@@ -111,7 +111,6 @@ static inline struct vip_buffer *to_vip_buffer(struct vb2_v4l2_buffer *vb2)
  * @input: input line for video signal ( 0 or 1 )
  * @disabled: Device is in power down state
  * @slock: for excluse acces of registers
- * @alloc_ctx: context for videobuf2
  * @vb_vidq: queue maintained by videobuf2 layer
  * @buffer_list: list of buffer in use
  * @sequence: sequence number of acquired buffer
@@ -141,7 +140,6 @@ struct sta2x11_vip {
 	int disabled;
 	spinlock_t slock;
 
-	struct vb2_alloc_ctx *alloc_ctx;
 	struct vb2_queue vb_vidq;
 	struct list_head buffer_list;
 	unsigned int sequence;
@@ -267,7 +265,7 @@ static void vip_active_buf_next(struct sta2x11_vip *vip)
 /* Videobuf2 Operations */
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
-		       unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct sta2x11_vip *vip = vb2_get_drv_priv(vq);
 
@@ -276,7 +274,6 @@ static int queue_setup(struct vb2_queue *vq,
 
 	*nplanes = 1;
 	sizes[0] = vip->format.sizeimage;
-	alloc_ctxs[0] = vip->alloc_ctx;
 
 	vip->sequence = 0;
 	vip->active = NULL;
@@ -861,25 +858,15 @@ static int sta2x11_vip_init_buffer(struct sta2x11_vip *vip)
 	vip->vb_vidq.ops = &vip_video_qops;
 	vip->vb_vidq.mem_ops = &vb2_dma_contig_memops;
 	vip->vb_vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	vip->vb_vidq.dev = &vip->pdev->dev;
 	err = vb2_queue_init(&vip->vb_vidq);
 	if (err)
 		return err;
 	INIT_LIST_HEAD(&vip->buffer_list);
 	spin_lock_init(&vip->lock);
-
-
-	vip->alloc_ctx = vb2_dma_contig_init_ctx(&vip->pdev->dev);
-	if (IS_ERR(vip->alloc_ctx)) {
-		v4l2_err(&vip->v4l2_dev, "Can't allocate buffer context");
-		return PTR_ERR(vip->alloc_ctx);
-	}
-
 	return 0;
 }
-static void sta2x11_vip_release_buffer(struct sta2x11_vip *vip)
-{
-	vb2_dma_contig_cleanup_ctx(vip->alloc_ctx);
-}
+
 static int sta2x11_vip_init_controls(struct sta2x11_vip *vip)
 {
 	/*
@@ -1120,7 +1107,6 @@ vrelease:
 	video_unregister_device(&vip->video_dev);
 	free_irq(pdev->irq, vip);
 release_buf:
-	sta2x11_vip_release_buffer(vip);
 	pci_disable_msi(pdev);
 unmap:
 	vb2_queue_release(&vip->vb_vidq);
diff --git a/drivers/media/pci/tw68/tw68-core.c b/drivers/media/pci/tw68/tw68-core.c
index 4e77618fbb2b..8474528be91e 100644
--- a/drivers/media/pci/tw68/tw68-core.c
+++ b/drivers/media/pci/tw68/tw68-core.c
@@ -305,19 +305,13 @@ static int tw68_initdev(struct pci_dev *pci_dev,
 	/* Then do any initialisation wanted before interrupts are on */
 	tw68_hw_init1(dev);
 
-	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		err = PTR_ERR(dev->alloc_ctx);
-		goto fail3;
-	}
-
 	/* get irq */
 	err = devm_request_irq(&pci_dev->dev, pci_dev->irq, tw68_irq,
 			  IRQF_SHARED, dev->name, dev);
 	if (err < 0) {
 		pr_err("%s: can't get IRQ %d\n",
 		       dev->name, pci_dev->irq);
-		goto fail4;
+		goto fail3;
 	}
 
 	/*
@@ -331,7 +325,7 @@ static int tw68_initdev(struct pci_dev *pci_dev,
 	if (err < 0) {
 		pr_err("%s: can't register video device\n",
 		       dev->name);
-		goto fail5;
+		goto fail4;
 	}
 	tw_setl(TW68_INTMASK, dev->pci_irqmask);
 
@@ -340,10 +334,8 @@ static int tw68_initdev(struct pci_dev *pci_dev,
 
 	return 0;
 
-fail5:
-	video_unregister_device(&dev->vdev);
 fail4:
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
+	video_unregister_device(&dev->vdev);
 fail3:
 	iounmap(dev->lmmio);
 fail2:
@@ -367,7 +359,6 @@ static void tw68_finidev(struct pci_dev *pci_dev)
 	/* unregister */
 	video_unregister_device(&dev->vdev);
 	v4l2_ctrl_handler_free(&dev->hdl);
-	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 
 	/* release resources */
 	iounmap(dev->lmmio);
diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c
index 07116a87a57b..5e8212845c87 100644
--- a/drivers/media/pci/tw68/tw68-video.c
+++ b/drivers/media/pci/tw68/tw68-video.c
@@ -378,7 +378,7 @@ static int tw68_buffer_count(unsigned int size, unsigned int count)
 
 static int tw68_queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct tw68_dev *dev = vb2_get_drv_priv(q);
 	unsigned tot_bufs = q->num_buffers + *num_buffers;
@@ -388,7 +388,6 @@ static int tw68_queue_setup(struct vb2_queue *q,
 		tot_bufs = 2;
 	tot_bufs = tw68_buffer_count(size, tot_bufs);
 	*num_buffers = tot_bufs - q->num_buffers;
-	alloc_ctxs[0] = dev->alloc_ctx;
 	/*
 	 * We allow create_bufs, but only if the sizeimage is >= as the
 	 * current sizeimage. The tw68_buffer_count calculation becomes quite
@@ -983,6 +982,7 @@ int tw68_video_init2(struct tw68_dev *dev, int video_nr)
 	dev->vidq.buf_struct_size = sizeof(struct tw68_buf);
 	dev->vidq.lock = &dev->lock;
 	dev->vidq.min_buffers_needed = 2;
+	dev->vidq.dev = &dev->pci->dev;
 	ret = vb2_queue_init(&dev->vidq);
 	if (ret)
 		return ret;
diff --git a/drivers/media/pci/tw68/tw68.h b/drivers/media/pci/tw68/tw68.h
index 6c7dcb300f34..5585c7ee23f2 100644
--- a/drivers/media/pci/tw68/tw68.h
+++ b/drivers/media/pci/tw68/tw68.h
@@ -165,7 +165,6 @@ struct tw68_dev {
 	unsigned		field;
 	struct vb2_queue	vidq;
 	struct list_head	active;
-	void			*alloc_ctx;
 
 	/* various v4l controls */
 	const struct tw68_tvnorm *tvnorm;	/* video */
diff --git a/drivers/media/pci/tw686x/Kconfig b/drivers/media/pci/tw686x/Kconfig
index fb8536974052..34ff37712313 100644
--- a/drivers/media/pci/tw686x/Kconfig
+++ b/drivers/media/pci/tw686x/Kconfig
@@ -3,6 +3,8 @@ config VIDEO_TW686X
 	depends on PCI && VIDEO_DEV && VIDEO_V4L2 && SND
 	depends on HAS_DMA
 	select VIDEOBUF2_VMALLOC
+	select VIDEOBUF2_DMA_CONTIG
+	select VIDEOBUF2_DMA_SG
 	select SND_PCM
 	help
 	  Support for Intersil/Techwell TW686x-based frame grabber cards.
diff --git a/drivers/media/pci/tw686x/tw686x-audio.c b/drivers/media/pci/tw686x/tw686x-audio.c
index 91459ab715b2..96e444c49173 100644
--- a/drivers/media/pci/tw686x/tw686x-audio.c
+++ b/drivers/media/pci/tw686x/tw686x-audio.c
@@ -62,12 +62,22 @@ void tw686x_audio_irq(struct tw686x_dev *dev, unsigned long requests,
 		}
 		spin_unlock_irqrestore(&ac->lock, flags);
 
+		if (!done || !next)
+			continue;
+		/*
+		 * Checking for a non-nil dma_desc[pb]->virt buffer is
+		 * the same as checking for memcpy DMA mode.
+		 */
 		desc = &ac->dma_descs[pb];
-		if (done && next && desc->virt) {
-			memcpy(done->virt, desc->virt, desc->size);
-			ac->ptr = done->dma - ac->buf[0].dma;
-			snd_pcm_period_elapsed(ac->ss);
+		if (desc->virt) {
+			memcpy(done->virt, desc->virt,
+			       dev->period_size);
+		} else {
+			u32 reg = pb ? ADMA_B_ADDR[ch] : ADMA_P_ADDR[ch];
+			reg_write(dev, reg, next->dma);
 		}
+		ac->ptr = done->dma - ac->buf[0].dma;
+		snd_pcm_period_elapsed(ac->ss);
 	}
 }
 
@@ -83,10 +93,9 @@ static int tw686x_pcm_hw_free(struct snd_pcm_substream *ss)
 }
 
 /*
- * The audio device rate is global and shared among all
- * capture channels. The driver makes no effort to prevent
- * rate modifications. User is free change the rate, but it
- * means changing the rate for all capture sub-devices.
+ * Audio parameters are global and shared among all
+ * capture channels. The driver prevents changes to
+ * the parameters if any audio channel is capturing.
  */
 static const struct snd_pcm_hardware tw686x_capture_hw = {
 	.info			= (SNDRV_PCM_INFO_MMAP |
@@ -99,9 +108,9 @@ static const struct snd_pcm_hardware tw686x_capture_hw = {
 	.rate_max		= 48000,
 	.channels_min		= 1,
 	.channels_max		= 1,
-	.buffer_bytes_max	= TW686X_AUDIO_PAGE_MAX * TW686X_AUDIO_PAGE_SZ,
-	.period_bytes_min	= TW686X_AUDIO_PAGE_SZ,
-	.period_bytes_max	= TW686X_AUDIO_PAGE_SZ,
+	.buffer_bytes_max	= TW686X_AUDIO_PAGE_MAX * AUDIO_DMA_SIZE_MAX,
+	.period_bytes_min	= AUDIO_DMA_SIZE_MIN,
+	.period_bytes_max	= AUDIO_DMA_SIZE_MAX,
 	.periods_min		= TW686X_AUDIO_PERIODS_MIN,
 	.periods_max		= TW686X_AUDIO_PERIODS_MAX,
 };
@@ -143,6 +152,14 @@ static int tw686x_pcm_prepare(struct snd_pcm_substream *ss)
 	int i;
 
 	spin_lock_irqsave(&dev->lock, flags);
+	/*
+	 * Given the audio parameters are global (i.e. shared across
+	 * DMA channels), we need to check new params are allowed.
+	 */
+	if (((dev->audio_rate != rt->rate) ||
+	     (dev->period_size != period_size)) && dev->audio_enabled)
+		goto err_audio_busy;
+
 	tw686x_disable_channel(dev, AUDIO_CHANNEL_OFFSET + ac->ch);
 	spin_unlock_irqrestore(&dev->lock, flags);
 
@@ -156,12 +173,21 @@ static int tw686x_pcm_prepare(struct snd_pcm_substream *ss)
 		reg_write(dev, AUDIO_CONTROL2, reg);
 	}
 
-	if (period_size != TW686X_AUDIO_PAGE_SZ ||
-	    rt->periods < TW686X_AUDIO_PERIODS_MIN ||
-	    rt->periods > TW686X_AUDIO_PERIODS_MAX) {
-		return -EINVAL;
+	if (dev->period_size != period_size) {
+		u32 reg;
+
+		dev->period_size = period_size;
+		reg = reg_read(dev, AUDIO_CONTROL1);
+		reg &= ~(AUDIO_DMA_SIZE_MASK << AUDIO_DMA_SIZE_SHIFT);
+		reg |= period_size << AUDIO_DMA_SIZE_SHIFT;
+
+		reg_write(dev, AUDIO_CONTROL1, reg);
 	}
 
+	if (rt->periods < TW686X_AUDIO_PERIODS_MIN ||
+	    rt->periods > TW686X_AUDIO_PERIODS_MAX)
+		return -EINVAL;
+
 	spin_lock_irqsave(&ac->lock, flags);
 	INIT_LIST_HEAD(&ac->buf_list);
 
@@ -181,9 +207,19 @@ static int tw686x_pcm_prepare(struct snd_pcm_substream *ss)
 	ac->curr_bufs[0] = p_buf;
 	ac->curr_bufs[1] = b_buf;
 	ac->ptr = 0;
+
+	if (dev->dma_mode != TW686X_DMA_MODE_MEMCPY) {
+		reg_write(dev, ADMA_P_ADDR[ac->ch], p_buf->dma);
+		reg_write(dev, ADMA_B_ADDR[ac->ch], b_buf->dma);
+	}
+
 	spin_unlock_irqrestore(&ac->lock, flags);
 
 	return 0;
+
+err_audio_busy:
+	spin_unlock_irqrestore(&dev->lock, flags);
+	return -EBUSY;
 }
 
 static int tw686x_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
@@ -197,6 +233,7 @@ static int tw686x_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 		if (ac->curr_bufs[0] && ac->curr_bufs[1]) {
 			spin_lock_irqsave(&dev->lock, flags);
+			dev->audio_enabled = 1;
 			tw686x_enable_channel(dev,
 				AUDIO_CHANNEL_OFFSET + ac->ch);
 			spin_unlock_irqrestore(&dev->lock, flags);
@@ -209,6 +246,7 @@ static int tw686x_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 		spin_lock_irqsave(&dev->lock, flags);
+		dev->audio_enabled = 0;
 		tw686x_disable_channel(dev, AUDIO_CHANNEL_OFFSET + ac->ch);
 		spin_unlock_irqrestore(&dev->lock, flags);
 
@@ -266,8 +304,8 @@ static int tw686x_snd_pcm_init(struct tw686x_dev *dev)
 	return snd_pcm_lib_preallocate_pages_for_all(pcm,
 				SNDRV_DMA_TYPE_DEV,
 				snd_dma_pci_data(dev->pci_dev),
-				TW686X_AUDIO_PAGE_MAX * TW686X_AUDIO_PAGE_SZ,
-				TW686X_AUDIO_PAGE_MAX * TW686X_AUDIO_PAGE_SZ);
+				TW686X_AUDIO_PAGE_MAX * AUDIO_DMA_SIZE_MAX,
+				TW686X_AUDIO_PAGE_MAX * AUDIO_DMA_SIZE_MAX);
 }
 
 static void tw686x_audio_dma_free(struct tw686x_dev *dev,
@@ -290,11 +328,19 @@ static int tw686x_audio_dma_alloc(struct tw686x_dev *dev,
 {
 	int pb;
 
+	/*
+	 * In the memcpy DMA mode we allocate a consistent buffer
+	 * and use it for the DMA capture. Otherwise, DMA
+	 * acts on the ALSA buffers as received in pcm_prepare.
+	 */
+	if (dev->dma_mode != TW686X_DMA_MODE_MEMCPY)
+		return 0;
+
 	for (pb = 0; pb < 2; pb++) {
 		u32 reg = pb ? ADMA_B_ADDR[ac->ch] : ADMA_P_ADDR[ac->ch];
 		void *virt;
 
-		virt = pci_alloc_consistent(dev->pci_dev, TW686X_AUDIO_PAGE_SZ,
+		virt = pci_alloc_consistent(dev->pci_dev, AUDIO_DMA_SIZE_MAX,
 					    &ac->dma_descs[pb].phys);
 		if (!virt) {
 			dev_err(&dev->pci_dev->dev,
@@ -303,7 +349,7 @@ static int tw686x_audio_dma_alloc(struct tw686x_dev *dev,
 			return -ENOMEM;
 		}
 		ac->dma_descs[pb].virt = virt;
-		ac->dma_descs[pb].size = TW686X_AUDIO_PAGE_SZ;
+		ac->dma_descs[pb].size = AUDIO_DMA_SIZE_MAX;
 		reg_write(dev, reg, ac->dma_descs[pb].phys);
 	}
 	return 0;
@@ -334,12 +380,8 @@ int tw686x_audio_init(struct tw686x_dev *dev)
 	struct snd_card *card;
 	int err, ch;
 
-	/*
-	 * AUDIO_CONTROL1
-	 * DMA byte length [31:19] = 4096 (i.e. ALSA period)
-	 * External audio enable [0] = enabled
-	 */
-	reg_write(dev, AUDIO_CONTROL1, 0x80000001);
+	/* Enable external audio */
+	reg_write(dev, AUDIO_CONTROL1, BIT(0));
 
 	err = snd_card_new(&pci_dev->dev, SNDRV_DEFAULT_IDX1,
 			   SNDRV_DEFAULT_STR1,
diff --git a/drivers/media/pci/tw686x/tw686x-core.c b/drivers/media/pci/tw686x/tw686x-core.c
index cf53b0e97be2..71a0453b1af1 100644
--- a/drivers/media/pci/tw686x/tw686x-core.c
+++ b/drivers/media/pci/tw686x/tw686x-core.c
@@ -21,12 +21,14 @@
  * under stress testings it has been found that the machine can
  * freeze completely if DMA registers are programmed while streaming
  * is active.
- * This driver tries to access hardware registers as infrequently
- * as possible by:
- *   i.  allocating fixed DMA buffers and memcpy'ing into
- *       vmalloc'ed buffers
- *   ii. using a timer to mitigate the rate of DMA reset operations,
- *       on DMA channels error.
+ *
+ * Therefore, driver implements a dma_mode called 'memcpy' which
+ * avoids cycling the DMA buffers, and insteads allocates extra DMA buffers
+ * and then copies into vmalloc'ed user buffers.
+ *
+ * In addition to this, when streaming is on, the driver tries to access
+ * hardware registers as infrequently as possible. This is done by using
+ * a timer to limit the rate at which DMA is reset on DMA channels error.
  */
 
 #include <linux/init.h>
@@ -55,6 +57,42 @@ static u32 dma_interval = 0x00098968;
 module_param(dma_interval, int, 0444);
 MODULE_PARM_DESC(dma_interval, "Minimum time span for DMA interrupting host");
 
+static unsigned int dma_mode = TW686X_DMA_MODE_MEMCPY;
+static const char *dma_mode_name(unsigned int mode)
+{
+	switch (mode) {
+	case TW686X_DMA_MODE_MEMCPY:
+		return "memcpy";
+	case TW686X_DMA_MODE_CONTIG:
+		return "contig";
+	case TW686X_DMA_MODE_SG:
+		return "sg";
+	default:
+		return "unknown";
+	}
+}
+
+static int tw686x_dma_mode_get(char *buffer, struct kernel_param *kp)
+{
+	return sprintf(buffer, dma_mode_name(dma_mode));
+}
+
+static int tw686x_dma_mode_set(const char *val, struct kernel_param *kp)
+{
+	if (!strcasecmp(val, dma_mode_name(TW686X_DMA_MODE_MEMCPY)))
+		dma_mode = TW686X_DMA_MODE_MEMCPY;
+	else if (!strcasecmp(val, dma_mode_name(TW686X_DMA_MODE_CONTIG)))
+		dma_mode = TW686X_DMA_MODE_CONTIG;
+	else if (!strcasecmp(val, dma_mode_name(TW686X_DMA_MODE_SG)))
+		dma_mode = TW686X_DMA_MODE_SG;
+	else
+		return -EINVAL;
+	return 0;
+}
+module_param_call(dma_mode, tw686x_dma_mode_set, tw686x_dma_mode_get,
+		  &dma_mode, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(dma_mode, "DMA operation mode (memcpy/contig/sg, default=memcpy)");
+
 void tw686x_disable_channel(struct tw686x_dev *dev, unsigned int channel)
 {
 	u32 dma_en = reg_read(dev, DMA_CHANNEL_ENABLE);
@@ -212,6 +250,7 @@ static int tw686x_probe(struct pci_dev *pci_dev,
 	if (!dev)
 		return -ENOMEM;
 	dev->type = pci_id->driver_data;
+	dev->dma_mode = dma_mode;
 	sprintf(dev->name, "tw%04X", pci_dev->device);
 
 	dev->video_channels = kcalloc(max_channels(dev),
@@ -228,9 +267,10 @@ static int tw686x_probe(struct pci_dev *pci_dev,
 		goto free_video;
 	}
 
-	pr_info("%s: PCI %s, IRQ %d, MMIO 0x%lx\n", dev->name,
+	pr_info("%s: PCI %s, IRQ %d, MMIO 0x%lx (%s mode)\n", dev->name,
 		pci_name(pci_dev), pci_dev->irq,
-		(unsigned long)pci_resource_start(pci_dev, 0));
+		(unsigned long)pci_resource_start(pci_dev, 0),
+		dma_mode_name(dma_mode));
 
 	dev->pci_dev = pci_dev;
 	if (pci_enable_device(pci_dev)) {
diff --git a/drivers/media/pci/tw686x/tw686x-regs.h b/drivers/media/pci/tw686x/tw686x-regs.h
index fcef586a4c8c..15a956642ef4 100644
--- a/drivers/media/pci/tw686x/tw686x-regs.h
+++ b/drivers/media/pci/tw686x/tw686x-regs.h
@@ -105,6 +105,10 @@
 						  0x2d0, 0x2d1, 0x2d2, 0x2d3 })
 
 #define SYS_MODE_DMA_SHIFT	13
+#define AUDIO_DMA_SIZE_SHIFT	19
+#define AUDIO_DMA_SIZE_MIN	SZ_512
+#define AUDIO_DMA_SIZE_MAX	SZ_4K
+#define AUDIO_DMA_SIZE_MASK	(SZ_8K - 1)
 
 #define DMA_CMD_ENABLE		BIT(31)
 #define INT_STATUS_DMA_TOUT	BIT(17)
@@ -119,4 +123,9 @@
 #define TW686X_STD_PAL_CN	5
 #define TW686X_STD_PAL_60	6
 
+#define TW686X_FIELD_MODE	0x3
+#define TW686X_FRAME_MODE	0x2
+/* 0x1 is reserved */
+#define TW686X_SG_MODE		0x0
+
 #define TW686X_FIFO_ERROR(x)	(x & ~(0xff))
diff --git a/drivers/media/pci/tw686x/tw686x-video.c b/drivers/media/pci/tw686x/tw686x-video.c
index 253e10823ba3..cdb16de770fe 100644
--- a/drivers/media/pci/tw686x/tw686x-video.c
+++ b/drivers/media/pci/tw686x/tw686x-video.c
@@ -19,6 +19,8 @@
 #include <linux/slab.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-event.h>
+#include <media/videobuf2-dma-contig.h>
+#include <media/videobuf2-dma-sg.h>
 #include <media/videobuf2-vmalloc.h>
 #include "tw686x.h"
 #include "tw686x-regs.h"
@@ -26,6 +28,11 @@
 #define TW686X_INPUTS_PER_CH		4
 #define TW686X_VIDEO_WIDTH		720
 #define TW686X_VIDEO_HEIGHT(id)		((id & V4L2_STD_525_60) ? 480 : 576)
+#define TW686X_MAX_FPS(id)		((id & V4L2_STD_525_60) ? 30 : 25)
+
+#define TW686X_MAX_SG_ENTRY_SIZE	4096
+#define TW686X_MAX_SG_DESC_COUNT	256 /* PAL 720x576 needs 203 4-KB pages */
+#define TW686X_SG_TABLE_SIZE		(TW686X_MAX_SG_DESC_COUNT * sizeof(struct tw686x_sg_desc))
 
 static const struct tw686x_format formats[] = {
 	{
@@ -43,53 +50,367 @@ static const struct tw686x_format formats[] = {
 	}
 };
 
-static unsigned int tw686x_fields_map(v4l2_std_id std, unsigned int fps)
+static void tw686x_buf_done(struct tw686x_video_channel *vc,
+			    unsigned int pb)
 {
-	static const unsigned int map[15] = {
-		0x00000000, 0x00000001, 0x00004001, 0x00104001, 0x00404041,
-		0x01041041, 0x01104411, 0x01111111, 0x04444445, 0x04511445,
-		0x05145145, 0x05151515, 0x05515455, 0x05551555, 0x05555555
-	};
+	struct tw686x_dma_desc *desc = &vc->dma_descs[pb];
+	struct tw686x_dev *dev = vc->dev;
+	struct vb2_v4l2_buffer *vb;
+	struct vb2_buffer *vb2_buf;
 
-	static const unsigned int std_625_50[26] = {
-		0, 1, 1, 2,  3,  3,  4,  4,  5,  5,  6,  7,  7,
-		   8, 8, 9, 10, 10, 11, 11, 12, 13, 13, 14, 14, 0
-	};
+	if (vc->curr_bufs[pb]) {
+		vb = &vc->curr_bufs[pb]->vb;
 
-	static const unsigned int std_525_60[31] = {
-		0, 1, 1, 1, 2,  2,  3,  3,  4,  4,  5,  5,  6,  6, 7, 7,
-		   8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13, 14, 0, 0
-	};
+		vb->field = dev->dma_ops->field;
+		vb->sequence = vc->sequence++;
+		vb2_buf = &vb->vb2_buf;
 
-	unsigned int i;
+		if (dev->dma_mode == TW686X_DMA_MODE_MEMCPY)
+			memcpy(vb2_plane_vaddr(vb2_buf, 0), desc->virt,
+			       desc->size);
+		vb2_buf->timestamp = ktime_get_ns();
+		vb2_buffer_done(vb2_buf, VB2_BUF_STATE_DONE);
+	}
+
+	vc->pb = !pb;
+}
+
+/*
+ * We can call this even when alloc_dma failed for the given channel
+ */
+static void tw686x_memcpy_dma_free(struct tw686x_video_channel *vc,
+				   unsigned int pb)
+{
+	struct tw686x_dma_desc *desc = &vc->dma_descs[pb];
+	struct tw686x_dev *dev = vc->dev;
+	struct pci_dev *pci_dev;
+	unsigned long flags;
+
+	/* Check device presence. Shouldn't really happen! */
+	spin_lock_irqsave(&dev->lock, flags);
+	pci_dev = dev->pci_dev;
+	spin_unlock_irqrestore(&dev->lock, flags);
+	if (!pci_dev) {
+		WARN(1, "trying to deallocate on missing device\n");
+		return;
+	}
+
+	if (desc->virt) {
+		pci_free_consistent(dev->pci_dev, desc->size,
+				    desc->virt, desc->phys);
+		desc->virt = NULL;
+	}
+}
+
+static int tw686x_memcpy_dma_alloc(struct tw686x_video_channel *vc,
+				   unsigned int pb)
+{
+	struct tw686x_dev *dev = vc->dev;
+	u32 reg = pb ? VDMA_B_ADDR[vc->ch] : VDMA_P_ADDR[vc->ch];
+	unsigned int len;
+	void *virt;
+
+	WARN(vc->dma_descs[pb].virt,
+	     "Allocating buffer but previous still here\n");
+
+	len = (vc->width * vc->height * vc->format->depth) >> 3;
+	virt = pci_alloc_consistent(dev->pci_dev, len,
+				    &vc->dma_descs[pb].phys);
+	if (!virt) {
+		v4l2_err(&dev->v4l2_dev,
+			 "dma%d: unable to allocate %s-buffer\n",
+			 vc->ch, pb ? "B" : "P");
+		return -ENOMEM;
+	}
+	vc->dma_descs[pb].size = len;
+	vc->dma_descs[pb].virt = virt;
+	reg_write(dev, reg, vc->dma_descs[pb].phys);
+
+	return 0;
+}
+
+static void tw686x_memcpy_buf_refill(struct tw686x_video_channel *vc,
+				     unsigned int pb)
+{
+	struct tw686x_v4l2_buf *buf;
+
+	while (!list_empty(&vc->vidq_queued)) {
+
+		buf = list_first_entry(&vc->vidq_queued,
+			struct tw686x_v4l2_buf, list);
+		list_del(&buf->list);
+
+		vc->curr_bufs[pb] = buf;
+		return;
+	}
+	vc->curr_bufs[pb] = NULL;
+}
 
-	if (std & V4L2_STD_525_60) {
-		if (fps >= ARRAY_SIZE(std_525_60))
-			fps = 30;
-		i = std_525_60[fps];
+static const struct tw686x_dma_ops memcpy_dma_ops = {
+	.alloc		= tw686x_memcpy_dma_alloc,
+	.free		= tw686x_memcpy_dma_free,
+	.buf_refill	= tw686x_memcpy_buf_refill,
+	.mem_ops	= &vb2_vmalloc_memops,
+	.hw_dma_mode	= TW686X_FRAME_MODE,
+	.field		= V4L2_FIELD_INTERLACED,
+};
+
+static void tw686x_contig_buf_refill(struct tw686x_video_channel *vc,
+				     unsigned int pb)
+{
+	struct tw686x_v4l2_buf *buf;
+
+	while (!list_empty(&vc->vidq_queued)) {
+		u32 reg = pb ? VDMA_B_ADDR[vc->ch] : VDMA_P_ADDR[vc->ch];
+		dma_addr_t phys;
+
+		buf = list_first_entry(&vc->vidq_queued,
+			struct tw686x_v4l2_buf, list);
+		list_del(&buf->list);
+
+		phys = vb2_dma_contig_plane_dma_addr(&buf->vb.vb2_buf, 0);
+		reg_write(vc->dev, reg, phys);
+
+		buf->vb.vb2_buf.state = VB2_BUF_STATE_ACTIVE;
+		vc->curr_bufs[pb] = buf;
+		return;
+	}
+	vc->curr_bufs[pb] = NULL;
+}
+
+static const struct tw686x_dma_ops contig_dma_ops = {
+	.buf_refill	= tw686x_contig_buf_refill,
+	.mem_ops	= &vb2_dma_contig_memops,
+	.hw_dma_mode	= TW686X_FRAME_MODE,
+	.field		= V4L2_FIELD_INTERLACED,
+};
+
+static int tw686x_sg_desc_fill(struct tw686x_sg_desc *descs,
+			       struct tw686x_v4l2_buf *buf,
+			       unsigned int buf_len)
+{
+	struct sg_table *vbuf = vb2_dma_sg_plane_desc(&buf->vb.vb2_buf, 0);
+	unsigned int len, entry_len;
+	struct scatterlist *sg;
+	int i, count;
+
+	/* Clear the scatter-gather table */
+	memset(descs, 0, TW686X_SG_TABLE_SIZE);
+
+	count = 0;
+	for_each_sg(vbuf->sgl, sg, vbuf->nents, i) {
+		dma_addr_t phys = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+
+		while (len && buf_len) {
+
+			if (count == TW686X_MAX_SG_DESC_COUNT)
+				return -ENOMEM;
+
+			entry_len = min_t(unsigned int, len,
+					  TW686X_MAX_SG_ENTRY_SIZE);
+			entry_len = min_t(unsigned int, entry_len, buf_len);
+			descs[count].phys = cpu_to_le32(phys);
+			descs[count++].flags_length =
+					cpu_to_le32(BIT(30) | entry_len);
+			phys += entry_len;
+			len -= entry_len;
+			buf_len -= entry_len;
+		}
+
+		if (!buf_len)
+			return 0;
+	}
+
+	return -ENOMEM;
+}
+
+static void tw686x_sg_buf_refill(struct tw686x_video_channel *vc,
+				 unsigned int pb)
+{
+	struct tw686x_dev *dev = vc->dev;
+	struct tw686x_v4l2_buf *buf;
+
+	while (!list_empty(&vc->vidq_queued)) {
+		unsigned int buf_len;
+
+		buf = list_first_entry(&vc->vidq_queued,
+			struct tw686x_v4l2_buf, list);
+		list_del(&buf->list);
+
+		buf_len = (vc->width * vc->height * vc->format->depth) >> 3;
+		if (tw686x_sg_desc_fill(vc->sg_descs[pb], buf, buf_len)) {
+			v4l2_err(&dev->v4l2_dev,
+				 "dma%d: unable to fill %s-buffer\n",
+				 vc->ch, pb ? "B" : "P");
+			vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+			continue;
+		}
+
+		buf->vb.vb2_buf.state = VB2_BUF_STATE_ACTIVE;
+		vc->curr_bufs[pb] = buf;
+		return;
+	}
+
+	vc->curr_bufs[pb] = NULL;
+}
+
+static void tw686x_sg_dma_free(struct tw686x_video_channel *vc,
+			       unsigned int pb)
+{
+	struct tw686x_dma_desc *desc = &vc->dma_descs[pb];
+	struct tw686x_dev *dev = vc->dev;
+
+	if (desc->size) {
+		pci_free_consistent(dev->pci_dev, desc->size,
+				    desc->virt, desc->phys);
+		desc->virt = NULL;
+	}
+
+	vc->sg_descs[pb] = NULL;
+}
+
+static int tw686x_sg_dma_alloc(struct tw686x_video_channel *vc,
+			       unsigned int pb)
+{
+	struct tw686x_dma_desc *desc = &vc->dma_descs[pb];
+	struct tw686x_dev *dev = vc->dev;
+	u32 reg = pb ? DMA_PAGE_TABLE1_ADDR[vc->ch] :
+		       DMA_PAGE_TABLE0_ADDR[vc->ch];
+	void *virt;
+
+	if (desc->size) {
+
+		virt = pci_alloc_consistent(dev->pci_dev, desc->size,
+					    &desc->phys);
+		if (!virt) {
+			v4l2_err(&dev->v4l2_dev,
+				 "dma%d: unable to allocate %s-buffer\n",
+				 vc->ch, pb ? "B" : "P");
+			return -ENOMEM;
+		}
+		desc->virt = virt;
+		reg_write(dev, reg, desc->phys);
 	} else {
-		if (fps >= ARRAY_SIZE(std_625_50))
-			fps = 25;
-		i = std_625_50[fps];
+		virt = dev->video_channels[0].dma_descs[pb].virt +
+		       vc->ch * TW686X_SG_TABLE_SIZE;
 	}
 
-	return map[i];
+	vc->sg_descs[pb] = virt;
+	return 0;
+}
+
+static int tw686x_sg_setup(struct tw686x_dev *dev)
+{
+	unsigned int sg_table_size, pb, ch, channels;
+
+	if (is_second_gen(dev)) {
+		/*
+		 * TW6865/TW6869: each channel needs a pair of
+		 * P-B descriptor tables.
+		 */
+		channels = max_channels(dev);
+		sg_table_size = TW686X_SG_TABLE_SIZE;
+	} else {
+		/*
+		 * TW6864/TW6868: we need to allocate a pair of
+		 * P-B descriptor tables, common for all channels.
+		 * Each table will be bigger than 4 KB.
+		 */
+		channels = 1;
+		sg_table_size = max_channels(dev) * TW686X_SG_TABLE_SIZE;
+	}
+
+	for (ch = 0; ch < channels; ch++) {
+		struct tw686x_video_channel *vc = &dev->video_channels[ch];
+
+		for (pb = 0; pb < 2; pb++)
+			vc->dma_descs[pb].size = sg_table_size;
+	}
+
+	return 0;
+}
+
+static const struct tw686x_dma_ops sg_dma_ops = {
+	.setup		= tw686x_sg_setup,
+	.alloc		= tw686x_sg_dma_alloc,
+	.free		= tw686x_sg_dma_free,
+	.buf_refill	= tw686x_sg_buf_refill,
+	.mem_ops	= &vb2_dma_sg_memops,
+	.hw_dma_mode	= TW686X_SG_MODE,
+	.field		= V4L2_FIELD_SEQ_TB,
+};
+
+static const unsigned int fps_map[15] = {
+	/*
+	 * bit 31 enables selecting the field control register
+	 * bits 0-29 are a bitmask with fields that will be output.
+	 * For NTSC (and PAL-M, PAL-60), all 30 bits are used.
+	 * For other PAL standards, only the first 25 bits are used.
+	 */
+	0x00000000, /* output all fields */
+	0x80000006, /* 2 fps (60Hz), 2 fps (50Hz) */
+	0x80018006, /* 4 fps (60Hz), 4 fps (50Hz) */
+	0x80618006, /* 6 fps (60Hz), 6 fps (50Hz) */
+	0x81818186, /* 8 fps (60Hz), 8 fps (50Hz) */
+	0x86186186, /* 10 fps (60Hz), 8 fps (50Hz) */
+	0x86619866, /* 12 fps (60Hz), 10 fps (50Hz) */
+	0x86666666, /* 14 fps (60Hz), 12 fps (50Hz) */
+	0x9999999e, /* 16 fps (60Hz), 14 fps (50Hz) */
+	0x99e6799e, /* 18 fps (60Hz), 16 fps (50Hz) */
+	0x9e79e79e, /* 20 fps (60Hz), 16 fps (50Hz) */
+	0x9e7e7e7e, /* 22 fps (60Hz), 18 fps (50Hz) */
+	0x9fe7f9fe, /* 24 fps (60Hz), 20 fps (50Hz) */
+	0x9ffe7ffe, /* 26 fps (60Hz), 22 fps (50Hz) */
+	0x9ffffffe, /* 28 fps (60Hz), 24 fps (50Hz) */
+};
+
+static unsigned int tw686x_real_fps(unsigned int index, unsigned int max_fps)
+{
+	unsigned long mask;
+
+	if (!index || index >= ARRAY_SIZE(fps_map))
+		return max_fps;
+
+	mask = GENMASK(max_fps - 1, 0);
+	return hweight_long(fps_map[index] & mask);
+}
+
+static unsigned int tw686x_fps_idx(unsigned int fps, unsigned int max_fps)
+{
+	unsigned int idx, real_fps;
+	int delta;
+
+	/* First guess */
+	idx = (12 + 15 * fps) / max_fps;
+
+	/* Minimal possible framerate is 2 frames per second */
+	if (!idx)
+		return 1;
+
+	/* Check if the difference is bigger than abs(1) and adjust */
+	real_fps = tw686x_real_fps(idx, max_fps);
+	delta = real_fps - fps;
+	if (delta < -1)
+		idx++;
+	else if (delta > 1)
+		idx--;
+
+	/* Max framerate */
+	if (idx >= 15)
+		return 0;
+
+	return idx;
 }
 
 static void tw686x_set_framerate(struct tw686x_video_channel *vc,
 				 unsigned int fps)
 {
-	unsigned int map;
-
-	if (vc->fps == fps)
-		return;
+	unsigned int i;
 
-	map = tw686x_fields_map(vc->video_standard, fps) << 1;
-	map |= map << 1;
-	if (map > 0)
-		map |= BIT(31);
-	reg_write(vc->dev, VIDEO_FIELD_CTRL[vc->ch], map);
-	vc->fps = fps;
+	i = tw686x_fps_idx(fps, TW686X_MAX_FPS(vc->video_standard));
+	reg_write(vc->dev, VIDEO_FIELD_CTRL[vc->ch], fps_map[i]);
+	vc->fps = tw686x_real_fps(i, TW686X_MAX_FPS(vc->video_standard));
 }
 
 static const struct tw686x_format *format_by_fourcc(unsigned int fourcc)
@@ -104,7 +425,7 @@ static const struct tw686x_format *format_by_fourcc(unsigned int fourcc)
 
 static int tw686x_queue_setup(struct vb2_queue *vq,
 			      unsigned int *nbuffers, unsigned int *nplanes,
-			      unsigned int sizes[], void *alloc_ctxs[])
+			      unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct tw686x_video_channel *vc = vb2_get_drv_priv(vq);
 	unsigned int szimage =
@@ -152,75 +473,6 @@ static void tw686x_buf_queue(struct vb2_buffer *vb)
 	spin_unlock_irqrestore(&vc->qlock, flags);
 }
 
-/*
- * We can call this even when alloc_dma failed for the given channel
- */
-static void tw686x_free_dma(struct tw686x_video_channel *vc, unsigned int pb)
-{
-	struct tw686x_dma_desc *desc = &vc->dma_descs[pb];
-	struct tw686x_dev *dev = vc->dev;
-	struct pci_dev *pci_dev;
-	unsigned long flags;
-
-	/* Check device presence. Shouldn't really happen! */
-	spin_lock_irqsave(&dev->lock, flags);
-	pci_dev = dev->pci_dev;
-	spin_unlock_irqrestore(&dev->lock, flags);
-	if (!pci_dev) {
-		WARN(1, "trying to deallocate on missing device\n");
-		return;
-	}
-
-	if (desc->virt) {
-		pci_free_consistent(dev->pci_dev, desc->size,
-				    desc->virt, desc->phys);
-		desc->virt = NULL;
-	}
-}
-
-static int tw686x_alloc_dma(struct tw686x_video_channel *vc, unsigned int pb)
-{
-	struct tw686x_dev *dev = vc->dev;
-	u32 reg = pb ? VDMA_B_ADDR[vc->ch] : VDMA_P_ADDR[vc->ch];
-	unsigned int len;
-	void *virt;
-
-	WARN(vc->dma_descs[pb].virt,
-	     "Allocating buffer but previous still here\n");
-
-	len = (vc->width * vc->height * vc->format->depth) >> 3;
-	virt = pci_alloc_consistent(dev->pci_dev, len,
-				    &vc->dma_descs[pb].phys);
-	if (!virt) {
-		v4l2_err(&dev->v4l2_dev,
-			 "dma%d: unable to allocate %s-buffer\n",
-			 vc->ch, pb ? "B" : "P");
-		return -ENOMEM;
-	}
-	vc->dma_descs[pb].size = len;
-	vc->dma_descs[pb].virt = virt;
-	reg_write(dev, reg, vc->dma_descs[pb].phys);
-
-	return 0;
-}
-
-static void tw686x_buffer_refill(struct tw686x_video_channel *vc,
-				 unsigned int pb)
-{
-	struct tw686x_v4l2_buf *buf;
-
-	while (!list_empty(&vc->vidq_queued)) {
-
-		buf = list_first_entry(&vc->vidq_queued,
-			struct tw686x_v4l2_buf, list);
-		list_del(&buf->list);
-
-		vc->curr_bufs[pb] = buf;
-		return;
-	}
-	vc->curr_bufs[pb] = NULL;
-}
-
 static void tw686x_clear_queue(struct tw686x_video_channel *vc,
 			       enum vb2_buffer_state state)
 {
@@ -262,7 +514,8 @@ static int tw686x_start_streaming(struct vb2_queue *vq, unsigned int count)
 	spin_lock_irqsave(&vc->qlock, flags);
 
 	/* Sanity check */
-	if (!vc->dma_descs[0].virt || !vc->dma_descs[1].virt) {
+	if (dev->dma_mode == TW686X_DMA_MODE_MEMCPY &&
+	    (!vc->dma_descs[0].virt || !vc->dma_descs[1].virt)) {
 		spin_unlock_irqrestore(&vc->qlock, flags);
 		v4l2_err(&dev->v4l2_dev,
 			 "video%d: refusing to start without DMA buffers\n",
@@ -272,7 +525,7 @@ static int tw686x_start_streaming(struct vb2_queue *vq, unsigned int count)
 	}
 
 	for (pb = 0; pb < 2; pb++)
-		tw686x_buffer_refill(vc, pb);
+		dev->dma_ops->buf_refill(vc, pb);
 	spin_unlock_irqrestore(&vc->qlock, flags);
 
 	vc->sequence = 0;
@@ -375,10 +628,11 @@ static int tw686x_g_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
 	struct tw686x_video_channel *vc = video_drvdata(file);
+	struct tw686x_dev *dev = vc->dev;
 
 	f->fmt.pix.width = vc->width;
 	f->fmt.pix.height = vc->height;
-	f->fmt.pix.field = V4L2_FIELD_INTERLACED;
+	f->fmt.pix.field = dev->dma_ops->field;
 	f->fmt.pix.pixelformat = vc->format->fourcc;
 	f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M;
 	f->fmt.pix.bytesperline = (f->fmt.pix.width * vc->format->depth) / 8;
@@ -390,6 +644,7 @@ static int tw686x_try_fmt_vid_cap(struct file *file, void *priv,
 				  struct v4l2_format *f)
 {
 	struct tw686x_video_channel *vc = video_drvdata(file);
+	struct tw686x_dev *dev = vc->dev;
 	unsigned int video_height = TW686X_VIDEO_HEIGHT(vc->video_standard);
 	const struct tw686x_format *format;
 
@@ -412,7 +667,7 @@ static int tw686x_try_fmt_vid_cap(struct file *file, void *priv,
 	f->fmt.pix.bytesperline = (f->fmt.pix.width * format->depth) / 8;
 	f->fmt.pix.sizeimage = f->fmt.pix.height * f->fmt.pix.bytesperline;
 	f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M;
-	f->fmt.pix.field = V4L2_FIELD_INTERLACED;
+	f->fmt.pix.field = dev->dma_ops->field;
 
 	return 0;
 }
@@ -421,6 +676,7 @@ static int tw686x_s_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
 	struct tw686x_video_channel *vc = video_drvdata(file);
+	struct tw686x_dev *dev = vc->dev;
 	u32 val, width, line_width, height;
 	unsigned long bitsperframe;
 	int err, pb;
@@ -438,15 +694,16 @@ static int tw686x_s_fmt_vid_cap(struct file *file, void *priv,
 	vc->height = f->fmt.pix.height;
 
 	/* We need new DMA buffers if the framesize has changed */
-	if (bitsperframe != vc->width * vc->height * vc->format->depth) {
+	if (dev->dma_ops->alloc &&
+	    bitsperframe != vc->width * vc->height * vc->format->depth) {
 		for (pb = 0; pb < 2; pb++)
-			tw686x_free_dma(vc, pb);
+			dev->dma_ops->free(vc, pb);
 
 		for (pb = 0; pb < 2; pb++) {
-			err = tw686x_alloc_dma(vc, pb);
+			err = dev->dma_ops->alloc(vc, pb);
 			if (err) {
 				if (pb > 0)
-					tw686x_free_dma(vc, 0);
+					dev->dma_ops->free(vc, 0);
 				return err;
 			}
 		}
@@ -464,6 +721,19 @@ static int tw686x_s_fmt_vid_cap(struct file *file, void *priv,
 	else
 		val &= ~BIT(24);
 
+	val &= ~0x7ffff;
+
+	/* Program the DMA scatter-gather */
+	if (dev->dma_mode == TW686X_DMA_MODE_SG) {
+		u32 start_idx, end_idx;
+
+		start_idx = is_second_gen(dev) ?
+				0 : vc->ch * TW686X_MAX_SG_DESC_COUNT;
+		end_idx = start_idx + TW686X_MAX_SG_DESC_COUNT - 1;
+
+		val |= (end_idx << 10) | start_idx;
+	}
+
 	val &= ~(0x7 << 20);
 	val |= vc->format->mode << 20;
 	reg_write(vc->dev, VDMA_CHANNEL_CONFIG[vc->ch], val);
@@ -540,6 +810,12 @@ static int tw686x_s_std(struct file *file, void *priv, v4l2_std_id id)
 	ret = tw686x_g_fmt_vid_cap(file, priv, &f);
 	if (!ret)
 		tw686x_s_fmt_vid_cap(file, priv, &f);
+
+	/*
+	 * Frame decimation depends on the chosen standard,
+	 * so reset it to the current value.
+	 */
+	tw686x_set_framerate(vc, vc->fps);
 	return 0;
 }
 
@@ -609,6 +885,40 @@ static int tw686x_g_std(struct file *file, void *priv, v4l2_std_id *id)
 	return 0;
 }
 
+static int tw686x_g_parm(struct file *file, void *priv,
+			 struct v4l2_streamparm *sp)
+{
+	struct tw686x_video_channel *vc = video_drvdata(file);
+	struct v4l2_captureparm *cp = &sp->parm.capture;
+
+	if (sp->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+	sp->parm.capture.readbuffers = 3;
+
+	cp->capability = V4L2_CAP_TIMEPERFRAME;
+	cp->timeperframe.numerator = 1;
+	cp->timeperframe.denominator = vc->fps;
+	return 0;
+}
+
+static int tw686x_s_parm(struct file *file, void *priv,
+			 struct v4l2_streamparm *sp)
+{
+	struct tw686x_video_channel *vc = video_drvdata(file);
+	struct v4l2_captureparm *cp = &sp->parm.capture;
+	unsigned int denominator = cp->timeperframe.denominator;
+	unsigned int numerator = cp->timeperframe.numerator;
+	unsigned int fps;
+
+	if (vb2_is_busy(&vc->vidq))
+		return -EBUSY;
+
+	fps = (!numerator || !denominator) ? 0 : denominator / numerator;
+	if (vc->fps != fps)
+		tw686x_set_framerate(vc, fps);
+	return tw686x_g_parm(file, priv, sp);
+}
+
 static int tw686x_enum_fmt_vid_cap(struct file *file, void *priv,
 				   struct v4l2_fmtdesc *f)
 {
@@ -695,6 +1005,9 @@ static const struct v4l2_ioctl_ops tw686x_video_ioctl_ops = {
 	.vidioc_g_std			= tw686x_g_std,
 	.vidioc_s_std			= tw686x_s_std,
 
+	.vidioc_g_parm			= tw686x_g_parm,
+	.vidioc_s_parm			= tw686x_s_parm,
+
 	.vidioc_enum_input		= tw686x_enum_input,
 	.vidioc_g_input			= tw686x_g_input,
 	.vidioc_s_input			= tw686x_s_input,
@@ -713,26 +1026,11 @@ static const struct v4l2_ioctl_ops tw686x_video_ioctl_ops = {
 	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
 };
 
-static void tw686x_buffer_copy(struct tw686x_video_channel *vc,
-			       unsigned int pb, struct vb2_v4l2_buffer *vb)
-{
-	struct tw686x_dma_desc *desc = &vc->dma_descs[pb];
-	struct vb2_buffer *vb2_buf = &vb->vb2_buf;
-
-	vb->field = V4L2_FIELD_INTERLACED;
-	vb->sequence = vc->sequence++;
-
-	memcpy(vb2_plane_vaddr(vb2_buf, 0), desc->virt, desc->size);
-	vb2_buf->timestamp = ktime_get_ns();
-	vb2_buffer_done(vb2_buf, VB2_BUF_STATE_DONE);
-}
-
 void tw686x_video_irq(struct tw686x_dev *dev, unsigned long requests,
 		      unsigned int pb_status, unsigned int fifo_status,
 		      unsigned int *reset_ch)
 {
 	struct tw686x_video_channel *vc;
-	struct vb2_v4l2_buffer *vb;
 	unsigned long flags;
 	unsigned int ch, pb;
 
@@ -781,14 +1079,9 @@ void tw686x_video_irq(struct tw686x_dev *dev, unsigned long requests,
 			continue;
 		}
 
-		/* handle video stream */
 		spin_lock_irqsave(&vc->qlock, flags);
-		if (vc->curr_bufs[pb]) {
-			vb = &vc->curr_bufs[pb]->vb;
-			tw686x_buffer_copy(vc, pb, vb);
-		}
-		vc->pb = !pb;
-		tw686x_buffer_refill(vc, pb);
+		tw686x_buf_done(vc, pb);
+		dev->dma_ops->buf_refill(vc, pb);
 		spin_unlock_irqrestore(&vc->qlock, flags);
 	}
 }
@@ -803,8 +1096,9 @@ void tw686x_video_free(struct tw686x_dev *dev)
 		if (vc->device)
 			video_unregister_device(vc->device);
 
-		for (pb = 0; pb < 2; pb++)
-			tw686x_free_dma(vc, pb);
+		if (dev->dma_ops->free)
+			for (pb = 0; pb < 2; pb++)
+				dev->dma_ops->free(vc, pb);
 	}
 }
 
@@ -813,10 +1107,25 @@ int tw686x_video_init(struct tw686x_dev *dev)
 	unsigned int ch, val, pb;
 	int err;
 
+	if (dev->dma_mode == TW686X_DMA_MODE_MEMCPY)
+		dev->dma_ops = &memcpy_dma_ops;
+	else if (dev->dma_mode == TW686X_DMA_MODE_CONTIG)
+		dev->dma_ops = &contig_dma_ops;
+	else if (dev->dma_mode == TW686X_DMA_MODE_SG)
+		dev->dma_ops = &sg_dma_ops;
+	else
+		return -EINVAL;
+
 	err = v4l2_device_register(&dev->pci_dev->dev, &dev->v4l2_dev);
 	if (err)
 		return err;
 
+	if (dev->dma_ops->setup) {
+		err = dev->dma_ops->setup(dev);
+		if (err)
+			return err;
+	}
+
 	for (ch = 0; ch < max_channels(dev); ch++) {
 		struct tw686x_video_channel *vc = &dev->video_channels[ch];
 		struct video_device *vdev;
@@ -842,10 +1151,12 @@ int tw686x_video_init(struct tw686x_dev *dev)
 		reg_write(dev, HACTIVE_LO[ch], 0xd0);
 		reg_write(dev, VIDEO_SIZE[ch], 0);
 
-		for (pb = 0; pb < 2; pb++) {
-			err = tw686x_alloc_dma(vc, pb);
-			if (err)
-				goto error;
+		if (dev->dma_ops->alloc) {
+			for (pb = 0; pb < 2; pb++) {
+				err = dev->dma_ops->alloc(vc, pb);
+				if (err)
+					goto error;
+			}
 		}
 
 		vc->vidq.io_modes = VB2_READ | VB2_MMAP | VB2_DMABUF;
@@ -853,11 +1164,12 @@ int tw686x_video_init(struct tw686x_dev *dev)
 		vc->vidq.drv_priv = vc;
 		vc->vidq.buf_struct_size = sizeof(struct tw686x_v4l2_buf);
 		vc->vidq.ops = &tw686x_video_qops;
-		vc->vidq.mem_ops = &vb2_vmalloc_memops;
+		vc->vidq.mem_ops = dev->dma_ops->mem_ops;
 		vc->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		vc->vidq.min_buffers_needed = 2;
 		vc->vidq.lock = &vc->vb_mutex;
 		vc->vidq.gfp_flags = GFP_DMA32;
+		vc->vidq.dev = &dev->pci_dev->dev;
 
 		err = vb2_queue_init(&vc->vidq);
 		if (err) {
@@ -915,10 +1227,9 @@ int tw686x_video_init(struct tw686x_dev *dev)
 		vc->num = vdev->num;
 	}
 
-	/* Set DMA frame mode on all channels. Only supported mode for now. */
 	val = TW686X_DEF_PHASE_REF;
 	for (ch = 0; ch < max_channels(dev); ch++)
-		val |= TW686X_FRAME_MODE << (16 + ch * 2);
+		val |= dev->dma_ops->hw_dma_mode << (16 + ch * 2);
 	reg_write(dev, PHASE_REF, val);
 
 	reg_write(dev, MISC2[0], 0xe7);
diff --git a/drivers/media/pci/tw686x/tw686x.h b/drivers/media/pci/tw686x/tw686x.h
index 44b5755acf02..f24a2a9bcdb2 100644
--- a/drivers/media/pci/tw686x/tw686x.h
+++ b/drivers/media/pci/tw686x/tw686x.h
@@ -27,16 +27,14 @@
 #define TYPE_SECOND_GEN		0x10
 #define TW686X_DEF_PHASE_REF	0x1518
 
-#define TW686X_FIELD_MODE	0x3
-#define TW686X_FRAME_MODE	0x2
-/* 0x1 is reserved */
-#define TW686X_SG_MODE		0x0
-
-#define TW686X_AUDIO_PAGE_SZ		4096
 #define TW686X_AUDIO_PAGE_MAX		16
 #define TW686X_AUDIO_PERIODS_MIN	2
 #define TW686X_AUDIO_PERIODS_MAX	TW686X_AUDIO_PAGE_MAX
 
+#define TW686X_DMA_MODE_MEMCPY		0
+#define TW686X_DMA_MODE_CONTIG		1
+#define TW686X_DMA_MODE_SG		2
+
 struct tw686x_format {
 	char *name;
 	unsigned int fourcc;
@@ -50,6 +48,12 @@ struct tw686x_dma_desc {
 	unsigned int size;
 };
 
+struct tw686x_sg_desc {
+	/* 3 MSBits for flags, 13 LSBits for length */
+	__le32 flags_length;
+	__le32 phys;
+};
+
 struct tw686x_audio_buf {
 	dma_addr_t dma;
 	void *virt;
@@ -82,6 +86,7 @@ struct tw686x_video_channel {
 	struct video_device *device;
 	struct tw686x_v4l2_buf *curr_bufs[2];
 	struct tw686x_dma_desc dma_descs[2];
+	struct tw686x_sg_desc *sg_descs[2];
 
 	struct v4l2_ctrl_handler ctrl_handler;
 	const struct tw686x_format *format;
@@ -99,6 +104,16 @@ struct tw686x_video_channel {
 	bool no_signal;
 };
 
+struct tw686x_dma_ops {
+	int (*setup)(struct tw686x_dev *dev);
+	int (*alloc)(struct tw686x_video_channel *vc, unsigned int pb);
+	void (*free)(struct tw686x_video_channel *vc, unsigned int pb);
+	void (*buf_refill)(struct tw686x_video_channel *vc, unsigned int pb);
+	const struct vb2_mem_ops *mem_ops;
+	enum v4l2_field field;
+	u32 hw_dma_mode;
+};
+
 /**
  * struct tw686x_dev - global device status
  * @lock: spinlock controlling access to the
@@ -112,15 +127,18 @@ struct tw686x_dev {
 
 	char name[32];
 	unsigned int type;
+	unsigned int dma_mode;
 	struct pci_dev *pci_dev;
 	__u32 __iomem *mmio;
 
-	void *alloc_ctx;
-
+	const struct tw686x_dma_ops *dma_ops;
 	struct tw686x_video_channel *video_channels;
 	struct tw686x_audio_channel *audio_channels;
 
-	int audio_rate; /* per-device value */
+	/* Per-device audio parameters */
+	int audio_rate;
+	int period_size;
+	int audio_enabled;
 
 	struct timer_list dma_delay_timer;
 	u32 pending_dma_en; /* must be protected by lock */
@@ -143,6 +161,12 @@ static inline unsigned int max_channels(struct tw686x_dev *dev)
 	return dev->type & TYPE_MAX_CHANNELS; /* 4 or 8 channels */
 }
 
+static inline unsigned is_second_gen(struct tw686x_dev *dev)
+{
+	/* each channel has its own DMA SG table */
+	return dev->type & TYPE_SECOND_GEN;
+}
+
 void tw686x_enable_channel(struct tw686x_dev *dev, unsigned int channel);
 void tw686x_disable_channel(struct tw686x_dev *dev, unsigned int channel);
 
diff --git a/drivers/media/pci/zoran/zr36016.c b/drivers/media/pci/zoran/zr36016.c
index b87ddba8608f..c12ca9f96bac 100644
--- a/drivers/media/pci/zoran/zr36016.c
+++ b/drivers/media/pci/zoran/zr36016.c
@@ -246,10 +246,6 @@ static int zr36016_pushit (struct zr36016 *ptr,
    //TODO//
    ========================================================================= */
 
-// needed offset values          PAL NTSC SECAM
-static const int zr016_xoff[] = { 20, 20, 20 };
-static const int zr016_yoff[] = { 8, 9, 7 };
-
 static void
 zr36016_init (struct zr36016 *ptr)
 {
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 84e041c0a70e..f25344bc7912 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -110,6 +110,7 @@ source "drivers/media/platform/exynos4-is/Kconfig"
 source "drivers/media/platform/s5p-tv/Kconfig"
 source "drivers/media/platform/am437x/Kconfig"
 source "drivers/media/platform/xilinx/Kconfig"
+source "drivers/media/platform/rcar-vin/Kconfig"
 
 config VIDEO_TI_CAL
 	tristate "TI CAL (Camera Adaptation Layer) driver"
@@ -152,6 +153,36 @@ config VIDEO_CODA
 	   Coda is a range of video codec IPs that supports
 	   H.264, MPEG-4, and other video formats.
 
+config VIDEO_MEDIATEK_VPU
+	tristate "Mediatek Video Processor Unit"
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	---help---
+	    This driver provides downloading VPU firmware and
+	    communicating with VPU. This driver for hw video
+	    codec embedded in Mediatek's MT8173 SOCs. It is able
+	    to handle video decoding/encoding in a range of formats.
+
+	    To compile this driver as a module, choose M here: the
+	    module will be called mtk-vpu.
+
+config VIDEO_MEDIATEK_VCODEC
+	tristate "Mediatek Video Codec driver"
+	depends on MTK_IOMMU || COMPILE_TEST
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select VIDEOBUF2_DMA_CONTIG
+	select V4L2_MEM2MEM_DEV
+	select VIDEO_MEDIATEK_VPU
+	default n
+	---help---
+	    Mediatek video codec driver provides HW capability to
+	    encode and decode in a range of video formats
+	    This driver rely on VPU driver to communicate with VPU.
+
+	    To compile this driver as a module, choose M here: the
+	    module will be called mtk-vcodec
+
 config VIDEO_MEM2MEM_DEINTERLACE
 	tristate "Deinterlace support"
 	depends on VIDEO_DEV && VIDEO_V4L2 && DMA_ENGINE
@@ -247,10 +278,24 @@ config VIDEO_RENESAS_JPU
 	  To compile this driver as a module, choose M here: the module
 	  will be called rcar_jpu.
 
+config VIDEO_RENESAS_FCP
+	tristate "Renesas Frame Compression Processor"
+	depends on ARCH_RENESAS || COMPILE_TEST
+	depends on OF
+	---help---
+	  This is a driver for the Renesas Frame Compression Processor (FCP).
+	  The FCP is a companion module of video processing modules in the
+	  Renesas R-Car Gen3 SoCs. It handles memory access for the codec,
+	  VSP and FDP modules.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called rcar-fcp.
+
 config VIDEO_RENESAS_VSP1
 	tristate "Renesas VSP1 Video Processing Engine"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && HAS_DMA
 	depends on (ARCH_RENESAS && OF) || COMPILE_TEST
+	depends on (!ARM64 && !VIDEO_RENESAS_FCP) || VIDEO_RENESAS_FCP
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  This is a V4L2 driver for the Renesas VSP1 video processing engine.
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index bbb7bd1eb268..21771c1a13fb 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -46,6 +46,7 @@ obj-$(CONFIG_VIDEO_SH_VOU)		+= sh_vou.o
 
 obj-$(CONFIG_SOC_CAMERA)		+= soc_camera/
 
+obj-$(CONFIG_VIDEO_RENESAS_FCP) 	+= rcar-fcp.o
 obj-$(CONFIG_VIDEO_RENESAS_JPU) 	+= rcar_jpu.o
 obj-$(CONFIG_VIDEO_RENESAS_VSP1)	+= vsp1/
 
@@ -55,4 +56,10 @@ obj-$(CONFIG_VIDEO_AM437X_VPFE)		+= am437x/
 
 obj-$(CONFIG_VIDEO_XILINX)		+= xilinx/
 
+obj-$(CONFIG_VIDEO_RCAR_VIN)		+= rcar-vin/
+
 ccflags-y += -I$(srctree)/drivers/media/i2c
+
+obj-$(CONFIG_VIDEO_MEDIATEK_VPU)	+= mtk-vpu/
+
+obj-$(CONFIG_VIDEO_MEDIATEK_VCODEC)	+= mtk-vcodec/
diff --git a/drivers/media/platform/am437x/am437x-vpfe.c b/drivers/media/platform/am437x/am437x-vpfe.c
index e749eb7c3be9..b33b9e35e60e 100644
--- a/drivers/media/platform/am437x/am437x-vpfe.c
+++ b/drivers/media/platform/am437x/am437x-vpfe.c
@@ -1901,21 +1901,20 @@ static void vpfe_calculate_offsets(struct vpfe_device *vpfe)
  * @nbuffers: ptr to number of buffers requested by application
  * @nplanes:: contains number of distinct video planes needed to hold a frame
  * @sizes[]: contains the size (in bytes) of each plane.
- * @alloc_ctxs: ptr to allocation context
+ * @alloc_devs: ptr to allocation context
  *
  * This callback function is called when reqbuf() is called to adjust
  * the buffer count and buffer size
  */
 static int vpfe_queue_setup(struct vb2_queue *vq,
 			    unsigned int *nbuffers, unsigned int *nplanes,
-			    unsigned int sizes[], void *alloc_ctxs[])
+			    unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct vpfe_device *vpfe = vb2_get_drv_priv(vq);
 	unsigned size = vpfe->fmt.fmt.pix.sizeimage;
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
-	alloc_ctxs[0] = vpfe->alloc_ctx;
 
 	if (*nplanes) {
 		if (sizes[0] < size)
@@ -2364,13 +2363,6 @@ static int vpfe_probe_complete(struct vpfe_device *vpfe)
 		goto probe_out;
 
 	/* Initialize videobuf2 queue as per the buffer type */
-	vpfe->alloc_ctx = vb2_dma_contig_init_ctx(vpfe->pdev);
-	if (IS_ERR(vpfe->alloc_ctx)) {
-		vpfe_err(vpfe, "Failed to get the context\n");
-		err = PTR_ERR(vpfe->alloc_ctx);
-		goto probe_out;
-	}
-
 	q = &vpfe->buffer_queue;
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
@@ -2381,11 +2373,11 @@ static int vpfe_probe_complete(struct vpfe_device *vpfe)
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &vpfe->lock;
 	q->min_buffers_needed = 1;
+	q->dev = vpfe->pdev;
 
 	err = vb2_queue_init(q);
 	if (err) {
 		vpfe_err(vpfe, "vb2_queue_init() failed\n");
-		vb2_dma_contig_cleanup_ctx(vpfe->alloc_ctx);
 		goto probe_out;
 	}
 
diff --git a/drivers/media/platform/am437x/am437x-vpfe.h b/drivers/media/platform/am437x/am437x-vpfe.h
index 777bf97fea57..17d7aa426788 100644
--- a/drivers/media/platform/am437x/am437x-vpfe.h
+++ b/drivers/media/platform/am437x/am437x-vpfe.h
@@ -264,8 +264,6 @@ struct vpfe_device {
 	struct v4l2_rect crop;
 	/* Buffer queue used in video-buf */
 	struct vb2_queue buffer_queue;
-	/* Allocator-specific contexts for each plane */
-	struct vb2_alloc_ctx *alloc_ctx;
 	/* Queue of filled frames */
 	struct list_head dma_queue;
 	/* IRQ lock for DMA queue */
diff --git a/drivers/media/platform/blackfin/bfin_capture.c b/drivers/media/platform/blackfin/bfin_capture.c
index d0092dae7a57..8eb03397d736 100644
--- a/drivers/media/platform/blackfin/bfin_capture.c
+++ b/drivers/media/platform/blackfin/bfin_capture.c
@@ -91,8 +91,6 @@ struct bcap_device {
 	struct bcap_buffer *cur_frm;
 	/* buffer queue used in videobuf2 */
 	struct vb2_queue buffer_queue;
-	/* allocator-specific contexts for each plane */
-	struct vb2_alloc_ctx *alloc_ctx;
 	/* queue of filled frames */
 	struct list_head dma_queue;
 	/* used in videobuf2 callback */
@@ -203,13 +201,12 @@ static void bcap_free_sensor_formats(struct bcap_device *bcap_dev)
 
 static int bcap_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct bcap_device *bcap_dev = vb2_get_drv_priv(vq);
 
 	if (vq->num_buffers + *nbuffers < 2)
 		*nbuffers = 2;
-	alloc_ctxs[0] = bcap_dev->alloc_ctx;
 
 	if (*nplanes)
 		return sizes[0] < bcap_dev->fmt.sizeimage ? -EINVAL : 0;
@@ -820,12 +817,6 @@ static int bcap_probe(struct platform_device *pdev)
 	}
 	bcap_dev->ppi->priv = bcap_dev;
 
-	bcap_dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(bcap_dev->alloc_ctx)) {
-		ret = PTR_ERR(bcap_dev->alloc_ctx);
-		goto err_free_ppi;
-	}
-
 	vfd = &bcap_dev->video_dev;
 	/* initialize field of video device */
 	vfd->release            = video_device_release_empty;
@@ -839,7 +830,7 @@ static int bcap_probe(struct platform_device *pdev)
 	if (ret) {
 		v4l2_err(pdev->dev.driver,
 				"Unable to register v4l2 device\n");
-		goto err_cleanup_ctx;
+		goto err_free_ppi;
 	}
 	v4l2_info(&bcap_dev->v4l2_dev, "v4l2 device registered\n");
 
@@ -863,6 +854,7 @@ static int bcap_probe(struct platform_device *pdev)
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &bcap_dev->mutex;
 	q->min_buffers_needed = 1;
+	q->dev = &pdev->dev;
 
 	ret = vb2_queue_init(q);
 	if (ret)
@@ -967,8 +959,6 @@ err_free_handler:
 	v4l2_ctrl_handler_free(&bcap_dev->ctrl_handler);
 err_unreg_v4l2:
 	v4l2_device_unregister(&bcap_dev->v4l2_dev);
-err_cleanup_ctx:
-	vb2_dma_contig_cleanup_ctx(bcap_dev->alloc_ctx);
 err_free_ppi:
 	ppi_delete_instance(bcap_dev->ppi);
 err_free_dev:
@@ -986,7 +976,6 @@ static int bcap_remove(struct platform_device *pdev)
 	video_unregister_device(&bcap_dev->video_dev);
 	v4l2_ctrl_handler_free(&bcap_dev->ctrl_handler);
 	v4l2_device_unregister(v4l2_dev);
-	vb2_dma_contig_cleanup_ctx(bcap_dev->alloc_ctx);
 	ppi_delete_instance(bcap_dev->ppi);
 	kfree(bcap_dev);
 	return 0;
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 133ab9f70f85..c39718a63e5e 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -1139,7 +1139,7 @@ static void set_default_params(struct coda_ctx *ctx)
  */
 static int coda_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct coda_ctx *ctx = vb2_get_drv_priv(vq);
 	struct coda_q_data *q_data;
@@ -1151,9 +1151,6 @@ static int coda_queue_setup(struct vb2_queue *vq,
 	*nplanes = 1;
 	sizes[0] = size;
 
-	/* Set to vb2-dma-contig allocator context, ignored by vb2-vmalloc */
-	alloc_ctxs[0] = ctx->dev->alloc_ctx;
-
 	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
 		 "get %d buffer(s) of size %d each.\n", *nbuffers, size);
 
@@ -1599,6 +1596,7 @@ static int coda_queue_init(struct coda_ctx *ctx, struct vb2_queue *vq)
 	 * that videobuf2 will keep the value of bytesused intact.
 	 */
 	vq->allow_zero_bytesused = 1;
+	vq->dev = &ctx->dev->plat_dev->dev;
 
 	return vb2_queue_init(vq);
 }
@@ -2040,16 +2038,10 @@ static void coda_fw_callback(const struct firmware *fw, void *context)
 	if (ret < 0)
 		goto put_pm;
 
-	dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		v4l2_err(&dev->v4l2_dev, "Failed to alloc vb2 context\n");
-		goto put_pm;
-	}
-
 	dev->m2m_dev = v4l2_m2m_init(&coda_m2m_ops);
 	if (IS_ERR(dev->m2m_dev)) {
 		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem device\n");
-		goto rel_ctx;
+		goto put_pm;
 	}
 
 	for (i = 0; i < dev->devtype->num_vdevs; i++) {
@@ -2072,8 +2064,6 @@ rel_vfd:
 	while (--i >= 0)
 		video_unregister_device(&dev->vfd[i]);
 	v4l2_m2m_release(dev->m2m_dev);
-rel_ctx:
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
 put_pm:
 	pm_runtime_put_sync(&pdev->dev);
 }
@@ -2226,7 +2216,7 @@ static int coda_probe(struct platform_device *pdev)
 	dev->rstc = devm_reset_control_get_optional(&pdev->dev, NULL);
 	if (IS_ERR(dev->rstc)) {
 		ret = PTR_ERR(dev->rstc);
-		if (ret == -ENOENT || ret == -ENOSYS) {
+		if (ret == -ENOENT || ret == -ENOTSUPP) {
 			dev->rstc = NULL;
 		} else {
 			dev_err(&pdev->dev, "failed get reset control: %d\n",
@@ -2324,8 +2314,6 @@ static int coda_remove(struct platform_device *pdev)
 	if (dev->m2m_dev)
 		v4l2_m2m_release(dev->m2m_dev);
 	pm_runtime_disable(&pdev->dev);
-	if (dev->alloc_ctx)
-		vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
 	v4l2_device_unregister(&dev->v4l2_dev);
 	destroy_workqueue(dev->workqueue);
 	if (dev->iram.vaddr)
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index 8f2c71e06966..53f96661683c 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -92,7 +92,6 @@ struct coda_dev {
 	struct mutex		coda_mutex;
 	struct workqueue_struct	*workqueue;
 	struct v4l2_m2m_dev	*m2m_dev;
-	struct vb2_alloc_ctx	*alloc_ctx;
 	struct list_head	instances;
 	unsigned long		instance_mask;
 	struct dentry		*debugfs_root;
diff --git a/drivers/media/platform/davinci/ccdc_hw_device.h b/drivers/media/platform/davinci/ccdc_hw_device.h
index 86b9b3518965..ae5605de7679 100644
--- a/drivers/media/platform/davinci/ccdc_hw_device.h
+++ b/drivers/media/platform/davinci/ccdc_hw_device.h
@@ -80,13 +80,6 @@ struct ccdc_hw_ops {
 	/* Pointer to function to get line length */
 	unsigned int (*get_line_length) (void);
 
-	/* Query CCDC control IDs */
-	int (*queryctrl)(struct v4l2_queryctrl *qctrl);
-	/* Set CCDC control */
-	int (*set_control)(struct v4l2_control *ctrl);
-	/* Get CCDC control */
-	int (*get_control)(struct v4l2_control *ctrl);
-
 	/* Pointer to function to set frame buffer address */
 	void (*setfbaddr) (unsigned long addr);
 	/* Pointer to function to get field id */
diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index 0abcdfe97a6c..0b1709e96673 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -230,7 +230,7 @@ static int vpbe_buffer_prepare(struct vb2_buffer *vb)
 static int
 vpbe_buffer_queue_setup(struct vb2_queue *vq,
 			unsigned int *nbuffers, unsigned int *nplanes,
-			unsigned int sizes[], void *alloc_ctxs[])
+			unsigned int sizes[], struct device *alloc_devs[])
 
 {
 	/* Get the file handle object and layer object */
@@ -242,7 +242,6 @@ vpbe_buffer_queue_setup(struct vb2_queue *vq,
 	/* Store number of buffers allocated in numbuffer member */
 	if (vq->num_buffers + *nbuffers < VPBE_DEFAULT_NUM_BUFS)
 		*nbuffers = VPBE_DEFAULT_NUM_BUFS - vq->num_buffers;
-	alloc_ctxs[0] = layer->alloc_ctx;
 
 	if (*nplanes)
 		return sizes[0] < layer->pix_fmt.sizeimage ? -EINVAL : 0;
@@ -1451,20 +1450,13 @@ static int vpbe_display_probe(struct platform_device *pdev)
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		q->min_buffers_needed = 1;
 		q->lock = &disp_dev->dev[i]->opslock;
+		q->dev = disp_dev->vpbe_dev->pdev;
 		err = vb2_queue_init(q);
 		if (err) {
 			v4l2_err(v4l2_dev, "vb2_queue_init() failed\n");
 			goto probe_out;
 		}
 
-		disp_dev->dev[i]->alloc_ctx =
-			vb2_dma_contig_init_ctx(disp_dev->vpbe_dev->pdev);
-		if (IS_ERR(disp_dev->dev[i]->alloc_ctx)) {
-			v4l2_err(v4l2_dev, "Failed to get the context\n");
-			err = PTR_ERR(disp_dev->dev[i]->alloc_ctx);
-			goto probe_out;
-		}
-
 		INIT_LIST_HEAD(&disp_dev->dev[i]->dma_queue);
 
 		if (register_device(disp_dev->dev[i], disp_dev, pdev)) {
@@ -1482,7 +1474,6 @@ probe_out:
 	for (k = 0; k < VPBE_DISPLAY_MAX_DEVICES; k++) {
 		/* Unregister video device */
 		if (disp_dev->dev[k] != NULL) {
-			vb2_dma_contig_cleanup_ctx(disp_dev->dev[k]->alloc_ctx);
 			video_unregister_device(&disp_dev->dev[k]->video_dev);
 			kfree(disp_dev->dev[k]);
 		}
@@ -1510,7 +1501,6 @@ static int vpbe_display_remove(struct platform_device *pdev)
 	for (i = 0; i < VPBE_DISPLAY_MAX_DEVICES; i++) {
 		/* Get the pointer to the layer object */
 		vpbe_display_layer = disp_dev->dev[i];
-		vb2_dma_contig_cleanup_ctx(vpbe_display_layer->alloc_ctx);
 		/* Unregister video device */
 		video_unregister_device(&vpbe_display_layer->video_dev);
 
diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c
index 08f7028c7560..5104cc0ee40e 100644
--- a/drivers/media/platform/davinci/vpif_capture.c
+++ b/drivers/media/platform/davinci/vpif_capture.c
@@ -107,14 +107,14 @@ static int vpif_buffer_prepare(struct vb2_buffer *vb)
  * @nbuffers: ptr to number of buffers requested by application
  * @nplanes:: contains number of distinct video planes needed to hold a frame
  * @sizes[]: contains the size (in bytes) of each plane.
- * @alloc_ctxs: ptr to allocation context
+ * @alloc_devs: ptr to allocation context
  *
  * This callback function is called when reqbuf() is called to adjust
  * the buffer count and buffer size
  */
 static int vpif_buffer_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct channel_obj *ch = vb2_get_drv_priv(vq);
 	struct common_obj *common = &ch->common[VPIF_VIDEO_INDEX];
@@ -133,7 +133,6 @@ static int vpif_buffer_queue_setup(struct vb2_queue *vq,
 
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = common->alloc_ctx;
 
 	/* Calculate the offset for Y and C data in the buffer */
 	vpif_calculate_offsets(ch);
@@ -1371,6 +1370,7 @@ static int vpif_probe_complete(void)
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		q->min_buffers_needed = 1;
 		q->lock = &common->lock;
+		q->dev = vpif_dev;
 
 		err = vb2_queue_init(q);
 		if (err) {
@@ -1378,13 +1378,6 @@ static int vpif_probe_complete(void)
 			goto probe_out;
 		}
 
-		common->alloc_ctx = vb2_dma_contig_init_ctx(vpif_dev);
-		if (IS_ERR(common->alloc_ctx)) {
-			vpif_err("Failed to get the context\n");
-			err = PTR_ERR(common->alloc_ctx);
-			goto probe_out;
-		}
-
 		INIT_LIST_HEAD(&common->dma_queue);
 
 		/* Initialize the video_device structure */
@@ -1412,7 +1405,6 @@ probe_out:
 		/* Get the pointer to the channel object */
 		ch = vpif_obj.dev[k];
 		common = &ch->common[k];
-		vb2_dma_contig_cleanup_ctx(common->alloc_ctx);
 		/* Unregister video device */
 		video_unregister_device(&ch->video_dev);
 	}
@@ -1546,7 +1538,6 @@ static int vpif_remove(struct platform_device *device)
 		/* Get the pointer to the channel object */
 		ch = vpif_obj.dev[i];
 		common = &ch->common[VPIF_VIDEO_INDEX];
-		vb2_dma_contig_cleanup_ctx(common->alloc_ctx);
 		/* Unregister video device */
 		video_unregister_device(&ch->video_dev);
 		kfree(vpif_obj.dev[i]);
diff --git a/drivers/media/platform/davinci/vpif_capture.h b/drivers/media/platform/davinci/vpif_capture.h
index 4a7600929b61..9e35b6771d22 100644
--- a/drivers/media/platform/davinci/vpif_capture.h
+++ b/drivers/media/platform/davinci/vpif_capture.h
@@ -65,8 +65,6 @@ struct common_obj {
 	struct v4l2_format fmt;
 	/* Buffer queue used in video-buf */
 	struct vb2_queue buffer_queue;
-	/* allocator-specific contexts for each plane */
-	struct vb2_alloc_ctx *alloc_ctx;
 	/* Queue of filled frames */
 	struct list_head dma_queue;
 	/* Used in video-buf */
diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c
index f40755cf1bf2..75b27233ec2f 100644
--- a/drivers/media/platform/davinci/vpif_display.c
+++ b/drivers/media/platform/davinci/vpif_display.c
@@ -102,14 +102,14 @@ static int vpif_buffer_prepare(struct vb2_buffer *vb)
  * @nbuffers: ptr to number of buffers requested by application
  * @nplanes:: contains number of distinct video planes needed to hold a frame
  * @sizes[]: contains the size (in bytes) of each plane.
- * @alloc_ctxs: ptr to allocation context
+ * @alloc_devs: ptr to allocation context
  *
  * This callback function is called when reqbuf() is called to adjust
  * the buffer count and buffer size
  */
 static int vpif_buffer_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct channel_obj *ch = vb2_get_drv_priv(vq);
 	struct common_obj *common = &ch->common[VPIF_VIDEO_INDEX];
@@ -126,7 +126,6 @@ static int vpif_buffer_queue_setup(struct vb2_queue *vq,
 
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = common->alloc_ctx;
 
 	/* Calculate the offset for Y and C data  in the buffer */
 	vpif_calculate_offsets(ch);
@@ -1191,19 +1190,13 @@ static int vpif_probe_complete(void)
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		q->min_buffers_needed = 1;
 		q->lock = &common->lock;
+		q->dev = vpif_dev;
 		err = vb2_queue_init(q);
 		if (err) {
 			vpif_err("vpif_display: vb2_queue_init() failed\n");
 			goto probe_out;
 		}
 
-		common->alloc_ctx = vb2_dma_contig_init_ctx(vpif_dev);
-		if (IS_ERR(common->alloc_ctx)) {
-			vpif_err("Failed to get the context\n");
-			err = PTR_ERR(common->alloc_ctx);
-			goto probe_out;
-		}
-
 		INIT_LIST_HEAD(&common->dma_queue);
 
 		/* register video device */
@@ -1233,7 +1226,6 @@ probe_out:
 	for (k = 0; k < j; k++) {
 		ch = vpif_obj.dev[k];
 		common = &ch->common[k];
-		vb2_dma_contig_cleanup_ctx(common->alloc_ctx);
 		video_unregister_device(&ch->video_dev);
 	}
 	return err;
@@ -1355,7 +1347,6 @@ static int vpif_remove(struct platform_device *device)
 		/* Get the pointer to the channel object */
 		ch = vpif_obj.dev[i];
 		common = &ch->common[VPIF_VIDEO_INDEX];
-		vb2_dma_contig_cleanup_ctx(common->alloc_ctx);
 		/* Unregister video device */
 		video_unregister_device(&ch->video_dev);
 		kfree(vpif_obj.dev[i]);
diff --git a/drivers/media/platform/davinci/vpif_display.h b/drivers/media/platform/davinci/vpif_display.h
index e7a1723a1b7a..af2765fdcea8 100644
--- a/drivers/media/platform/davinci/vpif_display.h
+++ b/drivers/media/platform/davinci/vpif_display.h
@@ -74,8 +74,6 @@ struct common_obj {
 	struct v4l2_format fmt;			/* Used to store the format */
 	struct vb2_queue buffer_queue;		/* Buffer queue used in
 						 * video-buf */
-	/* allocator-specific contexts for each plane */
-	struct vb2_alloc_ctx *alloc_ctx;
 
 	struct list_head dma_queue;		/* Queue of filled frames */
 	spinlock_t irqlock;			/* Used in video-buf */
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.c b/drivers/media/platform/exynos-gsc/gsc-core.c
index c04973669a47..787bd16c19e5 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.c
+++ b/drivers/media/platform/exynos-gsc/gsc-core.c
@@ -1123,19 +1123,13 @@ static int gsc_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_m2m;
 
-	/* Initialize continious memory allocator */
-	gsc->alloc_ctx = vb2_dma_contig_init_ctx(dev);
-	if (IS_ERR(gsc->alloc_ctx)) {
-		ret = PTR_ERR(gsc->alloc_ctx);
-		goto err_pm;
-	}
+	vb2_dma_contig_set_max_seg_size(dev, DMA_BIT_MASK(32));
 
 	dev_dbg(dev, "gsc-%d registered successfully\n", gsc->id);
 
 	pm_runtime_put(dev);
 	return 0;
-err_pm:
-	pm_runtime_put(dev);
+
 err_m2m:
 	gsc_unregister_m2m_device(gsc);
 err_v4l2:
@@ -1152,7 +1146,7 @@ static int gsc_remove(struct platform_device *pdev)
 	gsc_unregister_m2m_device(gsc);
 	v4l2_device_unregister(&gsc->v4l2_dev);
 
-	vb2_dma_contig_cleanup_ctx(gsc->alloc_ctx);
+	vb2_dma_contig_clear_max_seg_size(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	gsc_clk_put(gsc);
 
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.h b/drivers/media/platform/exynos-gsc/gsc-core.h
index ec4000c72172..7ad7b9dc2243 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.h
+++ b/drivers/media/platform/exynos-gsc/gsc-core.h
@@ -327,7 +327,6 @@ struct gsc_driverdata {
  * @irq_queue:	interrupt handler waitqueue
  * @m2m:	memory-to-memory V4L2 device information
  * @state:	flags used to synchronize m2m and capture mode operation
- * @alloc_ctx:	videobuf2 memory allocator context
  * @vdev:	video device for G-Scaler instance
  */
 struct gsc_dev {
@@ -341,7 +340,6 @@ struct gsc_dev {
 	wait_queue_head_t		irq_queue;
 	struct gsc_m2m_device		m2m;
 	unsigned long			state;
-	struct vb2_alloc_ctx		*alloc_ctx;
 	struct video_device		vdev;
 	struct v4l2_device		v4l2_dev;
 };
diff --git a/drivers/media/platform/exynos-gsc/gsc-m2m.c b/drivers/media/platform/exynos-gsc/gsc-m2m.c
index a600e32e2543..ec6494cbdd45 100644
--- a/drivers/media/platform/exynos-gsc/gsc-m2m.c
+++ b/drivers/media/platform/exynos-gsc/gsc-m2m.c
@@ -213,7 +213,7 @@ put_device:
 
 static int gsc_m2m_queue_setup(struct vb2_queue *vq,
 			unsigned int *num_buffers, unsigned int *num_planes,
-			unsigned int sizes[], void *allocators[])
+			unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct gsc_ctx *ctx = vb2_get_drv_priv(vq);
 	struct gsc_frame *frame;
@@ -227,10 +227,8 @@ static int gsc_m2m_queue_setup(struct vb2_queue *vq,
 		return -EINVAL;
 
 	*num_planes = frame->fmt->num_planes;
-	for (i = 0; i < frame->fmt->num_planes; i++) {
+	for (i = 0; i < frame->fmt->num_planes; i++)
 		sizes[i] = frame->payload[i];
-		allocators[i] = ctx->gsc_dev->alloc_ctx;
-	}
 	return 0;
 }
 
@@ -591,6 +589,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &ctx->gsc_dev->lock;
+	src_vq->dev = &ctx->gsc_dev->pdev->dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -605,6 +604,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &ctx->gsc_dev->lock;
+	dst_vq->dev = &ctx->gsc_dev->pdev->dev;
 
 	return vb2_queue_init(dst_vq);
 }
diff --git a/drivers/media/platform/exynos4-is/fimc-capture.c b/drivers/media/platform/exynos4-is/fimc-capture.c
index bf47d3b9cbe7..fdec499fbbda 100644
--- a/drivers/media/platform/exynos4-is/fimc-capture.c
+++ b/drivers/media/platform/exynos4-is/fimc-capture.c
@@ -340,7 +340,7 @@ int fimc_capture_resume(struct fimc_dev *fimc)
 
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *num_buffers, unsigned int *num_planes,
-		       unsigned int sizes[], void *allocators[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct fimc_ctx *ctx = vq->drv_priv;
 	struct fimc_frame *frame = &ctx->d_frame;
@@ -354,11 +354,9 @@ static int queue_setup(struct vb2_queue *vq,
 	if (*num_planes) {
 		if (*num_planes != fmt->memplanes)
 			return -EINVAL;
-		for (i = 0; i < *num_planes; i++) {
+		for (i = 0; i < *num_planes; i++)
 			if (sizes[i] < (wh * fmt->depth[i]) / 8)
 				return -EINVAL;
-			allocators[i] = ctx->fimc_dev->alloc_ctx;
-		}
 		return 0;
 	}
 
@@ -371,8 +369,6 @@ static int queue_setup(struct vb2_queue *vq,
 			sizes[i] = frame->payload[i];
 		else
 			sizes[i] = max_t(u32, size, frame->payload[i]);
-
-		allocators[i] = ctx->fimc_dev->alloc_ctx;
 	}
 
 	return 0;
@@ -1779,6 +1775,7 @@ static int fimc_register_capture_device(struct fimc_dev *fimc,
 	q->buf_struct_size = sizeof(struct fimc_vid_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &fimc->lock;
+	q->dev = &fimc->pdev->dev;
 
 	ret = vb2_queue_init(q);
 	if (ret)
diff --git a/drivers/media/platform/exynos4-is/fimc-core.c b/drivers/media/platform/exynos4-is/fimc-core.c
index b1c1cea82a27..8f89ca21b631 100644
--- a/drivers/media/platform/exynos4-is/fimc-core.c
+++ b/drivers/media/platform/exynos4-is/fimc-core.c
@@ -1018,19 +1018,11 @@ static int fimc_probe(struct platform_device *pdev)
 			goto err_sd;
 	}
 
-	/* Initialize contiguous memory allocator */
-	fimc->alloc_ctx = vb2_dma_contig_init_ctx(dev);
-	if (IS_ERR(fimc->alloc_ctx)) {
-		ret = PTR_ERR(fimc->alloc_ctx);
-		goto err_gclk;
-	}
+	vb2_dma_contig_set_max_seg_size(dev, DMA_BIT_MASK(32));
 
 	dev_dbg(dev, "FIMC.%d registered successfully\n", fimc->id);
 	return 0;
 
-err_gclk:
-	if (!pm_runtime_enabled(dev))
-		clk_disable(fimc->clock[CLK_GATE]);
 err_sd:
 	fimc_unregister_capture_subdev(fimc);
 err_sclk:
@@ -1123,7 +1115,7 @@ static int fimc_remove(struct platform_device *pdev)
 	pm_runtime_set_suspended(&pdev->dev);
 
 	fimc_unregister_capture_subdev(fimc);
-	vb2_dma_contig_cleanup_ctx(fimc->alloc_ctx);
+	vb2_dma_contig_clear_max_seg_size(&pdev->dev);
 
 	clk_disable(fimc->clock[CLK_BUS]);
 	fimc_clk_put(fimc);
diff --git a/drivers/media/platform/exynos4-is/fimc-core.h b/drivers/media/platform/exynos4-is/fimc-core.h
index 6b7435453d2a..5615fefbf7af 100644
--- a/drivers/media/platform/exynos4-is/fimc-core.h
+++ b/drivers/media/platform/exynos4-is/fimc-core.h
@@ -307,7 +307,6 @@ struct fimc_m2m_device {
  */
 struct fimc_vid_cap {
 	struct fimc_ctx			*ctx;
-	struct vb2_alloc_ctx		*alloc_ctx;
 	struct v4l2_subdev		subdev;
 	struct exynos_video_entity	ve;
 	struct media_pad		vd_pad;
@@ -417,7 +416,6 @@ struct fimc_ctx;
  * @m2m:	memory-to-memory V4L2 device information
  * @vid_cap:	camera capture device information
  * @state:	flags used to synchronize m2m and capture mode operation
- * @alloc_ctx:	videobuf2 memory allocator context
  * @pipeline:	fimc video capture pipeline data structure
  */
 struct fimc_dev {
@@ -436,7 +434,6 @@ struct fimc_dev {
 	struct fimc_m2m_device		m2m;
 	struct fimc_vid_cap		vid_cap;
 	unsigned long			state;
-	struct vb2_alloc_ctx		*alloc_ctx;
 };
 
 /**
diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c
index 979c388ebf60..32ca55f16677 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.c
+++ b/drivers/media/platform/exynos4-is/fimc-is.c
@@ -204,9 +204,6 @@ static int fimc_is_register_subdevs(struct fimc_is *is)
 	if (ret < 0)
 		return ret;
 
-	/* Initialize memory allocator context for the ISP DMA. */
-	is->isp.alloc_ctx = is->alloc_ctx;
-
 	for_each_compatible_node(i2c_bus, NULL, FIMC_IS_I2C_COMPATIBLE) {
 		for_each_available_child_of_node(i2c_bus, child) {
 			ret = fimc_is_parse_sensor_config(is, index, child);
@@ -847,18 +844,14 @@ static int fimc_is_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_pm;
 
-	is->alloc_ctx = vb2_dma_contig_init_ctx(dev);
-	if (IS_ERR(is->alloc_ctx)) {
-		ret = PTR_ERR(is->alloc_ctx);
-		goto err_pm;
-	}
+	vb2_dma_contig_set_max_seg_size(dev, DMA_BIT_MASK(32));
 	/*
 	 * Register FIMC-IS V4L2 subdevs to this driver. The video nodes
 	 * will be created within the subdev's registered() callback.
 	 */
 	ret = fimc_is_register_subdevs(is);
 	if (ret < 0)
-		goto err_vb;
+		goto err_pm;
 
 	ret = fimc_is_debugfs_create(is);
 	if (ret < 0)
@@ -877,8 +870,6 @@ err_dfs:
 	fimc_is_debugfs_remove(is);
 err_sd:
 	fimc_is_unregister_subdevs(is);
-err_vb:
-	vb2_dma_contig_cleanup_ctx(is->alloc_ctx);
 err_pm:
 	if (!pm_runtime_enabled(dev))
 		fimc_is_runtime_suspend(dev);
@@ -939,7 +930,7 @@ static int fimc_is_remove(struct platform_device *pdev)
 		fimc_is_runtime_suspend(dev);
 	free_irq(is->irq, is);
 	fimc_is_unregister_subdevs(is);
-	vb2_dma_contig_cleanup_ctx(is->alloc_ctx);
+	vb2_dma_contig_clear_max_seg_size(dev);
 	fimc_is_put_clocks(is);
 	fimc_is_debugfs_remove(is);
 	release_firmware(is->fw.f_w);
diff --git a/drivers/media/platform/exynos4-is/fimc-is.h b/drivers/media/platform/exynos4-is/fimc-is.h
index 386eb49ece7e..3a82c6a214c7 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.h
+++ b/drivers/media/platform/exynos4-is/fimc-is.h
@@ -233,7 +233,6 @@ struct chain_config {
  * @pdev: pointer to FIMC-IS platform device
  * @pctrl: pointer to pinctrl structure for this device
  * @v4l2_dev: pointer to top the level v4l2_device
- * @alloc_ctx: videobuf2 memory allocator context
  * @lock: mutex serializing video device and the subdev operations
  * @slock: spinlock protecting this data structure and the hw registers
  * @clocks: FIMC-LITE gate clock
@@ -256,7 +255,6 @@ struct fimc_is {
 	struct fimc_is_sensor		sensor[FIMC_IS_SENSORS_NUM];
 	struct fimc_is_setfile		setfile;
 
-	struct vb2_alloc_ctx		*alloc_ctx;
 	struct v4l2_ctrl_handler	ctrl_handler;
 
 	struct mutex			lock;
diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c
index c0816728cbfe..400ce0cb0c0d 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp-video.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c
@@ -40,7 +40,7 @@
 
 static int isp_video_capture_queue_setup(struct vb2_queue *vq,
 			unsigned int *num_buffers, unsigned int *num_planes,
-			unsigned int sizes[], void *allocators[])
+			unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct fimc_isp *isp = vb2_get_drv_priv(vq);
 	struct v4l2_pix_format_mplane *vid_fmt = &isp->video_capture.pixfmt;
@@ -57,20 +57,16 @@ static int isp_video_capture_queue_setup(struct vb2_queue *vq,
 	if (*num_planes) {
 		if (*num_planes != fmt->memplanes)
 			return -EINVAL;
-		for (i = 0; i < *num_planes; i++) {
+		for (i = 0; i < *num_planes; i++)
 			if (sizes[i] < (wh * fmt->depth[i]) / 8)
 				return -EINVAL;
-			allocators[i] = isp->alloc_ctx;
-		}
 		return 0;
 	}
 
 	*num_planes = fmt->memplanes;
 
-	for (i = 0; i < fmt->memplanes; i++) {
+	for (i = 0; i < fmt->memplanes; i++)
 		sizes[i] = (wh * fmt->depth[i]) / 8;
-		allocators[i] = isp->alloc_ctx;
-	}
 
 	return 0;
 }
@@ -597,6 +593,7 @@ int fimc_isp_video_device_register(struct fimc_isp *isp,
 	q->drv_priv = isp;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &isp->video_lock;
+	q->dev = &isp->pdev->dev;
 
 	ret = vb2_queue_init(q);
 	if (ret < 0)
diff --git a/drivers/media/platform/exynos4-is/fimc-isp.h b/drivers/media/platform/exynos4-is/fimc-isp.h
index e0686b5f1bf8..3cdd52491294 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp.h
+++ b/drivers/media/platform/exynos4-is/fimc-isp.h
@@ -148,7 +148,6 @@ struct fimc_is_video {
 /**
  * struct fimc_isp - FIMC-IS ISP data structure
  * @pdev: pointer to FIMC-IS platform device
- * @alloc_ctx: videobuf2 memory allocator context
  * @subdev: ISP v4l2_subdev
  * @subdev_pads: the ISP subdev media pads
  * @test_pattern: test pattern controls
@@ -161,7 +160,6 @@ struct fimc_is_video {
  */
 struct fimc_isp {
 	struct platform_device		*pdev;
-	struct vb2_alloc_ctx		*alloc_ctx;
 	struct v4l2_subdev		subdev;
 	struct media_pad		subdev_pads[FIMC_ISP_SD_PADS_NUM];
 	struct v4l2_mbus_framefmt	src_fmt;
diff --git a/drivers/media/platform/exynos4-is/fimc-lite.c b/drivers/media/platform/exynos4-is/fimc-lite.c
index dc1b929f7a33..a0f149fb88e1 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite.c
+++ b/drivers/media/platform/exynos4-is/fimc-lite.c
@@ -357,7 +357,7 @@ static void stop_streaming(struct vb2_queue *q)
 
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *num_buffers, unsigned int *num_planes,
-		       unsigned int sizes[], void *allocators[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct fimc_lite *fimc = vq->drv_priv;
 	struct flite_frame *frame = &fimc->out_frame;
@@ -371,20 +371,16 @@ static int queue_setup(struct vb2_queue *vq,
 	if (*num_planes) {
 		if (*num_planes != fmt->memplanes)
 			return -EINVAL;
-		for (i = 0; i < *num_planes; i++) {
+		for (i = 0; i < *num_planes; i++)
 			if (sizes[i] < (wh * fmt->depth[i]) / 8)
 				return -EINVAL;
-			allocators[i] = fimc->alloc_ctx;
-		}
 		return 0;
 	}
 
 	*num_planes = fmt->memplanes;
 
-	for (i = 0; i < fmt->memplanes; i++) {
+	for (i = 0; i < fmt->memplanes; i++)
 		sizes[i] = (wh * fmt->depth[i]) / 8;
-		allocators[i] = fimc->alloc_ctx;
-	}
 
 	return 0;
 }
@@ -1300,6 +1296,7 @@ static int fimc_lite_subdev_registered(struct v4l2_subdev *sd)
 	q->drv_priv = fimc;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &fimc->lock;
+	q->dev = &fimc->pdev->dev;
 
 	ret = vb2_queue_init(q);
 	if (ret < 0)
@@ -1551,11 +1548,7 @@ static int fimc_lite_probe(struct platform_device *pdev)
 			goto err_sd;
 	}
 
-	fimc->alloc_ctx = vb2_dma_contig_init_ctx(dev);
-	if (IS_ERR(fimc->alloc_ctx)) {
-		ret = PTR_ERR(fimc->alloc_ctx);
-		goto err_clk_dis;
-	}
+	vb2_dma_contig_set_max_seg_size(dev, DMA_BIT_MASK(32));
 
 	fimc_lite_set_default_config(fimc);
 
@@ -1563,9 +1556,6 @@ static int fimc_lite_probe(struct platform_device *pdev)
 		fimc->index);
 	return 0;
 
-err_clk_dis:
-	if (!pm_runtime_enabled(dev))
-		clk_disable(fimc->clock);
 err_sd:
 	fimc_lite_unregister_capture_subdev(fimc);
 err_clk_put:
@@ -1651,7 +1641,7 @@ static int fimc_lite_remove(struct platform_device *pdev)
 	pm_runtime_disable(dev);
 	pm_runtime_set_suspended(dev);
 	fimc_lite_unregister_capture_subdev(fimc);
-	vb2_dma_contig_cleanup_ctx(fimc->alloc_ctx);
+	vb2_dma_contig_clear_max_seg_size(dev);
 	fimc_lite_clk_put(fimc);
 
 	dev_info(dev, "Driver unloaded\n");
diff --git a/drivers/media/platform/exynos4-is/fimc-lite.h b/drivers/media/platform/exynos4-is/fimc-lite.h
index 11690d563e06..9ae1e96a1bc7 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite.h
+++ b/drivers/media/platform/exynos4-is/fimc-lite.h
@@ -113,7 +113,6 @@ struct flite_buffer {
  * @ve: exynos video device entity structure
  * @v4l2_dev: pointer to top the level v4l2_device
  * @fh: v4l2 file handle
- * @alloc_ctx: videobuf2 memory allocator context
  * @subdev: FIMC-LITE subdev
  * @vd_pad: media (sink) pad for the capture video node
  * @subdev_pads: the subdev media pads
@@ -148,7 +147,6 @@ struct fimc_lite {
 	struct exynos_video_entity ve;
 	struct v4l2_device	*v4l2_dev;
 	struct v4l2_fh		fh;
-	struct vb2_alloc_ctx	*alloc_ctx;
 	struct v4l2_subdev	subdev;
 	struct media_pad	vd_pad;
 	struct media_pad	subdev_pads[FLITE_SD_PADS_NUM];
diff --git a/drivers/media/platform/exynos4-is/fimc-m2m.c b/drivers/media/platform/exynos4-is/fimc-m2m.c
index 55ec4c99d484..b1309e114edb 100644
--- a/drivers/media/platform/exynos4-is/fimc-m2m.c
+++ b/drivers/media/platform/exynos4-is/fimc-m2m.c
@@ -50,30 +50,28 @@ void fimc_m2m_job_finish(struct fimc_ctx *ctx, int vb_state)
 	src_vb = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
 	dst_vb = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
 
-	if (src_vb && dst_vb) {
+	if (src_vb)
 		v4l2_m2m_buf_done(src_vb, vb_state);
+	if (dst_vb)
 		v4l2_m2m_buf_done(dst_vb, vb_state);
+	if (src_vb && dst_vb)
 		v4l2_m2m_job_finish(ctx->fimc_dev->m2m.m2m_dev,
 				    ctx->fh.m2m_ctx);
-	}
 }
 
 /* Complete the transaction which has been scheduled for execution. */
-static int fimc_m2m_shutdown(struct fimc_ctx *ctx)
+static void fimc_m2m_shutdown(struct fimc_ctx *ctx)
 {
 	struct fimc_dev *fimc = ctx->fimc_dev;
-	int ret;
 
 	if (!fimc_m2m_pending(fimc))
-		return 0;
+		return;
 
 	fimc_ctx_state_set(FIMC_CTX_SHUT, ctx);
 
-	ret = wait_event_timeout(fimc->irq_queue,
-			   !fimc_ctx_state_is_set(FIMC_CTX_SHUT, ctx),
-			   FIMC_SHUTDOWN_TIMEOUT);
-
-	return ret == 0 ? -ETIMEDOUT : ret;
+	wait_event_timeout(fimc->irq_queue,
+			!fimc_ctx_state_is_set(FIMC_CTX_SHUT, ctx),
+			FIMC_SHUTDOWN_TIMEOUT);
 }
 
 static int start_streaming(struct vb2_queue *q, unsigned int count)
@@ -88,12 +86,10 @@ static int start_streaming(struct vb2_queue *q, unsigned int count)
 static void stop_streaming(struct vb2_queue *q)
 {
 	struct fimc_ctx *ctx = q->drv_priv;
-	int ret;
 
-	ret = fimc_m2m_shutdown(ctx);
-	if (ret == -ETIMEDOUT)
-		fimc_m2m_job_finish(ctx, VB2_BUF_STATE_ERROR);
 
+	fimc_m2m_shutdown(ctx);
+	fimc_m2m_job_finish(ctx, VB2_BUF_STATE_ERROR);
 	pm_runtime_put(&ctx->fimc_dev->pdev->dev);
 }
 
@@ -178,7 +174,7 @@ static void fimc_job_abort(void *priv)
 
 static int fimc_queue_setup(struct vb2_queue *vq,
 			    unsigned int *num_buffers, unsigned int *num_planes,
-			    unsigned int sizes[], void *allocators[])
+			    unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct fimc_ctx *ctx = vb2_get_drv_priv(vq);
 	struct fimc_frame *f;
@@ -195,10 +191,8 @@ static int fimc_queue_setup(struct vb2_queue *vq,
 		return -EINVAL;
 
 	*num_planes = f->fmt->memplanes;
-	for (i = 0; i < f->fmt->memplanes; i++) {
+	for (i = 0; i < f->fmt->memplanes; i++)
 		sizes[i] = f->payload[i];
-		allocators[i] = ctx->fimc_dev->alloc_ctx;
-	}
 	return 0;
 }
 
@@ -562,6 +556,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &ctx->fimc_dev->lock;
+	src_vq->dev = &ctx->fimc_dev->pdev->dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -575,6 +570,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &ctx->fimc_dev->lock;
+	dst_vq->dev = &ctx->fimc_dev->pdev->dev;
 
 	return vb2_queue_init(dst_vq);
 }
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index bf954424e7be..86e681daa89d 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -649,23 +649,6 @@ static int s5pcsis_log_status(struct v4l2_subdev *sd)
 	return 0;
 }
 
-static int s5pcsis_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
-{
-	struct v4l2_mbus_framefmt *format = v4l2_subdev_get_try_format(sd, fh->pad, 0);
-
-	format->colorspace = V4L2_COLORSPACE_JPEG;
-	format->code = s5pcsis_formats[0].code;
-	format->width = S5PCSIS_DEF_PIX_WIDTH;
-	format->height = S5PCSIS_DEF_PIX_HEIGHT;
-	format->field = V4L2_FIELD_NONE;
-
-	return 0;
-}
-
-static const struct v4l2_subdev_internal_ops s5pcsis_sd_internal_ops = {
-	.open = s5pcsis_open,
-};
-
 static struct v4l2_subdev_core_ops s5pcsis_core_ops = {
 	.s_power = s5pcsis_s_power,
 	.log_status = s5pcsis_log_status,
diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 7383818c2be6..0fcb5c78031d 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -136,7 +136,6 @@ struct deinterlace_dev {
 	struct dma_chan		*dma_chan;
 
 	struct v4l2_m2m_dev	*m2m_dev;
-	struct vb2_alloc_ctx	*alloc_ctx;
 };
 
 struct deinterlace_ctx {
@@ -799,7 +798,7 @@ struct vb2_dc_conf {
 
 static int deinterlace_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct deinterlace_ctx *ctx = vb2_get_drv_priv(vq);
 	struct deinterlace_q_data *q_data;
@@ -820,8 +819,6 @@ static int deinterlace_queue_setup(struct vb2_queue *vq,
 	*nbuffers = count;
 	sizes[0] = size;
 
-	alloc_ctxs[0] = ctx->dev->alloc_ctx;
-
 	dprintk(ctx->dev, "get %d buffer(s) of size %d each.\n", count, size);
 
 	return 0;
@@ -874,6 +871,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->ops = &deinterlace_qops;
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->dev = ctx->dev->v4l2_dev.dev;
 	q_data[V4L2_M2M_SRC].fmt = &formats[0];
 	q_data[V4L2_M2M_SRC].width = 640;
 	q_data[V4L2_M2M_SRC].height = 480;
@@ -891,6 +889,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->ops = &deinterlace_qops;
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->dev = ctx->dev->v4l2_dev.dev;
 	q_data[V4L2_M2M_DST].fmt = &formats[0];
 	q_data[V4L2_M2M_DST].width = 640;
 	q_data[V4L2_M2M_DST].height = 480;
@@ -1046,13 +1045,6 @@ static int deinterlace_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pcdev);
 
-	pcdev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(pcdev->alloc_ctx)) {
-		v4l2_err(&pcdev->v4l2_dev, "Failed to alloc vb2 context\n");
-		ret = PTR_ERR(pcdev->alloc_ctx);
-		goto err_ctx;
-	}
-
 	pcdev->m2m_dev = v4l2_m2m_init(&m2m_ops);
 	if (IS_ERR(pcdev->m2m_dev)) {
 		v4l2_err(&pcdev->v4l2_dev, "Failed to init mem2mem device\n");
@@ -1064,8 +1056,6 @@ static int deinterlace_probe(struct platform_device *pdev)
 
 err_m2m:
 	video_unregister_device(&pcdev->vfd);
-err_ctx:
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
 unreg_dev:
 	v4l2_device_unregister(&pcdev->v4l2_dev);
 rel_dma:
@@ -1082,7 +1072,6 @@ static int deinterlace_remove(struct platform_device *pdev)
 	v4l2_m2m_release(pcdev->m2m_dev);
 	video_unregister_device(&pcdev->vfd);
 	v4l2_device_unregister(&pcdev->v4l2_dev);
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
 	dma_release_channel(pcdev->dma_chan);
 
 	return 0;
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c
index 9b878deb1437..af59bf4dca2d 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.c
+++ b/drivers/media/platform/marvell-ccic/mcam-core.c
@@ -973,7 +973,7 @@ static int mcam_cam_set_flip(struct mcam_camera *cam)
 	memset(&ctrl, 0, sizeof(ctrl));
 	ctrl.id = V4L2_CID_VFLIP;
 	ctrl.value = flip;
-	return sensor_call(cam, core, s_ctrl, &ctrl);
+	return v4l2_s_ctrl(NULL, cam->sensor->ctrl_handler, &ctrl);
 }
 
 
@@ -1051,7 +1051,7 @@ static int mcam_read_setup(struct mcam_camera *cam)
 static int mcam_vb_queue_setup(struct vb2_queue *vq,
 		unsigned int *nbufs,
 		unsigned int *num_planes, unsigned int sizes[],
-		void *alloc_ctxs[])
+		struct device *alloc_devs[])
 {
 	struct mcam_camera *cam = vb2_get_drv_priv(vq);
 	int minbufs = (cam->buffer_mode == B_DMA_contig) ? 3 : 2;
@@ -1059,10 +1059,6 @@ static int mcam_vb_queue_setup(struct vb2_queue *vq,
 
 	if (*nbufs < minbufs)
 		*nbufs = minbufs;
-	if (cam->buffer_mode == B_DMA_contig)
-		alloc_ctxs[0] = cam->vb_alloc_ctx;
-	else if (cam->buffer_mode == B_DMA_sg)
-		alloc_ctxs[0] = cam->vb_alloc_ctx_sg;
 
 	if (*num_planes)
 		return sizes[0] < size ? -EINVAL : 0;
@@ -1271,6 +1267,7 @@ static int mcam_setup_vb2(struct mcam_camera *cam)
 	vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 	vq->buf_struct_size = sizeof(struct mcam_vb_buffer);
+	vq->dev = cam->dev;
 	INIT_LIST_HEAD(&cam->buffers);
 	switch (cam->buffer_mode) {
 	case B_DMA_contig:
@@ -1279,9 +1276,6 @@ static int mcam_setup_vb2(struct mcam_camera *cam)
 		vq->mem_ops = &vb2_dma_contig_memops;
 		cam->dma_setup = mcam_ctlr_dma_contig;
 		cam->frame_complete = mcam_dma_contig_done;
-		cam->vb_alloc_ctx = vb2_dma_contig_init_ctx(cam->dev);
-		if (IS_ERR(cam->vb_alloc_ctx))
-			return PTR_ERR(cam->vb_alloc_ctx);
 #endif
 		break;
 	case B_DMA_sg:
@@ -1290,9 +1284,6 @@ static int mcam_setup_vb2(struct mcam_camera *cam)
 		vq->mem_ops = &vb2_dma_sg_memops;
 		cam->dma_setup = mcam_ctlr_dma_sg;
 		cam->frame_complete = mcam_dma_sg_done;
-		cam->vb_alloc_ctx_sg = vb2_dma_sg_init_ctx(cam->dev);
-		if (IS_ERR(cam->vb_alloc_ctx_sg))
-			return PTR_ERR(cam->vb_alloc_ctx_sg);
 #endif
 		break;
 	case B_vmalloc:
@@ -1309,18 +1300,6 @@ static int mcam_setup_vb2(struct mcam_camera *cam)
 	return vb2_queue_init(vq);
 }
 
-static void mcam_cleanup_vb2(struct mcam_camera *cam)
-{
-#ifdef MCAM_MODE_DMA_CONTIG
-	if (cam->buffer_mode == B_DMA_contig)
-		vb2_dma_contig_cleanup_ctx(cam->vb_alloc_ctx);
-#endif
-#ifdef MCAM_MODE_DMA_SG
-	if (cam->buffer_mode == B_DMA_sg)
-		vb2_dma_sg_cleanup_ctx(cam->vb_alloc_ctx_sg);
-#endif
-}
-
 
 /* ---------------------------------------------------------------------- */
 /*
@@ -1875,7 +1854,6 @@ void mccic_shutdown(struct mcam_camera *cam)
 		cam_warn(cam, "Removing a device with users!\n");
 		mcam_ctlr_power_down(cam);
 	}
-	mcam_cleanup_vb2(cam);
 	if (cam->buffer_mode == B_vmalloc)
 		mcam_free_dma_bufs(cam);
 	video_unregister_device(&cam->vdev);
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.h b/drivers/media/platform/marvell-ccic/mcam-core.h
index 35cd9e5aedf8..beb339f5561f 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.h
+++ b/drivers/media/platform/marvell-ccic/mcam-core.h
@@ -176,8 +176,6 @@ struct mcam_camera {
 
 	/* DMA buffers - DMA modes */
 	struct mcam_vb_buffer *vb_bufs[MAX_DMA_BUFS];
-	struct vb2_alloc_ctx *vb_alloc_ctx;
-	struct vb2_alloc_ctx *vb_alloc_ctx_sg;
 
 	/* Mode-specific ops, set at open time */
 	void (*dma_setup)(struct mcam_camera *cam);
diff --git a/drivers/media/platform/mtk-vcodec/Makefile b/drivers/media/platform/mtk-vcodec/Makefile
new file mode 100644
index 000000000000..dc5cb006d600
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/Makefile
@@ -0,0 +1,19 @@
+
+
+obj-$(CONFIG_VIDEO_MEDIATEK_VCODEC) += mtk-vcodec-enc.o mtk-vcodec-common.o
+
+
+
+mtk-vcodec-enc-y := venc/venc_vp8_if.o \
+		venc/venc_h264_if.o \
+		mtk_vcodec_enc.o \
+		mtk_vcodec_enc_drv.o \
+		mtk_vcodec_enc_pm.o \
+		venc_drv_if.o \
+		venc_vpu_if.o \
+
+
+mtk-vcodec-common-y := mtk_vcodec_intr.o \
+		mtk_vcodec_util.o\
+
+ccflags-y += -I$(srctree)/drivers/media/platform/mtk-vpu
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
new file mode 100644
index 000000000000..94f0a425be42
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
@@ -0,0 +1,335 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: PC Chen <pc.chen@mediatek.com>
+*         Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#ifndef _MTK_VCODEC_DRV_H_
+#define _MTK_VCODEC_DRV_H_
+
+#include <linux/platform_device.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/videobuf2-core.h>
+
+#include "mtk_vcodec_util.h"
+
+#define MTK_VCODEC_DRV_NAME	"mtk_vcodec_drv"
+#define MTK_VCODEC_ENC_NAME	"mtk-vcodec-enc"
+#define MTK_PLATFORM_STR	"platform:mt8173"
+
+
+#define MTK_VCODEC_MAX_PLANES	3
+#define MTK_V4L2_BENCHMARK	0
+#define WAIT_INTR_TIMEOUT_MS	1000
+
+/**
+ * enum mtk_hw_reg_idx - MTK hw register base index
+ */
+enum mtk_hw_reg_idx {
+	VDEC_SYS,
+	VDEC_MISC,
+	VDEC_LD,
+	VDEC_TOP,
+	VDEC_CM,
+	VDEC_AD,
+	VDEC_AV,
+	VDEC_PP,
+	VDEC_HWD,
+	VDEC_HWQ,
+	VDEC_HWB,
+	VDEC_HWG,
+	NUM_MAX_VDEC_REG_BASE,
+	/* h264 encoder */
+	VENC_SYS = NUM_MAX_VDEC_REG_BASE,
+	/* vp8 encoder */
+	VENC_LT_SYS,
+	NUM_MAX_VCODEC_REG_BASE
+};
+
+/**
+ * enum mtk_instance_type - The type of an MTK Vcodec instance.
+ */
+enum mtk_instance_type {
+	MTK_INST_DECODER		= 0,
+	MTK_INST_ENCODER		= 1,
+};
+
+/**
+ * enum mtk_instance_state - The state of an MTK Vcodec instance.
+ * @MTK_STATE_FREE - default state when instance is created
+ * @MTK_STATE_INIT - vcodec instance is initialized
+ * @MTK_STATE_HEADER - vdec had sps/pps header parsed or venc
+ *			had sps/pps header encoded
+ * @MTK_STATE_FLUSH - vdec is flushing. Only used by decoder
+ * @MTK_STATE_ABORT - vcodec should be aborted
+ */
+enum mtk_instance_state {
+	MTK_STATE_FREE = 0,
+	MTK_STATE_INIT = 1,
+	MTK_STATE_HEADER = 2,
+	MTK_STATE_FLUSH = 3,
+	MTK_STATE_ABORT = 4,
+};
+
+/**
+ * struct mtk_encode_param - General encoding parameters type
+ */
+enum mtk_encode_param {
+	MTK_ENCODE_PARAM_NONE = 0,
+	MTK_ENCODE_PARAM_BITRATE = (1 << 0),
+	MTK_ENCODE_PARAM_FRAMERATE = (1 << 1),
+	MTK_ENCODE_PARAM_INTRA_PERIOD = (1 << 2),
+	MTK_ENCODE_PARAM_FORCE_INTRA = (1 << 3),
+	MTK_ENCODE_PARAM_GOP_SIZE = (1 << 4),
+};
+
+enum mtk_fmt_type {
+	MTK_FMT_DEC = 0,
+	MTK_FMT_ENC = 1,
+	MTK_FMT_FRAME = 2,
+};
+
+/**
+ * struct mtk_video_fmt - Structure used to store information about pixelformats
+ */
+struct mtk_video_fmt {
+	u32	fourcc;
+	enum mtk_fmt_type	type;
+	u32	num_planes;
+};
+
+/**
+ * struct mtk_codec_framesizes - Structure used to store information about
+ *							framesizes
+ */
+struct mtk_codec_framesizes {
+	u32	fourcc;
+	struct	v4l2_frmsize_stepwise	stepwise;
+};
+
+/**
+ * struct mtk_q_type - Type of queue
+ */
+enum mtk_q_type {
+	MTK_Q_DATA_SRC = 0,
+	MTK_Q_DATA_DST = 1,
+};
+
+/**
+ * struct mtk_q_data - Structure used to store information about queue
+ */
+struct mtk_q_data {
+	unsigned int	visible_width;
+	unsigned int	visible_height;
+	unsigned int	coded_width;
+	unsigned int	coded_height;
+	enum v4l2_field	field;
+	unsigned int	bytesperline[MTK_VCODEC_MAX_PLANES];
+	unsigned int	sizeimage[MTK_VCODEC_MAX_PLANES];
+	struct mtk_video_fmt	*fmt;
+};
+
+/**
+ * struct mtk_enc_params - General encoding parameters
+ * @bitrate: target bitrate in bits per second
+ * @num_b_frame: number of b frames between p-frame
+ * @rc_frame: frame based rate control
+ * @rc_mb: macroblock based rate control
+ * @seq_hdr_mode: H.264 sequence header is encoded separately or joined
+ *		  with the first frame
+ * @intra_period: I frame period
+ * @gop_size: group of picture size, it's used as the intra frame period
+ * @framerate_num: frame rate numerator. ex: framerate_num=30 and
+ *		   framerate_denom=1 menas FPS is 30
+ * @framerate_denom: frame rate denominator. ex: framerate_num=30 and
+ *		     framerate_denom=1 menas FPS is 30
+ * @h264_max_qp: Max value for H.264 quantization parameter
+ * @h264_profile: V4L2 defined H.264 profile
+ * @h264_level: V4L2 defined H.264 level
+ * @force_intra: force/insert intra frame
+ */
+struct mtk_enc_params {
+	unsigned int	bitrate;
+	unsigned int	num_b_frame;
+	unsigned int	rc_frame;
+	unsigned int	rc_mb;
+	unsigned int	seq_hdr_mode;
+	unsigned int	intra_period;
+	unsigned int	gop_size;
+	unsigned int	framerate_num;
+	unsigned int	framerate_denom;
+	unsigned int	h264_max_qp;
+	unsigned int	h264_profile;
+	unsigned int	h264_level;
+	unsigned int	force_intra;
+};
+
+/**
+ * struct mtk_vcodec_pm - Power management data structure
+ */
+struct mtk_vcodec_pm {
+	struct clk	*vcodecpll;
+	struct clk	*univpll_d2;
+	struct clk	*clk_cci400_sel;
+	struct clk	*vdecpll;
+	struct clk	*vdec_sel;
+	struct clk	*vencpll_d2;
+	struct clk	*venc_sel;
+	struct clk	*univpll1_d2;
+	struct clk	*venc_lt_sel;
+	struct device	*larbvdec;
+	struct device	*larbvenc;
+	struct device	*larbvenclt;
+	struct device	*dev;
+	struct mtk_vcodec_dev	*mtkdev;
+};
+
+/**
+ * struct mtk_vcodec_ctx - Context (instance) private data.
+ *
+ * @type: type of the instance - decoder or encoder
+ * @dev: pointer to the mtk_vcodec_dev of the device
+ * @list: link to ctx_list of mtk_vcodec_dev
+ * @fh: struct v4l2_fh
+ * @m2m_ctx: pointer to the v4l2_m2m_ctx of the context
+ * @q_data: store information of input and output queue
+ *	    of the context
+ * @id: index of the context that this structure describes
+ * @state: state of the context
+ * @param_change: indicate encode parameter type
+ * @enc_params: encoding parameters
+ * @enc_if: hoooked encoder driver interface
+ * @drv_handle: driver handle for specific decode/encode instance
+ *
+ * @int_cond: variable used by the waitqueue
+ * @int_type: type of the last interrupt
+ * @queue: waitqueue that can be used to wait for this context to
+ *	   finish
+ * @irq_status: irq status
+ *
+ * @ctrl_hdl: handler for v4l2 framework
+ * @encode_work: worker for the encoding
+ *
+ * @colorspace: enum v4l2_colorspace; supplemental to pixelformat
+ * @ycbcr_enc: enum v4l2_ycbcr_encoding, Y'CbCr encoding
+ * @quantization: enum v4l2_quantization, colorspace quantization
+ * @xfer_func: enum v4l2_xfer_func, colorspace transfer function
+ */
+struct mtk_vcodec_ctx {
+	enum mtk_instance_type type;
+	struct mtk_vcodec_dev *dev;
+	struct list_head list;
+
+	struct v4l2_fh fh;
+	struct v4l2_m2m_ctx *m2m_ctx;
+	struct mtk_q_data q_data[2];
+	int id;
+	enum mtk_instance_state state;
+	enum mtk_encode_param param_change;
+	struct mtk_enc_params enc_params;
+
+	struct venc_common_if *enc_if;
+	unsigned long drv_handle;
+
+	int int_cond;
+	int int_type;
+	wait_queue_head_t queue;
+	unsigned int irq_status;
+
+	struct v4l2_ctrl_handler ctrl_hdl;
+	struct work_struct encode_work;
+
+	enum v4l2_colorspace colorspace;
+	enum v4l2_ycbcr_encoding ycbcr_enc;
+	enum v4l2_quantization quantization;
+	enum v4l2_xfer_func xfer_func;
+};
+
+/**
+ * struct mtk_vcodec_dev - driver data
+ * @v4l2_dev: V4L2 device to register video devices for.
+ * @vfd_enc: Video device for encoder.
+ *
+ * @m2m_dev_enc: m2m device for encoder.
+ * @plat_dev: platform device
+ * @vpu_plat_dev: mtk vpu platform device
+ * @ctx_list: list of struct mtk_vcodec_ctx
+ * @irqlock: protect data access by irq handler and work thread
+ * @curr_ctx: The context that is waiting for codec hardware
+ *
+ * @reg_base: Mapped address of MTK Vcodec registers.
+ *
+ * @id_counter: used to identify current opened instance
+ * @num_instances: counter of active MTK Vcodec instances
+ *
+ * @encode_workqueue: encode work queue
+ *
+ * @int_cond: used to identify interrupt condition happen
+ * @int_type: used to identify what kind of interrupt condition happen
+ * @dev_mutex: video_device lock
+ * @queue: waitqueue for waiting for completion of device commands
+ *
+ * @enc_irq: h264 encoder irq resource
+ * @enc_lt_irq: vp8 encoder irq resource
+ *
+ * @enc_mutex: encoder hardware lock.
+ *
+ * @pm: power management control
+ * @dec_capability: used to identify decode capability, ex: 4k
+ * @enc_capability: used to identify encode capability
+ */
+struct mtk_vcodec_dev {
+	struct v4l2_device v4l2_dev;
+	struct video_device *vfd_enc;
+
+	struct v4l2_m2m_dev *m2m_dev_enc;
+	struct platform_device *plat_dev;
+	struct platform_device *vpu_plat_dev;
+	struct list_head ctx_list;
+	spinlock_t irqlock;
+	struct mtk_vcodec_ctx *curr_ctx;
+	void __iomem *reg_base[NUM_MAX_VCODEC_REG_BASE];
+
+	unsigned long id_counter;
+	int num_instances;
+
+	struct workqueue_struct *encode_workqueue;
+
+	int int_cond;
+	int int_type;
+	struct mutex dev_mutex;
+	wait_queue_head_t queue;
+
+	int enc_irq;
+	int enc_lt_irq;
+
+	struct mutex enc_mutex;
+
+	struct mtk_vcodec_pm pm;
+	unsigned int dec_capability;
+	unsigned int enc_capability;
+};
+
+static inline struct mtk_vcodec_ctx *fh_to_ctx(struct v4l2_fh *fh)
+{
+	return container_of(fh, struct mtk_vcodec_ctx, fh);
+}
+
+static inline struct mtk_vcodec_ctx *ctrl_to_ctx(struct v4l2_ctrl *ctrl)
+{
+	return container_of(ctrl->handler, struct mtk_vcodec_ctx, ctrl_hdl);
+}
+
+#endif /* _MTK_VCODEC_DRV_H_ */
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
new file mode 100644
index 000000000000..3ed3f2d31df5
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
@@ -0,0 +1,1292 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: PC Chen <pc.chen@mediatek.com>
+*         Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#include <media/v4l2-event.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-dma-contig.h>
+#include <soc/mediatek/smi.h>
+
+#include "mtk_vcodec_drv.h"
+#include "mtk_vcodec_enc.h"
+#include "mtk_vcodec_intr.h"
+#include "mtk_vcodec_util.h"
+#include "venc_drv_if.h"
+
+#define MTK_VENC_MIN_W	160U
+#define MTK_VENC_MIN_H	128U
+#define MTK_VENC_MAX_W	1920U
+#define MTK_VENC_MAX_H	1088U
+#define DFT_CFG_WIDTH	MTK_VENC_MIN_W
+#define DFT_CFG_HEIGHT	MTK_VENC_MIN_H
+#define MTK_MAX_CTRLS_HINT	20
+#define OUT_FMT_IDX		0
+#define CAP_FMT_IDX		4
+
+
+static void mtk_venc_worker(struct work_struct *work);
+
+static struct mtk_video_fmt mtk_video_formats[] = {
+	{
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.type = MTK_FMT_FRAME,
+		.num_planes = 2,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_NV21M,
+		.type = MTK_FMT_FRAME,
+		.num_planes = 2,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YUV420M,
+		.type = MTK_FMT_FRAME,
+		.num_planes = 3,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_YVU420M,
+		.type = MTK_FMT_FRAME,
+		.num_planes = 3,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_H264,
+		.type = MTK_FMT_ENC,
+		.num_planes = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_VP8,
+		.type = MTK_FMT_ENC,
+		.num_planes = 1,
+	},
+};
+
+#define NUM_FORMATS ARRAY_SIZE(mtk_video_formats)
+
+static const struct mtk_codec_framesizes mtk_venc_framesizes[] = {
+	{
+		.fourcc	= V4L2_PIX_FMT_H264,
+		.stepwise = { MTK_VENC_MIN_W, MTK_VENC_MAX_W, 16,
+			      MTK_VENC_MIN_H, MTK_VENC_MAX_H, 16 },
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_VP8,
+		.stepwise = { MTK_VENC_MIN_W, MTK_VENC_MAX_W, 16,
+			      MTK_VENC_MIN_H, MTK_VENC_MAX_H, 16 },
+	},
+};
+
+#define NUM_SUPPORTED_FRAMESIZE ARRAY_SIZE(mtk_venc_framesizes)
+
+static int vidioc_venc_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct mtk_vcodec_ctx *ctx = ctrl_to_ctx(ctrl);
+	struct mtk_enc_params *p = &ctx->enc_params;
+	int ret = 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_MPEG_VIDEO_BITRATE:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_BITRATE val = %d",
+			       ctrl->val);
+		p->bitrate = ctrl->val;
+		ctx->param_change |= MTK_ENCODE_PARAM_BITRATE;
+		break;
+	case V4L2_CID_MPEG_VIDEO_B_FRAMES:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_B_FRAMES val = %d",
+			       ctrl->val);
+		p->num_b_frame = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_FRAME_RC_ENABLE:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_FRAME_RC_ENABLE val = %d",
+			       ctrl->val);
+		p->rc_frame = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_MAX_QP:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_H264_MAX_QP val = %d",
+			       ctrl->val);
+		p->h264_max_qp = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_HEADER_MODE:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_HEADER_MODE val = %d",
+			       ctrl->val);
+		p->seq_hdr_mode = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_MB_RC_ENABLE:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_MB_RC_ENABLE val = %d",
+			       ctrl->val);
+		p->rc_mb = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_H264_PROFILE val = %d",
+			       ctrl->val);
+		p->h264_profile = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_LEVEL:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_H264_LEVEL val = %d",
+			       ctrl->val);
+		p->h264_level = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_I_PERIOD:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_H264_I_PERIOD val = %d",
+			       ctrl->val);
+		p->intra_period = ctrl->val;
+		ctx->param_change |= MTK_ENCODE_PARAM_INTRA_PERIOD;
+		break;
+	case V4L2_CID_MPEG_VIDEO_GOP_SIZE:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_GOP_SIZE val = %d",
+			       ctrl->val);
+		p->gop_size = ctrl->val;
+		ctx->param_change |= MTK_ENCODE_PARAM_GOP_SIZE;
+		break;
+	case V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME:
+		mtk_v4l2_debug(2, "V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME");
+		p->force_intra = 1;
+		ctx->param_change |= MTK_ENCODE_PARAM_FORCE_INTRA;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops mtk_vcodec_enc_ctrl_ops = {
+	.s_ctrl = vidioc_venc_s_ctrl,
+};
+
+static int vidioc_enum_fmt(struct v4l2_fmtdesc *f, bool output_queue)
+{
+	struct mtk_video_fmt *fmt;
+	int i, j = 0;
+
+	for (i = 0; i < NUM_FORMATS; ++i) {
+		if (output_queue && mtk_video_formats[i].type != MTK_FMT_FRAME)
+			continue;
+		if (!output_queue && mtk_video_formats[i].type != MTK_FMT_ENC)
+			continue;
+
+		if (j == f->index) {
+			fmt = &mtk_video_formats[i];
+			f->pixelformat = fmt->fourcc;
+			memset(f->reserved, 0, sizeof(f->reserved));
+			return 0;
+		}
+		++j;
+	}
+
+	return -EINVAL;
+}
+
+static int vidioc_enum_framesizes(struct file *file, void *fh,
+				  struct v4l2_frmsizeenum *fsize)
+{
+	int i = 0;
+
+	if (fsize->index != 0)
+		return -EINVAL;
+
+	for (i = 0; i < NUM_SUPPORTED_FRAMESIZE; ++i) {
+		if (fsize->pixel_format != mtk_venc_framesizes[i].fourcc)
+			continue;
+
+		fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
+		fsize->stepwise = mtk_venc_framesizes[i].stepwise;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int vidioc_enum_fmt_vid_cap_mplane(struct file *file, void *pirv,
+					  struct v4l2_fmtdesc *f)
+{
+	return vidioc_enum_fmt(f, false);
+}
+
+static int vidioc_enum_fmt_vid_out_mplane(struct file *file, void *prov,
+					  struct v4l2_fmtdesc *f)
+{
+	return vidioc_enum_fmt(f, true);
+}
+
+static int vidioc_venc_querycap(struct file *file, void *priv,
+				struct v4l2_capability *cap)
+{
+	strlcpy(cap->driver, MTK_VCODEC_ENC_NAME, sizeof(cap->driver));
+	strlcpy(cap->bus_info, MTK_PLATFORM_STR, sizeof(cap->bus_info));
+	strlcpy(cap->card, MTK_PLATFORM_STR, sizeof(cap->card));
+
+	return 0;
+}
+
+static int vidioc_venc_s_parm(struct file *file, void *priv,
+			      struct v4l2_streamparm *a)
+{
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+
+	if (a->type != V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
+		return -EINVAL;
+
+	ctx->enc_params.framerate_num =
+			a->parm.output.timeperframe.denominator;
+	ctx->enc_params.framerate_denom =
+			a->parm.output.timeperframe.numerator;
+	ctx->param_change |= MTK_ENCODE_PARAM_FRAMERATE;
+
+	return 0;
+}
+
+static int vidioc_venc_g_parm(struct file *file, void *priv,
+			      struct v4l2_streamparm *a)
+{
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+
+	if (a->type != V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
+		return -EINVAL;
+
+	a->parm.output.timeperframe.denominator =
+			ctx->enc_params.framerate_num;
+	a->parm.output.timeperframe.numerator =
+			ctx->enc_params.framerate_denom;
+
+	return 0;
+}
+
+static struct mtk_q_data *mtk_venc_get_q_data(struct mtk_vcodec_ctx *ctx,
+					      enum v4l2_buf_type type)
+{
+	if (V4L2_TYPE_IS_OUTPUT(type))
+		return &ctx->q_data[MTK_Q_DATA_SRC];
+
+	return &ctx->q_data[MTK_Q_DATA_DST];
+}
+
+static struct mtk_video_fmt *mtk_venc_find_format(struct v4l2_format *f)
+{
+	struct mtk_video_fmt *fmt;
+	unsigned int k;
+
+	for (k = 0; k < NUM_FORMATS; k++) {
+		fmt = &mtk_video_formats[k];
+		if (fmt->fourcc == f->fmt.pix.pixelformat)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+/* V4L2 specification suggests the driver corrects the format struct if any of
+ * the dimensions is unsupported
+ */
+static int vidioc_try_fmt(struct v4l2_format *f, struct mtk_video_fmt *fmt)
+{
+	struct v4l2_pix_format_mplane *pix_fmt_mp = &f->fmt.pix_mp;
+	int i;
+
+	pix_fmt_mp->field = V4L2_FIELD_NONE;
+
+	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
+		pix_fmt_mp->num_planes = 1;
+		pix_fmt_mp->plane_fmt[0].bytesperline = 0;
+	} else if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
+		int tmp_w, tmp_h;
+
+		pix_fmt_mp->height = clamp(pix_fmt_mp->height,
+					MTK_VENC_MIN_H,
+					MTK_VENC_MAX_H);
+		pix_fmt_mp->width = clamp(pix_fmt_mp->width,
+					MTK_VENC_MIN_W,
+					MTK_VENC_MAX_W);
+
+		/* find next closer width align 16, heign align 32, size align
+		 * 64 rectangle
+		 */
+		tmp_w = pix_fmt_mp->width;
+		tmp_h = pix_fmt_mp->height;
+		v4l_bound_align_image(&pix_fmt_mp->width,
+					MTK_VENC_MIN_W,
+					MTK_VENC_MAX_W, 4,
+					&pix_fmt_mp->height,
+					MTK_VENC_MIN_H,
+					MTK_VENC_MAX_H, 5, 6);
+
+		if (pix_fmt_mp->width < tmp_w &&
+			(pix_fmt_mp->width + 16) <= MTK_VENC_MAX_W)
+			pix_fmt_mp->width += 16;
+		if (pix_fmt_mp->height < tmp_h &&
+			(pix_fmt_mp->height + 32) <= MTK_VENC_MAX_H)
+			pix_fmt_mp->height += 32;
+
+		mtk_v4l2_debug(0,
+			"before resize width=%d, height=%d, after resize width=%d, height=%d, sizeimage=%d %d",
+			tmp_w, tmp_h, pix_fmt_mp->width,
+			pix_fmt_mp->height,
+			pix_fmt_mp->plane_fmt[0].sizeimage,
+			pix_fmt_mp->plane_fmt[1].sizeimage);
+
+		pix_fmt_mp->num_planes = fmt->num_planes;
+		pix_fmt_mp->plane_fmt[0].sizeimage =
+				pix_fmt_mp->width * pix_fmt_mp->height +
+				((ALIGN(pix_fmt_mp->width, 16) * 2) * 16);
+		pix_fmt_mp->plane_fmt[0].bytesperline = pix_fmt_mp->width;
+
+		if (pix_fmt_mp->num_planes == 2) {
+			pix_fmt_mp->plane_fmt[1].sizeimage =
+				(pix_fmt_mp->width * pix_fmt_mp->height) / 2 +
+				(ALIGN(pix_fmt_mp->width, 16) * 16);
+			pix_fmt_mp->plane_fmt[2].sizeimage = 0;
+			pix_fmt_mp->plane_fmt[1].bytesperline =
+							pix_fmt_mp->width;
+			pix_fmt_mp->plane_fmt[2].bytesperline = 0;
+		} else if (pix_fmt_mp->num_planes == 3) {
+			pix_fmt_mp->plane_fmt[1].sizeimage =
+			pix_fmt_mp->plane_fmt[2].sizeimage =
+				(pix_fmt_mp->width * pix_fmt_mp->height) / 4 +
+				((ALIGN(pix_fmt_mp->width, 16) / 2) * 16);
+			pix_fmt_mp->plane_fmt[1].bytesperline =
+				pix_fmt_mp->plane_fmt[2].bytesperline =
+				pix_fmt_mp->width / 2;
+		}
+	}
+
+	for (i = 0; i < pix_fmt_mp->num_planes; i++)
+		memset(&(pix_fmt_mp->plane_fmt[i].reserved[0]), 0x0,
+			   sizeof(pix_fmt_mp->plane_fmt[0].reserved));
+
+	pix_fmt_mp->flags = 0;
+	memset(&pix_fmt_mp->reserved, 0x0,
+		sizeof(pix_fmt_mp->reserved));
+
+	return 0;
+}
+
+static void mtk_venc_set_param(struct mtk_vcodec_ctx *ctx,
+				struct venc_enc_param *param)
+{
+	struct mtk_q_data *q_data_src = &ctx->q_data[MTK_Q_DATA_SRC];
+	struct mtk_enc_params *enc_params = &ctx->enc_params;
+
+	switch (q_data_src->fmt->fourcc) {
+	case V4L2_PIX_FMT_YUV420M:
+		param->input_yuv_fmt = VENC_YUV_FORMAT_I420;
+		break;
+	case V4L2_PIX_FMT_YVU420M:
+		param->input_yuv_fmt = VENC_YUV_FORMAT_YV12;
+		break;
+	case V4L2_PIX_FMT_NV12M:
+		param->input_yuv_fmt = VENC_YUV_FORMAT_NV12;
+		break;
+	case V4L2_PIX_FMT_NV21M:
+		param->input_yuv_fmt = VENC_YUV_FORMAT_NV21;
+		break;
+	default:
+		mtk_v4l2_err("Unsupport fourcc =%d", q_data_src->fmt->fourcc);
+		break;
+	}
+	param->h264_profile = enc_params->h264_profile;
+	param->h264_level = enc_params->h264_level;
+
+	/* Config visible resolution */
+	param->width = q_data_src->visible_width;
+	param->height = q_data_src->visible_height;
+	/* Config coded resolution */
+	param->buf_width = q_data_src->coded_width;
+	param->buf_height = q_data_src->coded_height;
+	param->frm_rate = enc_params->framerate_num /
+			enc_params->framerate_denom;
+	param->intra_period = enc_params->intra_period;
+	param->gop_size = enc_params->gop_size;
+	param->bitrate = enc_params->bitrate;
+
+	mtk_v4l2_debug(0,
+		"fmt 0x%x, P/L %d/%d, w/h %d/%d, buf %d/%d, fps/bps %d/%d, gop %d, i_period %d",
+		param->input_yuv_fmt, param->h264_profile,
+		param->h264_level, param->width, param->height,
+		param->buf_width, param->buf_height,
+		param->frm_rate, param->bitrate,
+		param->gop_size, param->intra_period);
+}
+
+static int vidioc_venc_s_fmt_cap(struct file *file, void *priv,
+			     struct v4l2_format *f)
+{
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+	struct vb2_queue *vq;
+	struct mtk_q_data *q_data;
+	int i, ret;
+	struct mtk_video_fmt *fmt;
+
+	vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type);
+	if (!vq) {
+		mtk_v4l2_err("fail to get vq");
+		return -EINVAL;
+	}
+
+	if (vb2_is_busy(vq)) {
+		mtk_v4l2_err("queue busy");
+		return -EBUSY;
+	}
+
+	q_data = mtk_venc_get_q_data(ctx, f->type);
+	if (!q_data) {
+		mtk_v4l2_err("fail to get q data");
+		return -EINVAL;
+	}
+
+	fmt = mtk_venc_find_format(f);
+	if (!fmt) {
+		f->fmt.pix.pixelformat = mtk_video_formats[CAP_FMT_IDX].fourcc;
+		fmt = mtk_venc_find_format(f);
+	}
+
+	q_data->fmt = fmt;
+	ret = vidioc_try_fmt(f, q_data->fmt);
+	if (ret)
+		return ret;
+
+	q_data->coded_width = f->fmt.pix_mp.width;
+	q_data->coded_height = f->fmt.pix_mp.height;
+	q_data->field = f->fmt.pix_mp.field;
+
+	for (i = 0; i < f->fmt.pix_mp.num_planes; i++) {
+		struct v4l2_plane_pix_format	*plane_fmt;
+
+		plane_fmt = &f->fmt.pix_mp.plane_fmt[i];
+		q_data->bytesperline[i]	= plane_fmt->bytesperline;
+		q_data->sizeimage[i] = plane_fmt->sizeimage;
+	}
+
+	if (ctx->state == MTK_STATE_FREE) {
+		ret = venc_if_init(ctx, q_data->fmt->fourcc);
+		if (ret) {
+			mtk_v4l2_err("venc_if_init failed=%d, codec type=%x",
+					ret, q_data->fmt->fourcc);
+			return -EBUSY;
+		}
+		ctx->state = MTK_STATE_INIT;
+	}
+
+	return 0;
+}
+
+static int vidioc_venc_s_fmt_out(struct file *file, void *priv,
+			     struct v4l2_format *f)
+{
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+	struct vb2_queue *vq;
+	struct mtk_q_data *q_data;
+	int ret, i;
+	struct mtk_video_fmt *fmt;
+	unsigned int pitch_w_div16;
+	struct v4l2_pix_format_mplane *pix_fmt_mp = &f->fmt.pix_mp;
+
+	vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type);
+	if (!vq) {
+		mtk_v4l2_err("fail to get vq");
+		return -EINVAL;
+	}
+
+	if (vb2_is_busy(vq)) {
+		mtk_v4l2_err("queue busy");
+		return -EBUSY;
+	}
+
+	q_data = mtk_venc_get_q_data(ctx, f->type);
+	if (!q_data) {
+		mtk_v4l2_err("fail to get q data");
+		return -EINVAL;
+	}
+
+	fmt = mtk_venc_find_format(f);
+	if (!fmt) {
+		f->fmt.pix.pixelformat = mtk_video_formats[OUT_FMT_IDX].fourcc;
+		fmt = mtk_venc_find_format(f);
+	}
+
+	pix_fmt_mp->height = clamp(pix_fmt_mp->height,
+				MTK_VENC_MIN_H,
+				MTK_VENC_MAX_H);
+	pix_fmt_mp->width = clamp(pix_fmt_mp->width,
+				MTK_VENC_MIN_W,
+				MTK_VENC_MAX_W);
+
+	q_data->visible_width = f->fmt.pix_mp.width;
+	q_data->visible_height = f->fmt.pix_mp.height;
+	q_data->fmt = fmt;
+	ret = vidioc_try_fmt(f, q_data->fmt);
+	if (ret)
+		return ret;
+
+	q_data->coded_width = f->fmt.pix_mp.width;
+	q_data->coded_height = f->fmt.pix_mp.height;
+
+	pitch_w_div16 = DIV_ROUND_UP(q_data->visible_width, 16);
+	if (pitch_w_div16 % 8 != 0) {
+		/* Adjust returned width/height, so application could correctly
+		 * allocate hw required memory
+		 */
+		q_data->visible_height += 32;
+		vidioc_try_fmt(f, q_data->fmt);
+	}
+
+	q_data->field = f->fmt.pix_mp.field;
+	ctx->colorspace = f->fmt.pix_mp.colorspace;
+	ctx->ycbcr_enc = f->fmt.pix_mp.ycbcr_enc;
+	ctx->quantization = f->fmt.pix_mp.quantization;
+	ctx->xfer_func = f->fmt.pix_mp.xfer_func;
+
+	for (i = 0; i < f->fmt.pix_mp.num_planes; i++) {
+		struct v4l2_plane_pix_format *plane_fmt;
+
+		plane_fmt = &f->fmt.pix_mp.plane_fmt[i];
+		q_data->bytesperline[i] = plane_fmt->bytesperline;
+		q_data->sizeimage[i] = plane_fmt->sizeimage;
+	}
+
+	return 0;
+}
+
+static int vidioc_venc_g_fmt(struct file *file, void *priv,
+			     struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+	struct vb2_queue *vq;
+	struct mtk_q_data *q_data;
+	int i;
+
+	vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = mtk_venc_get_q_data(ctx, f->type);
+
+	pix->width = q_data->coded_width;
+	pix->height = q_data->coded_height;
+	pix->pixelformat = q_data->fmt->fourcc;
+	pix->field = q_data->field;
+	pix->num_planes = q_data->fmt->num_planes;
+	for (i = 0; i < pix->num_planes; i++) {
+		pix->plane_fmt[i].bytesperline = q_data->bytesperline[i];
+		pix->plane_fmt[i].sizeimage = q_data->sizeimage[i];
+		memset(&(pix->plane_fmt[i].reserved[0]), 0x0,
+		       sizeof(pix->plane_fmt[i].reserved));
+	}
+
+	pix->flags = 0;
+	pix->colorspace = ctx->colorspace;
+	pix->ycbcr_enc = ctx->ycbcr_enc;
+	pix->quantization = ctx->quantization;
+	pix->xfer_func = ctx->xfer_func;
+
+	return 0;
+}
+
+static int vidioc_try_fmt_vid_cap_mplane(struct file *file, void *priv,
+					 struct v4l2_format *f)
+{
+	struct mtk_video_fmt *fmt;
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+
+	fmt = mtk_venc_find_format(f);
+	if (!fmt) {
+		f->fmt.pix.pixelformat = mtk_video_formats[CAP_FMT_IDX].fourcc;
+		fmt = mtk_venc_find_format(f);
+	}
+	f->fmt.pix_mp.colorspace = ctx->colorspace;
+	f->fmt.pix_mp.ycbcr_enc = ctx->ycbcr_enc;
+	f->fmt.pix_mp.quantization = ctx->quantization;
+	f->fmt.pix_mp.xfer_func = ctx->xfer_func;
+
+	return vidioc_try_fmt(f, fmt);
+}
+
+static int vidioc_try_fmt_vid_out_mplane(struct file *file, void *priv,
+					 struct v4l2_format *f)
+{
+	struct mtk_video_fmt *fmt;
+
+	fmt = mtk_venc_find_format(f);
+	if (!fmt) {
+		f->fmt.pix.pixelformat = mtk_video_formats[OUT_FMT_IDX].fourcc;
+		fmt = mtk_venc_find_format(f);
+	}
+	if (!f->fmt.pix_mp.colorspace) {
+		f->fmt.pix_mp.colorspace = V4L2_COLORSPACE_REC709;
+		f->fmt.pix_mp.ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT;
+		f->fmt.pix_mp.quantization = V4L2_QUANTIZATION_DEFAULT;
+		f->fmt.pix_mp.xfer_func = V4L2_XFER_FUNC_DEFAULT;
+	}
+
+	return vidioc_try_fmt(f, fmt);
+}
+
+static int vidioc_venc_qbuf(struct file *file, void *priv,
+			    struct v4l2_buffer *buf)
+{
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+
+	if (ctx->state == MTK_STATE_ABORT) {
+		mtk_v4l2_err("[%d] Call on QBUF after unrecoverable error",
+				ctx->id);
+		return -EIO;
+	}
+
+	return v4l2_m2m_qbuf(file, ctx->m2m_ctx, buf);
+}
+
+static int vidioc_venc_dqbuf(struct file *file, void *priv,
+			     struct v4l2_buffer *buf)
+{
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+
+	if (ctx->state == MTK_STATE_ABORT) {
+		mtk_v4l2_err("[%d] Call on QBUF after unrecoverable error",
+				ctx->id);
+		return -EIO;
+	}
+
+	return v4l2_m2m_dqbuf(file, ctx->m2m_ctx, buf);
+}
+
+const struct v4l2_ioctl_ops mtk_venc_ioctl_ops = {
+	.vidioc_streamon		= v4l2_m2m_ioctl_streamon,
+	.vidioc_streamoff		= v4l2_m2m_ioctl_streamoff,
+
+	.vidioc_reqbufs			= v4l2_m2m_ioctl_reqbufs,
+	.vidioc_querybuf		= v4l2_m2m_ioctl_querybuf,
+	.vidioc_qbuf			= vidioc_venc_qbuf,
+	.vidioc_dqbuf			= vidioc_venc_dqbuf,
+
+	.vidioc_querycap		= vidioc_venc_querycap,
+	.vidioc_enum_fmt_vid_cap_mplane = vidioc_enum_fmt_vid_cap_mplane,
+	.vidioc_enum_fmt_vid_out_mplane = vidioc_enum_fmt_vid_out_mplane,
+	.vidioc_enum_framesizes		= vidioc_enum_framesizes,
+
+	.vidioc_try_fmt_vid_cap_mplane	= vidioc_try_fmt_vid_cap_mplane,
+	.vidioc_try_fmt_vid_out_mplane	= vidioc_try_fmt_vid_out_mplane,
+	.vidioc_expbuf			= v4l2_m2m_ioctl_expbuf,
+	.vidioc_subscribe_event		= v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
+
+	.vidioc_s_parm			= vidioc_venc_s_parm,
+	.vidioc_g_parm			= vidioc_venc_g_parm,
+	.vidioc_s_fmt_vid_cap_mplane	= vidioc_venc_s_fmt_cap,
+	.vidioc_s_fmt_vid_out_mplane	= vidioc_venc_s_fmt_out,
+
+	.vidioc_g_fmt_vid_cap_mplane	= vidioc_venc_g_fmt,
+	.vidioc_g_fmt_vid_out_mplane	= vidioc_venc_g_fmt,
+
+	.vidioc_create_bufs		= v4l2_m2m_ioctl_create_bufs,
+	.vidioc_prepare_buf		= v4l2_m2m_ioctl_prepare_buf,
+};
+
+static int vb2ops_venc_queue_setup(struct vb2_queue *vq,
+				   unsigned int *nbuffers,
+				   unsigned int *nplanes,
+				   unsigned int sizes[],
+				   struct device *alloc_devs[])
+{
+	struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(vq);
+	struct mtk_q_data *q_data;
+	unsigned int i;
+
+	q_data = mtk_venc_get_q_data(ctx, vq->type);
+
+	if (q_data == NULL)
+		return -EINVAL;
+
+	if (*nplanes) {
+		for (i = 0; i < *nplanes; i++)
+			if (sizes[i] < q_data->sizeimage[i])
+				return -EINVAL;
+	} else {
+		*nplanes = q_data->fmt->num_planes;
+		for (i = 0; i < *nplanes; i++)
+			sizes[i] = q_data->sizeimage[i];
+	}
+
+	return 0;
+}
+
+static int vb2ops_venc_buf_prepare(struct vb2_buffer *vb)
+{
+	struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct mtk_q_data *q_data;
+	int i;
+
+	q_data = mtk_venc_get_q_data(ctx, vb->vb2_queue->type);
+
+	for (i = 0; i < q_data->fmt->num_planes; i++) {
+		if (vb2_plane_size(vb, i) < q_data->sizeimage[i]) {
+			mtk_v4l2_err("data will not fit into plane %d (%lu < %d)",
+				i, vb2_plane_size(vb, i),
+				q_data->sizeimage[i]);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static void vb2ops_venc_buf_queue(struct vb2_buffer *vb)
+{
+	struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct vb2_v4l2_buffer *vb2_v4l2 =
+			container_of(vb, struct vb2_v4l2_buffer, vb2_buf);
+
+	struct mtk_video_enc_buf *mtk_buf =
+			container_of(vb2_v4l2, struct mtk_video_enc_buf, vb);
+
+	if ((vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) &&
+	    (ctx->param_change != MTK_ENCODE_PARAM_NONE)) {
+		mtk_v4l2_debug(1, "[%d] Before id=%d encode parameter change %x",
+			       ctx->id,
+			       mtk_buf->vb.vb2_buf.index,
+			       ctx->param_change);
+		mtk_buf->param_change = ctx->param_change;
+		mtk_buf->enc_params = ctx->enc_params;
+		ctx->param_change = MTK_ENCODE_PARAM_NONE;
+	}
+
+	v4l2_m2m_buf_queue(ctx->m2m_ctx, to_vb2_v4l2_buffer(vb));
+}
+
+static int vb2ops_venc_start_streaming(struct vb2_queue *q, unsigned int count)
+{
+	struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(q);
+	struct venc_enc_param param;
+	int ret;
+	int i;
+
+	/* Once state turn into MTK_STATE_ABORT, we need stop_streaming
+	  * to clear it
+	  */
+	if ((ctx->state == MTK_STATE_ABORT) || (ctx->state == MTK_STATE_FREE)) {
+		ret = -EIO;
+		goto err_set_param;
+	}
+
+	/* Do the initialization when both start_streaming have been called */
+	if (V4L2_TYPE_IS_OUTPUT(q->type)) {
+		if (!vb2_start_streaming_called(&ctx->m2m_ctx->cap_q_ctx.q))
+			return 0;
+	} else {
+		if (!vb2_start_streaming_called(&ctx->m2m_ctx->out_q_ctx.q))
+			return 0;
+	}
+
+	mtk_venc_set_param(ctx, &param);
+	ret = venc_if_set_param(ctx, VENC_SET_PARAM_ENC, &param);
+	if (ret) {
+		mtk_v4l2_err("venc_if_set_param failed=%d", ret);
+		ctx->state = MTK_STATE_ABORT;
+		goto err_set_param;
+	}
+	ctx->param_change = MTK_ENCODE_PARAM_NONE;
+
+	if ((ctx->q_data[MTK_Q_DATA_DST].fmt->fourcc == V4L2_PIX_FMT_H264) &&
+	    (ctx->enc_params.seq_hdr_mode !=
+				V4L2_MPEG_VIDEO_HEADER_MODE_SEPARATE)) {
+		ret = venc_if_set_param(ctx,
+					VENC_SET_PARAM_PREPEND_HEADER,
+					NULL);
+		if (ret) {
+			mtk_v4l2_err("venc_if_set_param failed=%d", ret);
+			ctx->state = MTK_STATE_ABORT;
+			goto err_set_param;
+		}
+		ctx->state = MTK_STATE_HEADER;
+	}
+
+	return 0;
+
+err_set_param:
+	for (i = 0; i < q->num_buffers; ++i) {
+		if (q->bufs[i]->state == VB2_BUF_STATE_ACTIVE) {
+			mtk_v4l2_debug(0, "[%d] id=%d, type=%d, %d -> VB2_BUF_STATE_QUEUED",
+					ctx->id, i, q->type,
+					(int)q->bufs[i]->state);
+			v4l2_m2m_buf_done(to_vb2_v4l2_buffer(q->bufs[i]),
+					VB2_BUF_STATE_QUEUED);
+		}
+	}
+
+	return ret;
+}
+
+static void vb2ops_venc_stop_streaming(struct vb2_queue *q)
+{
+	struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(q);
+	struct vb2_buffer *src_buf, *dst_buf;
+	int ret;
+
+	mtk_v4l2_debug(2, "[%d]-> type=%d", ctx->id, q->type);
+
+	if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
+		while ((dst_buf = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx))) {
+			dst_buf->planes[0].bytesused = 0;
+			v4l2_m2m_buf_done(to_vb2_v4l2_buffer(dst_buf),
+					VB2_BUF_STATE_ERROR);
+		}
+	} else {
+		while ((src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx)))
+			v4l2_m2m_buf_done(to_vb2_v4l2_buffer(src_buf),
+					VB2_BUF_STATE_ERROR);
+	}
+
+	if ((q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE &&
+	     vb2_is_streaming(&ctx->m2m_ctx->out_q_ctx.q)) ||
+	    (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE &&
+	     vb2_is_streaming(&ctx->m2m_ctx->cap_q_ctx.q))) {
+		mtk_v4l2_debug(1, "[%d]-> q type %d out=%d cap=%d",
+			       ctx->id, q->type,
+			       vb2_is_streaming(&ctx->m2m_ctx->out_q_ctx.q),
+			       vb2_is_streaming(&ctx->m2m_ctx->cap_q_ctx.q));
+		return;
+	}
+
+	/* Release the encoder if both streams are stopped. */
+	ret = venc_if_deinit(ctx);
+	if (ret)
+		mtk_v4l2_err("venc_if_deinit failed=%d", ret);
+
+	ctx->state = MTK_STATE_FREE;
+}
+
+static struct vb2_ops mtk_venc_vb2_ops = {
+	.queue_setup		= vb2ops_venc_queue_setup,
+	.buf_prepare		= vb2ops_venc_buf_prepare,
+	.buf_queue		= vb2ops_venc_buf_queue,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+	.start_streaming	= vb2ops_venc_start_streaming,
+	.stop_streaming		= vb2ops_venc_stop_streaming,
+};
+
+static int mtk_venc_encode_header(void *priv)
+{
+	struct mtk_vcodec_ctx *ctx = priv;
+	int ret;
+	struct vb2_buffer *dst_buf;
+	struct mtk_vcodec_mem bs_buf;
+	struct venc_done_result enc_result;
+
+	dst_buf = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx);
+	if (!dst_buf) {
+		mtk_v4l2_debug(1, "No dst buffer");
+		return -EINVAL;
+	}
+
+	bs_buf.va = vb2_plane_vaddr(dst_buf, 0);
+	bs_buf.dma_addr = vb2_dma_contig_plane_dma_addr(dst_buf, 0);
+	bs_buf.size = (size_t)dst_buf->planes[0].length;
+
+	mtk_v4l2_debug(1,
+			"[%d] buf id=%d va=0x%p dma_addr=0x%llx size=%zu",
+			ctx->id,
+			dst_buf->index, bs_buf.va,
+			(u64)bs_buf.dma_addr,
+			bs_buf.size);
+
+	ret = venc_if_encode(ctx,
+			VENC_START_OPT_ENCODE_SEQUENCE_HEADER,
+			NULL, &bs_buf, &enc_result);
+
+	if (ret) {
+		dst_buf->planes[0].bytesused = 0;
+		ctx->state = MTK_STATE_ABORT;
+		v4l2_m2m_buf_done(to_vb2_v4l2_buffer(dst_buf),
+				  VB2_BUF_STATE_ERROR);
+		mtk_v4l2_err("venc_if_encode failed=%d", ret);
+		return -EINVAL;
+	}
+
+	ctx->state = MTK_STATE_HEADER;
+	dst_buf->planes[0].bytesused = enc_result.bs_size;
+	v4l2_m2m_buf_done(to_vb2_v4l2_buffer(dst_buf), VB2_BUF_STATE_DONE);
+
+	return 0;
+}
+
+static int mtk_venc_param_change(struct mtk_vcodec_ctx *ctx)
+{
+	struct venc_enc_param enc_prm;
+	struct vb2_buffer *vb = v4l2_m2m_next_src_buf(ctx->m2m_ctx);
+	struct vb2_v4l2_buffer *vb2_v4l2 =
+			container_of(vb, struct vb2_v4l2_buffer, vb2_buf);
+	struct mtk_video_enc_buf *mtk_buf =
+			container_of(vb2_v4l2, struct mtk_video_enc_buf, vb);
+
+	int ret = 0;
+
+	memset(&enc_prm, 0, sizeof(enc_prm));
+	if (mtk_buf->param_change == MTK_ENCODE_PARAM_NONE)
+		return 0;
+
+	if (mtk_buf->param_change & MTK_ENCODE_PARAM_BITRATE) {
+		enc_prm.bitrate = mtk_buf->enc_params.bitrate;
+		mtk_v4l2_debug(1, "[%d] id=%d, change param br=%d",
+				ctx->id,
+				mtk_buf->vb.vb2_buf.index,
+				enc_prm.bitrate);
+		ret |= venc_if_set_param(ctx,
+					 VENC_SET_PARAM_ADJUST_BITRATE,
+					 &enc_prm);
+	}
+	if (!ret && mtk_buf->param_change & MTK_ENCODE_PARAM_FRAMERATE) {
+		enc_prm.frm_rate = mtk_buf->enc_params.framerate_num /
+				   mtk_buf->enc_params.framerate_denom;
+		mtk_v4l2_debug(1, "[%d] id=%d, change param fr=%d",
+			       ctx->id,
+			       mtk_buf->vb.vb2_buf.index,
+			       enc_prm.frm_rate);
+		ret |= venc_if_set_param(ctx,
+					 VENC_SET_PARAM_ADJUST_FRAMERATE,
+					 &enc_prm);
+	}
+	if (!ret && mtk_buf->param_change & MTK_ENCODE_PARAM_GOP_SIZE) {
+		enc_prm.gop_size = mtk_buf->enc_params.gop_size;
+		mtk_v4l2_debug(1, "change param intra period=%d",
+			       enc_prm.gop_size);
+		ret |= venc_if_set_param(ctx,
+					 VENC_SET_PARAM_GOP_SIZE,
+					 &enc_prm);
+	}
+	if (!ret && mtk_buf->param_change & MTK_ENCODE_PARAM_FORCE_INTRA) {
+		mtk_v4l2_debug(1, "[%d] id=%d, change param force I=%d",
+				ctx->id,
+				mtk_buf->vb.vb2_buf.index,
+				mtk_buf->enc_params.force_intra);
+		if (mtk_buf->enc_params.force_intra)
+			ret |= venc_if_set_param(ctx,
+						 VENC_SET_PARAM_FORCE_INTRA,
+						 NULL);
+	}
+
+	mtk_buf->param_change = MTK_ENCODE_PARAM_NONE;
+
+	if (ret) {
+		ctx->state = MTK_STATE_ABORT;
+		mtk_v4l2_err("venc_if_set_param %d failed=%d",
+				mtk_buf->param_change, ret);
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * v4l2_m2m_streamoff() holds dev_mutex and waits mtk_venc_worker()
+ * to call v4l2_m2m_job_finish().
+ * If mtk_venc_worker() tries to acquire dev_mutex, it will deadlock.
+ * So this function must not try to acquire dev->dev_mutex.
+ * This means v4l2 ioctls and mtk_venc_worker() can run at the same time.
+ * mtk_venc_worker() should be carefully implemented to avoid bugs.
+ */
+static void mtk_venc_worker(struct work_struct *work)
+{
+	struct mtk_vcodec_ctx *ctx = container_of(work, struct mtk_vcodec_ctx,
+				    encode_work);
+	struct vb2_buffer *src_buf, *dst_buf;
+	struct venc_frm_buf frm_buf;
+	struct mtk_vcodec_mem bs_buf;
+	struct venc_done_result enc_result;
+	int ret, i;
+	struct vb2_v4l2_buffer *vb2_v4l2;
+
+	/* check dst_buf, dst_buf may be removed in device_run
+	 * to stored encdoe header so we need check dst_buf and
+	 * call job_finish here to prevent recursion
+	 */
+	dst_buf = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx);
+	if (!dst_buf) {
+		v4l2_m2m_job_finish(ctx->dev->m2m_dev_enc, ctx->m2m_ctx);
+		return;
+	}
+
+	src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx);
+	memset(&frm_buf, 0, sizeof(frm_buf));
+	for (i = 0; i < src_buf->num_planes ; i++) {
+		frm_buf.fb_addr[i].va = vb2_plane_vaddr(src_buf, i);
+		frm_buf.fb_addr[i].dma_addr =
+				vb2_dma_contig_plane_dma_addr(src_buf, i);
+		frm_buf.fb_addr[i].size =
+				(size_t)src_buf->planes[i].length;
+	}
+	bs_buf.va = vb2_plane_vaddr(dst_buf, 0);
+	bs_buf.dma_addr = vb2_dma_contig_plane_dma_addr(dst_buf, 0);
+	bs_buf.size = (size_t)dst_buf->planes[0].length;
+
+	mtk_v4l2_debug(2,
+			"Framebuf VA=%p PA=%llx Size=0x%zx;VA=%p PA=0x%llx Size=0x%zx;VA=%p PA=0x%llx Size=%zu",
+			frm_buf.fb_addr[0].va,
+			(u64)frm_buf.fb_addr[0].dma_addr,
+			frm_buf.fb_addr[0].size,
+			frm_buf.fb_addr[1].va,
+			(u64)frm_buf.fb_addr[1].dma_addr,
+			frm_buf.fb_addr[1].size,
+			frm_buf.fb_addr[2].va,
+			(u64)frm_buf.fb_addr[2].dma_addr,
+			frm_buf.fb_addr[2].size);
+
+	ret = venc_if_encode(ctx, VENC_START_OPT_ENCODE_FRAME,
+			     &frm_buf, &bs_buf, &enc_result);
+
+	vb2_v4l2 = container_of(dst_buf, struct vb2_v4l2_buffer, vb2_buf);
+	if (enc_result.is_key_frm)
+		vb2_v4l2->flags |= V4L2_BUF_FLAG_KEYFRAME;
+
+	if (ret) {
+		v4l2_m2m_buf_done(to_vb2_v4l2_buffer(src_buf),
+				  VB2_BUF_STATE_ERROR);
+		dst_buf->planes[0].bytesused = 0;
+		v4l2_m2m_buf_done(to_vb2_v4l2_buffer(dst_buf),
+				  VB2_BUF_STATE_ERROR);
+		mtk_v4l2_err("venc_if_encode failed=%d", ret);
+	} else {
+		v4l2_m2m_buf_done(to_vb2_v4l2_buffer(src_buf),
+				  VB2_BUF_STATE_DONE);
+		dst_buf->planes[0].bytesused = enc_result.bs_size;
+		v4l2_m2m_buf_done(to_vb2_v4l2_buffer(dst_buf),
+				  VB2_BUF_STATE_DONE);
+		mtk_v4l2_debug(2, "venc_if_encode bs size=%d",
+				 enc_result.bs_size);
+	}
+
+	v4l2_m2m_job_finish(ctx->dev->m2m_dev_enc, ctx->m2m_ctx);
+
+	mtk_v4l2_debug(1, "<=== src_buf[%d] dst_buf[%d] venc_if_encode ret=%d Size=%u===>",
+			src_buf->index, dst_buf->index, ret,
+			enc_result.bs_size);
+}
+
+static void m2mops_venc_device_run(void *priv)
+{
+	struct mtk_vcodec_ctx *ctx = priv;
+
+	if ((ctx->q_data[MTK_Q_DATA_DST].fmt->fourcc == V4L2_PIX_FMT_H264) &&
+	    (ctx->state != MTK_STATE_HEADER)) {
+		/* encode h264 sps/pps header */
+		mtk_venc_encode_header(ctx);
+		queue_work(ctx->dev->encode_workqueue, &ctx->encode_work);
+		return;
+	}
+
+	mtk_venc_param_change(ctx);
+	queue_work(ctx->dev->encode_workqueue, &ctx->encode_work);
+}
+
+static int m2mops_venc_job_ready(void *m2m_priv)
+{
+	struct mtk_vcodec_ctx *ctx = m2m_priv;
+
+	if (ctx->state == MTK_STATE_ABORT || ctx->state == MTK_STATE_FREE) {
+		mtk_v4l2_debug(3, "[%d]Not ready: state=0x%x.",
+			       ctx->id, ctx->state);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void m2mops_venc_job_abort(void *priv)
+{
+	struct mtk_vcodec_ctx *ctx = priv;
+
+	ctx->state = MTK_STATE_ABORT;
+}
+
+static void m2mops_venc_lock(void *m2m_priv)
+{
+	struct mtk_vcodec_ctx *ctx = m2m_priv;
+
+	mutex_lock(&ctx->dev->dev_mutex);
+}
+
+static void m2mops_venc_unlock(void *m2m_priv)
+{
+	struct mtk_vcodec_ctx *ctx = m2m_priv;
+
+	mutex_unlock(&ctx->dev->dev_mutex);
+}
+
+const struct v4l2_m2m_ops mtk_venc_m2m_ops = {
+	.device_run	= m2mops_venc_device_run,
+	.job_ready	= m2mops_venc_job_ready,
+	.job_abort	= m2mops_venc_job_abort,
+	.lock		= m2mops_venc_lock,
+	.unlock		= m2mops_venc_unlock,
+};
+
+void mtk_vcodec_enc_set_default_params(struct mtk_vcodec_ctx *ctx)
+{
+	struct mtk_q_data *q_data;
+
+	ctx->m2m_ctx->q_lock = &ctx->dev->dev_mutex;
+	ctx->fh.m2m_ctx = ctx->m2m_ctx;
+	ctx->fh.ctrl_handler = &ctx->ctrl_hdl;
+	INIT_WORK(&ctx->encode_work, mtk_venc_worker);
+
+	ctx->colorspace = V4L2_COLORSPACE_REC709;
+	ctx->ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT;
+	ctx->quantization = V4L2_QUANTIZATION_DEFAULT;
+	ctx->xfer_func = V4L2_XFER_FUNC_DEFAULT;
+
+	q_data = &ctx->q_data[MTK_Q_DATA_SRC];
+	memset(q_data, 0, sizeof(struct mtk_q_data));
+	q_data->visible_width = DFT_CFG_WIDTH;
+	q_data->visible_height = DFT_CFG_HEIGHT;
+	q_data->coded_width = DFT_CFG_WIDTH;
+	q_data->coded_height = DFT_CFG_HEIGHT;
+	q_data->field = V4L2_FIELD_NONE;
+
+	q_data->fmt = &mtk_video_formats[OUT_FMT_IDX];
+
+	v4l_bound_align_image(&q_data->coded_width,
+				MTK_VENC_MIN_W,
+				MTK_VENC_MAX_W, 4,
+				&q_data->coded_height,
+				MTK_VENC_MIN_H,
+				MTK_VENC_MAX_H, 5, 6);
+
+	if (q_data->coded_width < DFT_CFG_WIDTH &&
+		(q_data->coded_width + 16) <= MTK_VENC_MAX_W)
+		q_data->coded_width += 16;
+	if (q_data->coded_height < DFT_CFG_HEIGHT &&
+		(q_data->coded_height + 32) <= MTK_VENC_MAX_H)
+		q_data->coded_height += 32;
+
+	q_data->sizeimage[0] =
+		q_data->coded_width * q_data->coded_height+
+		((ALIGN(q_data->coded_width, 16) * 2) * 16);
+	q_data->bytesperline[0] = q_data->coded_width;
+	q_data->sizeimage[1] =
+		(q_data->coded_width * q_data->coded_height) / 2 +
+		(ALIGN(q_data->coded_width, 16) * 16);
+	q_data->bytesperline[1] = q_data->coded_width;
+
+	q_data = &ctx->q_data[MTK_Q_DATA_DST];
+	memset(q_data, 0, sizeof(struct mtk_q_data));
+	q_data->coded_width = DFT_CFG_WIDTH;
+	q_data->coded_height = DFT_CFG_HEIGHT;
+	q_data->fmt = &mtk_video_formats[CAP_FMT_IDX];
+	q_data->field = V4L2_FIELD_NONE;
+	ctx->q_data[MTK_Q_DATA_DST].sizeimage[0] =
+		DFT_CFG_WIDTH * DFT_CFG_HEIGHT;
+	ctx->q_data[MTK_Q_DATA_DST].bytesperline[0] = 0;
+
+}
+
+int mtk_vcodec_enc_ctrls_setup(struct mtk_vcodec_ctx *ctx)
+{
+	const struct v4l2_ctrl_ops *ops = &mtk_vcodec_enc_ctrl_ops;
+	struct v4l2_ctrl_handler *handler = &ctx->ctrl_hdl;
+
+	v4l2_ctrl_handler_init(handler, MTK_MAX_CTRLS_HINT);
+
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_BITRATE,
+			1, 4000000, 1, 4000000);
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_B_FRAMES,
+			0, 2, 1, 0);
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_FRAME_RC_ENABLE,
+			0, 1, 1, 1);
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_H264_MAX_QP,
+			0, 51, 1, 51);
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_H264_I_PERIOD,
+			0, 65535, 1, 0);
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_GOP_SIZE,
+			0, 65535, 1, 0);
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_MB_RC_ENABLE,
+			0, 1, 1, 0);
+	v4l2_ctrl_new_std(handler, ops, V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME,
+			0, 0, 0, 0);
+	v4l2_ctrl_new_std_menu(handler, ops,
+			V4L2_CID_MPEG_VIDEO_HEADER_MODE,
+			V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME,
+			0, V4L2_MPEG_VIDEO_HEADER_MODE_SEPARATE);
+	v4l2_ctrl_new_std_menu(handler, ops, V4L2_CID_MPEG_VIDEO_H264_PROFILE,
+			V4L2_MPEG_VIDEO_H264_PROFILE_HIGH,
+			0, V4L2_MPEG_VIDEO_H264_PROFILE_MAIN);
+	v4l2_ctrl_new_std_menu(handler, ops, V4L2_CID_MPEG_VIDEO_H264_LEVEL,
+			V4L2_MPEG_VIDEO_H264_LEVEL_4_2,
+			0, V4L2_MPEG_VIDEO_H264_LEVEL_4_0);
+	if (handler->error) {
+		mtk_v4l2_err("Init control handler fail %d",
+				handler->error);
+		return handler->error;
+	}
+
+	v4l2_ctrl_handler_setup(&ctx->ctrl_hdl);
+
+	return 0;
+}
+
+int mtk_vcodec_enc_queue_init(void *priv, struct vb2_queue *src_vq,
+			      struct vb2_queue *dst_vq)
+{
+	struct mtk_vcodec_ctx *ctx = priv;
+	int ret;
+
+	/* Note: VB2_USERPTR works with dma-contig because mt8173
+	 * support iommu
+	 * https://patchwork.kernel.org/patch/8335461/
+	 * https://patchwork.kernel.org/patch/7596181/
+	 */
+	src_vq->type		= V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
+	src_vq->io_modes	= VB2_DMABUF | VB2_MMAP | VB2_USERPTR;
+	src_vq->drv_priv	= ctx;
+	src_vq->buf_struct_size = sizeof(struct mtk_video_enc_buf);
+	src_vq->ops		= &mtk_venc_vb2_ops;
+	src_vq->mem_ops		= &vb2_dma_contig_memops;
+	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->lock		= &ctx->dev->dev_mutex;
+	src_vq->dev		= &ctx->dev->plat_dev->dev;
+
+	ret = vb2_queue_init(src_vq);
+	if (ret)
+		return ret;
+
+	dst_vq->type		= V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+	dst_vq->io_modes	= VB2_DMABUF | VB2_MMAP | VB2_USERPTR;
+	dst_vq->drv_priv	= ctx;
+	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	dst_vq->ops		= &mtk_venc_vb2_ops;
+	dst_vq->mem_ops		= &vb2_dma_contig_memops;
+	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->lock		= &ctx->dev->dev_mutex;
+	dst_vq->dev		= &ctx->dev->plat_dev->dev;
+
+	return vb2_queue_init(dst_vq);
+}
+
+int mtk_venc_unlock(struct mtk_vcodec_ctx *ctx)
+{
+	struct mtk_vcodec_dev *dev = ctx->dev;
+
+	mutex_unlock(&dev->enc_mutex);
+	return 0;
+}
+
+int mtk_venc_lock(struct mtk_vcodec_ctx *ctx)
+{
+	struct mtk_vcodec_dev *dev = ctx->dev;
+
+	mutex_lock(&dev->enc_mutex);
+	return 0;
+}
+
+void mtk_vcodec_enc_release(struct mtk_vcodec_ctx *ctx)
+{
+	venc_if_deinit(ctx);
+}
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.h
new file mode 100644
index 000000000000..d7a154a97510
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.h
@@ -0,0 +1,58 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: PC Chen <pc.chen@mediatek.com>
+*         Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#ifndef _MTK_VCODEC_ENC_H_
+#define _MTK_VCODEC_ENC_H_
+
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-v4l2.h>
+
+#define MTK_VENC_IRQ_STATUS_SPS	0x1
+#define MTK_VENC_IRQ_STATUS_PPS	0x2
+#define MTK_VENC_IRQ_STATUS_FRM	0x4
+#define MTK_VENC_IRQ_STATUS_DRAM	0x8
+#define MTK_VENC_IRQ_STATUS_PAUSE	0x10
+#define MTK_VENC_IRQ_STATUS_SWITCH	0x20
+
+#define MTK_VENC_IRQ_STATUS_OFFSET	0x05C
+#define MTK_VENC_IRQ_ACK_OFFSET	0x060
+
+/**
+ * struct mtk_video_enc_buf - Private data related to each VB2 buffer.
+ * @vb: Pointer to related VB2 buffer.
+ * @list:	list that buffer link to
+ * @param_change: Types of encode parameter change before encoding this
+ *				buffer
+ * @enc_params: Encode parameters changed before encode this buffer
+ */
+struct mtk_video_enc_buf {
+	struct vb2_v4l2_buffer vb;
+	struct list_head list;
+	u32 param_change;
+	struct mtk_enc_params enc_params;
+};
+
+extern const struct v4l2_ioctl_ops mtk_venc_ioctl_ops;
+extern const struct v4l2_m2m_ops mtk_venc_m2m_ops;
+
+int mtk_venc_unlock(struct mtk_vcodec_ctx *ctx);
+int mtk_venc_lock(struct mtk_vcodec_ctx *ctx);
+int mtk_vcodec_enc_queue_init(void *priv, struct vb2_queue *src_vq,
+			      struct vb2_queue *dst_vq);
+void mtk_vcodec_enc_release(struct mtk_vcodec_ctx *ctx);
+int mtk_vcodec_enc_ctrls_setup(struct mtk_vcodec_ctx *ctx);
+void mtk_vcodec_enc_set_default_params(struct mtk_vcodec_ctx *ctx);
+
+#endif /* _MTK_VCODEC_ENC_H_ */
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c
new file mode 100644
index 000000000000..e277b7c23516
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c
@@ -0,0 +1,439 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: PC Chen <pc.chen@mediatek.com>
+*	Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-dma-contig.h>
+#include <linux/pm_runtime.h>
+
+#include "mtk_vcodec_drv.h"
+#include "mtk_vcodec_enc.h"
+#include "mtk_vcodec_enc_pm.h"
+#include "mtk_vcodec_intr.h"
+#include "mtk_vcodec_util.h"
+#include "mtk_vpu.h"
+
+module_param(mtk_v4l2_dbg_level, int, S_IRUGO | S_IWUSR);
+module_param(mtk_vcodec_dbg, bool, S_IRUGO | S_IWUSR);
+
+/* Wake up context wait_queue */
+static void wake_up_ctx(struct mtk_vcodec_ctx *ctx, unsigned int reason)
+{
+	ctx->int_cond = 1;
+	ctx->int_type = reason;
+	wake_up_interruptible(&ctx->queue);
+}
+
+static void clean_irq_status(unsigned int irq_status, void __iomem *addr)
+{
+	if (irq_status & MTK_VENC_IRQ_STATUS_PAUSE)
+		writel(MTK_VENC_IRQ_STATUS_PAUSE, addr);
+
+	if (irq_status & MTK_VENC_IRQ_STATUS_SWITCH)
+		writel(MTK_VENC_IRQ_STATUS_SWITCH, addr);
+
+	if (irq_status & MTK_VENC_IRQ_STATUS_DRAM)
+		writel(MTK_VENC_IRQ_STATUS_DRAM, addr);
+
+	if (irq_status & MTK_VENC_IRQ_STATUS_SPS)
+		writel(MTK_VENC_IRQ_STATUS_SPS, addr);
+
+	if (irq_status & MTK_VENC_IRQ_STATUS_PPS)
+		writel(MTK_VENC_IRQ_STATUS_PPS, addr);
+
+	if (irq_status & MTK_VENC_IRQ_STATUS_FRM)
+		writel(MTK_VENC_IRQ_STATUS_FRM, addr);
+
+}
+static irqreturn_t mtk_vcodec_enc_irq_handler(int irq, void *priv)
+{
+	struct mtk_vcodec_dev *dev = priv;
+	struct mtk_vcodec_ctx *ctx;
+	unsigned long flags;
+	void __iomem *addr;
+
+	spin_lock_irqsave(&dev->irqlock, flags);
+	ctx = dev->curr_ctx;
+	spin_unlock_irqrestore(&dev->irqlock, flags);
+
+	mtk_v4l2_debug(1, "id=%d", ctx->id);
+	addr = dev->reg_base[VENC_SYS] + MTK_VENC_IRQ_ACK_OFFSET;
+
+	ctx->irq_status = readl(dev->reg_base[VENC_SYS] +
+				(MTK_VENC_IRQ_STATUS_OFFSET));
+
+	clean_irq_status(ctx->irq_status, addr);
+
+	wake_up_ctx(ctx, MTK_INST_IRQ_RECEIVED);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t mtk_vcodec_enc_lt_irq_handler(int irq, void *priv)
+{
+	struct mtk_vcodec_dev *dev = priv;
+	struct mtk_vcodec_ctx *ctx;
+	unsigned long flags;
+	void __iomem *addr;
+
+	spin_lock_irqsave(&dev->irqlock, flags);
+	ctx = dev->curr_ctx;
+	spin_unlock_irqrestore(&dev->irqlock, flags);
+
+	mtk_v4l2_debug(1, "id=%d", ctx->id);
+	ctx->irq_status = readl(dev->reg_base[VENC_LT_SYS] +
+				(MTK_VENC_IRQ_STATUS_OFFSET));
+
+	addr = dev->reg_base[VENC_LT_SYS] + MTK_VENC_IRQ_ACK_OFFSET;
+
+	clean_irq_status(ctx->irq_status, addr);
+
+	wake_up_ctx(ctx, MTK_INST_IRQ_RECEIVED);
+	return IRQ_HANDLED;
+}
+
+static void mtk_vcodec_enc_reset_handler(void *priv)
+{
+	struct mtk_vcodec_dev *dev = priv;
+	struct mtk_vcodec_ctx *ctx;
+
+	mtk_v4l2_debug(0, "Watchdog timeout!!");
+
+	mutex_lock(&dev->dev_mutex);
+	list_for_each_entry(ctx, &dev->ctx_list, list) {
+		ctx->state = MTK_STATE_ABORT;
+		mtk_v4l2_debug(0, "[%d] Change to state MTK_STATE_ABORT",
+				ctx->id);
+	}
+	mutex_unlock(&dev->dev_mutex);
+}
+
+static int fops_vcodec_open(struct file *file)
+{
+	struct mtk_vcodec_dev *dev = video_drvdata(file);
+	struct mtk_vcodec_ctx *ctx = NULL;
+	int ret = 0;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	mutex_lock(&dev->dev_mutex);
+	/*
+	 * Use simple counter to uniquely identify this context. Only
+	 * used for logging.
+	 */
+	ctx->id = dev->id_counter++;
+	v4l2_fh_init(&ctx->fh, video_devdata(file));
+	file->private_data = &ctx->fh;
+	v4l2_fh_add(&ctx->fh);
+	INIT_LIST_HEAD(&ctx->list);
+	ctx->dev = dev;
+	init_waitqueue_head(&ctx->queue);
+
+	ctx->type = MTK_INST_ENCODER;
+	ret = mtk_vcodec_enc_ctrls_setup(ctx);
+	if (ret) {
+		mtk_v4l2_err("Failed to setup controls() (%d)",
+				ret);
+		goto err_ctrls_setup;
+	}
+	ctx->m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev_enc, ctx,
+				&mtk_vcodec_enc_queue_init);
+	if (IS_ERR((__force void *)ctx->m2m_ctx)) {
+		ret = PTR_ERR((__force void *)ctx->m2m_ctx);
+		mtk_v4l2_err("Failed to v4l2_m2m_ctx_init() (%d)",
+				ret);
+		goto err_m2m_ctx_init;
+	}
+	mtk_vcodec_enc_set_default_params(ctx);
+
+	if (v4l2_fh_is_singular(&ctx->fh)) {
+		/*
+		 * vpu_load_firmware checks if it was loaded already and
+		 * does nothing in that case
+		 */
+		ret = vpu_load_firmware(dev->vpu_plat_dev);
+		if (ret < 0) {
+			/*
+			 * Return 0 if downloading firmware successfully,
+			 * otherwise it is failed
+			 */
+			mtk_v4l2_err("vpu_load_firmware failed!");
+			goto err_load_fw;
+		}
+
+		dev->enc_capability =
+			vpu_get_venc_hw_capa(dev->vpu_plat_dev);
+		mtk_v4l2_debug(0, "encoder capability %x", dev->enc_capability);
+	}
+
+	mtk_v4l2_debug(2, "Create instance [%d]@%p m2m_ctx=%p ",
+			ctx->id, ctx, ctx->m2m_ctx);
+
+	dev->num_instances++;
+	list_add(&ctx->list, &dev->ctx_list);
+
+	mutex_unlock(&dev->dev_mutex);
+	mtk_v4l2_debug(0, "%s encoder [%d]", dev_name(&dev->plat_dev->dev),
+			ctx->id);
+	return ret;
+
+	/* Deinit when failure occurred */
+err_load_fw:
+	v4l2_m2m_ctx_release(ctx->m2m_ctx);
+err_m2m_ctx_init:
+	v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
+err_ctrls_setup:
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	kfree(ctx);
+	mutex_unlock(&dev->dev_mutex);
+
+	return ret;
+}
+
+static int fops_vcodec_release(struct file *file)
+{
+	struct mtk_vcodec_dev *dev = video_drvdata(file);
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(file->private_data);
+
+	mtk_v4l2_debug(1, "[%d] encoder", ctx->id);
+	mutex_lock(&dev->dev_mutex);
+
+	mtk_vcodec_enc_release(ctx);
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
+	v4l2_m2m_ctx_release(ctx->m2m_ctx);
+
+	list_del_init(&ctx->list);
+	dev->num_instances--;
+	kfree(ctx);
+	mutex_unlock(&dev->dev_mutex);
+	return 0;
+}
+
+static const struct v4l2_file_operations mtk_vcodec_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fops_vcodec_open,
+	.release	= fops_vcodec_release,
+	.poll		= v4l2_m2m_fop_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= v4l2_m2m_fop_mmap,
+};
+
+static int mtk_vcodec_probe(struct platform_device *pdev)
+{
+	struct mtk_vcodec_dev *dev;
+	struct video_device *vfd_enc;
+	struct resource *res;
+	int i, j, ret;
+	DEFINE_DMA_ATTRS(attrs);
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&dev->ctx_list);
+	dev->plat_dev = pdev;
+
+	dev->vpu_plat_dev = vpu_get_plat_device(dev->plat_dev);
+	if (dev->vpu_plat_dev == NULL) {
+		mtk_v4l2_err("[VPU] vpu device in not ready");
+		return -EPROBE_DEFER;
+	}
+
+	vpu_wdt_reg_handler(dev->vpu_plat_dev, mtk_vcodec_enc_reset_handler,
+				dev, VPU_RST_ENC);
+
+	ret = mtk_vcodec_init_enc_pm(dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to get mt vcodec clock source!");
+		return ret;
+	}
+
+	for (i = VENC_SYS, j = 0; i < NUM_MAX_VCODEC_REG_BASE; i++, j++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, j);
+		if (res == NULL) {
+			dev_err(&pdev->dev, "get memory resource failed.");
+			ret = -ENXIO;
+			goto err_res;
+		}
+		dev->reg_base[i] = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR((__force void *)dev->reg_base[i])) {
+			ret = PTR_ERR((__force void *)dev->reg_base[i]);
+			goto err_res;
+		}
+		mtk_v4l2_debug(2, "reg[%d] base=0x%p", i, dev->reg_base[i]);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (res == NULL) {
+		dev_err(&pdev->dev, "failed to get irq resource");
+		ret = -ENOENT;
+		goto err_res;
+	}
+
+	dev->enc_irq = platform_get_irq(pdev, 0);
+	ret = devm_request_irq(&pdev->dev, dev->enc_irq,
+			       mtk_vcodec_enc_irq_handler,
+			       0, pdev->name, dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to install dev->enc_irq %d (%d)",
+			dev->enc_irq,
+			ret);
+		ret = -EINVAL;
+		goto err_res;
+	}
+
+	dev->enc_lt_irq = platform_get_irq(pdev, 1);
+	ret = devm_request_irq(&pdev->dev,
+			       dev->enc_lt_irq, mtk_vcodec_enc_lt_irq_handler,
+			       0, pdev->name, dev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Failed to install dev->enc_lt_irq %d (%d)",
+			dev->enc_lt_irq, ret);
+		ret = -EINVAL;
+		goto err_res;
+	}
+
+	disable_irq(dev->enc_irq);
+	disable_irq(dev->enc_lt_irq); /* VENC_LT */
+	mutex_init(&dev->enc_mutex);
+	mutex_init(&dev->dev_mutex);
+	spin_lock_init(&dev->irqlock);
+
+	snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s",
+		 "[MTK_V4L2_VENC]");
+
+	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
+	if (ret) {
+		mtk_v4l2_err("v4l2_device_register err=%d", ret);
+		goto err_res;
+	}
+
+	init_waitqueue_head(&dev->queue);
+
+	/* allocate video device for encoder and register it */
+	vfd_enc = video_device_alloc();
+	if (!vfd_enc) {
+		mtk_v4l2_err("Failed to allocate video device");
+		ret = -ENOMEM;
+		goto err_enc_alloc;
+	}
+	vfd_enc->fops           = &mtk_vcodec_fops;
+	vfd_enc->ioctl_ops      = &mtk_venc_ioctl_ops;
+	vfd_enc->release        = video_device_release;
+	vfd_enc->lock           = &dev->dev_mutex;
+	vfd_enc->v4l2_dev       = &dev->v4l2_dev;
+	vfd_enc->vfl_dir        = VFL_DIR_M2M;
+	vfd_enc->device_caps	= V4L2_CAP_VIDEO_M2M_MPLANE |
+					V4L2_CAP_STREAMING;
+
+	snprintf(vfd_enc->name, sizeof(vfd_enc->name), "%s",
+		 MTK_VCODEC_ENC_NAME);
+	video_set_drvdata(vfd_enc, dev);
+	dev->vfd_enc = vfd_enc;
+	platform_set_drvdata(pdev, dev);
+
+	dev->m2m_dev_enc = v4l2_m2m_init(&mtk_venc_m2m_ops);
+	if (IS_ERR((__force void *)dev->m2m_dev_enc)) {
+		mtk_v4l2_err("Failed to init mem2mem enc device");
+		ret = PTR_ERR((__force void *)dev->m2m_dev_enc);
+		goto err_enc_mem_init;
+	}
+
+	dev->encode_workqueue =
+			alloc_ordered_workqueue(MTK_VCODEC_ENC_NAME,
+						WQ_MEM_RECLAIM |
+						WQ_FREEZABLE);
+	if (!dev->encode_workqueue) {
+		mtk_v4l2_err("Failed to create encode workqueue");
+		ret = -EINVAL;
+		goto err_event_workq;
+	}
+
+	ret = video_register_device(vfd_enc, VFL_TYPE_GRABBER, 1);
+	if (ret) {
+		mtk_v4l2_err("Failed to register video device");
+		goto err_enc_reg;
+	}
+
+	/* Avoid the iommu eat big hunks */
+	dma_set_attr(DMA_ATTR_ALLOC_SINGLE_PAGES, &attrs);
+
+	mtk_v4l2_debug(0, "encoder registered as /dev/video%d",
+			vfd_enc->num);
+
+	return 0;
+
+err_enc_reg:
+	destroy_workqueue(dev->encode_workqueue);
+err_event_workq:
+	v4l2_m2m_release(dev->m2m_dev_enc);
+err_enc_mem_init:
+	video_unregister_device(vfd_enc);
+err_enc_alloc:
+	v4l2_device_unregister(&dev->v4l2_dev);
+err_res:
+	mtk_vcodec_release_enc_pm(dev);
+	return ret;
+}
+
+static const struct of_device_id mtk_vcodec_enc_match[] = {
+	{.compatible = "mediatek,mt8173-vcodec-enc",},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtk_vcodec_enc_match);
+
+static int mtk_vcodec_enc_remove(struct platform_device *pdev)
+{
+	struct mtk_vcodec_dev *dev = platform_get_drvdata(pdev);
+
+	mtk_v4l2_debug_enter();
+	flush_workqueue(dev->encode_workqueue);
+	destroy_workqueue(dev->encode_workqueue);
+	if (dev->m2m_dev_enc)
+		v4l2_m2m_release(dev->m2m_dev_enc);
+
+	if (dev->vfd_enc)
+		video_unregister_device(dev->vfd_enc);
+
+	v4l2_device_unregister(&dev->v4l2_dev);
+	mtk_vcodec_release_enc_pm(dev);
+	return 0;
+}
+
+static struct platform_driver mtk_vcodec_enc_driver = {
+	.probe	= mtk_vcodec_probe,
+	.remove	= mtk_vcodec_enc_remove,
+	.driver	= {
+		.name	= MTK_VCODEC_ENC_NAME,
+		.of_match_table = mtk_vcodec_enc_match,
+	},
+};
+
+module_platform_driver(mtk_vcodec_enc_driver);
+
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Mediatek video codec V4L2 encoder driver");
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_pm.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_pm.c
new file mode 100644
index 000000000000..3e73e9db781f
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_pm.c
@@ -0,0 +1,137 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#include <linux/clk.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/pm_runtime.h>
+#include <soc/mediatek/smi.h>
+
+#include "mtk_vcodec_enc_pm.h"
+#include "mtk_vcodec_util.h"
+#include "mtk_vpu.h"
+
+
+int mtk_vcodec_init_enc_pm(struct mtk_vcodec_dev *mtkdev)
+{
+	struct device_node *node;
+	struct platform_device *pdev;
+	struct device *dev;
+	struct mtk_vcodec_pm *pm;
+	int ret = 0;
+
+	pdev = mtkdev->plat_dev;
+	pm = &mtkdev->pm;
+	memset(pm, 0, sizeof(struct mtk_vcodec_pm));
+	pm->mtkdev = mtkdev;
+	pm->dev = &pdev->dev;
+	dev = &pdev->dev;
+
+	node = of_parse_phandle(dev->of_node, "mediatek,larb", 0);
+	if (!node) {
+		mtk_v4l2_err("no mediatek,larb found");
+		return -1;
+	}
+	pdev = of_find_device_by_node(node);
+	if (!pdev) {
+		mtk_v4l2_err("no mediatek,larb device found");
+		return -1;
+	}
+	pm->larbvenc = &pdev->dev;
+
+	node = of_parse_phandle(dev->of_node, "mediatek,larb", 1);
+	if (!node) {
+		mtk_v4l2_err("no mediatek,larb found");
+		return -1;
+	}
+
+	pdev = of_find_device_by_node(node);
+	if (!pdev) {
+		mtk_v4l2_err("no mediatek,larb device found");
+		return -1;
+	}
+
+	pm->larbvenclt = &pdev->dev;
+	pdev = mtkdev->plat_dev;
+	pm->dev = &pdev->dev;
+
+	pm->vencpll_d2 = devm_clk_get(&pdev->dev, "venc_sel_src");
+	if (IS_ERR(pm->vencpll_d2)) {
+		mtk_v4l2_err("devm_clk_get vencpll_d2 fail");
+		ret = PTR_ERR(pm->vencpll_d2);
+	}
+
+	pm->venc_sel = devm_clk_get(&pdev->dev, "venc_sel");
+	if (IS_ERR(pm->venc_sel)) {
+		mtk_v4l2_err("devm_clk_get venc_sel fail");
+		ret = PTR_ERR(pm->venc_sel);
+	}
+
+	pm->univpll1_d2 = devm_clk_get(&pdev->dev, "venc_lt_sel_src");
+	if (IS_ERR(pm->univpll1_d2)) {
+		mtk_v4l2_err("devm_clk_get univpll1_d2 fail");
+		ret = PTR_ERR(pm->univpll1_d2);
+	}
+
+	pm->venc_lt_sel = devm_clk_get(&pdev->dev, "venc_lt_sel");
+	if (IS_ERR(pm->venc_lt_sel)) {
+		mtk_v4l2_err("devm_clk_get venc_lt_sel fail");
+		ret = PTR_ERR(pm->venc_lt_sel);
+	}
+
+	return ret;
+}
+
+void mtk_vcodec_release_enc_pm(struct mtk_vcodec_dev *mtkdev)
+{
+}
+
+
+void mtk_vcodec_enc_clock_on(struct mtk_vcodec_pm *pm)
+{
+	int ret;
+
+	ret = clk_prepare_enable(pm->venc_sel);
+	if (ret)
+		mtk_v4l2_err("clk_prepare_enable fail %d", ret);
+
+	ret = clk_set_parent(pm->venc_sel, pm->vencpll_d2);
+	if (ret)
+		mtk_v4l2_err("clk_set_parent fail %d", ret);
+
+	ret = clk_prepare_enable(pm->venc_lt_sel);
+	if (ret)
+		mtk_v4l2_err("clk_prepare_enable fail %d", ret);
+
+	ret = clk_set_parent(pm->venc_lt_sel, pm->univpll1_d2);
+	if (ret)
+		mtk_v4l2_err("clk_set_parent fail %d", ret);
+
+	ret = mtk_smi_larb_get(pm->larbvenc);
+	if (ret)
+		mtk_v4l2_err("mtk_smi_larb_get larb3 fail %d", ret);
+
+	ret = mtk_smi_larb_get(pm->larbvenclt);
+	if (ret)
+		mtk_v4l2_err("mtk_smi_larb_get larb4 fail %d", ret);
+
+}
+
+void mtk_vcodec_enc_clock_off(struct mtk_vcodec_pm *pm)
+{
+	mtk_smi_larb_put(pm->larbvenc);
+	mtk_smi_larb_put(pm->larbvenclt);
+	clk_disable_unprepare(pm->venc_lt_sel);
+	clk_disable_unprepare(pm->venc_sel);
+}
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_pm.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_pm.h
new file mode 100644
index 000000000000..f32167138976
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_pm.h
@@ -0,0 +1,26 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#ifndef _MTK_VCODEC_ENC_PM_H_
+#define _MTK_VCODEC_ENC_PM_H_
+
+#include "mtk_vcodec_drv.h"
+
+int mtk_vcodec_init_enc_pm(struct mtk_vcodec_dev *dev);
+void mtk_vcodec_release_enc_pm(struct mtk_vcodec_dev *dev);
+
+void mtk_vcodec_enc_clock_on(struct mtk_vcodec_pm *pm);
+void mtk_vcodec_enc_clock_off(struct mtk_vcodec_pm *pm);
+
+#endif /* _MTK_VCODEC_ENC_PM_H_ */
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_intr.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_intr.c
new file mode 100644
index 000000000000..52e7e5c9afa0
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_intr.c
@@ -0,0 +1,54 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#include <linux/errno.h>
+#include <linux/wait.h>
+
+#include "mtk_vcodec_drv.h"
+#include "mtk_vcodec_intr.h"
+#include "mtk_vcodec_util.h"
+
+int mtk_vcodec_wait_for_done_ctx(struct mtk_vcodec_ctx  *ctx, int command,
+				 unsigned int timeout_ms)
+{
+	wait_queue_head_t *waitqueue;
+	long timeout_jiff, ret;
+	int status = 0;
+
+	waitqueue = (wait_queue_head_t *)&ctx->queue;
+	timeout_jiff = msecs_to_jiffies(timeout_ms);
+
+	ret = wait_event_interruptible_timeout(*waitqueue,
+				(ctx->int_cond &&
+				(ctx->int_type == command)),
+				timeout_jiff);
+
+	if (!ret) {
+		status = -1;	/* timeout */
+		mtk_v4l2_err("[%d] cmd=%d, ctx->type=%d, wait_event_interruptible_timeout time=%ums out %d %d!",
+				ctx->id, ctx->type, command, timeout_ms,
+				ctx->int_cond, ctx->int_type);
+	} else if (-ERESTARTSYS == ret) {
+		mtk_v4l2_err("[%d] cmd=%d, ctx->type=%d, wait_event_interruptible_timeout interrupted by a signal %d %d",
+				ctx->id, ctx->type, command, ctx->int_cond,
+				ctx->int_type);
+		status = -1;
+	}
+
+	ctx->int_cond = 0;
+	ctx->int_type = 0;
+
+	return status;
+}
+EXPORT_SYMBOL(mtk_vcodec_wait_for_done_ctx);
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_intr.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_intr.h
new file mode 100644
index 000000000000..33e890f5aa9c
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_intr.h
@@ -0,0 +1,27 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#ifndef _MTK_VCODEC_INTR_H_
+#define _MTK_VCODEC_INTR_H_
+
+#define MTK_INST_IRQ_RECEIVED		0x1
+#define MTK_INST_WORK_THREAD_ABORT_DONE	0x2
+
+struct mtk_vcodec_ctx;
+
+/* timeout is ms */
+int mtk_vcodec_wait_for_done_ctx(struct mtk_vcodec_ctx *data, int command,
+				unsigned int timeout_ms);
+
+#endif /* _MTK_VCODEC_INTR_H_ */
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c
new file mode 100644
index 000000000000..5e3651372a3c
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c
@@ -0,0 +1,94 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: PC Chen <pc.chen@mediatek.com>
+*	Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#include <linux/module.h>
+
+#include "mtk_vcodec_drv.h"
+#include "mtk_vcodec_util.h"
+#include "mtk_vpu.h"
+
+/* For encoder, this will enable logs in venc/*/
+bool mtk_vcodec_dbg;
+EXPORT_SYMBOL(mtk_vcodec_dbg);
+
+/* The log level of v4l2 encoder or decoder driver.
+ * That is, files under mtk-vcodec/.
+ */
+int mtk_v4l2_dbg_level;
+EXPORT_SYMBOL(mtk_v4l2_dbg_level);
+
+void __iomem *mtk_vcodec_get_reg_addr(struct mtk_vcodec_ctx *data,
+					unsigned int reg_idx)
+{
+	struct mtk_vcodec_ctx *ctx = (struct mtk_vcodec_ctx *)data;
+
+	if (!data || reg_idx >= NUM_MAX_VCODEC_REG_BASE) {
+		mtk_v4l2_err("Invalid arguments, reg_idx=%d", reg_idx);
+		return NULL;
+	}
+	return ctx->dev->reg_base[reg_idx];
+}
+EXPORT_SYMBOL(mtk_vcodec_get_reg_addr);
+
+int mtk_vcodec_mem_alloc(struct mtk_vcodec_ctx *data,
+			struct mtk_vcodec_mem *mem)
+{
+	unsigned long size = mem->size;
+	struct mtk_vcodec_ctx *ctx = (struct mtk_vcodec_ctx *)data;
+	struct device *dev = &ctx->dev->plat_dev->dev;
+
+	mem->va = dma_alloc_coherent(dev, size, &mem->dma_addr, GFP_KERNEL);
+
+	if (!mem->va) {
+		mtk_v4l2_err("%s dma_alloc size=%ld failed!", dev_name(dev),
+			     size);
+		return -ENOMEM;
+	}
+
+	memset(mem->va, 0, size);
+
+	mtk_v4l2_debug(3, "[%d]  - va      = %p", ctx->id, mem->va);
+	mtk_v4l2_debug(3, "[%d]  - dma     = 0x%lx", ctx->id,
+		       (unsigned long)mem->dma_addr);
+	mtk_v4l2_debug(3, "[%d]    size = 0x%lx", ctx->id, size);
+
+	return 0;
+}
+EXPORT_SYMBOL(mtk_vcodec_mem_alloc);
+
+void mtk_vcodec_mem_free(struct mtk_vcodec_ctx *data,
+			struct mtk_vcodec_mem *mem)
+{
+	unsigned long size = mem->size;
+	struct mtk_vcodec_ctx *ctx = (struct mtk_vcodec_ctx *)data;
+	struct device *dev = &ctx->dev->plat_dev->dev;
+
+	if (!mem->va) {
+		mtk_v4l2_err("%s dma_free size=%ld failed!", dev_name(dev),
+			     size);
+		return;
+	}
+
+	dma_free_coherent(dev, size, mem->va, mem->dma_addr);
+	mem->va = NULL;
+	mem->dma_addr = 0;
+	mem->size = 0;
+
+	mtk_v4l2_debug(3, "[%d]  - va      = %p", ctx->id, mem->va);
+	mtk_v4l2_debug(3, "[%d]  - dma     = 0x%lx", ctx->id,
+		       (unsigned long)mem->dma_addr);
+	mtk_v4l2_debug(3, "[%d]    size = 0x%lx", ctx->id, size);
+}
+EXPORT_SYMBOL(mtk_vcodec_mem_free);
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.h
new file mode 100644
index 000000000000..d6345fc04840
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.h
@@ -0,0 +1,87 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: PC Chen <pc.chen@mediatek.com>
+*	Tiffany Lin <tiffany.lin@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#ifndef _MTK_VCODEC_UTIL_H_
+#define _MTK_VCODEC_UTIL_H_
+
+#include <linux/types.h>
+#include <linux/dma-direction.h>
+
+struct mtk_vcodec_mem {
+	size_t size;
+	void *va;
+	dma_addr_t dma_addr;
+};
+
+struct mtk_vcodec_ctx;
+
+extern int mtk_v4l2_dbg_level;
+extern bool mtk_vcodec_dbg;
+
+#define DEBUG	1
+
+#if defined(DEBUG)
+
+#define mtk_v4l2_debug(level, fmt, args...)				 \
+	do {								 \
+		if (mtk_v4l2_dbg_level >= level)			 \
+			pr_info("[MTK_V4L2] level=%d %s(),%d: " fmt "\n",\
+				level, __func__, __LINE__, ##args);	 \
+	} while (0)
+
+#define mtk_v4l2_err(fmt, args...)                \
+	pr_err("[MTK_V4L2][ERROR] %s:%d: " fmt "\n", __func__, __LINE__, \
+	       ##args)
+
+
+#define mtk_v4l2_debug_enter()  mtk_v4l2_debug(3, "+")
+#define mtk_v4l2_debug_leave()  mtk_v4l2_debug(3, "-")
+
+#define mtk_vcodec_debug(h, fmt, args...)				\
+	do {								\
+		if (mtk_vcodec_dbg)					\
+			pr_info("[MTK_VCODEC][%d]: %s() " fmt "\n",	\
+				((struct mtk_vcodec_ctx *)h->ctx)->id, \
+				__func__, ##args);			\
+	} while (0)
+
+#define mtk_vcodec_err(h, fmt, args...)					\
+	pr_err("[MTK_VCODEC][ERROR][%d]: %s() " fmt "\n",		\
+	       ((struct mtk_vcodec_ctx *)h->ctx)->id, __func__, ##args)
+
+#define mtk_vcodec_debug_enter(h)  mtk_vcodec_debug(h, "+")
+#define mtk_vcodec_debug_leave(h)  mtk_vcodec_debug(h, "-")
+
+#else
+
+#define mtk_v4l2_debug(level, fmt, args...)
+#define mtk_v4l2_err(fmt, args...)
+#define mtk_v4l2_debug_enter()
+#define mtk_v4l2_debug_leave()
+
+#define mtk_vcodec_debug(h, fmt, args...)
+#define mtk_vcodec_err(h, fmt, args...)
+#define mtk_vcodec_debug_enter(h)
+#define mtk_vcodec_debug_leave(h)
+
+#endif
+
+void __iomem *mtk_vcodec_get_reg_addr(struct mtk_vcodec_ctx *data,
+				unsigned int reg_idx);
+int mtk_vcodec_mem_alloc(struct mtk_vcodec_ctx *data,
+				struct mtk_vcodec_mem *mem);
+void mtk_vcodec_mem_free(struct mtk_vcodec_ctx *data,
+				struct mtk_vcodec_mem *mem);
+#endif /* _MTK_VCODEC_UTIL_H_ */
diff --git a/drivers/media/platform/mtk-vcodec/venc/venc_h264_if.c b/drivers/media/platform/mtk-vcodec/venc/venc_h264_if.c
new file mode 100644
index 000000000000..9a600525b3c1
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc/venc_h264_if.c
@@ -0,0 +1,679 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Jungchang Tsao <jungchang.tsao@mediatek.com>
+ *         Daniel Hsiao <daniel.hsiao@mediatek.com>
+ *         PoChun Lin <pochun.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "../mtk_vcodec_drv.h"
+#include "../mtk_vcodec_util.h"
+#include "../mtk_vcodec_intr.h"
+#include "../mtk_vcodec_enc.h"
+#include "../mtk_vcodec_enc_pm.h"
+#include "../venc_drv_base.h"
+#include "../venc_ipi_msg.h"
+#include "../venc_vpu_if.h"
+#include "mtk_vpu.h"
+
+static const char h264_filler_marker[] = {0x0, 0x0, 0x0, 0x1, 0xc};
+
+#define H264_FILLER_MARKER_SIZE ARRAY_SIZE(h264_filler_marker)
+#define VENC_PIC_BITSTREAM_BYTE_CNT 0x0098
+
+/**
+ * enum venc_h264_vpu_work_buf - h264 encoder buffer index
+ */
+enum venc_h264_vpu_work_buf {
+	VENC_H264_VPU_WORK_BUF_RC_INFO,
+	VENC_H264_VPU_WORK_BUF_RC_CODE,
+	VENC_H264_VPU_WORK_BUF_REC_LUMA,
+	VENC_H264_VPU_WORK_BUF_REC_CHROMA,
+	VENC_H264_VPU_WORK_BUF_REF_LUMA,
+	VENC_H264_VPU_WORK_BUF_REF_CHROMA,
+	VENC_H264_VPU_WORK_BUF_MV_INFO_1,
+	VENC_H264_VPU_WORK_BUF_MV_INFO_2,
+	VENC_H264_VPU_WORK_BUF_SKIP_FRAME,
+	VENC_H264_VPU_WORK_BUF_MAX,
+};
+
+/**
+ * enum venc_h264_bs_mode - for bs_mode argument in h264_enc_vpu_encode
+ */
+enum venc_h264_bs_mode {
+	H264_BS_MODE_SPS,
+	H264_BS_MODE_PPS,
+	H264_BS_MODE_FRAME,
+};
+
+/*
+ * struct venc_h264_vpu_config - Structure for h264 encoder configuration
+ * @input_fourcc: input fourcc
+ * @bitrate: target bitrate (in bps)
+ * @pic_w: picture width. Picture size is visible stream resolution, in pixels,
+ *         to be used for display purposes; must be smaller or equal to buffer
+ *         size.
+ * @pic_h: picture height
+ * @buf_w: buffer width. Buffer size is stream resolution in pixels aligned to
+ *         hardware requirements.
+ * @buf_h: buffer height
+ * @gop_size: group of picture size (idr frame)
+ * @intra_period: intra frame period
+ * @framerate: frame rate in fps
+ * @profile: as specified in standard
+ * @level: as specified in standard
+ * @wfd: WFD mode 1:on, 0:off
+ */
+struct venc_h264_vpu_config {
+	u32 input_fourcc;
+	u32 bitrate;
+	u32 pic_w;
+	u32 pic_h;
+	u32 buf_w;
+	u32 buf_h;
+	u32 gop_size;
+	u32 intra_period;
+	u32 framerate;
+	u32 profile;
+	u32 level;
+	u32 wfd;
+};
+
+/*
+ * struct venc_h264_vpu_buf - Structure for buffer information
+ * @align: buffer alignment (in bytes)
+ * @iova: IO virtual address
+ * @vpua: VPU side memory addr which is used by RC_CODE
+ * @size: buffer size (in bytes)
+ */
+struct venc_h264_vpu_buf {
+	u32 align;
+	u32 iova;
+	u32 vpua;
+	u32 size;
+};
+
+/*
+ * struct venc_h264_vsi - Structure for VPU driver control and info share
+ * This structure is allocated in VPU side and shared to AP side.
+ * @config: h264 encoder configuration
+ * @work_bufs: working buffer information in VPU side
+ * The work_bufs here is for storing the 'size' info shared to AP side.
+ * The similar item in struct venc_h264_inst is for memory allocation
+ * in AP side. The AP driver will copy the 'size' from here to the one in
+ * struct mtk_vcodec_mem, then invoke mtk_vcodec_mem_alloc to allocate
+ * the buffer. After that, bypass the 'dma_addr' to the 'iova' field here for
+ * register setting in VPU side.
+ */
+struct venc_h264_vsi {
+	struct venc_h264_vpu_config config;
+	struct venc_h264_vpu_buf work_bufs[VENC_H264_VPU_WORK_BUF_MAX];
+};
+
+/*
+ * struct venc_h264_inst - h264 encoder AP driver instance
+ * @hw_base: h264 encoder hardware register base
+ * @work_bufs: working buffer
+ * @pps_buf: buffer to store the pps bitstream
+ * @work_buf_allocated: working buffer allocated flag
+ * @frm_cnt: encoded frame count
+ * @prepend_hdr: when the v4l2 layer send VENC_SET_PARAM_PREPEND_HEADER cmd
+ *  through h264_enc_set_param interface, it will set this flag and prepend the
+ *  sps/pps in h264_enc_encode function.
+ * @vpu_inst: VPU instance to exchange information between AP and VPU
+ * @vsi: driver structure allocated by VPU side and shared to AP side for
+ *	 control and info share
+ * @ctx: context for v4l2 layer integration
+ */
+struct venc_h264_inst {
+	void __iomem *hw_base;
+	struct mtk_vcodec_mem work_bufs[VENC_H264_VPU_WORK_BUF_MAX];
+	struct mtk_vcodec_mem pps_buf;
+	bool work_buf_allocated;
+	unsigned int frm_cnt;
+	unsigned int prepend_hdr;
+	struct venc_vpu_inst vpu_inst;
+	struct venc_h264_vsi *vsi;
+	struct mtk_vcodec_ctx *ctx;
+};
+
+static inline void h264_write_reg(struct venc_h264_inst *inst, u32 addr,
+				  u32 val)
+{
+	writel(val, inst->hw_base + addr);
+}
+
+static inline u32 h264_read_reg(struct venc_h264_inst *inst, u32 addr)
+{
+	return readl(inst->hw_base + addr);
+}
+
+static unsigned int h264_get_profile(struct venc_h264_inst *inst,
+				     unsigned int profile)
+{
+	switch (profile) {
+	case V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE:
+		return 66;
+	case V4L2_MPEG_VIDEO_H264_PROFILE_MAIN:
+		return 77;
+	case V4L2_MPEG_VIDEO_H264_PROFILE_HIGH:
+		return 100;
+	case V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_BASELINE:
+		mtk_vcodec_err(inst, "unsupported CONSTRAINED_BASELINE");
+		return 0;
+	case V4L2_MPEG_VIDEO_H264_PROFILE_EXTENDED:
+		mtk_vcodec_err(inst, "unsupported EXTENDED");
+		return 0;
+	default:
+		mtk_vcodec_debug(inst, "unsupported profile %d", profile);
+		return 100;
+	}
+}
+
+static unsigned int h264_get_level(struct venc_h264_inst *inst,
+				   unsigned int level)
+{
+	switch (level) {
+	case V4L2_MPEG_VIDEO_H264_LEVEL_1B:
+		mtk_vcodec_err(inst, "unsupported 1B");
+		return 0;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_1_0:
+		return 10;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_1_1:
+		return 11;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_1_2:
+		return 12;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_1_3:
+		return 13;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_2_0:
+		return 20;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_2_1:
+		return 21;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_2_2:
+		return 22;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_3_0:
+		return 30;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_3_1:
+		return 31;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_3_2:
+		return 32;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_4_0:
+		return 40;
+	case V4L2_MPEG_VIDEO_H264_LEVEL_4_1:
+		return 41;
+	default:
+		mtk_vcodec_debug(inst, "unsupported level %d", level);
+		return 31;
+	}
+}
+
+static void h264_enc_free_work_buf(struct venc_h264_inst *inst)
+{
+	int i;
+
+	mtk_vcodec_debug_enter(inst);
+
+	/* Except the SKIP_FRAME buffers,
+	 * other buffers need to be freed by AP.
+	 */
+	for (i = 0; i < VENC_H264_VPU_WORK_BUF_MAX; i++) {
+		if (i != VENC_H264_VPU_WORK_BUF_SKIP_FRAME)
+			mtk_vcodec_mem_free(inst->ctx, &inst->work_bufs[i]);
+	}
+
+	mtk_vcodec_mem_free(inst->ctx, &inst->pps_buf);
+
+	mtk_vcodec_debug_leave(inst);
+}
+
+static int h264_enc_alloc_work_buf(struct venc_h264_inst *inst)
+{
+	int i;
+	int ret = 0;
+	struct venc_h264_vpu_buf *wb = inst->vsi->work_bufs;
+
+	mtk_vcodec_debug_enter(inst);
+
+	for (i = 0; i < VENC_H264_VPU_WORK_BUF_MAX; i++) {
+		/*
+		 * This 'wb' structure is set by VPU side and shared to AP for
+		 * buffer allocation and IO virtual addr mapping. For most of
+		 * the buffers, AP will allocate the buffer according to 'size'
+		 * field and store the IO virtual addr in 'iova' field. There
+		 * are two exceptions:
+		 * (1) RC_CODE buffer, it's pre-allocated in the VPU side, and
+		 * save the VPU addr in the 'vpua' field. The AP will translate
+		 * the VPU addr to the corresponding IO virtual addr and store
+		 * in 'iova' field for reg setting in VPU side.
+		 * (2) SKIP_FRAME buffer, it's pre-allocated in the VPU side,
+		 * and save the VPU addr in the 'vpua' field. The AP will
+		 * translate the VPU addr to the corresponding AP side virtual
+		 * address and do some memcpy access to move to bitstream buffer
+		 * assigned by v4l2 layer.
+		 */
+		inst->work_bufs[i].size = wb[i].size;
+		if (i == VENC_H264_VPU_WORK_BUF_SKIP_FRAME) {
+			inst->work_bufs[i].va = vpu_mapping_dm_addr(
+				inst->vpu_inst.dev, wb[i].vpua);
+			inst->work_bufs[i].dma_addr = 0;
+		} else {
+			ret = mtk_vcodec_mem_alloc(inst->ctx,
+						   &inst->work_bufs[i]);
+			if (ret) {
+				mtk_vcodec_err(inst,
+					       "cannot allocate buf %d", i);
+				goto err_alloc;
+			}
+			/*
+			 * This RC_CODE is pre-allocated by VPU and saved in VPU
+			 * addr. So we need use memcpy to copy RC_CODE from VPU
+			 * addr into IO virtual addr in 'iova' field for reg
+			 * setting in VPU side.
+			 */
+			if (i == VENC_H264_VPU_WORK_BUF_RC_CODE) {
+				void *tmp_va;
+
+				tmp_va = vpu_mapping_dm_addr(inst->vpu_inst.dev,
+							     wb[i].vpua);
+				memcpy(inst->work_bufs[i].va, tmp_va,
+				       wb[i].size);
+			}
+		}
+		wb[i].iova = inst->work_bufs[i].dma_addr;
+
+		mtk_vcodec_debug(inst,
+				 "work_buf[%d] va=0x%p iova=%pad size=%zu",
+				 i, inst->work_bufs[i].va,
+				 &inst->work_bufs[i].dma_addr,
+				 inst->work_bufs[i].size);
+	}
+
+	/* the pps_buf is used by AP side only */
+	inst->pps_buf.size = 128;
+	ret = mtk_vcodec_mem_alloc(inst->ctx, &inst->pps_buf);
+	if (ret) {
+		mtk_vcodec_err(inst, "cannot allocate pps_buf");
+		goto err_alloc;
+	}
+
+	mtk_vcodec_debug_leave(inst);
+
+	return ret;
+
+err_alloc:
+	h264_enc_free_work_buf(inst);
+
+	return ret;
+}
+
+static unsigned int h264_enc_wait_venc_done(struct venc_h264_inst *inst)
+{
+	unsigned int irq_status = 0;
+	struct mtk_vcodec_ctx *ctx = (struct mtk_vcodec_ctx *)inst->ctx;
+
+	if (!mtk_vcodec_wait_for_done_ctx(ctx, MTK_INST_IRQ_RECEIVED,
+					  WAIT_INTR_TIMEOUT_MS)) {
+		irq_status = ctx->irq_status;
+		mtk_vcodec_debug(inst, "irq_status %x <-", irq_status);
+	}
+	return irq_status;
+}
+
+static int h264_encode_sps(struct venc_h264_inst *inst,
+			   struct mtk_vcodec_mem *bs_buf,
+			   unsigned int *bs_size)
+{
+	int ret = 0;
+	unsigned int irq_status;
+
+	mtk_vcodec_debug_enter(inst);
+
+	ret = vpu_enc_encode(&inst->vpu_inst, H264_BS_MODE_SPS, NULL,
+			     bs_buf, bs_size);
+	if (ret)
+		return ret;
+
+	irq_status = h264_enc_wait_venc_done(inst);
+	if (irq_status != MTK_VENC_IRQ_STATUS_SPS) {
+		mtk_vcodec_err(inst, "expect irq status %d",
+			       MTK_VENC_IRQ_STATUS_SPS);
+		return -EINVAL;
+	}
+
+	*bs_size = h264_read_reg(inst, VENC_PIC_BITSTREAM_BYTE_CNT);
+	mtk_vcodec_debug(inst, "bs size %d <-", *bs_size);
+
+	return ret;
+}
+
+static int h264_encode_pps(struct venc_h264_inst *inst,
+			   struct mtk_vcodec_mem *bs_buf,
+			   unsigned int *bs_size)
+{
+	int ret = 0;
+	unsigned int irq_status;
+
+	mtk_vcodec_debug_enter(inst);
+
+	ret = vpu_enc_encode(&inst->vpu_inst, H264_BS_MODE_PPS, NULL,
+			     bs_buf, bs_size);
+	if (ret)
+		return ret;
+
+	irq_status = h264_enc_wait_venc_done(inst);
+	if (irq_status != MTK_VENC_IRQ_STATUS_PPS) {
+		mtk_vcodec_err(inst, "expect irq status %d",
+			       MTK_VENC_IRQ_STATUS_PPS);
+		return -EINVAL;
+	}
+
+	*bs_size = h264_read_reg(inst, VENC_PIC_BITSTREAM_BYTE_CNT);
+	mtk_vcodec_debug(inst, "bs size %d <-", *bs_size);
+
+	return ret;
+}
+
+static int h264_encode_header(struct venc_h264_inst *inst,
+			      struct mtk_vcodec_mem *bs_buf,
+			      unsigned int *bs_size)
+{
+	int ret = 0;
+	unsigned int bs_size_sps;
+	unsigned int bs_size_pps;
+
+	ret = h264_encode_sps(inst, bs_buf, &bs_size_sps);
+	if (ret)
+		return ret;
+
+	ret = h264_encode_pps(inst, &inst->pps_buf, &bs_size_pps);
+	if (ret)
+		return ret;
+
+	memcpy(bs_buf->va + bs_size_sps, inst->pps_buf.va, bs_size_pps);
+	*bs_size = bs_size_sps + bs_size_pps;
+
+	return ret;
+}
+
+static int h264_encode_frame(struct venc_h264_inst *inst,
+			     struct venc_frm_buf *frm_buf,
+			     struct mtk_vcodec_mem *bs_buf,
+			     unsigned int *bs_size)
+{
+	int ret = 0;
+	unsigned int irq_status;
+
+	mtk_vcodec_debug_enter(inst);
+
+	ret = vpu_enc_encode(&inst->vpu_inst, H264_BS_MODE_FRAME, frm_buf,
+			     bs_buf, bs_size);
+	if (ret)
+		return ret;
+
+	/*
+	 * skip frame case: The skip frame buffer is composed by vpu side only,
+	 * it does not trigger the hw, so skip the wait interrupt operation.
+	 */
+	if (inst->vpu_inst.state == VEN_IPI_MSG_ENC_STATE_SKIP) {
+		*bs_size = inst->vpu_inst.bs_size;
+		memcpy(bs_buf->va,
+		       inst->work_bufs[VENC_H264_VPU_WORK_BUF_SKIP_FRAME].va,
+		       *bs_size);
+		++inst->frm_cnt;
+		return ret;
+	}
+
+	irq_status = h264_enc_wait_venc_done(inst);
+	if (irq_status != MTK_VENC_IRQ_STATUS_FRM) {
+		mtk_vcodec_err(inst, "irq_status=%d failed", irq_status);
+		return -EIO;
+	}
+
+	*bs_size = h264_read_reg(inst, VENC_PIC_BITSTREAM_BYTE_CNT);
+
+	++inst->frm_cnt;
+	mtk_vcodec_debug(inst, "frm %d bs_size %d key_frm %d <-",
+			 inst->frm_cnt, *bs_size, inst->vpu_inst.is_key_frm);
+
+	return ret;
+}
+
+static void h264_encode_filler(struct venc_h264_inst *inst, void *buf,
+			       int size)
+{
+	unsigned char *p = buf;
+
+	if (size < H264_FILLER_MARKER_SIZE) {
+		mtk_vcodec_err(inst, "filler size too small %d", size);
+		return;
+	}
+
+	memcpy(p, h264_filler_marker, ARRAY_SIZE(h264_filler_marker));
+	size -= H264_FILLER_MARKER_SIZE;
+	p += H264_FILLER_MARKER_SIZE;
+	memset(p, 0xff, size);
+}
+
+static int h264_enc_init(struct mtk_vcodec_ctx *ctx, unsigned long *handle)
+{
+	int ret = 0;
+	struct venc_h264_inst *inst;
+
+	inst = kzalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	inst->ctx = ctx;
+	inst->vpu_inst.ctx = ctx;
+	inst->vpu_inst.dev = ctx->dev->vpu_plat_dev;
+	inst->vpu_inst.id = IPI_VENC_H264;
+	inst->hw_base = mtk_vcodec_get_reg_addr(inst->ctx, VENC_SYS);
+
+	mtk_vcodec_debug_enter(inst);
+
+	ret = vpu_enc_init(&inst->vpu_inst);
+
+	inst->vsi = (struct venc_h264_vsi *)inst->vpu_inst.vsi;
+
+	mtk_vcodec_debug_leave(inst);
+
+	if (ret)
+		kfree(inst);
+	else
+		(*handle) = (unsigned long)inst;
+
+	return ret;
+}
+
+static int h264_enc_encode(unsigned long handle,
+			   enum venc_start_opt opt,
+			   struct venc_frm_buf *frm_buf,
+			   struct mtk_vcodec_mem *bs_buf,
+			   struct venc_done_result *result)
+{
+	int ret = 0;
+	struct venc_h264_inst *inst = (struct venc_h264_inst *)handle;
+	struct mtk_vcodec_ctx *ctx = inst->ctx;
+
+	mtk_vcodec_debug(inst, "opt %d ->", opt);
+
+	enable_irq(ctx->dev->enc_irq);
+
+	switch (opt) {
+	case VENC_START_OPT_ENCODE_SEQUENCE_HEADER: {
+		unsigned int bs_size_hdr;
+
+		ret = h264_encode_header(inst, bs_buf, &bs_size_hdr);
+		if (ret)
+			goto encode_err;
+
+		result->bs_size = bs_size_hdr;
+		result->is_key_frm = false;
+		break;
+	}
+
+	case VENC_START_OPT_ENCODE_FRAME: {
+		int hdr_sz;
+		int hdr_sz_ext;
+		int filler_sz = 0;
+		const int bs_alignment = 128;
+		struct mtk_vcodec_mem tmp_bs_buf;
+		unsigned int bs_size_hdr;
+		unsigned int bs_size_frm;
+
+		if (!inst->prepend_hdr) {
+			ret = h264_encode_frame(inst, frm_buf, bs_buf,
+						&result->bs_size);
+			if (ret)
+				goto encode_err;
+			result->is_key_frm = inst->vpu_inst.is_key_frm;
+			break;
+		}
+
+		mtk_vcodec_debug(inst, "h264_encode_frame prepend SPS/PPS");
+
+		ret = h264_encode_header(inst, bs_buf, &bs_size_hdr);
+		if (ret)
+			goto encode_err;
+
+		hdr_sz = bs_size_hdr;
+		hdr_sz_ext = (hdr_sz & (bs_alignment - 1));
+		if (hdr_sz_ext) {
+			filler_sz = bs_alignment - hdr_sz_ext;
+			if (hdr_sz_ext + H264_FILLER_MARKER_SIZE > bs_alignment)
+				filler_sz += bs_alignment;
+			h264_encode_filler(inst, bs_buf->va + hdr_sz,
+					   filler_sz);
+		}
+
+		tmp_bs_buf.va = bs_buf->va + hdr_sz + filler_sz;
+		tmp_bs_buf.dma_addr = bs_buf->dma_addr + hdr_sz + filler_sz;
+		tmp_bs_buf.size = bs_buf->size - (hdr_sz + filler_sz);
+
+		ret = h264_encode_frame(inst, frm_buf, &tmp_bs_buf,
+					&bs_size_frm);
+		if (ret)
+			goto encode_err;
+
+		result->bs_size = hdr_sz + filler_sz + bs_size_frm;
+
+		mtk_vcodec_debug(inst, "hdr %d filler %d frame %d bs %d",
+				 hdr_sz, filler_sz, bs_size_frm,
+				 result->bs_size);
+
+		inst->prepend_hdr = 0;
+		result->is_key_frm = inst->vpu_inst.is_key_frm;
+		break;
+	}
+
+	default:
+		mtk_vcodec_err(inst, "venc_start_opt %d not supported", opt);
+		ret = -EINVAL;
+		break;
+	}
+
+encode_err:
+
+	disable_irq(ctx->dev->enc_irq);
+	mtk_vcodec_debug(inst, "opt %d <-", opt);
+
+	return ret;
+}
+
+static int h264_enc_set_param(unsigned long handle,
+			      enum venc_set_param_type type,
+			      struct venc_enc_param *enc_prm)
+{
+	int ret = 0;
+	struct venc_h264_inst *inst = (struct venc_h264_inst *)handle;
+
+	mtk_vcodec_debug(inst, "->type=%d", type);
+
+	switch (type) {
+	case VENC_SET_PARAM_ENC:
+		inst->vsi->config.input_fourcc = enc_prm->input_yuv_fmt;
+		inst->vsi->config.bitrate = enc_prm->bitrate;
+		inst->vsi->config.pic_w = enc_prm->width;
+		inst->vsi->config.pic_h = enc_prm->height;
+		inst->vsi->config.buf_w = enc_prm->buf_width;
+		inst->vsi->config.buf_h = enc_prm->buf_height;
+		inst->vsi->config.gop_size = enc_prm->gop_size;
+		inst->vsi->config.framerate = enc_prm->frm_rate;
+		inst->vsi->config.intra_period = enc_prm->intra_period;
+		inst->vsi->config.profile =
+			h264_get_profile(inst, enc_prm->h264_profile);
+		inst->vsi->config.level =
+			h264_get_level(inst, enc_prm->h264_level);
+		inst->vsi->config.wfd = 0;
+		ret = vpu_enc_set_param(&inst->vpu_inst, type, enc_prm);
+		if (ret)
+			break;
+		if (inst->work_buf_allocated) {
+			h264_enc_free_work_buf(inst);
+			inst->work_buf_allocated = false;
+		}
+		ret = h264_enc_alloc_work_buf(inst);
+		if (ret)
+			break;
+		inst->work_buf_allocated = true;
+		break;
+
+	case VENC_SET_PARAM_PREPEND_HEADER:
+		inst->prepend_hdr = 1;
+		mtk_vcodec_debug(inst, "set prepend header mode");
+		break;
+
+	default:
+		ret = vpu_enc_set_param(&inst->vpu_inst, type, enc_prm);
+		break;
+	}
+
+	mtk_vcodec_debug_leave(inst);
+
+	return ret;
+}
+
+static int h264_enc_deinit(unsigned long handle)
+{
+	int ret = 0;
+	struct venc_h264_inst *inst = (struct venc_h264_inst *)handle;
+
+	mtk_vcodec_debug_enter(inst);
+
+	ret = vpu_enc_deinit(&inst->vpu_inst);
+
+	if (inst->work_buf_allocated)
+		h264_enc_free_work_buf(inst);
+
+	mtk_vcodec_debug_leave(inst);
+	kfree(inst);
+
+	return ret;
+}
+
+static struct venc_common_if venc_h264_if = {
+	h264_enc_init,
+	h264_enc_encode,
+	h264_enc_set_param,
+	h264_enc_deinit,
+};
+
+struct venc_common_if *get_h264_enc_comm_if(void);
+
+struct venc_common_if *get_h264_enc_comm_if(void)
+{
+	return &venc_h264_if;
+}
diff --git a/drivers/media/platform/mtk-vcodec/venc/venc_vp8_if.c b/drivers/media/platform/mtk-vcodec/venc/venc_vp8_if.c
new file mode 100644
index 000000000000..60bbcd2a0510
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc/venc_vp8_if.c
@@ -0,0 +1,486 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Daniel Hsiao <daniel.hsiao@mediatek.com>
+ *         PoChun Lin <pochun.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "../mtk_vcodec_drv.h"
+#include "../mtk_vcodec_util.h"
+#include "../mtk_vcodec_intr.h"
+#include "../mtk_vcodec_enc.h"
+#include "../mtk_vcodec_enc_pm.h"
+#include "../venc_drv_base.h"
+#include "../venc_ipi_msg.h"
+#include "../venc_vpu_if.h"
+#include "mtk_vpu.h"
+
+#define VENC_BITSTREAM_FRAME_SIZE 0x0098
+#define VENC_BITSTREAM_HEADER_LEN 0x00e8
+
+/* This ac_tag is vp8 frame tag. */
+#define MAX_AC_TAG_SIZE 10
+
+/**
+ * enum venc_vp8_vpu_work_buf - vp8 encoder buffer index
+ */
+enum venc_vp8_vpu_work_buf {
+	VENC_VP8_VPU_WORK_BUF_LUMA,
+	VENC_VP8_VPU_WORK_BUF_LUMA2,
+	VENC_VP8_VPU_WORK_BUF_LUMA3,
+	VENC_VP8_VPU_WORK_BUF_CHROMA,
+	VENC_VP8_VPU_WORK_BUF_CHROMA2,
+	VENC_VP8_VPU_WORK_BUF_CHROMA3,
+	VENC_VP8_VPU_WORK_BUF_MV_INFO,
+	VENC_VP8_VPU_WORK_BUF_BS_HEADER,
+	VENC_VP8_VPU_WORK_BUF_PROB_BUF,
+	VENC_VP8_VPU_WORK_BUF_RC_INFO,
+	VENC_VP8_VPU_WORK_BUF_RC_CODE,
+	VENC_VP8_VPU_WORK_BUF_RC_CODE2,
+	VENC_VP8_VPU_WORK_BUF_RC_CODE3,
+	VENC_VP8_VPU_WORK_BUF_MAX,
+};
+
+/*
+ * struct venc_vp8_vpu_config - Structure for vp8 encoder configuration
+ * @input_fourcc: input fourcc
+ * @bitrate: target bitrate (in bps)
+ * @pic_w: picture width. Picture size is visible stream resolution, in pixels,
+ *         to be used for display purposes; must be smaller or equal to buffer
+ *         size.
+ * @pic_h: picture height
+ * @buf_w: buffer width (with 16 alignment). Buffer size is stream resolution
+ *         in pixels aligned to hardware requirements.
+ * @buf_h: buffer height (with 16 alignment)
+ * @gop_size: group of picture size (key frame)
+ * @framerate: frame rate in fps
+ * @ts_mode: temporal scalability mode (0: disable, 1: enable)
+ *	     support three temporal layers - 0: 7.5fps 1: 7.5fps 2: 15fps.
+ */
+struct venc_vp8_vpu_config {
+	u32 input_fourcc;
+	u32 bitrate;
+	u32 pic_w;
+	u32 pic_h;
+	u32 buf_w;
+	u32 buf_h;
+	u32 gop_size;
+	u32 framerate;
+	u32 ts_mode;
+};
+
+/*
+ * struct venc_vp8_vpu_buf -Structure for buffer information
+ * @align: buffer alignment (in bytes)
+ * @iova: IO virtual address
+ * @vpua: VPU side memory addr which is used by RC_CODE
+ * @size: buffer size (in bytes)
+ */
+struct venc_vp8_vpu_buf {
+	u32 align;
+	u32 iova;
+	u32 vpua;
+	u32 size;
+};
+
+/*
+ * struct venc_vp8_vsi - Structure for VPU driver control and info share
+ * This structure is allocated in VPU side and shared to AP side.
+ * @config: vp8 encoder configuration
+ * @work_bufs: working buffer information in VPU side
+ * The work_bufs here is for storing the 'size' info shared to AP side.
+ * The similar item in struct venc_vp8_inst is for memory allocation
+ * in AP side. The AP driver will copy the 'size' from here to the one in
+ * struct mtk_vcodec_mem, then invoke mtk_vcodec_mem_alloc to allocate
+ * the buffer. After that, bypass the 'dma_addr' to the 'iova' field here for
+ * register setting in VPU side.
+ */
+struct venc_vp8_vsi {
+	struct venc_vp8_vpu_config config;
+	struct venc_vp8_vpu_buf work_bufs[VENC_VP8_VPU_WORK_BUF_MAX];
+};
+
+/*
+ * struct venc_vp8_inst - vp8 encoder AP driver instance
+ * @hw_base: vp8 encoder hardware register base
+ * @work_bufs: working buffer
+ * @work_buf_allocated: working buffer allocated flag
+ * @frm_cnt: encoded frame count, it's used for I-frame judgement and
+ *	     reset when force intra cmd received.
+ * @ts_mode: temporal scalability mode (0: disable, 1: enable)
+ *	     support three temporal layers - 0: 7.5fps 1: 7.5fps 2: 15fps.
+ * @vpu_inst: VPU instance to exchange information between AP and VPU
+ * @vsi: driver structure allocated by VPU side and shared to AP side for
+ *	 control and info share
+ * @ctx: context for v4l2 layer integration
+ */
+struct venc_vp8_inst {
+	void __iomem *hw_base;
+	struct mtk_vcodec_mem work_bufs[VENC_VP8_VPU_WORK_BUF_MAX];
+	bool work_buf_allocated;
+	unsigned int frm_cnt;
+	unsigned int ts_mode;
+	struct venc_vpu_inst vpu_inst;
+	struct venc_vp8_vsi *vsi;
+	struct mtk_vcodec_ctx *ctx;
+};
+
+static inline void vp8_enc_write_reg(struct venc_vp8_inst *inst, u32 addr,
+				     u32 val)
+{
+	writel(val, inst->hw_base + addr);
+}
+
+static inline u32 vp8_enc_read_reg(struct venc_vp8_inst *inst, u32 addr)
+{
+	return readl(inst->hw_base + addr);
+}
+
+static void vp8_enc_free_work_buf(struct venc_vp8_inst *inst)
+{
+	int i;
+
+	mtk_vcodec_debug_enter(inst);
+
+	/* Buffers need to be freed by AP. */
+	for (i = 0; i < VENC_VP8_VPU_WORK_BUF_MAX; i++) {
+		if ((inst->work_bufs[i].size == 0))
+			continue;
+		mtk_vcodec_mem_free(inst->ctx, &inst->work_bufs[i]);
+	}
+
+	mtk_vcodec_debug_leave(inst);
+}
+
+static int vp8_enc_alloc_work_buf(struct venc_vp8_inst *inst)
+{
+	int i;
+	int ret = 0;
+	struct venc_vp8_vpu_buf *wb = inst->vsi->work_bufs;
+
+	mtk_vcodec_debug_enter(inst);
+
+	for (i = 0; i < VENC_VP8_VPU_WORK_BUF_MAX; i++) {
+		if ((wb[i].size == 0))
+			continue;
+		/*
+		 * This 'wb' structure is set by VPU side and shared to AP for
+		 * buffer allocation and IO virtual addr mapping. For most of
+		 * the buffers, AP will allocate the buffer according to 'size'
+		 * field and store the IO virtual addr in 'iova' field. For the
+		 * RC_CODEx buffers, they are pre-allocated in the VPU side
+		 * because they are inside VPU SRAM, and save the VPU addr in
+		 * the 'vpua' field. The AP will translate the VPU addr to the
+		 * corresponding IO virtual addr and store in 'iova' field.
+		 */
+		inst->work_bufs[i].size = wb[i].size;
+		ret = mtk_vcodec_mem_alloc(inst->ctx, &inst->work_bufs[i]);
+		if (ret) {
+			mtk_vcodec_err(inst,
+				       "cannot alloc work_bufs[%d]", i);
+			goto err_alloc;
+		}
+		/*
+		 * This RC_CODEx is pre-allocated by VPU and saved in VPU addr.
+		 * So we need use memcpy to copy RC_CODEx from VPU addr into IO
+		 * virtual addr in 'iova' field for reg setting in VPU side.
+		 */
+		if (i == VENC_VP8_VPU_WORK_BUF_RC_CODE ||
+		    i == VENC_VP8_VPU_WORK_BUF_RC_CODE2 ||
+		    i == VENC_VP8_VPU_WORK_BUF_RC_CODE3) {
+			void *tmp_va;
+
+			tmp_va = vpu_mapping_dm_addr(inst->vpu_inst.dev,
+						     wb[i].vpua);
+			memcpy(inst->work_bufs[i].va, tmp_va, wb[i].size);
+		}
+		wb[i].iova = inst->work_bufs[i].dma_addr;
+
+		mtk_vcodec_debug(inst,
+				 "work_bufs[%d] va=0x%p,iova=%pad,size=%zu",
+				 i, inst->work_bufs[i].va,
+				 &inst->work_bufs[i].dma_addr,
+				 inst->work_bufs[i].size);
+	}
+
+	mtk_vcodec_debug_leave(inst);
+
+	return ret;
+
+err_alloc:
+	vp8_enc_free_work_buf(inst);
+
+	return ret;
+}
+
+static unsigned int vp8_enc_wait_venc_done(struct venc_vp8_inst *inst)
+{
+	unsigned int irq_status = 0;
+	struct mtk_vcodec_ctx *ctx = (struct mtk_vcodec_ctx *)inst->ctx;
+
+	if (!mtk_vcodec_wait_for_done_ctx(ctx, MTK_INST_IRQ_RECEIVED,
+					  WAIT_INTR_TIMEOUT_MS)) {
+		irq_status = ctx->irq_status;
+		mtk_vcodec_debug(inst, "isr return %x", irq_status);
+	}
+	return irq_status;
+}
+
+/*
+ * Compose ac_tag, bitstream header and bitstream payload into
+ * one bitstream buffer.
+ */
+static int vp8_enc_compose_one_frame(struct venc_vp8_inst *inst,
+				     struct mtk_vcodec_mem *bs_buf,
+				     unsigned int *bs_size)
+{
+	unsigned int not_key;
+	u32 bs_frm_size;
+	u32 bs_hdr_len;
+	unsigned int ac_tag_size;
+	u8 ac_tag[MAX_AC_TAG_SIZE];
+	u32 tag;
+
+	bs_frm_size = vp8_enc_read_reg(inst, VENC_BITSTREAM_FRAME_SIZE);
+	bs_hdr_len = vp8_enc_read_reg(inst, VENC_BITSTREAM_HEADER_LEN);
+
+	/* if a frame is key frame, not_key is 0 */
+	not_key = !inst->vpu_inst.is_key_frm;
+	tag = (bs_hdr_len << 5) | 0x10 | not_key;
+	ac_tag[0] = tag & 0xff;
+	ac_tag[1] = (tag >> 8) & 0xff;
+	ac_tag[2] = (tag >> 16) & 0xff;
+
+	/* key frame */
+	if (not_key == 0) {
+		ac_tag_size = MAX_AC_TAG_SIZE;
+		ac_tag[3] = 0x9d;
+		ac_tag[4] = 0x01;
+		ac_tag[5] = 0x2a;
+		ac_tag[6] = inst->vsi->config.pic_w;
+		ac_tag[7] = inst->vsi->config.pic_w >> 8;
+		ac_tag[8] = inst->vsi->config.pic_h;
+		ac_tag[9] = inst->vsi->config.pic_h >> 8;
+	} else {
+		ac_tag_size = 3;
+	}
+
+	if (bs_buf->size < bs_hdr_len + bs_frm_size + ac_tag_size) {
+		mtk_vcodec_err(inst, "bitstream buf size is too small(%zu)",
+			       bs_buf->size);
+		return -EINVAL;
+	}
+
+	/*
+	* (1) The vp8 bitstream header and body are generated by the HW vp8
+	* encoder separately at the same time. We cannot know the bitstream
+	* header length in advance.
+	* (2) From the vp8 spec, there is no stuffing byte allowed between the
+	* ac tag, bitstream header and bitstream body.
+	*/
+	memmove(bs_buf->va + bs_hdr_len + ac_tag_size,
+		bs_buf->va, bs_frm_size);
+	memcpy(bs_buf->va + ac_tag_size,
+	       inst->work_bufs[VENC_VP8_VPU_WORK_BUF_BS_HEADER].va,
+	       bs_hdr_len);
+	memcpy(bs_buf->va, ac_tag, ac_tag_size);
+	*bs_size = bs_frm_size + bs_hdr_len + ac_tag_size;
+
+	return 0;
+}
+
+static int vp8_enc_encode_frame(struct venc_vp8_inst *inst,
+				struct venc_frm_buf *frm_buf,
+				struct mtk_vcodec_mem *bs_buf,
+				unsigned int *bs_size)
+{
+	int ret = 0;
+	unsigned int irq_status;
+
+	mtk_vcodec_debug(inst, "->frm_cnt=%d", inst->frm_cnt);
+
+	ret = vpu_enc_encode(&inst->vpu_inst, 0, frm_buf, bs_buf, bs_size);
+	if (ret)
+		return ret;
+
+	irq_status = vp8_enc_wait_venc_done(inst);
+	if (irq_status != MTK_VENC_IRQ_STATUS_FRM) {
+		mtk_vcodec_err(inst, "irq_status=%d failed", irq_status);
+		return -EIO;
+	}
+
+	if (vp8_enc_compose_one_frame(inst, bs_buf, bs_size)) {
+		mtk_vcodec_err(inst, "vp8_enc_compose_one_frame failed");
+		return -EINVAL;
+	}
+
+	inst->frm_cnt++;
+	mtk_vcodec_debug(inst, "<-size=%d key_frm=%d", *bs_size,
+			 inst->vpu_inst.is_key_frm);
+
+	return ret;
+}
+
+static int vp8_enc_init(struct mtk_vcodec_ctx *ctx, unsigned long *handle)
+{
+	int ret = 0;
+	struct venc_vp8_inst *inst;
+
+	inst = kzalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	inst->ctx = ctx;
+	inst->vpu_inst.ctx = ctx;
+	inst->vpu_inst.dev = ctx->dev->vpu_plat_dev;
+	inst->vpu_inst.id = IPI_VENC_VP8;
+	inst->hw_base = mtk_vcodec_get_reg_addr(inst->ctx, VENC_LT_SYS);
+
+	mtk_vcodec_debug_enter(inst);
+
+	ret = vpu_enc_init(&inst->vpu_inst);
+
+	inst->vsi = (struct venc_vp8_vsi *)inst->vpu_inst.vsi;
+
+	mtk_vcodec_debug_leave(inst);
+
+	if (ret)
+		kfree(inst);
+	else
+		(*handle) = (unsigned long)inst;
+
+	return ret;
+}
+
+static int vp8_enc_encode(unsigned long handle,
+			  enum venc_start_opt opt,
+			  struct venc_frm_buf *frm_buf,
+			  struct mtk_vcodec_mem *bs_buf,
+			  struct venc_done_result *result)
+{
+	int ret = 0;
+	struct venc_vp8_inst *inst = (struct venc_vp8_inst *)handle;
+	struct mtk_vcodec_ctx *ctx = inst->ctx;
+
+	mtk_vcodec_debug_enter(inst);
+
+	enable_irq(ctx->dev->enc_lt_irq);
+
+	switch (opt) {
+	case VENC_START_OPT_ENCODE_FRAME:
+		ret = vp8_enc_encode_frame(inst, frm_buf, bs_buf,
+					   &result->bs_size);
+		if (ret)
+			goto encode_err;
+		result->is_key_frm = inst->vpu_inst.is_key_frm;
+		break;
+
+	default:
+		mtk_vcodec_err(inst, "opt not support:%d", opt);
+		ret = -EINVAL;
+		break;
+	}
+
+encode_err:
+
+	disable_irq(ctx->dev->enc_lt_irq);
+	mtk_vcodec_debug_leave(inst);
+
+	return ret;
+}
+
+static int vp8_enc_set_param(unsigned long handle,
+			     enum venc_set_param_type type,
+			     struct venc_enc_param *enc_prm)
+{
+	int ret = 0;
+	struct venc_vp8_inst *inst = (struct venc_vp8_inst *)handle;
+
+	mtk_vcodec_debug(inst, "->type=%d", type);
+
+	switch (type) {
+	case VENC_SET_PARAM_ENC:
+		inst->vsi->config.input_fourcc = enc_prm->input_yuv_fmt;
+		inst->vsi->config.bitrate = enc_prm->bitrate;
+		inst->vsi->config.pic_w = enc_prm->width;
+		inst->vsi->config.pic_h = enc_prm->height;
+		inst->vsi->config.buf_w = enc_prm->buf_width;
+		inst->vsi->config.buf_h = enc_prm->buf_height;
+		inst->vsi->config.gop_size = enc_prm->gop_size;
+		inst->vsi->config.framerate = enc_prm->frm_rate;
+		inst->vsi->config.ts_mode = inst->ts_mode;
+		ret = vpu_enc_set_param(&inst->vpu_inst, type, enc_prm);
+		if (ret)
+			break;
+		if (inst->work_buf_allocated) {
+			vp8_enc_free_work_buf(inst);
+			inst->work_buf_allocated = false;
+		}
+		ret = vp8_enc_alloc_work_buf(inst);
+		if (ret)
+			break;
+		inst->work_buf_allocated = true;
+		break;
+
+	/*
+	 * VENC_SET_PARAM_TS_MODE must be called before VENC_SET_PARAM_ENC
+	 */
+	case VENC_SET_PARAM_TS_MODE:
+		inst->ts_mode = 1;
+		mtk_vcodec_debug(inst, "set ts_mode");
+		break;
+
+	default:
+		ret = vpu_enc_set_param(&inst->vpu_inst, type, enc_prm);
+		break;
+	}
+
+	mtk_vcodec_debug_leave(inst);
+
+	return ret;
+}
+
+static int vp8_enc_deinit(unsigned long handle)
+{
+	int ret = 0;
+	struct venc_vp8_inst *inst = (struct venc_vp8_inst *)handle;
+
+	mtk_vcodec_debug_enter(inst);
+
+	ret = vpu_enc_deinit(&inst->vpu_inst);
+
+	if (inst->work_buf_allocated)
+		vp8_enc_free_work_buf(inst);
+
+	mtk_vcodec_debug_leave(inst);
+	kfree(inst);
+
+	return ret;
+}
+
+static struct venc_common_if venc_vp8_if = {
+	vp8_enc_init,
+	vp8_enc_encode,
+	vp8_enc_set_param,
+	vp8_enc_deinit,
+};
+
+struct venc_common_if *get_vp8_enc_comm_if(void);
+
+struct venc_common_if *get_vp8_enc_comm_if(void)
+{
+	return &venc_vp8_if;
+}
diff --git a/drivers/media/platform/mtk-vcodec/venc_drv_base.h b/drivers/media/platform/mtk-vcodec/venc_drv_base.h
new file mode 100644
index 000000000000..6308d44dedf6
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc_drv_base.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Daniel Hsiao <daniel.hsiao@mediatek.com>
+ *	Jungchang Tsao <jungchang.tsao@mediatek.com>
+ *	Tiffany Lin <tiffany.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _VENC_DRV_BASE_
+#define _VENC_DRV_BASE_
+
+#include "mtk_vcodec_drv.h"
+
+#include "venc_drv_if.h"
+
+struct venc_common_if {
+	/**
+	 * (*init)() - initialize driver
+	 * @ctx:	[in] mtk v4l2 context
+	 * @handle: [out] driver handle
+	 */
+	int (*init)(struct mtk_vcodec_ctx *ctx, unsigned long *handle);
+
+	/**
+	 * (*encode)() - trigger encode
+	 * @handle: [in] driver handle
+	 * @opt: [in] encode option
+	 * @frm_buf: [in] frame buffer to store input frame
+	 * @bs_buf: [in] bitstream buffer to store output bitstream
+	 * @result: [out] encode result
+	 */
+	int (*encode)(unsigned long handle, enum venc_start_opt opt,
+		      struct venc_frm_buf *frm_buf,
+		      struct mtk_vcodec_mem *bs_buf,
+		      struct venc_done_result *result);
+
+	/**
+	 * (*set_param)() - set driver's parameter
+	 * @handle: [in] driver handle
+	 * @type: [in] parameter type
+	 * @in: [in] buffer to store the parameter
+	 */
+	int (*set_param)(unsigned long handle, enum venc_set_param_type type,
+			 struct venc_enc_param *in);
+
+	/**
+	 * (*deinit)() - deinitialize driver.
+	 * @handle: [in] driver handle
+	 */
+	int (*deinit)(unsigned long handle);
+};
+
+#endif
diff --git a/drivers/media/platform/mtk-vcodec/venc_drv_if.c b/drivers/media/platform/mtk-vcodec/venc_drv_if.c
new file mode 100644
index 000000000000..c4c83e7189c3
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc_drv_if.c
@@ -0,0 +1,113 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Daniel Hsiao <daniel.hsiao@mediatek.com>
+ *	Jungchang Tsao <jungchang.tsao@mediatek.com>
+ *	Tiffany Lin <tiffany.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "venc_drv_base.h"
+#include "venc_drv_if.h"
+
+#include "mtk_vcodec_enc.h"
+#include "mtk_vcodec_enc_pm.h"
+#include "mtk_vpu.h"
+
+struct venc_common_if *get_h264_enc_comm_if(void);
+struct venc_common_if *get_vp8_enc_comm_if(void);
+
+int venc_if_init(struct mtk_vcodec_ctx *ctx, unsigned int fourcc)
+{
+	int ret = 0;
+
+	switch (fourcc) {
+	case V4L2_PIX_FMT_VP8:
+		ctx->enc_if = get_vp8_enc_comm_if();
+		break;
+	case V4L2_PIX_FMT_H264:
+		ctx->enc_if = get_h264_enc_comm_if();
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	mtk_venc_lock(ctx);
+	mtk_vcodec_enc_clock_on(&ctx->dev->pm);
+	ret = ctx->enc_if->init(ctx, (unsigned long *)&ctx->drv_handle);
+	mtk_vcodec_enc_clock_off(&ctx->dev->pm);
+	mtk_venc_unlock(ctx);
+
+	return ret;
+}
+
+int venc_if_set_param(struct mtk_vcodec_ctx *ctx,
+		enum venc_set_param_type type, struct venc_enc_param *in)
+{
+	int ret = 0;
+
+	mtk_venc_lock(ctx);
+	mtk_vcodec_enc_clock_on(&ctx->dev->pm);
+	ret = ctx->enc_if->set_param(ctx->drv_handle, type, in);
+	mtk_vcodec_enc_clock_off(&ctx->dev->pm);
+	mtk_venc_unlock(ctx);
+
+	return ret;
+}
+
+int venc_if_encode(struct mtk_vcodec_ctx *ctx,
+		   enum venc_start_opt opt, struct venc_frm_buf *frm_buf,
+		   struct mtk_vcodec_mem *bs_buf,
+		   struct venc_done_result *result)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	mtk_venc_lock(ctx);
+
+	spin_lock_irqsave(&ctx->dev->irqlock, flags);
+	ctx->dev->curr_ctx = ctx;
+	spin_unlock_irqrestore(&ctx->dev->irqlock, flags);
+
+	mtk_vcodec_enc_clock_on(&ctx->dev->pm);
+	ret = ctx->enc_if->encode(ctx->drv_handle, opt, frm_buf,
+				  bs_buf, result);
+	mtk_vcodec_enc_clock_off(&ctx->dev->pm);
+
+	spin_lock_irqsave(&ctx->dev->irqlock, flags);
+	ctx->dev->curr_ctx = NULL;
+	spin_unlock_irqrestore(&ctx->dev->irqlock, flags);
+
+	mtk_venc_unlock(ctx);
+	return ret;
+}
+
+int venc_if_deinit(struct mtk_vcodec_ctx *ctx)
+{
+	int ret = 0;
+
+	if (ctx->drv_handle == 0)
+		return 0;
+
+	mtk_venc_lock(ctx);
+	mtk_vcodec_enc_clock_on(&ctx->dev->pm);
+	ret = ctx->enc_if->deinit(ctx->drv_handle);
+	mtk_vcodec_enc_clock_off(&ctx->dev->pm);
+	mtk_venc_unlock(ctx);
+
+	ctx->drv_handle = 0;
+
+	return ret;
+}
diff --git a/drivers/media/platform/mtk-vcodec/venc_drv_if.h b/drivers/media/platform/mtk-vcodec/venc_drv_if.h
new file mode 100644
index 000000000000..a6e7d32e55cb
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc_drv_if.h
@@ -0,0 +1,163 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Daniel Hsiao <daniel.hsiao@mediatek.com>
+ *		Jungchang Tsao <jungchang.tsao@mediatek.com>
+ *		Tiffany Lin <tiffany.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _VENC_DRV_IF_H_
+#define _VENC_DRV_IF_H_
+
+#include "mtk_vcodec_drv.h"
+#include "mtk_vcodec_util.h"
+
+/*
+ * enum venc_yuv_fmt - The type of input yuv format
+ * (VPU related: If you change the order, you must also update the VPU codes.)
+ * @VENC_YUV_FORMAT_I420: I420 YUV format
+ * @VENC_YUV_FORMAT_YV12: YV12 YUV format
+ * @VENC_YUV_FORMAT_NV12: NV12 YUV format
+ * @VENC_YUV_FORMAT_NV21: NV21 YUV format
+ */
+enum venc_yuv_fmt {
+	VENC_YUV_FORMAT_I420 = 3,
+	VENC_YUV_FORMAT_YV12 = 5,
+	VENC_YUV_FORMAT_NV12 = 6,
+	VENC_YUV_FORMAT_NV21 = 7,
+};
+
+/*
+ * enum venc_start_opt - encode frame option used in venc_if_encode()
+ * @VENC_START_OPT_ENCODE_SEQUENCE_HEADER: encode SPS/PPS for H264
+ * @VENC_START_OPT_ENCODE_FRAME: encode normal frame
+ */
+enum venc_start_opt {
+	VENC_START_OPT_ENCODE_SEQUENCE_HEADER,
+	VENC_START_OPT_ENCODE_FRAME,
+};
+
+/*
+ * enum venc_set_param_type - The type of set parameter used in
+ *						      venc_if_set_param()
+ * (VPU related: If you change the order, you must also update the VPU codes.)
+ * @VENC_SET_PARAM_ENC: set encoder parameters
+ * @VENC_SET_PARAM_FORCE_INTRA: force an intra frame
+ * @VENC_SET_PARAM_ADJUST_BITRATE: adjust bitrate (in bps)
+ * @VENC_SET_PARAM_ADJUST_FRAMERATE: set frame rate
+ * @VENC_SET_PARAM_GOP_SIZE: set IDR interval
+ * @VENC_SET_PARAM_INTRA_PERIOD: set I frame interval
+ * @VENC_SET_PARAM_SKIP_FRAME: set H264 skip one frame
+ * @VENC_SET_PARAM_PREPEND_HEADER: set H264 prepend SPS/PPS before IDR
+ * @VENC_SET_PARAM_TS_MODE: set VP8 temporal scalability mode
+ */
+enum venc_set_param_type {
+	VENC_SET_PARAM_ENC,
+	VENC_SET_PARAM_FORCE_INTRA,
+	VENC_SET_PARAM_ADJUST_BITRATE,
+	VENC_SET_PARAM_ADJUST_FRAMERATE,
+	VENC_SET_PARAM_GOP_SIZE,
+	VENC_SET_PARAM_INTRA_PERIOD,
+	VENC_SET_PARAM_SKIP_FRAME,
+	VENC_SET_PARAM_PREPEND_HEADER,
+	VENC_SET_PARAM_TS_MODE,
+};
+
+/*
+ * struct venc_enc_prm - encoder settings for VENC_SET_PARAM_ENC used in
+ *					  venc_if_set_param()
+ * @input_fourcc: input yuv format
+ * @h264_profile: V4L2 defined H.264 profile
+ * @h264_level: V4L2 defined H.264 level
+ * @width: image width
+ * @height: image height
+ * @buf_width: buffer width
+ * @buf_height: buffer height
+ * @frm_rate: frame rate in fps
+ * @intra_period: intra frame period
+ * @bitrate: target bitrate in bps
+ * @gop_size: group of picture size
+ */
+struct venc_enc_param {
+	enum venc_yuv_fmt input_yuv_fmt;
+	unsigned int h264_profile;
+	unsigned int h264_level;
+	unsigned int width;
+	unsigned int height;
+	unsigned int buf_width;
+	unsigned int buf_height;
+	unsigned int frm_rate;
+	unsigned int intra_period;
+	unsigned int bitrate;
+	unsigned int gop_size;
+};
+
+/*
+ * struct venc_frm_buf - frame buffer information used in venc_if_encode()
+ * @fb_addr: plane frame buffer addresses
+ */
+struct venc_frm_buf {
+	struct mtk_vcodec_mem fb_addr[MTK_VCODEC_MAX_PLANES];
+};
+
+/*
+ * struct venc_done_result - This is return information used in venc_if_encode()
+ * @bs_size: output bitstream size
+ * @is_key_frm: output is key frame or not
+ */
+struct venc_done_result {
+	unsigned int bs_size;
+	bool is_key_frm;
+};
+
+/*
+ * venc_if_init - Create the driver handle
+ * @ctx: device context
+ * @fourcc: encoder input format
+ * Return: 0 if creating handle successfully, otherwise it is failed.
+ */
+int venc_if_init(struct mtk_vcodec_ctx *ctx, unsigned int fourcc);
+
+/*
+ * venc_if_deinit - Release the driver handle
+ * @ctx: device context
+ * Return: 0 if releasing handle successfully, otherwise it is failed.
+ */
+int venc_if_deinit(struct mtk_vcodec_ctx *ctx);
+
+/*
+ * venc_if_set_param - Set parameter to driver
+ * @ctx: device context
+ * @type: parameter type
+ * @in: input parameter
+ * Return: 0 if setting param successfully, otherwise it is failed.
+ */
+int venc_if_set_param(struct mtk_vcodec_ctx *ctx,
+		      enum venc_set_param_type type,
+		      struct venc_enc_param *in);
+
+/*
+ * venc_if_encode - Encode one frame
+ * @ctx: device context
+ * @opt: encode frame option
+ * @frm_buf: input frame buffer information
+ * @bs_buf: output bitstream buffer infomraiton
+ * @result: encode result
+ * Return: 0 if encoding frame successfully, otherwise it is failed.
+ */
+int venc_if_encode(struct mtk_vcodec_ctx *ctx,
+		   enum venc_start_opt opt,
+		   struct venc_frm_buf *frm_buf,
+		   struct mtk_vcodec_mem *bs_buf,
+		   struct venc_done_result *result);
+
+#endif /* _VENC_DRV_IF_H_ */
diff --git a/drivers/media/platform/mtk-vcodec/venc_ipi_msg.h b/drivers/media/platform/mtk-vcodec/venc_ipi_msg.h
new file mode 100644
index 000000000000..4c869cb6fbf7
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc_ipi_msg.h
@@ -0,0 +1,210 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Jungchang Tsao <jungchang.tsao@mediatek.com>
+ *	   Daniel Hsiao <daniel.hsiao@mediatek.com>
+ *	   Tiffany Lin <tiffany.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _VENC_IPI_MSG_H_
+#define _VENC_IPI_MSG_H_
+
+#define AP_IPIMSG_VENC_BASE 0xC000
+#define VPU_IPIMSG_VENC_BASE 0xD000
+
+/**
+ * enum venc_ipi_msg_id - message id between AP and VPU
+ * (ipi stands for inter-processor interrupt)
+ * @AP_IPIMSG_ENC_XXX:		AP to VPU cmd message id
+ * @VPU_IPIMSG_ENC_XXX_DONE:	VPU ack AP cmd message id
+ */
+enum venc_ipi_msg_id {
+	AP_IPIMSG_ENC_INIT = AP_IPIMSG_VENC_BASE,
+	AP_IPIMSG_ENC_SET_PARAM,
+	AP_IPIMSG_ENC_ENCODE,
+	AP_IPIMSG_ENC_DEINIT,
+
+	VPU_IPIMSG_ENC_INIT_DONE = VPU_IPIMSG_VENC_BASE,
+	VPU_IPIMSG_ENC_SET_PARAM_DONE,
+	VPU_IPIMSG_ENC_ENCODE_DONE,
+	VPU_IPIMSG_ENC_DEINIT_DONE,
+};
+
+/**
+ * struct venc_ap_ipi_msg_init - AP to VPU init cmd structure
+ * @msg_id:	message id (AP_IPIMSG_XXX_ENC_INIT)
+ * @reserved:	reserved for future use. vpu is running in 32bit. Without
+ *		this reserved field, if kernel run in 64bit. this struct size
+ *		will be different between kernel and vpu
+ * @venc_inst:	AP encoder instance
+ *		(struct venc_vp8_inst/venc_h264_inst *)
+ */
+struct venc_ap_ipi_msg_init {
+	uint32_t msg_id;
+	uint32_t reserved;
+	uint64_t venc_inst;
+};
+
+/**
+ * struct venc_ap_ipi_msg_set_param - AP to VPU set_param cmd structure
+ * @msg_id:	message id (AP_IPIMSG_XXX_ENC_SET_PARAM)
+ * @vpu_inst_addr:	VPU encoder instance addr
+ *			(struct venc_vp8_vsi/venc_h264_vsi *)
+ * @param_id:	parameter id (venc_set_param_type)
+ * @data_item:	number of items in the data array
+ * @data[8]:	data array to store the set parameters
+ */
+struct venc_ap_ipi_msg_set_param {
+	uint32_t msg_id;
+	uint32_t vpu_inst_addr;
+	uint32_t param_id;
+	uint32_t data_item;
+	uint32_t data[8];
+};
+
+/**
+ * struct venc_ap_ipi_msg_enc - AP to VPU enc cmd structure
+ * @msg_id:	message id (AP_IPIMSG_XXX_ENC_ENCODE)
+ * @vpu_inst_addr:	VPU encoder instance addr
+ *			(struct venc_vp8_vsi/venc_h264_vsi *)
+ * @bs_mode:	bitstream mode for h264
+ *		(H264_BS_MODE_SPS/H264_BS_MODE_PPS/H264_BS_MODE_FRAME)
+ * @input_addr:	pointer to input image buffer plane
+ * @bs_addr:	pointer to output bit stream buffer
+ * @bs_size:	bit stream buffer size
+ */
+struct venc_ap_ipi_msg_enc {
+	uint32_t msg_id;
+	uint32_t vpu_inst_addr;
+	uint32_t bs_mode;
+	uint32_t input_addr[3];
+	uint32_t bs_addr;
+	uint32_t bs_size;
+};
+
+/**
+ * struct venc_ap_ipi_msg_deinit - AP to VPU deinit cmd structure
+ * @msg_id:	message id (AP_IPIMSG_XXX_ENC_DEINIT)
+ * @vpu_inst_addr:	VPU encoder instance addr
+ *			(struct venc_vp8_vsi/venc_h264_vsi *)
+ */
+struct venc_ap_ipi_msg_deinit {
+	uint32_t msg_id;
+	uint32_t vpu_inst_addr;
+};
+
+/**
+ * enum venc_ipi_msg_status - VPU ack AP cmd status
+ */
+enum venc_ipi_msg_status {
+	VENC_IPI_MSG_STATUS_OK,
+	VENC_IPI_MSG_STATUS_FAIL,
+};
+
+/**
+ * struct venc_vpu_ipi_msg_common - VPU ack AP cmd common structure
+ * @msg_id:	message id (VPU_IPIMSG_XXX_DONE)
+ * @status:	cmd status (venc_ipi_msg_status)
+ * @venc_inst:	AP encoder instance (struct venc_vp8_inst/venc_h264_inst *)
+ */
+struct venc_vpu_ipi_msg_common {
+	uint32_t msg_id;
+	uint32_t status;
+	uint64_t venc_inst;
+};
+
+/**
+ * struct venc_vpu_ipi_msg_init - VPU ack AP init cmd structure
+ * @msg_id:	message id (VPU_IPIMSG_XXX_ENC_SET_PARAM_DONE)
+ * @status:	cmd status (venc_ipi_msg_status)
+ * @venc_inst:	AP encoder instance (struct venc_vp8_inst/venc_h264_inst *)
+ * @vpu_inst_addr:	VPU encoder instance addr
+ *			(struct venc_vp8_vsi/venc_h264_vsi *)
+ * @reserved:	reserved for future use. vpu is running in 32bit. Without
+ *		this reserved field, if kernel run in 64bit. this struct size
+ *		will be different between kernel and vpu
+ */
+struct venc_vpu_ipi_msg_init {
+	uint32_t msg_id;
+	uint32_t status;
+	uint64_t venc_inst;
+	uint32_t vpu_inst_addr;
+	uint32_t reserved;
+};
+
+/**
+ * struct venc_vpu_ipi_msg_set_param - VPU ack AP set_param cmd structure
+ * @msg_id:	message id (VPU_IPIMSG_XXX_ENC_SET_PARAM_DONE)
+ * @status:	cmd status (venc_ipi_msg_status)
+ * @venc_inst:	AP encoder instance (struct venc_vp8_inst/venc_h264_inst *)
+ * @param_id:	parameter id (venc_set_param_type)
+ * @data_item:	number of items in the data array
+ * @data[6]:	data array to store the return result
+ */
+struct venc_vpu_ipi_msg_set_param {
+	uint32_t msg_id;
+	uint32_t status;
+	uint64_t venc_inst;
+	uint32_t param_id;
+	uint32_t data_item;
+	uint32_t data[6];
+};
+
+/**
+ * enum venc_ipi_msg_enc_state - Type of encode state
+ * VEN_IPI_MSG_ENC_STATE_FRAME:	one frame being encoded
+ * VEN_IPI_MSG_ENC_STATE_PART:	bit stream buffer full
+ * VEN_IPI_MSG_ENC_STATE_SKIP:	encoded skip frame
+ * VEN_IPI_MSG_ENC_STATE_ERROR:	encounter error
+ */
+enum venc_ipi_msg_enc_state {
+	VEN_IPI_MSG_ENC_STATE_FRAME,
+	VEN_IPI_MSG_ENC_STATE_PART,
+	VEN_IPI_MSG_ENC_STATE_SKIP,
+	VEN_IPI_MSG_ENC_STATE_ERROR,
+};
+
+/**
+ * struct venc_vpu_ipi_msg_enc - VPU ack AP enc cmd structure
+ * @msg_id:	message id (VPU_IPIMSG_XXX_ENC_ENCODE_DONE)
+ * @status:	cmd status (venc_ipi_msg_status)
+ * @venc_inst:	AP encoder instance (struct venc_vp8_inst/venc_h264_inst *)
+ * @state:	encode state (venc_ipi_msg_enc_state)
+ * @is_key_frm:	whether the encoded frame is key frame
+ * @bs_size:	encoded bitstream size
+ * @reserved:	reserved for future use. vpu is running in 32bit. Without
+ *		this reserved field, if kernel run in 64bit. this struct size
+ *		will be different between kernel and vpu
+ */
+struct venc_vpu_ipi_msg_enc {
+	uint32_t msg_id;
+	uint32_t status;
+	uint64_t venc_inst;
+	uint32_t state;
+	uint32_t is_key_frm;
+	uint32_t bs_size;
+	uint32_t reserved;
+};
+
+/**
+ * struct venc_vpu_ipi_msg_deinit - VPU ack AP deinit cmd structure
+ * @msg_id:   message id (VPU_IPIMSG_XXX_ENC_DEINIT_DONE)
+ * @status:   cmd status (venc_ipi_msg_status)
+ * @venc_inst:	AP encoder instance (struct venc_vp8_inst/venc_h264_inst *)
+ */
+struct venc_vpu_ipi_msg_deinit {
+	uint32_t msg_id;
+	uint32_t status;
+	uint64_t venc_inst;
+};
+
+#endif /* _VENC_IPI_MSG_H_ */
diff --git a/drivers/media/platform/mtk-vcodec/venc_vpu_if.c b/drivers/media/platform/mtk-vcodec/venc_vpu_if.c
new file mode 100644
index 000000000000..a01c7599b510
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc_vpu_if.c
@@ -0,0 +1,238 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: PoChun Lin <pochun.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mtk_vpu.h"
+#include "venc_ipi_msg.h"
+#include "venc_vpu_if.h"
+
+static void handle_enc_init_msg(struct venc_vpu_inst *vpu, void *data)
+{
+	struct venc_vpu_ipi_msg_init *msg = data;
+
+	vpu->inst_addr = msg->vpu_inst_addr;
+	vpu->vsi = vpu_mapping_dm_addr(vpu->dev, msg->vpu_inst_addr);
+}
+
+static void handle_enc_encode_msg(struct venc_vpu_inst *vpu, void *data)
+{
+	struct venc_vpu_ipi_msg_enc *msg = data;
+
+	vpu->state = msg->state;
+	vpu->bs_size = msg->bs_size;
+	vpu->is_key_frm = msg->is_key_frm;
+}
+
+static void vpu_enc_ipi_handler(void *data, unsigned int len, void *priv)
+{
+	struct venc_vpu_ipi_msg_common *msg = data;
+	struct venc_vpu_inst *vpu =
+		(struct venc_vpu_inst *)(unsigned long)msg->venc_inst;
+
+	mtk_vcodec_debug(vpu, "msg_id %x inst %p status %d",
+			 msg->msg_id, vpu, msg->status);
+
+	switch (msg->msg_id) {
+	case VPU_IPIMSG_ENC_INIT_DONE:
+		handle_enc_init_msg(vpu, data);
+		break;
+	case VPU_IPIMSG_ENC_SET_PARAM_DONE:
+		break;
+	case VPU_IPIMSG_ENC_ENCODE_DONE:
+		handle_enc_encode_msg(vpu, data);
+		break;
+	case VPU_IPIMSG_ENC_DEINIT_DONE:
+		break;
+	default:
+		mtk_vcodec_err(vpu, "unknown msg id %x", msg->msg_id);
+		break;
+	}
+
+	vpu->signaled = 1;
+	vpu->failure = (msg->status != VENC_IPI_MSG_STATUS_OK);
+
+	mtk_vcodec_debug_leave(vpu);
+}
+
+static int vpu_enc_send_msg(struct venc_vpu_inst *vpu, void *msg,
+			    int len)
+{
+	int status;
+
+	mtk_vcodec_debug_enter(vpu);
+
+	if (!vpu->dev) {
+		mtk_vcodec_err(vpu, "inst dev is NULL");
+		return -EINVAL;
+	}
+
+	status = vpu_ipi_send(vpu->dev, vpu->id, msg, len);
+	if (status) {
+		uint32_t msg_id = *(uint32_t *)msg;
+
+		mtk_vcodec_err(vpu, "vpu_ipi_send msg_id %x len %d fail %d",
+			       msg_id, len, status);
+		return -EINVAL;
+	}
+	if (vpu->failure)
+		return -EINVAL;
+
+	mtk_vcodec_debug_leave(vpu);
+
+	return 0;
+}
+
+int vpu_enc_init(struct venc_vpu_inst *vpu)
+{
+	int status;
+	struct venc_ap_ipi_msg_init out;
+
+	mtk_vcodec_debug_enter(vpu);
+
+	init_waitqueue_head(&vpu->wq_hd);
+	vpu->signaled = 0;
+	vpu->failure = 0;
+
+	status = vpu_ipi_register(vpu->dev, vpu->id, vpu_enc_ipi_handler,
+				  NULL, NULL);
+	if (status) {
+		mtk_vcodec_err(vpu, "vpu_ipi_register fail %d", status);
+		return -EINVAL;
+	}
+
+	memset(&out, 0, sizeof(out));
+	out.msg_id = AP_IPIMSG_ENC_INIT;
+	out.venc_inst = (unsigned long)vpu;
+	if (vpu_enc_send_msg(vpu, &out, sizeof(out))) {
+		mtk_vcodec_err(vpu, "AP_IPIMSG_ENC_INIT fail");
+		return -EINVAL;
+	}
+
+	mtk_vcodec_debug_leave(vpu);
+
+	return 0;
+}
+
+int vpu_enc_set_param(struct venc_vpu_inst *vpu,
+		      enum venc_set_param_type id,
+		      struct venc_enc_param *enc_param)
+{
+	struct venc_ap_ipi_msg_set_param out;
+
+	mtk_vcodec_debug(vpu, "id %d ->", id);
+
+	memset(&out, 0, sizeof(out));
+	out.msg_id = AP_IPIMSG_ENC_SET_PARAM;
+	out.vpu_inst_addr = vpu->inst_addr;
+	out.param_id = id;
+	switch (id) {
+	case VENC_SET_PARAM_ENC:
+		out.data_item = 0;
+		break;
+	case VENC_SET_PARAM_FORCE_INTRA:
+		out.data_item = 0;
+		break;
+	case VENC_SET_PARAM_ADJUST_BITRATE:
+		out.data_item = 1;
+		out.data[0] = enc_param->bitrate;
+		break;
+	case VENC_SET_PARAM_ADJUST_FRAMERATE:
+		out.data_item = 1;
+		out.data[0] = enc_param->frm_rate;
+		break;
+	case VENC_SET_PARAM_GOP_SIZE:
+		out.data_item = 1;
+		out.data[0] = enc_param->gop_size;
+		break;
+	case VENC_SET_PARAM_INTRA_PERIOD:
+		out.data_item = 1;
+		out.data[0] = enc_param->intra_period;
+		break;
+	case VENC_SET_PARAM_SKIP_FRAME:
+		out.data_item = 0;
+		break;
+	default:
+		mtk_vcodec_err(vpu, "id %d not supported", id);
+		return -EINVAL;
+	}
+	if (vpu_enc_send_msg(vpu, &out, sizeof(out))) {
+		mtk_vcodec_err(vpu,
+			       "AP_IPIMSG_ENC_SET_PARAM %d fail", id);
+		return -EINVAL;
+	}
+
+	mtk_vcodec_debug(vpu, "id %d <-", id);
+
+	return 0;
+}
+
+int vpu_enc_encode(struct venc_vpu_inst *vpu, unsigned int bs_mode,
+		   struct venc_frm_buf *frm_buf,
+		   struct mtk_vcodec_mem *bs_buf,
+		   unsigned int *bs_size)
+{
+	struct venc_ap_ipi_msg_enc out;
+
+	mtk_vcodec_debug(vpu, "bs_mode %d ->", bs_mode);
+
+	memset(&out, 0, sizeof(out));
+	out.msg_id = AP_IPIMSG_ENC_ENCODE;
+	out.vpu_inst_addr = vpu->inst_addr;
+	out.bs_mode = bs_mode;
+	if (frm_buf) {
+		if ((frm_buf->fb_addr[0].dma_addr % 16 == 0) &&
+		    (frm_buf->fb_addr[1].dma_addr % 16 == 0) &&
+		    (frm_buf->fb_addr[2].dma_addr % 16 == 0)) {
+			out.input_addr[0] = frm_buf->fb_addr[0].dma_addr;
+			out.input_addr[1] = frm_buf->fb_addr[1].dma_addr;
+			out.input_addr[2] = frm_buf->fb_addr[2].dma_addr;
+		} else {
+			mtk_vcodec_err(vpu, "dma_addr not align to 16");
+			return -EINVAL;
+		}
+	}
+	if (bs_buf) {
+		out.bs_addr = bs_buf->dma_addr;
+		out.bs_size = bs_buf->size;
+	}
+	if (vpu_enc_send_msg(vpu, &out, sizeof(out))) {
+		mtk_vcodec_err(vpu, "AP_IPIMSG_ENC_ENCODE %d fail",
+			       bs_mode);
+		return -EINVAL;
+	}
+
+	mtk_vcodec_debug(vpu, "bs_mode %d state %d size %d key_frm %d <-",
+			 bs_mode, vpu->state, vpu->bs_size, vpu->is_key_frm);
+
+	return 0;
+}
+
+int vpu_enc_deinit(struct venc_vpu_inst *vpu)
+{
+	struct venc_ap_ipi_msg_deinit out;
+
+	mtk_vcodec_debug_enter(vpu);
+
+	memset(&out, 0, sizeof(out));
+	out.msg_id = AP_IPIMSG_ENC_DEINIT;
+	out.vpu_inst_addr = vpu->inst_addr;
+	if (vpu_enc_send_msg(vpu, &out, sizeof(out))) {
+		mtk_vcodec_err(vpu, "AP_IPIMSG_ENC_DEINIT fail");
+		return -EINVAL;
+	}
+
+	mtk_vcodec_debug_leave(vpu);
+
+	return 0;
+}
diff --git a/drivers/media/platform/mtk-vcodec/venc_vpu_if.h b/drivers/media/platform/mtk-vcodec/venc_vpu_if.h
new file mode 100644
index 000000000000..215d1e01362e
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/venc_vpu_if.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: PoChun Lin <pochun.lin@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _VENC_VPU_IF_H_
+#define _VENC_VPU_IF_H_
+
+#include "mtk_vpu.h"
+#include "venc_drv_if.h"
+
+/*
+ * struct venc_vpu_inst - encoder VPU driver instance
+ * @wq_hd: wait queue used for vpu cmd trigger then wait vpu interrupt done
+ * @signaled: flag used for checking vpu interrupt done
+ * @failure: flag to show vpu cmd succeeds or not
+ * @state: enum venc_ipi_msg_enc_state
+ * @bs_size: bitstream size for skip frame case usage
+ * @is_key_frm: key frame flag
+ * @inst_addr: VPU instance addr
+ * @vsi: driver structure allocated by VPU side and shared to AP side for
+ *	 control and info share
+ * @id: the id of inter-processor interrupt
+ * @ctx: context for v4l2 layer integration
+ * @dev: device for v4l2 layer integration
+ */
+struct venc_vpu_inst {
+	wait_queue_head_t wq_hd;
+	int signaled;
+	int failure;
+	int state;
+	int bs_size;
+	int is_key_frm;
+	unsigned int inst_addr;
+	void *vsi;
+	enum ipi_id id;
+	struct mtk_vcodec_ctx *ctx;
+	struct platform_device *dev;
+};
+
+int vpu_enc_init(struct venc_vpu_inst *vpu);
+int vpu_enc_set_param(struct venc_vpu_inst *vpu,
+		      enum venc_set_param_type id,
+		      struct venc_enc_param *param);
+int vpu_enc_encode(struct venc_vpu_inst *vpu, unsigned int bs_mode,
+		   struct venc_frm_buf *frm_buf,
+		   struct mtk_vcodec_mem *bs_buf,
+		   unsigned int *bs_size);
+int vpu_enc_deinit(struct venc_vpu_inst *vpu);
+
+#endif
diff --git a/drivers/media/platform/mtk-vpu/Makefile b/drivers/media/platform/mtk-vpu/Makefile
new file mode 100644
index 000000000000..58cc1b4bc9f2
--- /dev/null
+++ b/drivers/media/platform/mtk-vpu/Makefile
@@ -0,0 +1,3 @@
+mtk-vpu-y += mtk_vpu.o
+
+obj-$(CONFIG_VIDEO_MEDIATEK_VPU) += mtk-vpu.o
diff --git a/drivers/media/platform/mtk-vpu/mtk_vpu.c b/drivers/media/platform/mtk-vpu/mtk_vpu.c
new file mode 100644
index 000000000000..c9bf58c97878
--- /dev/null
+++ b/drivers/media/platform/mtk-vpu/mtk_vpu.c
@@ -0,0 +1,946 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: Andrew-CT Chen <andrew-ct.chen@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+#include <linux/clk.h>
+#include <linux/debugfs.h>
+#include <linux/firmware.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/sched.h>
+#include <linux/sizes.h>
+
+#include "mtk_vpu.h"
+
+/**
+ * VPU (video processor unit) is a tiny processor controlling video hardware
+ * related to video codec, scaling and color format converting.
+ * VPU interfaces with other blocks by share memory and interrupt.
+ **/
+
+#define INIT_TIMEOUT_MS		2000U
+#define IPI_TIMEOUT_MS		2000U
+#define VPU_FW_VER_LEN		16
+
+/* maximum program/data TCM (Tightly-Coupled Memory) size */
+#define VPU_PTCM_SIZE		(96 * SZ_1K)
+#define VPU_DTCM_SIZE		(32 * SZ_1K)
+/* the offset to get data tcm address */
+#define VPU_DTCM_OFFSET		0x18000UL
+/* daynamic allocated maximum extended memory size */
+#define VPU_EXT_P_SIZE		SZ_1M
+#define VPU_EXT_D_SIZE		SZ_4M
+/* maximum binary firmware size */
+#define VPU_P_FW_SIZE		(VPU_PTCM_SIZE + VPU_EXT_P_SIZE)
+#define VPU_D_FW_SIZE		(VPU_DTCM_SIZE + VPU_EXT_D_SIZE)
+/* the size of share buffer between Host and  VPU */
+#define SHARE_BUF_SIZE		48
+
+/* binary firmware name */
+#define VPU_P_FW		"vpu_p.bin"
+#define VPU_D_FW		"vpu_d.bin"
+
+#define VPU_RESET		0x0
+#define VPU_TCM_CFG		0x0008
+#define VPU_PMEM_EXT0_ADDR	0x000C
+#define VPU_PMEM_EXT1_ADDR	0x0010
+#define VPU_TO_HOST		0x001C
+#define VPU_DMEM_EXT0_ADDR	0x0014
+#define VPU_DMEM_EXT1_ADDR	0x0018
+#define HOST_TO_VPU		0x0024
+#define VPU_PC_REG		0x0060
+#define VPU_WDT_REG		0x0084
+
+/* vpu inter-processor communication interrupt */
+#define VPU_IPC_INT		BIT(8)
+
+/**
+ * enum vpu_fw_type - VPU firmware type
+ *
+ * @P_FW: program firmware
+ * @D_FW: data firmware
+ *
+ */
+enum vpu_fw_type {
+	P_FW,
+	D_FW,
+};
+
+/**
+ * struct vpu_mem - VPU extended program/data memory information
+ *
+ * @va:		the kernel virtual memory address of VPU extended memory
+ * @pa:		the physical memory address of VPU extended memory
+ *
+ */
+struct vpu_mem {
+	void *va;
+	dma_addr_t pa;
+};
+
+/**
+ * struct vpu_regs - VPU TCM and configuration registers
+ *
+ * @tcm:	the register for VPU Tightly-Coupled Memory
+ * @cfg:	the register for VPU configuration
+ * @irq:	the irq number for VPU interrupt
+ */
+struct vpu_regs {
+	void __iomem *tcm;
+	void __iomem *cfg;
+	int irq;
+};
+
+/**
+ * struct vpu_wdt_handler - VPU watchdog reset handler
+ *
+ * @reset_func:	reset handler
+ * @priv:	private data
+ */
+struct vpu_wdt_handler {
+	void (*reset_func)(void *);
+	void *priv;
+};
+
+/**
+ * struct vpu_wdt - VPU watchdog workqueue
+ *
+ * @handler:	VPU watchdog reset handler
+ * @ws:		workstruct for VPU watchdog
+ * @wq:		workqueue for VPU watchdog
+ */
+struct vpu_wdt {
+	struct vpu_wdt_handler handler[VPU_RST_MAX];
+	struct work_struct ws;
+	struct workqueue_struct *wq;
+};
+
+/**
+ * struct vpu_run - VPU initialization status
+ *
+ * @signaled:		the signal of vpu initialization completed
+ * @fw_ver:		VPU firmware version
+ * @enc_capability:	encoder capability which is not used for now and
+ *			the value is reserved for future use
+ * @wq:			wait queue for VPU initialization status
+ */
+struct vpu_run {
+	u32 signaled;
+	char fw_ver[VPU_FW_VER_LEN];
+	unsigned int	enc_capability;
+	wait_queue_head_t wq;
+};
+
+/**
+ * struct vpu_ipi_desc - VPU IPI descriptor
+ *
+ * @handler:	IPI handler
+ * @name:	the name of IPI handler
+ * @priv:	the private data of IPI handler
+ */
+struct vpu_ipi_desc {
+	ipi_handler_t handler;
+	const char *name;
+	void *priv;
+};
+
+/**
+ * struct share_obj - DTCM (Data Tightly-Coupled Memory) buffer shared with
+ *		      AP and VPU
+ *
+ * @id:		IPI id
+ * @len:	share buffer length
+ * @share_buf:	share buffer data
+ */
+struct share_obj {
+	s32 id;
+	u32 len;
+	unsigned char share_buf[SHARE_BUF_SIZE];
+};
+
+/**
+ * struct mtk_vpu - vpu driver data
+ * @extmem:		VPU extended memory information
+ * @reg:		VPU TCM and configuration registers
+ * @run:		VPU initialization status
+ * @ipi_desc:		VPU IPI descriptor
+ * @recv_buf:		VPU DTCM share buffer for receiving. The
+ *			receive buffer is only accessed in interrupt context.
+ * @send_buf:		VPU DTCM share buffer for sending
+ * @dev:		VPU struct device
+ * @clk:		VPU clock on/off
+ * @fw_loaded:		indicate VPU firmware loaded
+ * @enable_4GB:		VPU 4GB mode on/off
+ * @vpu_mutex:		protect mtk_vpu (except recv_buf) and ensure only
+ *			one client to use VPU service at a time. For example,
+ *			suppose a client is using VPU to decode VP8.
+ *			If the other client wants to encode VP8,
+ *			it has to wait until VP8 decode completes.
+ * @wdt_refcnt		WDT reference count to make sure the watchdog can be
+ *			disabled if no other client is using VPU service
+ * @ack_wq:		The wait queue for each codec and mdp. When sleeping
+ *			processes wake up, they will check the condition
+ *			"ipi_id_ack" to run the corresponding action or
+ *			go back to sleep.
+ * @ipi_id_ack:		The ACKs for registered IPI function sending
+ *			interrupt to VPU
+ *
+ */
+struct mtk_vpu {
+	struct vpu_mem extmem[2];
+	struct vpu_regs reg;
+	struct vpu_run run;
+	struct vpu_wdt wdt;
+	struct vpu_ipi_desc ipi_desc[IPI_MAX];
+	struct share_obj *recv_buf;
+	struct share_obj *send_buf;
+	struct device *dev;
+	struct clk *clk;
+	bool fw_loaded;
+	bool enable_4GB;
+	struct mutex vpu_mutex; /* for protecting vpu data data structure */
+	u32 wdt_refcnt;
+	wait_queue_head_t ack_wq;
+	bool ipi_id_ack[IPI_MAX];
+};
+
+static inline void vpu_cfg_writel(struct mtk_vpu *vpu, u32 val, u32 offset)
+{
+	writel(val, vpu->reg.cfg + offset);
+}
+
+static inline u32 vpu_cfg_readl(struct mtk_vpu *vpu, u32 offset)
+{
+	return readl(vpu->reg.cfg + offset);
+}
+
+static inline bool vpu_running(struct mtk_vpu *vpu)
+{
+	return vpu_cfg_readl(vpu, VPU_RESET) & BIT(0);
+}
+
+static void vpu_clock_disable(struct mtk_vpu *vpu)
+{
+	/* Disable VPU watchdog */
+	mutex_lock(&vpu->vpu_mutex);
+	if (!--vpu->wdt_refcnt)
+		vpu_cfg_writel(vpu,
+			       vpu_cfg_readl(vpu, VPU_WDT_REG) & ~(1L << 31),
+			       VPU_WDT_REG);
+	mutex_unlock(&vpu->vpu_mutex);
+
+	clk_disable(vpu->clk);
+}
+
+static int vpu_clock_enable(struct mtk_vpu *vpu)
+{
+	int ret;
+
+	ret = clk_enable(vpu->clk);
+	if (ret)
+		return ret;
+	/* Enable VPU watchdog */
+	mutex_lock(&vpu->vpu_mutex);
+	if (!vpu->wdt_refcnt++)
+		vpu_cfg_writel(vpu,
+			       vpu_cfg_readl(vpu, VPU_WDT_REG) | (1L << 31),
+			       VPU_WDT_REG);
+	mutex_unlock(&vpu->vpu_mutex);
+
+	return ret;
+}
+
+int vpu_ipi_register(struct platform_device *pdev,
+		     enum ipi_id id, ipi_handler_t handler,
+		     const char *name, void *priv)
+{
+	struct mtk_vpu *vpu = platform_get_drvdata(pdev);
+	struct vpu_ipi_desc *ipi_desc;
+
+	if (!vpu) {
+		dev_err(&pdev->dev, "vpu device in not ready\n");
+		return -EPROBE_DEFER;
+	}
+
+	if (id >= 0 && id < IPI_MAX && handler) {
+		ipi_desc = vpu->ipi_desc;
+		ipi_desc[id].name = name;
+		ipi_desc[id].handler = handler;
+		ipi_desc[id].priv = priv;
+		return 0;
+	}
+
+	dev_err(&pdev->dev, "register vpu ipi id %d with invalid arguments\n",
+		id);
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(vpu_ipi_register);
+
+int vpu_ipi_send(struct platform_device *pdev,
+		 enum ipi_id id, void *buf,
+		 unsigned int len)
+{
+	struct mtk_vpu *vpu = platform_get_drvdata(pdev);
+	struct share_obj *send_obj = vpu->send_buf;
+	unsigned long timeout;
+	int ret = 0;
+
+	if (id <= IPI_VPU_INIT || id >= IPI_MAX ||
+	    len > sizeof(send_obj->share_buf) || !buf) {
+		dev_err(vpu->dev, "failed to send ipi message\n");
+		return -EINVAL;
+	}
+
+	ret = vpu_clock_enable(vpu);
+	if (ret) {
+		dev_err(vpu->dev, "failed to enable vpu clock\n");
+		return ret;
+	}
+	if (!vpu_running(vpu)) {
+		dev_err(vpu->dev, "vpu_ipi_send: VPU is not running\n");
+		ret = -EINVAL;
+		goto clock_disable;
+	}
+
+	mutex_lock(&vpu->vpu_mutex);
+
+	 /* Wait until VPU receives the last command */
+	timeout = jiffies + msecs_to_jiffies(IPI_TIMEOUT_MS);
+	do {
+		if (time_after(jiffies, timeout)) {
+			dev_err(vpu->dev, "vpu_ipi_send: IPI timeout!\n");
+			ret = -EIO;
+			goto mut_unlock;
+		}
+	} while (vpu_cfg_readl(vpu, HOST_TO_VPU));
+
+	memcpy((void *)send_obj->share_buf, buf, len);
+	send_obj->len = len;
+	send_obj->id = id;
+
+	vpu->ipi_id_ack[id] = false;
+	/* send the command to VPU */
+	vpu_cfg_writel(vpu, 0x1, HOST_TO_VPU);
+
+	mutex_unlock(&vpu->vpu_mutex);
+
+	/* wait for VPU's ACK */
+	timeout = msecs_to_jiffies(IPI_TIMEOUT_MS);
+	ret = wait_event_timeout(vpu->ack_wq, vpu->ipi_id_ack[id], timeout);
+	vpu->ipi_id_ack[id] = false;
+	if (ret == 0) {
+		dev_err(vpu->dev, "vpu ipi %d ack time out !", id);
+		ret = -EIO;
+		goto clock_disable;
+	}
+	vpu_clock_disable(vpu);
+
+	return 0;
+
+mut_unlock:
+	mutex_unlock(&vpu->vpu_mutex);
+clock_disable:
+	vpu_clock_disable(vpu);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vpu_ipi_send);
+
+static void vpu_wdt_reset_func(struct work_struct *ws)
+{
+	struct vpu_wdt *wdt = container_of(ws, struct vpu_wdt, ws);
+	struct mtk_vpu *vpu = container_of(wdt, struct mtk_vpu, wdt);
+	struct vpu_wdt_handler *handler = wdt->handler;
+	int index, ret;
+
+	dev_info(vpu->dev, "vpu reset\n");
+	ret = vpu_clock_enable(vpu);
+	if (ret) {
+		dev_err(vpu->dev, "[VPU] wdt enables clock failed %d\n", ret);
+		return;
+	}
+	mutex_lock(&vpu->vpu_mutex);
+	vpu_cfg_writel(vpu, 0x0, VPU_RESET);
+	vpu->fw_loaded = false;
+	mutex_unlock(&vpu->vpu_mutex);
+	vpu_clock_disable(vpu);
+
+	for (index = 0; index < VPU_RST_MAX; index++) {
+		if (handler[index].reset_func) {
+			handler[index].reset_func(handler[index].priv);
+			dev_dbg(vpu->dev, "wdt handler func %d\n", index);
+		}
+	}
+}
+
+int vpu_wdt_reg_handler(struct platform_device *pdev,
+			void wdt_reset(void *),
+			void *priv, enum rst_id id)
+{
+	struct mtk_vpu *vpu = platform_get_drvdata(pdev);
+	struct vpu_wdt_handler *handler;
+
+	if (!vpu) {
+		dev_err(&pdev->dev, "vpu device in not ready\n");
+		return -EPROBE_DEFER;
+	}
+
+	handler = vpu->wdt.handler;
+
+	if (id >= 0 && id < VPU_RST_MAX && wdt_reset) {
+		dev_dbg(vpu->dev, "wdt register id %d\n", id);
+		mutex_lock(&vpu->vpu_mutex);
+		handler[id].reset_func = wdt_reset;
+		handler[id].priv = priv;
+		mutex_unlock(&vpu->vpu_mutex);
+		return 0;
+	}
+
+	dev_err(vpu->dev, "register vpu wdt handler failed\n");
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(vpu_wdt_reg_handler);
+
+unsigned int vpu_get_venc_hw_capa(struct platform_device *pdev)
+{
+	struct mtk_vpu *vpu = platform_get_drvdata(pdev);
+
+	return vpu->run.enc_capability;
+}
+EXPORT_SYMBOL_GPL(vpu_get_venc_hw_capa);
+
+void *vpu_mapping_dm_addr(struct platform_device *pdev,
+			  u32 dtcm_dmem_addr)
+{
+	struct mtk_vpu *vpu = platform_get_drvdata(pdev);
+
+	if (!dtcm_dmem_addr ||
+	    (dtcm_dmem_addr > (VPU_DTCM_SIZE + VPU_EXT_D_SIZE))) {
+		dev_err(vpu->dev, "invalid virtual data memory address\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (dtcm_dmem_addr < VPU_DTCM_SIZE)
+		return (__force void *)(dtcm_dmem_addr + vpu->reg.tcm +
+					VPU_DTCM_OFFSET);
+
+	return vpu->extmem[D_FW].va + (dtcm_dmem_addr - VPU_DTCM_SIZE);
+}
+EXPORT_SYMBOL_GPL(vpu_mapping_dm_addr);
+
+struct platform_device *vpu_get_plat_device(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *vpu_node;
+	struct platform_device *vpu_pdev;
+
+	vpu_node = of_parse_phandle(dev->of_node, "mediatek,vpu", 0);
+	if (!vpu_node) {
+		dev_err(dev, "can't get vpu node\n");
+		return NULL;
+	}
+
+	vpu_pdev = of_find_device_by_node(vpu_node);
+	if (WARN_ON(!vpu_pdev)) {
+		dev_err(dev, "vpu pdev failed\n");
+		of_node_put(vpu_node);
+		return NULL;
+	}
+
+	return vpu_pdev;
+}
+EXPORT_SYMBOL_GPL(vpu_get_plat_device);
+
+/* load vpu program/data memory */
+static int load_requested_vpu(struct mtk_vpu *vpu,
+			      const struct firmware *vpu_fw,
+			      u8 fw_type)
+{
+	size_t tcm_size = fw_type ? VPU_DTCM_SIZE : VPU_PTCM_SIZE;
+	size_t fw_size = fw_type ? VPU_D_FW_SIZE : VPU_P_FW_SIZE;
+	char *fw_name = fw_type ? VPU_D_FW : VPU_P_FW;
+	size_t dl_size = 0;
+	size_t extra_fw_size = 0;
+	void *dest;
+	int ret;
+
+	ret = request_firmware(&vpu_fw, fw_name, vpu->dev);
+	if (ret < 0) {
+		dev_err(vpu->dev, "Failed to load %s, %d\n", fw_name, ret);
+		return ret;
+	}
+	dl_size = vpu_fw->size;
+	if (dl_size > fw_size) {
+		dev_err(vpu->dev, "fw %s size %zu is abnormal\n", fw_name,
+			dl_size);
+		release_firmware(vpu_fw);
+		return  -EFBIG;
+	}
+	dev_dbg(vpu->dev, "Downloaded fw %s size: %zu.\n",
+		fw_name,
+		dl_size);
+	/* reset VPU */
+	vpu_cfg_writel(vpu, 0x0, VPU_RESET);
+
+	/* handle extended firmware size */
+	if (dl_size > tcm_size) {
+		dev_dbg(vpu->dev, "fw size %zu > limited fw size %zu\n",
+			dl_size, tcm_size);
+		extra_fw_size = dl_size - tcm_size;
+		dev_dbg(vpu->dev, "extra_fw_size %zu\n", extra_fw_size);
+		dl_size = tcm_size;
+	}
+	dest = (__force void *)vpu->reg.tcm;
+	if (fw_type == D_FW)
+		dest += VPU_DTCM_OFFSET;
+	memcpy(dest, vpu_fw->data, dl_size);
+	/* download to extended memory if need */
+	if (extra_fw_size > 0) {
+		dest = vpu->extmem[fw_type].va;
+		dev_dbg(vpu->dev, "download extended memory type %x\n",
+			fw_type);
+		memcpy(dest, vpu_fw->data + tcm_size, extra_fw_size);
+	}
+
+	release_firmware(vpu_fw);
+
+	return 0;
+}
+
+int vpu_load_firmware(struct platform_device *pdev)
+{
+	struct mtk_vpu *vpu = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	struct vpu_run *run = &vpu->run;
+	const struct firmware *vpu_fw = NULL;
+	int ret;
+
+	if (!pdev) {
+		dev_err(dev, "VPU platform device is invalid\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&vpu->vpu_mutex);
+	if (vpu->fw_loaded) {
+		mutex_unlock(&vpu->vpu_mutex);
+		return 0;
+	}
+	mutex_unlock(&vpu->vpu_mutex);
+
+	ret = vpu_clock_enable(vpu);
+	if (ret) {
+		dev_err(dev, "enable clock failed %d\n", ret);
+		return ret;
+	}
+
+	mutex_lock(&vpu->vpu_mutex);
+
+	run->signaled = false;
+	dev_dbg(vpu->dev, "firmware request\n");
+	/* Downloading program firmware to device*/
+	ret = load_requested_vpu(vpu, vpu_fw, P_FW);
+	if (ret < 0) {
+		dev_err(dev, "Failed to request %s, %d\n", VPU_P_FW, ret);
+		goto OUT_LOAD_FW;
+	}
+
+	/* Downloading data firmware to device */
+	ret = load_requested_vpu(vpu, vpu_fw, D_FW);
+	if (ret < 0) {
+		dev_err(dev, "Failed to request %s, %d\n", VPU_D_FW, ret);
+		goto OUT_LOAD_FW;
+	}
+
+	vpu->fw_loaded = true;
+	/* boot up vpu */
+	vpu_cfg_writel(vpu, 0x1, VPU_RESET);
+
+	ret = wait_event_interruptible_timeout(run->wq,
+					       run->signaled,
+					       msecs_to_jiffies(INIT_TIMEOUT_MS)
+					       );
+	if (ret == 0) {
+		ret = -ETIME;
+		dev_err(dev, "wait vpu initialization timout!\n");
+		goto OUT_LOAD_FW;
+	} else if (-ERESTARTSYS == ret) {
+		dev_err(dev, "wait vpu interrupted by a signal!\n");
+		goto OUT_LOAD_FW;
+	}
+
+	ret = 0;
+	dev_info(dev, "vpu is ready. Fw version %s\n", run->fw_ver);
+
+OUT_LOAD_FW:
+	mutex_unlock(&vpu->vpu_mutex);
+	vpu_clock_disable(vpu);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vpu_load_firmware);
+
+static void vpu_init_ipi_handler(void *data, unsigned int len, void *priv)
+{
+	struct mtk_vpu *vpu = (struct mtk_vpu *)priv;
+	struct vpu_run *run = (struct vpu_run *)data;
+
+	vpu->run.signaled = run->signaled;
+	strncpy(vpu->run.fw_ver, run->fw_ver, VPU_FW_VER_LEN);
+	vpu->run.enc_capability = run->enc_capability;
+	wake_up_interruptible(&vpu->run.wq);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static ssize_t vpu_debug_read(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+	char buf[256];
+	unsigned int len;
+	unsigned int running, pc, vpu_to_host, host_to_vpu, wdt;
+	int ret;
+	struct device *dev = file->private_data;
+	struct mtk_vpu *vpu = dev_get_drvdata(dev);
+
+	ret = vpu_clock_enable(vpu);
+	if (ret) {
+		dev_err(vpu->dev, "[VPU] enable clock failed %d\n", ret);
+		return 0;
+	}
+
+	/* vpu register status */
+	running = vpu_running(vpu);
+	pc = vpu_cfg_readl(vpu, VPU_PC_REG);
+	wdt = vpu_cfg_readl(vpu, VPU_WDT_REG);
+	host_to_vpu = vpu_cfg_readl(vpu, HOST_TO_VPU);
+	vpu_to_host = vpu_cfg_readl(vpu, VPU_TO_HOST);
+	vpu_clock_disable(vpu);
+
+	if (running) {
+		len = snprintf(buf, sizeof(buf), "VPU is running\n\n"
+		"FW Version: %s\n"
+		"PC: 0x%x\n"
+		"WDT: 0x%x\n"
+		"Host to VPU: 0x%x\n"
+		"VPU to Host: 0x%x\n",
+		vpu->run.fw_ver, pc, wdt,
+		host_to_vpu, vpu_to_host);
+	} else {
+		len = snprintf(buf, sizeof(buf), "VPU not running\n");
+	}
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static const struct file_operations vpu_debug_fops = {
+	.open = simple_open,
+	.read = vpu_debug_read,
+};
+#endif /* CONFIG_DEBUG_FS */
+
+static void vpu_free_ext_mem(struct mtk_vpu *vpu, u8 fw_type)
+{
+	struct device *dev = vpu->dev;
+	size_t fw_ext_size = fw_type ? VPU_EXT_D_SIZE : VPU_EXT_P_SIZE;
+
+	dma_free_coherent(dev, fw_ext_size, vpu->extmem[fw_type].va,
+			  vpu->extmem[fw_type].pa);
+}
+
+static int vpu_alloc_ext_mem(struct mtk_vpu *vpu, u32 fw_type)
+{
+	struct device *dev = vpu->dev;
+	size_t fw_ext_size = fw_type ? VPU_EXT_D_SIZE : VPU_EXT_P_SIZE;
+	u32 vpu_ext_mem0 = fw_type ? VPU_DMEM_EXT0_ADDR : VPU_PMEM_EXT0_ADDR;
+	u32 vpu_ext_mem1 = fw_type ? VPU_DMEM_EXT1_ADDR : VPU_PMEM_EXT1_ADDR;
+	u32 offset_4gb = vpu->enable_4GB ? 0x40000000 : 0;
+
+	vpu->extmem[fw_type].va = dma_alloc_coherent(dev,
+					       fw_ext_size,
+					       &vpu->extmem[fw_type].pa,
+					       GFP_KERNEL);
+	if (!vpu->extmem[fw_type].va) {
+		dev_err(dev, "Failed to allocate the extended program memory\n");
+		return PTR_ERR(vpu->extmem[fw_type].va);
+	}
+
+	/* Disable extend0. Enable extend1 */
+	vpu_cfg_writel(vpu, 0x1, vpu_ext_mem0);
+	vpu_cfg_writel(vpu, (vpu->extmem[fw_type].pa & 0xFFFFF000) + offset_4gb,
+		       vpu_ext_mem1);
+
+	dev_info(dev, "%s extend memory phy=0x%llx virt=0x%p\n",
+		 fw_type ? "Data" : "Program",
+		 (unsigned long long)vpu->extmem[fw_type].pa,
+		 vpu->extmem[fw_type].va);
+
+	return 0;
+}
+
+static void vpu_ipi_handler(struct mtk_vpu *vpu)
+{
+	struct share_obj *rcv_obj = vpu->recv_buf;
+	struct vpu_ipi_desc *ipi_desc = vpu->ipi_desc;
+
+	if (rcv_obj->id < IPI_MAX && ipi_desc[rcv_obj->id].handler) {
+		ipi_desc[rcv_obj->id].handler(rcv_obj->share_buf,
+					      rcv_obj->len,
+					      ipi_desc[rcv_obj->id].priv);
+		if (rcv_obj->id > IPI_VPU_INIT) {
+			vpu->ipi_id_ack[rcv_obj->id] = true;
+			wake_up(&vpu->ack_wq);
+		}
+	} else {
+		dev_err(vpu->dev, "No such ipi id = %d\n", rcv_obj->id);
+	}
+}
+
+static int vpu_ipi_init(struct mtk_vpu *vpu)
+{
+	/* Disable VPU to host interrupt */
+	vpu_cfg_writel(vpu, 0x0, VPU_TO_HOST);
+
+	/* shared buffer initialization */
+	vpu->recv_buf = (__force struct share_obj *)(vpu->reg.tcm +
+						     VPU_DTCM_OFFSET);
+	vpu->send_buf = vpu->recv_buf + 1;
+	memset(vpu->recv_buf, 0, sizeof(struct share_obj));
+	memset(vpu->send_buf, 0, sizeof(struct share_obj));
+
+	return 0;
+}
+
+static irqreturn_t vpu_irq_handler(int irq, void *priv)
+{
+	struct mtk_vpu *vpu = priv;
+	u32 vpu_to_host;
+	int ret;
+
+	/*
+	 * Clock should have been enabled already.
+	 * Enable again in case vpu_ipi_send times out
+	 * and has disabled the clock.
+	 */
+	ret = clk_enable(vpu->clk);
+	if (ret) {
+		dev_err(vpu->dev, "[VPU] enable clock failed %d\n", ret);
+		return IRQ_NONE;
+	}
+	vpu_to_host = vpu_cfg_readl(vpu, VPU_TO_HOST);
+	if (vpu_to_host & VPU_IPC_INT) {
+		vpu_ipi_handler(vpu);
+	} else {
+		dev_err(vpu->dev, "vpu watchdog timeout! 0x%x", vpu_to_host);
+		queue_work(vpu->wdt.wq, &vpu->wdt.ws);
+	}
+
+	/* VPU won't send another interrupt until we set VPU_TO_HOST to 0. */
+	vpu_cfg_writel(vpu, 0x0, VPU_TO_HOST);
+	clk_disable(vpu->clk);
+
+	return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *vpu_debugfs;
+#endif
+static int mtk_vpu_probe(struct platform_device *pdev)
+{
+	struct mtk_vpu *vpu;
+	struct device *dev;
+	struct resource *res;
+	int ret = 0;
+
+	dev_dbg(&pdev->dev, "initialization\n");
+
+	dev = &pdev->dev;
+	vpu = devm_kzalloc(dev, sizeof(*vpu), GFP_KERNEL);
+	if (!vpu)
+		return -ENOMEM;
+
+	vpu->dev = &pdev->dev;
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "tcm");
+	vpu->reg.tcm = devm_ioremap_resource(dev, res);
+	if (IS_ERR((__force void *)vpu->reg.tcm))
+		return PTR_ERR((__force void *)vpu->reg.tcm);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg_reg");
+	vpu->reg.cfg = devm_ioremap_resource(dev, res);
+	if (IS_ERR((__force void *)vpu->reg.cfg))
+		return PTR_ERR((__force void *)vpu->reg.cfg);
+
+	/* Get VPU clock */
+	vpu->clk = devm_clk_get(dev, "main");
+	if (IS_ERR(vpu->clk)) {
+		dev_err(dev, "get vpu clock failed\n");
+		return PTR_ERR(vpu->clk);
+	}
+
+	platform_set_drvdata(pdev, vpu);
+
+	ret = clk_prepare(vpu->clk);
+	if (ret) {
+		dev_err(dev, "prepare vpu clock failed\n");
+		return ret;
+	}
+
+	/* VPU watchdog */
+	vpu->wdt.wq = create_singlethread_workqueue("vpu_wdt");
+	if (!vpu->wdt.wq) {
+		dev_err(dev, "initialize wdt workqueue failed\n");
+		return -ENOMEM;
+	}
+	INIT_WORK(&vpu->wdt.ws, vpu_wdt_reset_func);
+	mutex_init(&vpu->vpu_mutex);
+
+	ret = vpu_clock_enable(vpu);
+	if (ret) {
+		dev_err(dev, "enable vpu clock failed\n");
+		goto workqueue_destroy;
+	}
+
+	dev_dbg(dev, "vpu ipi init\n");
+	ret = vpu_ipi_init(vpu);
+	if (ret) {
+		dev_err(dev, "Failed to init ipi\n");
+		goto disable_vpu_clk;
+	}
+
+	/* register vpu initialization IPI */
+	ret = vpu_ipi_register(pdev, IPI_VPU_INIT, vpu_init_ipi_handler,
+			       "vpu_init", vpu);
+	if (ret) {
+		dev_err(dev, "Failed to register IPI_VPU_INIT\n");
+		goto vpu_mutex_destroy;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	vpu_debugfs = debugfs_create_file("mtk_vpu", S_IRUGO, NULL, (void *)dev,
+					  &vpu_debug_fops);
+	if (!vpu_debugfs) {
+		ret = -ENOMEM;
+		goto cleanup_ipi;
+	}
+#endif
+
+	/* Set PTCM to 96K and DTCM to 32K */
+	vpu_cfg_writel(vpu, 0x2, VPU_TCM_CFG);
+
+	vpu->enable_4GB = !!(totalram_pages > (SZ_2G >> PAGE_SHIFT));
+	dev_info(dev, "4GB mode %u\n", vpu->enable_4GB);
+
+	if (vpu->enable_4GB) {
+		ret = of_reserved_mem_device_init(dev);
+		if (ret)
+			dev_info(dev, "init reserved memory failed\n");
+			/* continue to use dynamic allocation if failed */
+	}
+
+	ret = vpu_alloc_ext_mem(vpu, D_FW);
+	if (ret) {
+		dev_err(dev, "Allocate DM failed\n");
+		goto remove_debugfs;
+	}
+
+	ret = vpu_alloc_ext_mem(vpu, P_FW);
+	if (ret) {
+		dev_err(dev, "Allocate PM failed\n");
+		goto free_d_mem;
+	}
+
+	init_waitqueue_head(&vpu->run.wq);
+	init_waitqueue_head(&vpu->ack_wq);
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res) {
+		dev_err(dev, "get IRQ resource failed.\n");
+		ret = -ENXIO;
+		goto free_p_mem;
+	}
+	vpu->reg.irq = platform_get_irq(pdev, 0);
+	ret = devm_request_irq(dev, vpu->reg.irq, vpu_irq_handler, 0,
+			       pdev->name, vpu);
+	if (ret) {
+		dev_err(dev, "failed to request irq\n");
+		goto free_p_mem;
+	}
+
+	vpu_clock_disable(vpu);
+	dev_dbg(dev, "initialization completed\n");
+
+	return 0;
+
+free_p_mem:
+	vpu_free_ext_mem(vpu, P_FW);
+free_d_mem:
+	vpu_free_ext_mem(vpu, D_FW);
+remove_debugfs:
+	of_reserved_mem_device_release(dev);
+#ifdef CONFIG_DEBUG_FS
+	debugfs_remove(vpu_debugfs);
+cleanup_ipi:
+#endif
+	memset(vpu->ipi_desc, 0, sizeof(struct vpu_ipi_desc) * IPI_MAX);
+vpu_mutex_destroy:
+	mutex_destroy(&vpu->vpu_mutex);
+disable_vpu_clk:
+	vpu_clock_disable(vpu);
+workqueue_destroy:
+	destroy_workqueue(vpu->wdt.wq);
+
+	return ret;
+}
+
+static const struct of_device_id mtk_vpu_match[] = {
+	{
+		.compatible = "mediatek,mt8173-vpu",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtk_vpu_match);
+
+static int mtk_vpu_remove(struct platform_device *pdev)
+{
+	struct mtk_vpu *vpu = platform_get_drvdata(pdev);
+
+#ifdef CONFIG_DEBUG_FS
+	debugfs_remove(vpu_debugfs);
+#endif
+	if (vpu->wdt.wq) {
+		flush_workqueue(vpu->wdt.wq);
+		destroy_workqueue(vpu->wdt.wq);
+	}
+	vpu_free_ext_mem(vpu, P_FW);
+	vpu_free_ext_mem(vpu, D_FW);
+	mutex_destroy(&vpu->vpu_mutex);
+	clk_unprepare(vpu->clk);
+
+	return 0;
+}
+
+static struct platform_driver mtk_vpu_driver = {
+	.probe	= mtk_vpu_probe,
+	.remove	= mtk_vpu_remove,
+	.driver	= {
+		.name	= "mtk_vpu",
+		.of_match_table = mtk_vpu_match,
+	},
+};
+
+module_platform_driver(mtk_vpu_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Mediatek Video Prosessor Unit driver");
diff --git a/drivers/media/platform/mtk-vpu/mtk_vpu.h b/drivers/media/platform/mtk-vpu/mtk_vpu.h
new file mode 100644
index 000000000000..5ab37f04bdfd
--- /dev/null
+++ b/drivers/media/platform/mtk-vpu/mtk_vpu.h
@@ -0,0 +1,162 @@
+/*
+* Copyright (c) 2016 MediaTek Inc.
+* Author: Andrew-CT Chen <andrew-ct.chen@mediatek.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*/
+
+#ifndef _MTK_VPU_H
+#define _MTK_VPU_H
+
+#include <linux/platform_device.h>
+
+/**
+ * VPU (video processor unit) is a tiny processor controlling video hardware
+ * related to video codec, scaling and color format converting.
+ * VPU interfaces with other blocks by share memory and interrupt.
+ **/
+
+typedef void (*ipi_handler_t) (void *data,
+			       unsigned int len,
+			       void *priv);
+
+/**
+ * enum ipi_id - the id of inter-processor interrupt
+ *
+ * @IPI_VPU_INIT:	 The interrupt from vpu is to notfiy kernel
+			 VPU initialization completed.
+			 IPI_VPU_INIT is sent from VPU when firmware is
+			 loaded. AP doesn't need to send IPI_VPU_INIT
+			 command to VPU.
+			 For other IPI below, AP should send the request
+			 to VPU to trigger the interrupt.
+ * @IPI_VENC_H264:	 The interrupt from vpu is to notify kernel to
+			 handle H264 video encoder job, and vice versa.
+ * @IPI_VENC_VP8:	 The interrupt fro vpu is to notify kernel to
+			 handle VP8 video encoder job,, and vice versa.
+ * @IPI_MAX:		 The maximum IPI number
+ */
+
+enum ipi_id {
+	IPI_VPU_INIT = 0,
+	IPI_VENC_H264,
+	IPI_VENC_VP8,
+	IPI_MAX,
+};
+
+/**
+ * enum rst_id - reset id to register reset function for VPU watchdog timeout
+ *
+ * @VPU_RST_ENC: encoder reset id
+ * @VPU_RST_MAX: maximum reset id
+ */
+enum rst_id {
+	VPU_RST_ENC,
+	VPU_RST_MAX,
+};
+
+/**
+ * vpu_ipi_register - register an ipi function
+ *
+ * @pdev:	VPU platform device
+ * @id:		IPI ID
+ * @handler:	IPI handler
+ * @name:	IPI name
+ * @priv:	private data for IPI handler
+ *
+ * Register an ipi function to receive ipi interrupt from VPU.
+ *
+ * Return: Return 0 if ipi registers successfully, otherwise it is failed.
+ */
+int vpu_ipi_register(struct platform_device *pdev, enum ipi_id id,
+		     ipi_handler_t handler, const char *name, void *priv);
+
+/**
+ * vpu_ipi_send - send data from AP to vpu.
+ *
+ * @pdev:	VPU platform device
+ * @id:		IPI ID
+ * @buf:	the data buffer
+ * @len:	the data buffer length
+ *
+ * This function is thread-safe. When this function returns,
+ * VPU has received the data and starts the processing.
+ * When the processing completes, IPI handler registered
+ * by vpu_ipi_register will be called in interrupt context.
+ *
+ * Return: Return 0 if sending data successfully, otherwise it is failed.
+ **/
+int vpu_ipi_send(struct platform_device *pdev,
+		 enum ipi_id id, void *buf,
+		 unsigned int len);
+
+/**
+ * vpu_get_plat_device - get VPU's platform device
+ *
+ * @pdev:	the platform device of the module requesting VPU platform
+ *		device for using VPU API.
+ *
+ * Return: Return NULL if it is failed.
+ * otherwise it is VPU's platform device
+ **/
+struct platform_device *vpu_get_plat_device(struct platform_device *pdev);
+
+/**
+ * vpu_wdt_reg_handler - register a VPU watchdog handler
+ *
+ * @pdev:               VPU platform device
+ * @vpu_wdt_reset_func:	the callback reset function
+ * @private_data:       the private data for reset function
+ * @rst_id:		reset id
+ *
+ * Register a handler performing own tasks when vpu reset by watchdog
+ *
+ * Return: Return 0 if the handler is added successfully,
+ * otherwise it is failed.
+ *
+ **/
+int vpu_wdt_reg_handler(struct platform_device *pdev,
+			void vpu_wdt_reset_func(void *),
+			void *priv, enum rst_id id);
+/**
+ * vpu_get_venc_hw_capa - get video encoder hardware capability
+ *
+ * @pdev:	VPU platform device
+ *
+ * Return: video encoder hardware capability
+ **/
+unsigned int vpu_get_venc_hw_capa(struct platform_device *pdev);
+
+/**
+ * vpu_load_firmware - download VPU firmware and boot it
+ *
+ * @pdev:	VPU platform device
+ *
+ * Return: Return 0 if downloading firmware successfully,
+ * otherwise it is failed
+ **/
+int vpu_load_firmware(struct platform_device *pdev);
+
+/**
+ * vpu_mapping_dm_addr - Mapping DTCM/DMEM to kernel virtual address
+ *
+ * @pdev:	VPU platform device
+ * @dmem_addr:	VPU's data memory address
+ *
+ * Mapping the VPU's DTCM (Data Tightly-Coupled Memory) /
+ * DMEM (Data Extended Memory) memory address to
+ * kernel virtual address.
+ *
+ * Return: Return ERR_PTR(-EINVAL) if mapping failed,
+ * otherwise the mapped kernel virtual address
+ **/
+void *vpu_mapping_dm_addr(struct platform_device *pdev,
+			  u32 dtcm_dmem_addr);
+#endif /* _MTK_VPU_H */
diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c
index 3c4012d42d69..c639406fe72e 100644
--- a/drivers/media/platform/mx2_emmaprp.c
+++ b/drivers/media/platform/mx2_emmaprp.c
@@ -211,7 +211,6 @@ struct emmaprp_dev {
 	struct clk		*clk_emma_ahb, *clk_emma_ipg;
 
 	struct v4l2_m2m_dev	*m2m_dev;
-	struct vb2_alloc_ctx	*alloc_ctx;
 };
 
 struct emmaprp_ctx {
@@ -690,7 +689,7 @@ static const struct v4l2_ioctl_ops emmaprp_ioctl_ops = {
  */
 static int emmaprp_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct emmaprp_ctx *ctx = vb2_get_drv_priv(vq);
 	struct emmaprp_q_data *q_data;
@@ -710,8 +709,6 @@ static int emmaprp_queue_setup(struct vb2_queue *vq,
 	*nbuffers = count;
 	sizes[0] = size;
 
-	alloc_ctxs[0] = ctx->dev->alloc_ctx;
-
 	dprintk(ctx->dev, "get %d buffer(s) of size %d each.\n", count, size);
 
 	return 0;
@@ -765,6 +762,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->ops = &emmaprp_qops;
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->dev = ctx->dev->v4l2_dev.dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -777,6 +775,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->ops = &emmaprp_qops;
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->dev = ctx->dev->v4l2_dev.dev;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -948,18 +947,11 @@ static int emmaprp_probe(struct platform_device *pdev)
 	if (ret)
 		goto rel_vdev;
 
-	pcdev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(pcdev->alloc_ctx)) {
-		v4l2_err(&pcdev->v4l2_dev, "Failed to alloc vb2 context\n");
-		ret = PTR_ERR(pcdev->alloc_ctx);
-		goto rel_vdev;
-	}
-
 	pcdev->m2m_dev = v4l2_m2m_init(&m2m_ops);
 	if (IS_ERR(pcdev->m2m_dev)) {
 		v4l2_err(&pcdev->v4l2_dev, "Failed to init mem2mem device\n");
 		ret = PTR_ERR(pcdev->m2m_dev);
-		goto rel_ctx;
+		goto rel_vdev;
 	}
 
 	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
@@ -973,8 +965,6 @@ static int emmaprp_probe(struct platform_device *pdev)
 
 rel_m2m:
 	v4l2_m2m_release(pcdev->m2m_dev);
-rel_ctx:
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
 rel_vdev:
 	video_device_release(vfd);
 unreg_dev:
@@ -993,7 +983,6 @@ static int emmaprp_remove(struct platform_device *pdev)
 
 	video_unregister_device(pcdev->vfd);
 	v4l2_m2m_release(pcdev->m2m_dev);
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
 	v4l2_device_unregister(&pcdev->v4l2_dev);
 	mutex_destroy(&pcdev->dev_mutex);
 
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index 70c28d19ea04..4afc999c0780 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -1318,71 +1318,16 @@ s_crop_err:
 	return ret;
 }
 
-static int vidioc_queryctrl(struct file *file, void *fh,
-		struct v4l2_queryctrl *ctrl)
+static int omap_vout_s_ctrl(struct v4l2_ctrl *ctrl)
 {
+	struct omap_vout_device *vout =
+		container_of(ctrl->handler, struct omap_vout_device, ctrl_handler);
 	int ret = 0;
 
 	switch (ctrl->id) {
-	case V4L2_CID_ROTATE:
-		ret = v4l2_ctrl_query_fill(ctrl, 0, 270, 90, 0);
-		break;
-	case V4L2_CID_BG_COLOR:
-		ret = v4l2_ctrl_query_fill(ctrl, 0, 0xFFFFFF, 1, 0);
-		break;
-	case V4L2_CID_VFLIP:
-		ret = v4l2_ctrl_query_fill(ctrl, 0, 1, 1, 0);
-		break;
-	default:
-		ctrl->name[0] = '\0';
-		ret = -EINVAL;
-	}
-	return ret;
-}
-
-static int vidioc_g_ctrl(struct file *file, void *fh, struct v4l2_control *ctrl)
-{
-	int ret = 0;
-	struct omap_vout_device *vout = fh;
-
-	switch (ctrl->id) {
-	case V4L2_CID_ROTATE:
-		ctrl->value = vout->control[0].value;
-		break;
-	case V4L2_CID_BG_COLOR:
-	{
-		struct omap_overlay_manager_info info;
-		struct omap_overlay *ovl;
-
-		ovl = vout->vid_info.overlays[0];
-		if (!ovl->manager || !ovl->manager->get_manager_info) {
-			ret = -EINVAL;
-			break;
-		}
-
-		ovl->manager->get_manager_info(ovl->manager, &info);
-		ctrl->value = info.default_color;
-		break;
-	}
-	case V4L2_CID_VFLIP:
-		ctrl->value = vout->control[2].value;
-		break;
-	default:
-		ret = -EINVAL;
-	}
-	return ret;
-}
-
-static int vidioc_s_ctrl(struct file *file, void *fh, struct v4l2_control *a)
-{
-	int ret = 0;
-	struct omap_vout_device *vout = fh;
-
-	switch (a->id) {
-	case V4L2_CID_ROTATE:
-	{
+	case V4L2_CID_ROTATE: {
 		struct omapvideo_info *ovid;
-		int rotation = a->value;
+		int rotation = ctrl->val;
 
 		ovid = &vout->vid_info;
 
@@ -1405,15 +1350,13 @@ static int vidioc_s_ctrl(struct file *file, void *fh, struct v4l2_control *a)
 			ret = -EINVAL;
 			break;
 		}
-
-		vout->control[0].value = rotation;
 		mutex_unlock(&vout->lock);
 		break;
 	}
 	case V4L2_CID_BG_COLOR:
 	{
 		struct omap_overlay *ovl;
-		unsigned int  color = a->value;
+		unsigned int color = ctrl->val;
 		struct omap_overlay_manager_info info;
 
 		ovl = vout->vid_info.overlays[0];
@@ -1432,15 +1375,13 @@ static int vidioc_s_ctrl(struct file *file, void *fh, struct v4l2_control *a)
 			ret = -EINVAL;
 			break;
 		}
-
-		vout->control[1].value = color;
 		mutex_unlock(&vout->lock);
 		break;
 	}
 	case V4L2_CID_VFLIP:
 	{
 		struct omapvideo_info *ovid;
-		unsigned int  mirror = a->value;
+		unsigned int mirror = ctrl->val;
 
 		ovid = &vout->vid_info;
 
@@ -1457,16 +1398,19 @@ static int vidioc_s_ctrl(struct file *file, void *fh, struct v4l2_control *a)
 			break;
 		}
 		vout->mirror = mirror;
-		vout->control[2].value = mirror;
 		mutex_unlock(&vout->lock);
 		break;
 	}
 	default:
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 	return ret;
 }
 
+static const struct v4l2_ctrl_ops omap_vout_ctrl_ops = {
+	.s_ctrl = omap_vout_s_ctrl,
+};
+
 static int vidioc_reqbufs(struct file *file, void *fh,
 			struct v4l2_requestbuffers *req)
 {
@@ -1831,11 +1775,8 @@ static const struct v4l2_ioctl_ops vout_ioctl_ops = {
 	.vidioc_g_fmt_vid_out			= vidioc_g_fmt_vid_out,
 	.vidioc_try_fmt_vid_out			= vidioc_try_fmt_vid_out,
 	.vidioc_s_fmt_vid_out			= vidioc_s_fmt_vid_out,
-	.vidioc_queryctrl    			= vidioc_queryctrl,
-	.vidioc_g_ctrl       			= vidioc_g_ctrl,
 	.vidioc_s_fbuf				= vidioc_s_fbuf,
 	.vidioc_g_fbuf				= vidioc_g_fbuf,
-	.vidioc_s_ctrl       			= vidioc_s_ctrl,
 	.vidioc_try_fmt_vid_out_overlay		= vidioc_try_fmt_vid_overlay,
 	.vidioc_s_fmt_vid_out_overlay		= vidioc_s_fmt_vid_overlay,
 	.vidioc_g_fmt_vid_out_overlay		= vidioc_g_fmt_vid_overlay,
@@ -1865,9 +1806,9 @@ static int __init omap_vout_setup_video_data(struct omap_vout_device *vout)
 {
 	struct video_device *vfd;
 	struct v4l2_pix_format *pix;
-	struct v4l2_control *control;
 	struct omap_overlay *ovl = vout->vid_info.overlays[0];
 	struct omap_dss_device *display = ovl->get_device(ovl);
+	struct v4l2_ctrl_handler *hdl;
 
 	/* set the default pix */
 	pix = &vout->pix;
@@ -1896,29 +1837,32 @@ static int __init omap_vout_setup_video_data(struct omap_vout_device *vout)
 
 	omap_vout_new_format(pix, &vout->fbuf, &vout->crop, &vout->win);
 
-	/*Initialize the control variables for
-	  rotation, flipping and background color. */
-	control = vout->control;
-	control[0].id = V4L2_CID_ROTATE;
-	control[0].value = 0;
+	hdl = &vout->ctrl_handler;
+	v4l2_ctrl_handler_init(hdl, 3);
+	v4l2_ctrl_new_std(hdl, &omap_vout_ctrl_ops,
+			  V4L2_CID_ROTATE, 0, 270, 90, 0);
+	v4l2_ctrl_new_std(hdl, &omap_vout_ctrl_ops,
+			  V4L2_CID_BG_COLOR, 0, 0xffffff, 1, 0);
+	v4l2_ctrl_new_std(hdl, &omap_vout_ctrl_ops,
+			  V4L2_CID_VFLIP, 0, 1, 1, 0);
+	if (hdl->error)
+		return hdl->error;
+
 	vout->rotation = 0;
 	vout->mirror = false;
-	vout->control[2].id = V4L2_CID_HFLIP;
-	vout->control[2].value = 0;
 	if (vout->vid_info.rotation_type == VOUT_ROT_VRFB)
 		vout->vrfb_bpp = 2;
 
-	control[1].id = V4L2_CID_BG_COLOR;
-	control[1].value = 0;
-
 	/* initialize the video_device struct */
 	vfd = vout->vfd = video_device_alloc();
 
 	if (!vfd) {
 		printk(KERN_ERR VOUT_NAME ": could not allocate"
 				" video device struct\n");
+		v4l2_ctrl_handler_free(hdl);
 		return -ENOMEM;
 	}
+	vfd->ctrl_handler = hdl;
 	vfd->release = video_device_release;
 	vfd->ioctl_ops = &vout_ioctl_ops;
 
@@ -2092,6 +2036,7 @@ static void omap_vout_cleanup_device(struct omap_vout_device *vout)
 			video_unregister_device(vfd);
 		}
 	}
+	v4l2_ctrl_handler_free(&vout->ctrl_handler);
 	if (ovid->rotation_type == VOUT_ROT_VRFB) {
 		omap_vout_release_vrfb(vout);
 		/* Free the VRFB buffer if allocated
diff --git a/drivers/media/platform/omap/omap_voutdef.h b/drivers/media/platform/omap/omap_voutdef.h
index 9ccfe1f475a4..49de1475e473 100644
--- a/drivers/media/platform/omap/omap_voutdef.h
+++ b/drivers/media/platform/omap/omap_voutdef.h
@@ -11,6 +11,7 @@
 #ifndef OMAP_VOUTDEF_H
 #define OMAP_VOUTDEF_H
 
+#include <media/v4l2-ctrls.h>
 #include <video/omapdss.h>
 #include <video/omapvrfb.h>
 
@@ -116,6 +117,7 @@ struct omap_vout_device {
 	struct omapvideo_info vid_info;
 	struct video_device *vfd;
 	struct omap2video_device *vid_dev;
+	struct v4l2_ctrl_handler ctrl_handler;
 	int vid;
 	int opened;
 
@@ -149,12 +151,9 @@ struct omap_vout_device {
 	/* Lock to protect the shared data structures in ioctl */
 	struct mutex lock;
 
-	/* V4L2 control structure for different control id */
-	struct v4l2_control control[MAX_CID];
 	enum dss_rotation rotation;
 	bool mirror;
 	int flicker_filter;
-	/* V4L2 control structure for different control id */
 
 	int bpp; /* bytes per pixel */
 	int vrfb_bpp; /* bytes per pixel with respect to VRFB */
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index 1b1a95d546f6..7d9f35976d18 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -331,7 +331,7 @@ isp_video_check_format(struct isp_video *video, struct isp_video_fh *vfh)
 
 static int isp_video_queue_setup(struct vb2_queue *queue,
 				 unsigned int *count, unsigned int *num_planes,
-				 unsigned int sizes[], void *alloc_ctxs[])
+				 unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct isp_video_fh *vfh = vb2_get_drv_priv(queue);
 	struct isp_video *video = vfh->video;
@@ -342,8 +342,6 @@ static int isp_video_queue_setup(struct vb2_queue *queue,
 	if (sizes[0] == 0)
 		return -EINVAL;
 
-	alloc_ctxs[0] = video->alloc_ctx;
-
 	*count = min(*count, video->capture_mem / PAGE_ALIGN(sizes[0]));
 
 	return 0;
@@ -1308,6 +1306,7 @@ static int isp_video_open(struct file *file)
 	queue->mem_ops = &vb2_dma_contig_memops;
 	queue->buf_struct_size = sizeof(struct isp_buffer);
 	queue->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	queue->dev = video->isp->dev;
 
 	ret = vb2_queue_init(&handle->queue);
 	if (ret < 0) {
@@ -1414,15 +1413,9 @@ int omap3isp_video_init(struct isp_video *video, const char *name)
 		return -EINVAL;
 	}
 
-	video->alloc_ctx = vb2_dma_contig_init_ctx(video->isp->dev);
-	if (IS_ERR(video->alloc_ctx))
-		return PTR_ERR(video->alloc_ctx);
-
 	ret = media_entity_pads_init(&video->video.entity, 1, &video->pad);
-	if (ret < 0) {
-		vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
+	if (ret < 0)
 		return ret;
-	}
 
 	mutex_init(&video->mutex);
 	atomic_set(&video->active, 0);
@@ -1451,7 +1444,6 @@ int omap3isp_video_init(struct isp_video *video, const char *name)
 
 void omap3isp_video_cleanup(struct isp_video *video)
 {
-	vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 	media_entity_cleanup(&video->video.entity);
 	mutex_destroy(&video->queue_lock);
 	mutex_destroy(&video->stream_lock);
diff --git a/drivers/media/platform/omap3isp/ispvideo.h b/drivers/media/platform/omap3isp/ispvideo.h
index 6a48d5879c56..f6a2082b4a0a 100644
--- a/drivers/media/platform/omap3isp/ispvideo.h
+++ b/drivers/media/platform/omap3isp/ispvideo.h
@@ -171,7 +171,6 @@ struct isp_video {
 	bool error;
 
 	/* Video buffers queue */
-	void *alloc_ctx;
 	struct vb2_queue *queue;
 	struct mutex queue_lock;	/* protects the queue */
 	spinlock_t irqlock;		/* protects dmaqueue */
diff --git a/drivers/media/platform/rcar-fcp.c b/drivers/media/platform/rcar-fcp.c
new file mode 100644
index 000000000000..6a7bcc3028b1
--- /dev/null
+++ b/drivers/media/platform/rcar-fcp.c
@@ -0,0 +1,181 @@
+/*
+ * rcar-fcp.c  --  R-Car Frame Compression Processor Driver
+ *
+ * Copyright (C) 2016 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+
+#include <media/rcar-fcp.h>
+
+struct rcar_fcp_device {
+	struct list_head list;
+	struct device *dev;
+};
+
+static LIST_HEAD(fcp_devices);
+static DEFINE_MUTEX(fcp_lock);
+
+/* -----------------------------------------------------------------------------
+ * Public API
+ */
+
+/**
+ * rcar_fcp_get - Find and acquire a reference to an FCP instance
+ * @np: Device node of the FCP instance
+ *
+ * Search the list of registered FCP instances for the instance corresponding to
+ * the given device node.
+ *
+ * Return a pointer to the FCP instance, or an ERR_PTR if the instance can't be
+ * found.
+ */
+struct rcar_fcp_device *rcar_fcp_get(const struct device_node *np)
+{
+	struct rcar_fcp_device *fcp;
+
+	mutex_lock(&fcp_lock);
+
+	list_for_each_entry(fcp, &fcp_devices, list) {
+		if (fcp->dev->of_node != np)
+			continue;
+
+		/*
+		 * Make sure the module won't be unloaded behind our back. This
+		 * is a poor man's safety net, the module should really not be
+		 * unloaded while FCP users can be active.
+		 */
+		if (!try_module_get(fcp->dev->driver->owner))
+			fcp = NULL;
+
+		goto done;
+	}
+
+	fcp = ERR_PTR(-EPROBE_DEFER);
+
+done:
+	mutex_unlock(&fcp_lock);
+	return fcp;
+}
+EXPORT_SYMBOL_GPL(rcar_fcp_get);
+
+/**
+ * rcar_fcp_put - Release a reference to an FCP instance
+ * @fcp: The FCP instance
+ *
+ * Release the FCP instance acquired by a call to rcar_fcp_get().
+ */
+void rcar_fcp_put(struct rcar_fcp_device *fcp)
+{
+	if (fcp)
+		module_put(fcp->dev->driver->owner);
+}
+EXPORT_SYMBOL_GPL(rcar_fcp_put);
+
+/**
+ * rcar_fcp_enable - Enable an FCP
+ * @fcp: The FCP instance
+ *
+ * Before any memory access through an FCP is performed by a module, the FCP
+ * must be enabled by a call to this function. The enable calls are reference
+ * counted, each successful call must be followed by one rcar_fcp_disable()
+ * call when no more memory transfer can occur through the FCP.
+ *
+ * Return 0 on success or a negative error code if an error occurs. The enable
+ * reference count isn't increased when this function returns an error.
+ */
+int rcar_fcp_enable(struct rcar_fcp_device *fcp)
+{
+	if (!fcp)
+		return 0;
+
+	return pm_runtime_get_sync(fcp->dev);
+}
+EXPORT_SYMBOL_GPL(rcar_fcp_enable);
+
+/**
+ * rcar_fcp_disable - Disable an FCP
+ * @fcp: The FCP instance
+ *
+ * This function is the counterpart of rcar_fcp_enable(). As enable calls are
+ * reference counted a disable call may not disable the FCP synchronously.
+ */
+void rcar_fcp_disable(struct rcar_fcp_device *fcp)
+{
+	if (fcp)
+		pm_runtime_put(fcp->dev);
+}
+EXPORT_SYMBOL_GPL(rcar_fcp_disable);
+
+/* -----------------------------------------------------------------------------
+ * Platform Driver
+ */
+
+static int rcar_fcp_probe(struct platform_device *pdev)
+{
+	struct rcar_fcp_device *fcp;
+
+	fcp = devm_kzalloc(&pdev->dev, sizeof(*fcp), GFP_KERNEL);
+	if (fcp == NULL)
+		return -ENOMEM;
+
+	fcp->dev = &pdev->dev;
+
+	pm_runtime_enable(&pdev->dev);
+
+	mutex_lock(&fcp_lock);
+	list_add_tail(&fcp->list, &fcp_devices);
+	mutex_unlock(&fcp_lock);
+
+	platform_set_drvdata(pdev, fcp);
+
+	return 0;
+}
+
+static int rcar_fcp_remove(struct platform_device *pdev)
+{
+	struct rcar_fcp_device *fcp = platform_get_drvdata(pdev);
+
+	mutex_lock(&fcp_lock);
+	list_del(&fcp->list);
+	mutex_unlock(&fcp_lock);
+
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id rcar_fcp_of_match[] = {
+	{ .compatible = "renesas,fcpv" },
+	{ },
+};
+
+static struct platform_driver rcar_fcp_platform_driver = {
+	.probe		= rcar_fcp_probe,
+	.remove		= rcar_fcp_remove,
+	.driver		= {
+		.name	= "rcar-fcp",
+		.of_match_table = rcar_fcp_of_match,
+		.suppress_bind_attrs = true,
+	},
+};
+
+module_platform_driver(rcar_fcp_platform_driver);
+
+MODULE_ALIAS("rcar-fcp");
+MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
+MODULE_DESCRIPTION("Renesas FCP Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/rcar-vin/Kconfig b/drivers/media/platform/rcar-vin/Kconfig
new file mode 100644
index 000000000000..b2ff2d4e8bb1
--- /dev/null
+++ b/drivers/media/platform/rcar-vin/Kconfig
@@ -0,0 +1,11 @@
+config VIDEO_RCAR_VIN
+	tristate "R-Car Video Input (VIN) Driver"
+	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && OF && HAS_DMA
+	depends on ARCH_RENESAS || COMPILE_TEST
+	select VIDEOBUF2_DMA_CONTIG
+	---help---
+	  Support for Renesas R-Car Video Input (VIN) driver.
+	  Supports R-Car Gen2 SoCs.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called rcar-vin.
diff --git a/drivers/media/platform/rcar-vin/Makefile b/drivers/media/platform/rcar-vin/Makefile
new file mode 100644
index 000000000000..48c5632c21dc
--- /dev/null
+++ b/drivers/media/platform/rcar-vin/Makefile
@@ -0,0 +1,3 @@
+rcar-vin-objs = rcar-core.o rcar-dma.o rcar-v4l2.o
+
+obj-$(CONFIG_VIDEO_RCAR_VIN) += rcar-vin.o
diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
new file mode 100644
index 000000000000..4b2007b73463
--- /dev/null
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -0,0 +1,334 @@
+/*
+ * Driver for Renesas R-Car VIN
+ *
+ * Copyright (C) 2016 Renesas Electronics Corp.
+ * Copyright (C) 2011-2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Cogent Embedded, Inc., <source@cogentembedded.com>
+ * Copyright (C) 2008 Magnus Damm
+ *
+ * Based on the soc-camera rcar_vin driver
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_graph.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include <media/v4l2-of.h>
+
+#include "rcar-vin.h"
+
+/* -----------------------------------------------------------------------------
+ * Async notifier
+ */
+
+#define notifier_to_vin(n) container_of(n, struct rvin_dev, notifier)
+
+static int rvin_mbus_supported(struct rvin_dev *vin)
+{
+	struct v4l2_subdev *sd;
+	struct v4l2_subdev_mbus_code_enum code = {
+		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
+	};
+
+	sd = vin_to_source(vin);
+
+	code.index = 0;
+	while (!v4l2_subdev_call(sd, pad, enum_mbus_code, NULL, &code)) {
+		code.index++;
+		switch (code.code) {
+		case MEDIA_BUS_FMT_YUYV8_1X16:
+		case MEDIA_BUS_FMT_YUYV8_2X8:
+		case MEDIA_BUS_FMT_YUYV10_2X10:
+		case MEDIA_BUS_FMT_RGB888_1X24:
+			vin->source.code = code.code;
+			vin_dbg(vin, "Found supported media bus format: %d\n",
+				vin->source.code);
+			return true;
+		default:
+			break;
+		}
+	}
+
+	return false;
+}
+
+static int rvin_graph_notify_complete(struct v4l2_async_notifier *notifier)
+{
+	struct rvin_dev *vin = notifier_to_vin(notifier);
+	int ret;
+
+	ret = v4l2_device_register_subdev_nodes(&vin->v4l2_dev);
+	if (ret < 0) {
+		vin_err(vin, "Failed to register subdev nodes\n");
+		return ret;
+	}
+
+	if (!rvin_mbus_supported(vin)) {
+		vin_err(vin, "No supported mediabus format found\n");
+		return -EINVAL;
+	}
+
+	return rvin_v4l2_probe(vin);
+}
+
+static void rvin_graph_notify_unbind(struct v4l2_async_notifier *notifier,
+				     struct v4l2_subdev *sd,
+				     struct v4l2_async_subdev *asd)
+{
+	struct rvin_dev *vin = notifier_to_vin(notifier);
+
+	rvin_v4l2_remove(vin);
+}
+
+static int rvin_graph_notify_bound(struct v4l2_async_notifier *notifier,
+				   struct v4l2_subdev *subdev,
+				   struct v4l2_async_subdev *asd)
+{
+	struct rvin_dev *vin = notifier_to_vin(notifier);
+
+	vin_dbg(vin, "subdev %s bound\n", subdev->name);
+
+	vin->entity.entity = &subdev->entity;
+	vin->entity.subdev = subdev;
+
+	return 0;
+}
+
+static int rvin_graph_parse(struct rvin_dev *vin,
+			    struct device_node *node)
+{
+	struct device_node *remote;
+	struct device_node *ep = NULL;
+	struct device_node *next;
+	int ret = 0;
+
+	while (1) {
+		next = of_graph_get_next_endpoint(node, ep);
+		if (!next)
+			break;
+
+		of_node_put(ep);
+		ep = next;
+
+		remote = of_graph_get_remote_port_parent(ep);
+		if (!remote) {
+			ret = -EINVAL;
+			break;
+		}
+
+		/* Skip entities that we have already processed. */
+		if (remote == vin->dev->of_node) {
+			of_node_put(remote);
+			continue;
+		}
+
+		/* Remote node to connect */
+		if (!vin->entity.node) {
+			vin->entity.node = remote;
+			vin->entity.asd.match_type = V4L2_ASYNC_MATCH_OF;
+			vin->entity.asd.match.of.node = remote;
+			ret++;
+		}
+	}
+
+	of_node_put(ep);
+
+	return ret;
+}
+
+static int rvin_graph_init(struct rvin_dev *vin)
+{
+	struct v4l2_async_subdev **subdevs = NULL;
+	int ret;
+
+	/* Parse the graph to extract a list of subdevice DT nodes. */
+	ret = rvin_graph_parse(vin, vin->dev->of_node);
+	if (ret < 0) {
+		vin_err(vin, "Graph parsing failed\n");
+		goto done;
+	}
+
+	if (!ret) {
+		vin_err(vin, "No subdev found in graph\n");
+		goto done;
+	}
+
+	if (ret != 1) {
+		vin_err(vin, "More then one subdev found in graph\n");
+		goto done;
+	}
+
+	/* Register the subdevices notifier. */
+	subdevs = devm_kzalloc(vin->dev, sizeof(*subdevs), GFP_KERNEL);
+	if (subdevs == NULL) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	subdevs[0] = &vin->entity.asd;
+
+	vin->notifier.subdevs = subdevs;
+	vin->notifier.num_subdevs = 1;
+	vin->notifier.bound = rvin_graph_notify_bound;
+	vin->notifier.unbind = rvin_graph_notify_unbind;
+	vin->notifier.complete = rvin_graph_notify_complete;
+
+	ret = v4l2_async_notifier_register(&vin->v4l2_dev, &vin->notifier);
+	if (ret < 0) {
+		vin_err(vin, "Notifier registration failed\n");
+		goto done;
+	}
+
+	ret = 0;
+
+done:
+	if (ret < 0) {
+		v4l2_async_notifier_unregister(&vin->notifier);
+		of_node_put(vin->entity.node);
+	}
+
+	return ret;
+}
+
+/* -----------------------------------------------------------------------------
+ * Platform Device Driver
+ */
+
+static const struct of_device_id rvin_of_id_table[] = {
+	{ .compatible = "renesas,vin-r8a7794", .data = (void *)RCAR_GEN2 },
+	{ .compatible = "renesas,vin-r8a7793", .data = (void *)RCAR_GEN2 },
+	{ .compatible = "renesas,vin-r8a7791", .data = (void *)RCAR_GEN2 },
+	{ .compatible = "renesas,vin-r8a7790", .data = (void *)RCAR_GEN2 },
+	{ .compatible = "renesas,vin-r8a7779", .data = (void *)RCAR_H1 },
+	{ .compatible = "renesas,vin-r8a7778", .data = (void *)RCAR_M1 },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rvin_of_id_table);
+
+static int rvin_parse_dt(struct rvin_dev *vin)
+{
+	const struct of_device_id *match;
+	struct v4l2_of_endpoint ep;
+	struct device_node *np;
+	int ret;
+
+	match = of_match_device(of_match_ptr(rvin_of_id_table), vin->dev);
+	if (!match)
+		return -ENODEV;
+
+	vin->chip = (enum chip_id)match->data;
+
+	np = of_graph_get_next_endpoint(vin->dev->of_node, NULL);
+	if (!np) {
+		vin_err(vin, "Could not find endpoint\n");
+		return -EINVAL;
+	}
+
+	ret = v4l2_of_parse_endpoint(np, &ep);
+	if (ret) {
+		vin_err(vin, "Could not parse endpoint\n");
+		return ret;
+	}
+
+	of_node_put(np);
+
+	vin->mbus_cfg.type = ep.bus_type;
+
+	switch (vin->mbus_cfg.type) {
+	case V4L2_MBUS_PARALLEL:
+		vin->mbus_cfg.flags = ep.bus.parallel.flags;
+		break;
+	case V4L2_MBUS_BT656:
+		vin->mbus_cfg.flags = 0;
+		break;
+	default:
+		vin_err(vin, "Unknown media bus type\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rcar_vin_probe(struct platform_device *pdev)
+{
+	struct rvin_dev *vin;
+	struct resource *mem;
+	int irq, ret;
+
+	vin = devm_kzalloc(&pdev->dev, sizeof(*vin), GFP_KERNEL);
+	if (!vin)
+		return -ENOMEM;
+
+	vin->dev = &pdev->dev;
+
+	ret = rvin_parse_dt(vin);
+	if (ret)
+		return ret;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (mem == NULL)
+		return -EINVAL;
+
+	vin->base = devm_ioremap_resource(vin->dev, mem);
+	if (IS_ERR(vin->base))
+		return PTR_ERR(vin->base);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0)
+		return ret;
+
+	ret = rvin_dma_probe(vin, irq);
+	if (ret)
+		return ret;
+
+	ret = rvin_graph_init(vin);
+	if (ret < 0)
+		goto error;
+
+	pm_suspend_ignore_children(&pdev->dev, true);
+	pm_runtime_enable(&pdev->dev);
+
+	platform_set_drvdata(pdev, vin);
+
+	return 0;
+error:
+	rvin_dma_remove(vin);
+
+	return ret;
+}
+
+static int rcar_vin_remove(struct platform_device *pdev)
+{
+	struct rvin_dev *vin = platform_get_drvdata(pdev);
+
+	pm_runtime_disable(&pdev->dev);
+
+	v4l2_async_notifier_unregister(&vin->notifier);
+
+	rvin_dma_remove(vin);
+
+	return 0;
+}
+
+static struct platform_driver rcar_vin_driver = {
+	.driver = {
+		.name = "rcar-vin",
+		.of_match_table = rvin_of_id_table,
+	},
+	.probe = rcar_vin_probe,
+	.remove = rcar_vin_remove,
+};
+
+module_platform_driver(rcar_vin_driver);
+
+MODULE_AUTHOR("Niklas Söderlund <niklas.soderlund@ragnatech.se>");
+MODULE_DESCRIPTION("Renesas R-Car VIN camera host driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
new file mode 100644
index 000000000000..496aa97b6400
--- /dev/null
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -0,0 +1,1187 @@
+/*
+ * Driver for Renesas R-Car VIN
+ *
+ * Copyright (C) 2016 Renesas Electronics Corp.
+ * Copyright (C) 2011-2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Cogent Embedded, Inc., <source@cogentembedded.com>
+ * Copyright (C) 2008 Magnus Damm
+ *
+ * Based on the soc-camera rcar_vin driver
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+
+#include <media/videobuf2-dma-contig.h>
+
+#include "rcar-vin.h"
+
+/* -----------------------------------------------------------------------------
+ * HW Functions
+ */
+
+/* Register offsets for R-Car VIN */
+#define VNMC_REG	0x00	/* Video n Main Control Register */
+#define VNMS_REG	0x04	/* Video n Module Status Register */
+#define VNFC_REG	0x08	/* Video n Frame Capture Register */
+#define VNSLPRC_REG	0x0C	/* Video n Start Line Pre-Clip Register */
+#define VNELPRC_REG	0x10	/* Video n End Line Pre-Clip Register */
+#define VNSPPRC_REG	0x14	/* Video n Start Pixel Pre-Clip Register */
+#define VNEPPRC_REG	0x18	/* Video n End Pixel Pre-Clip Register */
+#define VNSLPOC_REG	0x1C	/* Video n Start Line Post-Clip Register */
+#define VNELPOC_REG	0x20	/* Video n End Line Post-Clip Register */
+#define VNSPPOC_REG	0x24	/* Video n Start Pixel Post-Clip Register */
+#define VNEPPOC_REG	0x28	/* Video n End Pixel Post-Clip Register */
+#define VNIS_REG	0x2C	/* Video n Image Stride Register */
+#define VNMB_REG(m)	(0x30 + ((m) << 2)) /* Video n Memory Base m Register */
+#define VNIE_REG	0x40	/* Video n Interrupt Enable Register */
+#define VNINTS_REG	0x44	/* Video n Interrupt Status Register */
+#define VNSI_REG	0x48	/* Video n Scanline Interrupt Register */
+#define VNMTC_REG	0x4C	/* Video n Memory Transfer Control Register */
+#define VNYS_REG	0x50	/* Video n Y Scale Register */
+#define VNXS_REG	0x54	/* Video n X Scale Register */
+#define VNDMR_REG	0x58	/* Video n Data Mode Register */
+#define VNDMR2_REG	0x5C	/* Video n Data Mode Register 2 */
+#define VNUVAOF_REG	0x60	/* Video n UV Address Offset Register */
+#define VNC1A_REG	0x80	/* Video n Coefficient Set C1A Register */
+#define VNC1B_REG	0x84	/* Video n Coefficient Set C1B Register */
+#define VNC1C_REG	0x88	/* Video n Coefficient Set C1C Register */
+#define VNC2A_REG	0x90	/* Video n Coefficient Set C2A Register */
+#define VNC2B_REG	0x94	/* Video n Coefficient Set C2B Register */
+#define VNC2C_REG	0x98	/* Video n Coefficient Set C2C Register */
+#define VNC3A_REG	0xA0	/* Video n Coefficient Set C3A Register */
+#define VNC3B_REG	0xA4	/* Video n Coefficient Set C3B Register */
+#define VNC3C_REG	0xA8	/* Video n Coefficient Set C3C Register */
+#define VNC4A_REG	0xB0	/* Video n Coefficient Set C4A Register */
+#define VNC4B_REG	0xB4	/* Video n Coefficient Set C4B Register */
+#define VNC4C_REG	0xB8	/* Video n Coefficient Set C4C Register */
+#define VNC5A_REG	0xC0	/* Video n Coefficient Set C5A Register */
+#define VNC5B_REG	0xC4	/* Video n Coefficient Set C5B Register */
+#define VNC5C_REG	0xC8	/* Video n Coefficient Set C5C Register */
+#define VNC6A_REG	0xD0	/* Video n Coefficient Set C6A Register */
+#define VNC6B_REG	0xD4	/* Video n Coefficient Set C6B Register */
+#define VNC6C_REG	0xD8	/* Video n Coefficient Set C6C Register */
+#define VNC7A_REG	0xE0	/* Video n Coefficient Set C7A Register */
+#define VNC7B_REG	0xE4	/* Video n Coefficient Set C7B Register */
+#define VNC7C_REG	0xE8	/* Video n Coefficient Set C7C Register */
+#define VNC8A_REG	0xF0	/* Video n Coefficient Set C8A Register */
+#define VNC8B_REG	0xF4	/* Video n Coefficient Set C8B Register */
+#define VNC8C_REG	0xF8	/* Video n Coefficient Set C8C Register */
+
+
+/* Register bit fields for R-Car VIN */
+/* Video n Main Control Register bits */
+#define VNMC_FOC		(1 << 21)
+#define VNMC_YCAL		(1 << 19)
+#define VNMC_INF_YUV8_BT656	(0 << 16)
+#define VNMC_INF_YUV8_BT601	(1 << 16)
+#define VNMC_INF_YUV10_BT656	(2 << 16)
+#define VNMC_INF_YUV10_BT601	(3 << 16)
+#define VNMC_INF_YUV16		(5 << 16)
+#define VNMC_INF_RGB888		(6 << 16)
+#define VNMC_VUP		(1 << 10)
+#define VNMC_IM_ODD		(0 << 3)
+#define VNMC_IM_ODD_EVEN	(1 << 3)
+#define VNMC_IM_EVEN		(2 << 3)
+#define VNMC_IM_FULL		(3 << 3)
+#define VNMC_BPS		(1 << 1)
+#define VNMC_ME			(1 << 0)
+
+/* Video n Module Status Register bits */
+#define VNMS_FBS_MASK		(3 << 3)
+#define VNMS_FBS_SHIFT		3
+#define VNMS_AV			(1 << 1)
+#define VNMS_CA			(1 << 0)
+
+/* Video n Frame Capture Register bits */
+#define VNFC_C_FRAME		(1 << 1)
+#define VNFC_S_FRAME		(1 << 0)
+
+/* Video n Interrupt Enable Register bits */
+#define VNIE_FIE		(1 << 4)
+#define VNIE_EFE		(1 << 1)
+
+/* Video n Data Mode Register bits */
+#define VNDMR_EXRGB		(1 << 8)
+#define VNDMR_BPSM		(1 << 4)
+#define VNDMR_DTMD_YCSEP	(1 << 1)
+#define VNDMR_DTMD_ARGB1555	(1 << 0)
+
+/* Video n Data Mode Register 2 bits */
+#define VNDMR2_VPS		(1 << 30)
+#define VNDMR2_HPS		(1 << 29)
+#define VNDMR2_FTEV		(1 << 17)
+#define VNDMR2_VLV(n)		((n & 0xf) << 12)
+
+static void rvin_write(struct rvin_dev *vin, u32 value, u32 offset)
+{
+	iowrite32(value, vin->base + offset);
+}
+
+static u32 rvin_read(struct rvin_dev *vin, u32 offset)
+{
+	return ioread32(vin->base + offset);
+}
+
+static int rvin_setup(struct rvin_dev *vin)
+{
+	u32 vnmc, dmr, dmr2, interrupts;
+	bool progressive = false, output_is_yuv = false, input_is_yuv = false;
+
+	switch (vin->format.field) {
+	case V4L2_FIELD_TOP:
+		vnmc = VNMC_IM_ODD;
+		break;
+	case V4L2_FIELD_BOTTOM:
+		vnmc = VNMC_IM_EVEN;
+		break;
+	case V4L2_FIELD_INTERLACED:
+	case V4L2_FIELD_INTERLACED_TB:
+		vnmc = VNMC_IM_FULL;
+		break;
+	case V4L2_FIELD_INTERLACED_BT:
+		vnmc = VNMC_IM_FULL | VNMC_FOC;
+		break;
+	case V4L2_FIELD_NONE:
+		if (vin->continuous) {
+			vnmc = VNMC_IM_ODD_EVEN;
+			progressive = true;
+		} else {
+			vnmc = VNMC_IM_ODD;
+		}
+		break;
+	default:
+		vnmc = VNMC_IM_ODD;
+		break;
+	}
+
+	/*
+	 * Input interface
+	 */
+	switch (vin->source.code) {
+	case MEDIA_BUS_FMT_YUYV8_1X16:
+		/* BT.601/BT.1358 16bit YCbCr422 */
+		vnmc |= VNMC_INF_YUV16;
+		input_is_yuv = true;
+		break;
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		/* BT.656 8bit YCbCr422 or BT.601 8bit YCbCr422 */
+		vnmc |= vin->mbus_cfg.type == V4L2_MBUS_BT656 ?
+			VNMC_INF_YUV8_BT656 : VNMC_INF_YUV8_BT601;
+		input_is_yuv = true;
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X24:
+		vnmc |= VNMC_INF_RGB888;
+		break;
+	case MEDIA_BUS_FMT_YUYV10_2X10:
+		/* BT.656 10bit YCbCr422 or BT.601 10bit YCbCr422 */
+		vnmc |= vin->mbus_cfg.type == V4L2_MBUS_BT656 ?
+			VNMC_INF_YUV10_BT656 : VNMC_INF_YUV10_BT601;
+		input_is_yuv = true;
+		break;
+	default:
+		break;
+	}
+
+	/* Enable VSYNC Field Toogle mode after one VSYNC input */
+	dmr2 = VNDMR2_FTEV | VNDMR2_VLV(1);
+
+	/* Hsync Signal Polarity Select */
+	if (!(vin->mbus_cfg.flags & V4L2_MBUS_HSYNC_ACTIVE_LOW))
+		dmr2 |= VNDMR2_HPS;
+
+	/* Vsync Signal Polarity Select */
+	if (!(vin->mbus_cfg.flags & V4L2_MBUS_VSYNC_ACTIVE_LOW))
+		dmr2 |= VNDMR2_VPS;
+
+	/*
+	 * Output format
+	 */
+	switch (vin->format.pixelformat) {
+	case V4L2_PIX_FMT_NV16:
+		rvin_write(vin,
+			   ALIGN(vin->format.width * vin->format.height, 0x80),
+			   VNUVAOF_REG);
+		dmr = VNDMR_DTMD_YCSEP;
+		output_is_yuv = true;
+		break;
+	case V4L2_PIX_FMT_YUYV:
+		dmr = VNDMR_BPSM;
+		output_is_yuv = true;
+		break;
+	case V4L2_PIX_FMT_UYVY:
+		dmr = 0;
+		output_is_yuv = true;
+		break;
+	case V4L2_PIX_FMT_XRGB555:
+		dmr = VNDMR_DTMD_ARGB1555;
+		break;
+	case V4L2_PIX_FMT_RGB565:
+		dmr = 0;
+		break;
+	case V4L2_PIX_FMT_XBGR32:
+		if (vin->chip == RCAR_GEN2 || vin->chip == RCAR_H1) {
+			dmr = VNDMR_EXRGB;
+			break;
+		}
+		/* fall through */
+	default:
+		vin_err(vin, "Invalid pixelformat (0x%x)\n",
+			vin->format.pixelformat);
+		return -EINVAL;
+	}
+
+	/* Always update on field change */
+	vnmc |= VNMC_VUP;
+
+	/* If input and output use the same colorspace, use bypass mode */
+	if (input_is_yuv == output_is_yuv)
+		vnmc |= VNMC_BPS;
+
+	/* Progressive or interlaced mode */
+	interrupts = progressive ? VNIE_FIE : VNIE_EFE;
+
+	/* Ack interrupts */
+	rvin_write(vin, interrupts, VNINTS_REG);
+	/* Enable interrupts */
+	rvin_write(vin, interrupts, VNIE_REG);
+	/* Start capturing */
+	rvin_write(vin, dmr, VNDMR_REG);
+	rvin_write(vin, dmr2, VNDMR2_REG);
+
+	/* Enable module */
+	rvin_write(vin, vnmc | VNMC_ME, VNMC_REG);
+
+	return 0;
+}
+
+static void rvin_capture_on(struct rvin_dev *vin)
+{
+	vin_dbg(vin, "Capture on in %s mode\n",
+		vin->continuous ? "continuous" : "single");
+
+	if (vin->continuous)
+		/* Continuous Frame Capture Mode */
+		rvin_write(vin, VNFC_C_FRAME, VNFC_REG);
+	else
+		/* Single Frame Capture Mode */
+		rvin_write(vin, VNFC_S_FRAME, VNFC_REG);
+}
+
+static void rvin_capture_off(struct rvin_dev *vin)
+{
+	/* Set continuous & single transfer off */
+	rvin_write(vin, 0, VNFC_REG);
+}
+
+static int rvin_capture_start(struct rvin_dev *vin)
+{
+	int ret;
+
+	rvin_crop_scale_comp(vin);
+
+	ret = rvin_setup(vin);
+	if (ret)
+		return ret;
+
+	rvin_capture_on(vin);
+
+	return 0;
+}
+
+static void rvin_capture_stop(struct rvin_dev *vin)
+{
+	rvin_capture_off(vin);
+
+	/* Disable module */
+	rvin_write(vin, rvin_read(vin, VNMC_REG) & ~VNMC_ME, VNMC_REG);
+}
+
+static void rvin_disable_interrupts(struct rvin_dev *vin)
+{
+	rvin_write(vin, 0, VNIE_REG);
+}
+
+static u32 rvin_get_interrupt_status(struct rvin_dev *vin)
+{
+	return rvin_read(vin, VNINTS_REG);
+}
+
+static void rvin_ack_interrupt(struct rvin_dev *vin)
+{
+	rvin_write(vin, rvin_read(vin, VNINTS_REG), VNINTS_REG);
+}
+
+static bool rvin_capture_active(struct rvin_dev *vin)
+{
+	return rvin_read(vin, VNMS_REG) & VNMS_CA;
+}
+
+static int rvin_get_active_slot(struct rvin_dev *vin)
+{
+	if (vin->continuous)
+		return (rvin_read(vin, VNMS_REG) & VNMS_FBS_MASK)
+			>> VNMS_FBS_SHIFT;
+
+	return 0;
+}
+
+static void rvin_set_slot_addr(struct rvin_dev *vin, int slot, dma_addr_t addr)
+{
+	const struct rvin_video_format *fmt;
+	int offsetx, offsety;
+	dma_addr_t offset;
+
+	fmt = rvin_format_from_pixel(vin->format.pixelformat);
+
+	/*
+	 * There is no HW support for composition do the beast we can
+	 * by modifying the buffer offset
+	 */
+	offsetx = vin->compose.left * fmt->bpp;
+	offsety = vin->compose.top * vin->format.bytesperline;
+	offset = addr + offsetx + offsety;
+
+	/*
+	 * The address needs to be 128 bytes aligned. Driver should never accept
+	 * settings that do not satisfy this in the first place...
+	 */
+	if (WARN_ON((offsetx | offsety | offset) & HW_BUFFER_MASK))
+		return;
+
+	rvin_write(vin, offset, VNMB_REG(slot));
+}
+
+/* -----------------------------------------------------------------------------
+ * Crop and Scaling Gen2
+ */
+
+struct vin_coeff {
+	unsigned short xs_value;
+	u32 coeff_set[24];
+};
+
+static const struct vin_coeff vin_coeff_set[] = {
+	{ 0x0000, {
+			  0x00000000, 0x00000000, 0x00000000,
+			  0x00000000, 0x00000000, 0x00000000,
+			  0x00000000, 0x00000000, 0x00000000,
+			  0x00000000, 0x00000000, 0x00000000,
+			  0x00000000, 0x00000000, 0x00000000,
+			  0x00000000, 0x00000000, 0x00000000,
+			  0x00000000, 0x00000000, 0x00000000,
+			  0x00000000, 0x00000000, 0x00000000 },
+	},
+	{ 0x1000, {
+			  0x000fa400, 0x000fa400, 0x09625902,
+			  0x000003f8, 0x00000403, 0x3de0d9f0,
+			  0x001fffed, 0x00000804, 0x3cc1f9c3,
+			  0x001003de, 0x00000c01, 0x3cb34d7f,
+			  0x002003d2, 0x00000c00, 0x3d24a92d,
+			  0x00200bca, 0x00000bff, 0x3df600d2,
+			  0x002013cc, 0x000007ff, 0x3ed70c7e,
+			  0x00100fde, 0x00000000, 0x3f87c036 },
+	},
+	{ 0x1200, {
+			  0x002ffff1, 0x002ffff1, 0x02a0a9c8,
+			  0x002003e7, 0x001ffffa, 0x000185bc,
+			  0x002007dc, 0x000003ff, 0x3e52859c,
+			  0x00200bd4, 0x00000002, 0x3d53996b,
+			  0x00100fd0, 0x00000403, 0x3d04ad2d,
+			  0x00000bd5, 0x00000403, 0x3d35ace7,
+			  0x3ff003e4, 0x00000801, 0x3dc674a1,
+			  0x3fffe800, 0x00000800, 0x3e76f461 },
+	},
+	{ 0x1400, {
+			  0x00100be3, 0x00100be3, 0x04d1359a,
+			  0x00000fdb, 0x002003ed, 0x0211fd93,
+			  0x00000fd6, 0x002003f4, 0x0002d97b,
+			  0x000007d6, 0x002ffffb, 0x3e93b956,
+			  0x3ff003da, 0x001003ff, 0x3db49926,
+			  0x3fffefe9, 0x00100001, 0x3d655cee,
+			  0x3fffd400, 0x00000003, 0x3d65f4b6,
+			  0x000fb421, 0x00000402, 0x3dc6547e },
+	},
+	{ 0x1600, {
+			  0x00000bdd, 0x00000bdd, 0x06519578,
+			  0x3ff007da, 0x00000be3, 0x03c24973,
+			  0x3ff003d9, 0x00000be9, 0x01b30d5f,
+			  0x3ffff7df, 0x001003f1, 0x0003c542,
+			  0x000fdfec, 0x001003f7, 0x3ec4711d,
+			  0x000fc400, 0x002ffffd, 0x3df504f1,
+			  0x001fa81a, 0x002ffc00, 0x3d957cc2,
+			  0x002f8c3c, 0x00100000, 0x3db5c891 },
+	},
+	{ 0x1800, {
+			  0x3ff003dc, 0x3ff003dc, 0x0791e558,
+			  0x000ff7dd, 0x3ff007de, 0x05328554,
+			  0x000fe7e3, 0x3ff00be2, 0x03232546,
+			  0x000fd7ee, 0x000007e9, 0x0143bd30,
+			  0x001fb800, 0x000007ee, 0x00044511,
+			  0x002fa015, 0x000007f4, 0x3ef4bcee,
+			  0x002f8832, 0x001003f9, 0x3e4514c7,
+			  0x001f7853, 0x001003fd, 0x3de54c9f },
+	},
+	{ 0x1a00, {
+			  0x000fefe0, 0x000fefe0, 0x08721d3c,
+			  0x001fdbe7, 0x000ffbde, 0x0652a139,
+			  0x001fcbf0, 0x000003df, 0x0463292e,
+			  0x002fb3ff, 0x3ff007e3, 0x0293a91d,
+			  0x002f9c12, 0x3ff00be7, 0x01241905,
+			  0x001f8c29, 0x000007ed, 0x3fe470eb,
+			  0x000f7c46, 0x000007f2, 0x3f04b8ca,
+			  0x3fef7865, 0x000007f6, 0x3e74e4a8 },
+	},
+	{ 0x1c00, {
+			  0x001fd3e9, 0x001fd3e9, 0x08f23d26,
+			  0x002fbff3, 0x001fe3e4, 0x0712ad23,
+			  0x002fa800, 0x000ff3e0, 0x05631d1b,
+			  0x001f9810, 0x000ffbe1, 0x03b3890d,
+			  0x000f8c23, 0x000003e3, 0x0233e8fa,
+			  0x3fef843b, 0x000003e7, 0x00f430e4,
+			  0x3fbf8456, 0x3ff00bea, 0x00046cc8,
+			  0x3f8f8c72, 0x3ff00bef, 0x3f3490ac },
+	},
+	{ 0x1e00, {
+			  0x001fbbf4, 0x001fbbf4, 0x09425112,
+			  0x001fa800, 0x002fc7ed, 0x0792b110,
+			  0x000f980e, 0x001fdbe6, 0x0613110a,
+			  0x3fff8c20, 0x001fe7e3, 0x04a368fd,
+			  0x3fcf8c33, 0x000ff7e2, 0x0343b8ed,
+			  0x3f9f8c4a, 0x000fffe3, 0x0203f8da,
+			  0x3f5f9c61, 0x000003e6, 0x00e428c5,
+			  0x3f1fb07b, 0x000003eb, 0x3fe440af },
+	},
+	{ 0x2000, {
+			  0x000fa400, 0x000fa400, 0x09625902,
+			  0x3fff980c, 0x001fb7f5, 0x0812b0ff,
+			  0x3fdf901c, 0x001fc7ed, 0x06b2fcfa,
+			  0x3faf902d, 0x001fd3e8, 0x055348f1,
+			  0x3f7f983f, 0x001fe3e5, 0x04038ce3,
+			  0x3f3fa454, 0x001fefe3, 0x02e3c8d1,
+			  0x3f0fb86a, 0x001ff7e4, 0x01c3e8c0,
+			  0x3ecfd880, 0x000fffe6, 0x00c404ac },
+	},
+	{ 0x2200, {
+			  0x3fdf9c0b, 0x3fdf9c0b, 0x09725cf4,
+			  0x3fbf9818, 0x3fffa400, 0x0842a8f1,
+			  0x3f8f9827, 0x000fb3f7, 0x0702f0ec,
+			  0x3f5fa037, 0x000fc3ef, 0x05d330e4,
+			  0x3f2fac49, 0x001fcfea, 0x04a364d9,
+			  0x3effc05c, 0x001fdbe7, 0x038394ca,
+			  0x3ecfdc6f, 0x001fe7e6, 0x0273b0bb,
+			  0x3ea00083, 0x001fefe6, 0x0183c0a9 },
+	},
+	{ 0x2400, {
+			  0x3f9fa014, 0x3f9fa014, 0x098260e6,
+			  0x3f7f9c23, 0x3fcf9c0a, 0x08629ce5,
+			  0x3f4fa431, 0x3fefa400, 0x0742d8e1,
+			  0x3f1fb440, 0x3fffb3f8, 0x062310d9,
+			  0x3eefc850, 0x000fbbf2, 0x050340d0,
+			  0x3ecfe062, 0x000fcbec, 0x041364c2,
+			  0x3ea00073, 0x001fd3ea, 0x03037cb5,
+			  0x3e902086, 0x001fdfe8, 0x022388a5 },
+	},
+	{ 0x2600, {
+			  0x3f5fa81e, 0x3f5fa81e, 0x096258da,
+			  0x3f3fac2b, 0x3f8fa412, 0x088290d8,
+			  0x3f0fbc38, 0x3fafa408, 0x0772c8d5,
+			  0x3eefcc47, 0x3fcfa800, 0x0672f4ce,
+			  0x3ecfe456, 0x3fefaffa, 0x05531cc6,
+			  0x3eb00066, 0x3fffbbf3, 0x047334bb,
+			  0x3ea01c77, 0x000fc7ee, 0x039348ae,
+			  0x3ea04486, 0x000fd3eb, 0x02b350a1 },
+	},
+	{ 0x2800, {
+			  0x3f2fb426, 0x3f2fb426, 0x094250ce,
+			  0x3f0fc032, 0x3f4fac1b, 0x086284cd,
+			  0x3eefd040, 0x3f7fa811, 0x0782acc9,
+			  0x3ecfe84c, 0x3f9fa807, 0x06a2d8c4,
+			  0x3eb0005b, 0x3fbfac00, 0x05b2f4bc,
+			  0x3eb0186a, 0x3fdfb3fa, 0x04c308b4,
+			  0x3eb04077, 0x3fefbbf4, 0x03f31ca8,
+			  0x3ec06884, 0x000fbff2, 0x03031c9e },
+	},
+	{ 0x2a00, {
+			  0x3f0fc42d, 0x3f0fc42d, 0x090240c4,
+			  0x3eefd439, 0x3f2fb822, 0x08526cc2,
+			  0x3edfe845, 0x3f4fb018, 0x078294bf,
+			  0x3ec00051, 0x3f6fac0f, 0x06b2b4bb,
+			  0x3ec0185f, 0x3f8fac07, 0x05e2ccb4,
+			  0x3ec0386b, 0x3fafac00, 0x0502e8ac,
+			  0x3ed05c77, 0x3fcfb3fb, 0x0432f0a3,
+			  0x3ef08482, 0x3fdfbbf6, 0x0372f898 },
+	},
+	{ 0x2c00, {
+			  0x3eefdc31, 0x3eefdc31, 0x08e238b8,
+			  0x3edfec3d, 0x3f0fc828, 0x082258b9,
+			  0x3ed00049, 0x3f1fc01e, 0x077278b6,
+			  0x3ed01455, 0x3f3fb815, 0x06c294b2,
+			  0x3ed03460, 0x3f5fb40d, 0x0602acac,
+			  0x3ef0506c, 0x3f7fb006, 0x0542c0a4,
+			  0x3f107476, 0x3f9fb400, 0x0472c89d,
+			  0x3f309c80, 0x3fbfb7fc, 0x03b2cc94 },
+	},
+	{ 0x2e00, {
+			  0x3eefec37, 0x3eefec37, 0x088220b0,
+			  0x3ee00041, 0x3effdc2d, 0x07f244ae,
+			  0x3ee0144c, 0x3f0fd023, 0x07625cad,
+			  0x3ef02c57, 0x3f1fc81a, 0x06c274a9,
+			  0x3f004861, 0x3f3fbc13, 0x060288a6,
+			  0x3f20686b, 0x3f5fb80c, 0x05529c9e,
+			  0x3f408c74, 0x3f6fb805, 0x04b2ac96,
+			  0x3f80ac7e, 0x3f8fb800, 0x0402ac8e },
+	},
+	{ 0x3000, {
+			  0x3ef0003a, 0x3ef0003a, 0x084210a6,
+			  0x3ef01045, 0x3effec32, 0x07b228a7,
+			  0x3f00284e, 0x3f0fdc29, 0x073244a4,
+			  0x3f104058, 0x3f0fd420, 0x06a258a2,
+			  0x3f305c62, 0x3f2fc818, 0x0612689d,
+			  0x3f508069, 0x3f3fc011, 0x05728496,
+			  0x3f80a072, 0x3f4fc00a, 0x04d28c90,
+			  0x3fc0c07b, 0x3f6fbc04, 0x04429088 },
+	},
+	{ 0x3200, {
+			  0x3f00103e, 0x3f00103e, 0x07f1fc9e,
+			  0x3f102447, 0x3f000035, 0x0782149d,
+			  0x3f203c4f, 0x3f0ff02c, 0x07122c9c,
+			  0x3f405458, 0x3f0fe424, 0x06924099,
+			  0x3f607061, 0x3f1fd41d, 0x06024c97,
+			  0x3f909068, 0x3f2fcc16, 0x05726490,
+			  0x3fc0b070, 0x3f3fc80f, 0x04f26c8a,
+			  0x0000d077, 0x3f4fc409, 0x04627484 },
+	},
+	{ 0x3400, {
+			  0x3f202040, 0x3f202040, 0x07a1e898,
+			  0x3f303449, 0x3f100c38, 0x0741fc98,
+			  0x3f504c50, 0x3f10002f, 0x06e21495,
+			  0x3f706459, 0x3f1ff028, 0x06722492,
+			  0x3fa08060, 0x3f1fe421, 0x05f2348f,
+			  0x3fd09c67, 0x3f1fdc19, 0x05824c89,
+			  0x0000bc6e, 0x3f2fd014, 0x04f25086,
+			  0x0040dc74, 0x3f3fcc0d, 0x04825c7f },
+	},
+	{ 0x3600, {
+			  0x3f403042, 0x3f403042, 0x0761d890,
+			  0x3f504848, 0x3f301c3b, 0x0701f090,
+			  0x3f805c50, 0x3f200c33, 0x06a2008f,
+			  0x3fa07458, 0x3f10002b, 0x06520c8d,
+			  0x3fd0905e, 0x3f1ff424, 0x05e22089,
+			  0x0000ac65, 0x3f1fe81d, 0x05823483,
+			  0x0030cc6a, 0x3f2fdc18, 0x04f23c81,
+			  0x0080e871, 0x3f2fd412, 0x0482407c },
+	},
+	{ 0x3800, {
+			  0x3f604043, 0x3f604043, 0x0721c88a,
+			  0x3f80544a, 0x3f502c3c, 0x06d1d88a,
+			  0x3fb06851, 0x3f301c35, 0x0681e889,
+			  0x3fd08456, 0x3f30082f, 0x0611fc88,
+			  0x00009c5d, 0x3f200027, 0x05d20884,
+			  0x0030b863, 0x3f2ff421, 0x05621880,
+			  0x0070d468, 0x3f2fe81b, 0x0502247c,
+			  0x00c0ec6f, 0x3f2fe015, 0x04a22877 },
+	},
+	{ 0x3a00, {
+			  0x3f904c44, 0x3f904c44, 0x06e1b884,
+			  0x3fb0604a, 0x3f70383e, 0x0691c885,
+			  0x3fe07451, 0x3f502c36, 0x0661d483,
+			  0x00009055, 0x3f401831, 0x0601ec81,
+			  0x0030a85b, 0x3f300c2a, 0x05b1f480,
+			  0x0070c061, 0x3f300024, 0x0562047a,
+			  0x00b0d867, 0x3f3ff41e, 0x05020c77,
+			  0x00f0f46b, 0x3f2fec19, 0x04a21474 },
+	},
+	{ 0x3c00, {
+			  0x3fb05c43, 0x3fb05c43, 0x06c1b07e,
+			  0x3fe06c4b, 0x3f902c3f, 0x0681c081,
+			  0x0000844f, 0x3f703838, 0x0631cc7d,
+			  0x00309855, 0x3f602433, 0x05d1d47e,
+			  0x0060b459, 0x3f50142e, 0x0581e47b,
+			  0x00a0c85f, 0x3f400828, 0x0531f078,
+			  0x00e0e064, 0x3f300021, 0x0501fc73,
+			  0x00b0fc6a, 0x3f3ff41d, 0x04a20873 },
+	},
+	{ 0x3e00, {
+			  0x3fe06444, 0x3fe06444, 0x0681a07a,
+			  0x00007849, 0x3fc0503f, 0x0641b07a,
+			  0x0020904d, 0x3fa0403a, 0x05f1c07a,
+			  0x0060a453, 0x3f803034, 0x05c1c878,
+			  0x0090b858, 0x3f70202f, 0x0571d477,
+			  0x00d0d05d, 0x3f501829, 0x0531e073,
+			  0x0110e462, 0x3f500825, 0x04e1e471,
+			  0x01510065, 0x3f40001f, 0x04a1f06d },
+	},
+	{ 0x4000, {
+			  0x00007044, 0x00007044, 0x06519476,
+			  0x00208448, 0x3fe05c3f, 0x0621a476,
+			  0x0050984d, 0x3fc04c3a, 0x05e1b075,
+			  0x0080ac52, 0x3fa03c35, 0x05a1b875,
+			  0x00c0c056, 0x3f803030, 0x0561c473,
+			  0x0100d45b, 0x3f70202b, 0x0521d46f,
+			  0x0140e860, 0x3f601427, 0x04d1d46e,
+			  0x01810064, 0x3f500822, 0x0491dc6b },
+	},
+	{ 0x5000, {
+			  0x0110a442, 0x0110a442, 0x0551545e,
+			  0x0140b045, 0x00e0983f, 0x0531585f,
+			  0x0160c047, 0x00c08c3c, 0x0511645e,
+			  0x0190cc4a, 0x00908039, 0x04f1685f,
+			  0x01c0dc4c, 0x00707436, 0x04d1705e,
+			  0x0200e850, 0x00506833, 0x04b1785b,
+			  0x0230f453, 0x00305c30, 0x0491805a,
+			  0x02710056, 0x0010542d, 0x04718059 },
+	},
+	{ 0x6000, {
+			  0x01c0bc40, 0x01c0bc40, 0x04c13052,
+			  0x01e0c841, 0x01a0b43d, 0x04c13851,
+			  0x0210cc44, 0x0180a83c, 0x04a13453,
+			  0x0230d845, 0x0160a03a, 0x04913c52,
+			  0x0260e047, 0x01409838, 0x04714052,
+			  0x0280ec49, 0x01208c37, 0x04514c50,
+			  0x02b0f44b, 0x01008435, 0x04414c50,
+			  0x02d1004c, 0x00e07c33, 0x0431544f },
+	},
+	{ 0x7000, {
+			  0x0230c83e, 0x0230c83e, 0x04711c4c,
+			  0x0250d03f, 0x0210c43c, 0x0471204b,
+			  0x0270d840, 0x0200b83c, 0x0451244b,
+			  0x0290dc42, 0x01e0b43a, 0x0441244c,
+			  0x02b0e443, 0x01c0b038, 0x0441284b,
+			  0x02d0ec44, 0x01b0a438, 0x0421304a,
+			  0x02f0f445, 0x0190a036, 0x04213449,
+			  0x0310f847, 0x01709c34, 0x04213848 },
+	},
+	{ 0x8000, {
+			  0x0280d03d, 0x0280d03d, 0x04310c48,
+			  0x02a0d43e, 0x0270c83c, 0x04311047,
+			  0x02b0dc3e, 0x0250c83a, 0x04311447,
+			  0x02d0e040, 0x0240c03a, 0x04211446,
+			  0x02e0e840, 0x0220bc39, 0x04111847,
+			  0x0300e842, 0x0210b438, 0x04012445,
+			  0x0310f043, 0x0200b037, 0x04012045,
+			  0x0330f444, 0x01e0ac36, 0x03f12445 },
+	},
+	{ 0xefff, {
+			  0x0340dc3a, 0x0340dc3a, 0x03b0ec40,
+			  0x0340e03a, 0x0330e039, 0x03c0f03e,
+			  0x0350e03b, 0x0330dc39, 0x03c0ec3e,
+			  0x0350e43a, 0x0320dc38, 0x03c0f43e,
+			  0x0360e43b, 0x0320d839, 0x03b0f03e,
+			  0x0360e83b, 0x0310d838, 0x03c0fc3b,
+			  0x0370e83b, 0x0310d439, 0x03a0f83d,
+			  0x0370e83c, 0x0300d438, 0x03b0fc3c },
+	}
+};
+
+static void rvin_set_coeff(struct rvin_dev *vin, unsigned short xs)
+{
+	int i;
+	const struct vin_coeff *p_prev_set = NULL;
+	const struct vin_coeff *p_set = NULL;
+
+	/* Look for suitable coefficient values */
+	for (i = 0; i < ARRAY_SIZE(vin_coeff_set); i++) {
+		p_prev_set = p_set;
+		p_set = &vin_coeff_set[i];
+
+		if (xs < p_set->xs_value)
+			break;
+	}
+
+	/* Use previous value if its XS value is closer */
+	if (p_prev_set && p_set &&
+	    xs - p_prev_set->xs_value < p_set->xs_value - xs)
+		p_set = p_prev_set;
+
+	/* Set coefficient registers */
+	rvin_write(vin, p_set->coeff_set[0], VNC1A_REG);
+	rvin_write(vin, p_set->coeff_set[1], VNC1B_REG);
+	rvin_write(vin, p_set->coeff_set[2], VNC1C_REG);
+
+	rvin_write(vin, p_set->coeff_set[3], VNC2A_REG);
+	rvin_write(vin, p_set->coeff_set[4], VNC2B_REG);
+	rvin_write(vin, p_set->coeff_set[5], VNC2C_REG);
+
+	rvin_write(vin, p_set->coeff_set[6], VNC3A_REG);
+	rvin_write(vin, p_set->coeff_set[7], VNC3B_REG);
+	rvin_write(vin, p_set->coeff_set[8], VNC3C_REG);
+
+	rvin_write(vin, p_set->coeff_set[9], VNC4A_REG);
+	rvin_write(vin, p_set->coeff_set[10], VNC4B_REG);
+	rvin_write(vin, p_set->coeff_set[11], VNC4C_REG);
+
+	rvin_write(vin, p_set->coeff_set[12], VNC5A_REG);
+	rvin_write(vin, p_set->coeff_set[13], VNC5B_REG);
+	rvin_write(vin, p_set->coeff_set[14], VNC5C_REG);
+
+	rvin_write(vin, p_set->coeff_set[15], VNC6A_REG);
+	rvin_write(vin, p_set->coeff_set[16], VNC6B_REG);
+	rvin_write(vin, p_set->coeff_set[17], VNC6C_REG);
+
+	rvin_write(vin, p_set->coeff_set[18], VNC7A_REG);
+	rvin_write(vin, p_set->coeff_set[19], VNC7B_REG);
+	rvin_write(vin, p_set->coeff_set[20], VNC7C_REG);
+
+	rvin_write(vin, p_set->coeff_set[21], VNC8A_REG);
+	rvin_write(vin, p_set->coeff_set[22], VNC8B_REG);
+	rvin_write(vin, p_set->coeff_set[23], VNC8C_REG);
+}
+
+void rvin_crop_scale_comp(struct rvin_dev *vin)
+{
+	u32 xs, ys;
+
+	/* Set Start/End Pixel/Line Pre-Clip */
+	rvin_write(vin, vin->crop.left, VNSPPRC_REG);
+	rvin_write(vin, vin->crop.left + vin->crop.width - 1, VNEPPRC_REG);
+	switch (vin->format.field) {
+	case V4L2_FIELD_INTERLACED:
+	case V4L2_FIELD_INTERLACED_TB:
+	case V4L2_FIELD_INTERLACED_BT:
+		rvin_write(vin, vin->crop.top / 2, VNSLPRC_REG);
+		rvin_write(vin, (vin->crop.top + vin->crop.height) / 2 - 1,
+			   VNELPRC_REG);
+		break;
+	default:
+		rvin_write(vin, vin->crop.top, VNSLPRC_REG);
+		rvin_write(vin, vin->crop.top + vin->crop.height - 1,
+			   VNELPRC_REG);
+		break;
+	}
+
+	/* Set scaling coefficient */
+	ys = 0;
+	if (vin->crop.height != vin->compose.height)
+		ys = (4096 * vin->crop.height) / vin->compose.height;
+	rvin_write(vin, ys, VNYS_REG);
+
+	xs = 0;
+	if (vin->crop.width != vin->compose.width)
+		xs = (4096 * vin->crop.width) / vin->compose.width;
+
+	/* Horizontal upscaling is up to double size */
+	if (xs > 0 && xs < 2048)
+		xs = 2048;
+
+	rvin_write(vin, xs, VNXS_REG);
+
+	/* Horizontal upscaling is done out by scaling down from double size */
+	if (xs < 4096)
+		xs *= 2;
+
+	rvin_set_coeff(vin, xs);
+
+	/* Set Start/End Pixel/Line Post-Clip */
+	rvin_write(vin, 0, VNSPPOC_REG);
+	rvin_write(vin, 0, VNSLPOC_REG);
+	rvin_write(vin, vin->format.width - 1, VNEPPOC_REG);
+	switch (vin->format.field) {
+	case V4L2_FIELD_INTERLACED:
+	case V4L2_FIELD_INTERLACED_TB:
+	case V4L2_FIELD_INTERLACED_BT:
+		rvin_write(vin, vin->format.height / 2 - 1, VNELPOC_REG);
+		break;
+	default:
+		rvin_write(vin, vin->format.height - 1, VNELPOC_REG);
+		break;
+	}
+
+	if (vin->format.pixelformat == V4L2_PIX_FMT_NV16)
+		rvin_write(vin, ALIGN(vin->format.width, 0x20), VNIS_REG);
+	else
+		rvin_write(vin, ALIGN(vin->format.width, 0x10), VNIS_REG);
+
+	vin_dbg(vin,
+		"Pre-Clip: %ux%u@%u:%u YS: %d XS: %d Post-Clip: %ux%u@%u:%u\n",
+		vin->crop.width, vin->crop.height, vin->crop.left,
+		vin->crop.top, ys, xs, vin->format.width, vin->format.height,
+		0, 0);
+}
+
+void rvin_scale_try(struct rvin_dev *vin, struct v4l2_pix_format *pix,
+		    u32 width, u32 height)
+{
+	/* All VIN channels on Gen2 have scalers */
+	pix->width = width;
+	pix->height = height;
+}
+
+/* -----------------------------------------------------------------------------
+ * DMA Functions
+ */
+
+#define RVIN_TIMEOUT_MS 100
+#define RVIN_RETRIES 10
+
+struct rvin_buffer {
+	struct vb2_v4l2_buffer vb;
+	struct list_head list;
+};
+
+#define to_buf_list(vb2_buffer) (&container_of(vb2_buffer, \
+					       struct rvin_buffer, \
+					       vb)->list)
+
+/* Moves a buffer from the queue to the HW slots */
+static bool rvin_fill_hw_slot(struct rvin_dev *vin, int slot)
+{
+	struct rvin_buffer *buf;
+	struct vb2_v4l2_buffer *vbuf;
+	dma_addr_t phys_addr_top;
+
+	if (vin->queue_buf[slot] != NULL)
+		return true;
+
+	if (list_empty(&vin->buf_list))
+		return false;
+
+	vin_dbg(vin, "Filling HW slot: %d\n", slot);
+
+	/* Keep track of buffer we give to HW */
+	buf = list_entry(vin->buf_list.next, struct rvin_buffer, list);
+	vbuf = &buf->vb;
+	list_del_init(to_buf_list(vbuf));
+	vin->queue_buf[slot] = vbuf;
+
+	/* Setup DMA */
+	phys_addr_top = vb2_dma_contig_plane_dma_addr(&vbuf->vb2_buf, 0);
+	rvin_set_slot_addr(vin, slot, phys_addr_top);
+
+	return true;
+}
+
+static bool rvin_fill_hw(struct rvin_dev *vin)
+{
+	int slot, limit;
+
+	limit = vin->continuous ? HW_BUFFER_NUM : 1;
+
+	for (slot = 0; slot < limit; slot++)
+		if (!rvin_fill_hw_slot(vin, slot))
+			return false;
+	return true;
+}
+
+static irqreturn_t rvin_irq(int irq, void *data)
+{
+	struct rvin_dev *vin = data;
+	u32 int_status;
+	int slot;
+	unsigned int sequence, handled = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vin->qlock, flags);
+
+	int_status = rvin_get_interrupt_status(vin);
+	if (!int_status)
+		goto done;
+
+	rvin_ack_interrupt(vin);
+	handled = 1;
+
+	/* Nothing to do if capture status is 'STOPPED' */
+	if (vin->state == STOPPED) {
+		vin_dbg(vin, "IRQ while state stopped\n");
+		goto done;
+	}
+
+	/* Nothing to do if capture status is 'STOPPING' */
+	if (vin->state == STOPPING) {
+		vin_dbg(vin, "IRQ while state stopping\n");
+		goto done;
+	}
+
+	/* Prepare for capture and update state */
+	slot = rvin_get_active_slot(vin);
+	sequence = vin->sequence++;
+
+	vin_dbg(vin, "IRQ %02d: %d\tbuf0: %c buf1: %c buf2: %c\tmore: %d\n",
+		sequence, slot,
+		slot == 0 ? 'x' : vin->queue_buf[0] != NULL ? '1' : '0',
+		slot == 1 ? 'x' : vin->queue_buf[1] != NULL ? '1' : '0',
+		slot == 2 ? 'x' : vin->queue_buf[2] != NULL ? '1' : '0',
+		!list_empty(&vin->buf_list));
+
+	/* HW have written to a slot that is not prepared we are in trouble */
+	if (WARN_ON((vin->queue_buf[slot] == NULL)))
+		goto done;
+
+	/* Capture frame */
+	vin->queue_buf[slot]->field = vin->format.field;
+	vin->queue_buf[slot]->sequence = sequence;
+	vin->queue_buf[slot]->vb2_buf.timestamp = ktime_get_ns();
+	vb2_buffer_done(&vin->queue_buf[slot]->vb2_buf, VB2_BUF_STATE_DONE);
+	vin->queue_buf[slot] = NULL;
+
+	/* Prepare for next frame */
+	if (!rvin_fill_hw(vin)) {
+
+		/*
+		 * Can't supply HW with new buffers fast enough. Halt
+		 * capture until more buffers are available.
+		 */
+		vin->state = STALLED;
+
+		/*
+		 * The continuous capturing requires an explicit stop
+		 * operation when there is no buffer to be set into
+		 * the VnMBm registers.
+		 */
+		if (vin->continuous) {
+			rvin_capture_off(vin);
+			vin_dbg(vin, "IRQ %02d: hw not ready stop\n", sequence);
+		}
+	} else {
+		/*
+		 * The single capturing requires an explicit capture
+		 * operation to fetch the next frame.
+		 */
+		if (!vin->continuous)
+			rvin_capture_on(vin);
+	}
+done:
+	spin_unlock_irqrestore(&vin->qlock, flags);
+
+	return IRQ_RETVAL(handled);
+}
+
+/* Need to hold qlock before calling */
+static void return_all_buffers(struct rvin_dev *vin,
+			       enum vb2_buffer_state state)
+{
+	struct rvin_buffer *buf, *node;
+	int i;
+
+	for (i = 0; i < HW_BUFFER_NUM; i++) {
+		if (vin->queue_buf[i]) {
+			vb2_buffer_done(&vin->queue_buf[i]->vb2_buf,
+					state);
+			vin->queue_buf[i] = NULL;
+		}
+	}
+
+	list_for_each_entry_safe(buf, node, &vin->buf_list, list) {
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
+		list_del(&buf->list);
+	}
+}
+
+static int rvin_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
+			    unsigned int *nplanes, unsigned int sizes[],
+			    struct device *alloc_devs[])
+
+{
+	struct rvin_dev *vin = vb2_get_drv_priv(vq);
+
+	/* Make sure the image size is large enough. */
+	if (*nplanes)
+		return sizes[0] < vin->format.sizeimage ? -EINVAL : 0;
+
+	*nplanes = 1;
+	sizes[0] = vin->format.sizeimage;
+
+	return 0;
+};
+
+static int rvin_buffer_prepare(struct vb2_buffer *vb)
+{
+	struct rvin_dev *vin = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned long size = vin->format.sizeimage;
+
+	if (vb2_plane_size(vb, 0) < size) {
+		vin_err(vin, "buffer too small (%lu < %lu)\n",
+			vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+
+	vb2_set_plane_payload(vb, 0, size);
+
+	return 0;
+}
+
+static void rvin_buffer_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rvin_dev *vin = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vin->qlock, flags);
+
+	list_add_tail(to_buf_list(vbuf), &vin->buf_list);
+
+	/*
+	 * If capture is stalled add buffer to HW and restart
+	 * capturing if HW is ready to continue.
+	 */
+	if (vin->state == STALLED)
+		if (rvin_fill_hw(vin))
+			rvin_capture_on(vin);
+
+	spin_unlock_irqrestore(&vin->qlock, flags);
+}
+
+static int rvin_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct rvin_dev *vin = vb2_get_drv_priv(vq);
+	struct v4l2_subdev *sd;
+	unsigned long flags;
+	int ret;
+
+	sd = vin_to_source(vin);
+	v4l2_subdev_call(sd, video, s_stream, 1);
+
+	spin_lock_irqsave(&vin->qlock, flags);
+
+	vin->state = RUNNING;
+	vin->sequence = 0;
+
+	/* Continuous capture requires more buffers then there are HW slots */
+	vin->continuous = count > HW_BUFFER_NUM;
+
+	/*
+	 * This should never happen but if we don't have enough
+	 * buffers for HW bail out
+	 */
+	if (!rvin_fill_hw(vin)) {
+		vin_err(vin, "HW not ready to start, not enough buffers available\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = rvin_capture_start(vin);
+out:
+	/* Return all buffers if something went wrong */
+	if (ret) {
+		return_all_buffers(vin, VB2_BUF_STATE_QUEUED);
+		v4l2_subdev_call(sd, video, s_stream, 0);
+	}
+
+	spin_unlock_irqrestore(&vin->qlock, flags);
+
+	return ret;
+}
+
+static void rvin_stop_streaming(struct vb2_queue *vq)
+{
+	struct rvin_dev *vin = vb2_get_drv_priv(vq);
+	struct v4l2_subdev *sd;
+	unsigned long flags;
+	int retries = 0;
+
+	spin_lock_irqsave(&vin->qlock, flags);
+
+	vin->state = STOPPING;
+
+	/* Wait for streaming to stop */
+	while (retries++ < RVIN_RETRIES) {
+
+		rvin_capture_stop(vin);
+
+		/* Check if HW is stopped */
+		if (!rvin_capture_active(vin)) {
+			vin->state = STOPPED;
+			break;
+		}
+
+		spin_unlock_irqrestore(&vin->qlock, flags);
+		msleep(RVIN_TIMEOUT_MS);
+		spin_lock_irqsave(&vin->qlock, flags);
+	}
+
+	if (vin->state != STOPPED) {
+		/*
+		 * If this happens something have gone horribly wrong.
+		 * Set state to stopped to prevent the interrupt handler
+		 * to make things worse...
+		 */
+		vin_err(vin, "Failed stop HW, something is seriously broken\n");
+		vin->state = STOPPED;
+	}
+
+	/* Release all active buffers */
+	return_all_buffers(vin, VB2_BUF_STATE_ERROR);
+
+	spin_unlock_irqrestore(&vin->qlock, flags);
+
+	sd = vin_to_source(vin);
+	v4l2_subdev_call(sd, video, s_stream, 0);
+
+	/* disable interrupts */
+	rvin_disable_interrupts(vin);
+}
+
+static struct vb2_ops rvin_qops = {
+	.queue_setup		= rvin_queue_setup,
+	.buf_prepare		= rvin_buffer_prepare,
+	.buf_queue		= rvin_buffer_queue,
+	.start_streaming	= rvin_start_streaming,
+	.stop_streaming		= rvin_stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+};
+
+void rvin_dma_remove(struct rvin_dev *vin)
+{
+	mutex_destroy(&vin->lock);
+
+	v4l2_device_unregister(&vin->v4l2_dev);
+}
+
+int rvin_dma_probe(struct rvin_dev *vin, int irq)
+{
+	struct vb2_queue *q = &vin->queue;
+	int i, ret;
+
+	/* Initialize the top-level structure */
+	ret = v4l2_device_register(vin->dev, &vin->v4l2_dev);
+	if (ret)
+		return ret;
+
+	mutex_init(&vin->lock);
+	INIT_LIST_HEAD(&vin->buf_list);
+
+	spin_lock_init(&vin->qlock);
+
+	vin->state = STOPPED;
+
+	for (i = 0; i < HW_BUFFER_NUM; i++)
+		vin->queue_buf[i] = NULL;
+
+	/* buffer queue */
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_READ | VB2_DMABUF;
+	q->lock = &vin->lock;
+	q->drv_priv = vin;
+	q->buf_struct_size = sizeof(struct rvin_buffer);
+	q->ops = &rvin_qops;
+	q->mem_ops = &vb2_dma_contig_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->min_buffers_needed = 2;
+	q->dev = vin->dev;
+
+	ret = vb2_queue_init(q);
+	if (ret < 0) {
+		vin_err(vin, "failed to initialize VB2 queue\n");
+		goto error;
+	}
+
+	/* irq */
+	ret = devm_request_irq(vin->dev, irq, rvin_irq, IRQF_SHARED,
+			       KBUILD_MODNAME, vin);
+	if (ret) {
+		vin_err(vin, "failed to request irq\n");
+		goto error;
+	}
+
+	return 0;
+error:
+	rvin_dma_remove(vin);
+
+	return ret;
+}
diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c
new file mode 100644
index 000000000000..10a5c107e8b9
--- /dev/null
+++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c
@@ -0,0 +1,874 @@
+/*
+ * Driver for Renesas R-Car VIN
+ *
+ * Copyright (C) 2016 Renesas Electronics Corp.
+ * Copyright (C) 2011-2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Cogent Embedded, Inc., <source@cogentembedded.com>
+ * Copyright (C) 2008 Magnus Damm
+ *
+ * Based on the soc-camera rcar_vin driver
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/pm_runtime.h>
+
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-rect.h>
+
+#include "rcar-vin.h"
+
+#define RVIN_DEFAULT_FORMAT	V4L2_PIX_FMT_YUYV
+#define RVIN_MAX_WIDTH		2048
+#define RVIN_MAX_HEIGHT		2048
+
+/* -----------------------------------------------------------------------------
+ * Format Conversions
+ */
+
+static const struct rvin_video_format rvin_formats[] = {
+	{
+		.fourcc			= V4L2_PIX_FMT_NV16,
+		.bpp			= 1,
+	},
+	{
+		.fourcc			= V4L2_PIX_FMT_YUYV,
+		.bpp			= 2,
+	},
+	{
+		.fourcc			= V4L2_PIX_FMT_UYVY,
+		.bpp			= 2,
+	},
+	{
+		.fourcc			= V4L2_PIX_FMT_RGB565,
+		.bpp			= 2,
+	},
+	{
+		.fourcc			= V4L2_PIX_FMT_XRGB555,
+		.bpp			= 2,
+	},
+	{
+		.fourcc			= V4L2_PIX_FMT_XBGR32,
+		.bpp			= 4,
+	},
+};
+
+const struct rvin_video_format *rvin_format_from_pixel(u32 pixelformat)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rvin_formats); i++)
+		if (rvin_formats[i].fourcc == pixelformat)
+			return rvin_formats + i;
+
+	return NULL;
+}
+
+static u32 rvin_format_bytesperline(struct v4l2_pix_format *pix)
+{
+	const struct rvin_video_format *fmt;
+
+	fmt = rvin_format_from_pixel(pix->pixelformat);
+
+	if (WARN_ON(!fmt))
+		return -EINVAL;
+
+	return pix->width * fmt->bpp;
+}
+
+static u32 rvin_format_sizeimage(struct v4l2_pix_format *pix)
+{
+	if (pix->pixelformat == V4L2_PIX_FMT_NV16)
+		return pix->bytesperline * pix->height * 2;
+
+	return pix->bytesperline * pix->height;
+}
+
+/* -----------------------------------------------------------------------------
+ * V4L2
+ */
+
+static int __rvin_try_format_source(struct rvin_dev *vin,
+					u32 which,
+					struct v4l2_pix_format *pix,
+					struct rvin_source_fmt *source)
+{
+	struct v4l2_subdev *sd;
+	struct v4l2_subdev_pad_config *pad_cfg;
+	struct v4l2_subdev_format format = {
+		.which = which,
+	};
+	int ret;
+
+	sd = vin_to_source(vin);
+
+	v4l2_fill_mbus_format(&format.format, pix, vin->source.code);
+
+	pad_cfg = v4l2_subdev_alloc_pad_config(sd);
+	if (pad_cfg == NULL)
+		return -ENOMEM;
+
+	format.pad = vin->src_pad_idx;
+
+	ret = v4l2_device_call_until_err(sd->v4l2_dev, 0, pad, set_fmt,
+					 pad_cfg, &format);
+	if (ret < 0)
+		goto cleanup;
+
+	v4l2_fill_pix_format(pix, &format.format);
+
+	source->width = pix->width;
+	source->height = pix->height;
+
+	vin_dbg(vin, "Source resolution: %ux%u\n", source->width,
+		source->height);
+
+cleanup:
+	v4l2_subdev_free_pad_config(pad_cfg);
+	return 0;
+}
+
+static int __rvin_try_format(struct rvin_dev *vin,
+				 u32 which,
+				 struct v4l2_pix_format *pix,
+				 struct rvin_source_fmt *source)
+{
+	const struct rvin_video_format *info;
+	u32 rwidth, rheight, walign;
+
+	/* Requested */
+	rwidth = pix->width;
+	rheight = pix->height;
+
+	/*
+	 * Retrieve format information and select the current format if the
+	 * requested format isn't supported.
+	 */
+	info = rvin_format_from_pixel(pix->pixelformat);
+	if (!info) {
+		vin_dbg(vin, "Format %x not found, keeping %x\n",
+			pix->pixelformat, vin->format.pixelformat);
+		*pix = vin->format;
+		pix->width = rwidth;
+		pix->height = rheight;
+	}
+
+	/* Always recalculate */
+	pix->bytesperline = 0;
+	pix->sizeimage = 0;
+
+	/* Limit to source capabilities */
+	__rvin_try_format_source(vin, which, pix, source);
+
+	/* If source can't match format try if VIN can scale */
+	if (source->width != rwidth || source->height != rheight)
+		rvin_scale_try(vin, pix, rwidth, rheight);
+
+	/* HW limit width to a multiple of 32 (2^5) for NV16 else 2 (2^1) */
+	walign = vin->format.pixelformat == V4L2_PIX_FMT_NV16 ? 5 : 1;
+
+	/* Limit to VIN capabilities */
+	v4l_bound_align_image(&pix->width, 2, RVIN_MAX_WIDTH, walign,
+			      &pix->height, 4, RVIN_MAX_HEIGHT, 2, 0);
+
+	switch (pix->field) {
+	case V4L2_FIELD_NONE:
+	case V4L2_FIELD_TOP:
+	case V4L2_FIELD_BOTTOM:
+	case V4L2_FIELD_INTERLACED_TB:
+	case V4L2_FIELD_INTERLACED_BT:
+	case V4L2_FIELD_INTERLACED:
+		break;
+	default:
+		pix->field = V4L2_FIELD_NONE;
+		break;
+	}
+
+	pix->bytesperline = max_t(u32, pix->bytesperline,
+				  rvin_format_bytesperline(pix));
+	pix->sizeimage = max_t(u32, pix->sizeimage,
+			       rvin_format_sizeimage(pix));
+
+	vin_dbg(vin, "Requested %ux%u Got %ux%u bpl: %d size: %d\n",
+		rwidth, rheight, pix->width, pix->height,
+		pix->bytesperline, pix->sizeimage);
+
+	return 0;
+}
+
+static int rvin_querycap(struct file *file, void *priv,
+			 struct v4l2_capability *cap)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+
+	strlcpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver));
+	strlcpy(cap->card, "R_Car_VIN", sizeof(cap->card));
+	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
+		 dev_name(vin->dev));
+	return 0;
+}
+
+static int rvin_try_fmt_vid_cap(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct rvin_source_fmt source;
+
+	return __rvin_try_format(vin, V4L2_SUBDEV_FORMAT_TRY, &f->fmt.pix,
+				     &source);
+}
+
+static int rvin_s_fmt_vid_cap(struct file *file, void *priv,
+			      struct v4l2_format *f)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct rvin_source_fmt source;
+	int ret;
+
+	if (vb2_is_busy(&vin->queue))
+		return -EBUSY;
+
+	ret = __rvin_try_format(vin, V4L2_SUBDEV_FORMAT_ACTIVE, &f->fmt.pix,
+				    &source);
+	if (ret)
+		return ret;
+
+	vin->source.width = source.width;
+	vin->source.height = source.height;
+
+	vin->format = f->fmt.pix;
+
+	return 0;
+}
+
+static int rvin_g_fmt_vid_cap(struct file *file, void *priv,
+			      struct v4l2_format *f)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+
+	f->fmt.pix = vin->format;
+
+	return 0;
+}
+
+static int rvin_enum_fmt_vid_cap(struct file *file, void *priv,
+				 struct v4l2_fmtdesc *f)
+{
+	if (f->index >= ARRAY_SIZE(rvin_formats))
+		return -EINVAL;
+
+	f->pixelformat = rvin_formats[f->index].fourcc;
+
+	return 0;
+}
+
+static int rvin_g_selection(struct file *file, void *fh,
+			    struct v4l2_selection *s)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+
+	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+		s->r.left = s->r.top = 0;
+		s->r.width = vin->source.width;
+		s->r.height = vin->source.height;
+		break;
+	case V4L2_SEL_TGT_CROP:
+		s->r = vin->crop;
+		break;
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
+		s->r.left = s->r.top = 0;
+		s->r.width = vin->format.width;
+		s->r.height = vin->format.height;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		s->r = vin->compose;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rvin_s_selection(struct file *file, void *fh,
+			    struct v4l2_selection *s)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	const struct rvin_video_format *fmt;
+	struct v4l2_rect r = s->r;
+	struct v4l2_rect max_rect;
+	struct v4l2_rect min_rect = {
+		.width = 6,
+		.height = 2,
+	};
+
+	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	v4l2_rect_set_min_size(&r, &min_rect);
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_CROP:
+		/* Can't crop outside of source input */
+		max_rect.top = max_rect.left = 0;
+		max_rect.width = vin->source.width;
+		max_rect.height = vin->source.height;
+		v4l2_rect_map_inside(&r, &max_rect);
+
+		v4l_bound_align_image(&r.width, 2, vin->source.width, 1,
+				      &r.height, 4, vin->source.height, 2, 0);
+
+		r.top  = clamp_t(s32, r.top, 0, vin->source.height - r.height);
+		r.left = clamp_t(s32, r.left, 0, vin->source.width - r.width);
+
+		vin->crop = s->r = r;
+
+		vin_dbg(vin, "Cropped %dx%d@%d:%d of %dx%d\n",
+			 r.width, r.height, r.left, r.top,
+			 vin->source.width, vin->source.height);
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		/* Make sure compose rect fits inside output format */
+		max_rect.top = max_rect.left = 0;
+		max_rect.width = vin->format.width;
+		max_rect.height = vin->format.height;
+		v4l2_rect_map_inside(&r, &max_rect);
+
+		/*
+		 * Composing is done by adding a offset to the buffer address,
+		 * the HW wants this address to be aligned to HW_BUFFER_MASK.
+		 * Make sure the top and left values meets this requirement.
+		 */
+		while ((r.top * vin->format.bytesperline) & HW_BUFFER_MASK)
+			r.top--;
+
+		fmt = rvin_format_from_pixel(vin->format.pixelformat);
+		while ((r.left * fmt->bpp) & HW_BUFFER_MASK)
+			r.left--;
+
+		vin->compose = s->r = r;
+
+		vin_dbg(vin, "Compose %dx%d@%d:%d in %dx%d\n",
+			 r.width, r.height, r.left, r.top,
+			 vin->format.width, vin->format.height);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* HW supports modifying configuration while running */
+	rvin_crop_scale_comp(vin);
+
+	return 0;
+}
+
+static int rvin_cropcap(struct file *file, void *priv,
+			struct v4l2_cropcap *crop)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+
+	if (crop->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	return v4l2_subdev_call(sd, video, cropcap, crop);
+}
+
+static int rvin_enum_input(struct file *file, void *priv,
+			   struct v4l2_input *i)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+	int ret;
+
+	if (i->index != 0)
+		return -EINVAL;
+
+	ret = v4l2_subdev_call(sd, video, g_input_status, &i->status);
+	if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		return ret;
+
+	i->type = V4L2_INPUT_TYPE_CAMERA;
+	i->std = vin->vdev.tvnorms;
+
+	if (v4l2_subdev_has_op(sd, pad, dv_timings_cap))
+		i->capabilities = V4L2_IN_CAP_DV_TIMINGS;
+
+	strlcpy(i->name, "Camera", sizeof(i->name));
+
+	return 0;
+}
+
+static int rvin_g_input(struct file *file, void *priv, unsigned int *i)
+{
+	*i = 0;
+	return 0;
+}
+
+static int rvin_s_input(struct file *file, void *priv, unsigned int i)
+{
+	if (i > 0)
+		return -EINVAL;
+	return 0;
+}
+
+static int rvin_querystd(struct file *file, void *priv, v4l2_std_id *a)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+
+	return v4l2_subdev_call(sd, video, querystd, a);
+}
+
+static int rvin_s_std(struct file *file, void *priv, v4l2_std_id a)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+	struct v4l2_subdev_format fmt = {
+		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
+	};
+	struct v4l2_mbus_framefmt *mf = &fmt.format;
+	int ret = v4l2_subdev_call(sd, video, s_std, a);
+
+	if (ret < 0)
+		return ret;
+
+	/* Changing the standard will change the width/height */
+	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt);
+	if (ret) {
+		vin_err(vin, "Failed to get initial format\n");
+		return ret;
+	}
+
+	vin->format.width = mf->width;
+	vin->format.height = mf->height;
+
+	vin->crop.top = vin->crop.left = 0;
+	vin->crop.width = mf->width;
+	vin->crop.height = mf->height;
+
+	vin->compose.top = vin->compose.left = 0;
+	vin->compose.width = mf->width;
+	vin->compose.height = mf->height;
+
+	return 0;
+}
+
+static int rvin_g_std(struct file *file, void *priv, v4l2_std_id *a)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+
+	return v4l2_subdev_call(sd, video, g_std, a);
+}
+
+static int rvin_subscribe_event(struct v4l2_fh *fh,
+				const struct v4l2_event_subscription *sub)
+{
+	switch (sub->type) {
+	case V4L2_EVENT_SOURCE_CHANGE:
+		return v4l2_event_subscribe(fh, sub, 4, NULL);
+	}
+	return v4l2_ctrl_subscribe_event(fh, sub);
+}
+
+static int rvin_enum_dv_timings(struct file *file, void *priv_fh,
+				    struct v4l2_enum_dv_timings *timings)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+	int pad, ret;
+
+	pad = timings->pad;
+	timings->pad = vin->src_pad_idx;
+
+	ret = v4l2_subdev_call(sd, pad, enum_dv_timings, timings);
+
+	timings->pad = pad;
+
+	return ret;
+}
+
+static int rvin_s_dv_timings(struct file *file, void *priv_fh,
+				    struct v4l2_dv_timings *timings)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+	int err;
+
+	err = v4l2_subdev_call(sd,
+			video, s_dv_timings, timings);
+	if (!err) {
+		vin->source.width = timings->bt.width;
+		vin->source.height = timings->bt.height;
+		vin->format.width = timings->bt.width;
+		vin->format.height = timings->bt.height;
+	}
+	return err;
+}
+
+static int rvin_g_dv_timings(struct file *file, void *priv_fh,
+				    struct v4l2_dv_timings *timings)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+
+	return v4l2_subdev_call(sd,
+			video, g_dv_timings, timings);
+}
+
+static int rvin_query_dv_timings(struct file *file, void *priv_fh,
+				    struct v4l2_dv_timings *timings)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+
+	return v4l2_subdev_call(sd,
+			video, query_dv_timings, timings);
+}
+
+static int rvin_dv_timings_cap(struct file *file, void *priv_fh,
+				    struct v4l2_dv_timings_cap *cap)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	struct v4l2_subdev *sd = vin_to_source(vin);
+	int pad, ret;
+
+	pad = cap->pad;
+	cap->pad = vin->src_pad_idx;
+
+	ret = v4l2_subdev_call(sd, pad, dv_timings_cap, cap);
+
+	cap->pad = pad;
+
+	return ret;
+}
+
+static const struct v4l2_ioctl_ops rvin_ioctl_ops = {
+	.vidioc_querycap		= rvin_querycap,
+	.vidioc_try_fmt_vid_cap		= rvin_try_fmt_vid_cap,
+	.vidioc_g_fmt_vid_cap		= rvin_g_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap		= rvin_s_fmt_vid_cap,
+	.vidioc_enum_fmt_vid_cap	= rvin_enum_fmt_vid_cap,
+
+	.vidioc_g_selection		= rvin_g_selection,
+	.vidioc_s_selection		= rvin_s_selection,
+
+	.vidioc_cropcap			= rvin_cropcap,
+
+	.vidioc_enum_input		= rvin_enum_input,
+	.vidioc_g_input			= rvin_g_input,
+	.vidioc_s_input			= rvin_s_input,
+
+	.vidioc_dv_timings_cap		= rvin_dv_timings_cap,
+	.vidioc_enum_dv_timings		= rvin_enum_dv_timings,
+	.vidioc_g_dv_timings		= rvin_g_dv_timings,
+	.vidioc_s_dv_timings		= rvin_s_dv_timings,
+	.vidioc_query_dv_timings	= rvin_query_dv_timings,
+
+	.vidioc_querystd		= rvin_querystd,
+	.vidioc_g_std			= rvin_g_std,
+	.vidioc_s_std			= rvin_s_std,
+
+	.vidioc_reqbufs			= vb2_ioctl_reqbufs,
+	.vidioc_create_bufs		= vb2_ioctl_create_bufs,
+	.vidioc_querybuf		= vb2_ioctl_querybuf,
+	.vidioc_qbuf			= vb2_ioctl_qbuf,
+	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
+	.vidioc_expbuf			= vb2_ioctl_expbuf,
+	.vidioc_prepare_buf		= vb2_ioctl_prepare_buf,
+	.vidioc_streamon		= vb2_ioctl_streamon,
+	.vidioc_streamoff		= vb2_ioctl_streamoff,
+
+	.vidioc_log_status		= v4l2_ctrl_log_status,
+	.vidioc_subscribe_event		= rvin_subscribe_event,
+	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
+};
+
+/* -----------------------------------------------------------------------------
+ * File Operations
+ */
+
+static int rvin_power_on(struct rvin_dev *vin)
+{
+	int ret;
+	struct v4l2_subdev *sd = vin_to_source(vin);
+
+	pm_runtime_get_sync(vin->v4l2_dev.dev);
+
+	ret = v4l2_subdev_call(sd, core, s_power, 1);
+	if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		return ret;
+	return 0;
+}
+
+static int rvin_power_off(struct rvin_dev *vin)
+{
+	int ret;
+	struct v4l2_subdev *sd = vin_to_source(vin);
+
+	ret = v4l2_subdev_call(sd, core, s_power, 0);
+
+	pm_runtime_put(vin->v4l2_dev.dev);
+
+	if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		return ret;
+
+	return 0;
+}
+
+static int rvin_initialize_device(struct file *file)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	int ret;
+
+	struct v4l2_format f = {
+		.type = V4L2_BUF_TYPE_VIDEO_CAPTURE,
+		.fmt.pix = {
+			.width		= vin->format.width,
+			.height		= vin->format.height,
+			.field		= vin->format.field,
+			.colorspace	= vin->format.colorspace,
+			.pixelformat	= vin->format.pixelformat,
+		},
+	};
+
+	ret = rvin_power_on(vin);
+	if (ret < 0)
+		return ret;
+
+	pm_runtime_enable(&vin->vdev.dev);
+	ret = pm_runtime_resume(&vin->vdev.dev);
+	if (ret < 0 && ret != -ENOSYS)
+		goto eresume;
+
+	/*
+	 * Try to configure with default parameters. Notice: this is the
+	 * very first open, so, we cannot race against other calls,
+	 * apart from someone else calling open() simultaneously, but
+	 * .host_lock is protecting us against it.
+	 */
+	ret = rvin_s_fmt_vid_cap(file, NULL, &f);
+	if (ret < 0)
+		goto esfmt;
+
+	v4l2_ctrl_handler_setup(&vin->ctrl_handler);
+
+	return 0;
+esfmt:
+	pm_runtime_disable(&vin->vdev.dev);
+eresume:
+	rvin_power_off(vin);
+
+	return ret;
+}
+
+static int rvin_open(struct file *file)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	int ret;
+
+	mutex_lock(&vin->lock);
+
+	file->private_data = vin;
+
+	ret = v4l2_fh_open(file);
+	if (ret)
+		goto unlock;
+
+	if (!v4l2_fh_is_singular_file(file))
+		goto unlock;
+
+	if (rvin_initialize_device(file)) {
+		v4l2_fh_release(file);
+		ret = -ENODEV;
+	}
+
+unlock:
+	mutex_unlock(&vin->lock);
+	return ret;
+}
+
+static int rvin_release(struct file *file)
+{
+	struct rvin_dev *vin = video_drvdata(file);
+	bool fh_singular;
+	int ret;
+
+	mutex_lock(&vin->lock);
+
+	/* Save the singular status before we call the clean-up helper */
+	fh_singular = v4l2_fh_is_singular_file(file);
+
+	/* the release helper will cleanup any on-going streaming */
+	ret = _vb2_fop_release(file, NULL);
+
+	/*
+	 * If this was the last open file.
+	 * Then de-initialize hw module.
+	 */
+	if (fh_singular) {
+		pm_runtime_suspend(&vin->vdev.dev);
+		pm_runtime_disable(&vin->vdev.dev);
+		rvin_power_off(vin);
+	}
+
+	mutex_unlock(&vin->lock);
+
+	return ret;
+}
+
+static const struct v4l2_file_operations rvin_fops = {
+	.owner		= THIS_MODULE,
+	.unlocked_ioctl	= video_ioctl2,
+	.open		= rvin_open,
+	.release	= rvin_release,
+	.poll		= vb2_fop_poll,
+	.mmap		= vb2_fop_mmap,
+	.read		= vb2_fop_read,
+};
+
+void rvin_v4l2_remove(struct rvin_dev *vin)
+{
+	v4l2_info(&vin->v4l2_dev, "Removing %s\n",
+		  video_device_node_name(&vin->vdev));
+
+	/* Checks internaly if handlers have been init or not */
+	v4l2_ctrl_handler_free(&vin->ctrl_handler);
+
+	/* Checks internaly if vdev have been init or not */
+	video_unregister_device(&vin->vdev);
+}
+
+static void rvin_notify(struct v4l2_subdev *sd,
+			unsigned int notification, void *arg)
+{
+	struct rvin_dev *vin =
+		container_of(sd->v4l2_dev, struct rvin_dev, v4l2_dev);
+
+	switch (notification) {
+	case V4L2_DEVICE_NOTIFY_EVENT:
+		v4l2_event_queue(&vin->vdev, arg);
+		break;
+	default:
+		break;
+	}
+}
+
+int rvin_v4l2_probe(struct rvin_dev *vin)
+{
+	struct v4l2_subdev_format fmt = {
+		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
+	};
+	struct v4l2_mbus_framefmt *mf = &fmt.format;
+	struct video_device *vdev = &vin->vdev;
+	struct v4l2_subdev *sd = vin_to_source(vin);
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	int pad_idx;
+#endif
+	int ret;
+
+	v4l2_set_subdev_hostdata(sd, vin);
+
+	vin->v4l2_dev.notify = rvin_notify;
+
+	ret = v4l2_subdev_call(sd, video, g_tvnorms, &vin->vdev.tvnorms);
+	if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		return ret;
+
+	if (vin->vdev.tvnorms == 0) {
+		/* Disable the STD API if there are no tvnorms defined */
+		v4l2_disable_ioctl(&vin->vdev, VIDIOC_G_STD);
+		v4l2_disable_ioctl(&vin->vdev, VIDIOC_S_STD);
+		v4l2_disable_ioctl(&vin->vdev, VIDIOC_QUERYSTD);
+		v4l2_disable_ioctl(&vin->vdev, VIDIOC_ENUMSTD);
+	}
+
+	/* Add the controls */
+	/*
+	 * Currently the subdev with the largest number of controls (13) is
+	 * ov6550. So let's pick 16 as a hint for the control handler. Note
+	 * that this is a hint only: too large and you waste some memory, too
+	 * small and there is a (very) small performance hit when looking up
+	 * controls in the internal hash.
+	 */
+	ret = v4l2_ctrl_handler_init(&vin->ctrl_handler, 16);
+	if (ret < 0)
+		return ret;
+
+	ret = v4l2_ctrl_add_handler(&vin->ctrl_handler, sd->ctrl_handler, NULL);
+	if (ret < 0)
+		return ret;
+
+	/* video node */
+	vdev->fops = &rvin_fops;
+	vdev->v4l2_dev = &vin->v4l2_dev;
+	vdev->queue = &vin->queue;
+	strlcpy(vdev->name, KBUILD_MODNAME, sizeof(vdev->name));
+	vdev->release = video_device_release_empty;
+	vdev->ioctl_ops = &rvin_ioctl_ops;
+	vdev->lock = &vin->lock;
+	vdev->ctrl_handler = &vin->ctrl_handler;
+	vdev->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING |
+		V4L2_CAP_READWRITE;
+
+	vin->src_pad_idx = 0;
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	for (pad_idx = 0; pad_idx < sd->entity.num_pads; pad_idx++)
+		if (sd->entity.pads[pad_idx].flags
+				== MEDIA_PAD_FL_SOURCE)
+			break;
+	if (pad_idx >= sd->entity.num_pads)
+		return -EINVAL;
+
+	vin->src_pad_idx = pad_idx;
+#endif
+	fmt.pad = vin->src_pad_idx;
+
+	/* Try to improve our guess of a reasonable window format */
+	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt);
+	if (ret) {
+		vin_err(vin, "Failed to get initial format\n");
+		return ret;
+	}
+
+	/* Set default format */
+	vin->format.width	= mf->width;
+	vin->format.height	= mf->height;
+	vin->format.colorspace	= mf->colorspace;
+	vin->format.field	= mf->field;
+	vin->format.pixelformat	= RVIN_DEFAULT_FORMAT;
+
+
+	/* Set initial crop and compose */
+	vin->crop.top = vin->crop.left = 0;
+	vin->crop.width = mf->width;
+	vin->crop.height = mf->height;
+
+	vin->compose.top = vin->compose.left = 0;
+	vin->compose.width = mf->width;
+	vin->compose.height = mf->height;
+
+	ret = video_register_device(&vin->vdev, VFL_TYPE_GRABBER, -1);
+	if (ret) {
+		vin_err(vin, "Failed to register video device\n");
+		return ret;
+	}
+
+	video_set_drvdata(&vin->vdev, vin);
+
+	v4l2_info(&vin->v4l2_dev, "Device registered as %s\n",
+		  video_device_node_name(&vin->vdev));
+
+	return ret;
+}
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
new file mode 100644
index 000000000000..31ad39a39937
--- /dev/null
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -0,0 +1,163 @@
+/*
+ * Driver for Renesas R-Car VIN
+ *
+ * Copyright (C) 2016 Renesas Electronics Corp.
+ * Copyright (C) 2011-2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Cogent Embedded, Inc., <source@cogentembedded.com>
+ * Copyright (C) 2008 Magnus Damm
+ *
+ * Based on the soc-camera rcar_vin driver
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __RCAR_VIN__
+#define __RCAR_VIN__
+
+#include <media/v4l2-async.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
+#include <media/videobuf2-v4l2.h>
+
+/* Number of HW buffers */
+#define HW_BUFFER_NUM 3
+
+/* Address alignment mask for HW buffers */
+#define HW_BUFFER_MASK 0x7f
+
+enum chip_id {
+	RCAR_GEN2,
+	RCAR_H1,
+	RCAR_M1,
+};
+
+/**
+ * STOPPED  - No operation in progress
+ * RUNNING  - Operation in progress have buffers
+ * STALLED  - No operation in progress have no buffers
+ * STOPPING - Stopping operation
+ */
+enum rvin_dma_state {
+	STOPPED = 0,
+	RUNNING,
+	STALLED,
+	STOPPING,
+};
+
+/**
+ * struct rvin_source_fmt - Source information
+ * @code:	Media bus format from source
+ * @width:	Width from source
+ * @height:	Height from source
+ */
+struct rvin_source_fmt {
+	u32 code;
+	u32 width;
+	u32 height;
+};
+
+/**
+ * struct rvin_video_format - Data format stored in memory
+ * @fourcc:	Pixelformat
+ * @bpp:	Bytes per pixel
+ */
+struct rvin_video_format {
+	u32 fourcc;
+	u8 bpp;
+};
+
+struct rvin_graph_entity {
+	struct device_node *node;
+	struct media_entity *entity;
+
+	struct v4l2_async_subdev asd;
+	struct v4l2_subdev *subdev;
+};
+
+/**
+ * struct rvin_dev - Renesas VIN device structure
+ * @dev:		(OF) device
+ * @base:		device I/O register space remapped to virtual memory
+ * @chip:		type of VIN chip
+ * @mbus_cfg		media bus configuration
+ *
+ * @vdev:		V4L2 video device associated with VIN
+ * @v4l2_dev:		V4L2 device
+ * @src_pad_idx:	source pad index for media controller drivers
+ * @ctrl_handler:	V4L2 control handler
+ * @notifier:		V4L2 asynchronous subdevs notifier
+ * @entity:		entity in the DT for subdevice
+ *
+ * @lock:		protects @queue
+ * @queue:		vb2 buffers queue
+ *
+ * @qlock:		protects @queue_buf, @buf_list, @continuous, @sequence
+ *			@state
+ * @queue_buf:		Keeps track of buffers given to HW slot
+ * @buf_list:		list of queued buffers
+ * @continuous:		tracks if active operation is continuous or single mode
+ * @sequence:		V4L2 buffers sequence number
+ * @state:		keeps track of operation state
+ *
+ * @source:		active format from the video source
+ * @format:		active V4L2 pixel format
+ *
+ * @crop:		active cropping
+ * @compose:		active composing
+ */
+struct rvin_dev {
+	struct device *dev;
+	void __iomem *base;
+	enum chip_id chip;
+	struct v4l2_mbus_config mbus_cfg;
+
+	struct video_device vdev;
+	struct v4l2_device v4l2_dev;
+	int src_pad_idx;
+	struct v4l2_ctrl_handler ctrl_handler;
+	struct v4l2_async_notifier notifier;
+	struct rvin_graph_entity entity;
+
+	struct mutex lock;
+	struct vb2_queue queue;
+
+	spinlock_t qlock;
+	struct vb2_v4l2_buffer *queue_buf[HW_BUFFER_NUM];
+	struct list_head buf_list;
+	bool continuous;
+	unsigned int sequence;
+	enum rvin_dma_state state;
+
+	struct rvin_source_fmt source;
+	struct v4l2_pix_format format;
+
+	struct v4l2_rect crop;
+	struct v4l2_rect compose;
+};
+
+#define vin_to_source(vin)		vin->entity.subdev
+
+/* Debug */
+#define vin_dbg(d, fmt, arg...)		dev_dbg(d->dev, fmt, ##arg)
+#define vin_info(d, fmt, arg...)	dev_info(d->dev, fmt, ##arg)
+#define vin_warn(d, fmt, arg...)	dev_warn(d->dev, fmt, ##arg)
+#define vin_err(d, fmt, arg...)		dev_err(d->dev, fmt, ##arg)
+
+int rvin_dma_probe(struct rvin_dev *vin, int irq);
+void rvin_dma_remove(struct rvin_dev *vin);
+
+int rvin_v4l2_probe(struct rvin_dev *vin);
+void rvin_v4l2_remove(struct rvin_dev *vin);
+
+const struct rvin_video_format *rvin_format_from_pixel(u32 pixelformat);
+
+/* Cropping, composing and scaling */
+void rvin_scale_try(struct rvin_dev *vin, struct v4l2_pix_format *pix,
+		    u32 width, u32 height);
+void rvin_crop_scale_comp(struct rvin_dev *vin);
+
+#endif
diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index 552789a69c86..16782ceb29c3 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -203,7 +203,6 @@
  * @irq: JPEG IP irq
  * @clk: JPEG IP clock
  * @dev: JPEG IP struct device
- * @alloc_ctx: videobuf2 memory allocator's context
  * @ref_count: reference counter
  */
 struct jpu {
@@ -220,7 +219,6 @@ struct jpu {
 	unsigned int		irq;
 	struct clk		*clk;
 	struct device		*dev;
-	void			*alloc_ctx;
 	int			ref_count;
 };
 
@@ -1016,7 +1014,7 @@ error_free:
  */
 static int jpu_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct jpu_ctx *ctx = vb2_get_drv_priv(vq);
 	struct jpu_q_data *q_data;
@@ -1033,17 +1031,14 @@ static int jpu_queue_setup(struct vb2_queue *vq,
 
 			if (sizes[i] < q_size)
 				return -EINVAL;
-			alloc_ctxs[i] = ctx->jpu->alloc_ctx;
 		}
 		return 0;
 	}
 
 	*nplanes = q_data->format.num_planes;
 
-	for (i = 0; i < *nplanes; i++) {
+	for (i = 0; i < *nplanes; i++)
 		sizes[i] = q_data->format.plane_fmt[i].sizeimage;
-		alloc_ctxs[i] = ctx->jpu->alloc_ctx;
-	}
 
 	return 0;
 }
@@ -1214,6 +1209,7 @@ static int jpu_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &ctx->jpu->mutex;
+	src_vq->dev = ctx->jpu->v4l2_dev.dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -1228,6 +1224,7 @@ static int jpu_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &ctx->jpu->mutex;
+	dst_vq->dev = ctx->jpu->v4l2_dev.dev;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -1676,13 +1673,6 @@ static int jpu_probe(struct platform_device *pdev)
 		goto device_register_rollback;
 	}
 
-	jpu->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(jpu->alloc_ctx)) {
-		v4l2_err(&jpu->v4l2_dev, "Failed to init memory allocator\n");
-		ret = PTR_ERR(jpu->alloc_ctx);
-		goto m2m_init_rollback;
-	}
-
 	/* fill in qantization and Huffman tables for encoder */
 	for (i = 0; i < JPU_MAX_QUALITY; i++)
 		jpu_generate_hdr(i, (unsigned char *)jpeg_hdrs[i]);
@@ -1699,7 +1689,7 @@ static int jpu_probe(struct platform_device *pdev)
 	ret = video_register_device(&jpu->vfd_encoder, VFL_TYPE_GRABBER, -1);
 	if (ret) {
 		v4l2_err(&jpu->v4l2_dev, "Failed to register video device\n");
-		goto vb2_allocator_rollback;
+		goto m2m_init_rollback;
 	}
 
 	video_set_drvdata(&jpu->vfd_encoder, jpu);
@@ -1732,9 +1722,6 @@ static int jpu_probe(struct platform_device *pdev)
 enc_vdev_register_rollback:
 	video_unregister_device(&jpu->vfd_encoder);
 
-vb2_allocator_rollback:
-	vb2_dma_contig_cleanup_ctx(jpu->alloc_ctx);
-
 m2m_init_rollback:
 	v4l2_m2m_release(jpu->m2m_dev);
 
@@ -1750,7 +1737,6 @@ static int jpu_remove(struct platform_device *pdev)
 
 	video_unregister_device(&jpu->vfd_decoder);
 	video_unregister_device(&jpu->vfd_encoder);
-	vb2_dma_contig_cleanup_ctx(jpu->alloc_ctx);
 	v4l2_m2m_release(jpu->m2m_dev);
 	v4l2_device_unregister(&jpu->v4l2_dev);
 
diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
index bd060ef5d1e1..0413a861a59a 100644
--- a/drivers/media/platform/s3c-camif/camif-capture.c
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -437,10 +437,9 @@ static void stop_streaming(struct vb2_queue *vq)
 
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *num_buffers, unsigned int *num_planes,
-		       unsigned int sizes[], void *allocators[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct camif_vp *vp = vb2_get_drv_priv(vq);
-	struct camif_dev *camif = vp->camif;
 	struct camif_frame *frame = &vp->out_frame;
 	const struct camif_fmt *fmt = vp->out_fmt;
 	unsigned int size;
@@ -449,7 +448,6 @@ static int queue_setup(struct vb2_queue *vq,
 		return -EINVAL;
 
 	size = (frame->f_width * frame->f_height * fmt->depth) / 8;
-	allocators[0] = camif->alloc_ctx;
 
 	if (*num_planes)
 		return sizes[0] < size ? -EINVAL : 0;
@@ -1138,6 +1136,7 @@ int s3c_camif_register_video_node(struct camif_dev *camif, int idx)
 	q->drv_priv = vp;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &vp->camif->lock;
+	q->dev = camif->v4l2_dev.dev;
 
 	ret = vb2_queue_init(q);
 	if (ret)
diff --git a/drivers/media/platform/s3c-camif/camif-core.c b/drivers/media/platform/s3c-camif/camif-core.c
index af237af204e2..ec4001970313 100644
--- a/drivers/media/platform/s3c-camif/camif-core.c
+++ b/drivers/media/platform/s3c-camif/camif-core.c
@@ -474,16 +474,9 @@ static int s3c_camif_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_pm;
 
-	/* Initialize contiguous memory allocator */
-	camif->alloc_ctx = vb2_dma_contig_init_ctx(dev);
-	if (IS_ERR(camif->alloc_ctx)) {
-		ret = PTR_ERR(camif->alloc_ctx);
-		goto err_alloc;
-	}
-
 	ret = camif_media_dev_init(camif);
 	if (ret < 0)
-		goto err_mdev;
+		goto err_alloc;
 
 	ret = camif_register_sensor(camif);
 	if (ret < 0)
@@ -517,8 +510,6 @@ err_sens:
 	media_device_unregister(&camif->media_dev);
 	media_device_cleanup(&camif->media_dev);
 	camif_unregister_media_entities(camif);
-err_mdev:
-	vb2_dma_contig_cleanup_ctx(camif->alloc_ctx);
 err_alloc:
 	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
diff --git a/drivers/media/platform/s3c-camif/camif-core.h b/drivers/media/platform/s3c-camif/camif-core.h
index 57cbc3d9725d..1f5c8c94ce89 100644
--- a/drivers/media/platform/s3c-camif/camif-core.h
+++ b/drivers/media/platform/s3c-camif/camif-core.h
@@ -254,7 +254,6 @@ struct camif_vp {
  * @ctrl_handler: v4l2 control handler (owned by @subdev)
  * @test_pattern: test pattern controls
  * @vp:           video path (DMA) description (codec/preview)
- * @alloc_ctx:    memory buffer allocator context
  * @variant:      variant information for this device
  * @dev:	  pointer to the CAMIF device struct
  * @pdata:	  a copy of the driver's platform data
@@ -291,7 +290,6 @@ struct camif_dev {
 	u8				colorfx_cr;
 
 	struct camif_vp			vp[CAMIF_VP_NUM];
-	struct vb2_alloc_ctx		*alloc_ctx;
 
 	const struct s3c_camif_variant	*variant;
 	struct device			*dev;
diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 612d1ea514f1..391dd7a7b362 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -103,7 +103,7 @@ static struct g2d_frame *get_frame(struct g2d_ctx *ctx,
 
 static int g2d_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct g2d_ctx *ctx = vb2_get_drv_priv(vq);
 	struct g2d_frame *f = get_frame(ctx, vq->type);
@@ -113,7 +113,6 @@ static int g2d_queue_setup(struct vb2_queue *vq,
 
 	sizes[0] = f->size;
 	*nplanes = 1;
-	alloc_ctxs[0] = ctx->dev->alloc_ctx;
 
 	if (*nbuffers == 0)
 		*nbuffers = 1;
@@ -159,6 +158,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &ctx->dev->mutex;
+	src_vq->dev = ctx->dev->v4l2_dev.dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -172,6 +172,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &ctx->dev->mutex;
+	dst_vq->dev = ctx->dev->v4l2_dev.dev;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -681,15 +682,11 @@ static int g2d_probe(struct platform_device *pdev)
 		goto put_clk_gate;
 	}
 
-	dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		ret = PTR_ERR(dev->alloc_ctx);
-		goto unprep_clk_gate;
-	}
+	vb2_dma_contig_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));
 
 	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
 	if (ret)
-		goto alloc_ctx_cleanup;
+		goto unprep_clk_gate;
 	vfd = video_device_alloc();
 	if (!vfd) {
 		v4l2_err(&dev->v4l2_dev, "Failed to allocate video device\n");
@@ -734,8 +731,6 @@ rel_vdev:
 	video_device_release(vfd);
 unreg_v4l2_dev:
 	v4l2_device_unregister(&dev->v4l2_dev);
-alloc_ctx_cleanup:
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
 unprep_clk_gate:
 	clk_unprepare(dev->gate);
 put_clk_gate:
@@ -756,7 +751,7 @@ static int g2d_remove(struct platform_device *pdev)
 	v4l2_m2m_release(dev->m2m_dev);
 	video_unregister_device(dev->vfd);
 	v4l2_device_unregister(&dev->v4l2_dev);
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
+	vb2_dma_contig_clear_max_seg_size(&pdev->dev);
 	clk_unprepare(dev->gate);
 	clk_put(dev->gate);
 	clk_unprepare(dev->clk);
diff --git a/drivers/media/platform/s5p-g2d/g2d.h b/drivers/media/platform/s5p-g2d/g2d.h
index e31df541aa62..dd812b557e87 100644
--- a/drivers/media/platform/s5p-g2d/g2d.h
+++ b/drivers/media/platform/s5p-g2d/g2d.h
@@ -25,7 +25,6 @@ struct g2d_dev {
 	struct mutex		mutex;
 	spinlock_t		ctrl_lock;
 	atomic_t		num_inst;
-	struct vb2_alloc_ctx	*alloc_ctx;
 	void __iomem		*regs;
 	struct clk		*clk;
 	struct clk		*gate;
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index caa19b408551..785e6936c881 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -2436,7 +2436,7 @@ static struct v4l2_m2m_ops exynos4_jpeg_m2m_ops = {
 
 static int s5p_jpeg_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct s5p_jpeg_ctx *ctx = vb2_get_drv_priv(vq);
 	struct s5p_jpeg_q_data *q_data = NULL;
@@ -2457,7 +2457,6 @@ static int s5p_jpeg_queue_setup(struct vb2_queue *vq,
 	*nbuffers = count;
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = ctx->jpeg->alloc_ctx;
 
 	return 0;
 }
@@ -2563,6 +2562,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &ctx->jpeg->lock;
+	src_vq->dev = ctx->jpeg->dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -2576,6 +2576,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &ctx->jpeg->lock;
+	dst_vq->dev = ctx->jpeg->dev;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -2843,19 +2844,14 @@ static int s5p_jpeg_probe(struct platform_device *pdev)
 		goto device_register_rollback;
 	}
 
-	jpeg->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(jpeg->alloc_ctx)) {
-		v4l2_err(&jpeg->v4l2_dev, "Failed to init memory allocator\n");
-		ret = PTR_ERR(jpeg->alloc_ctx);
-		goto m2m_init_rollback;
-	}
+	vb2_dma_contig_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));
 
 	/* JPEG encoder /dev/videoX node */
 	jpeg->vfd_encoder = video_device_alloc();
 	if (!jpeg->vfd_encoder) {
 		v4l2_err(&jpeg->v4l2_dev, "Failed to allocate video device\n");
 		ret = -ENOMEM;
-		goto vb2_allocator_rollback;
+		goto m2m_init_rollback;
 	}
 	snprintf(jpeg->vfd_encoder->name, sizeof(jpeg->vfd_encoder->name),
 				"%s-enc", S5P_JPEG_M2M_NAME);
@@ -2871,7 +2867,7 @@ static int s5p_jpeg_probe(struct platform_device *pdev)
 	if (ret) {
 		v4l2_err(&jpeg->v4l2_dev, "Failed to register video device\n");
 		video_device_release(jpeg->vfd_encoder);
-		goto vb2_allocator_rollback;
+		goto m2m_init_rollback;
 	}
 
 	video_set_drvdata(jpeg->vfd_encoder, jpeg);
@@ -2920,9 +2916,6 @@ static int s5p_jpeg_probe(struct platform_device *pdev)
 enc_vdev_register_rollback:
 	video_unregister_device(jpeg->vfd_encoder);
 
-vb2_allocator_rollback:
-	vb2_dma_contig_cleanup_ctx(jpeg->alloc_ctx);
-
 m2m_init_rollback:
 	v4l2_m2m_release(jpeg->m2m_dev);
 
@@ -2941,7 +2934,7 @@ static int s5p_jpeg_remove(struct platform_device *pdev)
 
 	video_unregister_device(jpeg->vfd_decoder);
 	video_unregister_device(jpeg->vfd_encoder);
-	vb2_dma_contig_cleanup_ctx(jpeg->alloc_ctx);
+	vb2_dma_contig_clear_max_seg_size(&pdev->dev);
 	v4l2_m2m_release(jpeg->m2m_dev);
 	v4l2_device_unregister(&jpeg->v4l2_dev);
 
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.h b/drivers/media/platform/s5p-jpeg/jpeg-core.h
index 9b1db0934909..4492a3535df5 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.h
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.h
@@ -110,7 +110,6 @@ enum  exynos4_jpeg_img_quality_level {
  * @irq:		JPEG IP irq
  * @clocks:		JPEG IP clock(s)
  * @dev:		JPEG IP struct device
- * @alloc_ctx:		videobuf2 memory allocator's context
  * @variant:		driver variant to be used
  * @irq_status		interrupt flags set during single encode/decode
 			operation
@@ -130,7 +129,6 @@ struct s5p_jpeg {
 	enum exynos4_jpeg_result irq_ret;
 	struct clk		*clocks[JPEG_MAX_CLOCKS];
 	struct device		*dev;
-	void			*alloc_ctx;
 	struct s5p_jpeg_variant *variant;
 	u32			irq_status;
 };
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index b16466fe35ee..e3f104fafd0a 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -22,6 +22,7 @@
 #include <media/v4l2-event.h>
 #include <linux/workqueue.h>
 #include <linux/of.h>
+#include <linux/of_reserved_mem.h>
 #include <media/videobuf2-v4l2.h>
 #include "s5p_mfc_common.h"
 #include "s5p_mfc_ctrl.h"
@@ -29,11 +30,11 @@
 #include "s5p_mfc_dec.h"
 #include "s5p_mfc_enc.h"
 #include "s5p_mfc_intr.h"
+#include "s5p_mfc_iommu.h"
 #include "s5p_mfc_opr.h"
 #include "s5p_mfc_cmd.h"
 #include "s5p_mfc_pm.h"
 
-#define S5P_MFC_NAME		"s5p-mfc"
 #define S5P_MFC_DEC_NAME	"s5p-mfc-dec"
 #define S5P_MFC_ENC_NAME	"s5p-mfc-enc"
 
@@ -1043,55 +1044,94 @@ static const struct v4l2_file_operations s5p_mfc_fops = {
 	.mmap = s5p_mfc_mmap,
 };
 
-static int match_child(struct device *dev, void *data)
+/* DMA memory related helper functions */
+static void s5p_mfc_memdev_release(struct device *dev)
 {
-	if (!dev_name(dev))
-		return 0;
-	return !strcmp(dev_name(dev), (char *)data);
+	of_reserved_mem_device_release(dev);
 }
 
-static void *mfc_get_drv_data(struct platform_device *pdev);
-
-static int s5p_mfc_alloc_memdevs(struct s5p_mfc_dev *dev)
+static struct device *s5p_mfc_alloc_memdev(struct device *dev,
+					   const char *name, unsigned int idx)
 {
-	unsigned int mem_info[2] = { };
+	struct device *child;
+	int ret;
 
-	dev->mem_dev_l = devm_kzalloc(&dev->plat_dev->dev,
-			sizeof(struct device), GFP_KERNEL);
-	if (!dev->mem_dev_l) {
-		mfc_err("Not enough memory\n");
-		return -ENOMEM;
-	}
-	device_initialize(dev->mem_dev_l);
-	of_property_read_u32_array(dev->plat_dev->dev.of_node,
-			"samsung,mfc-l", mem_info, 2);
-	if (dma_declare_coherent_memory(dev->mem_dev_l, mem_info[0],
-				mem_info[0], mem_info[1],
-				DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE) == 0) {
-		mfc_err("Failed to declare coherent memory for\n"
-		"MFC device\n");
-		return -ENOMEM;
+	child = devm_kzalloc(dev, sizeof(struct device), GFP_KERNEL);
+	if (!child)
+		return NULL;
+
+	device_initialize(child);
+	dev_set_name(child, "%s:%s", dev_name(dev), name);
+	child->parent = dev;
+	child->bus = dev->bus;
+	child->coherent_dma_mask = dev->coherent_dma_mask;
+	child->dma_mask = dev->dma_mask;
+	child->release = s5p_mfc_memdev_release;
+
+	if (device_add(child) == 0) {
+		ret = of_reserved_mem_device_init_by_idx(child, dev->of_node,
+							 idx);
+		if (ret == 0)
+			return child;
 	}
 
-	dev->mem_dev_r = devm_kzalloc(&dev->plat_dev->dev,
-			sizeof(struct device), GFP_KERNEL);
-	if (!dev->mem_dev_r) {
-		mfc_err("Not enough memory\n");
-		return -ENOMEM;
+	put_device(child);
+	return NULL;
+}
+
+static int s5p_mfc_configure_dma_memory(struct s5p_mfc_dev *mfc_dev)
+{
+	struct device *dev = &mfc_dev->plat_dev->dev;
+
+	/*
+	 * When IOMMU is available, we cannot use the default configuration,
+	 * because of MFC firmware requirements: address space limited to
+	 * 256M and non-zero default start address.
+	 * This is still simplified, not optimal configuration, but for now
+	 * IOMMU core doesn't allow to configure device's IOMMUs channel
+	 * separately.
+	 */
+	if (exynos_is_iommu_available(dev)) {
+		int ret = exynos_configure_iommu(dev, S5P_MFC_IOMMU_DMA_BASE,
+						 S5P_MFC_IOMMU_DMA_SIZE);
+		if (ret == 0)
+			mfc_dev->mem_dev_l = mfc_dev->mem_dev_r = dev;
+		return ret;
 	}
-	device_initialize(dev->mem_dev_r);
-	of_property_read_u32_array(dev->plat_dev->dev.of_node,
-			"samsung,mfc-r", mem_info, 2);
-	if (dma_declare_coherent_memory(dev->mem_dev_r, mem_info[0],
-				mem_info[0], mem_info[1],
-				DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE) == 0) {
-		pr_err("Failed to declare coherent memory for\n"
-		"MFC device\n");
-		return -ENOMEM;
+
+	/*
+	 * Create and initialize virtual devices for accessing
+	 * reserved memory regions.
+	 */
+	mfc_dev->mem_dev_l = s5p_mfc_alloc_memdev(dev, "left",
+						  MFC_BANK1_ALLOC_CTX);
+	if (!mfc_dev->mem_dev_l)
+		return -ENODEV;
+	mfc_dev->mem_dev_r = s5p_mfc_alloc_memdev(dev, "right",
+						  MFC_BANK2_ALLOC_CTX);
+	if (!mfc_dev->mem_dev_r) {
+		device_unregister(mfc_dev->mem_dev_l);
+		return -ENODEV;
 	}
+
 	return 0;
 }
 
+static void s5p_mfc_unconfigure_dma_memory(struct s5p_mfc_dev *mfc_dev)
+{
+	struct device *dev = &mfc_dev->plat_dev->dev;
+
+	if (exynos_is_iommu_available(dev)) {
+		exynos_unconfigure_iommu(dev);
+		return;
+	}
+
+	device_unregister(mfc_dev->mem_dev_l);
+	device_unregister(mfc_dev->mem_dev_r);
+}
+
+static void *mfc_get_drv_data(struct platform_device *pdev);
+
 /* MFC probe function */
 static int s5p_mfc_probe(struct platform_device *pdev)
 {
@@ -1117,14 +1157,11 @@ static int s5p_mfc_probe(struct platform_device *pdev)
 
 	dev->variant = mfc_get_drv_data(pdev);
 
-	ret = s5p_mfc_init_pm(dev);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to get mfc clock source\n");
-		return ret;
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
+	if (res == NULL) {
+		dev_err(&pdev->dev, "failed to get io resource\n");
+		return -ENOENT;
+	}
 	dev->regs_base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(dev->regs_base))
 		return PTR_ERR(dev->regs_base);
@@ -1132,54 +1169,36 @@ static int s5p_mfc_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (res == NULL) {
 		dev_err(&pdev->dev, "failed to get irq resource\n");
-		ret = -ENOENT;
-		goto err_res;
+		return -ENOENT;
 	}
 	dev->irq = res->start;
 	ret = devm_request_irq(&pdev->dev, dev->irq, s5p_mfc_irq,
 					0, pdev->name, dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to install irq (%d)\n", ret);
-		goto err_res;
+		return ret;
 	}
 
-	if (pdev->dev.of_node) {
-		ret = s5p_mfc_alloc_memdevs(dev);
-		if (ret < 0)
-			goto err_res;
-	} else {
-		dev->mem_dev_l = device_find_child(&dev->plat_dev->dev,
-				"s5p-mfc-l", match_child);
-		if (!dev->mem_dev_l) {
-			mfc_err("Mem child (L) device get failed\n");
-			ret = -ENODEV;
-			goto err_res;
-		}
-		dev->mem_dev_r = device_find_child(&dev->plat_dev->dev,
-				"s5p-mfc-r", match_child);
-		if (!dev->mem_dev_r) {
-			mfc_err("Mem child (R) device get failed\n");
-			ret = -ENODEV;
-			goto err_res;
-		}
+	ret = s5p_mfc_configure_dma_memory(dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to configure DMA memory\n");
+		return ret;
 	}
 
-	dev->alloc_ctx[0] = vb2_dma_contig_init_ctx(dev->mem_dev_l);
-	if (IS_ERR(dev->alloc_ctx[0])) {
-		ret = PTR_ERR(dev->alloc_ctx[0]);
-		goto err_res;
-	}
-	dev->alloc_ctx[1] = vb2_dma_contig_init_ctx(dev->mem_dev_r);
-	if (IS_ERR(dev->alloc_ctx[1])) {
-		ret = PTR_ERR(dev->alloc_ctx[1]);
-		goto err_mem_init_ctx_1;
+	ret = s5p_mfc_init_pm(dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to get mfc clock source\n");
+		goto err_dma;
 	}
 
+	vb2_dma_contig_set_max_seg_size(dev->mem_dev_l, DMA_BIT_MASK(32));
+	vb2_dma_contig_set_max_seg_size(dev->mem_dev_r, DMA_BIT_MASK(32));
+
 	mutex_init(&dev->mfc_mutex);
 
 	ret = s5p_mfc_alloc_firmware(dev);
 	if (ret)
-		goto err_alloc_fw;
+		goto err_res;
 
 	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
 	if (ret)
@@ -1201,14 +1220,6 @@ static int s5p_mfc_probe(struct platform_device *pdev)
 	vfd->vfl_dir	= VFL_DIR_M2M;
 	snprintf(vfd->name, sizeof(vfd->name), "%s", S5P_MFC_DEC_NAME);
 	dev->vfd_dec	= vfd;
-	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
-	if (ret) {
-		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
-		video_device_release(vfd);
-		goto err_dec_reg;
-	}
-	v4l2_info(&dev->v4l2_dev,
-		  "decoder registered as /dev/video%d\n", vfd->num);
 	video_set_drvdata(vfd, dev);
 
 	/* encoder */
@@ -1226,14 +1237,6 @@ static int s5p_mfc_probe(struct platform_device *pdev)
 	vfd->vfl_dir	= VFL_DIR_M2M;
 	snprintf(vfd->name, sizeof(vfd->name), "%s", S5P_MFC_ENC_NAME);
 	dev->vfd_enc	= vfd;
-	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
-	if (ret) {
-		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
-		video_device_release(vfd);
-		goto err_enc_reg;
-	}
-	v4l2_info(&dev->v4l2_dev,
-		  "encoder registered as /dev/video%d\n", vfd->num);
 	video_set_drvdata(vfd, dev);
 	platform_set_drvdata(pdev, dev);
 
@@ -1250,26 +1253,41 @@ static int s5p_mfc_probe(struct platform_device *pdev)
 	s5p_mfc_init_hw_cmds(dev);
 	s5p_mfc_init_regs(dev);
 
+	/* Register decoder and encoder */
+	ret = video_register_device(dev->vfd_dec, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
+		goto err_dec_reg;
+	}
+	v4l2_info(&dev->v4l2_dev,
+		  "decoder registered as /dev/video%d\n", dev->vfd_dec->num);
+
+	ret = video_register_device(dev->vfd_enc, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
+		goto err_enc_reg;
+	}
+	v4l2_info(&dev->v4l2_dev,
+		  "encoder registered as /dev/video%d\n", dev->vfd_enc->num);
+
 	pr_debug("%s--\n", __func__);
 	return 0;
 
 /* Deinit MFC if probe had failed */
 err_enc_reg:
-	video_device_release(dev->vfd_enc);
-err_enc_alloc:
 	video_unregister_device(dev->vfd_dec);
 err_dec_reg:
+	video_device_release(dev->vfd_enc);
+err_enc_alloc:
 	video_device_release(dev->vfd_dec);
 err_dec_alloc:
 	v4l2_device_unregister(&dev->v4l2_dev);
 err_v4l2_dev_reg:
 	s5p_mfc_release_firmware(dev);
-err_alloc_fw:
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx[1]);
-err_mem_init_ctx_1:
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx[0]);
 err_res:
 	s5p_mfc_final_pm(dev);
+err_dma:
+	s5p_mfc_unconfigure_dma_memory(dev);
 
 	pr_debug("%s-- with error\n", __func__);
 	return ret;
@@ -1289,14 +1307,13 @@ static int s5p_mfc_remove(struct platform_device *pdev)
 
 	video_unregister_device(dev->vfd_enc);
 	video_unregister_device(dev->vfd_dec);
+	video_device_release(dev->vfd_enc);
+	video_device_release(dev->vfd_dec);
 	v4l2_device_unregister(&dev->v4l2_dev);
 	s5p_mfc_release_firmware(dev);
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx[0]);
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx[1]);
-	if (pdev->dev.of_node) {
-		put_device(dev->mem_dev_l);
-		put_device(dev->mem_dev_r);
-	}
+	s5p_mfc_unconfigure_dma_memory(dev);
+	vb2_dma_contig_clear_max_seg_size(dev->mem_dev_l);
+	vb2_dma_contig_clear_max_seg_size(dev->mem_dev_r);
 
 	s5p_mfc_final_pm(dev);
 	return 0;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
index 9eb2481ec292..373e346fce3e 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
@@ -25,6 +25,8 @@
 #include "regs-mfc.h"
 #include "regs-mfc-v8.h"
 
+#define S5P_MFC_NAME		"s5p-mfc"
+
 /* Definitions related to MFC memory */
 
 /* Offset base used to differentiate between CAPTURE and OUTPUT
@@ -285,7 +287,6 @@ struct s5p_mfc_priv_buf {
  * @watchdog_cnt:	counter for the watchdog
  * @watchdog_workqueue:	workqueue for the watchdog
  * @watchdog_work:	worker for the watchdog
- * @alloc_ctx:		videobuf2 allocator contexts for two memory banks
  * @enter_suspend:	flag set when entering suspend
  * @ctx_buf:		common context memory (MFCv6)
  * @warn_start:		hardware error code from which warnings start
@@ -328,7 +329,6 @@ struct s5p_mfc_dev {
 	struct timer_list watchdog_timer;
 	struct workqueue_struct *watchdog_workqueue;
 	struct work_struct watchdog_work;
-	void *alloc_ctx[2];
 	unsigned long enter_suspend;
 
 	struct s5p_mfc_priv_buf ctx_buf;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
index f2d6376ce618..47c997d9e8cb 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
@@ -265,9 +265,10 @@ static int vidioc_querycap(struct file *file, void *priv,
 {
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 
-	strncpy(cap->driver, dev->plat_dev->name, sizeof(cap->driver) - 1);
-	strncpy(cap->card, dev->plat_dev->name, sizeof(cap->card) - 1);
-	cap->bus_info[0] = 0;
+	strncpy(cap->driver, S5P_MFC_NAME, sizeof(cap->driver) - 1);
+	strncpy(cap->card, dev->vfd_dec->name, sizeof(cap->card) - 1);
+	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
+		 dev_name(&dev->plat_dev->dev));
 	/*
 	 * This is only a mem-to-mem video device. The capture and output
 	 * device capability flags are left only for backward compatibility
@@ -423,7 +424,7 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 	pix_mp = &f->fmt.pix_mp;
 	if (ret)
 		return ret;
-	if (ctx->vq_src.streaming || ctx->vq_dst.streaming) {
+	if (vb2_is_streaming(&ctx->vq_src) || vb2_is_streaming(&ctx->vq_dst)) {
 		v4l2_err(&dev->v4l2_dev, "%s queue busy\n", __func__);
 		ret = -EBUSY;
 		goto out;
@@ -474,7 +475,6 @@ static int reqbufs_output(struct s5p_mfc_dev *dev, struct s5p_mfc_ctx *ctx,
 		ret = vb2_reqbufs(&ctx->vq_src, reqbufs);
 		if (ret)
 			goto out;
-		s5p_mfc_close_mfc_inst(dev, ctx);
 		ctx->src_bufs_cnt = 0;
 		ctx->output_state = QUEUE_FREE;
 	} else if (ctx->output_state == QUEUE_FREE) {
@@ -565,7 +565,7 @@ out:
 	return ret;
 }
 
-/* Reqeust buffers */
+/* Request buffers */
 static int vidioc_reqbufs(struct file *file, void *priv,
 					  struct v4l2_requestbuffers *reqbufs)
 {
@@ -573,7 +573,7 @@ static int vidioc_reqbufs(struct file *file, void *priv,
 	struct s5p_mfc_ctx *ctx = fh_to_ctx(priv);
 
 	if (reqbufs->memory != V4L2_MEMORY_MMAP) {
-		mfc_err("Only V4L2_MEMORY_MAP is supported\n");
+		mfc_debug(2, "Only V4L2_MEMORY_MMAP is supported\n");
 		return -EINVAL;
 	}
 
@@ -821,7 +821,7 @@ static int vidioc_decoder_cmd(struct file *file, void *priv,
 		if (cmd->flags != 0)
 			return -EINVAL;
 
-		if (!ctx->vq_src.streaming)
+		if (!vb2_is_streaming(&ctx->vq_src))
 			return -EINVAL;
 
 		spin_lock_irqsave(&dev->irqlock, flags);
@@ -890,7 +890,7 @@ static const struct v4l2_ioctl_ops s5p_mfc_dec_ioctl_ops = {
 static int s5p_mfc_queue_setup(struct vb2_queue *vq,
 			unsigned int *buf_count,
 			unsigned int *plane_count, unsigned int psize[],
-			void *allocators[])
+			struct device *alloc_devs[])
 {
 	struct s5p_mfc_ctx *ctx = fh_to_ctx(vq->drv_priv);
 	struct s5p_mfc_dev *dev = ctx->dev;
@@ -931,16 +931,14 @@ static int s5p_mfc_queue_setup(struct vb2_queue *vq,
 		psize[1] = ctx->chroma_size;
 
 		if (IS_MFCV6_PLUS(dev))
-			allocators[0] =
-				ctx->dev->alloc_ctx[MFC_BANK1_ALLOC_CTX];
+			alloc_devs[0] = ctx->dev->mem_dev_l;
 		else
-			allocators[0] =
-				ctx->dev->alloc_ctx[MFC_BANK2_ALLOC_CTX];
-		allocators[1] = ctx->dev->alloc_ctx[MFC_BANK1_ALLOC_CTX];
+			alloc_devs[0] = ctx->dev->mem_dev_r;
+		alloc_devs[1] = ctx->dev->mem_dev_l;
 	} else if (vq->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE &&
 		   ctx->state == MFCINST_INIT) {
 		psize[0] = ctx->dec_src_buf_size;
-		allocators[0] = ctx->dev->alloc_ctx[MFC_BANK1_ALLOC_CTX];
+		alloc_devs[0] = ctx->dev->mem_dev_l;
 	} else {
 		mfc_err("This video node is dedicated to decoding. Decoding not initialized\n");
 		return -EINVAL;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
index 034b5c1d35a1..fcc2e054c61f 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
@@ -943,9 +943,10 @@ static int vidioc_querycap(struct file *file, void *priv,
 {
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 
-	strncpy(cap->driver, dev->plat_dev->name, sizeof(cap->driver) - 1);
-	strncpy(cap->card, dev->plat_dev->name, sizeof(cap->card) - 1);
-	cap->bus_info[0] = 0;
+	strncpy(cap->driver, S5P_MFC_NAME, sizeof(cap->driver) - 1);
+	strncpy(cap->card, dev->vfd_enc->name, sizeof(cap->card) - 1);
+	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
+		 dev_name(&dev->plat_dev->dev));
 	/*
 	 * This is only a mem-to-mem video device. The capture and output
 	 * device capability flags are left only for backward compatibility
@@ -1043,10 +1044,6 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
 			mfc_err("failed to try output format\n");
 			return -EINVAL;
 		}
-		if (pix_fmt_mp->plane_fmt[0].sizeimage == 0) {
-			mfc_err("must be set encoding output size\n");
-			return -EINVAL;
-		}
 		if ((dev->variant->version_bit & fmt->versions) == 0) {
 			mfc_err("Unsupported format by this MFC version.\n");
 			return -EINVAL;
@@ -1060,11 +1057,6 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
 			mfc_err("failed to try output format\n");
 			return -EINVAL;
 		}
-
-		if (fmt->num_planes != pix_fmt_mp->num_planes) {
-			mfc_err("failed to try output format\n");
-			return -EINVAL;
-		}
 		if ((dev->variant->version_bit & fmt->versions) == 0) {
 			mfc_err("Unsupported format by this MFC version.\n");
 			return -EINVAL;
@@ -1144,7 +1136,10 @@ static int vidioc_reqbufs(struct file *file, void *priv,
 		return -EINVAL;
 	if (reqbufs->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
 		if (reqbufs->count == 0) {
+			mfc_debug(2, "Freeing buffers\n");
 			ret = vb2_reqbufs(&ctx->vq_dst, reqbufs);
+			s5p_mfc_hw_call(dev->mfc_ops, release_codec_buffers,
+					ctx);
 			ctx->capture_state = QUEUE_FREE;
 			return ret;
 		}
@@ -1817,7 +1812,7 @@ static int check_vb_with_fmt(struct s5p_mfc_fmt *fmt, struct vb2_buffer *vb)
 
 static int s5p_mfc_queue_setup(struct vb2_queue *vq,
 			unsigned int *buf_count, unsigned int *plane_count,
-			unsigned int psize[], void *allocators[])
+			unsigned int psize[], struct device *alloc_devs[])
 {
 	struct s5p_mfc_ctx *ctx = fh_to_ctx(vq->drv_priv);
 	struct s5p_mfc_dev *dev = ctx->dev;
@@ -1837,7 +1832,7 @@ static int s5p_mfc_queue_setup(struct vb2_queue *vq,
 		if (*buf_count > MFC_MAX_BUFFERS)
 			*buf_count = MFC_MAX_BUFFERS;
 		psize[0] = ctx->enc_dst_buf_size;
-		allocators[0] = ctx->dev->alloc_ctx[MFC_BANK1_ALLOC_CTX];
+		alloc_devs[0] = ctx->dev->mem_dev_l;
 	} else if (vq->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
 		if (ctx->src_fmt)
 			*plane_count = ctx->src_fmt->num_planes;
@@ -1853,15 +1848,11 @@ static int s5p_mfc_queue_setup(struct vb2_queue *vq,
 		psize[1] = ctx->chroma_size;
 
 		if (IS_MFCV6_PLUS(dev)) {
-			allocators[0] =
-				ctx->dev->alloc_ctx[MFC_BANK1_ALLOC_CTX];
-			allocators[1] =
-				ctx->dev->alloc_ctx[MFC_BANK1_ALLOC_CTX];
+			alloc_devs[0] = ctx->dev->mem_dev_l;
+			alloc_devs[1] = ctx->dev->mem_dev_l;
 		} else {
-			allocators[0] =
-				ctx->dev->alloc_ctx[MFC_BANK2_ALLOC_CTX];
-			allocators[1] =
-				ctx->dev->alloc_ctx[MFC_BANK2_ALLOC_CTX];
+			alloc_devs[0] = ctx->dev->mem_dev_r;
+			alloc_devs[1] = ctx->dev->mem_dev_r;
 		}
 	} else {
 		mfc_err("invalid queue type: %d\n", vq->type);
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_iommu.h b/drivers/media/platform/s5p-mfc/s5p_mfc_iommu.h
new file mode 100644
index 000000000000..6962132ae8fa
--- /dev/null
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_iommu.h
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) 2015 Samsung Electronics Co.Ltd
+ * Authors: Marek Szyprowski <m.szyprowski@samsung.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef S5P_MFC_IOMMU_H_
+#define S5P_MFC_IOMMU_H_
+
+#define S5P_MFC_IOMMU_DMA_BASE	0x20000000lu
+#define S5P_MFC_IOMMU_DMA_SIZE	SZ_256M
+
+#if defined(CONFIG_EXYNOS_IOMMU) && defined(CONFIG_ARM_DMA_USE_IOMMU)
+
+#include <asm/dma-iommu.h>
+
+static inline bool exynos_is_iommu_available(struct device *dev)
+{
+	return dev->archdata.iommu != NULL;
+}
+
+static inline void exynos_unconfigure_iommu(struct device *dev)
+{
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+
+	arm_iommu_detach_device(dev);
+	arm_iommu_release_mapping(mapping);
+}
+
+static inline int exynos_configure_iommu(struct device *dev,
+					 unsigned int base, unsigned int size)
+{
+	struct dma_iommu_mapping *mapping = NULL;
+	int ret;
+
+	/* Disable the default mapping created by device core */
+	if (to_dma_iommu_mapping(dev))
+		exynos_unconfigure_iommu(dev);
+
+	mapping = arm_iommu_create_mapping(dev->bus, base, size);
+	if (IS_ERR(mapping)) {
+		pr_warn("Failed to create IOMMU mapping for device %s\n",
+			dev_name(dev));
+		return PTR_ERR(mapping);
+	}
+
+	ret = arm_iommu_attach_device(dev, mapping);
+	if (ret) {
+		pr_warn("Failed to attached device %s to IOMMU_mapping\n",
+				dev_name(dev));
+		arm_iommu_release_mapping(mapping);
+		return ret;
+	}
+
+	return 0;
+}
+
+#else
+
+static inline bool exynos_is_iommu_available(struct device *dev)
+{
+	return false;
+}
+
+static inline int exynos_configure_iommu(struct device *dev,
+					 unsigned int base, unsigned int size)
+{
+	return -ENOSYS;
+}
+
+static inline void exynos_unconfigure_iommu(struct device *dev) { }
+
+#endif
+
+#endif /* S5P_MFC_IOMMU_H_ */
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
index 5f97a3398c11..930dc2dddae6 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
@@ -54,6 +54,7 @@ int s5p_mfc_init_pm(struct s5p_mfc_dev *dev)
 		pm->clock = clk_get(&dev->plat_dev->dev, MFC_SCLK_NAME);
 		if (IS_ERR(pm->clock)) {
 			mfc_info("Failed to get MFC special clock control\n");
+			pm->clock = NULL;
 		} else {
 			clk_set_rate(pm->clock, MFC_SCLK_RATE);
 			ret = clk_prepare_enable(pm->clock);
@@ -76,8 +77,10 @@ int s5p_mfc_init_pm(struct s5p_mfc_dev *dev)
 
 err_s_clk:
 	clk_put(pm->clock);
+	pm->clock = NULL;
 err_p_ip_clk:
 	clk_put(pm->clock_gate);
+	pm->clock_gate = NULL;
 err_g_ip_clk:
 	return ret;
 }
@@ -88,9 +91,11 @@ void s5p_mfc_final_pm(struct s5p_mfc_dev *dev)
 	    pm->clock) {
 		clk_disable_unprepare(pm->clock);
 		clk_put(pm->clock);
+		pm->clock = NULL;
 	}
 	clk_unprepare(pm->clock_gate);
 	clk_put(pm->clock_gate);
+	pm->clock_gate = NULL;
 #ifdef CONFIG_PM
 	pm_runtime_disable(pm->device);
 #endif
@@ -98,12 +103,13 @@ void s5p_mfc_final_pm(struct s5p_mfc_dev *dev)
 
 int s5p_mfc_clock_on(void)
 {
-	int ret;
+	int ret = 0;
 #ifdef CLK_DEBUG
 	atomic_inc(&clk_ref);
 	mfc_debug(3, "+ %d\n", atomic_read(&clk_ref));
 #endif
-	ret = clk_enable(pm->clock_gate);
+	if (!IS_ERR_OR_NULL(pm->clock_gate))
+		ret = clk_enable(pm->clock_gate);
 	return ret;
 }
 
@@ -113,7 +119,8 @@ void s5p_mfc_clock_off(void)
 	atomic_dec(&clk_ref);
 	mfc_debug(3, "- %d\n", atomic_read(&clk_ref));
 #endif
-	clk_disable(pm->clock_gate);
+	if (!IS_ERR_OR_NULL(pm->clock_gate))
+		clk_disable(pm->clock_gate);
 }
 
 int s5p_mfc_power_on(void)
diff --git a/drivers/media/platform/s5p-tv/mixer.h b/drivers/media/platform/s5p-tv/mixer.h
index 4dd62a918fcf..869f0ce86f6e 100644
--- a/drivers/media/platform/s5p-tv/mixer.h
+++ b/drivers/media/platform/s5p-tv/mixer.h
@@ -245,8 +245,6 @@ struct mxr_device {
 
 	/** V4L2 device */
 	struct v4l2_device v4l2_dev;
-	/** context of allocator */
-	void *alloc_ctx;
 	/** event wait queue */
 	wait_queue_head_t event_queue;
 	/** state flags */
diff --git a/drivers/media/platform/s5p-tv/mixer_video.c b/drivers/media/platform/s5p-tv/mixer_video.c
index 7ab5578a0405..ee74e2b44d69 100644
--- a/drivers/media/platform/s5p-tv/mixer_video.c
+++ b/drivers/media/platform/s5p-tv/mixer_video.c
@@ -80,12 +80,7 @@ int mxr_acquire_video(struct mxr_device *mdev,
 		goto fail;
 	}
 
-	mdev->alloc_ctx = vb2_dma_contig_init_ctx(mdev->dev);
-	if (IS_ERR(mdev->alloc_ctx)) {
-		mxr_err(mdev, "could not acquire vb2 allocator\n");
-		ret = PTR_ERR(mdev->alloc_ctx);
-		goto fail_v4l2_dev;
-	}
+	vb2_dma_contig_set_max_seg_size(mdev->dev, DMA_BIT_MASK(32));
 
 	/* registering outputs */
 	mdev->output_cnt = 0;
@@ -120,7 +115,7 @@ int mxr_acquire_video(struct mxr_device *mdev,
 		mxr_err(mdev, "failed to register any output\n");
 		ret = -ENODEV;
 		/* skipping fail_output because there is nothing to free */
-		goto fail_vb2_allocator;
+		goto fail_v4l2_dev;
 	}
 
 	return 0;
@@ -131,10 +126,6 @@ fail_output:
 		kfree(mdev->output[i]);
 	memset(mdev->output, 0, sizeof(mdev->output));
 
-fail_vb2_allocator:
-	/* freeing allocator context */
-	vb2_dma_contig_cleanup_ctx(mdev->alloc_ctx);
-
 fail_v4l2_dev:
 	/* NOTE: automatically unregister all subdevs */
 	v4l2_device_unregister(v4l2_dev);
@@ -151,7 +142,7 @@ void mxr_release_video(struct mxr_device *mdev)
 	for (i = 0; i < mdev->output_cnt; ++i)
 		kfree(mdev->output[i]);
 
-	vb2_dma_contig_cleanup_ctx(mdev->alloc_ctx);
+	vb2_dma_contig_clear_max_seg_size(mdev->dev);
 	v4l2_device_unregister(&mdev->v4l2_dev);
 }
 
@@ -883,7 +874,7 @@ static const struct v4l2_file_operations mxr_fops = {
 
 static int queue_setup(struct vb2_queue *vq,
 	unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[],
-	void *alloc_ctxs[])
+	struct device *alloc_devs[])
 {
 	struct mxr_layer *layer = vb2_get_drv_priv(vq);
 	const struct mxr_format *fmt = layer->fmt;
@@ -901,7 +892,6 @@ static int queue_setup(struct vb2_queue *vq,
 
 	*nplanes = fmt->num_subframes;
 	for (i = 0; i < fmt->num_subframes; ++i) {
-		alloc_ctxs[i] = layer->mdev->alloc_ctx;
 		sizes[i] = planes[i].sizeimage;
 		mxr_dbg(mdev, "size[%d] = %08x\n", i, sizes[i]);
 	}
@@ -1110,6 +1100,7 @@ struct mxr_layer *mxr_base_layer_create(struct mxr_device *mdev,
 		.min_buffers_needed = 1,
 		.mem_ops = &vb2_dma_contig_memops,
 		.lock = &layer->mutex,
+		.dev = mdev->dev,
 	};
 
 	return layer;
diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c
index 82b5d69b87fa..15a562af13c7 100644
--- a/drivers/media/platform/sh_veu.c
+++ b/drivers/media/platform/sh_veu.c
@@ -118,7 +118,6 @@ struct sh_veu_dev {
 	struct sh_veu_file *output;
 	struct mutex fop_lock;
 	void __iomem *base;
-	struct vb2_alloc_ctx *alloc_ctx;
 	spinlock_t lock;
 	bool is_2h;
 	unsigned int xaction;
@@ -866,7 +865,7 @@ static const struct v4l2_ioctl_ops sh_veu_ioctl_ops = {
 
 static int sh_veu_queue_setup(struct vb2_queue *vq,
 			      unsigned int *nbuffers, unsigned int *nplanes,
-			      unsigned int sizes[], void *alloc_ctxs[])
+			      unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct sh_veu_dev *veu = vb2_get_drv_priv(vq);
 	struct sh_veu_vfmt *vfmt = sh_veu_get_vfmt(veu, vq->type);
@@ -882,14 +881,11 @@ static int sh_veu_queue_setup(struct vb2_queue *vq,
 		*nbuffers = count;
 	}
 
-	if (*nplanes) {
-		alloc_ctxs[0] = veu->alloc_ctx;
+	if (*nplanes)
 		return sizes[0] < size ? -EINVAL : 0;
-	}
 
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = veu->alloc_ctx;
 
 	dev_dbg(veu->dev, "get %d buffer(s) of size %d each.\n", count, size);
 
@@ -948,6 +944,7 @@ static int sh_veu_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->lock = &veu->fop_lock;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->dev = veu->v4l2_dev.dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret < 0)
@@ -962,6 +959,7 @@ static int sh_veu_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->lock = &veu->fop_lock;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->dev = veu->v4l2_dev.dev;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -1148,12 +1146,6 @@ static int sh_veu_probe(struct platform_device *pdev)
 
 	vdev = &veu->vdev;
 
-	veu->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(veu->alloc_ctx)) {
-		ret = PTR_ERR(veu->alloc_ctx);
-		goto einitctx;
-	}
-
 	*vdev = sh_veu_videodev;
 	vdev->v4l2_dev = &veu->v4l2_dev;
 	spin_lock_init(&veu->lock);
@@ -1187,8 +1179,6 @@ evidreg:
 	pm_runtime_disable(&pdev->dev);
 	v4l2_m2m_release(veu->m2m_dev);
 em2minit:
-	vb2_dma_contig_cleanup_ctx(veu->alloc_ctx);
-einitctx:
 	v4l2_device_unregister(&veu->v4l2_dev);
 	return ret;
 }
@@ -1202,7 +1192,6 @@ static int sh_veu_remove(struct platform_device *pdev)
 	video_unregister_device(&veu->vdev);
 	pm_runtime_disable(&pdev->dev);
 	v4l2_m2m_release(veu->m2m_dev);
-	vb2_dma_contig_cleanup_ctx(veu->alloc_ctx);
 	v4l2_device_unregister(&veu->v4l2_dev);
 
 	return 0;
diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index 115740498274..e1f39b4cf1cd 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -86,7 +86,6 @@ struct sh_vou_device {
 	v4l2_std_id std;
 	int pix_idx;
 	struct vb2_queue queue;
-	struct vb2_alloc_ctx *alloc_ctx;
 	struct sh_vou_buffer *active;
 	enum sh_vou_status status;
 	unsigned sequence;
@@ -245,7 +244,7 @@ static void sh_vou_stream_config(struct sh_vou_device *vou_dev)
 /* Locking: caller holds fop_lock mutex */
 static int sh_vou_queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
-		       unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct sh_vou_device *vou_dev = vb2_get_drv_priv(vq);
 	struct v4l2_pix_format *pix = &vou_dev->pix;
@@ -253,7 +252,6 @@ static int sh_vou_queue_setup(struct vb2_queue *vq,
 
 	dev_dbg(vou_dev->v4l2_dev.dev, "%s()\n", __func__);
 
-	alloc_ctxs[0] = vou_dev->alloc_ctx;
 	if (*nplanes)
 		return sizes[0] < pix->height * bytes_per_line ? -EINVAL : 0;
 	*nplanes = 1;
@@ -1304,16 +1302,11 @@ static int sh_vou_probe(struct platform_device *pdev)
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->min_buffers_needed = 2;
 	q->lock = &vou_dev->fop_lock;
+	q->dev = &pdev->dev;
 	ret = vb2_queue_init(q);
 	if (ret)
-		goto einitctx;
+		goto ei2cgadap;
 
-	vou_dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(vou_dev->alloc_ctx)) {
-		dev_err(&pdev->dev, "Can't allocate buffer context");
-		ret = PTR_ERR(vou_dev->alloc_ctx);
-		goto einitctx;
-	}
 	vdev->queue = q;
 	INIT_LIST_HEAD(&vou_dev->buf_list);
 
@@ -1348,8 +1341,6 @@ ei2cnd:
 ereset:
 	i2c_put_adapter(i2c_adap);
 ei2cgadap:
-	vb2_dma_contig_cleanup_ctx(vou_dev->alloc_ctx);
-einitctx:
 	pm_runtime_disable(&pdev->dev);
 	v4l2_device_unregister(&vou_dev->v4l2_dev);
 	return ret;
@@ -1367,7 +1358,6 @@ static int sh_vou_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	video_unregister_device(&vou_dev->vdev);
 	i2c_put_adapter(client->adapter);
-	vb2_dma_contig_cleanup_ctx(vou_dev->alloc_ctx);
 	v4l2_device_unregister(&vou_dev->v4l2_dev);
 	return 0;
 }
diff --git a/drivers/media/platform/soc_camera/Kconfig b/drivers/media/platform/soc_camera/Kconfig
index 83029a4854ae..39f66414f621 100644
--- a/drivers/media/platform/soc_camera/Kconfig
+++ b/drivers/media/platform/soc_camera/Kconfig
@@ -25,8 +25,8 @@ config VIDEO_PXA27x
 	---help---
 	  This is a v4l2 driver for the PXA27x Quick Capture Interface
 
-config VIDEO_RCAR_VIN
-	tristate "R-Car Video Input (VIN) support"
+config VIDEO_RCAR_VIN_OLD
+	tristate "R-Car Video Input (VIN) support (DEPRECATED)"
 	depends on VIDEO_DEV && SOC_CAMERA
 	depends on ARCH_RENESAS || COMPILE_TEST
 	depends on HAS_DMA
diff --git a/drivers/media/platform/soc_camera/Makefile b/drivers/media/platform/soc_camera/Makefile
index 7ee71ae231c7..7703cb7ce456 100644
--- a/drivers/media/platform/soc_camera/Makefile
+++ b/drivers/media/platform/soc_camera/Makefile
@@ -10,4 +10,4 @@ obj-$(CONFIG_VIDEO_ATMEL_ISI)		+= atmel-isi.o
 obj-$(CONFIG_VIDEO_PXA27x)		+= pxa_camera.o
 obj-$(CONFIG_VIDEO_SH_MOBILE_CEU)	+= sh_mobile_ceu_camera.o
 obj-$(CONFIG_VIDEO_SH_MOBILE_CSI2)	+= sh_mobile_csi2.o
-obj-$(CONFIG_VIDEO_RCAR_VIN)		+= rcar_vin.o
+obj-$(CONFIG_VIDEO_RCAR_VIN_OLD)	+= rcar_vin.o
diff --git a/drivers/media/platform/soc_camera/atmel-isi.c b/drivers/media/platform/soc_camera/atmel-isi.c
index ab2d9b9b1f5d..30211f6b4483 100644
--- a/drivers/media/platform/soc_camera/atmel-isi.c
+++ b/drivers/media/platform/soc_camera/atmel-isi.c
@@ -72,8 +72,6 @@ struct atmel_isi {
 
 	int				sequence;
 
-	struct vb2_alloc_ctx		*alloc_ctx;
-
 	/* Allocate descriptors for dma buffer use */
 	struct fbd			*p_fb_descriptors;
 	dma_addr_t			fb_descriptors_phys;
@@ -305,7 +303,7 @@ static int atmel_isi_wait_status(struct atmel_isi *isi, int wait_reset)
    ------------------------------------------------------------------*/
 static int queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
@@ -322,7 +320,6 @@ static int queue_setup(struct vb2_queue *vq,
 
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = isi->alloc_ctx;
 
 	isi->sequence = 0;
 	isi->active = NULL;
@@ -567,6 +564,7 @@ static int isi_camera_init_videobuf(struct vb2_queue *q,
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &ici->host_lock;
+	q->dev = ici->v4l2_dev.dev;
 
 	return vb2_queue_init(q);
 }
@@ -963,7 +961,6 @@ static int atmel_isi_remove(struct platform_device *pdev)
 					struct atmel_isi, soc_host);
 
 	soc_camera_host_unregister(soc_host);
-	vb2_dma_contig_cleanup_ctx(isi->alloc_ctx);
 	dma_free_coherent(&pdev->dev,
 			sizeof(struct fbd) * MAX_BUFFER_NUM,
 			isi->p_fb_descriptors,
@@ -1067,12 +1064,6 @@ static int atmel_isi_probe(struct platform_device *pdev)
 		list_add(&isi->dma_desc[i].list, &isi->dma_desc_head);
 	}
 
-	isi->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(isi->alloc_ctx)) {
-		ret = PTR_ERR(isi->alloc_ctx);
-		goto err_alloc_ctx;
-	}
-
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	isi->regs = devm_ioremap_resource(&pdev->dev, regs);
 	if (IS_ERR(isi->regs)) {
@@ -1119,8 +1110,6 @@ err_register_soc_camera_host:
 	pm_runtime_disable(&pdev->dev);
 err_req_irq:
 err_ioremap:
-	vb2_dma_contig_cleanup_ctx(isi->alloc_ctx);
-err_alloc_ctx:
 	dma_free_coherent(&pdev->dev,
 			sizeof(struct fbd) * MAX_BUFFER_NUM,
 			isi->p_fb_descriptors,
diff --git a/drivers/media/platform/soc_camera/rcar_vin.c b/drivers/media/platform/soc_camera/rcar_vin.c
index 3f9c1b8456c3..9c137522c660 100644
--- a/drivers/media/platform/soc_camera/rcar_vin.c
+++ b/drivers/media/platform/soc_camera/rcar_vin.c
@@ -484,7 +484,6 @@ struct rcar_vin_priv {
 	struct list_head		capture;
 #define MAX_BUFFER_NUM			3
 	struct vb2_v4l2_buffer		*queue_buf[MAX_BUFFER_NUM];
-	struct vb2_alloc_ctx		*alloc_ctx;
 	enum v4l2_field			field;
 	unsigned int			pdata_flags;
 	unsigned int			vb_count;
@@ -534,14 +533,12 @@ struct rcar_vin_cam {
 static int rcar_vin_videobuf_setup(struct vb2_queue *vq,
 				   unsigned int *count,
 				   unsigned int *num_planes,
-				   unsigned int sizes[], void *alloc_ctxs[])
+				   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct rcar_vin_priv *priv = ici->priv;
 
-	alloc_ctxs[0] = priv->alloc_ctx;
-
 	if (!vq->num_buffers)
 		priv->sequence = 0;
 
@@ -1816,6 +1813,7 @@ static int rcar_vin_init_videobuf2(struct vb2_queue *vq,
 	vq->buf_struct_size = sizeof(struct rcar_vin_buffer);
 	vq->timestamp_flags  = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	vq->lock = &ici->host_lock;
+	vq->dev = ici->v4l2_dev.dev;
 
 	return vb2_queue_init(vq);
 }
@@ -1912,10 +1910,6 @@ static int rcar_vin_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	priv->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(priv->alloc_ctx))
-		return PTR_ERR(priv->alloc_ctx);
-
 	priv->ici.priv = priv;
 	priv->ici.v4l2_dev.dev = &pdev->dev;
 	priv->ici.drv_name = dev_name(&pdev->dev);
@@ -1946,7 +1940,6 @@ static int rcar_vin_probe(struct platform_device *pdev)
 
 cleanup:
 	pm_runtime_disable(&pdev->dev);
-	vb2_dma_contig_cleanup_ctx(priv->alloc_ctx);
 
 	return ret;
 }
@@ -1954,12 +1947,9 @@ cleanup:
 static int rcar_vin_remove(struct platform_device *pdev)
 {
 	struct soc_camera_host *soc_host = to_soc_camera_host(&pdev->dev);
-	struct rcar_vin_priv *priv = container_of(soc_host,
-						  struct rcar_vin_priv, ici);
 
 	soc_camera_host_unregister(soc_host);
 	pm_runtime_disable(&pdev->dev);
-	vb2_dma_contig_cleanup_ctx(priv->alloc_ctx);
 
 	return 0;
 }
diff --git a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
index b9f369c0fb94..02b519dde42a 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
@@ -113,7 +113,6 @@ struct sh_mobile_ceu_dev {
 	spinlock_t lock;		/* Protects video buffer lists */
 	struct list_head capture;
 	struct vb2_v4l2_buffer *active;
-	struct vb2_alloc_ctx *alloc_ctx;
 
 	struct sh_mobile_ceu_info *pdata;
 	struct completion complete;
@@ -211,14 +210,12 @@ static int sh_mobile_ceu_soft_reset(struct sh_mobile_ceu_dev *pcdev)
  */
 static int sh_mobile_ceu_videobuf_setup(struct vb2_queue *vq,
 			unsigned int *count, unsigned int *num_planes,
-			unsigned int sizes[], void *alloc_ctxs[])
+			unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct sh_mobile_ceu_dev *pcdev = ici->priv;
 
-	alloc_ctxs[0] = pcdev->alloc_ctx;
-
 	if (!vq->num_buffers)
 		pcdev->sequence = 0;
 
@@ -1670,6 +1667,7 @@ static int sh_mobile_ceu_init_videobuf(struct vb2_queue *q,
 	q->buf_struct_size = sizeof(struct sh_mobile_ceu_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &ici->host_lock;
+	q->dev = ici->v4l2_dev.dev;
 
 	return vb2_queue_init(q);
 }
@@ -1822,12 +1820,6 @@ static int sh_mobile_ceu_probe(struct platform_device *pdev)
 	pcdev->ici.ops = &sh_mobile_ceu_host_ops;
 	pcdev->ici.capabilities = SOCAM_HOST_CAP_STRIDE;
 
-	pcdev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(pcdev->alloc_ctx)) {
-		err = PTR_ERR(pcdev->alloc_ctx);
-		goto exit_free_clk;
-	}
-
 	if (pcdev->pdata && pcdev->pdata->asd_sizes) {
 		struct v4l2_async_subdev **asd;
 		char name[] = "sh-mobile-csi2";
@@ -1872,7 +1864,7 @@ static int sh_mobile_ceu_probe(struct platform_device *pdev)
 
 		if (!csi2_pdev) {
 			err = -ENOMEM;
-			goto exit_free_ctx;
+			goto exit_free_clk;
 		}
 
 		pcdev->csi2_pdev		= csi2_pdev;
@@ -1955,8 +1947,6 @@ exit_pdev_put:
 		pcdev->csi2_pdev->resource = NULL;
 		platform_device_put(pcdev->csi2_pdev);
 	}
-exit_free_ctx:
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
 exit_free_clk:
 	pm_runtime_disable(&pdev->dev);
 exit_release_mem:
@@ -1976,7 +1966,6 @@ static int sh_mobile_ceu_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	if (platform_get_resource(pdev, IORESOURCE_MEM, 1))
 		dma_release_declared_memory(&pdev->dev);
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
 	if (csi2_pdev && csi2_pdev->dev.driver) {
 		struct module *csi2_drv = csi2_pdev->dev.driver->owner;
 		platform_device_del(csi2_pdev);
diff --git a/drivers/media/platform/sti/bdisp/bdisp-filter.h b/drivers/media/platform/sti/bdisp/bdisp-filter.h
index fc8c54f725ad..53e52fb4127f 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-filter.h
+++ b/drivers/media/platform/sti/bdisp/bdisp-filter.h
@@ -19,178 +19,6 @@ struct bdisp_filter_h_spec {
 	const u16 max;
 	const u8 coef[BDISP_HF_NB];
 };
-
-static const struct bdisp_filter_h_spec bdisp_h_spec[] = {
-	{
-		.min = 0,
-		.max = 921,
-		.coef = {
-			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
-			0x00, 0x00, 0xff, 0x07, 0x3d, 0xfc, 0x01, 0x00,
-			0x00, 0x01, 0xfd, 0x11, 0x36, 0xf9, 0x02, 0x00,
-			0x00, 0x01, 0xfb, 0x1b, 0x2e, 0xf9, 0x02, 0x00,
-			0x00, 0x01, 0xf9, 0x26, 0x26, 0xf9, 0x01, 0x00,
-			0x00, 0x02, 0xf9, 0x30, 0x19, 0xfb, 0x01, 0x00,
-			0x00, 0x02, 0xf9, 0x39, 0x0e, 0xfd, 0x01, 0x00,
-			0x00, 0x01, 0xfc, 0x3e, 0x06, 0xff, 0x00, 0x00
-		}
-	},
-	{
-		.min = 921,
-		.max = 1024,
-		.coef = {
-			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
-			0xff, 0x03, 0xfd, 0x08, 0x3e, 0xf9, 0x04, 0xfe,
-			0xfd, 0x06, 0xf8, 0x13, 0x3b, 0xf4, 0x07, 0xfc,
-			0xfb, 0x08, 0xf5, 0x1f, 0x34, 0xf1, 0x09, 0xfb,
-			0xfb, 0x09, 0xf2, 0x2b, 0x2a, 0xf1, 0x09, 0xfb,
-			0xfb, 0x09, 0xf2, 0x35, 0x1e, 0xf4, 0x08, 0xfb,
-			0xfc, 0x07, 0xf5, 0x3c, 0x12, 0xf7, 0x06, 0xfd,
-			0xfe, 0x04, 0xfa, 0x3f, 0x07, 0xfc, 0x03, 0xff
-		}
-	},
-	{
-		.min = 1024,
-		.max = 1126,
-		.coef = {
-			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
-			0xff, 0x03, 0xfd, 0x08, 0x3e, 0xf9, 0x04, 0xfe,
-			0xfd, 0x06, 0xf8, 0x13, 0x3b, 0xf4, 0x07, 0xfc,
-			0xfb, 0x08, 0xf5, 0x1f, 0x34, 0xf1, 0x09, 0xfb,
-			0xfb, 0x09, 0xf2, 0x2b, 0x2a, 0xf1, 0x09, 0xfb,
-			0xfb, 0x09, 0xf2, 0x35, 0x1e, 0xf4, 0x08, 0xfb,
-			0xfc, 0x07, 0xf5, 0x3c, 0x12, 0xf7, 0x06, 0xfd,
-			0xfe, 0x04, 0xfa, 0x3f, 0x07, 0xfc, 0x03, 0xff
-		}
-	},
-	{
-		.min = 1126,
-		.max = 1228,
-		.coef = {
-			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
-			0xff, 0x03, 0xfd, 0x08, 0x3e, 0xf9, 0x04, 0xfe,
-			0xfd, 0x06, 0xf8, 0x13, 0x3b, 0xf4, 0x07, 0xfc,
-			0xfb, 0x08, 0xf5, 0x1f, 0x34, 0xf1, 0x09, 0xfb,
-			0xfb, 0x09, 0xf2, 0x2b, 0x2a, 0xf1, 0x09, 0xfb,
-			0xfb, 0x09, 0xf2, 0x35, 0x1e, 0xf4, 0x08, 0xfb,
-			0xfc, 0x07, 0xf5, 0x3c, 0x12, 0xf7, 0x06, 0xfd,
-			0xfe, 0x04, 0xfa, 0x3f, 0x07, 0xfc, 0x03, 0xff
-		}
-	},
-	{
-		.min = 1228,
-		.max = 1331,
-		.coef = {
-			0xfd, 0x04, 0xfc, 0x05, 0x39, 0x05, 0xfc, 0x04,
-			0xfc, 0x06, 0xf9, 0x0c, 0x39, 0xfe, 0x00, 0x02,
-			0xfb, 0x08, 0xf6, 0x17, 0x35, 0xf9, 0x02, 0x00,
-			0xfc, 0x08, 0xf4, 0x20, 0x30, 0xf4, 0x05, 0xff,
-			0xfd, 0x07, 0xf4, 0x29, 0x28, 0xf3, 0x07, 0xfd,
-			0xff, 0x05, 0xf5, 0x31, 0x1f, 0xf3, 0x08, 0xfc,
-			0x00, 0x02, 0xf9, 0x38, 0x14, 0xf6, 0x08, 0xfb,
-			0x02, 0x00, 0xff, 0x3a, 0x0b, 0xf8, 0x06, 0xfc
-		}
-	},
-	{
-		.min = 1331,
-		.max = 1433,
-		.coef = {
-			0xfc, 0x06, 0xf9, 0x09, 0x34, 0x09, 0xf9, 0x06,
-			0xfd, 0x07, 0xf7, 0x10, 0x32, 0x02, 0xfc, 0x05,
-			0xfe, 0x07, 0xf6, 0x17, 0x2f, 0xfc, 0xff, 0x04,
-			0xff, 0x06, 0xf5, 0x20, 0x2a, 0xf9, 0x01, 0x02,
-			0x00, 0x04, 0xf6, 0x27, 0x25, 0xf6, 0x04, 0x00,
-			0x02, 0x01, 0xf9, 0x2d, 0x1d, 0xf5, 0x06, 0xff,
-			0x04, 0xff, 0xfd, 0x31, 0x15, 0xf5, 0x07, 0xfe,
-			0x05, 0xfc, 0x02, 0x35, 0x0d, 0xf7, 0x07, 0xfd
-		}
-	},
-	{
-		.min = 1433,
-		.max = 1536,
-		.coef = {
-			0xfe, 0x06, 0xf8, 0x0b, 0x30, 0x0b, 0xf8, 0x06,
-			0xff, 0x06, 0xf7, 0x12, 0x2d, 0x05, 0xfa, 0x06,
-			0x00, 0x04, 0xf6, 0x18, 0x2c, 0x00, 0xfc, 0x06,
-			0x01, 0x02, 0xf7, 0x1f, 0x27, 0xfd, 0xff, 0x04,
-			0x03, 0x00, 0xf9, 0x24, 0x24, 0xf9, 0x00, 0x03,
-			0x04, 0xff, 0xfd, 0x29, 0x1d, 0xf7, 0x02, 0x01,
-			0x06, 0xfc, 0x00, 0x2d, 0x17, 0xf6, 0x04, 0x00,
-			0x06, 0xfa, 0x05, 0x30, 0x0f, 0xf7, 0x06, 0xff
-		}
-	},
-	{
-		.min = 1536,
-		.max = 2048,
-		.coef = {
-			0x05, 0xfd, 0xfb, 0x13, 0x25, 0x13, 0xfb, 0xfd,
-			0x05, 0xfc, 0xfd, 0x17, 0x24, 0x0f, 0xf9, 0xff,
-			0x04, 0xfa, 0xff, 0x1b, 0x24, 0x0b, 0xf9, 0x00,
-			0x03, 0xf9, 0x01, 0x1f, 0x23, 0x08, 0xf8, 0x01,
-			0x02, 0xf9, 0x04, 0x22, 0x20, 0x04, 0xf9, 0x02,
-			0x01, 0xf8, 0x08, 0x25, 0x1d, 0x01, 0xf9, 0x03,
-			0x00, 0xf9, 0x0c, 0x25, 0x1a, 0xfe, 0xfa, 0x04,
-			0xff, 0xf9, 0x10, 0x26, 0x15, 0xfc, 0xfc, 0x05
-		}
-	},
-	{
-		.min = 2048,
-		.max = 3072,
-		.coef = {
-			0xfc, 0xfd, 0x06, 0x13, 0x18, 0x13, 0x06, 0xfd,
-			0xfc, 0xfe, 0x08, 0x15, 0x17, 0x12, 0x04, 0xfc,
-			0xfb, 0xfe, 0x0a, 0x16, 0x18, 0x10, 0x03, 0xfc,
-			0xfb, 0x00, 0x0b, 0x18, 0x17, 0x0f, 0x01, 0xfb,
-			0xfb, 0x00, 0x0d, 0x19, 0x17, 0x0d, 0x00, 0xfb,
-			0xfb, 0x01, 0x0f, 0x19, 0x16, 0x0b, 0x00, 0xfb,
-			0xfc, 0x03, 0x11, 0x19, 0x15, 0x09, 0xfe, 0xfb,
-			0xfc, 0x04, 0x12, 0x1a, 0x12, 0x08, 0xfe, 0xfc
-		}
-	},
-	{
-		.min = 3072,
-		.max = 4096,
-		.coef = {
-			0xfe, 0x02, 0x09, 0x0f, 0x0e, 0x0f, 0x09, 0x02,
-			0xff, 0x02, 0x09, 0x0f, 0x10, 0x0e, 0x08, 0x01,
-			0xff, 0x03, 0x0a, 0x10, 0x10, 0x0d, 0x07, 0x00,
-			0x00, 0x04, 0x0b, 0x10, 0x0f, 0x0c, 0x06, 0x00,
-			0x00, 0x05, 0x0c, 0x10, 0x0e, 0x0c, 0x05, 0x00,
-			0x00, 0x06, 0x0c, 0x11, 0x0e, 0x0b, 0x04, 0x00,
-			0x00, 0x07, 0x0d, 0x11, 0x0f, 0x0a, 0x03, 0xff,
-			0x01, 0x08, 0x0e, 0x11, 0x0e, 0x09, 0x02, 0xff
-		}
-	},
-	{
-		.min = 4096,
-		.max = 5120,
-		.coef = {
-			0x00, 0x04, 0x09, 0x0c, 0x0e, 0x0c, 0x09, 0x04,
-			0x01, 0x05, 0x09, 0x0c, 0x0d, 0x0c, 0x08, 0x04,
-			0x01, 0x05, 0x0a, 0x0c, 0x0e, 0x0b, 0x08, 0x03,
-			0x02, 0x06, 0x0a, 0x0d, 0x0c, 0x0b, 0x07, 0x03,
-			0x02, 0x07, 0x0a, 0x0d, 0x0d, 0x0a, 0x07, 0x02,
-			0x03, 0x07, 0x0b, 0x0d, 0x0c, 0x0a, 0x06, 0x02,
-			0x03, 0x08, 0x0b, 0x0d, 0x0d, 0x0a, 0x05, 0x01,
-			0x04, 0x08, 0x0c, 0x0d, 0x0c, 0x09, 0x05, 0x01
-		}
-	},
-	{
-		.min = 5120,
-		.max = 65535,
-		.coef = {
-			0x03, 0x06, 0x09, 0x0b, 0x09, 0x0b, 0x09, 0x06,
-			0x03, 0x06, 0x09, 0x0b, 0x0c, 0x0a, 0x08, 0x05,
-			0x03, 0x06, 0x09, 0x0b, 0x0c, 0x0a, 0x08, 0x05,
-			0x04, 0x07, 0x09, 0x0b, 0x0b, 0x0a, 0x08, 0x04,
-			0x04, 0x07, 0x0a, 0x0b, 0x0b, 0x0a, 0x07, 0x04,
-			0x04, 0x08, 0x0a, 0x0b, 0x0b, 0x09, 0x07, 0x04,
-			0x05, 0x08, 0x0a, 0x0b, 0x0c, 0x09, 0x06, 0x03,
-			0x05, 0x08, 0x0a, 0x0b, 0x0c, 0x09, 0x06, 0x03
-		}
-	}
-};
-
 /**
  * struct bdisp_filter_v_spec - Vertical filter specification
  *
@@ -204,138 +32,6 @@ struct bdisp_filter_v_spec {
 	const u8 coef[BDISP_VF_NB];
 };
 
-static const struct bdisp_filter_v_spec bdisp_v_spec[] = {
-	{
-		.min = 0,
-		.max = 1024,
-		.coef = {
-			0x00, 0x00, 0x40, 0x00, 0x00,
-			0x00, 0x06, 0x3d, 0xfd, 0x00,
-			0xfe, 0x0f, 0x38, 0xfb, 0x00,
-			0xfd, 0x19, 0x2f, 0xfb, 0x00,
-			0xfc, 0x24, 0x24, 0xfc, 0x00,
-			0xfb, 0x2f, 0x19, 0xfd, 0x00,
-			0xfb, 0x38, 0x0f, 0xfe, 0x00,
-			0xfd, 0x3d, 0x06, 0x00, 0x00
-		}
-	},
-	{
-		.min = 1024,
-		.max = 1331,
-		.coef = {
-			0xfc, 0x05, 0x3e, 0x05, 0xfc,
-			0xf8, 0x0e, 0x3b, 0xff, 0x00,
-			0xf5, 0x18, 0x38, 0xf9, 0x02,
-			0xf4, 0x21, 0x31, 0xf5, 0x05,
-			0xf4, 0x2a, 0x27, 0xf4, 0x07,
-			0xf6, 0x30, 0x1e, 0xf4, 0x08,
-			0xf9, 0x35, 0x15, 0xf6, 0x07,
-			0xff, 0x37, 0x0b, 0xf9, 0x06
-		}
-	},
-	{
-		.min = 1331,
-		.max = 1433,
-		.coef = {
-			0xf8, 0x0a, 0x3c, 0x0a, 0xf8,
-			0xf6, 0x12, 0x3b, 0x02, 0xfb,
-			0xf4, 0x1b, 0x35, 0xfd, 0xff,
-			0xf4, 0x23, 0x30, 0xf8, 0x01,
-			0xf6, 0x29, 0x27, 0xf6, 0x04,
-			0xf9, 0x2e, 0x1e, 0xf5, 0x06,
-			0xfd, 0x31, 0x16, 0xf6, 0x06,
-			0x02, 0x32, 0x0d, 0xf8, 0x07
-		}
-	},
-	{
-		.min = 1433,
-		.max = 1536,
-		.coef = {
-			0xf6, 0x0e, 0x38, 0x0e, 0xf6,
-			0xf5, 0x15, 0x38, 0x06, 0xf8,
-			0xf5, 0x1d, 0x33, 0x00, 0xfb,
-			0xf6, 0x23, 0x2d, 0xfc, 0xfe,
-			0xf9, 0x28, 0x26, 0xf9, 0x00,
-			0xfc, 0x2c, 0x1e, 0xf7, 0x03,
-			0x00, 0x2e, 0x18, 0xf6, 0x04,
-			0x05, 0x2e, 0x11, 0xf7, 0x05
-		}
-	},
-	{
-		.min = 1536,
-		.max = 2048,
-		.coef = {
-			0xfb, 0x13, 0x24, 0x13, 0xfb,
-			0xfd, 0x17, 0x23, 0x0f, 0xfa,
-			0xff, 0x1a, 0x23, 0x0b, 0xf9,
-			0x01, 0x1d, 0x22, 0x07, 0xf9,
-			0x04, 0x20, 0x1f, 0x04, 0xf9,
-			0x07, 0x22, 0x1c, 0x01, 0xfa,
-			0x0b, 0x24, 0x17, 0xff, 0xfb,
-			0x0f, 0x24, 0x14, 0xfd, 0xfc
-		}
-	},
-	{
-		.min = 2048,
-		.max = 3072,
-		.coef = {
-			0x05, 0x10, 0x16, 0x10, 0x05,
-			0x06, 0x11, 0x16, 0x0f, 0x04,
-			0x08, 0x13, 0x15, 0x0e, 0x02,
-			0x09, 0x14, 0x16, 0x0c, 0x01,
-			0x0b, 0x15, 0x15, 0x0b, 0x00,
-			0x0d, 0x16, 0x13, 0x0a, 0x00,
-			0x0f, 0x17, 0x13, 0x08, 0xff,
-			0x11, 0x18, 0x12, 0x07, 0xfe
-		}
-	},
-	{
-		.min = 3072,
-		.max = 4096,
-		.coef = {
-			0x09, 0x0f, 0x10, 0x0f, 0x09,
-			0x09, 0x0f, 0x12, 0x0e, 0x08,
-			0x0a, 0x10, 0x11, 0x0e, 0x07,
-			0x0b, 0x11, 0x11, 0x0d, 0x06,
-			0x0c, 0x11, 0x12, 0x0c, 0x05,
-			0x0d, 0x12, 0x11, 0x0c, 0x04,
-			0x0e, 0x12, 0x11, 0x0b, 0x04,
-			0x0f, 0x13, 0x11, 0x0a, 0x03
-		}
-	},
-	{
-		.min = 4096,
-		.max = 5120,
-		.coef = {
-			0x0a, 0x0e, 0x10, 0x0e, 0x0a,
-			0x0b, 0x0e, 0x0f, 0x0e, 0x0a,
-			0x0b, 0x0f, 0x10, 0x0d, 0x09,
-			0x0c, 0x0f, 0x10, 0x0d, 0x08,
-			0x0d, 0x0f, 0x0f, 0x0d, 0x08,
-			0x0d, 0x10, 0x10, 0x0c, 0x07,
-			0x0e, 0x10, 0x0f, 0x0c, 0x07,
-			0x0f, 0x10, 0x10, 0x0b, 0x06
-		}
-	},
-	{
-		.min = 5120,
-		.max = 65535,
-		.coef = {
-			0x0b, 0x0e, 0x0e, 0x0e, 0x0b,
-			0x0b, 0x0e, 0x0f, 0x0d, 0x0b,
-			0x0c, 0x0e, 0x0f, 0x0d, 0x0a,
-			0x0c, 0x0e, 0x0f, 0x0d, 0x0a,
-			0x0d, 0x0f, 0x0e, 0x0d, 0x09,
-			0x0d, 0x0f, 0x0f, 0x0c, 0x09,
-			0x0e, 0x0f, 0x0e, 0x0c, 0x09,
-			0x0e, 0x0f, 0x0f, 0x0c, 0x08
-		}
-	}
-};
-
-#define NB_H_FILTER ARRAY_SIZE(bdisp_h_spec)
-#define NB_V_FILTER ARRAY_SIZE(bdisp_v_spec)
-
 /* RGB YUV 601 standard conversion */
 static const u32 bdisp_rgb_to_yuv[] = {
 		0x0e1e8bee, 0x08420419, 0xfb5ed471, 0x08004080,
diff --git a/drivers/media/platform/sti/bdisp/bdisp-hw.c b/drivers/media/platform/sti/bdisp/bdisp-hw.c
index 052c932ac942..3df66d11c795 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-hw.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-hw.c
@@ -47,6 +47,311 @@ struct bdisp_filter_addr {
 	dma_addr_t paddr;    /* Physical address for filter table */
 };
 
+static const struct bdisp_filter_h_spec bdisp_h_spec[] = {
+	{
+		.min = 0,
+		.max = 921,
+		.coef = {
+			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0xff, 0x07, 0x3d, 0xfc, 0x01, 0x00,
+			0x00, 0x01, 0xfd, 0x11, 0x36, 0xf9, 0x02, 0x00,
+			0x00, 0x01, 0xfb, 0x1b, 0x2e, 0xf9, 0x02, 0x00,
+			0x00, 0x01, 0xf9, 0x26, 0x26, 0xf9, 0x01, 0x00,
+			0x00, 0x02, 0xf9, 0x30, 0x19, 0xfb, 0x01, 0x00,
+			0x00, 0x02, 0xf9, 0x39, 0x0e, 0xfd, 0x01, 0x00,
+			0x00, 0x01, 0xfc, 0x3e, 0x06, 0xff, 0x00, 0x00
+		}
+	},
+	{
+		.min = 921,
+		.max = 1024,
+		.coef = {
+			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
+			0xff, 0x03, 0xfd, 0x08, 0x3e, 0xf9, 0x04, 0xfe,
+			0xfd, 0x06, 0xf8, 0x13, 0x3b, 0xf4, 0x07, 0xfc,
+			0xfb, 0x08, 0xf5, 0x1f, 0x34, 0xf1, 0x09, 0xfb,
+			0xfb, 0x09, 0xf2, 0x2b, 0x2a, 0xf1, 0x09, 0xfb,
+			0xfb, 0x09, 0xf2, 0x35, 0x1e, 0xf4, 0x08, 0xfb,
+			0xfc, 0x07, 0xf5, 0x3c, 0x12, 0xf7, 0x06, 0xfd,
+			0xfe, 0x04, 0xfa, 0x3f, 0x07, 0xfc, 0x03, 0xff
+		}
+	},
+	{
+		.min = 1024,
+		.max = 1126,
+		.coef = {
+			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
+			0xff, 0x03, 0xfd, 0x08, 0x3e, 0xf9, 0x04, 0xfe,
+			0xfd, 0x06, 0xf8, 0x13, 0x3b, 0xf4, 0x07, 0xfc,
+			0xfb, 0x08, 0xf5, 0x1f, 0x34, 0xf1, 0x09, 0xfb,
+			0xfb, 0x09, 0xf2, 0x2b, 0x2a, 0xf1, 0x09, 0xfb,
+			0xfb, 0x09, 0xf2, 0x35, 0x1e, 0xf4, 0x08, 0xfb,
+			0xfc, 0x07, 0xf5, 0x3c, 0x12, 0xf7, 0x06, 0xfd,
+			0xfe, 0x04, 0xfa, 0x3f, 0x07, 0xfc, 0x03, 0xff
+		}
+	},
+	{
+		.min = 1126,
+		.max = 1228,
+		.coef = {
+			0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
+			0xff, 0x03, 0xfd, 0x08, 0x3e, 0xf9, 0x04, 0xfe,
+			0xfd, 0x06, 0xf8, 0x13, 0x3b, 0xf4, 0x07, 0xfc,
+			0xfb, 0x08, 0xf5, 0x1f, 0x34, 0xf1, 0x09, 0xfb,
+			0xfb, 0x09, 0xf2, 0x2b, 0x2a, 0xf1, 0x09, 0xfb,
+			0xfb, 0x09, 0xf2, 0x35, 0x1e, 0xf4, 0x08, 0xfb,
+			0xfc, 0x07, 0xf5, 0x3c, 0x12, 0xf7, 0x06, 0xfd,
+			0xfe, 0x04, 0xfa, 0x3f, 0x07, 0xfc, 0x03, 0xff
+		}
+	},
+	{
+		.min = 1228,
+		.max = 1331,
+		.coef = {
+			0xfd, 0x04, 0xfc, 0x05, 0x39, 0x05, 0xfc, 0x04,
+			0xfc, 0x06, 0xf9, 0x0c, 0x39, 0xfe, 0x00, 0x02,
+			0xfb, 0x08, 0xf6, 0x17, 0x35, 0xf9, 0x02, 0x00,
+			0xfc, 0x08, 0xf4, 0x20, 0x30, 0xf4, 0x05, 0xff,
+			0xfd, 0x07, 0xf4, 0x29, 0x28, 0xf3, 0x07, 0xfd,
+			0xff, 0x05, 0xf5, 0x31, 0x1f, 0xf3, 0x08, 0xfc,
+			0x00, 0x02, 0xf9, 0x38, 0x14, 0xf6, 0x08, 0xfb,
+			0x02, 0x00, 0xff, 0x3a, 0x0b, 0xf8, 0x06, 0xfc
+		}
+	},
+	{
+		.min = 1331,
+		.max = 1433,
+		.coef = {
+			0xfc, 0x06, 0xf9, 0x09, 0x34, 0x09, 0xf9, 0x06,
+			0xfd, 0x07, 0xf7, 0x10, 0x32, 0x02, 0xfc, 0x05,
+			0xfe, 0x07, 0xf6, 0x17, 0x2f, 0xfc, 0xff, 0x04,
+			0xff, 0x06, 0xf5, 0x20, 0x2a, 0xf9, 0x01, 0x02,
+			0x00, 0x04, 0xf6, 0x27, 0x25, 0xf6, 0x04, 0x00,
+			0x02, 0x01, 0xf9, 0x2d, 0x1d, 0xf5, 0x06, 0xff,
+			0x04, 0xff, 0xfd, 0x31, 0x15, 0xf5, 0x07, 0xfe,
+			0x05, 0xfc, 0x02, 0x35, 0x0d, 0xf7, 0x07, 0xfd
+		}
+	},
+	{
+		.min = 1433,
+		.max = 1536,
+		.coef = {
+			0xfe, 0x06, 0xf8, 0x0b, 0x30, 0x0b, 0xf8, 0x06,
+			0xff, 0x06, 0xf7, 0x12, 0x2d, 0x05, 0xfa, 0x06,
+			0x00, 0x04, 0xf6, 0x18, 0x2c, 0x00, 0xfc, 0x06,
+			0x01, 0x02, 0xf7, 0x1f, 0x27, 0xfd, 0xff, 0x04,
+			0x03, 0x00, 0xf9, 0x24, 0x24, 0xf9, 0x00, 0x03,
+			0x04, 0xff, 0xfd, 0x29, 0x1d, 0xf7, 0x02, 0x01,
+			0x06, 0xfc, 0x00, 0x2d, 0x17, 0xf6, 0x04, 0x00,
+			0x06, 0xfa, 0x05, 0x30, 0x0f, 0xf7, 0x06, 0xff
+		}
+	},
+	{
+		.min = 1536,
+		.max = 2048,
+		.coef = {
+			0x05, 0xfd, 0xfb, 0x13, 0x25, 0x13, 0xfb, 0xfd,
+			0x05, 0xfc, 0xfd, 0x17, 0x24, 0x0f, 0xf9, 0xff,
+			0x04, 0xfa, 0xff, 0x1b, 0x24, 0x0b, 0xf9, 0x00,
+			0x03, 0xf9, 0x01, 0x1f, 0x23, 0x08, 0xf8, 0x01,
+			0x02, 0xf9, 0x04, 0x22, 0x20, 0x04, 0xf9, 0x02,
+			0x01, 0xf8, 0x08, 0x25, 0x1d, 0x01, 0xf9, 0x03,
+			0x00, 0xf9, 0x0c, 0x25, 0x1a, 0xfe, 0xfa, 0x04,
+			0xff, 0xf9, 0x10, 0x26, 0x15, 0xfc, 0xfc, 0x05
+		}
+	},
+	{
+		.min = 2048,
+		.max = 3072,
+		.coef = {
+			0xfc, 0xfd, 0x06, 0x13, 0x18, 0x13, 0x06, 0xfd,
+			0xfc, 0xfe, 0x08, 0x15, 0x17, 0x12, 0x04, 0xfc,
+			0xfb, 0xfe, 0x0a, 0x16, 0x18, 0x10, 0x03, 0xfc,
+			0xfb, 0x00, 0x0b, 0x18, 0x17, 0x0f, 0x01, 0xfb,
+			0xfb, 0x00, 0x0d, 0x19, 0x17, 0x0d, 0x00, 0xfb,
+			0xfb, 0x01, 0x0f, 0x19, 0x16, 0x0b, 0x00, 0xfb,
+			0xfc, 0x03, 0x11, 0x19, 0x15, 0x09, 0xfe, 0xfb,
+			0xfc, 0x04, 0x12, 0x1a, 0x12, 0x08, 0xfe, 0xfc
+		}
+	},
+	{
+		.min = 3072,
+		.max = 4096,
+		.coef = {
+			0xfe, 0x02, 0x09, 0x0f, 0x0e, 0x0f, 0x09, 0x02,
+			0xff, 0x02, 0x09, 0x0f, 0x10, 0x0e, 0x08, 0x01,
+			0xff, 0x03, 0x0a, 0x10, 0x10, 0x0d, 0x07, 0x00,
+			0x00, 0x04, 0x0b, 0x10, 0x0f, 0x0c, 0x06, 0x00,
+			0x00, 0x05, 0x0c, 0x10, 0x0e, 0x0c, 0x05, 0x00,
+			0x00, 0x06, 0x0c, 0x11, 0x0e, 0x0b, 0x04, 0x00,
+			0x00, 0x07, 0x0d, 0x11, 0x0f, 0x0a, 0x03, 0xff,
+			0x01, 0x08, 0x0e, 0x11, 0x0e, 0x09, 0x02, 0xff
+		}
+	},
+	{
+		.min = 4096,
+		.max = 5120,
+		.coef = {
+			0x00, 0x04, 0x09, 0x0c, 0x0e, 0x0c, 0x09, 0x04,
+			0x01, 0x05, 0x09, 0x0c, 0x0d, 0x0c, 0x08, 0x04,
+			0x01, 0x05, 0x0a, 0x0c, 0x0e, 0x0b, 0x08, 0x03,
+			0x02, 0x06, 0x0a, 0x0d, 0x0c, 0x0b, 0x07, 0x03,
+			0x02, 0x07, 0x0a, 0x0d, 0x0d, 0x0a, 0x07, 0x02,
+			0x03, 0x07, 0x0b, 0x0d, 0x0c, 0x0a, 0x06, 0x02,
+			0x03, 0x08, 0x0b, 0x0d, 0x0d, 0x0a, 0x05, 0x01,
+			0x04, 0x08, 0x0c, 0x0d, 0x0c, 0x09, 0x05, 0x01
+		}
+	},
+	{
+		.min = 5120,
+		.max = 65535,
+		.coef = {
+			0x03, 0x06, 0x09, 0x0b, 0x09, 0x0b, 0x09, 0x06,
+			0x03, 0x06, 0x09, 0x0b, 0x0c, 0x0a, 0x08, 0x05,
+			0x03, 0x06, 0x09, 0x0b, 0x0c, 0x0a, 0x08, 0x05,
+			0x04, 0x07, 0x09, 0x0b, 0x0b, 0x0a, 0x08, 0x04,
+			0x04, 0x07, 0x0a, 0x0b, 0x0b, 0x0a, 0x07, 0x04,
+			0x04, 0x08, 0x0a, 0x0b, 0x0b, 0x09, 0x07, 0x04,
+			0x05, 0x08, 0x0a, 0x0b, 0x0c, 0x09, 0x06, 0x03,
+			0x05, 0x08, 0x0a, 0x0b, 0x0c, 0x09, 0x06, 0x03
+		}
+	}
+};
+
+#define NB_H_FILTER ARRAY_SIZE(bdisp_h_spec)
+
+
+static const struct bdisp_filter_v_spec bdisp_v_spec[] = {
+	{
+		.min = 0,
+		.max = 1024,
+		.coef = {
+			0x00, 0x00, 0x40, 0x00, 0x00,
+			0x00, 0x06, 0x3d, 0xfd, 0x00,
+			0xfe, 0x0f, 0x38, 0xfb, 0x00,
+			0xfd, 0x19, 0x2f, 0xfb, 0x00,
+			0xfc, 0x24, 0x24, 0xfc, 0x00,
+			0xfb, 0x2f, 0x19, 0xfd, 0x00,
+			0xfb, 0x38, 0x0f, 0xfe, 0x00,
+			0xfd, 0x3d, 0x06, 0x00, 0x00
+		}
+	},
+	{
+		.min = 1024,
+		.max = 1331,
+		.coef = {
+			0xfc, 0x05, 0x3e, 0x05, 0xfc,
+			0xf8, 0x0e, 0x3b, 0xff, 0x00,
+			0xf5, 0x18, 0x38, 0xf9, 0x02,
+			0xf4, 0x21, 0x31, 0xf5, 0x05,
+			0xf4, 0x2a, 0x27, 0xf4, 0x07,
+			0xf6, 0x30, 0x1e, 0xf4, 0x08,
+			0xf9, 0x35, 0x15, 0xf6, 0x07,
+			0xff, 0x37, 0x0b, 0xf9, 0x06
+		}
+	},
+	{
+		.min = 1331,
+		.max = 1433,
+		.coef = {
+			0xf8, 0x0a, 0x3c, 0x0a, 0xf8,
+			0xf6, 0x12, 0x3b, 0x02, 0xfb,
+			0xf4, 0x1b, 0x35, 0xfd, 0xff,
+			0xf4, 0x23, 0x30, 0xf8, 0x01,
+			0xf6, 0x29, 0x27, 0xf6, 0x04,
+			0xf9, 0x2e, 0x1e, 0xf5, 0x06,
+			0xfd, 0x31, 0x16, 0xf6, 0x06,
+			0x02, 0x32, 0x0d, 0xf8, 0x07
+		}
+	},
+	{
+		.min = 1433,
+		.max = 1536,
+		.coef = {
+			0xf6, 0x0e, 0x38, 0x0e, 0xf6,
+			0xf5, 0x15, 0x38, 0x06, 0xf8,
+			0xf5, 0x1d, 0x33, 0x00, 0xfb,
+			0xf6, 0x23, 0x2d, 0xfc, 0xfe,
+			0xf9, 0x28, 0x26, 0xf9, 0x00,
+			0xfc, 0x2c, 0x1e, 0xf7, 0x03,
+			0x00, 0x2e, 0x18, 0xf6, 0x04,
+			0x05, 0x2e, 0x11, 0xf7, 0x05
+		}
+	},
+	{
+		.min = 1536,
+		.max = 2048,
+		.coef = {
+			0xfb, 0x13, 0x24, 0x13, 0xfb,
+			0xfd, 0x17, 0x23, 0x0f, 0xfa,
+			0xff, 0x1a, 0x23, 0x0b, 0xf9,
+			0x01, 0x1d, 0x22, 0x07, 0xf9,
+			0x04, 0x20, 0x1f, 0x04, 0xf9,
+			0x07, 0x22, 0x1c, 0x01, 0xfa,
+			0x0b, 0x24, 0x17, 0xff, 0xfb,
+			0x0f, 0x24, 0x14, 0xfd, 0xfc
+		}
+	},
+	{
+		.min = 2048,
+		.max = 3072,
+		.coef = {
+			0x05, 0x10, 0x16, 0x10, 0x05,
+			0x06, 0x11, 0x16, 0x0f, 0x04,
+			0x08, 0x13, 0x15, 0x0e, 0x02,
+			0x09, 0x14, 0x16, 0x0c, 0x01,
+			0x0b, 0x15, 0x15, 0x0b, 0x00,
+			0x0d, 0x16, 0x13, 0x0a, 0x00,
+			0x0f, 0x17, 0x13, 0x08, 0xff,
+			0x11, 0x18, 0x12, 0x07, 0xfe
+		}
+	},
+	{
+		.min = 3072,
+		.max = 4096,
+		.coef = {
+			0x09, 0x0f, 0x10, 0x0f, 0x09,
+			0x09, 0x0f, 0x12, 0x0e, 0x08,
+			0x0a, 0x10, 0x11, 0x0e, 0x07,
+			0x0b, 0x11, 0x11, 0x0d, 0x06,
+			0x0c, 0x11, 0x12, 0x0c, 0x05,
+			0x0d, 0x12, 0x11, 0x0c, 0x04,
+			0x0e, 0x12, 0x11, 0x0b, 0x04,
+			0x0f, 0x13, 0x11, 0x0a, 0x03
+		}
+	},
+	{
+		.min = 4096,
+		.max = 5120,
+		.coef = {
+			0x0a, 0x0e, 0x10, 0x0e, 0x0a,
+			0x0b, 0x0e, 0x0f, 0x0e, 0x0a,
+			0x0b, 0x0f, 0x10, 0x0d, 0x09,
+			0x0c, 0x0f, 0x10, 0x0d, 0x08,
+			0x0d, 0x0f, 0x0f, 0x0d, 0x08,
+			0x0d, 0x10, 0x10, 0x0c, 0x07,
+			0x0e, 0x10, 0x0f, 0x0c, 0x07,
+			0x0f, 0x10, 0x10, 0x0b, 0x06
+		}
+	},
+	{
+		.min = 5120,
+		.max = 65535,
+		.coef = {
+			0x0b, 0x0e, 0x0e, 0x0e, 0x0b,
+			0x0b, 0x0e, 0x0f, 0x0d, 0x0b,
+			0x0c, 0x0e, 0x0f, 0x0d, 0x0a,
+			0x0c, 0x0e, 0x0f, 0x0d, 0x0a,
+			0x0d, 0x0f, 0x0e, 0x0d, 0x09,
+			0x0d, 0x0f, 0x0f, 0x0c, 0x09,
+			0x0e, 0x0f, 0x0e, 0x0c, 0x09,
+			0x0e, 0x0f, 0x0f, 0x0c, 0x08
+		}
+	}
+};
+
+#define NB_V_FILTER ARRAY_SIZE(bdisp_v_spec)
+
 static struct bdisp_filter_addr bdisp_h_filter[NB_H_FILTER];
 static struct bdisp_filter_addr bdisp_v_filter[NB_V_FILTER];
 
diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
index d12a419c044a..3b1ac687d0df 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
@@ -439,7 +439,7 @@ static void bdisp_ctrls_delete(struct bdisp_ctx *ctx)
 
 static int bdisp_queue_setup(struct vb2_queue *vq,
 			     unsigned int *nb_buf, unsigned int *nb_planes,
-			     unsigned int sizes[], void *allocators[])
+			     unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct bdisp_ctx *ctx = vb2_get_drv_priv(vq);
 	struct bdisp_frame *frame = ctx_get_frame(ctx, vq->type);
@@ -453,7 +453,6 @@ static int bdisp_queue_setup(struct vb2_queue *vq,
 		dev_err(ctx->bdisp_dev->dev, "Invalid format\n");
 		return -EINVAL;
 	}
-	allocators[0] = ctx->bdisp_dev->alloc_ctx;
 
 	if (*nb_planes)
 		return sizes[0] < frame->sizeimage ? -EINVAL : 0;
@@ -553,6 +552,7 @@ static int queue_init(void *priv,
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &ctx->bdisp_dev->lock;
+	src_vq->dev = ctx->bdisp_dev->v4l2_dev.dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -567,6 +567,7 @@ static int queue_init(void *priv,
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &ctx->bdisp_dev->lock;
+	dst_vq->dev = ctx->bdisp_dev->v4l2_dev.dev;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -1269,8 +1270,6 @@ static int bdisp_remove(struct platform_device *pdev)
 
 	bdisp_hw_free_filters(bdisp->dev);
 
-	vb2_dma_contig_cleanup_ctx(bdisp->alloc_ctx);
-
 	pm_runtime_disable(&pdev->dev);
 
 	bdisp_debugfs_remove(bdisp);
@@ -1371,18 +1370,11 @@ static int bdisp_probe(struct platform_device *pdev)
 		goto err_dbg;
 	}
 
-	/* Continuous memory allocator */
-	bdisp->alloc_ctx = vb2_dma_contig_init_ctx(dev);
-	if (IS_ERR(bdisp->alloc_ctx)) {
-		ret = PTR_ERR(bdisp->alloc_ctx);
-		goto err_pm;
-	}
-
 	/* Filters */
 	if (bdisp_hw_alloc_filters(bdisp->dev)) {
 		dev_err(bdisp->dev, "no memory for filters\n");
 		ret = -ENOMEM;
-		goto err_vb2_dma;
+		goto err_pm;
 	}
 
 	/* Register */
@@ -1401,8 +1393,6 @@ static int bdisp_probe(struct platform_device *pdev)
 
 err_filter:
 	bdisp_hw_free_filters(bdisp->dev);
-err_vb2_dma:
-	vb2_dma_contig_cleanup_ctx(bdisp->alloc_ctx);
 err_pm:
 	pm_runtime_put(dev);
 err_dbg:
diff --git a/drivers/media/platform/sti/bdisp/bdisp.h b/drivers/media/platform/sti/bdisp/bdisp.h
index 0cf98577222c..b3fbf9902595 100644
--- a/drivers/media/platform/sti/bdisp/bdisp.h
+++ b/drivers/media/platform/sti/bdisp/bdisp.h
@@ -175,7 +175,6 @@ struct bdisp_dbg {
  * @id:         device index
  * @m2m:        memory-to-memory V4L2 device information
  * @state:      flags used to synchronize m2m and capture mode operation
- * @alloc_ctx:  videobuf2 memory allocator context
  * @clock:      IP clock
  * @regs:       registers
  * @irq_queue:  interrupt handler waitqueue
@@ -193,7 +192,6 @@ struct bdisp_dev {
 	u16                     id;
 	struct bdisp_m2m_device m2m;
 	unsigned long           state;
-	struct vb2_alloc_ctx    *alloc_ctx;
 	struct clk              *clock;
 	void __iomem            *regs;
 	wait_queue_head_t       irq_queue;
diff --git a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c
index 7dddf77a62cf..30c148b9d65e 100644
--- a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c
+++ b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c
@@ -1161,6 +1161,7 @@ static int load_c8sectpfe_fw(struct c8sectpfei *fei)
 	if (err) {
 		dev_err(fei->dev, "c8sectpfe_elf_sanity_check failed err=(%d)\n"
 			, err);
+		release_firmware(fw);
 		return err;
 	}
 
diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c
index 82001e6b5553..e967fcfdc1d8 100644
--- a/drivers/media/platform/ti-vpe/cal.c
+++ b/drivers/media/platform/ti-vpe/cal.c
@@ -287,7 +287,6 @@ struct cal_ctx {
 	/* Several counters */
 	unsigned long		jiffies;
 
-	struct vb2_alloc_ctx	*alloc_ctx;
 	struct cal_dmaqueue	vidq;
 
 	/* Input Number */
@@ -1226,14 +1225,13 @@ static int cal_enum_frameintervals(struct file *file, void *priv,
  */
 static int cal_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct cal_ctx *ctx = vb2_get_drv_priv(vq);
 	unsigned size = ctx->v_fmt.fmt.pix.sizeimage;
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
-	alloc_ctxs[0] = ctx->alloc_ctx;
 
 	if (*nplanes) {
 		if (sizes[0] < size)
@@ -1551,6 +1549,7 @@ static int cal_complete_ctx(struct cal_ctx *ctx)
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &ctx->mutex;
 	q->min_buffers_needed = 3;
+	q->dev = ctx->v4l2_dev.dev;
 
 	ret = vb2_queue_init(q);
 	if (ret)
@@ -1578,18 +1577,7 @@ static int cal_complete_ctx(struct cal_ctx *ctx)
 	v4l2_info(&ctx->v4l2_dev, "V4L2 device registered as %s\n",
 		  video_device_node_name(vfd));
 
-	ctx->alloc_ctx = vb2_dma_contig_init_ctx(vfd->v4l2_dev->dev);
-	if (IS_ERR(ctx->alloc_ctx)) {
-		ctx_err(ctx, "Failed to alloc vb2 context\n");
-		ret = PTR_ERR(ctx->alloc_ctx);
-		goto vdev_unreg;
-	}
-
 	return 0;
-
-vdev_unreg:
-	video_unregister_device(vfd);
-	return ret;
 }
 
 static struct device_node *
@@ -1914,7 +1902,6 @@ static int cal_remove(struct platform_device *pdev)
 				video_device_node_name(&ctx->vdev));
 			camerarx_phy_disable(ctx);
 			v4l2_async_notifier_unregister(&ctx->notifier);
-			vb2_dma_contig_cleanup_ctx(ctx->alloc_ctx);
 			v4l2_ctrl_handler_free(&ctx->ctrl_handler);
 			v4l2_device_unregister(&ctx->v4l2_dev);
 			video_unregister_device(&ctx->vdev);
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index 1fa00c2cf3d7..55a1458ac783 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -362,7 +362,6 @@ struct vpe_dev {
 	void __iomem		*base;
 	struct resource		*res;
 
-	struct vb2_alloc_ctx	*alloc_ctx;
 	struct vpdma_data	*vpdma;		/* vpdma data handle */
 	struct sc_data		*sc;		/* scaler data handle */
 	struct csc_data		*csc;		/* csc data handle */
@@ -1797,7 +1796,7 @@ static const struct v4l2_ioctl_ops vpe_ioctl_ops = {
  */
 static int vpe_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	int i;
 	struct vpe_ctx *ctx = vb2_get_drv_priv(vq);
@@ -1807,10 +1806,8 @@ static int vpe_queue_setup(struct vb2_queue *vq,
 
 	*nplanes = q_data->fmt->coplanar ? 2 : 1;
 
-	for (i = 0; i < *nplanes; i++) {
+	for (i = 0; i < *nplanes; i++)
 		sizes[i] = q_data->sizeimage[i];
-		alloc_ctxs[i] = ctx->dev->alloc_ctx;
-	}
 
 	vpe_dbg(ctx->dev, "get %d buffer(s) of size %d", *nbuffers,
 		sizes[VPE_LUMA]);
@@ -1907,6 +1904,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &dev->dev_mutex;
+	src_vq->dev = dev->v4l2_dev.dev;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -1921,6 +1919,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &dev->dev_mutex;
+	dst_vq->dev = dev->v4l2_dev.dev;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -2161,7 +2160,6 @@ static void vpe_fw_cb(struct platform_device *pdev)
 		vpe_runtime_put(pdev);
 		pm_runtime_disable(&pdev->dev);
 		v4l2_m2m_release(dev->m2m_dev);
-		vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
 		v4l2_device_unregister(&dev->v4l2_dev);
 
 		return;
@@ -2213,18 +2211,11 @@ static int vpe_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dev);
 
-	dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		vpe_err(dev, "Failed to alloc vb2 context\n");
-		ret = PTR_ERR(dev->alloc_ctx);
-		goto v4l2_dev_unreg;
-	}
-
 	dev->m2m_dev = v4l2_m2m_init(&m2m_ops);
 	if (IS_ERR(dev->m2m_dev)) {
 		vpe_err(dev, "Failed to init mem2mem device\n");
 		ret = PTR_ERR(dev->m2m_dev);
-		goto rel_ctx;
+		goto v4l2_dev_unreg;
 	}
 
 	pm_runtime_enable(&pdev->dev);
@@ -2269,8 +2260,6 @@ runtime_put:
 rel_m2m:
 	pm_runtime_disable(&pdev->dev);
 	v4l2_m2m_release(dev->m2m_dev);
-rel_ctx:
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
 v4l2_dev_unreg:
 	v4l2_device_unregister(&dev->v4l2_dev);
 
@@ -2286,7 +2275,6 @@ static int vpe_remove(struct platform_device *pdev)
 	v4l2_m2m_release(dev->m2m_dev);
 	video_unregister_device(&dev->vfd);
 	v4l2_device_unregister(&dev->v4l2_dev);
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
 
 	vpe_set_clock_enable(dev, 0);
 	vpe_runtime_put(pdev);
diff --git a/drivers/media/platform/via-camera.c b/drivers/media/platform/via-camera.c
index 1254f7e4d732..7ca12deba89c 100644
--- a/drivers/media/platform/via-camera.c
+++ b/drivers/media/platform/via-camera.c
@@ -240,7 +240,7 @@ static int viacam_set_flip(struct via_camera *cam)
 	memset(&ctrl, 0, sizeof(ctrl));
 	ctrl.id = V4L2_CID_VFLIP;
 	ctrl.value = flip_image;
-	return sensor_call(cam, core, s_ctrl, &ctrl);
+	return v4l2_s_ctrl(NULL, cam->sensor->ctrl_handler, &ctrl);
 }
 
 /*
diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index c4b5fab83666..6b17015048ae 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -711,7 +711,7 @@ static const struct v4l2_ioctl_ops vim2m_ioctl_ops = {
 
 static int vim2m_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct vim2m_ctx *ctx = vb2_get_drv_priv(vq);
 	struct vim2m_q_data *q_data;
@@ -731,11 +731,6 @@ static int vim2m_queue_setup(struct vb2_queue *vq,
 	*nplanes = 1;
 	sizes[0] = size;
 
-	/*
-	 * videobuf2-vmalloc allocator is context-less so no need to set
-	 * alloc_ctxs array.
-	 */
-
 	dprintk(ctx->dev, "get %d buffer(s) of size %d each.\n", count, size);
 
 	return 0;
diff --git a/drivers/media/platform/vivid/Kconfig b/drivers/media/platform/vivid/Kconfig
index f535f576913d..8e6918c5c87c 100644
--- a/drivers/media/platform/vivid/Kconfig
+++ b/drivers/media/platform/vivid/Kconfig
@@ -6,6 +6,7 @@ config VIDEO_VIVID
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
+	select MEDIA_CEC_EDID
 	select VIDEOBUF2_VMALLOC
 	select VIDEO_V4L2_TPG
 	default n
@@ -22,6 +23,13 @@ config VIDEO_VIVID
 	  Say Y here if you want to test video apps or debug V4L devices.
 	  When in doubt, say N.
 
+config VIDEO_VIVID_CEC
+	bool "Enable CEC emulation support"
+	depends on VIDEO_VIVID && MEDIA_CEC
+	---help---
+	  When selected the vivid module will emulate the optional
+	  HDMI CEC feature.
+
 config VIDEO_VIVID_MAX_DEVS
 	int "Maximum number of devices"
 	depends on VIDEO_VIVID
diff --git a/drivers/media/platform/vivid/Makefile b/drivers/media/platform/vivid/Makefile
index 633c8a1b2c27..29738810e3ee 100644
--- a/drivers/media/platform/vivid/Makefile
+++ b/drivers/media/platform/vivid/Makefile
@@ -3,4 +3,8 @@ vivid-objs := vivid-core.o vivid-ctrls.o vivid-vid-common.o vivid-vbi-gen.o \
 		vivid-radio-rx.o vivid-radio-tx.o vivid-radio-common.o \
 		vivid-rds-gen.o vivid-sdr-cap.o vivid-vbi-cap.o vivid-vbi-out.o \
 		vivid-osd.o
+ifeq ($(CONFIG_VIDEO_VIVID_CEC),y)
+  vivid-objs += vivid-cec.o
+endif
+
 obj-$(CONFIG_VIDEO_VIVID) += vivid.o
diff --git a/drivers/media/platform/vivid/vivid-cec.c b/drivers/media/platform/vivid/vivid-cec.c
new file mode 100644
index 000000000000..66aa7292076b
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-cec.c
@@ -0,0 +1,241 @@
+/*
+ * vivid-cec.c - A Virtual Video Test Driver, cec emulation
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#include <media/cec.h>
+
+#include "vivid-core.h"
+#include "vivid-cec.h"
+
+void vivid_cec_bus_free_work(struct vivid_dev *dev)
+{
+	spin_lock(&dev->cec_slock);
+	while (!list_empty(&dev->cec_work_list)) {
+		struct vivid_cec_work *cw =
+			list_first_entry(&dev->cec_work_list,
+					 struct vivid_cec_work, list);
+
+		spin_unlock(&dev->cec_slock);
+		cancel_delayed_work_sync(&cw->work);
+		spin_lock(&dev->cec_slock);
+		list_del(&cw->list);
+		cec_transmit_done(cw->adap, CEC_TX_STATUS_LOW_DRIVE, 0, 0, 1, 0);
+		kfree(cw);
+	}
+	spin_unlock(&dev->cec_slock);
+}
+
+static bool vivid_cec_find_dest_adap(struct vivid_dev *dev,
+				     struct cec_adapter *adap, u8 dest)
+{
+	unsigned int i;
+
+	if (dest >= 0xf)
+		return false;
+
+	if (adap != dev->cec_rx_adap && dev->cec_rx_adap &&
+	    dev->cec_rx_adap->is_configured &&
+	    cec_has_log_addr(dev->cec_rx_adap, dest))
+		return true;
+
+	for (i = 0; i < MAX_OUTPUTS && dev->cec_tx_adap[i]; i++) {
+		if (adap == dev->cec_tx_adap[i])
+			continue;
+		if (!dev->cec_tx_adap[i]->is_configured)
+			continue;
+		if (cec_has_log_addr(dev->cec_tx_adap[i], dest))
+			return true;
+	}
+	return false;
+}
+
+static void vivid_cec_xfer_done_worker(struct work_struct *work)
+{
+	struct vivid_cec_work *cw =
+		container_of(work, struct vivid_cec_work, work.work);
+	struct vivid_dev *dev = cw->dev;
+	struct cec_adapter *adap = cw->adap;
+	u8 dest = cec_msg_destination(&cw->msg);
+	bool valid_dest;
+	unsigned int i;
+
+	valid_dest = cec_msg_is_broadcast(&cw->msg);
+	if (!valid_dest)
+		valid_dest = vivid_cec_find_dest_adap(dev, adap, dest);
+
+	cw->tx_status = valid_dest ? CEC_TX_STATUS_OK : CEC_TX_STATUS_NACK;
+	spin_lock(&dev->cec_slock);
+	dev->cec_xfer_time_jiffies = 0;
+	dev->cec_xfer_start_jiffies = 0;
+	list_del(&cw->list);
+	spin_unlock(&dev->cec_slock);
+	cec_transmit_done(cw->adap, cw->tx_status, 0, valid_dest ? 0 : 1, 0, 0);
+
+	/* Broadcast message */
+	if (adap != dev->cec_rx_adap)
+		cec_received_msg(dev->cec_rx_adap, &cw->msg);
+	for (i = 0; i < MAX_OUTPUTS && dev->cec_tx_adap[i]; i++)
+		if (adap != dev->cec_tx_adap[i])
+			cec_received_msg(dev->cec_tx_adap[i], &cw->msg);
+	kfree(cw);
+}
+
+static void vivid_cec_xfer_try_worker(struct work_struct *work)
+{
+	struct vivid_cec_work *cw =
+		container_of(work, struct vivid_cec_work, work.work);
+	struct vivid_dev *dev = cw->dev;
+
+	spin_lock(&dev->cec_slock);
+	if (dev->cec_xfer_time_jiffies) {
+		list_del(&cw->list);
+		spin_unlock(&dev->cec_slock);
+		cec_transmit_done(cw->adap, CEC_TX_STATUS_ARB_LOST, 1, 0, 0, 0);
+		kfree(cw);
+	} else {
+		INIT_DELAYED_WORK(&cw->work, vivid_cec_xfer_done_worker);
+		dev->cec_xfer_start_jiffies = jiffies;
+		dev->cec_xfer_time_jiffies = usecs_to_jiffies(cw->usecs);
+		spin_unlock(&dev->cec_slock);
+		schedule_delayed_work(&cw->work, dev->cec_xfer_time_jiffies);
+	}
+}
+
+static int vivid_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	return 0;
+}
+
+static int vivid_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
+{
+	return 0;
+}
+
+/*
+ * One data bit takes 2400 us, each byte needs 10 bits so that's 24000 us
+ * per byte.
+ */
+#define USECS_PER_BYTE 24000
+
+static int vivid_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				   u32 signal_free_time, struct cec_msg *msg)
+{
+	struct vivid_dev *dev = adap->priv;
+	struct vivid_cec_work *cw = kzalloc(sizeof(*cw), GFP_KERNEL);
+	long delta_jiffies = 0;
+
+	if (cw == NULL)
+		return -ENOMEM;
+	cw->dev = dev;
+	cw->adap = adap;
+	cw->usecs = CEC_FREE_TIME_TO_USEC(signal_free_time) +
+		    msg->len * USECS_PER_BYTE;
+	cw->msg = *msg;
+
+	spin_lock(&dev->cec_slock);
+	list_add(&cw->list, &dev->cec_work_list);
+	if (dev->cec_xfer_time_jiffies == 0) {
+		INIT_DELAYED_WORK(&cw->work, vivid_cec_xfer_done_worker);
+		dev->cec_xfer_start_jiffies = jiffies;
+		dev->cec_xfer_time_jiffies = usecs_to_jiffies(cw->usecs);
+		delta_jiffies = dev->cec_xfer_time_jiffies;
+	} else {
+		INIT_DELAYED_WORK(&cw->work, vivid_cec_xfer_try_worker);
+		delta_jiffies = dev->cec_xfer_start_jiffies +
+			dev->cec_xfer_time_jiffies - jiffies;
+	}
+	spin_unlock(&dev->cec_slock);
+	schedule_delayed_work(&cw->work, delta_jiffies < 0 ? 0 : delta_jiffies);
+	return 0;
+}
+
+static int vivid_received(struct cec_adapter *adap, struct cec_msg *msg)
+{
+	struct vivid_dev *dev = adap->priv;
+	struct cec_msg reply;
+	u8 dest = cec_msg_destination(msg);
+	u16 pa;
+	u8 disp_ctl;
+	char osd[14];
+
+	if (cec_msg_is_broadcast(msg))
+		dest = adap->log_addrs.log_addr[0];
+	cec_msg_init(&reply, dest, cec_msg_initiator(msg));
+
+	switch (cec_msg_opcode(msg)) {
+	case CEC_MSG_SET_STREAM_PATH:
+		if (cec_is_sink(adap))
+			return -ENOMSG;
+		cec_ops_set_stream_path(msg, &pa);
+		if (pa != adap->phys_addr)
+			return -ENOMSG;
+		cec_msg_active_source(&reply, adap->phys_addr);
+		cec_transmit_msg(adap, &reply, false);
+		break;
+	case CEC_MSG_SET_OSD_STRING:
+		if (!cec_is_sink(adap))
+			return -ENOMSG;
+		cec_ops_set_osd_string(msg, &disp_ctl, osd);
+		switch (disp_ctl) {
+		case CEC_OP_DISP_CTL_DEFAULT:
+			strcpy(dev->osd, osd);
+			dev->osd_jiffies = jiffies;
+			break;
+		case CEC_OP_DISP_CTL_UNTIL_CLEARED:
+			strcpy(dev->osd, osd);
+			dev->osd_jiffies = 0;
+			break;
+		case CEC_OP_DISP_CTL_CLEAR:
+			dev->osd[0] = 0;
+			dev->osd_jiffies = 0;
+			break;
+		default:
+			cec_msg_feature_abort(&reply, cec_msg_opcode(msg),
+					      CEC_OP_ABORT_INVALID_OP);
+			cec_transmit_msg(adap, &reply, false);
+			break;
+		}
+		break;
+	default:
+		return -ENOMSG;
+	}
+	return 0;
+}
+
+static const struct cec_adap_ops vivid_cec_adap_ops = {
+	.adap_enable = vivid_cec_adap_enable,
+	.adap_log_addr = vivid_cec_adap_log_addr,
+	.adap_transmit = vivid_cec_adap_transmit,
+	.received = vivid_received,
+};
+
+struct cec_adapter *vivid_cec_alloc_adap(struct vivid_dev *dev,
+					 unsigned int idx,
+					 struct device *parent,
+					 bool is_source)
+{
+	char name[sizeof(dev->vid_out_dev.name) + 2];
+	u32 caps = CEC_CAP_TRANSMIT | CEC_CAP_LOG_ADDRS |
+		CEC_CAP_PASSTHROUGH | CEC_CAP_RC | CEC_CAP_MONITOR_ALL;
+
+	snprintf(name, sizeof(name), "%s%d",
+		 is_source ? dev->vid_out_dev.name : dev->vid_cap_dev.name,
+		 idx);
+	return cec_allocate_adapter(&vivid_cec_adap_ops, dev,
+		name, caps, 1, parent);
+}
diff --git a/drivers/media/platform/vivid/vivid-cec.h b/drivers/media/platform/vivid/vivid-cec.h
new file mode 100644
index 000000000000..97892afa6b3b
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-cec.h
@@ -0,0 +1,33 @@
+/*
+ * vivid-cec.h - A Virtual Video Test Driver, cec emulation
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#ifdef CONFIG_VIDEO_VIVID_CEC
+struct cec_adapter *vivid_cec_alloc_adap(struct vivid_dev *dev,
+					 unsigned int idx,
+					 struct device *parent,
+					 bool is_source);
+void vivid_cec_bus_free_work(struct vivid_dev *dev);
+
+#else
+
+static inline void vivid_cec_bus_free_work(struct vivid_dev *dev)
+{
+}
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-core.c b/drivers/media/platform/vivid/vivid-core.c
index c14da84af09b..7f937136c3f5 100644
--- a/drivers/media/platform/vivid/vivid-core.c
+++ b/drivers/media/platform/vivid/vivid-core.c
@@ -46,6 +46,7 @@
 #include "vivid-vbi-cap.h"
 #include "vivid-vbi-out.h"
 #include "vivid-osd.h"
+#include "vivid-cec.h"
 #include "vivid-ctrls.h"
 
 #define VIVID_MODULE_NAME "vivid"
@@ -684,6 +685,11 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		dev->input_name_counter[i] = in_type_counter[dev->input_type[i]]++;
 	}
 	dev->has_audio_inputs = in_type_counter[TV] && in_type_counter[SVID];
+	if (in_type_counter[HDMI] == 16) {
+		/* The CEC physical address only allows for max 15 inputs */
+		in_type_counter[HDMI]--;
+		dev->num_inputs--;
+	}
 
 	/* how many outputs do we have and of what type? */
 	dev->num_outputs = num_outputs[inst];
@@ -696,6 +702,15 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		dev->output_name_counter[i] = out_type_counter[dev->output_type[i]]++;
 	}
 	dev->has_audio_outputs = out_type_counter[SVID];
+	if (out_type_counter[HDMI] == 16) {
+		/*
+		 * The CEC physical address only allows for max 15 inputs,
+		 * so outputs are also limited to 15 to allow for easy
+		 * CEC output to input mapping.
+		 */
+		out_type_counter[HDMI]--;
+		dev->num_outputs--;
+	}
 
 	/* do we create a video capture device? */
 	dev->has_vid_cap = node_type & 0x0001;
@@ -1010,6 +1025,17 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	INIT_LIST_HEAD(&dev->vbi_out_active);
 	INIT_LIST_HEAD(&dev->sdr_cap_active);
 
+	INIT_LIST_HEAD(&dev->cec_work_list);
+	spin_lock_init(&dev->cec_slock);
+	/*
+	 * Same as create_singlethread_workqueue, but now I can use the
+	 * string formatting of alloc_ordered_workqueue.
+	 */
+	dev->cec_workqueue =
+		alloc_ordered_workqueue("vivid-%03d-cec", WQ_MEM_RECLAIM, inst);
+	if (!dev->cec_workqueue)
+		goto unreg_dev;
+
 	/* start creating the vb2 queues */
 	if (dev->has_vid_cap) {
 		/* initialize vid_cap queue */
@@ -1117,7 +1143,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	/* finally start creating the device nodes */
 	if (dev->has_vid_cap) {
 		vfd = &dev->vid_cap_dev;
-		strlcpy(vfd->name, "vivid-vid-cap", sizeof(vfd->name));
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-vid-cap", inst);
 		vfd->fops = &vivid_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
 		vfd->device_caps = dev->vid_cap_caps;
@@ -1133,6 +1160,27 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		vfd->lock = &dev->mutex;
 		video_set_drvdata(vfd, dev);
 
+#ifdef CONFIG_VIDEO_VIVID_CEC
+		if (in_type_counter[HDMI]) {
+			struct cec_adapter *adap;
+
+			adap = vivid_cec_alloc_adap(dev, 0, &pdev->dev, false);
+			ret = PTR_ERR_OR_ZERO(adap);
+			if (ret < 0)
+				goto unreg_dev;
+			dev->cec_rx_adap = adap;
+			ret = cec_register_adapter(adap);
+			if (ret < 0) {
+				cec_delete_adapter(adap);
+				dev->cec_rx_adap = NULL;
+				goto unreg_dev;
+			}
+			cec_s_phys_addr(adap, 0, false);
+			v4l2_info(&dev->v4l2_dev, "CEC adapter %s registered for HDMI input %d\n",
+				  dev_name(&adap->devnode.dev), i);
+		}
+#endif
+
 		ret = video_register_device(vfd, VFL_TYPE_GRABBER, vid_cap_nr[inst]);
 		if (ret < 0)
 			goto unreg_dev;
@@ -1141,8 +1189,13 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	}
 
 	if (dev->has_vid_out) {
+#ifdef CONFIG_VIDEO_VIVID_CEC
+		unsigned int bus_cnt = 0;
+#endif
+
 		vfd = &dev->vid_out_dev;
-		strlcpy(vfd->name, "vivid-vid-out", sizeof(vfd->name));
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-vid-out", inst);
 		vfd->vfl_dir = VFL_DIR_TX;
 		vfd->fops = &vivid_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
@@ -1159,6 +1212,35 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		vfd->lock = &dev->mutex;
 		video_set_drvdata(vfd, dev);
 
+#ifdef CONFIG_VIDEO_VIVID_CEC
+		for (i = 0; i < dev->num_outputs; i++) {
+			struct cec_adapter *adap;
+
+			if (dev->output_type[i] != HDMI)
+				continue;
+			dev->cec_output2bus_map[i] = bus_cnt;
+			adap = vivid_cec_alloc_adap(dev, bus_cnt,
+						     &pdev->dev, true);
+			ret = PTR_ERR_OR_ZERO(adap);
+			if (ret < 0)
+				goto unreg_dev;
+			dev->cec_tx_adap[bus_cnt] = adap;
+			ret = cec_register_adapter(adap);
+			if (ret < 0) {
+				cec_delete_adapter(adap);
+				dev->cec_tx_adap[bus_cnt] = NULL;
+				goto unreg_dev;
+			}
+			bus_cnt++;
+			if (bus_cnt <= out_type_counter[HDMI])
+				cec_s_phys_addr(adap, bus_cnt << 12, false);
+			else
+				cec_s_phys_addr(adap, 0x1000, false);
+			v4l2_info(&dev->v4l2_dev, "CEC adapter %s registered for HDMI output %d\n",
+				  dev_name(&adap->devnode.dev), i);
+		}
+#endif
+
 		ret = video_register_device(vfd, VFL_TYPE_GRABBER, vid_out_nr[inst]);
 		if (ret < 0)
 			goto unreg_dev;
@@ -1168,7 +1250,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 
 	if (dev->has_vbi_cap) {
 		vfd = &dev->vbi_cap_dev;
-		strlcpy(vfd->name, "vivid-vbi-cap", sizeof(vfd->name));
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-vbi-cap", inst);
 		vfd->fops = &vivid_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
 		vfd->device_caps = dev->vbi_cap_caps;
@@ -1191,7 +1274,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 
 	if (dev->has_vbi_out) {
 		vfd = &dev->vbi_out_dev;
-		strlcpy(vfd->name, "vivid-vbi-out", sizeof(vfd->name));
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-vbi-out", inst);
 		vfd->vfl_dir = VFL_DIR_TX;
 		vfd->fops = &vivid_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
@@ -1215,7 +1299,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 
 	if (dev->has_sdr_cap) {
 		vfd = &dev->sdr_cap_dev;
-		strlcpy(vfd->name, "vivid-sdr-cap", sizeof(vfd->name));
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-sdr-cap", inst);
 		vfd->fops = &vivid_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
 		vfd->device_caps = dev->sdr_cap_caps;
@@ -1234,7 +1319,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 
 	if (dev->has_radio_rx) {
 		vfd = &dev->radio_rx_dev;
-		strlcpy(vfd->name, "vivid-rad-rx", sizeof(vfd->name));
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-rad-rx", inst);
 		vfd->fops = &vivid_radio_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
 		vfd->device_caps = dev->radio_rx_caps;
@@ -1252,7 +1338,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 
 	if (dev->has_radio_tx) {
 		vfd = &dev->radio_tx_dev;
-		strlcpy(vfd->name, "vivid-rad-tx", sizeof(vfd->name));
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-rad-tx", inst);
 		vfd->vfl_dir = VFL_DIR_TX;
 		vfd->fops = &vivid_radio_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
@@ -1282,6 +1369,13 @@ unreg_dev:
 	video_unregister_device(&dev->vbi_cap_dev);
 	video_unregister_device(&dev->vid_out_dev);
 	video_unregister_device(&dev->vid_cap_dev);
+	cec_unregister_adapter(dev->cec_rx_adap);
+	for (i = 0; i < MAX_OUTPUTS; i++)
+		cec_unregister_adapter(dev->cec_tx_adap[i]);
+	if (dev->cec_workqueue) {
+		vivid_cec_bus_free_work(dev);
+		destroy_workqueue(dev->cec_workqueue);
+	}
 free_dev:
 	v4l2_device_put(&dev->v4l2_dev);
 	return ret;
@@ -1331,8 +1425,7 @@ static int vivid_probe(struct platform_device *pdev)
 static int vivid_remove(struct platform_device *pdev)
 {
 	struct vivid_dev *dev;
-	unsigned i;
-
+	unsigned int i, j;
 
 	for (i = 0; i < n_devs; i++) {
 		dev = vivid_devs[i];
@@ -1380,6 +1473,13 @@ static int vivid_remove(struct platform_device *pdev)
 			unregister_framebuffer(&dev->fb_info);
 			vivid_fb_release_buffers(dev);
 		}
+		cec_unregister_adapter(dev->cec_rx_adap);
+		for (j = 0; j < MAX_OUTPUTS; j++)
+			cec_unregister_adapter(dev->cec_tx_adap[j]);
+		if (dev->cec_workqueue) {
+			vivid_cec_bus_free_work(dev);
+			destroy_workqueue(dev->cec_workqueue);
+		}
 		v4l2_device_put(&dev->v4l2_dev);
 		vivid_devs[i] = NULL;
 	}
diff --git a/drivers/media/platform/vivid/vivid-core.h b/drivers/media/platform/vivid/vivid-core.h
index 776783bec227..a7daa40d0a49 100644
--- a/drivers/media/platform/vivid/vivid-core.h
+++ b/drivers/media/platform/vivid/vivid-core.h
@@ -21,6 +21,8 @@
 #define _VIVID_CORE_H_
 
 #include <linux/fb.h>
+#include <linux/workqueue.h>
+#include <media/cec.h>
 #include <media/videobuf2-v4l2.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-dev.h>
@@ -132,6 +134,17 @@ enum vivid_colorspace {
 #define VIVID_INVALID_SIGNAL(mode) \
 	((mode) == NO_SIGNAL || (mode) == NO_LOCK || (mode) == OUT_OF_RANGE)
 
+struct vivid_cec_work {
+	struct list_head	list;
+	struct delayed_work	work;
+	struct cec_adapter	*adap;
+	struct vivid_dev	*dev;
+	unsigned int		usecs;
+	unsigned int		timeout_ms;
+	u8			tx_status;
+	struct cec_msg		msg;
+};
+
 struct vivid_dev {
 	unsigned			inst;
 	struct v4l2_device		v4l2_dev;
@@ -497,6 +510,20 @@ struct vivid_dev {
 	/* Shared between radio receiver and transmitter */
 	bool				radio_rds_loop;
 	struct timespec			radio_rds_init_ts;
+
+	/* CEC */
+	struct cec_adapter		*cec_rx_adap;
+	struct cec_adapter		*cec_tx_adap[MAX_OUTPUTS];
+	struct workqueue_struct		*cec_workqueue;
+	spinlock_t			cec_slock;
+	struct list_head		cec_work_list;
+	unsigned int			cec_xfer_time_jiffies;
+	unsigned long			cec_xfer_start_jiffies;
+	u8				cec_output2bus_map[MAX_OUTPUTS];
+
+	/* CEC OSD String */
+	char				osd[14];
+	unsigned long			osd_jiffies;
 };
 
 static inline bool vivid_is_webcam(const struct vivid_dev *dev)
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
index 3b8c10108dfa..6ca71aabb576 100644
--- a/drivers/media/platform/vivid/vivid-kthread-cap.c
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -552,6 +552,19 @@ static void vivid_fillbuff(struct vivid_dev *dev, struct vivid_buffer *buf)
 			snprintf(str, sizeof(str), " button pressed!");
 			tpg_gen_text(tpg, basep, line++ * line_height, 16, str);
 		}
+		if (dev->osd[0]) {
+			if (vivid_is_hdmi_cap(dev)) {
+				snprintf(str, sizeof(str),
+					 " OSD \"%s\"", dev->osd);
+				tpg_gen_text(tpg, basep, line++ * line_height,
+					     16, str);
+			}
+			if (dev->osd_jiffies &&
+			    time_is_before_jiffies(dev->osd_jiffies + 5 * HZ)) {
+				dev->osd[0] = 0;
+				dev->osd_jiffies = 0;
+			}
+		}
 	}
 
 	/*
diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c
index 3d1604cb982f..ebd7b9c4dd83 100644
--- a/drivers/media/platform/vivid/vivid-sdr-cap.c
+++ b/drivers/media/platform/vivid/vivid-sdr-cap.c
@@ -51,8 +51,6 @@ static const struct vivid_format formats[] = {
 	},
 };
 
-static const unsigned int NUM_FORMATS = ARRAY_SIZE(formats);
-
 static const struct v4l2_frequency_band bands_adc[] = {
 	{
 		.tuner = 0,
@@ -215,7 +213,7 @@ static int vivid_thread_sdr_cap(void *data)
 
 static int sdr_cap_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
-		       unsigned sizes[], void *alloc_ctxs[])
+		       unsigned sizes[], struct device *alloc_devs[])
 {
 	/* 2 = max 16-bit sample returned */
 	sizes[0] = SDR_CAP_SAMPLES_PER_BUF * 2;
diff --git a/drivers/media/platform/vivid/vivid-vbi-cap.c b/drivers/media/platform/vivid/vivid-vbi-cap.c
index cda45a582bfe..d66ef95dd2b5 100644
--- a/drivers/media/platform/vivid/vivid-vbi-cap.c
+++ b/drivers/media/platform/vivid/vivid-vbi-cap.c
@@ -137,7 +137,7 @@ void vivid_sliced_vbi_cap_process(struct vivid_dev *dev,
 
 static int vbi_cap_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
-		       unsigned sizes[], void *alloc_ctxs[])
+		       unsigned sizes[], struct device *alloc_devs[])
 {
 	struct vivid_dev *dev = vb2_get_drv_priv(vq);
 	bool is_60hz = dev->std_cap & V4L2_STD_525_60;
diff --git a/drivers/media/platform/vivid/vivid-vbi-out.c b/drivers/media/platform/vivid/vivid-vbi-out.c
index 3c5a469e6f49..d2989195cf03 100644
--- a/drivers/media/platform/vivid/vivid-vbi-out.c
+++ b/drivers/media/platform/vivid/vivid-vbi-out.c
@@ -29,7 +29,7 @@
 
 static int vbi_out_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
-		       unsigned sizes[], void *alloc_ctxs[])
+		       unsigned sizes[], struct device *alloc_devs[])
 {
 	struct vivid_dev *dev = vb2_get_drv_priv(vq);
 	bool is_60hz = dev->std_out & V4L2_STD_525_60;
diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c
index 4f730f355a17..d404a7ce33a4 100644
--- a/drivers/media/platform/vivid/vivid-vid-cap.c
+++ b/drivers/media/platform/vivid/vivid-vid-cap.c
@@ -36,8 +36,7 @@
 /* timeperframe: min/max and default */
 static const struct v4l2_fract
 	tpf_min     = {.numerator = 1,		.denominator = FPS_MAX},
-	tpf_max     = {.numerator = FPS_MAX,	.denominator = 1},
-	tpf_default = {.numerator = 1,		.denominator = 30};
+	tpf_max     = {.numerator = FPS_MAX,	.denominator = 1};
 
 static const struct vivid_fmt formats_ovl[] = {
 	{
@@ -98,7 +97,7 @@ static const struct v4l2_discrete_probe webcam_probe = {
 
 static int vid_cap_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
-		       unsigned sizes[], void *alloc_ctxs[])
+		       unsigned sizes[], struct device *alloc_devs[])
 {
 	struct vivid_dev *dev = vb2_get_drv_priv(vq);
 	unsigned buffers = tpg_g_buffers(&dev->tpg);
@@ -145,11 +144,6 @@ static int vid_cap_queue_setup(struct vb2_queue *vq,
 
 	*nplanes = buffers;
 
-	/*
-	 * videobuf2-vmalloc allocator is context-less so no need to set
-	 * alloc_ctxs array.
-	 */
-
 	dprintk(dev, 1, "%s: count=%d\n", __func__, *nbuffers);
 	for (p = 0; p < buffers; p++)
 		dprintk(dev, 1, "%s: size[%u]=%u\n", __func__, p, sizes[p]);
@@ -1701,6 +1695,9 @@ int vidioc_s_edid(struct file *file, void *_fh,
 			 struct v4l2_edid *edid)
 {
 	struct vivid_dev *dev = video_drvdata(file);
+	u16 phys_addr;
+	unsigned int i;
+	int ret;
 
 	memset(edid->reserved, 0, sizeof(edid->reserved));
 	if (edid->pad >= dev->num_inputs)
@@ -1709,14 +1706,32 @@ int vidioc_s_edid(struct file *file, void *_fh,
 		return -EINVAL;
 	if (edid->blocks == 0) {
 		dev->edid_blocks = 0;
-		return 0;
+		phys_addr = CEC_PHYS_ADDR_INVALID;
+		goto set_phys_addr;
 	}
 	if (edid->blocks > dev->edid_max_blocks) {
 		edid->blocks = dev->edid_max_blocks;
 		return -E2BIG;
 	}
+	phys_addr = cec_get_edid_phys_addr(edid->edid, edid->blocks * 128, NULL);
+	ret = cec_phys_addr_validate(phys_addr, &phys_addr, NULL);
+	if (ret)
+		return ret;
+
+	if (vb2_is_busy(&dev->vb_vid_cap_q))
+		return -EBUSY;
+
 	dev->edid_blocks = edid->blocks;
 	memcpy(dev->edid, edid->edid, edid->blocks * 128);
+
+set_phys_addr:
+	/* TODO: a proper hotplug detect cycle should be emulated here */
+	cec_s_phys_addr(dev->cec_rx_adap, phys_addr, false);
+
+	for (i = 0; i < MAX_OUTPUTS && dev->cec_tx_adap[i]; i++)
+		cec_s_phys_addr(dev->cec_tx_adap[i],
+				cec_phys_addr_for_input(phys_addr, i + 1),
+				false);
 	return 0;
 }
 
@@ -1836,6 +1851,7 @@ int vivid_vid_cap_s_parm(struct file *file, void *priv,
 	/* resync the thread's timings */
 	dev->cap_seq_resync = true;
 	dev->timeperframe_vid_cap = tpf;
+	parm->parm.capture.capability   = V4L2_CAP_TIMEPERFRAME;
 	parm->parm.capture.timeperframe = tpf;
 	parm->parm.capture.readbuffers  = 1;
 	return 0;
diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c
index 39ea2284789c..fcda3ae4e6b0 100644
--- a/drivers/media/platform/vivid/vivid-vid-common.c
+++ b/drivers/media/platform/vivid/vivid-vid-common.c
@@ -811,6 +811,7 @@ int vidioc_g_edid(struct file *file, void *_fh,
 {
 	struct vivid_dev *dev = video_drvdata(file);
 	struct video_device *vdev = video_devdata(file);
+	struct cec_adapter *adap;
 
 	memset(edid->reserved, 0, sizeof(edid->reserved));
 	if (vdev->vfl_dir == VFL_DIR_RX) {
@@ -818,11 +819,16 @@ int vidioc_g_edid(struct file *file, void *_fh,
 			return -EINVAL;
 		if (dev->input_type[edid->pad] != HDMI)
 			return -EINVAL;
+		adap = dev->cec_rx_adap;
 	} else {
+		unsigned int bus_idx;
+
 		if (edid->pad >= dev->num_outputs)
 			return -EINVAL;
 		if (dev->output_type[edid->pad] != HDMI)
 			return -EINVAL;
+		bus_idx = dev->cec_output2bus_map[edid->pad];
+		adap = dev->cec_tx_adap[bus_idx];
 	}
 	if (edid->start_block == 0 && edid->blocks == 0) {
 		edid->blocks = dev->edid_blocks;
@@ -835,5 +841,6 @@ int vidioc_g_edid(struct file *file, void *_fh,
 	if (edid->start_block + edid->blocks > dev->edid_blocks)
 		edid->blocks = dev->edid_blocks - edid->start_block;
 	memcpy(edid->edid, dev->edid, edid->blocks * 128);
+	cec_set_edid_phys_addr(edid->edid, edid->blocks * 128, adap->phys_addr);
 	return 0;
 }
diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c
index f92f4496d527..dd609eea4753 100644
--- a/drivers/media/platform/vivid/vivid-vid-out.c
+++ b/drivers/media/platform/vivid/vivid-vid-out.c
@@ -34,7 +34,7 @@
 
 static int vid_out_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
-		       unsigned sizes[], void *alloc_ctxs[])
+		       unsigned sizes[], struct device *alloc_devs[])
 {
 	struct vivid_dev *dev = vb2_get_drv_priv(vq);
 	const struct vivid_fmt *vfmt = dev->fmt_out;
@@ -87,11 +87,6 @@ static int vid_out_queue_setup(struct vb2_queue *vq,
 
 	*nplanes = planes;
 
-	/*
-	 * videobuf2-vmalloc allocator is context-less so no need to set
-	 * alloc_ctxs array.
-	 */
-
 	dprintk(dev, 1, "%s: count=%d\n", __func__, *nbuffers);
 	for (p = 0; p < planes; p++)
 		dprintk(dev, 1, "%s: size[%u]=%u\n", __func__, p, sizes[p]);
diff --git a/drivers/media/platform/vsp1/Makefile b/drivers/media/platform/vsp1/Makefile
index 95b3ac2ea7ef..1328e1bd2143 100644
--- a/drivers/media/platform/vsp1/Makefile
+++ b/drivers/media/platform/vsp1/Makefile
@@ -1,7 +1,8 @@
 vsp1-y					:= vsp1_drv.o vsp1_entity.o vsp1_pipe.o
 vsp1-y					+= vsp1_dl.o vsp1_drm.o vsp1_video.o
 vsp1-y					+= vsp1_rpf.o vsp1_rwpf.o vsp1_wpf.o
-vsp1-y					+= vsp1_hsit.o vsp1_lif.o vsp1_lut.o
+vsp1-y					+= vsp1_clu.o vsp1_hsit.o vsp1_lut.o
 vsp1-y					+= vsp1_bru.o vsp1_sru.o vsp1_uds.o
+vsp1-y					+= vsp1_lif.o
 
 obj-$(CONFIG_VIDEO_RENESAS_VSP1)	+= vsp1.o
diff --git a/drivers/media/platform/vsp1/vsp1.h b/drivers/media/platform/vsp1/vsp1.h
index 46738b6c5f72..06a2ec7e5ad4 100644
--- a/drivers/media/platform/vsp1/vsp1.h
+++ b/drivers/media/platform/vsp1/vsp1.h
@@ -25,11 +25,13 @@
 
 struct clk;
 struct device;
+struct rcar_fcp_device;
 
 struct vsp1_drm;
 struct vsp1_entity;
 struct vsp1_platform_data;
 struct vsp1_bru;
+struct vsp1_clu;
 struct vsp1_hsit;
 struct vsp1_lif;
 struct vsp1_lut;
@@ -45,6 +47,9 @@ struct vsp1_uds;
 #define VSP1_HAS_LUT		(1 << 1)
 #define VSP1_HAS_SRU		(1 << 2)
 #define VSP1_HAS_BRU		(1 << 3)
+#define VSP1_HAS_CLU		(1 << 4)
+#define VSP1_HAS_WPF_VFLIP	(1 << 5)
+#define VSP1_HAS_WPF_HFLIP	(1 << 6)
 
 struct vsp1_device_info {
 	u32 version;
@@ -62,12 +67,10 @@ struct vsp1_device {
 	const struct vsp1_device_info *info;
 
 	void __iomem *mmio;
-	struct clk *clock;
-
-	struct mutex lock;
-	int ref_count;
+	struct rcar_fcp_device *fcp;
 
 	struct vsp1_bru *bru;
+	struct vsp1_clu *clu;
 	struct vsp1_hsit *hsi;
 	struct vsp1_hsit *hst;
 	struct vsp1_lif *lif;
diff --git a/drivers/media/platform/vsp1/vsp1_bru.c b/drivers/media/platform/vsp1/vsp1_bru.c
index b1068c018011..8268b87727a7 100644
--- a/drivers/media/platform/vsp1/vsp1_bru.c
+++ b/drivers/media/platform/vsp1/vsp1_bru.c
@@ -249,7 +249,7 @@ static int bru_set_selection(struct v4l2_subdev *subdev,
 	return 0;
 }
 
-static struct v4l2_subdev_pad_ops bru_pad_ops = {
+static const struct v4l2_subdev_pad_ops bru_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = bru_enum_mbus_code,
 	.enum_frame_size = bru_enum_frame_size,
@@ -259,7 +259,7 @@ static struct v4l2_subdev_pad_ops bru_pad_ops = {
 	.set_selection = bru_set_selection,
 };
 
-static struct v4l2_subdev_ops bru_ops = {
+static const struct v4l2_subdev_ops bru_ops = {
 	.pad    = &bru_pad_ops,
 };
 
@@ -269,13 +269,16 @@ static struct v4l2_subdev_ops bru_ops = {
 
 static void bru_configure(struct vsp1_entity *entity,
 			  struct vsp1_pipeline *pipe,
-			  struct vsp1_dl_list *dl)
+			  struct vsp1_dl_list *dl, bool full)
 {
 	struct vsp1_bru *bru = to_bru(&entity->subdev);
 	struct v4l2_mbus_framefmt *format;
 	unsigned int flags;
 	unsigned int i;
 
+	if (!full)
+		return;
+
 	format = vsp1_entity_get_pad_format(&bru->entity, bru->entity.config,
 					    bru->entity.source_pad);
 
@@ -390,7 +393,8 @@ struct vsp1_bru *vsp1_bru_create(struct vsp1_device *vsp1)
 	bru->entity.type = VSP1_ENTITY_BRU;
 
 	ret = vsp1_entity_init(vsp1, &bru->entity, "bru",
-			       vsp1->info->num_bru_inputs + 1, &bru_ops);
+			       vsp1->info->num_bru_inputs + 1, &bru_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_COMPOSER);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
diff --git a/drivers/media/platform/vsp1/vsp1_clu.c b/drivers/media/platform/vsp1/vsp1_clu.c
new file mode 100644
index 000000000000..b63d2dbe5ea3
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_clu.c
@@ -0,0 +1,292 @@
+/*
+ * vsp1_clu.c  --  R-Car VSP1 Cubic Look-Up Table
+ *
+ * Copyright (C) 2015-2016 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+
+#include <media/v4l2-subdev.h>
+
+#include "vsp1.h"
+#include "vsp1_clu.h"
+#include "vsp1_dl.h"
+
+#define CLU_MIN_SIZE				4U
+#define CLU_MAX_SIZE				8190U
+
+/* -----------------------------------------------------------------------------
+ * Device Access
+ */
+
+static inline void vsp1_clu_write(struct vsp1_clu *clu, struct vsp1_dl_list *dl,
+				  u32 reg, u32 data)
+{
+	vsp1_dl_list_write(dl, reg, data);
+}
+
+/* -----------------------------------------------------------------------------
+ * Controls
+ */
+
+#define V4L2_CID_VSP1_CLU_TABLE			(V4L2_CID_USER_BASE | 0x1001)
+#define V4L2_CID_VSP1_CLU_MODE			(V4L2_CID_USER_BASE | 0x1002)
+#define V4L2_CID_VSP1_CLU_MODE_2D		0
+#define V4L2_CID_VSP1_CLU_MODE_3D		1
+
+static int clu_set_table(struct vsp1_clu *clu, struct v4l2_ctrl *ctrl)
+{
+	struct vsp1_dl_body *dlb;
+	unsigned int i;
+
+	dlb = vsp1_dl_fragment_alloc(clu->entity.vsp1, 1 + 17 * 17 * 17);
+	if (!dlb)
+		return -ENOMEM;
+
+	vsp1_dl_fragment_write(dlb, VI6_CLU_ADDR, 0);
+	for (i = 0; i < 17 * 17 * 17; ++i)
+		vsp1_dl_fragment_write(dlb, VI6_CLU_DATA, ctrl->p_new.p_u32[i]);
+
+	spin_lock_irq(&clu->lock);
+	swap(clu->clu, dlb);
+	spin_unlock_irq(&clu->lock);
+
+	vsp1_dl_fragment_free(dlb);
+	return 0;
+}
+
+static int clu_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vsp1_clu *clu =
+		container_of(ctrl->handler, struct vsp1_clu, ctrls);
+
+	switch (ctrl->id) {
+	case V4L2_CID_VSP1_CLU_TABLE:
+		clu_set_table(clu, ctrl);
+		break;
+
+	case V4L2_CID_VSP1_CLU_MODE:
+		clu->mode = ctrl->val;
+		break;
+	}
+
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops clu_ctrl_ops = {
+	.s_ctrl = clu_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config clu_table_control = {
+	.ops = &clu_ctrl_ops,
+	.id = V4L2_CID_VSP1_CLU_TABLE,
+	.name = "Look-Up Table",
+	.type = V4L2_CTRL_TYPE_U32,
+	.min = 0x00000000,
+	.max = 0x00ffffff,
+	.step = 1,
+	.def = 0,
+	.dims = { 17, 17, 17 },
+};
+
+static const char * const clu_mode_menu[] = {
+	"2D",
+	"3D",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config clu_mode_control = {
+	.ops = &clu_ctrl_ops,
+	.id = V4L2_CID_VSP1_CLU_MODE,
+	.name = "Mode",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.min = 0,
+	.max = 1,
+	.def = 1,
+	.qmenu = clu_mode_menu,
+};
+
+/* -----------------------------------------------------------------------------
+ * V4L2 Subdevice Pad Operations
+ */
+
+static int clu_enum_mbus_code(struct v4l2_subdev *subdev,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_mbus_code_enum *code)
+{
+	static const unsigned int codes[] = {
+		MEDIA_BUS_FMT_ARGB8888_1X32,
+		MEDIA_BUS_FMT_AHSV8888_1X32,
+		MEDIA_BUS_FMT_AYUV8_1X32,
+	};
+
+	return vsp1_subdev_enum_mbus_code(subdev, cfg, code, codes,
+					  ARRAY_SIZE(codes));
+}
+
+static int clu_enum_frame_size(struct v4l2_subdev *subdev,
+			       struct v4l2_subdev_pad_config *cfg,
+			       struct v4l2_subdev_frame_size_enum *fse)
+{
+	return vsp1_subdev_enum_frame_size(subdev, cfg, fse, CLU_MIN_SIZE,
+					   CLU_MIN_SIZE, CLU_MAX_SIZE,
+					   CLU_MAX_SIZE);
+}
+
+static int clu_set_format(struct v4l2_subdev *subdev,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *fmt)
+{
+	struct vsp1_clu *clu = to_clu(subdev);
+	struct v4l2_subdev_pad_config *config;
+	struct v4l2_mbus_framefmt *format;
+
+	config = vsp1_entity_get_pad_config(&clu->entity, cfg, fmt->which);
+	if (!config)
+		return -EINVAL;
+
+	/* Default to YUV if the requested format is not supported. */
+	if (fmt->format.code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+	    fmt->format.code != MEDIA_BUS_FMT_AHSV8888_1X32 &&
+	    fmt->format.code != MEDIA_BUS_FMT_AYUV8_1X32)
+		fmt->format.code = MEDIA_BUS_FMT_AYUV8_1X32;
+
+	format = vsp1_entity_get_pad_format(&clu->entity, config, fmt->pad);
+
+	if (fmt->pad == CLU_PAD_SOURCE) {
+		/* The CLU output format can't be modified. */
+		fmt->format = *format;
+		return 0;
+	}
+
+	format->code = fmt->format.code;
+	format->width = clamp_t(unsigned int, fmt->format.width,
+				CLU_MIN_SIZE, CLU_MAX_SIZE);
+	format->height = clamp_t(unsigned int, fmt->format.height,
+				 CLU_MIN_SIZE, CLU_MAX_SIZE);
+	format->field = V4L2_FIELD_NONE;
+	format->colorspace = V4L2_COLORSPACE_SRGB;
+
+	fmt->format = *format;
+
+	/* Propagate the format to the source pad. */
+	format = vsp1_entity_get_pad_format(&clu->entity, config,
+					    CLU_PAD_SOURCE);
+	*format = fmt->format;
+
+	return 0;
+}
+
+/* -----------------------------------------------------------------------------
+ * V4L2 Subdevice Operations
+ */
+
+static const struct v4l2_subdev_pad_ops clu_pad_ops = {
+	.init_cfg = vsp1_entity_init_cfg,
+	.enum_mbus_code = clu_enum_mbus_code,
+	.enum_frame_size = clu_enum_frame_size,
+	.get_fmt = vsp1_subdev_get_pad_format,
+	.set_fmt = clu_set_format,
+};
+
+static const struct v4l2_subdev_ops clu_ops = {
+	.pad    = &clu_pad_ops,
+};
+
+/* -----------------------------------------------------------------------------
+ * VSP1 Entity Operations
+ */
+
+static void clu_configure(struct vsp1_entity *entity,
+			  struct vsp1_pipeline *pipe,
+			  struct vsp1_dl_list *dl, bool full)
+{
+	struct vsp1_clu *clu = to_clu(&entity->subdev);
+	struct vsp1_dl_body *dlb;
+	unsigned long flags;
+	u32 ctrl = VI6_CLU_CTRL_AAI | VI6_CLU_CTRL_MVS | VI6_CLU_CTRL_EN;
+
+	/* The format can't be changed during streaming, only verify it at
+	 * stream start and store the information internally for future partial
+	 * reconfiguration calls.
+	 */
+	if (full) {
+		struct v4l2_mbus_framefmt *format;
+
+		format = vsp1_entity_get_pad_format(&clu->entity,
+						    clu->entity.config,
+						    CLU_PAD_SINK);
+		clu->yuv_mode = format->code == MEDIA_BUS_FMT_AYUV8_1X32;
+		return;
+	}
+
+	/* 2D mode can only be used with the YCbCr pixel encoding. */
+	if (clu->mode == V4L2_CID_VSP1_CLU_MODE_2D && clu->yuv_mode)
+		ctrl |= VI6_CLU_CTRL_AX1I_2D | VI6_CLU_CTRL_AX2I_2D
+		     |  VI6_CLU_CTRL_OS0_2D | VI6_CLU_CTRL_OS1_2D
+		     |  VI6_CLU_CTRL_OS2_2D | VI6_CLU_CTRL_M2D;
+
+	vsp1_clu_write(clu, dl, VI6_CLU_CTRL, ctrl);
+
+	spin_lock_irqsave(&clu->lock, flags);
+	dlb = clu->clu;
+	clu->clu = NULL;
+	spin_unlock_irqrestore(&clu->lock, flags);
+
+	if (dlb)
+		vsp1_dl_list_add_fragment(dl, dlb);
+}
+
+static const struct vsp1_entity_operations clu_entity_ops = {
+	.configure = clu_configure,
+};
+
+/* -----------------------------------------------------------------------------
+ * Initialization and Cleanup
+ */
+
+struct vsp1_clu *vsp1_clu_create(struct vsp1_device *vsp1)
+{
+	struct vsp1_clu *clu;
+	int ret;
+
+	clu = devm_kzalloc(vsp1->dev, sizeof(*clu), GFP_KERNEL);
+	if (clu == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&clu->lock);
+
+	clu->entity.ops = &clu_entity_ops;
+	clu->entity.type = VSP1_ENTITY_CLU;
+
+	ret = vsp1_entity_init(vsp1, &clu->entity, "clu", 2, &clu_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_LUT);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	/* Initialize the control handler. */
+	v4l2_ctrl_handler_init(&clu->ctrls, 2);
+	v4l2_ctrl_new_custom(&clu->ctrls, &clu_table_control, NULL);
+	v4l2_ctrl_new_custom(&clu->ctrls, &clu_mode_control, NULL);
+
+	clu->entity.subdev.ctrl_handler = &clu->ctrls;
+
+	if (clu->ctrls.error) {
+		dev_err(vsp1->dev, "clu: failed to initialize controls\n");
+		ret = clu->ctrls.error;
+		vsp1_entity_destroy(&clu->entity);
+		return ERR_PTR(ret);
+	}
+
+	v4l2_ctrl_handler_setup(&clu->ctrls);
+
+	return clu;
+}
diff --git a/drivers/media/platform/vsp1/vsp1_clu.h b/drivers/media/platform/vsp1/vsp1_clu.h
new file mode 100644
index 000000000000..036e0a2f1a42
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_clu.h
@@ -0,0 +1,48 @@
+/*
+ * vsp1_clu.h  --  R-Car VSP1 Cubic Look-Up Table
+ *
+ * Copyright (C) 2015 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __VSP1_CLU_H__
+#define __VSP1_CLU_H__
+
+#include <linux/spinlock.h>
+
+#include <media/media-entity.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-subdev.h>
+
+#include "vsp1_entity.h"
+
+struct vsp1_device;
+struct vsp1_dl_body;
+
+#define CLU_PAD_SINK				0
+#define CLU_PAD_SOURCE				1
+
+struct vsp1_clu {
+	struct vsp1_entity entity;
+
+	struct v4l2_ctrl_handler ctrls;
+
+	bool yuv_mode;
+	spinlock_t lock;
+	unsigned int mode;
+	struct vsp1_dl_body *clu;
+};
+
+static inline struct vsp1_clu *to_clu(struct v4l2_subdev *subdev)
+{
+	return container_of(subdev, struct vsp1_clu, entity.subdev);
+}
+
+struct vsp1_clu *vsp1_clu_create(struct vsp1_device *vsp1);
+
+#endif /* __VSP1_CLU_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index e238d9b9376b..37c3518aa2a8 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -15,6 +15,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 
 #include "vsp1.h"
 #include "vsp1_dl.h"
@@ -92,11 +93,13 @@ enum vsp1_dl_mode {
  * @index: index of the related WPF
  * @mode: display list operation mode (header or headerless)
  * @vsp1: the VSP1 device
- * @lock: protects the active, queued and pending lists
+ * @lock: protects the free, active, queued, pending and gc_fragments lists
  * @free: array of all free display lists
  * @active: list currently being processed (loaded) by hardware
  * @queued: list queued to the hardware (written to the DL registers)
  * @pending: list waiting to be queued to the hardware
+ * @gc_work: fragments garbage collector work struct
+ * @gc_fragments: array of display list fragments waiting to be freed
  */
 struct vsp1_dl_manager {
 	unsigned int index;
@@ -108,6 +111,9 @@ struct vsp1_dl_manager {
 	struct vsp1_dl_list *active;
 	struct vsp1_dl_list *queued;
 	struct vsp1_dl_list *pending;
+
+	struct work_struct gc_work;
+	struct list_head gc_fragments;
 };
 
 /* -----------------------------------------------------------------------------
@@ -262,21 +268,10 @@ static struct vsp1_dl_list *vsp1_dl_list_alloc(struct vsp1_dl_manager *dlm)
 	return dl;
 }
 
-static void vsp1_dl_list_free_fragments(struct vsp1_dl_list *dl)
-{
-	struct vsp1_dl_body *dlb, *next;
-
-	list_for_each_entry_safe(dlb, next, &dl->fragments, list) {
-		list_del(&dlb->list);
-		vsp1_dl_body_cleanup(dlb);
-		kfree(dlb);
-	}
-}
-
 static void vsp1_dl_list_free(struct vsp1_dl_list *dl)
 {
 	vsp1_dl_body_cleanup(&dl->body0);
-	vsp1_dl_list_free_fragments(dl);
+	list_splice_init(&dl->fragments, &dl->dlm->gc_fragments);
 	kfree(dl);
 }
 
@@ -311,7 +306,16 @@ static void __vsp1_dl_list_put(struct vsp1_dl_list *dl)
 	if (!dl)
 		return;
 
-	vsp1_dl_list_free_fragments(dl);
+	/* We can't free fragments here as DMA memory can only be freed in
+	 * interruptible context. Move all fragments to the display list
+	 * manager's list of fragments to be freed, they will be
+	 * garbage-collected by the work queue.
+	 */
+	if (!list_empty(&dl->fragments)) {
+		list_splice_init(&dl->fragments, &dl->dlm->gc_fragments);
+		schedule_work(&dl->dlm->gc_work);
+	}
+
 	dl->body0.num_entries = 0;
 
 	list_add_tail(&dl->list, &dl->dlm->free);
@@ -550,6 +554,40 @@ void vsp1_dlm_reset(struct vsp1_dl_manager *dlm)
 	dlm->pending = NULL;
 }
 
+/*
+ * Free all fragments awaiting to be garbage-collected.
+ *
+ * This function must be called without the display list manager lock held.
+ */
+static void vsp1_dlm_fragments_free(struct vsp1_dl_manager *dlm)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dlm->lock, flags);
+
+	while (!list_empty(&dlm->gc_fragments)) {
+		struct vsp1_dl_body *dlb;
+
+		dlb = list_first_entry(&dlm->gc_fragments, struct vsp1_dl_body,
+				       list);
+		list_del(&dlb->list);
+
+		spin_unlock_irqrestore(&dlm->lock, flags);
+		vsp1_dl_fragment_free(dlb);
+		spin_lock_irqsave(&dlm->lock, flags);
+	}
+
+	spin_unlock_irqrestore(&dlm->lock, flags);
+}
+
+static void vsp1_dlm_garbage_collect(struct work_struct *work)
+{
+	struct vsp1_dl_manager *dlm =
+		container_of(work, struct vsp1_dl_manager, gc_work);
+
+	vsp1_dlm_fragments_free(dlm);
+}
+
 struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 					unsigned int index,
 					unsigned int prealloc)
@@ -568,6 +606,8 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 
 	spin_lock_init(&dlm->lock);
 	INIT_LIST_HEAD(&dlm->free);
+	INIT_LIST_HEAD(&dlm->gc_fragments);
+	INIT_WORK(&dlm->gc_work, vsp1_dlm_garbage_collect);
 
 	for (i = 0; i < prealloc; ++i) {
 		struct vsp1_dl_list *dl;
@@ -589,8 +629,12 @@ void vsp1_dlm_destroy(struct vsp1_dl_manager *dlm)
 	if (!dlm)
 		return;
 
+	cancel_work_sync(&dlm->gc_work);
+
 	list_for_each_entry_safe(dl, next, &dlm->free, list) {
 		list_del(&dl->list);
 		vsp1_dl_list_free(dl);
 	}
+
+	vsp1_dlm_fragments_free(dlm);
 }
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index fc4bbc401e67..fe9665e57b3b 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -230,42 +230,33 @@ EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin);
  * vsp1_du_atomic_update - Setup one RPF input of the VSP pipeline
  * @dev: the VSP device
  * @rpf_index: index of the RPF to setup (0-based)
- * @pixelformat: V4L2 pixel format for the RPF memory input
- * @pitch: number of bytes per line in the image stored in memory
- * @mem: DMA addresses of the memory buffers (one per plane)
- * @src: the source crop rectangle for the RPF
- * @dst: the destination compose rectangle for the BRU input
- * @alpha: global alpha value for the input
- * @zpos: the Z-order position of the input
+ * @cfg: the RPF configuration
  *
- * Configure the VSP to perform composition of the image referenced by @mem
- * through RPF @rpf_index, using the @src crop rectangle and the @dst
+ * Configure the VSP to perform image composition through RPF @rpf_index as
+ * described by the @cfg configuration. The image to compose is referenced by
+ * @cfg.mem and composed using the @cfg.src crop rectangle and the @cfg.dst
  * composition rectangle. The Z-order is configurable with higher @zpos values
  * displayed on top.
  *
- * Image format as stored in memory is expressed as a V4L2 @pixelformat value.
- * As a special case, setting the pixel format to 0 will disable the RPF. The
- * @pitch, @mem, @src and @dst parameters are ignored in that case. Calling the
+ * If the @cfg configuration is NULL, the RPF will be disabled. Calling the
  * function on a disabled RPF is allowed.
  *
- * The memory pitch is configurable to allow for padding at end of lines, or
- * simple for images that extend beyond the crop rectangle boundaries. The
- * @pitch value is expressed in bytes and applies to all planes for multiplanar
- * formats.
+ * Image format as stored in memory is expressed as a V4L2 @cfg.pixelformat
+ * value. The memory pitch is configurable to allow for padding at end of lines,
+ * or simply for images that extend beyond the crop rectangle boundaries. The
+ * @cfg.pitch value is expressed in bytes and applies to all planes for
+ * multiplanar formats.
  *
  * The source memory buffer is referenced by the DMA address of its planes in
- * the @mem array. Up to two planes are supported. The second plane DMA address
- * is ignored for formats using a single plane.
+ * the @cfg.mem array. Up to two planes are supported. The second plane DMA
+ * address is ignored for formats using a single plane.
  *
  * This function isn't reentrant, the caller needs to serialize calls.
  *
  * Return 0 on success or a negative error code on failure.
  */
-int vsp1_du_atomic_update_ext(struct device *dev, unsigned int rpf_index,
-			      u32 pixelformat, unsigned int pitch,
-			      dma_addr_t mem[2], const struct v4l2_rect *src,
-			      const struct v4l2_rect *dst, unsigned int alpha,
-			      unsigned int zpos)
+int vsp1_du_atomic_update(struct device *dev, unsigned int rpf_index,
+			  const struct vsp1_du_atomic_config *cfg)
 {
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 	const struct vsp1_format_info *fmtinfo;
@@ -276,7 +267,7 @@ int vsp1_du_atomic_update_ext(struct device *dev, unsigned int rpf_index,
 
 	rpf = vsp1->rpf[rpf_index];
 
-	if (pixelformat == 0) {
+	if (!cfg) {
 		dev_dbg(vsp1->dev, "%s: RPF%u: disable requested\n", __func__,
 			rpf_index);
 
@@ -287,38 +278,39 @@ int vsp1_du_atomic_update_ext(struct device *dev, unsigned int rpf_index,
 	dev_dbg(vsp1->dev,
 		"%s: RPF%u: (%u,%u)/%ux%u -> (%u,%u)/%ux%u (%08x), pitch %u dma { %pad, %pad } zpos %u\n",
 		__func__, rpf_index,
-		src->left, src->top, src->width, src->height,
-		dst->left, dst->top, dst->width, dst->height,
-		pixelformat, pitch, &mem[0], &mem[1], zpos);
+		cfg->src.left, cfg->src.top, cfg->src.width, cfg->src.height,
+		cfg->dst.left, cfg->dst.top, cfg->dst.width, cfg->dst.height,
+		cfg->pixelformat, cfg->pitch, &cfg->mem[0], &cfg->mem[1],
+		cfg->zpos);
 
 	/* Store the format, stride, memory buffer address, crop and compose
 	 * rectangles and Z-order position and for the input.
 	 */
-	fmtinfo = vsp1_get_format_info(pixelformat);
+	fmtinfo = vsp1_get_format_info(cfg->pixelformat);
 	if (!fmtinfo) {
 		dev_dbg(vsp1->dev, "Unsupport pixel format %08x for RPF\n",
-			pixelformat);
+			cfg->pixelformat);
 		return -EINVAL;
 	}
 
 	rpf->fmtinfo = fmtinfo;
 	rpf->format.num_planes = fmtinfo->planes;
-	rpf->format.plane_fmt[0].bytesperline = pitch;
-	rpf->format.plane_fmt[1].bytesperline = pitch;
-	rpf->alpha = alpha;
+	rpf->format.plane_fmt[0].bytesperline = cfg->pitch;
+	rpf->format.plane_fmt[1].bytesperline = cfg->pitch;
+	rpf->alpha = cfg->alpha;
 
-	rpf->mem.addr[0] = mem[0];
-	rpf->mem.addr[1] = mem[1];
+	rpf->mem.addr[0] = cfg->mem[0];
+	rpf->mem.addr[1] = cfg->mem[1];
 	rpf->mem.addr[2] = 0;
 
-	vsp1->drm->inputs[rpf_index].crop = *src;
-	vsp1->drm->inputs[rpf_index].compose = *dst;
-	vsp1->drm->inputs[rpf_index].zpos = zpos;
+	vsp1->drm->inputs[rpf_index].crop = cfg->src;
+	vsp1->drm->inputs[rpf_index].compose = cfg->dst;
+	vsp1->drm->inputs[rpf_index].zpos = cfg->zpos;
 	vsp1->drm->inputs[rpf_index].enabled = true;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(vsp1_du_atomic_update_ext);
+EXPORT_SYMBOL_GPL(vsp1_du_atomic_update);
 
 static int vsp1_du_setup_rpf_pipe(struct vsp1_device *vsp1,
 				  struct vsp1_rwpf *rpf, unsigned int bru_input)
@@ -499,8 +491,10 @@ void vsp1_du_atomic_flush(struct device *dev)
 
 		vsp1_entity_route_setup(entity, pipe->dl);
 
-		if (entity->ops->configure)
-			entity->ops->configure(entity, pipe, pipe->dl);
+		if (entity->ops->configure) {
+			entity->ops->configure(entity, pipe, pipe->dl, true);
+			entity->ops->configure(entity, pipe, pipe->dl, false);
+		}
 
 		/* The memory buffer address must be applied after configuring
 		 * the RPF to make sure the crop offset are computed.
diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c
index e2d779fac0eb..cc316d281687 100644
--- a/drivers/media/platform/vsp1/vsp1_drv.c
+++ b/drivers/media/platform/vsp1/vsp1_drv.c
@@ -19,12 +19,15 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/videodev2.h>
 
+#include <media/rcar-fcp.h>
 #include <media/v4l2-subdev.h>
 
 #include "vsp1.h"
 #include "vsp1_bru.h"
+#include "vsp1_clu.h"
 #include "vsp1_dl.h"
 #include "vsp1_drm.h"
 #include "vsp1_hsit.h"
@@ -145,7 +148,7 @@ static int vsp1_uapi_create_links(struct vsp1_device *vsp1)
 			return ret;
 	}
 
-	if (vsp1->info->features & VSP1_HAS_LIF) {
+	if (vsp1->lif) {
 		ret = media_create_pad_link(&vsp1->wpf[0]->entity.subdev.entity,
 					    RWPF_PAD_SOURCE,
 					    &vsp1->lif->entity.subdev.entity,
@@ -168,19 +171,15 @@ static int vsp1_uapi_create_links(struct vsp1_device *vsp1)
 
 	for (i = 0; i < vsp1->info->wpf_count; ++i) {
 		/* Connect the video device to the WPF. All connections are
-		 * immutable except for the WPF0 source link if a LIF is
-		 * present.
+		 * immutable.
 		 */
 		struct vsp1_rwpf *wpf = vsp1->wpf[i];
-		unsigned int flags = MEDIA_LNK_FL_ENABLED;
-
-		if (!(vsp1->info->features & VSP1_HAS_LIF) || i != 0)
-			flags |= MEDIA_LNK_FL_IMMUTABLE;
 
 		ret = media_create_pad_link(&wpf->entity.subdev.entity,
 					    RWPF_PAD_SOURCE,
 					    &wpf->video->video.entity, 0,
-					    flags);
+					    MEDIA_LNK_FL_IMMUTABLE |
+					    MEDIA_LNK_FL_ENABLED);
 		if (ret < 0)
 			return ret;
 	}
@@ -204,7 +203,8 @@ static void vsp1_destroy_entities(struct vsp1_device *vsp1)
 	}
 
 	v4l2_device_unregister(&vsp1->v4l2_dev);
-	media_device_unregister(&vsp1->media_dev);
+	if (vsp1->info->uapi)
+		media_device_unregister(&vsp1->media_dev);
 	media_device_cleanup(&vsp1->media_dev);
 
 	if (!vsp1->info->uapi)
@@ -252,6 +252,16 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->bru->entity.list_dev, &vsp1->entities);
 	}
 
+	if (vsp1->info->features & VSP1_HAS_CLU) {
+		vsp1->clu = vsp1_clu_create(vsp1);
+		if (IS_ERR(vsp1->clu)) {
+			ret = PTR_ERR(vsp1->clu);
+			goto done;
+		}
+
+		list_add_tail(&vsp1->clu->entity.list_dev, &vsp1->entities);
+	}
+
 	vsp1->hsi = vsp1_hsit_create(vsp1, true);
 	if (IS_ERR(vsp1->hsi)) {
 		ret = PTR_ERR(vsp1->hsi);
@@ -268,7 +278,11 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 
 	list_add_tail(&vsp1->hst->entity.list_dev, &vsp1->entities);
 
-	if (vsp1->info->features & VSP1_HAS_LIF) {
+	/* The LIF is only supported when used in conjunction with the DU, in
+	 * which case the userspace API is disabled. If the userspace API is
+	 * enabled skip the LIF, even when present.
+	 */
+	if (vsp1->info->features & VSP1_HAS_LIF && !vsp1->info->uapi) {
 		vsp1->lif = vsp1_lif_create(vsp1);
 		if (IS_ERR(vsp1->lif)) {
 			ret = PTR_ERR(vsp1->lif);
@@ -379,14 +393,15 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 	/* Register subdev nodes if the userspace API is enabled or initialize
 	 * the DRM pipeline otherwise.
 	 */
-	if (vsp1->info->uapi)
+	if (vsp1->info->uapi) {
 		ret = v4l2_device_register_subdev_nodes(&vsp1->v4l2_dev);
-	else
-		ret = vsp1_drm_init(vsp1);
-	if (ret < 0)
-		goto done;
+		if (ret < 0)
+			goto done;
 
-	ret = media_device_register(mdev);
+		ret = media_device_register(mdev);
+	} else {
+		ret = vsp1_drm_init(vsp1);
+	}
 
 done:
 	if (ret < 0)
@@ -462,35 +477,16 @@ static int vsp1_device_init(struct vsp1_device *vsp1)
 /*
  * vsp1_device_get - Acquire the VSP1 device
  *
- * Increment the VSP1 reference count and initialize the device if the first
- * reference is taken.
+ * Make sure the device is not suspended and initialize it if needed.
  *
  * Return 0 on success or a negative error code otherwise.
  */
 int vsp1_device_get(struct vsp1_device *vsp1)
 {
-	int ret = 0;
-
-	mutex_lock(&vsp1->lock);
-	if (vsp1->ref_count > 0)
-		goto done;
-
-	ret = clk_prepare_enable(vsp1->clock);
-	if (ret < 0)
-		goto done;
-
-	ret = vsp1_device_init(vsp1);
-	if (ret < 0) {
-		clk_disable_unprepare(vsp1->clock);
-		goto done;
-	}
-
-done:
-	if (!ret)
-		vsp1->ref_count++;
+	int ret;
 
-	mutex_unlock(&vsp1->lock);
-	return ret;
+	ret = pm_runtime_get_sync(vsp1->dev);
+	return ret < 0 ? ret : 0;
 }
 
 /*
@@ -501,54 +497,59 @@ done:
  */
 void vsp1_device_put(struct vsp1_device *vsp1)
 {
-	mutex_lock(&vsp1->lock);
-
-	if (--vsp1->ref_count == 0)
-		clk_disable_unprepare(vsp1->clock);
-
-	mutex_unlock(&vsp1->lock);
+	pm_runtime_put_sync(vsp1->dev);
 }
 
 /* -----------------------------------------------------------------------------
  * Power Management
  */
 
-#ifdef CONFIG_PM_SLEEP
-static int vsp1_pm_suspend(struct device *dev)
+static int __maybe_unused vsp1_pm_suspend(struct device *dev)
 {
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 
-	WARN_ON(mutex_is_locked(&vsp1->lock));
+	vsp1_pipelines_suspend(vsp1);
+	pm_runtime_force_suspend(vsp1->dev);
 
-	if (vsp1->ref_count == 0)
-		return 0;
+	return 0;
+}
 
-	vsp1_pipelines_suspend(vsp1);
+static int __maybe_unused vsp1_pm_resume(struct device *dev)
+{
+	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 
-	clk_disable_unprepare(vsp1->clock);
+	pm_runtime_force_resume(vsp1->dev);
+	vsp1_pipelines_resume(vsp1);
 
 	return 0;
 }
 
-static int vsp1_pm_resume(struct device *dev)
+static int __maybe_unused vsp1_pm_runtime_suspend(struct device *dev)
 {
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 
-	WARN_ON(mutex_is_locked(&vsp1->lock));
+	rcar_fcp_disable(vsp1->fcp);
 
-	if (vsp1->ref_count == 0)
-		return 0;
+	return 0;
+}
 
-	clk_prepare_enable(vsp1->clock);
+static int __maybe_unused vsp1_pm_runtime_resume(struct device *dev)
+{
+	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
+	int ret;
 
-	vsp1_pipelines_resume(vsp1);
+	if (vsp1->info) {
+		ret = vsp1_device_init(vsp1);
+		if (ret < 0)
+			return ret;
+	}
 
-	return 0;
+	return rcar_fcp_enable(vsp1->fcp);
 }
-#endif
 
 static const struct dev_pm_ops vsp1_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(vsp1_pm_suspend, vsp1_pm_resume)
+	SET_RUNTIME_PM_OPS(vsp1_pm_runtime_suspend, vsp1_pm_runtime_resume, NULL)
 };
 
 /* -----------------------------------------------------------------------------
@@ -559,7 +560,8 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 	{
 		.version = VI6_IP_VERSION_MODEL_VSPS_H2,
 		.gen = 2,
-		.features = VSP1_HAS_BRU | VSP1_HAS_LUT | VSP1_HAS_SRU,
+		.features = VSP1_HAS_BRU | VSP1_HAS_CLU | VSP1_HAS_LUT
+			  | VSP1_HAS_SRU | VSP1_HAS_WPF_VFLIP,
 		.rpf_count = 5,
 		.uds_count = 3,
 		.wpf_count = 4,
@@ -568,9 +570,9 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 	}, {
 		.version = VI6_IP_VERSION_MODEL_VSPR_H2,
 		.gen = 2,
-		.features = VSP1_HAS_BRU | VSP1_HAS_SRU,
+		.features = VSP1_HAS_BRU | VSP1_HAS_SRU | VSP1_HAS_WPF_VFLIP,
 		.rpf_count = 5,
-		.uds_count = 1,
+		.uds_count = 3,
 		.wpf_count = 4,
 		.num_bru_inputs = 4,
 		.uapi = true,
@@ -580,22 +582,24 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 		.features = VSP1_HAS_BRU | VSP1_HAS_LIF | VSP1_HAS_LUT,
 		.rpf_count = 4,
 		.uds_count = 1,
-		.wpf_count = 4,
+		.wpf_count = 1,
 		.num_bru_inputs = 4,
 		.uapi = true,
 	}, {
 		.version = VI6_IP_VERSION_MODEL_VSPS_M2,
 		.gen = 2,
-		.features = VSP1_HAS_BRU | VSP1_HAS_LUT | VSP1_HAS_SRU,
+		.features = VSP1_HAS_BRU | VSP1_HAS_CLU | VSP1_HAS_LUT
+			  | VSP1_HAS_SRU | VSP1_HAS_WPF_VFLIP,
 		.rpf_count = 5,
-		.uds_count = 3,
+		.uds_count = 1,
 		.wpf_count = 4,
 		.num_bru_inputs = 4,
 		.uapi = true,
 	}, {
 		.version = VI6_IP_VERSION_MODEL_VSPI_GEN3,
 		.gen = 3,
-		.features = VSP1_HAS_LUT | VSP1_HAS_SRU,
+		.features = VSP1_HAS_CLU | VSP1_HAS_LUT | VSP1_HAS_SRU
+			  | VSP1_HAS_WPF_HFLIP | VSP1_HAS_WPF_VFLIP,
 		.rpf_count = 1,
 		.uds_count = 1,
 		.wpf_count = 1,
@@ -603,7 +607,7 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 	}, {
 		.version = VI6_IP_VERSION_MODEL_VSPBD_GEN3,
 		.gen = 3,
-		.features = VSP1_HAS_BRU,
+		.features = VSP1_HAS_BRU | VSP1_HAS_WPF_VFLIP,
 		.rpf_count = 5,
 		.wpf_count = 1,
 		.num_bru_inputs = 5,
@@ -611,7 +615,8 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 	}, {
 		.version = VI6_IP_VERSION_MODEL_VSPBC_GEN3,
 		.gen = 3,
-		.features = VSP1_HAS_BRU | VSP1_HAS_LUT,
+		.features = VSP1_HAS_BRU | VSP1_HAS_CLU | VSP1_HAS_LUT
+			  | VSP1_HAS_WPF_VFLIP,
 		.rpf_count = 5,
 		.wpf_count = 1,
 		.num_bru_inputs = 5,
@@ -619,7 +624,7 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 	}, {
 		.version = VI6_IP_VERSION_MODEL_VSPD_GEN3,
 		.gen = 3,
-		.features = VSP1_HAS_BRU | VSP1_HAS_LIF,
+		.features = VSP1_HAS_BRU | VSP1_HAS_LIF | VSP1_HAS_WPF_VFLIP,
 		.rpf_count = 5,
 		.wpf_count = 2,
 		.num_bru_inputs = 5,
@@ -629,6 +634,7 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 static int vsp1_probe(struct platform_device *pdev)
 {
 	struct vsp1_device *vsp1;
+	struct device_node *fcp_node;
 	struct resource *irq;
 	struct resource *io;
 	unsigned int i;
@@ -640,22 +646,17 @@ static int vsp1_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	vsp1->dev = &pdev->dev;
-	mutex_init(&vsp1->lock);
 	INIT_LIST_HEAD(&vsp1->entities);
 	INIT_LIST_HEAD(&vsp1->videos);
 
-	/* I/O, IRQ and clock resources */
+	platform_set_drvdata(pdev, vsp1);
+
+	/* I/O and IRQ resources (clock managed by the clock PM domain) */
 	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	vsp1->mmio = devm_ioremap_resource(&pdev->dev, io);
 	if (IS_ERR(vsp1->mmio))
 		return PTR_ERR(vsp1->mmio);
 
-	vsp1->clock = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(vsp1->clock)) {
-		dev_err(&pdev->dev, "failed to get clock\n");
-		return PTR_ERR(vsp1->clock);
-	}
-
 	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!irq) {
 		dev_err(&pdev->dev, "missing IRQ\n");
@@ -669,13 +670,27 @@ static int vsp1_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* FCP (optional) */
+	fcp_node = of_parse_phandle(pdev->dev.of_node, "renesas,fcp", 0);
+	if (fcp_node) {
+		vsp1->fcp = rcar_fcp_get(fcp_node);
+		of_node_put(fcp_node);
+		if (IS_ERR(vsp1->fcp)) {
+			dev_dbg(&pdev->dev, "FCP not found (%ld)\n",
+				PTR_ERR(vsp1->fcp));
+			return PTR_ERR(vsp1->fcp);
+		}
+	}
+
 	/* Configure device parameters based on the version register. */
-	ret = clk_prepare_enable(vsp1->clock);
+	pm_runtime_enable(&pdev->dev);
+
+	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0)
-		return ret;
+		goto done;
 
 	version = vsp1_read(vsp1, VI6_IP_VERSION);
-	clk_disable_unprepare(vsp1->clock);
+	pm_runtime_put_sync(&pdev->dev);
 
 	for (i = 0; i < ARRAY_SIZE(vsp1_device_infos); ++i) {
 		if ((version & VI6_IP_VERSION_MODEL_MASK) ==
@@ -687,7 +702,8 @@ static int vsp1_probe(struct platform_device *pdev)
 
 	if (!vsp1->info) {
 		dev_err(&pdev->dev, "unsupported IP version 0x%08x\n", version);
-		return -ENXIO;
+		ret = -ENXIO;
+		goto done;
 	}
 
 	dev_dbg(&pdev->dev, "IP version 0x%08x\n", version);
@@ -696,12 +712,14 @@ static int vsp1_probe(struct platform_device *pdev)
 	ret = vsp1_create_entities(vsp1);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to create entities\n");
-		return ret;
+		goto done;
 	}
 
-	platform_set_drvdata(pdev, vsp1);
+done:
+	if (ret)
+		pm_runtime_disable(&pdev->dev);
 
-	return 0;
+	return ret;
 }
 
 static int vsp1_remove(struct platform_device *pdev)
@@ -709,6 +727,9 @@ static int vsp1_remove(struct platform_device *pdev)
 	struct vsp1_device *vsp1 = platform_get_drvdata(pdev);
 
 	vsp1_destroy_entities(vsp1);
+	rcar_fcp_put(vsp1->fcp);
+
+	pm_runtime_disable(&pdev->dev);
 
 	return 0;
 }
diff --git a/drivers/media/platform/vsp1/vsp1_entity.c b/drivers/media/platform/vsp1/vsp1_entity.c
index 3d070bcc6053..4cf6cc719c00 100644
--- a/drivers/media/platform/vsp1/vsp1_entity.c
+++ b/drivers/media/platform/vsp1/vsp1_entity.c
@@ -22,6 +22,12 @@
 #include "vsp1_dl.h"
 #include "vsp1_entity.h"
 
+static inline struct vsp1_entity *
+media_entity_to_vsp1_entity(struct media_entity *entity)
+{
+	return container_of(entity, struct vsp1_entity, subdev.entity);
+}
+
 void vsp1_entity_route_setup(struct vsp1_entity *source,
 			     struct vsp1_dl_list *dl)
 {
@@ -30,7 +36,7 @@ void vsp1_entity_route_setup(struct vsp1_entity *source,
 	if (source->route->reg == 0)
 		return;
 
-	sink = container_of(source->sink, struct vsp1_entity, subdev.entity);
+	sink = media_entity_to_vsp1_entity(source->sink);
 	vsp1_dl_list_write(dl, source->route->reg,
 			   sink->route->inputs[source->sink_pad]);
 }
@@ -81,12 +87,30 @@ vsp1_entity_get_pad_format(struct vsp1_entity *entity,
 	return v4l2_subdev_get_try_format(&entity->subdev, cfg, pad);
 }
 
+/**
+ * vsp1_entity_get_pad_selection - Get a pad selection from storage for entity
+ * @entity: the entity
+ * @cfg: the configuration storage
+ * @pad: the pad number
+ * @target: the selection target
+ *
+ * Return the selection rectangle stored in the given configuration for an
+ * entity's pad. The configuration can be an ACTIVE or TRY configuration. The
+ * selection target can be COMPOSE or CROP.
+ */
 struct v4l2_rect *
-vsp1_entity_get_pad_compose(struct vsp1_entity *entity,
-			    struct v4l2_subdev_pad_config *cfg,
-			    unsigned int pad)
+vsp1_entity_get_pad_selection(struct vsp1_entity *entity,
+			      struct v4l2_subdev_pad_config *cfg,
+			      unsigned int pad, unsigned int target)
 {
-	return v4l2_subdev_get_try_compose(&entity->subdev, cfg, pad);
+	switch (target) {
+	case V4L2_SEL_TGT_COMPOSE:
+		return v4l2_subdev_get_try_compose(&entity->subdev, cfg, pad);
+	case V4L2_SEL_TGT_CROP:
+		return v4l2_subdev_get_try_crop(&entity->subdev, cfg, pad);
+	default:
+		return NULL;
+	}
 }
 
 /*
@@ -252,7 +276,7 @@ int vsp1_entity_link_setup(struct media_entity *entity,
 	if (!(local->flags & MEDIA_PAD_FL_SOURCE))
 		return 0;
 
-	source = container_of(local->entity, struct vsp1_entity, subdev.entity);
+	source = media_entity_to_vsp1_entity(local->entity);
 
 	if (!source->route)
 		return 0;
@@ -274,33 +298,50 @@ int vsp1_entity_link_setup(struct media_entity *entity,
  * Initialization
  */
 
+#define VSP1_ENTITY_ROUTE(ent)						\
+	{ VSP1_ENTITY_##ent, 0, VI6_DPR_##ent##_ROUTE,			\
+	  { VI6_DPR_NODE_##ent }, VI6_DPR_NODE_##ent }
+
+#define VSP1_ENTITY_ROUTE_RPF(idx)					\
+	{ VSP1_ENTITY_RPF, idx, VI6_DPR_RPF_ROUTE(idx),			\
+	  { 0, }, VI6_DPR_NODE_RPF(idx) }
+
+#define VSP1_ENTITY_ROUTE_UDS(idx)					\
+	{ VSP1_ENTITY_UDS, idx, VI6_DPR_UDS_ROUTE(idx),			\
+	  { VI6_DPR_NODE_UDS(idx) }, VI6_DPR_NODE_UDS(idx) }
+
+#define VSP1_ENTITY_ROUTE_WPF(idx)					\
+	{ VSP1_ENTITY_WPF, idx, 0,					\
+	  { VI6_DPR_NODE_WPF(idx) }, VI6_DPR_NODE_WPF(idx) }
+
 static const struct vsp1_route vsp1_routes[] = {
 	{ VSP1_ENTITY_BRU, 0, VI6_DPR_BRU_ROUTE,
 	  { VI6_DPR_NODE_BRU_IN(0), VI6_DPR_NODE_BRU_IN(1),
 	    VI6_DPR_NODE_BRU_IN(2), VI6_DPR_NODE_BRU_IN(3),
-	    VI6_DPR_NODE_BRU_IN(4) } },
-	{ VSP1_ENTITY_HSI, 0, VI6_DPR_HSI_ROUTE, { VI6_DPR_NODE_HSI, } },
-	{ VSP1_ENTITY_HST, 0, VI6_DPR_HST_ROUTE, { VI6_DPR_NODE_HST, } },
-	{ VSP1_ENTITY_LIF, 0, 0, { VI6_DPR_NODE_LIF, } },
-	{ VSP1_ENTITY_LUT, 0, VI6_DPR_LUT_ROUTE, { VI6_DPR_NODE_LUT, } },
-	{ VSP1_ENTITY_RPF, 0, VI6_DPR_RPF_ROUTE(0), { 0, } },
-	{ VSP1_ENTITY_RPF, 1, VI6_DPR_RPF_ROUTE(1), { 0, } },
-	{ VSP1_ENTITY_RPF, 2, VI6_DPR_RPF_ROUTE(2), { 0, } },
-	{ VSP1_ENTITY_RPF, 3, VI6_DPR_RPF_ROUTE(3), { 0, } },
-	{ VSP1_ENTITY_RPF, 4, VI6_DPR_RPF_ROUTE(4), { 0, } },
-	{ VSP1_ENTITY_SRU, 0, VI6_DPR_SRU_ROUTE, { VI6_DPR_NODE_SRU, } },
-	{ VSP1_ENTITY_UDS, 0, VI6_DPR_UDS_ROUTE(0), { VI6_DPR_NODE_UDS(0), } },
-	{ VSP1_ENTITY_UDS, 1, VI6_DPR_UDS_ROUTE(1), { VI6_DPR_NODE_UDS(1), } },
-	{ VSP1_ENTITY_UDS, 2, VI6_DPR_UDS_ROUTE(2), { VI6_DPR_NODE_UDS(2), } },
-	{ VSP1_ENTITY_WPF, 0, 0, { VI6_DPR_NODE_WPF(0), } },
-	{ VSP1_ENTITY_WPF, 1, 0, { VI6_DPR_NODE_WPF(1), } },
-	{ VSP1_ENTITY_WPF, 2, 0, { VI6_DPR_NODE_WPF(2), } },
-	{ VSP1_ENTITY_WPF, 3, 0, { VI6_DPR_NODE_WPF(3), } },
+	    VI6_DPR_NODE_BRU_IN(4) }, VI6_DPR_NODE_BRU_OUT },
+	VSP1_ENTITY_ROUTE(CLU),
+	VSP1_ENTITY_ROUTE(HSI),
+	VSP1_ENTITY_ROUTE(HST),
+	{ VSP1_ENTITY_LIF, 0, 0, { VI6_DPR_NODE_LIF, }, VI6_DPR_NODE_LIF },
+	VSP1_ENTITY_ROUTE(LUT),
+	VSP1_ENTITY_ROUTE_RPF(0),
+	VSP1_ENTITY_ROUTE_RPF(1),
+	VSP1_ENTITY_ROUTE_RPF(2),
+	VSP1_ENTITY_ROUTE_RPF(3),
+	VSP1_ENTITY_ROUTE_RPF(4),
+	VSP1_ENTITY_ROUTE(SRU),
+	VSP1_ENTITY_ROUTE_UDS(0),
+	VSP1_ENTITY_ROUTE_UDS(1),
+	VSP1_ENTITY_ROUTE_UDS(2),
+	VSP1_ENTITY_ROUTE_WPF(0),
+	VSP1_ENTITY_ROUTE_WPF(1),
+	VSP1_ENTITY_ROUTE_WPF(2),
+	VSP1_ENTITY_ROUTE_WPF(3),
 };
 
 int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity,
 		     const char *name, unsigned int num_pads,
-		     const struct v4l2_subdev_ops *ops)
+		     const struct v4l2_subdev_ops *ops, u32 function)
 {
 	struct v4l2_subdev *subdev;
 	unsigned int i;
@@ -341,6 +382,7 @@ int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity,
 	subdev = &entity->subdev;
 	v4l2_subdev_init(subdev, ops);
 
+	subdev->entity.function = function;
 	subdev->entity.ops = &vsp1->media_ops;
 	subdev->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
diff --git a/drivers/media/platform/vsp1/vsp1_entity.h b/drivers/media/platform/vsp1/vsp1_entity.h
index 69eff4e17350..b43457fd2c43 100644
--- a/drivers/media/platform/vsp1/vsp1_entity.h
+++ b/drivers/media/platform/vsp1/vsp1_entity.h
@@ -24,6 +24,7 @@ struct vsp1_pipeline;
 
 enum vsp1_entity_type {
 	VSP1_ENTITY_BRU,
+	VSP1_ENTITY_CLU,
 	VSP1_ENTITY_HSI,
 	VSP1_ENTITY_HST,
 	VSP1_ENTITY_LIF,
@@ -42,17 +43,21 @@ enum vsp1_entity_type {
  * @index: Entity index this routing entry is associated with
  * @reg: Output routing configuration register
  * @inputs: Target node value for each input
+ * @output: Target node value for entity output
  *
  * Each $vsp1_route entry describes routing configuration for the entity
  * specified by the entry's @type and @index. @reg indicates the register that
  * holds output routing configuration for the entity, and the @inputs array
- * store the target node value for each input of the entity.
+ * store the target node value for each input of the entity. The @output field
+ * stores the target node value of the entity output when used as a source for
+ * histogram generation.
  */
 struct vsp1_route {
 	enum vsp1_entity_type type;
 	unsigned int index;
 	unsigned int reg;
 	unsigned int inputs[VSP1_ENTITY_MAX_INPUTS];
+	unsigned int output;
 };
 
 /**
@@ -68,7 +73,7 @@ struct vsp1_entity_operations {
 	void (*destroy)(struct vsp1_entity *);
 	void (*set_memory)(struct vsp1_entity *, struct vsp1_dl_list *dl);
 	void (*configure)(struct vsp1_entity *, struct vsp1_pipeline *,
-			  struct vsp1_dl_list *);
+			  struct vsp1_dl_list *, bool);
 };
 
 struct vsp1_entity {
@@ -100,7 +105,7 @@ static inline struct vsp1_entity *to_vsp1_entity(struct v4l2_subdev *subdev)
 
 int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity,
 		     const char *name, unsigned int num_pads,
-		     const struct v4l2_subdev_ops *ops);
+		     const struct v4l2_subdev_ops *ops, u32 function);
 void vsp1_entity_destroy(struct vsp1_entity *entity);
 
 extern const struct v4l2_subdev_internal_ops vsp1_subdev_internal_ops;
@@ -118,9 +123,9 @@ vsp1_entity_get_pad_format(struct vsp1_entity *entity,
 			   struct v4l2_subdev_pad_config *cfg,
 			   unsigned int pad);
 struct v4l2_rect *
-vsp1_entity_get_pad_compose(struct vsp1_entity *entity,
-			    struct v4l2_subdev_pad_config *cfg,
-			    unsigned int pad);
+vsp1_entity_get_pad_selection(struct vsp1_entity *entity,
+			      struct v4l2_subdev_pad_config *cfg,
+			      unsigned int pad, unsigned int target);
 int vsp1_entity_init_cfg(struct v4l2_subdev *subdev,
 			 struct v4l2_subdev_pad_config *cfg);
 
diff --git a/drivers/media/platform/vsp1/vsp1_hsit.c b/drivers/media/platform/vsp1/vsp1_hsit.c
index 68b8567b374d..6e5077beb38c 100644
--- a/drivers/media/platform/vsp1/vsp1_hsit.c
+++ b/drivers/media/platform/vsp1/vsp1_hsit.c
@@ -107,7 +107,7 @@ static int hsit_set_format(struct v4l2_subdev *subdev,
 	return 0;
 }
 
-static struct v4l2_subdev_pad_ops hsit_pad_ops = {
+static const struct v4l2_subdev_pad_ops hsit_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = hsit_enum_mbus_code,
 	.enum_frame_size = hsit_enum_frame_size,
@@ -115,7 +115,7 @@ static struct v4l2_subdev_pad_ops hsit_pad_ops = {
 	.set_fmt = hsit_set_format,
 };
 
-static struct v4l2_subdev_ops hsit_ops = {
+static const struct v4l2_subdev_ops hsit_ops = {
 	.pad    = &hsit_pad_ops,
 };
 
@@ -125,10 +125,13 @@ static struct v4l2_subdev_ops hsit_ops = {
 
 static void hsit_configure(struct vsp1_entity *entity,
 			   struct vsp1_pipeline *pipe,
-			   struct vsp1_dl_list *dl)
+			   struct vsp1_dl_list *dl, bool full)
 {
 	struct vsp1_hsit *hsit = to_hsit(&entity->subdev);
 
+	if (!full)
+		return;
+
 	if (hsit->inverse)
 		vsp1_hsit_write(hsit, dl, VI6_HSI_CTRL, VI6_HSI_CTRL_EN);
 	else
@@ -161,8 +164,9 @@ struct vsp1_hsit *vsp1_hsit_create(struct vsp1_device *vsp1, bool inverse)
 	else
 		hsit->entity.type = VSP1_ENTITY_HST;
 
-	ret = vsp1_entity_init(vsp1, &hsit->entity, inverse ? "hsi" : "hst", 2,
-			       &hsit_ops);
+	ret = vsp1_entity_init(vsp1, &hsit->entity, inverse ? "hsi" : "hst",
+			       2, &hsit_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
diff --git a/drivers/media/platform/vsp1/vsp1_lif.c b/drivers/media/platform/vsp1/vsp1_lif.c
index 0217393f22df..a720063f38c5 100644
--- a/drivers/media/platform/vsp1/vsp1_lif.c
+++ b/drivers/media/platform/vsp1/vsp1_lif.c
@@ -104,7 +104,7 @@ static int lif_set_format(struct v4l2_subdev *subdev,
 	return 0;
 }
 
-static struct v4l2_subdev_pad_ops lif_pad_ops = {
+static const struct v4l2_subdev_pad_ops lif_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = lif_enum_mbus_code,
 	.enum_frame_size = lif_enum_frame_size,
@@ -112,7 +112,7 @@ static struct v4l2_subdev_pad_ops lif_pad_ops = {
 	.set_fmt = lif_set_format,
 };
 
-static struct v4l2_subdev_ops lif_ops = {
+static const struct v4l2_subdev_ops lif_ops = {
 	.pad    = &lif_pad_ops,
 };
 
@@ -122,7 +122,7 @@ static struct v4l2_subdev_ops lif_ops = {
 
 static void lif_configure(struct vsp1_entity *entity,
 			  struct vsp1_pipeline *pipe,
-			  struct vsp1_dl_list *dl)
+			  struct vsp1_dl_list *dl, bool full)
 {
 	const struct v4l2_mbus_framefmt *format;
 	struct vsp1_lif *lif = to_lif(&entity->subdev);
@@ -130,6 +130,9 @@ static void lif_configure(struct vsp1_entity *entity,
 	unsigned int obth = 400;
 	unsigned int lbth = 200;
 
+	if (!full)
+		return;
+
 	format = vsp1_entity_get_pad_format(&lif->entity, lif->entity.config,
 					    LIF_PAD_SOURCE);
 
@@ -165,7 +168,12 @@ struct vsp1_lif *vsp1_lif_create(struct vsp1_device *vsp1)
 	lif->entity.ops = &lif_entity_ops;
 	lif->entity.type = VSP1_ENTITY_LIF;
 
-	ret = vsp1_entity_init(vsp1, &lif->entity, "lif", 2, &lif_ops);
+	/* The LIF is never exposed to userspace, but media entity registration
+	 * requires a function to be set. Use PROC_VIDEO_PIXEL_FORMATTER just to
+	 * avoid triggering a WARN_ON(), the value won't be seen anywhere.
+	 */
+	ret = vsp1_entity_init(vsp1, &lif->entity, "lif", 2, &lif_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
diff --git a/drivers/media/platform/vsp1/vsp1_lut.c b/drivers/media/platform/vsp1/vsp1_lut.c
index aa09e59f0ab8..dc31de9602ba 100644
--- a/drivers/media/platform/vsp1/vsp1_lut.c
+++ b/drivers/media/platform/vsp1/vsp1_lut.c
@@ -13,7 +13,6 @@
 
 #include <linux/device.h>
 #include <linux/gfp.h>
-#include <linux/vsp1.h>
 
 #include <media/v4l2-subdev.h>
 
@@ -35,43 +34,62 @@ static inline void vsp1_lut_write(struct vsp1_lut *lut, struct vsp1_dl_list *dl,
 }
 
 /* -----------------------------------------------------------------------------
- * V4L2 Subdevice Core Operations
+ * Controls
  */
 
-static int lut_set_table(struct vsp1_lut *lut, struct vsp1_lut_config *config)
+#define V4L2_CID_VSP1_LUT_TABLE			(V4L2_CID_USER_BASE | 0x1001)
+
+static int lut_set_table(struct vsp1_lut *lut, struct v4l2_ctrl *ctrl)
 {
 	struct vsp1_dl_body *dlb;
 	unsigned int i;
 
-	dlb = vsp1_dl_fragment_alloc(lut->entity.vsp1, ARRAY_SIZE(config->lut));
+	dlb = vsp1_dl_fragment_alloc(lut->entity.vsp1, 256);
 	if (!dlb)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(config->lut); ++i)
+	for (i = 0; i < 256; ++i)
 		vsp1_dl_fragment_write(dlb, VI6_LUT_TABLE + 4 * i,
-				       config->lut[i]);
+				       ctrl->p_new.p_u32[i]);
 
-	mutex_lock(&lut->lock);
+	spin_lock_irq(&lut->lock);
 	swap(lut->lut, dlb);
-	mutex_unlock(&lut->lock);
+	spin_unlock_irq(&lut->lock);
 
 	vsp1_dl_fragment_free(dlb);
 	return 0;
 }
 
-static long lut_ioctl(struct v4l2_subdev *subdev, unsigned int cmd, void *arg)
+static int lut_s_ctrl(struct v4l2_ctrl *ctrl)
 {
-	struct vsp1_lut *lut = to_lut(subdev);
-
-	switch (cmd) {
-	case VIDIOC_VSP1_LUT_CONFIG:
-		return lut_set_table(lut, arg);
+	struct vsp1_lut *lut =
+		container_of(ctrl->handler, struct vsp1_lut, ctrls);
 
-	default:
-		return -ENOIOCTLCMD;
+	switch (ctrl->id) {
+	case V4L2_CID_VSP1_LUT_TABLE:
+		lut_set_table(lut, ctrl);
+		break;
 	}
+
+	return 0;
 }
 
+static const struct v4l2_ctrl_ops lut_ctrl_ops = {
+	.s_ctrl = lut_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config lut_table_control = {
+	.ops = &lut_ctrl_ops,
+	.id = V4L2_CID_VSP1_LUT_TABLE,
+	.name = "Look-Up Table",
+	.type = V4L2_CTRL_TYPE_U32,
+	.min = 0x00000000,
+	.max = 0x00ffffff,
+	.step = 1,
+	.def = 0,
+	.dims = { 256},
+};
+
 /* -----------------------------------------------------------------------------
  * V4L2 Subdevice Pad Operations
  */
@@ -147,11 +165,7 @@ static int lut_set_format(struct v4l2_subdev *subdev,
  * V4L2 Subdevice Operations
  */
 
-static struct v4l2_subdev_core_ops lut_core_ops = {
-	.ioctl = lut_ioctl,
-};
-
-static struct v4l2_subdev_pad_ops lut_pad_ops = {
+static const struct v4l2_subdev_pad_ops lut_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = lut_enum_mbus_code,
 	.enum_frame_size = lut_enum_frame_size,
@@ -159,8 +173,7 @@ static struct v4l2_subdev_pad_ops lut_pad_ops = {
 	.set_fmt = lut_set_format,
 };
 
-static struct v4l2_subdev_ops lut_ops = {
-	.core	= &lut_core_ops,
+static const struct v4l2_subdev_ops lut_ops = {
 	.pad    = &lut_pad_ops,
 };
 
@@ -170,18 +183,24 @@ static struct v4l2_subdev_ops lut_ops = {
 
 static void lut_configure(struct vsp1_entity *entity,
 			  struct vsp1_pipeline *pipe,
-			  struct vsp1_dl_list *dl)
+			  struct vsp1_dl_list *dl, bool full)
 {
 	struct vsp1_lut *lut = to_lut(&entity->subdev);
+	struct vsp1_dl_body *dlb;
+	unsigned long flags;
 
-	vsp1_lut_write(lut, dl, VI6_LUT_CTRL, VI6_LUT_CTRL_EN);
-
-	mutex_lock(&lut->lock);
-	if (lut->lut) {
-		vsp1_dl_list_add_fragment(dl, lut->lut);
-		lut->lut = NULL;
+	if (full) {
+		vsp1_lut_write(lut, dl, VI6_LUT_CTRL, VI6_LUT_CTRL_EN);
+		return;
 	}
-	mutex_unlock(&lut->lock);
+
+	spin_lock_irqsave(&lut->lock, flags);
+	dlb = lut->lut;
+	lut->lut = NULL;
+	spin_unlock_irqrestore(&lut->lock, flags);
+
+	if (dlb)
+		vsp1_dl_list_add_fragment(dl, dlb);
 }
 
 static const struct vsp1_entity_operations lut_entity_ops = {
@@ -201,12 +220,30 @@ struct vsp1_lut *vsp1_lut_create(struct vsp1_device *vsp1)
 	if (lut == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	spin_lock_init(&lut->lock);
+
 	lut->entity.ops = &lut_entity_ops;
 	lut->entity.type = VSP1_ENTITY_LUT;
 
-	ret = vsp1_entity_init(vsp1, &lut->entity, "lut", 2, &lut_ops);
+	ret = vsp1_entity_init(vsp1, &lut->entity, "lut", 2, &lut_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_LUT);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
+	/* Initialize the control handler. */
+	v4l2_ctrl_handler_init(&lut->ctrls, 1);
+	v4l2_ctrl_new_custom(&lut->ctrls, &lut_table_control, NULL);
+
+	lut->entity.subdev.ctrl_handler = &lut->ctrls;
+
+	if (lut->ctrls.error) {
+		dev_err(vsp1->dev, "lut: failed to initialize controls\n");
+		ret = lut->ctrls.error;
+		vsp1_entity_destroy(&lut->entity);
+		return ERR_PTR(ret);
+	}
+
+	v4l2_ctrl_handler_setup(&lut->ctrls);
+
 	return lut;
 }
diff --git a/drivers/media/platform/vsp1/vsp1_lut.h b/drivers/media/platform/vsp1/vsp1_lut.h
index cef874f22b6a..f8c4e8f0a79d 100644
--- a/drivers/media/platform/vsp1/vsp1_lut.h
+++ b/drivers/media/platform/vsp1/vsp1_lut.h
@@ -13,9 +13,10 @@
 #ifndef __VSP1_LUT_H__
 #define __VSP1_LUT_H__
 
-#include <linux/mutex.h>
+#include <linux/spinlock.h>
 
 #include <media/media-entity.h>
+#include <media/v4l2-ctrls.h>
 #include <media/v4l2-subdev.h>
 
 #include "vsp1_entity.h"
@@ -28,7 +29,9 @@ struct vsp1_device;
 struct vsp1_lut {
 	struct vsp1_entity entity;
 
-	struct mutex lock;
+	struct v4l2_ctrl_handler ctrls;
+
+	spinlock_t lock;
 	struct vsp1_dl_body *lut;
 };
 
diff --git a/drivers/media/platform/vsp1/vsp1_pipe.c b/drivers/media/platform/vsp1/vsp1_pipe.c
index 4f3b4a1d028a..3e75fb3fcace 100644
--- a/drivers/media/platform/vsp1/vsp1_pipe.c
+++ b/drivers/media/platform/vsp1/vsp1_pipe.c
@@ -172,13 +172,17 @@ void vsp1_pipeline_reset(struct vsp1_pipeline *pipe)
 			bru->inputs[i].rpf = NULL;
 	}
 
-	for (i = 0; i < pipe->num_inputs; ++i) {
-		pipe->inputs[i]->pipe = NULL;
-		pipe->inputs[i] = NULL;
+	for (i = 0; i < ARRAY_SIZE(pipe->inputs); ++i) {
+		if (pipe->inputs[i]) {
+			pipe->inputs[i]->pipe = NULL;
+			pipe->inputs[i] = NULL;
+		}
 	}
 
-	pipe->output->pipe = NULL;
-	pipe->output = NULL;
+	if (pipe->output) {
+		pipe->output->pipe = NULL;
+		pipe->output = NULL;
+	}
 
 	INIT_LIST_HEAD(&pipe->entities);
 	pipe->state = VSP1_PIPELINE_STOPPED;
@@ -286,6 +290,8 @@ void vsp1_pipeline_frame_end(struct vsp1_pipeline *pipe)
 
 	if (pipe->frame_end)
 		pipe->frame_end(pipe);
+
+	pipe->sequence++;
 }
 
 /*
@@ -295,42 +301,20 @@ void vsp1_pipeline_frame_end(struct vsp1_pipeline *pipe)
  * to be scaled, we disable alpha scaling when the UDS input has a fixed alpha
  * value. The UDS then outputs a fixed alpha value which needs to be programmed
  * from the input RPF alpha.
- *
- * This function can only be called from a subdev s_stream handler as it
- * requires a valid display list context.
  */
 void vsp1_pipeline_propagate_alpha(struct vsp1_pipeline *pipe,
-				   struct vsp1_entity *input,
-				   struct vsp1_dl_list *dl,
-				   unsigned int alpha)
+				   struct vsp1_dl_list *dl, unsigned int alpha)
 {
-	struct vsp1_entity *entity;
-	struct media_pad *pad;
-
-	pad = media_entity_remote_pad(&input->pads[RWPF_PAD_SOURCE]);
-
-	while (pad) {
-		if (!is_media_entity_v4l2_subdev(pad->entity))
-			break;
-
-		entity = to_vsp1_entity(media_entity_to_v4l2_subdev(pad->entity));
-
-		/* The BRU background color has a fixed alpha value set to 255,
-		 * the output alpha value is thus always equal to 255.
-		 */
-		if (entity->type == VSP1_ENTITY_BRU)
-			alpha = 255;
-
-		if (entity->type == VSP1_ENTITY_UDS) {
-			struct vsp1_uds *uds = to_uds(&entity->subdev);
+	if (!pipe->uds)
+		return;
 
-			vsp1_uds_set_alpha(uds, dl, alpha);
-			break;
-		}
+	/* The BRU background color has a fixed alpha value set to 255, the
+	 * output alpha value is thus always equal to 255.
+	 */
+	if (pipe->uds_input->type == VSP1_ENTITY_BRU)
+		alpha = 255;
 
-		pad = &entity->pads[entity->source_pad];
-		pad = media_entity_remote_pad(pad);
-	}
+	vsp1_uds_set_alpha(pipe->uds, dl, alpha);
 }
 
 void vsp1_pipelines_suspend(struct vsp1_device *vsp1)
@@ -383,7 +367,7 @@ void vsp1_pipelines_resume(struct vsp1_device *vsp1)
 {
 	unsigned int i;
 
-	/* Resume pipeline all running pipelines. */
+	/* Resume all running pipelines. */
 	for (i = 0; i < vsp1->info->wpf_count; ++i) {
 		struct vsp1_rwpf *wpf = vsp1->wpf[i];
 		struct vsp1_pipeline *pipe;
diff --git a/drivers/media/platform/vsp1/vsp1_pipe.h b/drivers/media/platform/vsp1/vsp1_pipe.h
index 7b56113511dd..d20d997b1fda 100644
--- a/drivers/media/platform/vsp1/vsp1_pipe.h
+++ b/drivers/media/platform/vsp1/vsp1_pipe.h
@@ -61,12 +61,13 @@ enum vsp1_pipeline_state {
  * @pipe: the media pipeline
  * @irqlock: protects the pipeline state
  * @state: current state
- * @wq: work queue to wait for state change completion
+ * @wq: wait queue to wait for state change completion
  * @frame_end: frame end interrupt handler
  * @lock: protects the pipeline use count and stream count
  * @kref: pipeline reference count
  * @stream_count: number of streaming video nodes
  * @buffers_ready: bitmask of RPFs and WPFs with at least one buffer available
+ * @sequence: frame sequence number
  * @num_inputs: number of RPFs
  * @inputs: array of RPFs in the pipeline (indexed by RPF index)
  * @output: WPF at the output of the pipeline
@@ -90,6 +91,7 @@ struct vsp1_pipeline {
 	struct kref kref;
 	unsigned int stream_count;
 	unsigned int buffers_ready;
+	unsigned int sequence;
 
 	unsigned int num_inputs;
 	struct vsp1_rwpf *inputs[VSP1_MAX_RPF];
@@ -115,9 +117,7 @@ bool vsp1_pipeline_ready(struct vsp1_pipeline *pipe);
 void vsp1_pipeline_frame_end(struct vsp1_pipeline *pipe);
 
 void vsp1_pipeline_propagate_alpha(struct vsp1_pipeline *pipe,
-				   struct vsp1_entity *input,
-				   struct vsp1_dl_list *dl,
-				   unsigned int alpha);
+				   struct vsp1_dl_list *dl, unsigned int alpha);
 
 void vsp1_pipelines_suspend(struct vsp1_device *vsp1);
 void vsp1_pipelines_resume(struct vsp1_device *vsp1);
diff --git a/drivers/media/platform/vsp1/vsp1_regs.h b/drivers/media/platform/vsp1/vsp1_regs.h
index 927b5fb94c48..3b03007ba625 100644
--- a/drivers/media/platform/vsp1/vsp1_regs.h
+++ b/drivers/media/platform/vsp1/vsp1_regs.h
@@ -154,10 +154,10 @@
 #define VI6_RPF_ALPH_SEL_AEXT_EXT	(1 << 18)
 #define VI6_RPF_ALPH_SEL_AEXT_ONE	(2 << 18)
 #define VI6_RPF_ALPH_SEL_AEXT_MASK	(3 << 18)
-#define VI6_RPF_ALPH_SEL_ALPHA0_MASK	(0xff << 8)
-#define VI6_RPF_ALPH_SEL_ALPHA0_SHIFT	8
-#define VI6_RPF_ALPH_SEL_ALPHA1_MASK	(0xff << 0)
-#define VI6_RPF_ALPH_SEL_ALPHA1_SHIFT	0
+#define VI6_RPF_ALPH_SEL_ALPHA1_MASK	(0xff << 8)
+#define VI6_RPF_ALPH_SEL_ALPHA1_SHIFT	8
+#define VI6_RPF_ALPH_SEL_ALPHA0_MASK	(0xff << 0)
+#define VI6_RPF_ALPH_SEL_ALPHA0_SHIFT	0
 
 #define VI6_RPF_VRTCOL_SET		0x0318
 #define VI6_RPF_VRTCOL_SET_LAYA_MASK	(0xff << 24)
@@ -255,6 +255,8 @@
 #define VI6_WPF_OUTFMT_PDV_MASK		(0xff << 24)
 #define VI6_WPF_OUTFMT_PDV_SHIFT	24
 #define VI6_WPF_OUTFMT_PXA		(1 << 23)
+#define VI6_WPF_OUTFMT_ROT		(1 << 18)
+#define VI6_WPF_OUTFMT_HFLP		(1 << 17)
 #define VI6_WPF_OUTFMT_FLP		(1 << 16)
 #define VI6_WPF_OUTFMT_SPYCS		(1 << 15)
 #define VI6_WPF_OUTFMT_SPUVS		(1 << 14)
@@ -289,6 +291,11 @@
 #define VI6_WPF_RNDCTRL_CLMD_EXT	(2 << 12)
 #define VI6_WPF_RNDCTRL_CLMD_MASK	(3 << 12)
 
+#define VI6_WPF_ROT_CTRL		0x1018
+#define VI6_WPF_ROT_CTRL_LN16		(1 << 17)
+#define VI6_WPF_ROT_CTRL_LMEM_WD_MASK	(0x1fff << 0)
+#define VI6_WPF_ROT_CTRL_LMEM_WD_SHIFT	0
+
 #define VI6_WPF_DSTM_STRIDE_Y		0x101c
 #define VI6_WPF_DSTM_STRIDE_C		0x1020
 #define VI6_WPF_DSTM_ADDR_Y		0x1024
@@ -444,6 +451,15 @@
  */
 
 #define VI6_CLU_CTRL			0x2900
+#define VI6_CLU_CTRL_AAI		(1 << 28)
+#define VI6_CLU_CTRL_MVS		(1 << 24)
+#define VI6_CLU_CTRL_AX1I_2D		(3 << 14)
+#define VI6_CLU_CTRL_AX2I_2D		(1 << 12)
+#define VI6_CLU_CTRL_OS0_2D		(3 << 8)
+#define VI6_CLU_CTRL_OS1_2D		(1 << 6)
+#define VI6_CLU_CTRL_OS2_2D		(3 << 4)
+#define VI6_CLU_CTRL_M2D		(1 << 1)
+#define VI6_CLU_CTRL_EN			(1 << 0)
 
 /* -----------------------------------------------------------------------------
  * HST Control Registers
diff --git a/drivers/media/platform/vsp1/vsp1_rpf.c b/drivers/media/platform/vsp1/vsp1_rpf.c
index 49168db3f529..388838913205 100644
--- a/drivers/media/platform/vsp1/vsp1_rpf.c
+++ b/drivers/media/platform/vsp1/vsp1_rpf.c
@@ -38,7 +38,7 @@ static inline void vsp1_rpf_write(struct vsp1_rwpf *rpf,
  * V4L2 Subdevice Operations
  */
 
-static struct v4l2_subdev_ops rpf_ops = {
+static const struct v4l2_subdev_ops rpf_ops = {
 	.pad    = &vsp1_rwpf_pad_ops,
 };
 
@@ -60,7 +60,7 @@ static void rpf_set_memory(struct vsp1_entity *entity, struct vsp1_dl_list *dl)
 
 static void rpf_configure(struct vsp1_entity *entity,
 			  struct vsp1_pipeline *pipe,
-			  struct vsp1_dl_list *dl)
+			  struct vsp1_dl_list *dl, bool full)
 {
 	struct vsp1_rwpf *rpf = to_rwpf(&entity->subdev);
 	const struct vsp1_format_info *fmtinfo = rpf->fmtinfo;
@@ -73,6 +73,16 @@ static void rpf_configure(struct vsp1_entity *entity,
 	u32 pstride;
 	u32 infmt;
 
+	if (!full) {
+		vsp1_rpf_write(rpf, dl, VI6_RPF_VRTCOL_SET,
+			       rpf->alpha << VI6_RPF_VRTCOL_SET_LAYA_SHIFT);
+		vsp1_rpf_write(rpf, dl, VI6_RPF_MULT_ALPHA, rpf->mult_alpha |
+			       (rpf->alpha << VI6_RPF_MULT_ALPHA_RATIO_SHIFT));
+
+		vsp1_pipeline_propagate_alpha(pipe, dl, rpf->alpha);
+		return;
+	}
+
 	/* Source size, stride and crop offsets.
 	 *
 	 * The crop offsets correspond to the location of the crop rectangle top
@@ -130,9 +140,10 @@ static void rpf_configure(struct vsp1_entity *entity,
 	if (pipe->bru) {
 		const struct v4l2_rect *compose;
 
-		compose = vsp1_entity_get_pad_compose(pipe->bru,
-						      pipe->bru->config,
-						      rpf->bru_input);
+		compose = vsp1_entity_get_pad_selection(pipe->bru,
+							pipe->bru->config,
+							rpf->bru_input,
+							V4L2_SEL_TGT_COMPOSE);
 		left = compose->left;
 		top = compose->top;
 	}
@@ -167,9 +178,6 @@ static void rpf_configure(struct vsp1_entity *entity,
 		       (fmtinfo->alpha ? VI6_RPF_ALPH_SEL_ASEL_PACKED
 				       : VI6_RPF_ALPH_SEL_ASEL_FIXED));
 
-	vsp1_rpf_write(rpf, dl, VI6_RPF_VRTCOL_SET,
-		       rpf->alpha << VI6_RPF_VRTCOL_SET_LAYA_SHIFT);
-
 	if (entity->vsp1->info->gen == 3) {
 		u32 mult;
 
@@ -187,8 +195,7 @@ static void rpf_configure(struct vsp1_entity *entity,
 			mult = VI6_RPF_MULT_ALPHA_A_MMD_RATIO
 			     | (premultiplied ?
 				VI6_RPF_MULT_ALPHA_P_MMD_RATIO :
-				VI6_RPF_MULT_ALPHA_P_MMD_NONE)
-			     | (rpf->alpha << VI6_RPF_MULT_ALPHA_RATIO_SHIFT);
+				VI6_RPF_MULT_ALPHA_P_MMD_NONE);
 		} else {
 			/* When the input doesn't contain an alpha channel the
 			 * global alpha value is applied in the unpacking unit,
@@ -199,11 +206,9 @@ static void rpf_configure(struct vsp1_entity *entity,
 			     | VI6_RPF_MULT_ALPHA_P_MMD_NONE;
 		}
 
-		vsp1_rpf_write(rpf, dl, VI6_RPF_MULT_ALPHA, mult);
+		rpf->mult_alpha = mult;
 	}
 
-	vsp1_pipeline_propagate_alpha(pipe, &rpf->entity, dl, rpf->alpha);
-
 	vsp1_rpf_write(rpf, dl, VI6_RPF_MSK_CTRL, 0);
 	vsp1_rpf_write(rpf, dl, VI6_RPF_CKEY_CTRL, 0);
 
@@ -236,18 +241,21 @@ struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 	rpf->entity.index = index;
 
 	sprintf(name, "rpf.%u", index);
-	ret = vsp1_entity_init(vsp1, &rpf->entity, name, 2, &rpf_ops);
+	ret = vsp1_entity_init(vsp1, &rpf->entity, name, 2, &rpf_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
 	/* Initialize the control handler. */
-	ret = vsp1_rwpf_init_ctrls(rpf);
+	ret = vsp1_rwpf_init_ctrls(rpf, 0);
 	if (ret < 0) {
 		dev_err(vsp1->dev, "rpf%u: failed to initialize controls\n",
 			index);
 		goto error;
 	}
 
+	v4l2_ctrl_handler_setup(&rpf->ctrls);
+
 	return rpf;
 
 error:
diff --git a/drivers/media/platform/vsp1/vsp1_rwpf.c b/drivers/media/platform/vsp1/vsp1_rwpf.c
index 3b6e032e7806..8d461b375e91 100644
--- a/drivers/media/platform/vsp1/vsp1_rwpf.c
+++ b/drivers/media/platform/vsp1/vsp1_rwpf.c
@@ -241,11 +241,9 @@ static const struct v4l2_ctrl_ops vsp1_rwpf_ctrl_ops = {
 	.s_ctrl = vsp1_rwpf_s_ctrl,
 };
 
-int vsp1_rwpf_init_ctrls(struct vsp1_rwpf *rwpf)
+int vsp1_rwpf_init_ctrls(struct vsp1_rwpf *rwpf, unsigned int ncontrols)
 {
-	rwpf->alpha = 255;
-
-	v4l2_ctrl_handler_init(&rwpf->ctrls, 1);
+	v4l2_ctrl_handler_init(&rwpf->ctrls, ncontrols + 1);
 	v4l2_ctrl_new_std(&rwpf->ctrls, &vsp1_rwpf_ctrl_ops,
 			  V4L2_CID_ALPHA_COMPONENT, 0, 255, 1, 255);
 
diff --git a/drivers/media/platform/vsp1/vsp1_rwpf.h b/drivers/media/platform/vsp1/vsp1_rwpf.h
index 9ff7c78f239e..cb20484e80da 100644
--- a/drivers/media/platform/vsp1/vsp1_rwpf.h
+++ b/drivers/media/platform/vsp1/vsp1_rwpf.h
@@ -13,6 +13,8 @@
 #ifndef __VSP1_RWPF_H__
 #define __VSP1_RWPF_H__
 
+#include <linux/spinlock.h>
+
 #include <media/media-entity.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-subdev.h>
@@ -49,6 +51,16 @@ struct vsp1_rwpf {
 
 	unsigned int alpha;
 
+	u32 mult_alpha;
+	u32 outfmt;
+
+	struct {
+		spinlock_t lock;
+		struct v4l2_ctrl *ctrls[2];
+		unsigned int pending;
+		unsigned int active;
+	} flip;
+
 	unsigned int offsets[2];
 	struct vsp1_rwpf_memory mem;
 
@@ -68,7 +80,7 @@ static inline struct vsp1_rwpf *entity_to_rwpf(struct vsp1_entity *entity)
 struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index);
 struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index);
 
-int vsp1_rwpf_init_ctrls(struct vsp1_rwpf *rwpf);
+int vsp1_rwpf_init_ctrls(struct vsp1_rwpf *rwpf, unsigned int ncontrols);
 
 extern const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops;
 
diff --git a/drivers/media/platform/vsp1/vsp1_sru.c b/drivers/media/platform/vsp1/vsp1_sru.c
index 97ef997ae735..47f5e0cea2ce 100644
--- a/drivers/media/platform/vsp1/vsp1_sru.c
+++ b/drivers/media/platform/vsp1/vsp1_sru.c
@@ -37,7 +37,7 @@ static inline void vsp1_sru_write(struct vsp1_sru *sru, struct vsp1_dl_list *dl,
  * Controls
  */
 
-#define V4L2_CID_VSP1_SRU_INTENSITY		(V4L2_CID_USER_BASE + 1)
+#define V4L2_CID_VSP1_SRU_INTENSITY		(V4L2_CID_USER_BASE | 0x1001)
 
 struct vsp1_sru_param {
 	u32 ctrl0;
@@ -239,7 +239,7 @@ static int sru_set_format(struct v4l2_subdev *subdev,
 	return 0;
 }
 
-static struct v4l2_subdev_pad_ops sru_pad_ops = {
+static const struct v4l2_subdev_pad_ops sru_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = sru_enum_mbus_code,
 	.enum_frame_size = sru_enum_frame_size,
@@ -247,7 +247,7 @@ static struct v4l2_subdev_pad_ops sru_pad_ops = {
 	.set_fmt = sru_set_format,
 };
 
-static struct v4l2_subdev_ops sru_ops = {
+static const struct v4l2_subdev_ops sru_ops = {
 	.pad    = &sru_pad_ops,
 };
 
@@ -257,7 +257,7 @@ static struct v4l2_subdev_ops sru_ops = {
 
 static void sru_configure(struct vsp1_entity *entity,
 			  struct vsp1_pipeline *pipe,
-			  struct vsp1_dl_list *dl)
+			  struct vsp1_dl_list *dl, bool full)
 {
 	const struct vsp1_sru_param *param;
 	struct vsp1_sru *sru = to_sru(&entity->subdev);
@@ -265,6 +265,9 @@ static void sru_configure(struct vsp1_entity *entity,
 	struct v4l2_mbus_framefmt *output;
 	u32 ctrl0;
 
+	if (!full)
+		return;
+
 	input = vsp1_entity_get_pad_format(&sru->entity, sru->entity.config,
 					   SRU_PAD_SINK);
 	output = vsp1_entity_get_pad_format(&sru->entity, sru->entity.config,
@@ -308,7 +311,8 @@ struct vsp1_sru *vsp1_sru_create(struct vsp1_device *vsp1)
 	sru->entity.ops = &sru_entity_ops;
 	sru->entity.type = VSP1_ENTITY_SRU;
 
-	ret = vsp1_entity_init(vsp1, &sru->entity, "sru", 2, &sru_ops);
+	ret = vsp1_entity_init(vsp1, &sru->entity, "sru", 2, &sru_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_SCALER);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
diff --git a/drivers/media/platform/vsp1/vsp1_uds.c b/drivers/media/platform/vsp1/vsp1_uds.c
index 1875e29da184..652dcd895022 100644
--- a/drivers/media/platform/vsp1/vsp1_uds.c
+++ b/drivers/media/platform/vsp1/vsp1_uds.c
@@ -40,9 +40,11 @@ static inline void vsp1_uds_write(struct vsp1_uds *uds, struct vsp1_dl_list *dl,
  * Scaling Computation
  */
 
-void vsp1_uds_set_alpha(struct vsp1_uds *uds, struct vsp1_dl_list *dl,
+void vsp1_uds_set_alpha(struct vsp1_entity *entity, struct vsp1_dl_list *dl,
 			unsigned int alpha)
 {
+	struct vsp1_uds *uds = to_uds(&entity->subdev);
+
 	vsp1_uds_write(uds, dl, VI6_UDS_ALPVAL,
 		       alpha << VI6_UDS_ALPVAL_VAL0_SHIFT);
 }
@@ -226,7 +228,7 @@ static int uds_set_format(struct v4l2_subdev *subdev,
  * V4L2 Subdevice Operations
  */
 
-static struct v4l2_subdev_pad_ops uds_pad_ops = {
+static const struct v4l2_subdev_pad_ops uds_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = uds_enum_mbus_code,
 	.enum_frame_size = uds_enum_frame_size,
@@ -234,7 +236,7 @@ static struct v4l2_subdev_pad_ops uds_pad_ops = {
 	.set_fmt = uds_set_format,
 };
 
-static struct v4l2_subdev_ops uds_ops = {
+static const struct v4l2_subdev_ops uds_ops = {
 	.pad    = &uds_pad_ops,
 };
 
@@ -244,7 +246,7 @@ static struct v4l2_subdev_ops uds_ops = {
 
 static void uds_configure(struct vsp1_entity *entity,
 			  struct vsp1_pipeline *pipe,
-			  struct vsp1_dl_list *dl)
+			  struct vsp1_dl_list *dl, bool full)
 {
 	struct vsp1_uds *uds = to_uds(&entity->subdev);
 	const struct v4l2_mbus_framefmt *output;
@@ -253,6 +255,9 @@ static void uds_configure(struct vsp1_entity *entity,
 	unsigned int vscale;
 	bool multitap;
 
+	if (!full)
+		return;
+
 	input = vsp1_entity_get_pad_format(&uds->entity, uds->entity.config,
 					   UDS_PAD_SINK);
 	output = vsp1_entity_get_pad_format(&uds->entity, uds->entity.config,
@@ -314,7 +319,8 @@ struct vsp1_uds *vsp1_uds_create(struct vsp1_device *vsp1, unsigned int index)
 	uds->entity.index = index;
 
 	sprintf(name, "uds.%u", index);
-	ret = vsp1_entity_init(vsp1, &uds->entity, name, 2, &uds_ops);
+	ret = vsp1_entity_init(vsp1, &uds->entity, name, 2, &uds_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_SCALER);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
diff --git a/drivers/media/platform/vsp1/vsp1_uds.h b/drivers/media/platform/vsp1/vsp1_uds.h
index 5c8cbfcad4cc..7bf3cdcffc65 100644
--- a/drivers/media/platform/vsp1/vsp1_uds.h
+++ b/drivers/media/platform/vsp1/vsp1_uds.h
@@ -35,7 +35,7 @@ static inline struct vsp1_uds *to_uds(struct v4l2_subdev *subdev)
 
 struct vsp1_uds *vsp1_uds_create(struct vsp1_device *vsp1, unsigned int index);
 
-void vsp1_uds_set_alpha(struct vsp1_uds *uds, struct vsp1_dl_list *dl,
+void vsp1_uds_set_alpha(struct vsp1_entity *uds, struct vsp1_dl_list *dl,
 			unsigned int alpha);
 
 #endif /* __VSP1_UDS_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index a9aec5c0bec6..9fb4fc26a359 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -219,7 +219,7 @@ vsp1_video_complete_buffer(struct vsp1_video *video)
 
 	spin_unlock_irqrestore(&video->irqlock, flags);
 
-	done->buf.sequence = video->sequence++;
+	done->buf.sequence = pipe->sequence;
 	done->buf.vb2_buf.timestamp = ktime_get_ns();
 	for (i = 0; i < done->buf.vb2_buf.num_planes; ++i)
 		vb2_set_plane_payload(&done->buf.vb2_buf, i,
@@ -251,11 +251,17 @@ static void vsp1_video_frame_end(struct vsp1_pipeline *pipe,
 static void vsp1_video_pipeline_run(struct vsp1_pipeline *pipe)
 {
 	struct vsp1_device *vsp1 = pipe->output->entity.vsp1;
+	struct vsp1_entity *entity;
 	unsigned int i;
 
 	if (!pipe->dl)
 		pipe->dl = vsp1_dl_list_get(pipe->output->dlm);
 
+	list_for_each_entry(entity, &pipe->entities, list_pipe) {
+		if (entity->ops->configure)
+			entity->ops->configure(entity, pipe, pipe->dl, false);
+	}
+
 	for (i = 0; i < vsp1->info->rpf_count; ++i) {
 		struct vsp1_rwpf *rwpf = pipe->inputs[i];
 
@@ -519,8 +525,8 @@ static void vsp1_video_pipeline_put(struct vsp1_pipeline *pipe)
 
 static int
 vsp1_video_queue_setup(struct vb2_queue *vq,
-		     unsigned int *nbuffers, unsigned int *nplanes,
-		     unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int *nbuffers, unsigned int *nplanes,
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct vsp1_video *video = vb2_get_drv_priv(vq);
 	const struct v4l2_pix_format_mplane *format = &video->rwpf->format;
@@ -530,20 +536,16 @@ vsp1_video_queue_setup(struct vb2_queue *vq,
 		if (*nplanes != format->num_planes)
 			return -EINVAL;
 
-		for (i = 0; i < *nplanes; i++) {
+		for (i = 0; i < *nplanes; i++)
 			if (sizes[i] < format->plane_fmt[i].sizeimage)
 				return -EINVAL;
-			alloc_ctxs[i] = video->alloc_ctx;
-		}
 		return 0;
 	}
 
 	*nplanes = format->num_planes;
 
-	for (i = 0; i < format->num_planes; ++i) {
+	for (i = 0; i < format->num_planes; ++i)
 		sizes[i] = format->plane_fmt[i].sizeimage;
-		alloc_ctxs[i] = video->alloc_ctx;
-	}
 
 	return 0;
 }
@@ -632,7 +634,7 @@ static int vsp1_video_setup_pipeline(struct vsp1_pipeline *pipe)
 		vsp1_entity_route_setup(entity, pipe->dl);
 
 		if (entity->ops->configure)
-			entity->ops->configure(entity, pipe, pipe->dl);
+			entity->ops->configure(entity, pipe, pipe->dl, true);
 	}
 
 	return 0;
@@ -674,7 +676,7 @@ static void vsp1_video_stop_streaming(struct vb2_queue *vq)
 	int ret;
 
 	mutex_lock(&pipe->lock);
-	if (--pipe->stream_count == 0) {
+	if (--pipe->stream_count == pipe->num_inputs) {
 		/* Stop the pipeline. */
 		ret = vsp1_pipeline_stop(pipe);
 		if (ret == -ETIMEDOUT)
@@ -696,7 +698,7 @@ static void vsp1_video_stop_streaming(struct vb2_queue *vq)
 	spin_unlock_irqrestore(&video->irqlock, flags);
 }
 
-static struct vb2_ops vsp1_video_queue_qops = {
+static const struct vb2_ops vsp1_video_queue_qops = {
 	.queue_setup = vsp1_video_queue_setup,
 	.buf_prepare = vsp1_video_buffer_prepare,
 	.buf_queue = vsp1_video_buffer_queue,
@@ -805,8 +807,6 @@ vsp1_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	if (video->queue.owner && video->queue.owner != file->private_data)
 		return -EBUSY;
 
-	video->sequence = 0;
-
 	/* Get a pipeline for the video node and start streaming on it. No link
 	 * touching an entity in the pipeline can be activated or deactivated
 	 * once streaming is started.
@@ -915,7 +915,7 @@ static int vsp1_video_release(struct file *file)
 	return 0;
 }
 
-static struct v4l2_file_operations vsp1_video_fops = {
+static const struct v4l2_file_operations vsp1_video_fops = {
 	.owner = THIS_MODULE,
 	.unlocked_ioctl = video_ioctl2,
 	.open = vsp1_video_open,
@@ -982,13 +982,6 @@ struct vsp1_video *vsp1_video_create(struct vsp1_device *vsp1,
 
 	video_set_drvdata(&video->video, video);
 
-	/* ... and the buffers queue... */
-	video->alloc_ctx = vb2_dma_contig_init_ctx(video->vsp1->dev);
-	if (IS_ERR(video->alloc_ctx)) {
-		ret = PTR_ERR(video->alloc_ctx);
-		goto error;
-	}
-
 	video->queue.type = video->type;
 	video->queue.io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
 	video->queue.lock = &video->lock;
@@ -997,6 +990,7 @@ struct vsp1_video *vsp1_video_create(struct vsp1_device *vsp1,
 	video->queue.ops = &vsp1_video_queue_qops;
 	video->queue.mem_ops = &vb2_dma_contig_memops;
 	video->queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	video->queue.dev = video->vsp1->dev;
 	ret = vb2_queue_init(&video->queue);
 	if (ret < 0) {
 		dev_err(video->vsp1->dev, "failed to initialize vb2 queue\n");
@@ -1014,7 +1008,6 @@ struct vsp1_video *vsp1_video_create(struct vsp1_device *vsp1,
 	return video;
 
 error:
-	vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 	vsp1_video_cleanup(video);
 	return ERR_PTR(ret);
 }
@@ -1024,6 +1017,5 @@ void vsp1_video_cleanup(struct vsp1_video *video)
 	if (video_is_registered(&video->video))
 		video_unregister_device(&video->video);
 
-	vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 	media_entity_cleanup(&video->video.entity);
 }
diff --git a/drivers/media/platform/vsp1/vsp1_video.h b/drivers/media/platform/vsp1/vsp1_video.h
index 867b00807c46..50ea7f02205f 100644
--- a/drivers/media/platform/vsp1/vsp1_video.h
+++ b/drivers/media/platform/vsp1/vsp1_video.h
@@ -46,10 +46,8 @@ struct vsp1_video {
 	unsigned int pipe_index;
 
 	struct vb2_queue queue;
-	void *alloc_ctx;
 	spinlock_t irqlock;
 	struct list_head irqqueue;
-	unsigned int sequence;
 };
 
 static inline struct vsp1_video *to_vsp1_video(struct video_device *vdev)
diff --git a/drivers/media/platform/vsp1/vsp1_wpf.c b/drivers/media/platform/vsp1/vsp1_wpf.c
index 6c91eaa35e75..31983169c24a 100644
--- a/drivers/media/platform/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/vsp1/vsp1_wpf.c
@@ -37,6 +37,97 @@ static inline void vsp1_wpf_write(struct vsp1_rwpf *wpf,
 }
 
 /* -----------------------------------------------------------------------------
+ * Controls
+ */
+
+enum wpf_flip_ctrl {
+	WPF_CTRL_VFLIP = 0,
+	WPF_CTRL_HFLIP = 1,
+	WPF_CTRL_MAX,
+};
+
+static int vsp1_wpf_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vsp1_rwpf *wpf =
+		container_of(ctrl->handler, struct vsp1_rwpf, ctrls);
+	unsigned int i;
+	u32 flip = 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_HFLIP:
+	case V4L2_CID_VFLIP:
+		for (i = 0; i < WPF_CTRL_MAX; ++i) {
+			if (wpf->flip.ctrls[i])
+				flip |= wpf->flip.ctrls[i]->val ? BIT(i) : 0;
+		}
+
+		spin_lock_irq(&wpf->flip.lock);
+		wpf->flip.pending = flip;
+		spin_unlock_irq(&wpf->flip.lock);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vsp1_wpf_ctrl_ops = {
+	.s_ctrl = vsp1_wpf_s_ctrl,
+};
+
+static int wpf_init_controls(struct vsp1_rwpf *wpf)
+{
+	struct vsp1_device *vsp1 = wpf->entity.vsp1;
+	unsigned int num_flip_ctrls;
+
+	spin_lock_init(&wpf->flip.lock);
+
+	if (wpf->entity.index != 0) {
+		/* Only WPF0 supports flipping. */
+		num_flip_ctrls = 0;
+	} else if (vsp1->info->features & VSP1_HAS_WPF_HFLIP) {
+		/* When horizontal flip is supported the WPF implements two
+		 * controls (horizontal flip and vertical flip).
+		 */
+		num_flip_ctrls = 2;
+	} else if (vsp1->info->features & VSP1_HAS_WPF_VFLIP) {
+		/* When only vertical flip is supported the WPF implements a
+		 * single control (vertical flip).
+		 */
+		num_flip_ctrls = 1;
+	} else {
+		/* Otherwise flipping is not supported. */
+		num_flip_ctrls = 0;
+	}
+
+	vsp1_rwpf_init_ctrls(wpf, num_flip_ctrls);
+
+	if (num_flip_ctrls >= 1) {
+		wpf->flip.ctrls[WPF_CTRL_VFLIP] =
+			v4l2_ctrl_new_std(&wpf->ctrls, &vsp1_wpf_ctrl_ops,
+					  V4L2_CID_VFLIP, 0, 1, 1, 0);
+	}
+
+	if (num_flip_ctrls == 2) {
+		wpf->flip.ctrls[WPF_CTRL_HFLIP] =
+			v4l2_ctrl_new_std(&wpf->ctrls, &vsp1_wpf_ctrl_ops,
+					  V4L2_CID_HFLIP, 0, 1, 1, 0);
+
+		v4l2_ctrl_cluster(2, wpf->flip.ctrls);
+	}
+
+	if (wpf->ctrls.error) {
+		dev_err(vsp1->dev, "wpf%u: failed to initialize controls\n",
+			wpf->entity.index);
+		return wpf->ctrls.error;
+	}
+
+	return 0;
+}
+
+/* -----------------------------------------------------------------------------
  * V4L2 Subdevice Core Operations
  */
 
@@ -62,11 +153,11 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
  * V4L2 Subdevice Operations
  */
 
-static struct v4l2_subdev_video_ops wpf_video_ops = {
+static const struct v4l2_subdev_video_ops wpf_video_ops = {
 	.s_stream = wpf_s_stream,
 };
 
-static struct v4l2_subdev_ops wpf_ops = {
+static const struct v4l2_subdev_ops wpf_ops = {
 	.video	= &wpf_video_ops,
 	.pad    = &vsp1_rwpf_pad_ops,
 };
@@ -85,15 +176,37 @@ static void vsp1_wpf_destroy(struct vsp1_entity *entity)
 static void wpf_set_memory(struct vsp1_entity *entity, struct vsp1_dl_list *dl)
 {
 	struct vsp1_rwpf *wpf = entity_to_rwpf(entity);
+	const struct v4l2_pix_format_mplane *format = &wpf->format;
+	struct vsp1_rwpf_memory mem = wpf->mem;
+	unsigned int flip = wpf->flip.active;
+	unsigned int offset;
+
+	/* Update the memory offsets based on flipping configuration. The
+	 * destination addresses point to the locations where the VSP starts
+	 * writing to memory, which can be different corners of the image
+	 * depending on vertical flipping. Horizontal flipping is handled
+	 * through a line buffer and doesn't modify the start address.
+	 */
+	if (flip & BIT(WPF_CTRL_VFLIP)) {
+		mem.addr[0] += (format->height - 1)
+			     * format->plane_fmt[0].bytesperline;
+
+		if (format->num_planes > 1) {
+			offset = (format->height / wpf->fmtinfo->vsub - 1)
+			       * format->plane_fmt[1].bytesperline;
+			mem.addr[1] += offset;
+			mem.addr[2] += offset;
+		}
+	}
 
-	vsp1_wpf_write(wpf, dl, VI6_WPF_DSTM_ADDR_Y, wpf->mem.addr[0]);
-	vsp1_wpf_write(wpf, dl, VI6_WPF_DSTM_ADDR_C0, wpf->mem.addr[1]);
-	vsp1_wpf_write(wpf, dl, VI6_WPF_DSTM_ADDR_C1, wpf->mem.addr[2]);
+	vsp1_wpf_write(wpf, dl, VI6_WPF_DSTM_ADDR_Y, mem.addr[0]);
+	vsp1_wpf_write(wpf, dl, VI6_WPF_DSTM_ADDR_C0, mem.addr[1]);
+	vsp1_wpf_write(wpf, dl, VI6_WPF_DSTM_ADDR_C1, mem.addr[2]);
 }
 
 static void wpf_configure(struct vsp1_entity *entity,
 			  struct vsp1_pipeline *pipe,
-			  struct vsp1_dl_list *dl)
+			  struct vsp1_dl_list *dl, bool full)
 {
 	struct vsp1_rwpf *wpf = to_rwpf(&entity->subdev);
 	struct vsp1_device *vsp1 = wpf->entity.vsp1;
@@ -104,6 +217,26 @@ static void wpf_configure(struct vsp1_entity *entity,
 	u32 outfmt = 0;
 	u32 srcrpf = 0;
 
+	if (!full) {
+		const unsigned int mask = BIT(WPF_CTRL_VFLIP)
+					| BIT(WPF_CTRL_HFLIP);
+
+		spin_lock(&wpf->flip.lock);
+		wpf->flip.active = (wpf->flip.active & ~mask)
+				 | (wpf->flip.pending & mask);
+		spin_unlock(&wpf->flip.lock);
+
+		outfmt = (wpf->alpha << VI6_WPF_OUTFMT_PDV_SHIFT) | wpf->outfmt;
+
+		if (wpf->flip.active & BIT(WPF_CTRL_VFLIP))
+			outfmt |= VI6_WPF_OUTFMT_FLP;
+		if (wpf->flip.active & BIT(WPF_CTRL_HFLIP))
+			outfmt |= VI6_WPF_OUTFMT_HFLP;
+
+		vsp1_wpf_write(wpf, dl, VI6_WPF_OUTFMT, outfmt);
+		return;
+	}
+
 	/* Cropping */
 	crop = vsp1_rwpf_get_crop(wpf, wpf->entity.config);
 
@@ -143,13 +276,18 @@ static void wpf_configure(struct vsp1_entity *entity,
 				       format->plane_fmt[1].bytesperline);
 
 		vsp1_wpf_write(wpf, dl, VI6_WPF_DSWAP, fmtinfo->swap);
+
+		if (vsp1->info->features & VSP1_HAS_WPF_HFLIP &&
+		    wpf->entity.index == 0)
+			vsp1_wpf_write(wpf, dl, VI6_WPF_ROT_CTRL,
+				       VI6_WPF_ROT_CTRL_LN16 |
+				       (256 << VI6_WPF_ROT_CTRL_LMEM_WD_SHIFT));
 	}
 
 	if (sink_format->code != source_format->code)
 		outfmt |= VI6_WPF_OUTFMT_CSC;
 
-	outfmt |= wpf->alpha << VI6_WPF_OUTFMT_PDV_SHIFT;
-	vsp1_wpf_write(wpf, dl, VI6_WPF_OUTFMT, outfmt);
+	wpf->outfmt = outfmt;
 
 	vsp1_dl_list_write(dl, VI6_DPR_WPF_FPORCH(wpf->entity.index),
 			   VI6_DPR_WPF_FPORCH_FP_WPFN);
@@ -216,7 +354,8 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 	wpf->entity.index = index;
 
 	sprintf(name, "wpf.%u", index);
-	ret = vsp1_entity_init(vsp1, &wpf->entity, name, 2, &wpf_ops);
+	ret = vsp1_entity_init(vsp1, &wpf->entity, name, 2, &wpf_ops,
+			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
@@ -228,13 +367,15 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 	}
 
 	/* Initialize the control handler. */
-	ret = vsp1_rwpf_init_ctrls(wpf);
+	ret = wpf_init_controls(wpf);
 	if (ret < 0) {
 		dev_err(vsp1->dev, "wpf%u: failed to initialize controls\n",
 			index);
 		goto error;
 	}
 
+	v4l2_ctrl_handler_setup(&wpf->ctrls);
+
 	return wpf;
 
 error:
diff --git a/drivers/media/platform/xilinx/xilinx-dma.c b/drivers/media/platform/xilinx/xilinx-dma.c
index 7f6898b13cac..7ae1a134b1ff 100644
--- a/drivers/media/platform/xilinx/xilinx-dma.c
+++ b/drivers/media/platform/xilinx/xilinx-dma.c
@@ -318,11 +318,10 @@ static void xvip_dma_complete(void *param)
 static int
 xvip_dma_queue_setup(struct vb2_queue *vq,
 		     unsigned int *nbuffers, unsigned int *nplanes,
-		     unsigned int sizes[], void *alloc_ctxs[])
+		     unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct xvip_dma *dma = vb2_get_drv_priv(vq);
 
-	alloc_ctxs[0] = dma->alloc_ctx;
 	/* Make sure the image size is large enough. */
 	if (*nplanes)
 		return sizes[0] < dma->format.sizeimage ? -EINVAL : 0;
@@ -706,12 +705,6 @@ int xvip_dma_init(struct xvip_composite_device *xdev, struct xvip_dma *dma,
 	video_set_drvdata(&dma->video, dma);
 
 	/* ... and the buffers queue... */
-	dma->alloc_ctx = vb2_dma_contig_init_ctx(dma->xdev->dev);
-	if (IS_ERR(dma->alloc_ctx)) {
-		ret = PTR_ERR(dma->alloc_ctx);
-		goto error;
-	}
-
 	/* Don't enable VB2_READ and VB2_WRITE, as using the read() and write()
 	 * V4L2 APIs would be inefficient. Testing on the command line with a
 	 * 'cat /dev/video?' thus won't be possible, but given that the driver
@@ -728,6 +721,7 @@ int xvip_dma_init(struct xvip_composite_device *xdev, struct xvip_dma *dma,
 	dma->queue.mem_ops = &vb2_dma_contig_memops;
 	dma->queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC
 				   | V4L2_BUF_FLAG_TSTAMP_SRC_EOF;
+	dma->queue.dev = dma->xdev->dev;
 	ret = vb2_queue_init(&dma->queue);
 	if (ret < 0) {
 		dev_err(dma->xdev->dev, "failed to initialize VB2 queue\n");
@@ -766,9 +760,6 @@ void xvip_dma_cleanup(struct xvip_dma *dma)
 	if (dma->dma)
 		dma_release_channel(dma->dma);
 
-	if (!IS_ERR_OR_NULL(dma->alloc_ctx))
-		vb2_dma_contig_cleanup_ctx(dma->alloc_ctx);
-
 	media_entity_cleanup(&dma->video.entity);
 
 	mutex_destroy(&dma->lock);
diff --git a/drivers/media/platform/xilinx/xilinx-dma.h b/drivers/media/platform/xilinx/xilinx-dma.h
index 7a1621a2ef40..e95d136c153a 100644
--- a/drivers/media/platform/xilinx/xilinx-dma.h
+++ b/drivers/media/platform/xilinx/xilinx-dma.h
@@ -65,7 +65,6 @@ static inline struct xvip_pipeline *to_xvip_pipeline(struct media_entity *e)
  * @format: active V4L2 pixel format
  * @fmtinfo: format information corresponding to the active @format
  * @queue: vb2 buffers queue
- * @alloc_ctx: allocation context for the vb2 @queue
  * @sequence: V4L2 buffers sequence number
  * @queued_bufs: list of queued buffers
  * @queued_lock: protects the buf_queued list
@@ -88,7 +87,6 @@ struct xvip_dma {
 	const struct xvip_video_format *fmtinfo;
 
 	struct vb2_queue queue;
-	void *alloc_ctx;
 	unsigned int sequence;
 
 	struct list_head queued_bufs;
diff --git a/drivers/media/radio/radio-aztech.c b/drivers/media/radio/radio-aztech.c
index 705dd6f9162c..f445327f282d 100644
--- a/drivers/media/radio/radio-aztech.c
+++ b/drivers/media/radio/radio-aztech.c
@@ -43,7 +43,6 @@ MODULE_VERSION("1.0.0");
 static int io[AZTECH_MAX] = { [0] = CONFIG_RADIO_AZTECH_PORT,
 			      [1 ... (AZTECH_MAX - 1)] = -1 };
 static int radio_nr[AZTECH_MAX]	= { [0 ... (AZTECH_MAX - 1)] = -1 };
-static const int radio_wait_time = 1000;
 
 module_param_array(io, int, NULL, 0444);
 MODULE_PARM_DESC(io, "I/O addresses of the Aztech card (0x350 or 0x358)");
diff --git a/drivers/media/radio/radio-maxiradio.c b/drivers/media/radio/radio-maxiradio.c
index 70fd8e80198a..8253f79d5d75 100644
--- a/drivers/media/radio/radio-maxiradio.c
+++ b/drivers/media/radio/radio-maxiradio.c
@@ -183,6 +183,7 @@ static void maxiradio_remove(struct pci_dev *pdev)
 	outb(0, dev->io);
 	v4l2_device_unregister(v4l2_dev);
 	release_region(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0));
+	kfree(dev);
 }
 
 static struct pci_device_id maxiradio_pci_tbl[] = {
diff --git a/drivers/media/rc/ene_ir.c b/drivers/media/rc/ene_ir.c
index 8d77e1c4a141..d1c61cd035f6 100644
--- a/drivers/media/rc/ene_ir.c
+++ b/drivers/media/rc/ene_ir.c
@@ -904,7 +904,7 @@ static int ene_set_tx_carrier(struct rc_dev *rdev, u32 carrier)
 
 		dbg("TX: out of range %d-%d kHz carrier",
 			2000 / ENE_CIRMOD_PRD_MIN, 2000 / ENE_CIRMOD_PRD_MAX);
-		return -1;
+		return -EINVAL;
 	}
 
 	dev->tx_period = period;
diff --git a/drivers/media/rc/iguanair.c b/drivers/media/rc/iguanair.c
index ee60e17fba05..5f634545ddd8 100644
--- a/drivers/media/rc/iguanair.c
+++ b/drivers/media/rc/iguanair.c
@@ -330,7 +330,7 @@ static int iguanair_set_tx_carrier(struct rc_dev *dev, uint32_t carrier)
 
 	mutex_unlock(&ir->lock);
 
-	return carrier;
+	return 0;
 }
 
 static int iguanair_set_tx_mask(struct rc_dev *dev, uint32_t mask)
diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c
index 5effc65d2947..c3277308a70b 100644
--- a/drivers/media/rc/ir-lirc-codec.c
+++ b/drivers/media/rc/ir-lirc-codec.c
@@ -292,7 +292,10 @@ static long ir_lirc_ioctl(struct file *filep, unsigned int cmd,
 		    tmp > dev->max_timeout)
 				return -EINVAL;
 
-		dev->timeout = tmp;
+		if (dev->s_timeout)
+			ret = dev->s_timeout(dev, tmp);
+		if (!ret)
+			dev->timeout = tmp;
 		break;
 
 	case LIRC_SET_REC_TIMEOUT_REPORTS:
diff --git a/drivers/media/rc/ir-rc5-decoder.c b/drivers/media/rc/ir-rc5-decoder.c
index 6ffe776abf6b..a0fd4e6b2155 100644
--- a/drivers/media/rc/ir-rc5-decoder.c
+++ b/drivers/media/rc/ir-rc5-decoder.c
@@ -29,7 +29,7 @@
 #define RC5_BIT_START		(1 * RC5_UNIT)
 #define RC5_BIT_END		(1 * RC5_UNIT)
 #define RC5X_SPACE		(4 * RC5_UNIT)
-#define RC5_TRAILER		(10 * RC5_UNIT) /* In reality, approx 100 */
+#define RC5_TRAILER		(6 * RC5_UNIT) /* In reality, approx 100 */
 
 enum rc5_state {
 	STATE_INACTIVE,
diff --git a/drivers/media/rc/keymaps/Makefile b/drivers/media/rc/keymaps/Makefile
index fbbd3bbcd252..d7b13fae1267 100644
--- a/drivers/media/rc/keymaps/Makefile
+++ b/drivers/media/rc/keymaps/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_RC_MAP) += rc-adstech-dvb-t-pci.o \
 			rc-behold.o \
 			rc-behold-columbus.o \
 			rc-budget-ci-old.o \
+			rc-cec.o \
 			rc-cinergy-1400.o \
 			rc-cinergy.o \
 			rc-delock-61959.o \
@@ -28,6 +29,7 @@ obj-$(CONFIG_RC_MAP) += rc-adstech-dvb-t-pci.o \
 			rc-dm1105-nec.o \
 			rc-dntv-live-dvb-t.o \
 			rc-dntv-live-dvbt-pro.o \
+			rc-dtt200u.o \
 			rc-dvbsky.o \
 			rc-em-terratec.o \
 			rc-encore-enltv2.o \
diff --git a/drivers/media/rc/keymaps/rc-cec.c b/drivers/media/rc/keymaps/rc-cec.c
new file mode 100644
index 000000000000..354c8e724b8e
--- /dev/null
+++ b/drivers/media/rc/keymaps/rc-cec.c
@@ -0,0 +1,182 @@
+/* Keytable for the CEC remote control
+ *
+ * Copyright (c) 2015 by Kamil Debski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <media/rc-map.h>
+#include <linux/module.h>
+
+/*
+ * CEC Spec "High-Definition Multimedia Interface Specification" can be obtained
+ * here: http://xtreamerdev.googlecode.com/files/CEC_Specs.pdf
+ * The list of control codes is listed in Table 27: User Control Codes p. 95
+ */
+
+static struct rc_map_table cec[] = {
+	{ 0x00, KEY_OK },
+	{ 0x01, KEY_UP },
+	{ 0x02, KEY_DOWN },
+	{ 0x03, KEY_LEFT },
+	{ 0x04, KEY_RIGHT },
+	{ 0x05, KEY_RIGHT_UP },
+	{ 0x06, KEY_RIGHT_DOWN },
+	{ 0x07, KEY_LEFT_UP },
+	{ 0x08, KEY_LEFT_DOWN },
+	{ 0x09, KEY_ROOT_MENU }, /* CEC Spec: Device Root Menu - see Note 2 */
+	/*
+	 * Note 2: This is the initial display that a device shows. It is
+	 * device-dependent and can be, for example, a contents menu, setup
+	 * menu, favorite menu or other menu. The actual menu displayed
+	 * may also depend on the device's current state.
+	 */
+	{ 0x0a, KEY_SETUP },
+	{ 0x0b, KEY_MENU }, /* CEC Spec: Contents Menu */
+	{ 0x0c, KEY_FAVORITES }, /* CEC Spec: Favorite Menu */
+	{ 0x0d, KEY_EXIT },
+	/* 0x0e-0x0f: Reserved */
+	{ 0x10, KEY_MEDIA_TOP_MENU },
+	{ 0x11, KEY_CONTEXT_MENU },
+	/* 0x12-0x1c: Reserved */
+	{ 0x1d, KEY_DIGITS }, /* CEC Spec: select/toggle a Number Entry Mode */
+	{ 0x1e, KEY_NUMERIC_11 },
+	{ 0x1f, KEY_NUMERIC_12 },
+	/* 0x20-0x29: Keys 0 to 9 */
+	{ 0x20, KEY_NUMERIC_0 },
+	{ 0x21, KEY_NUMERIC_1 },
+	{ 0x22, KEY_NUMERIC_2 },
+	{ 0x23, KEY_NUMERIC_3 },
+	{ 0x24, KEY_NUMERIC_4 },
+	{ 0x25, KEY_NUMERIC_5 },
+	{ 0x26, KEY_NUMERIC_6 },
+	{ 0x27, KEY_NUMERIC_7 },
+	{ 0x28, KEY_NUMERIC_8 },
+	{ 0x29, KEY_NUMERIC_9 },
+	{ 0x2a, KEY_DOT },
+	{ 0x2b, KEY_ENTER },
+	{ 0x2c, KEY_CLEAR },
+	/* 0x2d-0x2e: Reserved */
+	{ 0x2f, KEY_NEXT_FAVORITE }, /* CEC Spec: Next Favorite */
+	{ 0x30, KEY_CHANNELUP },
+	{ 0x31, KEY_CHANNELDOWN },
+	{ 0x32, KEY_PREVIOUS }, /* CEC Spec: Previous Channel */
+	{ 0x33, KEY_SOUND }, /* CEC Spec: Sound Select */
+	{ 0x34, KEY_VIDEO }, /* 0x34: CEC Spec: Input Select */
+	{ 0x35, KEY_INFO }, /* CEC Spec: Display Information */
+	{ 0x36, KEY_HELP },
+	{ 0x37, KEY_PAGEUP },
+	{ 0x38, KEY_PAGEDOWN },
+	/* 0x39-0x3f: Reserved */
+	{ 0x40, KEY_POWER },
+	{ 0x41, KEY_VOLUMEUP },
+	{ 0x42, KEY_VOLUMEDOWN },
+	{ 0x43, KEY_MUTE },
+	{ 0x44, KEY_PLAYCD },
+	{ 0x45, KEY_STOPCD },
+	{ 0x46, KEY_PAUSECD },
+	{ 0x47, KEY_RECORD },
+	{ 0x48, KEY_REWIND },
+	{ 0x49, KEY_FASTFORWARD },
+	{ 0x4a, KEY_EJECTCD }, /* CEC Spec: Eject */
+	{ 0x4b, KEY_FORWARD },
+	{ 0x4c, KEY_BACK },
+	{ 0x4d, KEY_STOP_RECORD }, /* CEC Spec: Stop-Record */
+	{ 0x4e, KEY_PAUSE_RECORD }, /* CEC Spec: Pause-Record */
+	/* 0x4f: Reserved */
+	{ 0x50, KEY_ANGLE },
+	{ 0x51, KEY_TV2 },
+	{ 0x52, KEY_VOD }, /* CEC Spec: Video on Demand */
+	{ 0x53, KEY_EPG },
+	{ 0x54, KEY_TIME }, /* CEC Spec: Timer */
+	{ 0x55, KEY_CONFIG },
+	/*
+	 * The following codes are hard to implement at this moment, as they
+	 * carry an additional additional argument. Most likely changes to RC
+	 * framework are necessary.
+	 * For now they are interpreted by the CEC framework as non keycodes
+	 * and are passed as messages enabling user application to parse them.
+	 */
+	/* 0x56: CEC Spec: Select Broadcast Type */
+	/* 0x57: CEC Spec: Select Sound presentation */
+	{ 0x58, KEY_AUDIO_DESC }, /* CEC 2.0 and up */
+	{ 0x59, KEY_WWW }, /* CEC 2.0 and up */
+	{ 0x5a, KEY_3D_MODE }, /* CEC 2.0 and up */
+	/* 0x5b-0x5f: Reserved */
+	{ 0x60, KEY_PLAYCD }, /* CEC Spec: Play Function */
+	{ 0x6005, KEY_FASTFORWARD },
+	{ 0x6006, KEY_FASTFORWARD },
+	{ 0x6007, KEY_FASTFORWARD },
+	{ 0x6015, KEY_SLOW },
+	{ 0x6016, KEY_SLOW },
+	{ 0x6017, KEY_SLOW },
+	{ 0x6009, KEY_FASTREVERSE },
+	{ 0x600a, KEY_FASTREVERSE },
+	{ 0x600b, KEY_FASTREVERSE },
+	{ 0x6019, KEY_SLOWREVERSE },
+	{ 0x601a, KEY_SLOWREVERSE },
+	{ 0x601b, KEY_SLOWREVERSE },
+	{ 0x6020, KEY_REWIND },
+	{ 0x6024, KEY_PLAYCD },
+	{ 0x6025, KEY_PAUSECD },
+	{ 0x61, KEY_PLAYPAUSE }, /* CEC Spec: Pause-Play Function */
+	{ 0x62, KEY_RECORD }, /* Spec: Record Function */
+	{ 0x63, KEY_PAUSE_RECORD }, /* CEC Spec: Pause-Record Function */
+	{ 0x64, KEY_STOPCD }, /* CEC Spec: Stop Function */
+	{ 0x65, KEY_MUTE }, /* CEC Spec: Mute Function */
+	{ 0x66, KEY_UNMUTE }, /* CEC Spec: Restore the volume */
+	/*
+	 * The following codes are hard to implement at this moment, as they
+	 * carry an additional additional argument. Most likely changes to RC
+	 * framework are necessary.
+	 * For now they are interpreted by the CEC framework as non keycodes
+	 * and are passed as messages enabling user application to parse them.
+	 */
+	/* 0x67: CEC Spec: Tune Function */
+	/* 0x68: CEC Spec: Seleect Media Function */
+	/* 0x69: CEC Spec: Select A/V Input Function */
+	/* 0x6a: CEC Spec: Select Audio Input Function */
+	{ 0x6b, KEY_POWER }, /* CEC Spec: Power Toggle Function */
+	{ 0x6c, KEY_SLEEP }, /* CEC Spec: Power Off Function */
+	{ 0x6d, KEY_WAKEUP }, /* CEC Spec: Power On Function */
+	/* 0x6e-0x70: Reserved */
+	{ 0x71, KEY_BLUE }, /* CEC Spec: F1 (Blue) */
+	{ 0x72, KEY_RED }, /* CEC Spec: F2 (Red) */
+	{ 0x73, KEY_GREEN }, /* CEC Spec: F3 (Green) */
+	{ 0x74, KEY_YELLOW }, /* CEC Spec: F4 (Yellow) */
+	{ 0x75, KEY_F5 },
+	{ 0x76, KEY_DATA }, /* CEC Spec: Data - see Note 3 */
+	/*
+	 * Note 3: This is used, for example, to enter or leave a digital TV
+	 * data broadcast application.
+	 */
+	/* 0x77-0xff: Reserved */
+};
+
+static struct rc_map_list cec_map = {
+	.map = {
+		.scan		= cec,
+		.size		= ARRAY_SIZE(cec),
+		.rc_type	= RC_TYPE_CEC,
+		.name		= RC_MAP_CEC,
+	}
+};
+
+static int __init init_rc_map_cec(void)
+{
+	return rc_map_register(&cec_map);
+}
+
+static void __exit exit_rc_map_cec(void)
+{
+	rc_map_unregister(&cec_map);
+}
+
+module_init(init_rc_map_cec);
+module_exit(exit_rc_map_cec);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Kamil Debski");
diff --git a/drivers/media/rc/keymaps/rc-dtt200u.c b/drivers/media/rc/keymaps/rc-dtt200u.c
new file mode 100644
index 000000000000..25650e9e4664
--- /dev/null
+++ b/drivers/media/rc/keymaps/rc-dtt200u.c
@@ -0,0 +1,59 @@
+/* Keytable for Wideview WT-220U.
+ *
+ * Copyright (c) 2016 Jonathan McDowell <noodles@earth.li>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <media/rc-map.h>
+#include <linux/module.h>
+
+/* key list for the tiny remote control (Yakumo, don't know about the others) */
+static struct rc_map_table dtt200u_table[] = {
+	{ 0x8001, KEY_MUTE },
+	{ 0x8002, KEY_CHANNELDOWN },
+	{ 0x8003, KEY_VOLUMEDOWN },
+	{ 0x8004, KEY_1 },
+	{ 0x8005, KEY_2 },
+	{ 0x8006, KEY_3 },
+	{ 0x8007, KEY_4 },
+	{ 0x8008, KEY_5 },
+	{ 0x8009, KEY_6 },
+	{ 0x800a, KEY_7 },
+	{ 0x800c, KEY_ZOOM },
+	{ 0x800d, KEY_0 },
+	{ 0x800e, KEY_SELECT },
+	{ 0x8012, KEY_POWER },
+	{ 0x801a, KEY_CHANNELUP },
+	{ 0x801b, KEY_8 },
+	{ 0x801e, KEY_VOLUMEUP },
+	{ 0x801f, KEY_9 },
+};
+
+static struct rc_map_list dtt200u_map = {
+	.map = {
+		.scan    = dtt200u_table,
+		.size    = ARRAY_SIZE(dtt200u_table),
+		.rc_type = RC_TYPE_NEC,
+		.name    = RC_MAP_DTT200U,
+	}
+};
+
+static int __init init_rc_map_dtt200u(void)
+{
+	return rc_map_register(&dtt200u_map);
+}
+
+static void __exit exit_rc_map_dtt200u(void)
+{
+	rc_map_unregister(&dtt200u_map);
+}
+
+module_init(init_rc_map_dtt200u)
+module_exit(exit_rc_map_dtt200u)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jonathan McDowell <noodles@earth.li>");
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index 92ae1903c010..91f9bb87ce68 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -19,6 +19,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -80,8 +82,6 @@ static void lirc_irctl_init(struct irctl *ir)
 
 static void lirc_irctl_cleanup(struct irctl *ir)
 {
-	dev_dbg(ir->d.dev, LOGHEAD "cleaning up\n", ir->d.name, ir->d.minor);
-
 	device_destroy(lirc_class, MKDEV(MAJOR(lirc_base_dev), ir->d.minor));
 
 	if (ir->buf != ir->d.rbuf) {
@@ -97,28 +97,25 @@ static void lirc_irctl_cleanup(struct irctl *ir)
  */
 static int lirc_add_to_buf(struct irctl *ir)
 {
-	if (ir->d.add_to_buf) {
-		int res = -ENODATA;
-		int got_data = 0;
+	int res;
+	int got_data = -1;
 
-		/*
-		 * service the device as long as it is returning
-		 * data and we have space
-		 */
-get_data:
-		res = ir->d.add_to_buf(ir->d.data, ir->buf);
-		if (res == 0) {
-			got_data++;
-			goto get_data;
-		}
+	if (!ir->d.add_to_buf)
+		return 0;
 
-		if (res == -ENODEV)
-			kthread_stop(ir->task);
+	/*
+	 * service the device as long as it is returning
+	 * data and we have space
+	 */
+	do {
+		got_data++;
+		res = ir->d.add_to_buf(ir->d.data, ir->buf);
+	} while (!res);
 
-		return got_data ? 0 : res;
-	}
+	if (res == -ENODEV)
+		kthread_stop(ir->task);
 
-	return 0;
+	return got_data ? 0 : res;
 }
 
 /* main function of the polling thread
@@ -127,9 +124,6 @@ static int lirc_thread(void *irctl)
 {
 	struct irctl *ir = irctl;
 
-	dev_dbg(ir->d.dev, LOGHEAD "poll thread started\n",
-		ir->d.name, ir->d.minor);
-
 	do {
 		if (ir->open) {
 			if (ir->jiffies_to_wait) {
@@ -146,9 +140,6 @@ static int lirc_thread(void *irctl)
 		}
 	} while (!kthread_should_stop());
 
-	dev_dbg(ir->d.dev, LOGHEAD "poll thread ended\n",
-		ir->d.name, ir->d.minor);
-
 	return 0;
 }
 
@@ -203,74 +194,86 @@ err_out:
 	return retval;
 }
 
-int lirc_register_driver(struct lirc_driver *d)
+static int lirc_allocate_buffer(struct irctl *ir)
 {
-	struct irctl *ir;
-	int minor;
+	int err = 0;
 	int bytes_in_key;
 	unsigned int chunk_size;
 	unsigned int buffer_size;
+	struct lirc_driver *d = &ir->d;
+
+	mutex_lock(&lirc_dev_lock);
+
+	bytes_in_key = BITS_TO_LONGS(d->code_length) +
+						(d->code_length % 8 ? 1 : 0);
+	buffer_size = d->buffer_size ? d->buffer_size : BUFLEN / bytes_in_key;
+	chunk_size  = d->chunk_size  ? d->chunk_size  : bytes_in_key;
+
+	if (d->rbuf) {
+		ir->buf = d->rbuf;
+	} else {
+		ir->buf = kmalloc(sizeof(struct lirc_buffer), GFP_KERNEL);
+		if (!ir->buf) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = lirc_buffer_init(ir->buf, chunk_size, buffer_size);
+		if (err) {
+			kfree(ir->buf);
+			goto out;
+		}
+	}
+	ir->chunk_size = ir->buf->chunk_size;
+
+out:
+	mutex_unlock(&lirc_dev_lock);
+
+	return err;
+}
+
+static int lirc_allocate_driver(struct lirc_driver *d)
+{
+	struct irctl *ir;
+	int minor;
 	int err;
 
 	if (!d) {
-		printk(KERN_ERR "lirc_dev: lirc_register_driver: "
-		       "driver pointer must be not NULL!\n");
-		err = -EBADRQC;
-		goto out;
+		pr_err("driver pointer must be not NULL!\n");
+		return -EBADRQC;
 	}
 
 	if (!d->dev) {
-		printk(KERN_ERR "%s: dev pointer not filled in!\n", __func__);
-		err = -EINVAL;
-		goto out;
+		pr_err("dev pointer not filled in!\n");
+		return -EINVAL;
 	}
 
-	if (MAX_IRCTL_DEVICES <= d->minor) {
-		dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-			"\"minor\" must be between 0 and %d (%d)!\n",
-			MAX_IRCTL_DEVICES - 1, d->minor);
-		err = -EBADRQC;
-		goto out;
+	if (d->minor >= MAX_IRCTL_DEVICES) {
+		dev_err(d->dev, "minor must be between 0 and %d!\n",
+						MAX_IRCTL_DEVICES - 1);
+		return -EBADRQC;
 	}
 
-	if (1 > d->code_length || (BUFLEN * 8) < d->code_length) {
-		dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-			"code length in bits for minor (%d) "
-			"must be less than %d!\n",
-			d->minor, BUFLEN * 8);
-		err = -EBADRQC;
-		goto out;
+	if (d->code_length < 1 || d->code_length > (BUFLEN * 8)) {
+		dev_err(d->dev, "code length must be less than %d bits\n",
+								BUFLEN * 8);
+		return -EBADRQC;
 	}
 
-	dev_dbg(d->dev, "lirc_dev: lirc_register_driver: sample_rate: %d\n",
-		d->sample_rate);
 	if (d->sample_rate) {
 		if (2 > d->sample_rate || HZ < d->sample_rate) {
-			dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-				"sample_rate must be between 2 and %d!\n", HZ);
-			err = -EBADRQC;
-			goto out;
+			dev_err(d->dev, "invalid %d sample rate\n",
+							d->sample_rate);
+			return -EBADRQC;
 		}
 		if (!d->add_to_buf) {
-			dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-				"add_to_buf cannot be NULL when "
-				"sample_rate is set\n");
-			err = -EBADRQC;
-			goto out;
-		}
-	} else if (!(d->fops && d->fops->read) && !d->rbuf) {
-		dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-			"fops->read and rbuf cannot all be NULL!\n");
-		err = -EBADRQC;
-		goto out;
-	} else if (!d->rbuf) {
-		if (!(d->fops && d->fops->read && d->fops->poll &&
-		      d->fops->unlocked_ioctl)) {
-			dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-				"neither read, poll nor unlocked_ioctl can be NULL!\n");
-			err = -EBADRQC;
-			goto out;
+			dev_err(d->dev, "add_to_buf not set\n");
+			return -EBADRQC;
 		}
+	} else if (!d->rbuf && !(d->fops && d->fops->read &&
+				d->fops->poll && d->fops->unlocked_ioctl)) {
+		dev_err(d->dev, "undefined read, poll, ioctl\n");
+		return -EBADRQC;
 	}
 
 	mutex_lock(&lirc_dev_lock);
@@ -282,15 +285,13 @@ int lirc_register_driver(struct lirc_driver *d)
 		for (minor = 0; minor < MAX_IRCTL_DEVICES; minor++)
 			if (!irctls[minor])
 				break;
-		if (MAX_IRCTL_DEVICES == minor) {
-			dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-				"no free slots for drivers!\n");
+		if (minor == MAX_IRCTL_DEVICES) {
+			dev_err(d->dev, "no free slots for drivers!\n");
 			err = -ENOMEM;
 			goto out_lock;
 		}
 	} else if (irctls[minor]) {
-		dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-			"minor (%d) just registered!\n", minor);
+		dev_err(d->dev, "minor (%d) just registered!\n", minor);
 		err = -EBUSY;
 		goto out_lock;
 	}
@@ -304,37 +305,9 @@ int lirc_register_driver(struct lirc_driver *d)
 	irctls[minor] = ir;
 	d->minor = minor;
 
-	if (d->sample_rate) {
-		ir->jiffies_to_wait = HZ / d->sample_rate;
-	} else {
-		/* it means - wait for external event in task queue */
-		ir->jiffies_to_wait = 0;
-	}
-
 	/* some safety check 8-) */
 	d->name[sizeof(d->name)-1] = '\0';
 
-	bytes_in_key = BITS_TO_LONGS(d->code_length) +
-			(d->code_length % 8 ? 1 : 0);
-	buffer_size = d->buffer_size ? d->buffer_size : BUFLEN / bytes_in_key;
-	chunk_size  = d->chunk_size  ? d->chunk_size  : bytes_in_key;
-
-	if (d->rbuf) {
-		ir->buf = d->rbuf;
-	} else {
-		ir->buf = kmalloc(sizeof(struct lirc_buffer), GFP_KERNEL);
-		if (!ir->buf) {
-			err = -ENOMEM;
-			goto out_lock;
-		}
-		err = lirc_buffer_init(ir->buf, chunk_size, buffer_size);
-		if (err) {
-			kfree(ir->buf);
-			goto out_lock;
-		}
-	}
-	ir->chunk_size = ir->buf->chunk_size;
-
 	if (d->features == 0)
 		d->features = LIRC_CAN_REC_LIRCCODE;
 
@@ -345,15 +318,19 @@ int lirc_register_driver(struct lirc_driver *d)
 		      "lirc%u", ir->d.minor);
 
 	if (d->sample_rate) {
+		ir->jiffies_to_wait = HZ / d->sample_rate;
+
 		/* try to fire up polling thread */
 		ir->task = kthread_run(lirc_thread, (void *)ir, "lirc_dev");
 		if (IS_ERR(ir->task)) {
-			dev_err(d->dev, "lirc_dev: lirc_register_driver: "
-				"cannot run poll thread for minor = %d\n",
-				d->minor);
+			dev_err(d->dev, "cannot run thread for minor = %d\n",
+								d->minor);
 			err = -ECHILD;
 			goto out_sysfs;
 		}
+	} else {
+		/* it means - wait for external event in task queue */
+		ir->jiffies_to_wait = 0;
 	}
 
 	err = lirc_cdev_add(ir);
@@ -371,9 +348,26 @@ out_sysfs:
 	device_destroy(lirc_class, MKDEV(MAJOR(lirc_base_dev), ir->d.minor));
 out_lock:
 	mutex_unlock(&lirc_dev_lock);
-out:
+
 	return err;
 }
+
+int lirc_register_driver(struct lirc_driver *d)
+{
+	int minor, err = 0;
+
+	minor = lirc_allocate_driver(d);
+	if (minor < 0)
+		return minor;
+
+	if (LIRC_CAN_REC(d->features)) {
+		err = lirc_allocate_buffer(irctls[minor]);
+		if (err)
+			lirc_unregister_driver(minor);
+	}
+
+	return err ? err : minor;
+}
 EXPORT_SYMBOL(lirc_register_driver);
 
 int lirc_unregister_driver(int minor)
@@ -382,15 +376,14 @@ int lirc_unregister_driver(int minor)
 	struct cdev *cdev;
 
 	if (minor < 0 || minor >= MAX_IRCTL_DEVICES) {
-		printk(KERN_ERR "lirc_dev: %s: minor (%d) must be between "
-		       "0 and %d!\n", __func__, minor, MAX_IRCTL_DEVICES - 1);
+		pr_err("minor (%d) must be between 0 and %d!\n",
+					minor, MAX_IRCTL_DEVICES - 1);
 		return -EBADRQC;
 	}
 
 	ir = irctls[minor];
 	if (!ir) {
-		printk(KERN_ERR "lirc_dev: %s: failed to get irctl struct "
-		       "for minor %d!\n", __func__, minor);
+		pr_err("failed to get irctl\n");
 		return -ENOENT;
 	}
 
@@ -399,8 +392,8 @@ int lirc_unregister_driver(int minor)
 	mutex_lock(&lirc_dev_lock);
 
 	if (ir->d.minor != minor) {
-		printk(KERN_ERR "lirc_dev: %s: minor (%d) device not "
-		       "registered!\n", __func__, minor);
+		dev_err(ir->d.dev, "lirc_dev: minor %d device not registered\n",
+									minor);
 		mutex_unlock(&lirc_dev_lock);
 		return -ENOENT;
 	}
@@ -418,7 +411,10 @@ int lirc_unregister_driver(int minor)
 			ir->d.name, ir->d.minor);
 		wake_up_interruptible(&ir->buf->wait_poll);
 		mutex_lock(&ir->irctl_lock);
-		ir->d.set_use_dec(ir->d.data);
+
+		if (ir->d.set_use_dec)
+			ir->d.set_use_dec(ir->d.data);
+
 		module_put(cdev->owner);
 		mutex_unlock(&ir->irctl_lock);
 	} else {
@@ -442,8 +438,7 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
 	int retval = 0;
 
 	if (iminor(inode) >= MAX_IRCTL_DEVICES) {
-		printk(KERN_WARNING "lirc_dev [%d]: open result = -ENODEV\n",
-		       iminor(inode));
+		pr_err("open result for %d is -ENODEV\n", iminor(inode));
 		return -ENODEV;
 	}
 
@@ -477,7 +472,8 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
 	cdev = ir->cdev;
 	if (try_module_get(cdev->owner)) {
 		ir->open++;
-		retval = ir->d.set_use_inc(ir->d.data);
+		if (ir->d.set_use_inc)
+			retval = ir->d.set_use_inc(ir->d.data);
 
 		if (retval) {
 			module_put(cdev->owner);
@@ -490,10 +486,6 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
 	}
 
 error:
-	if (ir)
-		dev_dbg(ir->d.dev, LOGHEAD "open result = %d\n",
-			ir->d.name, ir->d.minor, retval);
-
 	mutex_unlock(&lirc_dev_lock);
 
 	nonseekable_open(inode, file);
@@ -509,14 +501,12 @@ int lirc_dev_fop_close(struct inode *inode, struct file *file)
 	int ret;
 
 	if (!ir) {
-		printk(KERN_ERR "%s: called with invalid irctl\n", __func__);
+		pr_err("called with invalid irctl\n");
 		return -EINVAL;
 	}
 
 	cdev = ir->cdev;
 
-	dev_dbg(ir->d.dev, LOGHEAD "close called\n", ir->d.name, ir->d.minor);
-
 	ret = mutex_lock_killable(&lirc_dev_lock);
 	WARN_ON(ret);
 
@@ -524,7 +514,8 @@ int lirc_dev_fop_close(struct inode *inode, struct file *file)
 
 	ir->open--;
 	if (ir->attached) {
-		ir->d.set_use_dec(ir->d.data);
+		if (ir->d.set_use_dec)
+			ir->d.set_use_dec(ir->d.data);
 		module_put(cdev->owner);
 	} else {
 		lirc_irctl_cleanup(ir);
@@ -547,12 +538,10 @@ unsigned int lirc_dev_fop_poll(struct file *file, poll_table *wait)
 	unsigned int ret;
 
 	if (!ir) {
-		printk(KERN_ERR "%s: called with invalid irctl\n", __func__);
+		pr_err("called with invalid irctl\n");
 		return POLLERR;
 	}
 
-	dev_dbg(ir->d.dev, LOGHEAD "poll called\n", ir->d.name, ir->d.minor);
-
 	if (!ir->attached)
 		return POLLERR;
 
@@ -580,7 +569,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct irctl *ir = irctls[iminor(file_inode(file))];
 
 	if (!ir) {
-		printk(KERN_ERR "lirc_dev: %s: no irctl found!\n", __func__);
+		pr_err("no irctl found!\n");
 		return -ENODEV;
 	}
 
@@ -588,7 +577,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		ir->d.name, ir->d.minor, cmd);
 
 	if (ir->d.minor == NOPLUG || !ir->attached) {
-		dev_dbg(ir->d.dev, LOGHEAD "ioctl result = -ENODEV\n",
+		dev_err(ir->d.dev, LOGHEAD "ioctl result = -ENODEV\n",
 			ir->d.name, ir->d.minor);
 		return -ENODEV;
 	}
@@ -600,8 +589,8 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		result = put_user(ir->d.features, (__u32 __user *)arg);
 		break;
 	case LIRC_GET_REC_MODE:
-		if (!(ir->d.features & LIRC_CAN_REC_MASK)) {
-			result = -ENOSYS;
+		if (LIRC_CAN_REC(ir->d.features)) {
+			result = -ENOTTY;
 			break;
 		}
 
@@ -610,8 +599,8 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				  (__u32 __user *)arg);
 		break;
 	case LIRC_SET_REC_MODE:
-		if (!(ir->d.features & LIRC_CAN_REC_MASK)) {
-			result = -ENOSYS;
+		if (LIRC_CAN_REC(ir->d.features)) {
+			result = -ENOTTY;
 			break;
 		}
 
@@ -629,7 +618,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case LIRC_GET_MIN_TIMEOUT:
 		if (!(ir->d.features & LIRC_CAN_SET_REC_TIMEOUT) ||
 		    ir->d.min_timeout == 0) {
-			result = -ENOSYS;
+			result = -ENOTTY;
 			break;
 		}
 
@@ -638,7 +627,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case LIRC_GET_MAX_TIMEOUT:
 		if (!(ir->d.features & LIRC_CAN_SET_REC_TIMEOUT) ||
 		    ir->d.max_timeout == 0) {
-			result = -ENOSYS;
+			result = -ENOTTY;
 			break;
 		}
 
@@ -648,9 +637,6 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		result = -EINVAL;
 	}
 
-	dev_dbg(ir->d.dev, LOGHEAD "ioctl result = %d\n",
-		ir->d.name, ir->d.minor, result);
-
 	mutex_unlock(&ir->irctl_lock);
 
 	return result;
@@ -668,7 +654,7 @@ ssize_t lirc_dev_fop_read(struct file *file,
 	DECLARE_WAITQUEUE(wait, current);
 
 	if (!ir) {
-		printk(KERN_ERR "%s: called with invalid irctl\n", __func__);
+		pr_err("called with invalid irctl\n");
 		return -ENODEV;
 	}
 
@@ -709,7 +695,8 @@ ssize_t lirc_dev_fop_read(struct file *file,
 			/* According to the read(2) man page, 'written' can be
 			 * returned as less than 'length', instead of blocking
 			 * again, returning -EWOULDBLOCK, or returning
-			 * -ERESTARTSYS */
+			 * -ERESTARTSYS
+			 */
 			if (written)
 				break;
 			if (file->f_flags & O_NONBLOCK) {
@@ -755,8 +742,6 @@ out_locked:
 
 out_unlocked:
 	kfree(buf);
-	dev_dbg(ir->d.dev, LOGHEAD "read result = %s (%d)\n",
-		ir->d.name, ir->d.minor, ret ? "<fail>" : "<ok>", ret);
 
 	return ret ? ret : written;
 }
@@ -775,12 +760,10 @@ ssize_t lirc_dev_fop_write(struct file *file, const char __user *buffer,
 	struct irctl *ir = irctls[iminor(file_inode(file))];
 
 	if (!ir) {
-		printk(KERN_ERR "%s: called with invalid irctl\n", __func__);
+		pr_err("called with invalid irctl\n");
 		return -ENODEV;
 	}
 
-	dev_dbg(ir->d.dev, LOGHEAD "write called\n", ir->d.name, ir->d.minor);
-
 	if (!ir->attached)
 		return -ENODEV;
 
@@ -795,25 +778,23 @@ static int __init lirc_dev_init(void)
 
 	lirc_class = class_create(THIS_MODULE, "lirc");
 	if (IS_ERR(lirc_class)) {
-		retval = PTR_ERR(lirc_class);
-		printk(KERN_ERR "lirc_dev: class_create failed\n");
-		goto error;
+		pr_err("class_create failed\n");
+		return PTR_ERR(lirc_class);
 	}
 
 	retval = alloc_chrdev_region(&lirc_base_dev, 0, MAX_IRCTL_DEVICES,
 				     IRCTL_DEV_NAME);
 	if (retval) {
 		class_destroy(lirc_class);
-		printk(KERN_ERR "lirc_dev: alloc_chrdev_region failed\n");
-		goto error;
+		pr_err("alloc_chrdev_region failed\n");
+		return retval;
 	}
 
 
-	printk(KERN_INFO "lirc_dev: IR Remote Control driver registered, "
-	       "major %d \n", MAJOR(lirc_base_dev));
+	pr_info("IR Remote Control driver registered, major %d\n",
+						MAJOR(lirc_base_dev));
 
-error:
-	return retval;
+	return 0;
 }
 
 
@@ -822,7 +803,7 @@ static void __exit lirc_dev_exit(void)
 {
 	class_destroy(lirc_class);
 	unregister_chrdev_region(lirc_base_dev, MAX_IRCTL_DEVICES);
-	printk(KERN_INFO "lirc_dev: module unloaded\n");
+	pr_info("module unloaded\n");
 }
 
 module_init(lirc_dev_init);
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 5cf2e749b9eb..4f8c7effdcee 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -887,6 +887,12 @@ static int mceusb_set_tx_mask(struct rc_dev *dev, u32 mask)
 {
 	struct mceusb_dev *ir = dev->priv;
 
+	/* return number of transmitters */
+	int emitters = ir->num_txports ? ir->num_txports : 2;
+
+	if (mask >= (1 << emitters))
+		return emitters;
+
 	if (ir->flags.tx_mask_normal)
 		ir->tx_mask = mask;
 	else
@@ -936,7 +942,7 @@ static int mceusb_set_tx_carrier(struct rc_dev *dev, u32 carrier)
 
 	}
 
-	return carrier;
+	return 0;
 }
 
 /*
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index 99b303b702ac..00215f343819 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -139,11 +139,7 @@ static inline void nvt_cir_reg_write(struct nvt_dev *nvt, u8 val, u8 offset)
 /* read val from cir config register */
 static u8 nvt_cir_reg_read(struct nvt_dev *nvt, u8 offset)
 {
-	u8 val;
-
-	val = inb(nvt->cir_addr + offset);
-
-	return val;
+	return inb(nvt->cir_addr + offset);
 }
 
 /* write val to cir wake register */
@@ -156,11 +152,7 @@ static inline void nvt_cir_wake_reg_write(struct nvt_dev *nvt,
 /* read val from cir wake config register */
 static u8 nvt_cir_wake_reg_read(struct nvt_dev *nvt, u8 offset)
 {
-	u8 val;
-
-	val = inb(nvt->cir_wake_addr + offset);
-
-	return val;
+	return inb(nvt->cir_wake_addr + offset);
 }
 
 /* don't override io address if one is set already */
@@ -401,6 +393,7 @@ static int nvt_hw_detect(struct nvt_dev *nvt)
 	/* Check if we're wired for the alternate EFER setup */
 	nvt->chip_major = nvt_cr_read(nvt, CR_CHIP_ID_HI);
 	if (nvt->chip_major == 0xff) {
+		nvt_efm_disable(nvt);
 		nvt->cr_efir = CR_EFIR2;
 		nvt->cr_efdr = CR_EFDR2;
 		nvt_efm_enable(nvt);
@@ -480,18 +473,14 @@ static void nvt_cir_wake_ldev_init(struct nvt_dev *nvt)
 
 	nvt_set_ioaddr(nvt, &nvt->cir_wake_addr);
 
-	nvt_cr_write(nvt, nvt->cir_wake_irq, CR_CIR_IRQ_RSRC);
-
-	nvt_dbg("CIR Wake initialized, base io port address: 0x%lx, irq: %d",
-		nvt->cir_wake_addr, nvt->cir_wake_irq);
+	nvt_dbg("CIR Wake initialized, base io port address: 0x%lx",
+		nvt->cir_wake_addr);
 }
 
 /* clear out the hardware's cir rx fifo */
 static void nvt_clear_cir_fifo(struct nvt_dev *nvt)
 {
-	u8 val;
-
-	val = nvt_cir_reg_read(nvt, CIR_FIFOCON);
+	u8 val = nvt_cir_reg_read(nvt, CIR_FIFOCON);
 	nvt_cir_reg_write(nvt, val | CIR_FIFOCON_RXFIFOCLR, CIR_FIFOCON);
 }
 
@@ -527,7 +516,7 @@ static void nvt_set_cir_iren(struct nvt_dev *nvt)
 {
 	u8 iren;
 
-	iren = CIR_IREN_RTR | CIR_IREN_PE;
+	iren = CIR_IREN_RTR | CIR_IREN_PE | CIR_IREN_RFO;
 	nvt_cir_reg_write(nvt, iren, CIR_IREN);
 }
 
@@ -566,34 +555,15 @@ static void nvt_cir_regs_init(struct nvt_dev *nvt)
 
 static void nvt_cir_wake_regs_init(struct nvt_dev *nvt)
 {
-	/* set number of bytes needed for wake from s3 (default 65) */
-	nvt_cir_wake_reg_write(nvt, CIR_WAKE_FIFO_CMP_BYTES,
-			       CIR_WAKE_FIFO_CMP_DEEP);
-
-	/* set tolerance/variance allowed per byte during wake compare */
-	nvt_cir_wake_reg_write(nvt, CIR_WAKE_CMP_TOLERANCE,
-			       CIR_WAKE_FIFO_CMP_TOL);
-
-	/* set sample limit count (PE interrupt raised when reached) */
-	nvt_cir_wake_reg_write(nvt, CIR_RX_LIMIT_COUNT >> 8, CIR_WAKE_SLCH);
-	nvt_cir_wake_reg_write(nvt, CIR_RX_LIMIT_COUNT & 0xff, CIR_WAKE_SLCL);
-
-	/* set cir wake fifo rx trigger level (currently 67) */
-	nvt_cir_wake_reg_write(nvt, CIR_WAKE_FIFOCON_RX_TRIGGER_LEV,
-			       CIR_WAKE_FIFOCON);
-
 	/*
-	 * Enable TX and RX, specific carrier on = low, off = high, and set
-	 * sample period (currently 50us)
+	 * Disable RX, set specific carrier on = low, off = high,
+	 * and sample period (currently 50us)
 	 */
-	nvt_cir_wake_reg_write(nvt, CIR_WAKE_IRCON_MODE0 | CIR_WAKE_IRCON_RXEN |
+	nvt_cir_wake_reg_write(nvt, CIR_WAKE_IRCON_MODE0 |
 			       CIR_WAKE_IRCON_R | CIR_WAKE_IRCON_RXINV |
 			       CIR_WAKE_IRCON_SAMPLE_PERIOD_SEL,
 			       CIR_WAKE_IRCON);
 
-	/* clear cir wake rx fifo */
-	nvt_clear_cir_wake_fifo(nvt);
-
 	/* clear any and all stray interrupts */
 	nvt_cir_wake_reg_write(nvt, 0xff, CIR_WAKE_IRSTS);
 
@@ -788,8 +758,6 @@ static void nvt_process_rx_ir_data(struct nvt_dev *nvt)
 
 	nvt_dbg_verbose("Processing buffer of len %d", nvt->pkts);
 
-	init_ir_raw_event(&rawir);
-
 	for (i = 0; i < nvt->pkts; i++) {
 		sample = nvt->buf[i];
 
@@ -835,19 +803,10 @@ static void nvt_get_rx_ir_data(struct nvt_dev *nvt)
 {
 	u8 fifocount, val;
 	unsigned int b_idx;
-	bool overrun = false;
 	int i;
 
 	/* Get count of how many bytes to read from RX FIFO */
 	fifocount = nvt_cir_reg_read(nvt, CIR_RXFCONT);
-	/* if we get 0xff, probably means the logical dev is disabled */
-	if (fifocount == 0xff)
-		return;
-	/* watch out for a fifo overrun condition */
-	else if (fifocount > RX_BUF_LEN) {
-		overrun = true;
-		fifocount = RX_BUF_LEN;
-	}
 
 	nvt_dbg("attempting to fetch %u bytes from hw rx fifo", fifocount);
 
@@ -869,9 +828,6 @@ static void nvt_get_rx_ir_data(struct nvt_dev *nvt)
 	nvt_dbg("%s: pkts now %d", __func__, nvt->pkts);
 
 	nvt_process_rx_ir_data(nvt);
-
-	if (overrun)
-		nvt_handle_rx_fifo_overrun(nvt);
 }
 
 static void nvt_cir_log_irqs(u8 status, u8 iren)
@@ -907,7 +863,7 @@ static bool nvt_cir_tx_inactive(struct nvt_dev *nvt)
 static irqreturn_t nvt_cir_isr(int irq, void *data)
 {
 	struct nvt_dev *nvt = data;
-	u8 status, iren, cur_state;
+	u8 status, iren;
 	unsigned long flags;
 
 	nvt_dbg_verbose("%s firing", __func__);
@@ -945,23 +901,15 @@ static irqreturn_t nvt_cir_isr(int irq, void *data)
 
 	nvt_cir_log_irqs(status, iren);
 
-	if (status & CIR_IRSTS_RTR) {
-		/* FIXME: add code for study/learn mode */
+	if (status & CIR_IRSTS_RFO)
+		nvt_handle_rx_fifo_overrun(nvt);
+
+	else if (status & (CIR_IRSTS_RTR | CIR_IRSTS_PE)) {
 		/* We only do rx if not tx'ing */
 		if (nvt_cir_tx_inactive(nvt))
 			nvt_get_rx_ir_data(nvt);
 	}
 
-	if (status & CIR_IRSTS_PE) {
-		if (nvt_cir_tx_inactive(nvt))
-			nvt_get_rx_ir_data(nvt);
-
-		cur_state = nvt->study_state;
-
-		if (cur_state == ST_STUDY_NONE)
-			nvt_clear_cir_fifo(nvt);
-	}
-
 	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 
 	if (status & CIR_IRSTS_TE)
@@ -1003,51 +951,6 @@ static irqreturn_t nvt_cir_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-/* Interrupt service routine for CIR Wake */
-static irqreturn_t nvt_cir_wake_isr(int irq, void *data)
-{
-	u8 status, iren, val;
-	struct nvt_dev *nvt = data;
-	unsigned long flags;
-
-	nvt_dbg_wake("%s firing", __func__);
-
-	spin_lock_irqsave(&nvt->nvt_lock, flags);
-
-	status = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IRSTS);
-	iren = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IREN);
-
-	/* IRQ may be shared with CIR, therefore check for each
-	 * status bit whether the related interrupt source is enabled
-	 */
-	if (!(status & iren)) {
-		spin_unlock_irqrestore(&nvt->nvt_lock, flags);
-		return IRQ_NONE;
-	}
-
-	if (status & CIR_WAKE_IRSTS_IR_PENDING)
-		nvt_clear_cir_wake_fifo(nvt);
-
-	nvt_cir_wake_reg_write(nvt, status, CIR_WAKE_IRSTS);
-	nvt_cir_wake_reg_write(nvt, 0, CIR_WAKE_IRSTS);
-
-	if ((status & CIR_WAKE_IRSTS_PE) &&
-	    (nvt->wake_state == ST_WAKE_START)) {
-		while (nvt_cir_wake_reg_read(nvt, CIR_WAKE_RD_FIFO_ONLY_IDX)) {
-			val = nvt_cir_wake_reg_read(nvt, CIR_WAKE_RD_FIFO_ONLY);
-			nvt_dbg("setting wake up key: 0x%x", val);
-		}
-
-		nvt_cir_wake_reg_write(nvt, 0, CIR_WAKE_IREN);
-		nvt->wake_state = ST_WAKE_FINISH;
-	}
-
-	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
-
-	nvt_dbg_wake("%s done", __func__);
-	return IRQ_HANDLED;
-}
-
 static void nvt_disable_cir(struct nvt_dev *nvt)
 {
 	unsigned long flags;
@@ -1151,8 +1054,6 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 	nvt->cir_irq  = pnp_irq(pdev, 0);
 
 	nvt->cir_wake_addr = pnp_port_start(pdev, 1);
-	/* irq is always shared between cir and cir wake */
-	nvt->cir_wake_irq  = nvt->cir_irq;
 
 	nvt->cr_efir = CR_EFIR;
 	nvt->cr_efdr = CR_EFDR;
@@ -1228,11 +1129,6 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 			    CIR_IOREG_LENGTH, NVT_DRIVER_NAME "-wake"))
 		goto exit_unregister_device;
 
-	if (devm_request_irq(&pdev->dev, nvt->cir_wake_irq,
-			     nvt_cir_wake_isr, IRQF_SHARED,
-			     NVT_DRIVER_NAME "-wake", (void *)nvt))
-		goto exit_unregister_device;
-
 	ret = device_create_file(&rdev->dev, &dev_attr_wakeup_data);
 	if (ret)
 		goto exit_unregister_device;
@@ -1283,10 +1179,6 @@ static int nvt_suspend(struct pnp_dev *pdev, pm_message_t state)
 
 	spin_lock_irqsave(&nvt->nvt_lock, flags);
 
-	/* zero out misc state tracking */
-	nvt->study_state = ST_STUDY_NONE;
-	nvt->wake_state = ST_WAKE_NONE;
-
 	/* disable all CIR interrupts */
 	nvt_cir_reg_write(nvt, 0, CIR_IREN);
 
diff --git a/drivers/media/rc/nuvoton-cir.h b/drivers/media/rc/nuvoton-cir.h
index c9c98ebb19ee..acf735fc7170 100644
--- a/drivers/media/rc/nuvoton-cir.h
+++ b/drivers/media/rc/nuvoton-cir.h
@@ -104,7 +104,6 @@ struct nvt_dev {
 	unsigned long cir_addr;
 	unsigned long cir_wake_addr;
 	int cir_irq;
-	int cir_wake_irq;
 
 	enum nvt_chip_ver chip_ver;
 	/* hardware id */
@@ -112,36 +111,12 @@ struct nvt_dev {
 	u8 chip_minor;
 
 	/* hardware features */
-	bool hw_learning_capable;
 	bool hw_tx_capable;
 
-	/* rx settings */
-	bool learning_enabled;
-
-	/* track cir wake state */
-	u8 wake_state;
-	/* for study */
-	u8 study_state;
 	/* carrier period = 1 / frequency */
 	u32 carrier;
 };
 
-/* study states */
-#define ST_STUDY_NONE      0x0
-#define ST_STUDY_START     0x1
-#define ST_STUDY_CARRIER   0x2
-#define ST_STUDY_ALL_RECV  0x4
-
-/* wake states */
-#define ST_WAKE_NONE	0x0
-#define ST_WAKE_START	0x1
-#define ST_WAKE_FINISH	0x2
-
-/* receive states */
-#define ST_RX_WAIT_7F		0x1
-#define ST_RX_WAIT_HEAD		0x2
-#define ST_RX_WAIT_SILENT_END	0x4
-
 /* send states */
 #define ST_TX_NONE	0x0
 #define ST_TX_REQUEST	0x2
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 7dfc7c2188f0..8e7f2929fa6f 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -130,13 +130,18 @@ static struct rc_map_list empty_map = {
 static int ir_create_table(struct rc_map *rc_map,
 			   const char *name, u64 rc_type, size_t size)
 {
-	rc_map->name = name;
+	rc_map->name = kstrdup(name, GFP_KERNEL);
+	if (!rc_map->name)
+		return -ENOMEM;
 	rc_map->rc_type = rc_type;
 	rc_map->alloc = roundup_pow_of_two(size * sizeof(struct rc_map_table));
 	rc_map->size = rc_map->alloc / sizeof(struct rc_map_table);
 	rc_map->scan = kmalloc(rc_map->alloc, GFP_KERNEL);
-	if (!rc_map->scan)
+	if (!rc_map->scan) {
+		kfree(rc_map->name);
+		rc_map->name = NULL;
 		return -ENOMEM;
+	}
 
 	IR_dprintk(1, "Allocated space for %u keycode entries (%u bytes)\n",
 		   rc_map->size, rc_map->alloc);
@@ -153,6 +158,7 @@ static int ir_create_table(struct rc_map *rc_map,
 static void ir_free_table(struct rc_map *rc_map)
 {
 	rc_map->size = 0;
+	kfree(rc_map->name);
 	kfree(rc_map->scan);
 	rc_map->scan = NULL;
 }
@@ -804,6 +810,7 @@ static const struct {
 	{ RC_BIT_SHARP,		"sharp",	"ir-sharp-decoder"	},
 	{ RC_BIT_MCE_KBD,	"mce_kbd",	"ir-mce_kbd-decoder"	},
 	{ RC_BIT_XMP,		"xmp",		"ir-xmp-decoder"	},
+	{ RC_BIT_CEC,		"cec",		NULL			},
 };
 
 /**
diff --git a/drivers/media/rc/redrat3.c b/drivers/media/rc/redrat3.c
index ec74244a3853..399f44d89a29 100644
--- a/drivers/media/rc/redrat3.c
+++ b/drivers/media/rc/redrat3.c
@@ -188,8 +188,7 @@ struct redrat3_dev {
 	/* usb dma */
 	dma_addr_t dma_in;
 
-	/* rx signal timeout timer */
-	struct timer_list rx_timeout;
+	/* rx signal timeout */
 	u32 hw_timeout;
 
 	/* Is the device currently transmitting?*/
@@ -330,22 +329,11 @@ static u32 redrat3_us_to_len(u32 microsec)
 	return result ? result : 1;
 }
 
-/* timer callback to send reset event */
-static void redrat3_rx_timeout(unsigned long data)
-{
-	struct redrat3_dev *rr3 = (struct redrat3_dev *)data;
-
-	dev_dbg(rr3->dev, "calling ir_raw_event_reset\n");
-	ir_raw_event_reset(rr3->rc);
-}
-
 static void redrat3_process_ir_data(struct redrat3_dev *rr3)
 {
 	DEFINE_IR_RAW_EVENT(rawir);
 	struct device *dev;
-	unsigned i, trailer = 0;
-	unsigned sig_size, single_len, offset, val;
-	unsigned long delay;
+	unsigned int i, sig_size, single_len, offset, val;
 	u32 mod_freq;
 
 	if (!rr3) {
@@ -355,10 +343,6 @@ static void redrat3_process_ir_data(struct redrat3_dev *rr3)
 
 	dev = rr3->dev;
 
-	/* Make sure we reset the IR kfifo after a bit of inactivity */
-	delay = usecs_to_jiffies(rr3->hw_timeout);
-	mod_timer(&rr3->rx_timeout, jiffies + delay);
-
 	mod_freq = redrat3_val_to_mod_freq(&rr3->irdata);
 	dev_dbg(dev, "Got mod_freq of %u\n", mod_freq);
 
@@ -376,9 +360,6 @@ static void redrat3_process_ir_data(struct redrat3_dev *rr3)
 			rawir.pulse = true;
 
 		rawir.duration = US_TO_NS(single_len);
-		/* Save initial pulse length to fudge trailer */
-		if (i == 0)
-			trailer = rawir.duration;
 		/* cap the value to IR_MAX_DURATION */
 		rawir.duration = (rawir.duration > IR_MAX_DURATION) ?
 				 IR_MAX_DURATION : rawir.duration;
@@ -388,18 +369,13 @@ static void redrat3_process_ir_data(struct redrat3_dev *rr3)
 		ir_raw_event_store_with_filter(rr3->rc, &rawir);
 	}
 
-	/* add a trailing space, if need be */
-	if (i % 2) {
-		rawir.pulse = false;
-		/* this duration is made up, and may not be ideal... */
-		if (trailer < US_TO_NS(1000))
-			rawir.duration = US_TO_NS(2800);
-		else
-			rawir.duration = trailer;
-		dev_dbg(dev, "storing trailing space with duration %d\n",
-			rawir.duration);
-		ir_raw_event_store_with_filter(rr3->rc, &rawir);
-	}
+	/* add a trailing space */
+	rawir.pulse = false;
+	rawir.timeout = true;
+	rawir.duration = US_TO_NS(rr3->hw_timeout);
+	dev_dbg(dev, "storing trailing timeout with duration %d\n",
+							rawir.duration);
+	ir_raw_event_store_with_filter(rr3->rc, &rawir);
 
 	dev_dbg(dev, "calling ir_raw_event_handle\n");
 	ir_raw_event_handle(rr3->rc);
@@ -499,6 +475,37 @@ static u32 redrat3_get_timeout(struct redrat3_dev *rr3)
 	return timeout;
 }
 
+static int redrat3_set_timeout(struct rc_dev *rc_dev, unsigned int timeoutns)
+{
+	struct redrat3_dev *rr3 = rc_dev->priv;
+	struct usb_device *udev = rr3->udev;
+	struct device *dev = rr3->dev;
+	u32 *timeout;
+	int ret;
+
+	timeout = kmalloc(sizeof(*timeout), GFP_KERNEL);
+	if (!timeout)
+		return -ENOMEM;
+
+	*timeout = cpu_to_be32(redrat3_us_to_len(timeoutns / 1000));
+	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), RR3_SET_IR_PARAM,
+		     USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
+		     RR3_IR_IO_SIG_TIMEOUT, 0, timeout, sizeof(*timeout),
+		     HZ * 25);
+	dev_dbg(dev, "set ir parm timeout %d ret 0x%02x\n",
+						be32_to_cpu(*timeout), ret);
+
+	if (ret == sizeof(*timeout)) {
+		rr3->hw_timeout = timeoutns / 1000;
+		ret = 0;
+	} else if (ret >= 0)
+		ret = -EIO;
+
+	kfree(timeout);
+
+	return ret;
+}
+
 static void redrat3_reset(struct redrat3_dev *rr3)
 {
 	struct usb_device *udev = rr3->udev;
@@ -708,7 +715,7 @@ static int redrat3_set_tx_carrier(struct rc_dev *rcdev, u32 carrier)
 
 	rr3->carrier = carrier;
 
-	return carrier;
+	return 0;
 }
 
 static int redrat3_transmit_ir(struct rc_dev *rcdev, unsigned *txbuf,
@@ -880,7 +887,10 @@ static struct rc_dev *redrat3_init_rc_dev(struct redrat3_dev *rr3)
 	rc->priv = rr3;
 	rc->driver_type = RC_DRIVER_IR_RAW;
 	rc->allowed_protocols = RC_BIT_ALL;
-	rc->timeout = US_TO_NS(2750);
+	rc->min_timeout = MS_TO_NS(RR3_RX_MIN_TIMEOUT);
+	rc->max_timeout = MS_TO_NS(RR3_RX_MAX_TIMEOUT);
+	rc->timeout = US_TO_NS(rr3->hw_timeout);
+	rc->s_timeout = redrat3_set_timeout;
 	rc->tx_ir = redrat3_transmit_ir;
 	rc->s_tx_carrier = redrat3_set_tx_carrier;
 	rc->driver_name = DRIVER_NAME;
@@ -990,7 +1000,7 @@ static int redrat3_dev_probe(struct usb_interface *intf,
 	if (retval < 0)
 		goto error;
 
-	/* store current hardware timeout, in us, will use for kfifo resets */
+	/* store current hardware timeout, in µs */
 	rr3->hw_timeout = redrat3_get_timeout(rr3);
 
 	/* default.. will get overridden by any sends with a freq defined */
@@ -1026,7 +1036,6 @@ static int redrat3_dev_probe(struct usb_interface *intf,
 		retval = -ENOMEM;
 		goto led_free_error;
 	}
-	setup_timer(&rr3->rx_timeout, redrat3_rx_timeout, (unsigned long)rr3);
 
 	/* we can register the device now, as it is ready */
 	usb_set_intfdata(intf, rr3);
@@ -1055,7 +1064,6 @@ static void redrat3_dev_disconnect(struct usb_interface *intf)
 	usb_set_intfdata(intf, NULL);
 	rc_unregister_device(rr3->rc);
 	led_classdev_unregister(&rr3->led);
-	del_timer_sync(&rr3->rx_timeout);
 	redrat3_delete(rr3, udev);
 }
 
diff --git a/drivers/media/rc/winbond-cir.c b/drivers/media/rc/winbond-cir.c
index d839f73f6a05..95ae60e659a1 100644
--- a/drivers/media/rc/winbond-cir.c
+++ b/drivers/media/rc/winbond-cir.c
@@ -615,6 +615,10 @@ wbcir_txmask(struct rc_dev *dev, u32 mask)
 	unsigned long flags;
 	u8 val;
 
+	/* return the number of transmitters */
+	if (mask > 15)
+		return 4;
+
 	/* Four outputs, only one output can be enabled at a time */
 	switch (mask) {
 	case 0x1:
diff --git a/drivers/media/tuners/it913x.c b/drivers/media/tuners/it913x.c
index 5c96da693289..6c3ef2181fcd 100644
--- a/drivers/media/tuners/it913x.c
+++ b/drivers/media/tuners/it913x.c
@@ -464,6 +464,7 @@ MODULE_DEVICE_TABLE(i2c, it913x_id_table);
 static struct i2c_driver it913x_driver = {
 	.driver = {
 		.name	= "it913x",
+		.suppress_bind_attrs	= true,
 	},
 	.probe		= it913x_probe,
 	.remove		= it913x_remove,
diff --git a/drivers/media/tuners/mt2063.c b/drivers/media/tuners/mt2063.c
index 6457ac91ef09..7f0b9d5940db 100644
--- a/drivers/media/tuners/mt2063.c
+++ b/drivers/media/tuners/mt2063.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/videodev2.h>
+#include <linux/gcd.h>
 
 #include "mt2063.h"
 
@@ -665,27 +666,6 @@ static u32 MT2063_ChooseFirstIF(struct MT2063_AvoidSpursData_t *pAS_Info)
 }
 
 /**
- * gcd() - Uses Euclid's algorithm
- *
- * @u, @v:	Unsigned values whose GCD is desired.
- *
- * Returns THE greatest common divisor of u and v, if either value is 0,
- * the other value is returned as the result.
- */
-static u32 MT2063_gcd(u32 u, u32 v)
-{
-	u32 r;
-
-	while (v != 0) {
-		r = u % v;
-		u = v;
-		v = r;
-	}
-
-	return u;
-}
-
-/**
  * IsSpurInBand() - Checks to see if a spur will be present within the IF's
  *                  bandwidth. (fIFOut +/- fIFBW, -fIFOut +/- fIFBW)
  *
@@ -731,12 +711,12 @@ static u32 IsSpurInBand(struct MT2063_AvoidSpursData_t *pAS_Info,
 	 ** of f_LO1, f_LO2 and the edge value.  Use the larger of this
 	 ** gcd-based scale factor or f_Scale.
 	 */
-	lo_gcd = MT2063_gcd(f_LO1, f_LO2);
-	gd_Scale = max((u32) MT2063_gcd(lo_gcd, d), f_Scale);
+	lo_gcd = gcd(f_LO1, f_LO2);
+	gd_Scale = max((u32) gcd(lo_gcd, d), f_Scale);
 	hgds = gd_Scale / 2;
-	gc_Scale = max((u32) MT2063_gcd(lo_gcd, c), f_Scale);
+	gc_Scale = max((u32) gcd(lo_gcd, c), f_Scale);
 	hgcs = gc_Scale / 2;
-	gf_Scale = max((u32) MT2063_gcd(lo_gcd, f), f_Scale);
+	gf_Scale = max((u32) gcd(lo_gcd, f), f_Scale);
 	hgfs = gf_Scale / 2;
 
 	n0 = DIV_ROUND_UP(f_LO2 - d, f_LO1 - f_LO2);
diff --git a/drivers/media/tuners/r820t.c b/drivers/media/tuners/r820t.c
index 6ab35e315fe7..08dca40356d2 100644
--- a/drivers/media/tuners/r820t.c
+++ b/drivers/media/tuners/r820t.c
@@ -337,20 +337,6 @@ static int r820t_xtal_capacitor[][2] = {
 };
 
 /*
- * measured with a Racal 6103E GSM test set at 928 MHz with -60 dBm
- * input power, for raw results see:
- *	http://steve-m.de/projects/rtl-sdr/gain_measurement/r820t/
- */
-
-static const int r820t_lna_gain_steps[]  = {
-	0, 9, 13, 40, 38, 13, 31, 22, 26, 31, 26, 14, 19, 5, 35, 13
-};
-
-static const int r820t_mixer_gain_steps[]  = {
-	0, 5, 10, 10, 19, 9, 10, 25, 17, 10, 8, 16, 13, 6, 3, -8
-};
-
-/*
  * I2C read/write code and shadow registers logic
  */
 static void shadow_store(struct r820t_priv *priv, u8 reg, const u8 *val,
@@ -1216,6 +1202,21 @@ static int r820t_read_gain(struct r820t_priv *priv)
 
 #if 0
 /* FIXME: This routine requires more testing */
+
+/*
+ * measured with a Racal 6103E GSM test set at 928 MHz with -60 dBm
+ * input power, for raw results see:
+ *	http://steve-m.de/projects/rtl-sdr/gain_measurement/r820t/
+ */
+
+static const int r820t_lna_gain_steps[]  = {
+	0, 9, 13, 40, 38, 13, 31, 22, 26, 31, 26, 14, 19, 5, 35, 13
+};
+
+static const int r820t_mixer_gain_steps[]  = {
+	0, 5, 10, 10, 19, 9, 10, 25, 17, 10, 8, 16, 13, 6, 3, -8
+};
+
 static int r820t_set_gain_mode(struct r820t_priv *priv,
 			       bool set_manual_gain,
 			       int gain)
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index b07a681f3fbc..57b250847cd3 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -514,7 +514,8 @@ MODULE_DEVICE_TABLE(i2c, si2157_id_table);
 
 static struct i2c_driver si2157_driver = {
 	.driver = {
-		.name	= "si2157",
+		.name	             = "si2157",
+		.suppress_bind_attrs = true,
 	},
 	.probe		= si2157_probe,
 	.remove		= si2157_remove,
diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c
index 92d9d4214c3a..fe031b06935f 100644
--- a/drivers/media/usb/airspy/airspy.c
+++ b/drivers/media/usb/airspy/airspy.c
@@ -488,7 +488,7 @@ static void airspy_disconnect(struct usb_interface *intf)
 /* Videobuf2 operations */
 static int airspy_queue_setup(struct vb2_queue *vq,
 		unsigned int *nbuffers,
-		unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
+		unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct airspy *s = vb2_get_drv_priv(vq);
 
diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c
index 321ea5cf1329..bf53553d2624 100644
--- a/drivers/media/usb/au0828/au0828-core.c
+++ b/drivers/media/usb/au0828/au0828-core.c
@@ -142,7 +142,7 @@ static void au0828_unregister_media_device(struct au0828_dev *dev)
 	struct media_device *mdev = dev->media_dev;
 	struct media_entity_notify *notify, *nextp;
 
-	if (!mdev || !media_devnode_is_registered(&mdev->devnode))
+	if (!mdev || !media_devnode_is_registered(mdev->devnode))
 		return;
 
 	/* Remove au0828 entity_notify callbacks */
@@ -482,7 +482,7 @@ static int au0828_media_device_register(struct au0828_dev *dev,
 	if (!dev->media_dev)
 		return 0;
 
-	if (!media_devnode_is_registered(&dev->media_dev->devnode)) {
+	if (!media_devnode_is_registered(dev->media_dev->devnode)) {
 
 		/* register media device */
 		ret = media_device_register(dev->media_dev);
diff --git a/drivers/media/usb/au0828/au0828-vbi.c b/drivers/media/usb/au0828/au0828-vbi.c
index b4efc103ae57..e0930ce59b8d 100644
--- a/drivers/media/usb/au0828/au0828-vbi.c
+++ b/drivers/media/usb/au0828/au0828-vbi.c
@@ -32,7 +32,7 @@
 
 static int vbi_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct au0828_dev *dev = vb2_get_drv_priv(vq);
 	unsigned long size = dev->vbi_width * dev->vbi_height * 2;
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 7d0ec4cb248c..82b026985868 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -698,7 +698,7 @@ int au0828_v4l2_device_register(struct usb_interface *interface,
 
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
-		       unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct au0828_dev *dev = vb2_get_drv_priv(vq);
 	unsigned long size = dev->height * dev->bytesperline;
diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c
index 00da024b47a6..29d450c15f29 100644
--- a/drivers/media/usb/cx231xx/cx231xx-417.c
+++ b/drivers/media/usb/cx231xx/cx231xx-417.c
@@ -1570,10 +1570,12 @@ static int vidioc_s_ctrl(struct file *file, void *priv,
 {
 	struct cx231xx_fh  *fh  = file->private_data;
 	struct cx231xx *dev = fh->dev;
+	struct v4l2_subdev *sd;
 
 	dprintk(3, "enter vidioc_s_ctrl()\n");
 	/* Update the A/V core */
-	call_all(dev, core, s_ctrl, ctl);
+	v4l2_device_for_each_subdev(sd, &dev->v4l2_dev)
+		v4l2_s_ctrl(NULL, sd->ctrl_handler, ctl);
 	dprintk(3, "exit vidioc_s_ctrl()\n");
 	return 0;
 }
diff --git a/drivers/media/usb/dvb-usb-v2/Kconfig b/drivers/media/usb/dvb-usb-v2/Kconfig
index 3dc8ef004f8b..524533d3eb29 100644
--- a/drivers/media/usb/dvb-usb-v2/Kconfig
+++ b/drivers/media/usb/dvb-usb-v2/Kconfig
@@ -127,17 +127,22 @@ config DVB_USB_MXL111SF
 config DVB_USB_RTL28XXU
 	tristate "Realtek RTL28xxU DVB USB support"
 	depends on DVB_USB_V2 && I2C_MUX
+	select DVB_MN88472 if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_MN88473 if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_RTL2830
 	select DVB_RTL2832
 	select DVB_RTL2832_SDR if (MEDIA_SUBDRV_AUTOSELECT && MEDIA_SDR_SUPPORT)
-	select MEDIA_TUNER_QT1010 if MEDIA_SUBDRV_AUTOSELECT
-	select MEDIA_TUNER_MT2060 if MEDIA_SUBDRV_AUTOSELECT
-	select MEDIA_TUNER_MXL5005S if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_SI2168 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_E4000 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_FC0012 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_FC0013 if MEDIA_SUBDRV_AUTOSELECT
-	select MEDIA_TUNER_E4000 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_FC2580 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_MT2060 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_MXL5005S if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_QT1010 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_R820T if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_SI2157 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_TUA9001 if MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Say Y here to support the Realtek RTL28xxU DVB USB receiver.
 
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 2638e3251f2a..ca018cd3fcd4 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -49,6 +49,7 @@ static int af9035_ctrl_msg(struct dvb_usb_device *d, struct usb_req *req)
 #define CHECKSUM_LEN 2
 #define USB_TIMEOUT 2000
 	struct state *state = d_to_priv(d);
+	struct usb_interface *intf = d->intf;
 	int ret, wlen, rlen;
 	u16 checksum, tmp_checksum;
 
@@ -57,8 +58,8 @@ static int af9035_ctrl_msg(struct dvb_usb_device *d, struct usb_req *req)
 	/* buffer overflow check */
 	if (req->wlen > (BUF_LEN - REQ_HDR_LEN - CHECKSUM_LEN) ||
 			req->rlen > (BUF_LEN - ACK_HDR_LEN - CHECKSUM_LEN)) {
-		dev_err(&d->udev->dev, "%s: too much data wlen=%d rlen=%d\n",
-				KBUILD_MODNAME, req->wlen, req->rlen);
+		dev_err(&intf->dev, "too much data wlen=%d rlen=%d\n",
+			req->wlen, req->rlen);
 		ret = -EINVAL;
 		goto exit;
 	}
@@ -94,10 +95,8 @@ static int af9035_ctrl_msg(struct dvb_usb_device *d, struct usb_req *req)
 	checksum = af9035_checksum(state->buf, rlen - 2);
 	tmp_checksum = (state->buf[rlen - 2] << 8) | state->buf[rlen - 1];
 	if (tmp_checksum != checksum) {
-		dev_err(&d->udev->dev,
-				"%s: command=%02x checksum mismatch (%04x != %04x)\n",
-				KBUILD_MODNAME, req->cmd, tmp_checksum,
-				checksum);
+		dev_err(&intf->dev, "command=%02x checksum mismatch (%04x != %04x)\n",
+			req->cmd, tmp_checksum, checksum);
 		ret = -EIO;
 		goto exit;
 	}
@@ -110,8 +109,8 @@ static int af9035_ctrl_msg(struct dvb_usb_device *d, struct usb_req *req)
 			goto exit;
 		}
 
-		dev_dbg(&d->udev->dev, "%s: command=%02x failed fw error=%d\n",
-				__func__, req->cmd, state->buf[2]);
+		dev_dbg(&intf->dev, "command=%02x failed fw error=%d\n",
+			req->cmd, state->buf[2]);
 		ret = -EIO;
 		goto exit;
 	}
@@ -122,20 +121,20 @@ static int af9035_ctrl_msg(struct dvb_usb_device *d, struct usb_req *req)
 exit:
 	mutex_unlock(&d->usb_mutex);
 	if (ret < 0)
-		dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&intf->dev, "failed=%d\n", ret);
 	return ret;
 }
 
 /* write multiple registers */
 static int af9035_wr_regs(struct dvb_usb_device *d, u32 reg, u8 *val, int len)
 {
+	struct usb_interface *intf = d->intf;
 	u8 wbuf[MAX_XFER_SIZE];
 	u8 mbox = (reg >> 16) & 0xff;
 	struct usb_req req = { CMD_MEM_WR, mbox, 6 + len, wbuf, 0, NULL };
 
 	if (6 + len > sizeof(wbuf)) {
-		dev_warn(&d->udev->dev, "%s: i2c wr: len=%d is too big!\n",
-			 KBUILD_MODNAME, len);
+		dev_warn(&intf->dev, "i2c wr: len=%d is too big!\n", len);
 		return -EOPNOTSUPP;
 	}
 
@@ -198,6 +197,7 @@ static int af9035_add_i2c_dev(struct dvb_usb_device *d, const char *type,
 {
 	int ret, num;
 	struct state *state = d_to_priv(d);
+	struct usb_interface *intf = d->intf;
 	struct i2c_client *client;
 	struct i2c_board_info board_info = {
 		.addr = addr,
@@ -212,11 +212,10 @@ static int af9035_add_i2c_dev(struct dvb_usb_device *d, const char *type,
 			break;
 	}
 
-	dev_dbg(&d->udev->dev, "%s: num=%d\n", __func__, num);
+	dev_dbg(&intf->dev, "num=%d\n", num);
 
 	if (num == AF9035_I2C_CLIENT_MAX) {
-		dev_err(&d->udev->dev, "%s: I2C client out of index\n",
-				KBUILD_MODNAME);
+		dev_err(&intf->dev, "I2C client out of index\n");
 		ret = -ENODEV;
 		goto err;
 	}
@@ -240,7 +239,7 @@ static int af9035_add_i2c_dev(struct dvb_usb_device *d, const char *type,
 	state->i2c_client[num] = client;
 	return 0;
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -248,6 +247,7 @@ static void af9035_del_i2c_dev(struct dvb_usb_device *d)
 {
 	int num;
 	struct state *state = d_to_priv(d);
+	struct usb_interface *intf = d->intf;
 	struct i2c_client *client;
 
 	/* find last used client */
@@ -257,11 +257,10 @@ static void af9035_del_i2c_dev(struct dvb_usb_device *d)
 			break;
 	}
 
-	dev_dbg(&d->udev->dev, "%s: num=%d\n", __func__, num);
+	dev_dbg(&intf->dev, "num=%d\n", num);
 
 	if (num == -1) {
-		dev_err(&d->udev->dev, "%s: I2C client out of index\n",
-				KBUILD_MODNAME);
+		dev_err(&intf->dev, "I2C client out of index\n");
 		goto err;
 	}
 
@@ -276,7 +275,7 @@ static void af9035_del_i2c_dev(struct dvb_usb_device *d)
 	state->i2c_client[num] = NULL;
 	return;
 err:
-	dev_dbg(&d->udev->dev, "%s: failed\n", __func__);
+	dev_dbg(&intf->dev, "failed\n");
 }
 
 static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
@@ -348,6 +347,9 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 
 			ret = af9035_rd_regs(d, reg, &msg[1].buf[0],
 					msg[1].len);
+		} else if (state->no_read) {
+			memset(msg[1].buf, 0, msg[1].len);
+			ret = 0;
 		} else {
 			/* I2C write + read */
 			u8 buf[MAX_XFER_SIZE];
@@ -367,10 +369,25 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 				memcpy(&buf[3], msg[0].buf, msg[0].len);
 			} else {
 				buf[1] = msg[0].addr << 1;
-				buf[2] = 0x00; /* reg addr len */
 				buf[3] = 0x00; /* reg addr MSB */
 				buf[4] = 0x00; /* reg addr LSB */
-				memcpy(&buf[5], msg[0].buf, msg[0].len);
+
+				/* Keep prev behavior for write req len > 2*/
+				if (msg[0].len > 2) {
+					buf[2] = 0x00; /* reg addr len */
+					memcpy(&buf[5], msg[0].buf, msg[0].len);
+
+				/* Use reg addr fields if write req len <= 2 */
+				} else {
+					req.wlen = 5;
+					buf[2] = msg[0].len;
+					if (msg[0].len == 2) {
+						buf[3] = msg[0].buf[0];
+						buf[4] = msg[0].buf[1];
+					} else if (msg[0].len == 1) {
+						buf[4] = msg[0].buf[0];
+					}
+				}
 			}
 			ret = af9035_ctrl_msg(d, &req);
 		}
@@ -421,6 +438,9 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 		if (msg[0].len > 40) {
 			/* TODO: correct limits > 40 */
 			ret = -EOPNOTSUPP;
+		} else if (state->no_read) {
+			memset(msg[0].buf, 0, msg[0].len);
+			ret = 0;
 		} else {
 			/* I2C read */
 			u8 buf[5];
@@ -475,7 +495,9 @@ static struct i2c_algorithm af9035_i2c_algo = {
 static int af9035_identify_state(struct dvb_usb_device *d, const char **name)
 {
 	struct state *state = d_to_priv(d);
-	int ret;
+	struct usb_interface *intf = d->intf;
+	int ret, ts_mode_invalid;
+	u8 tmp;
 	u8 wbuf[1] = { 1 };
 	u8 rbuf[4];
 	struct usb_req req = { CMD_FW_QUERYINFO, 0, sizeof(wbuf), wbuf,
@@ -492,10 +514,8 @@ static int af9035_identify_state(struct dvb_usb_device *d, const char **name)
 	if (ret < 0)
 		goto err;
 
-	dev_info(&d->udev->dev,
-			"%s: prechip_version=%02x chip_version=%02x chip_type=%04x\n",
-			KBUILD_MODNAME, state->prechip_version,
-			state->chip_version, state->chip_type);
+	dev_info(&intf->dev, "prechip_version=%02x chip_version=%02x chip_type=%04x\n",
+		 state->prechip_version, state->chip_version, state->chip_type);
 
 	if (state->chip_type == 0x9135) {
 		if (state->chip_version == 0x02)
@@ -511,11 +531,41 @@ static int af9035_identify_state(struct dvb_usb_device *d, const char **name)
 		state->eeprom_addr = EEPROM_BASE_AF9035;
 	}
 
+
+	/* check for dual tuner mode */
+	ret = af9035_rd_reg(d, state->eeprom_addr + EEPROM_TS_MODE, &tmp);
+	if (ret < 0)
+		goto err;
+
+	ts_mode_invalid = 0;
+	switch (tmp) {
+	case 0:
+		break;
+	case 1:
+	case 3:
+		state->dual_mode = true;
+		break;
+	case 5:
+		if (state->chip_type != 0x9135 && state->chip_type != 0x9306)
+			state->dual_mode = true;	/* AF9035 */
+		else
+			ts_mode_invalid = 1;
+		break;
+	default:
+		ts_mode_invalid = 1;
+	}
+
+	dev_dbg(&intf->dev, "ts mode=%d dual mode=%d\n", tmp, state->dual_mode);
+
+	if (ts_mode_invalid)
+		dev_info(&intf->dev, "ts mode=%d not supported, defaulting to single tuner mode!", tmp);
+
+
 	ret = af9035_ctrl_msg(d, &req);
 	if (ret < 0)
 		goto err;
 
-	dev_dbg(&d->udev->dev, "%s: reply=%*ph\n", __func__, 4, rbuf);
+	dev_dbg(&intf->dev, "reply=%*ph\n", 4, rbuf);
 	if (rbuf[0] || rbuf[1] || rbuf[2] || rbuf[3])
 		ret = WARM;
 	else
@@ -524,7 +574,7 @@ static int af9035_identify_state(struct dvb_usb_device *d, const char **name)
 	return ret;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -532,6 +582,7 @@ err:
 static int af9035_download_firmware_old(struct dvb_usb_device *d,
 		const struct firmware *fw)
 {
+	struct usb_interface *intf = d->intf;
 	int ret, i, j, len;
 	u8 wbuf[1];
 	struct usb_req req = { 0, 0, 0, NULL, 0, NULL };
@@ -562,14 +613,12 @@ static int af9035_download_firmware_old(struct dvb_usb_device *d,
 		hdr_checksum = fw->data[fw->size - i + 5] << 8;
 		hdr_checksum |= fw->data[fw->size - i + 6] << 0;
 
-		dev_dbg(&d->udev->dev,
-				"%s: core=%d addr=%04x data_len=%d checksum=%04x\n",
-				__func__, hdr_core, hdr_addr, hdr_data_len,
-				hdr_checksum);
+		dev_dbg(&intf->dev, "core=%d addr=%04x data_len=%d checksum=%04x\n",
+			hdr_core, hdr_addr, hdr_data_len, hdr_checksum);
 
 		if (((hdr_core != 1) && (hdr_core != 2)) ||
 				(hdr_data_len > i)) {
-			dev_dbg(&d->udev->dev, "%s: bad firmware\n", __func__);
+			dev_dbg(&intf->dev, "bad firmware\n");
 			break;
 		}
 
@@ -600,18 +649,17 @@ static int af9035_download_firmware_old(struct dvb_usb_device *d,
 
 		i -= hdr_data_len + HDR_SIZE;
 
-		dev_dbg(&d->udev->dev, "%s: data uploaded=%zu\n",
-				__func__, fw->size - i);
+		dev_dbg(&intf->dev, "data uploaded=%zu\n", fw->size - i);
 	}
 
 	/* print warn if firmware is bad, continue and see what happens */
 	if (i)
-		dev_warn(&d->udev->dev, "%s: bad firmware\n", KBUILD_MODNAME);
+		dev_warn(&intf->dev, "bad firmware\n");
 
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -619,6 +667,7 @@ err:
 static int af9035_download_firmware_new(struct dvb_usb_device *d,
 		const struct firmware *fw)
 {
+	struct usb_interface *intf = d->intf;
 	int ret, i, i_prev;
 	struct usb_req req_fw_dl = { CMD_FW_SCATTER_WR, 0, 0, NULL, 0, NULL };
 	#define HDR_SIZE 7
@@ -648,15 +697,14 @@ static int af9035_download_firmware_new(struct dvb_usb_device *d,
 			if (ret < 0)
 				goto err;
 
-			dev_dbg(&d->udev->dev, "%s: data uploaded=%d\n",
-					__func__, i);
+			dev_dbg(&intf->dev, "data uploaded=%d\n", i);
 		}
 	}
 
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -664,6 +712,7 @@ err:
 static int af9035_download_firmware(struct dvb_usb_device *d,
 		const struct firmware *fw)
 {
+	struct usb_interface *intf = d->intf;
 	struct state *state = d_to_priv(d);
 	int ret;
 	u8 wbuf[1];
@@ -672,7 +721,7 @@ static int af9035_download_firmware(struct dvb_usb_device *d,
 	struct usb_req req = { 0, 0, 0, NULL, 0, NULL };
 	struct usb_req req_fw_ver = { CMD_FW_QUERYINFO, 0, 1, wbuf, 4, rbuf };
 
-	dev_dbg(&d->udev->dev, "%s:\n", __func__);
+	dev_dbg(&intf->dev, "\n");
 
 	/*
 	 * In case of dual tuner configuration we need to do some extra
@@ -680,11 +729,7 @@ static int af9035_download_firmware(struct dvb_usb_device *d,
 	 * which is done by master demod.
 	 * Master feeds also clock and controls power via GPIO.
 	 */
-	ret = af9035_rd_reg(d, state->eeprom_addr + EEPROM_TS_MODE, &tmp);
-	if (ret < 0)
-		goto err;
-
-	if (tmp == 1 || tmp == 3 || tmp == 5) {
+	if (state->dual_mode) {
 		/* configure gpioh1, reset & power slave demod */
 		ret = af9035_wr_reg_mask(d, 0x00d8b0, 0x01, 0x01);
 		if (ret < 0)
@@ -752,25 +797,25 @@ static int af9035_download_firmware(struct dvb_usb_device *d,
 		goto err;
 
 	if (!(rbuf[0] || rbuf[1] || rbuf[2] || rbuf[3])) {
-		dev_err(&d->udev->dev, "%s: firmware did not run\n",
-				KBUILD_MODNAME);
+		dev_err(&intf->dev, "firmware did not run\n");
 		ret = -ENODEV;
 		goto err;
 	}
 
-	dev_info(&d->udev->dev, "%s: firmware version=%d.%d.%d.%d",
-			KBUILD_MODNAME, rbuf[0], rbuf[1], rbuf[2], rbuf[3]);
+	dev_info(&intf->dev, "firmware version=%d.%d.%d.%d",
+		 rbuf[0], rbuf[1], rbuf[2], rbuf[3]);
 
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int af9035_read_config(struct dvb_usb_device *d)
 {
+	struct usb_interface *intf = d->intf;
 	struct state *state = d_to_priv(d);
 	int ret, i;
 	u8 tmp;
@@ -805,7 +850,7 @@ static int af9035_read_config(struct dvb_usb_device *d)
 			goto err;
 
 		if (tmp == 0x00) {
-			dev_dbg(&d->udev->dev, "%s: no eeprom\n", __func__);
+			dev_dbg(&intf->dev, "no eeprom\n");
 			goto skip_eeprom;
 		}
 	} else if (state->chip_type == 0x9306) {
@@ -817,18 +862,6 @@ static int af9035_read_config(struct dvb_usb_device *d)
 	}
 
 
-
-	/* check if there is dual tuners */
-	ret = af9035_rd_reg(d, state->eeprom_addr + EEPROM_TS_MODE, &tmp);
-	if (ret < 0)
-		goto err;
-
-	if (tmp == 1 || tmp == 3 || tmp == 5)
-		state->dual_mode = true;
-
-	dev_dbg(&d->udev->dev, "%s: ts mode=%d dual mode=%d\n", __func__,
-			tmp, state->dual_mode);
-
 	if (state->dual_mode) {
 		/* read 2nd demodulator I2C address */
 		ret = af9035_rd_reg(d,
@@ -840,8 +873,7 @@ static int af9035_read_config(struct dvb_usb_device *d)
 		if (tmp)
 			state->af9033_i2c_addr[1] = tmp;
 
-		dev_dbg(&d->udev->dev, "%s: 2nd demod I2C addr=%02x\n",
-				__func__, tmp);
+		dev_dbg(&intf->dev, "2nd demod I2C addr=%02x\n", tmp);
 	}
 
 	addr = state->eeprom_addr;
@@ -852,8 +884,7 @@ static int af9035_read_config(struct dvb_usb_device *d)
 		if (ret < 0)
 			goto err;
 
-		dev_dbg(&d->udev->dev, "%s: [%d]tuner=%02x\n",
-				__func__, i, tmp);
+		dev_dbg(&intf->dev, "[%d]tuner=%02x\n", i, tmp);
 
 		/* tuner sanity check */
 		if (state->chip_type == 0x9135) {
@@ -882,10 +913,8 @@ static int af9035_read_config(struct dvb_usb_device *d)
 		}
 
 		if (state->af9033_config[i].tuner != tmp) {
-			dev_info(&d->udev->dev,
-					"%s: [%d] overriding tuner from %02x to %02x\n",
-					KBUILD_MODNAME, i, tmp,
-					state->af9033_config[i].tuner);
+			dev_info(&intf->dev, "[%d] overriding tuner from %02x to %02x\n",
+				 i, tmp, state->af9033_config[i].tuner);
 		}
 
 		switch (state->af9033_config[i].tuner) {
@@ -905,9 +934,8 @@ static int af9035_read_config(struct dvb_usb_device *d)
 		case AF9033_TUNER_IT9135_62:
 			break;
 		default:
-			dev_warn(&d->udev->dev,
-					"%s: tuner id=%02x not supported, please report!",
-					KBUILD_MODNAME, tmp);
+			dev_warn(&intf->dev, "tuner id=%02x not supported, please report!",
+				 tmp);
 		}
 
 		/* disable dual mode if driver does not support it */
@@ -924,9 +952,7 @@ static int af9035_read_config(struct dvb_usb_device *d)
 				break;
 			default:
 				state->dual_mode = false;
-				dev_info(&d->udev->dev,
-						"%s: driver does not support 2nd tuner and will disable it",
-						KBUILD_MODNAME);
+				dev_info(&intf->dev, "driver does not support 2nd tuner and will disable it");
 		}
 
 		/* tuner IF frequency */
@@ -942,7 +968,7 @@ static int af9035_read_config(struct dvb_usb_device *d)
 
 		tmp16 |= tmp << 8;
 
-		dev_dbg(&d->udev->dev, "%s: [%d]IF=%d\n", __func__, i, tmp16);
+		dev_dbg(&intf->dev, "[%d]IF=%d\n", i, tmp16);
 
 		addr += 0x10; /* shift for the 2nd tuner params */
 	}
@@ -962,10 +988,24 @@ skip_eeprom:
 			state->af9033_config[i].clock = clock_lut_af9035[tmp];
 	}
 
+	state->no_read = false;
+	/* Some MXL5007T devices cannot properly handle tuner I2C read ops. */
+	if (state->af9033_config[0].tuner == AF9033_TUNER_MXL5007T &&
+		le16_to_cpu(d->udev->descriptor.idVendor) == USB_VID_AVERMEDIA)
+
+		switch (le16_to_cpu(d->udev->descriptor.idProduct)) {
+		case USB_PID_AVERMEDIA_A867:
+		case USB_PID_AVERMEDIA_TWINSTAR:
+			dev_info(&intf->dev,
+				 "Device may have issues with I2C read operations. Enabling fix.\n");
+			state->no_read = true;
+			break;
+		}
+
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -973,10 +1013,11 @@ err:
 static int af9035_tua9001_tuner_callback(struct dvb_usb_device *d,
 		int cmd, int arg)
 {
+	struct usb_interface *intf = d->intf;
 	int ret;
 	u8 val;
 
-	dev_dbg(&d->udev->dev, "%s: cmd=%d arg=%d\n", __func__, cmd, arg);
+	dev_dbg(&intf->dev, "cmd=%d arg=%d\n", cmd, arg);
 
 	/*
 	 * CEN     always enabled by hardware wiring
@@ -1010,7 +1051,7 @@ static int af9035_tua9001_tuner_callback(struct dvb_usb_device *d,
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1019,6 +1060,7 @@ err:
 static int af9035_fc0011_tuner_callback(struct dvb_usb_device *d,
 		int cmd, int arg)
 {
+	struct usb_interface *intf = d->intf;
 	int ret;
 
 	switch (cmd) {
@@ -1076,7 +1118,7 @@ static int af9035_fc0011_tuner_callback(struct dvb_usb_device *d,
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1102,9 +1144,10 @@ static int af9035_frontend_callback(void *adapter_priv, int component,
 {
 	struct i2c_adapter *adap = adapter_priv;
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
+	struct usb_interface *intf = d->intf;
 
-	dev_dbg(&d->udev->dev, "%s: component=%d cmd=%d arg=%d\n",
-			__func__, component, cmd, arg);
+	dev_dbg(&intf->dev, "component=%d cmd=%d arg=%d\n",
+		component, cmd, arg);
 
 	switch (component) {
 	case DVB_FRONTEND_COMPONENT_TUNER:
@@ -1127,9 +1170,10 @@ static int af9035_frontend_attach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
+	struct usb_interface *intf = d->intf;
 	int ret;
 
-	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
 	if (!state->af9033_config[adap->id].tuner) {
 		/* unsupported tuner */
@@ -1156,7 +1200,7 @@ static int af9035_frontend_attach(struct dvb_usb_adapter *adap)
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1165,11 +1209,12 @@ static int it930x_frontend_attach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
+	struct usb_interface *intf = d->intf;
 	int ret;
 	struct si2168_config si2168_config;
 	struct i2c_adapter *adapter;
 
-	dev_dbg(&d->udev->dev, "adap->id=%d\n", adap->id);
+	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
 	memset(&si2168_config, 0, sizeof(si2168_config));
 	si2168_config.i2c_adapter = &adapter;
@@ -1192,7 +1237,7 @@ static int it930x_frontend_attach(struct dvb_usb_adapter *adap)
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1201,9 +1246,10 @@ static int af9035_frontend_detach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
+	struct usb_interface *intf = d->intf;
 	int demod2;
 
-	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
 	/*
 	 * For dual tuner devices we have to resolve 2nd demod client, as there
@@ -1279,12 +1325,13 @@ static int af9035_tuner_attach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
+	struct usb_interface *intf = d->intf;
 	int ret;
 	struct dvb_frontend *fe;
 	struct i2c_msg msg[1];
 	u8 tuner_addr;
 
-	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
 	/*
 	 * XXX: Hack used in that function: we abuse unused I2C address bit [7]
@@ -1522,7 +1569,7 @@ static int af9035_tuner_attach(struct dvb_usb_adapter *adap)
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1531,10 +1578,11 @@ static int it930x_tuner_attach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
+	struct usb_interface *intf = d->intf;
 	int ret;
 	struct si2157_config si2157_config;
 
-	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
 	/* I2C master bus 2 clock speed 300k */
 	ret = af9035_wr_reg(d, 0x00f6a7, 0x07);
@@ -1590,7 +1638,7 @@ static int it930x_tuner_attach(struct dvb_usb_adapter *adap)
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1600,8 +1648,9 @@ static int it930x_tuner_detach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
+	struct usb_interface *intf = d->intf;
 
-	dev_dbg(&d->udev->dev, "adap->id=%d\n", adap->id);
+	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
 	if (adap->id == 1) {
 		if (state->i2c_client[3])
@@ -1619,8 +1668,9 @@ static int af9035_tuner_detach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
+	struct usb_interface *intf = d->intf;
 
-	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
 	switch (state->af9033_config[adap->id].tuner) {
 	case AF9033_TUNER_TUA9001:
@@ -1646,6 +1696,7 @@ static int af9035_tuner_detach(struct dvb_usb_adapter *adap)
 static int af9035_init(struct dvb_usb_device *d)
 {
 	struct state *state = d_to_priv(d);
+	struct usb_interface *intf = d->intf;
 	int ret, i;
 	u16 frame_size = (d->udev->speed == USB_SPEED_FULL ? 5 : 87) * 188 / 4;
 	u8 packet_size = (d->udev->speed == USB_SPEED_FULL ? 64 : 512) / 4;
@@ -1670,9 +1721,8 @@ static int af9035_init(struct dvb_usb_device *d)
 		{ 0x80f9a4, 0x00, 0x01 },
 	};
 
-	dev_dbg(&d->udev->dev,
-			"%s: USB speed=%d frame_size=%04x packet_size=%02x\n",
-			__func__, d->udev->speed, frame_size, packet_size);
+	dev_dbg(&intf->dev, "USB speed=%d frame_size=%04x packet_size=%02x\n",
+		d->udev->speed, frame_size, packet_size);
 
 	/* init endpoints */
 	for (i = 0; i < ARRAY_SIZE(tab); i++) {
@@ -1685,7 +1735,7 @@ static int af9035_init(struct dvb_usb_device *d)
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1693,6 +1743,7 @@ err:
 static int it930x_init(struct dvb_usb_device *d)
 {
 	struct state *state = d_to_priv(d);
+	struct usb_interface *intf = d->intf;
 	int ret, i;
 	u16 frame_size = (d->udev->speed == USB_SPEED_FULL ? 5 : 816) * 188 / 4;
 	u8 packet_size = (d->udev->speed == USB_SPEED_FULL ? 64 : 512) / 4;
@@ -1752,9 +1803,8 @@ static int it930x_init(struct dvb_usb_device *d)
 		{ 0x00da5a, 0x1f, 0xff }, /* ts_fail_ignore */
 	};
 
-	dev_dbg(&d->udev->dev,
-			"%s: USB speed=%d frame_size=%04x packet_size=%02x\n",
-			__func__, d->udev->speed, frame_size, packet_size);
+	dev_dbg(&intf->dev, "USB speed=%d frame_size=%04x packet_size=%02x\n",
+		d->udev->speed, frame_size, packet_size);
 
 	/* init endpoints */
 	for (i = 0; i < ARRAY_SIZE(tab); i++) {
@@ -1767,7 +1817,7 @@ static int it930x_init(struct dvb_usb_device *d)
 
 	return 0;
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1776,6 +1826,7 @@ err:
 #if IS_ENABLED(CONFIG_RC_CORE)
 static int af9035_rc_query(struct dvb_usb_device *d)
 {
+	struct usb_interface *intf = d->intf;
 	int ret;
 	u32 key;
 	u8 buf[4];
@@ -1801,14 +1852,14 @@ static int af9035_rc_query(struct dvb_usb_device *d)
 					buf[2] << 8  | buf[3]);
 	}
 
-	dev_dbg(&d->udev->dev, "%s: %*ph\n", __func__, 4, buf);
+	dev_dbg(&intf->dev, "%*ph\n", 4, buf);
 
 	rc_keydown(d->rc_dev, RC_TYPE_NEC, key, 0);
 
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1816,6 +1867,7 @@ err:
 static int af9035_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 {
 	struct state *state = d_to_priv(d);
+	struct usb_interface *intf = d->intf;
 	int ret;
 	u8 tmp;
 
@@ -1823,7 +1875,7 @@ static int af9035_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 	if (ret < 0)
 		goto err;
 
-	dev_dbg(&d->udev->dev, "%s: ir_mode=%02x\n", __func__, tmp);
+	dev_dbg(&intf->dev, "ir_mode=%02x\n", tmp);
 
 	/* don't activate rc if in HID mode or if not available */
 	if (tmp == 5) {
@@ -1832,7 +1884,7 @@ static int af9035_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 		if (ret < 0)
 			goto err;
 
-		dev_dbg(&d->udev->dev, "%s: ir_type=%02x\n", __func__, tmp);
+		dev_dbg(&intf->dev, "ir_type=%02x\n", tmp);
 
 		switch (tmp) {
 		case 0: /* NEC */
@@ -1855,7 +1907,7 @@ static int af9035_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 	return 0;
 
 err:
-	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&intf->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -1867,8 +1919,9 @@ static int af9035_get_stream_config(struct dvb_frontend *fe, u8 *ts_type,
 		struct usb_data_stream_properties *stream)
 {
 	struct dvb_usb_device *d = fe_to_d(fe);
+	struct usb_interface *intf = d->intf;
 
-	dev_dbg(&d->udev->dev, "%s: adap=%d\n", __func__, fe_to_adap(fe)->id);
+	dev_dbg(&intf->dev, "adap=%d\n", fe_to_adap(fe)->id);
 
 	if (d->udev->speed == USB_SPEED_FULL)
 		stream->u.bulk.buffersize = 5 * 188;
@@ -1920,7 +1973,7 @@ static int af9035_probe(struct usb_interface *intf,
 	if ((le16_to_cpu(udev->descriptor.idVendor) == USB_VID_TERRATEC) &&
 			(le16_to_cpu(udev->descriptor.idProduct) == 0x0099)) {
 		if (!strcmp("Afatech", manufacturer)) {
-			dev_dbg(&udev->dev, "%s: rejecting device\n", __func__);
+			dev_dbg(&udev->dev, "rejecting device\n");
 			return -ENODEV;
 		}
 	}
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.h b/drivers/media/usb/dvb-usb-v2/af9035.h
index 89e629a24aec..1f83c9218ad0 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.h
+++ b/drivers/media/usb/dvb-usb-v2/af9035.h
@@ -62,6 +62,7 @@ struct state {
 	u8 chip_version;
 	u16 chip_type;
 	u8 dual_mode:1;
+	u8 no_read:1;
 	u16 eeprom_addr;
 	u8 af9033_i2c_addr[2];
 	struct af9033_config af9033_config[2];
@@ -112,7 +113,7 @@ static const u32 clock_lut_it9135[] = {
  * 0  TS
  * 1  DCA + PIP
  * 3  PIP
- * 5  DCA + PIP
+ * 5  DCA + PIP (AF9035 only)
  * n  DCA
  *
  * Values 0, 3 and 5 are seen to this day. 0 for single TS and 3/5 for dual TS.
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index eb7af8cb8aca..6643762a9ff7 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -624,7 +624,7 @@ static int rtl28xxu_identify_state(struct dvb_usb_device *d, const char **name)
 	dev_dbg(&d->intf->dev, "chip_id=%u\n", dev->chip_id);
 
 	/* Retry failed I2C messages */
-	d->i2c_adap.retries = 1;
+	d->i2c_adap.retries = 3;
 	d->i2c_adap.timeout = msecs_to_jiffies(10);
 
 	return WARM;
diff --git a/drivers/media/usb/dvb-usb/dtt200u.c b/drivers/media/usb/dvb-usb/dtt200u.c
index ca3b69aa9688..be633ece4194 100644
--- a/drivers/media/usb/dvb-usb/dtt200u.c
+++ b/drivers/media/usb/dvb-usb/dtt200u.c
@@ -55,36 +55,36 @@ static int dtt200u_pid_filter(struct dvb_usb_adapter *adap, int index, u16 pid,
 	return dvb_usb_generic_write(adap->dev, b_pid, 4);
 }
 
-/* remote control */
-/* key list for the tiny remote control (Yakumo, don't know about the others) */
-static struct rc_map_table rc_map_dtt200u_table[] = {
-	{ 0x8001, KEY_MUTE },
-	{ 0x8002, KEY_CHANNELDOWN },
-	{ 0x8003, KEY_VOLUMEDOWN },
-	{ 0x8004, KEY_1 },
-	{ 0x8005, KEY_2 },
-	{ 0x8006, KEY_3 },
-	{ 0x8007, KEY_4 },
-	{ 0x8008, KEY_5 },
-	{ 0x8009, KEY_6 },
-	{ 0x800a, KEY_7 },
-	{ 0x800c, KEY_ZOOM },
-	{ 0x800d, KEY_0 },
-	{ 0x800e, KEY_SELECT },
-	{ 0x8012, KEY_POWER },
-	{ 0x801a, KEY_CHANNELUP },
-	{ 0x801b, KEY_8 },
-	{ 0x801e, KEY_VOLUMEUP },
-	{ 0x801f, KEY_9 },
-};
-
-static int dtt200u_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
+static int dtt200u_rc_query(struct dvb_usb_device *d)
 {
 	u8 key[5],cmd = GET_RC_CODE;
+	u32 scancode;
+
 	dvb_usb_generic_rw(d,&cmd,1,key,5,0);
-	dvb_usb_nec_rc_key_to_event(d,key,event,state);
+	if (key[0] == 1) {
+		scancode = key[1];
+		if ((u8) ~key[1] != key[2]) {
+			/* Extended NEC */
+			scancode = scancode << 8;
+			scancode |= key[2];
+		}
+		scancode = scancode << 8;
+		scancode |= key[3];
+
+		/* Check command checksum is ok */
+		if ((u8) ~key[3] == key[4])
+			rc_keydown(d->rc_dev, RC_TYPE_NEC, scancode, 0);
+		else
+			rc_keyup(d->rc_dev);
+	} else if (key[0] == 2) {
+		rc_repeat(d->rc_dev);
+	} else {
+		rc_keyup(d->rc_dev);
+	}
+
 	if (key[0] != 0)
 		deb_info("key: %*ph\n", 5, key);
+
 	return 0;
 }
 
@@ -164,11 +164,11 @@ static struct dvb_usb_device_properties dtt200u_properties = {
 	},
 	.power_ctrl      = dtt200u_power_ctrl,
 
-	.rc.legacy = {
+	.rc.core = {
 		.rc_interval     = 300,
-		.rc_map_table    = rc_map_dtt200u_table,
-		.rc_map_size     = ARRAY_SIZE(rc_map_dtt200u_table),
+		.rc_codes        = RC_MAP_DTT200U,
 		.rc_query        = dtt200u_rc_query,
+		.allowed_protos  = RC_BIT_NEC,
 	},
 
 	.generic_bulk_ctrl_endpoint = 0x01,
@@ -214,11 +214,11 @@ static struct dvb_usb_device_properties wt220u_properties = {
 	},
 	.power_ctrl      = dtt200u_power_ctrl,
 
-	.rc.legacy = {
+	.rc.core = {
 		.rc_interval     = 300,
-		.rc_map_table      = rc_map_dtt200u_table,
-		.rc_map_size = ARRAY_SIZE(rc_map_dtt200u_table),
+		.rc_codes        = RC_MAP_DTT200U,
 		.rc_query        = dtt200u_rc_query,
+		.allowed_protos  = RC_BIT_NEC,
 	},
 
 	.generic_bulk_ctrl_endpoint = 0x01,
@@ -264,11 +264,11 @@ static struct dvb_usb_device_properties wt220u_fc_properties = {
 	},
 	.power_ctrl      = dtt200u_power_ctrl,
 
-	.rc.legacy = {
+	.rc.core = {
 		.rc_interval     = 300,
-		.rc_map_table    = rc_map_dtt200u_table,
-		.rc_map_size     = ARRAY_SIZE(rc_map_dtt200u_table),
+		.rc_codes        = RC_MAP_DTT200U,
 		.rc_query        = dtt200u_rc_query,
+		.allowed_protos  = RC_BIT_NEC,
 	},
 
 	.generic_bulk_ctrl_endpoint = 0x01,
@@ -314,11 +314,11 @@ static struct dvb_usb_device_properties wt220u_zl0353_properties = {
 	},
 	.power_ctrl      = dtt200u_power_ctrl,
 
-	.rc.legacy = {
+	.rc.core = {
 		.rc_interval     = 300,
-		.rc_map_table    = rc_map_dtt200u_table,
-		.rc_map_size     = ARRAY_SIZE(rc_map_dtt200u_table),
+		.rc_codes        = RC_MAP_DTT200U,
 		.rc_query        = dtt200u_rc_query,
+		.allowed_protos  = RC_BIT_NEC,
 	},
 
 	.generic_bulk_ctrl_endpoint = 0x01,
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-dvb.c b/drivers/media/usb/dvb-usb/dvb-usb-dvb.c
index 6477b04e95c7..a04c0a250625 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-dvb.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-dvb.c
@@ -320,8 +320,6 @@ int dvb_usb_adapter_frontend_init(struct dvb_usb_adapter *adap)
 
 		adap->num_frontends_initialized++;
 	}
-	if (ret)
-		return ret;
 
 	ret = dvb_create_media_graph(&adap->dvb_adap, true);
 	if (ret)
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 49b55d7069b1..5fb0c650926e 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -847,7 +847,7 @@ static int su3000_power_ctrl(struct dvb_usb_device *d, int i)
 	struct dw2102_state *state = (struct dw2102_state *)d->priv;
 	u8 obuf[] = {0xde, 0};
 
-	info("%s: %d, initialized %d\n", __func__, i, state->initialized);
+	info("%s: %d, initialized %d", __func__, i, state->initialized);
 
 	if (i && !state->initialized) {
 		state->initialized = 1;
@@ -894,7 +894,7 @@ static int su3000_identify_state(struct usb_device *udev,
 				 struct dvb_usb_device_description **desc,
 				 int *cold)
 {
-	info("%s\n", __func__);
+	info("%s", __func__);
 
 	*cold = 0;
 	return 0;
@@ -1132,7 +1132,7 @@ static int dw2104_frontend_attach(struct dvb_usb_adapter *d)
 				tuner_ops->set_bandwidth = stb6100_set_bandw;
 				tuner_ops->get_bandwidth = stb6100_get_bandw;
 				d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-				info("Attached STV0900+STB6100!\n");
+				info("Attached STV0900+STB6100!");
 				return 0;
 			}
 		}
@@ -1146,7 +1146,7 @@ static int dw2104_frontend_attach(struct dvb_usb_adapter *d)
 					&dw2104_stv6110_config,
 					&d->dev->i2c_adap)) {
 				d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-				info("Attached STV0900+STV6110A!\n");
+				info("Attached STV0900+STV6110A!");
 				return 0;
 			}
 		}
@@ -1157,7 +1157,7 @@ static int dw2104_frontend_attach(struct dvb_usb_adapter *d)
 				&d->dev->i2c_adap);
 		if (d->fe_adap[0].fe != NULL) {
 			d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-			info("Attached cx24116!\n");
+			info("Attached cx24116!");
 			return 0;
 		}
 	}
@@ -1168,7 +1168,7 @@ static int dw2104_frontend_attach(struct dvb_usb_adapter *d)
 		dvb_attach(ts2020_attach, d->fe_adap[0].fe,
 			&dw2104_ts2020_config, &d->dev->i2c_adap);
 		d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-		info("Attached DS3000!\n");
+		info("Attached DS3000!");
 		return 0;
 	}
 
@@ -1187,7 +1187,7 @@ static int dw2102_frontend_attach(struct dvb_usb_adapter *d)
 					&d->dev->i2c_adap);
 		if (d->fe_adap[0].fe != NULL) {
 			d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-			info("Attached si21xx!\n");
+			info("Attached si21xx!");
 			return 0;
 		}
 	}
@@ -1199,7 +1199,7 @@ static int dw2102_frontend_attach(struct dvb_usb_adapter *d)
 			if (dvb_attach(stb6000_attach, d->fe_adap[0].fe, 0x61,
 					&d->dev->i2c_adap)) {
 				d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-				info("Attached stv0288!\n");
+				info("Attached stv0288!");
 				return 0;
 			}
 		}
@@ -1211,7 +1211,7 @@ static int dw2102_frontend_attach(struct dvb_usb_adapter *d)
 					&d->dev->i2c_adap);
 		if (d->fe_adap[0].fe != NULL) {
 			d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-			info("Attached stv0299!\n");
+			info("Attached stv0299!");
 			return 0;
 		}
 	}
@@ -1223,7 +1223,7 @@ static int dw3101_frontend_attach(struct dvb_usb_adapter *d)
 	d->fe_adap[0].fe = dvb_attach(tda10023_attach, &dw3101_tda10023_config,
 				&d->dev->i2c_adap, 0x48);
 	if (d->fe_adap[0].fe != NULL) {
-		info("Attached tda10023!\n");
+		info("Attached tda10023!");
 		return 0;
 	}
 	return -EIO;
@@ -1237,7 +1237,7 @@ static int zl100313_frontend_attach(struct dvb_usb_adapter *d)
 		if (dvb_attach(zl10039_attach, d->fe_adap[0].fe, 0x60,
 				&d->dev->i2c_adap)) {
 			d->fe_adap[0].fe->ops.set_voltage = dw210x_set_voltage;
-			info("Attached zl100313+zl10039!\n");
+			info("Attached zl100313+zl10039!");
 			return 0;
 		}
 	}
@@ -1262,7 +1262,7 @@ static int stv0288_frontend_attach(struct dvb_usb_adapter *d)
 
 	dw210x_op_rw(d->dev->udev, 0x8a, 0, 0, obuf, 2, DW210X_WRITE_MSG);
 
-	info("Attached stv0288+stb6000!\n");
+	info("Attached stv0288+stb6000!");
 
 	return 0;
 
@@ -1287,7 +1287,7 @@ static int ds3000_frontend_attach(struct dvb_usb_adapter *d)
 
 	dw210x_op_rw(d->dev->udev, 0x8a, 0, 0, obuf, 2, DW210X_WRITE_MSG);
 
-	info("Attached ds3000+ts2020!\n");
+	info("Attached ds3000+ts2020!");
 
 	return 0;
 }
@@ -1305,7 +1305,7 @@ static int prof_7500_frontend_attach(struct dvb_usb_adapter *d)
 
 	dw210x_op_rw(d->dev->udev, 0x8a, 0, 0, obuf, 2, DW210X_WRITE_MSG);
 
-	info("Attached STV0900+STB6100A!\n");
+	info("Attached STV0900+STB6100A!");
 
 	return 0;
 }
@@ -1353,11 +1353,11 @@ static int su3000_frontend_attach(struct dvb_usb_adapter *d)
 	if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
 				&dw2104_ts2020_config,
 				&d->dev->i2c_adap)) {
-		info("Attached DS3000/TS2020!\n");
+		info("Attached DS3000/TS2020!");
 		return 0;
 	}
 
-	info("Failed to attach DS3000/TS2020!\n");
+	info("Failed to attach DS3000/TS2020!");
 	return -EIO;
 }
 
@@ -1402,12 +1402,12 @@ static int t220_frontend_attach(struct dvb_usb_adapter *d)
 	if (d->fe_adap[0].fe != NULL) {
 		if (dvb_attach(tda18271_attach, d->fe_adap[0].fe, 0x60,
 					&d->dev->i2c_adap, &tda18271_config)) {
-			info("Attached TDA18271HD/CXD2820R!\n");
+			info("Attached TDA18271HD/CXD2820R!");
 			return 0;
 		}
 	}
 
-	info("Failed to attach TDA18271HD/CXD2820R!\n");
+	info("Failed to attach TDA18271HD/CXD2820R!");
 	return -EIO;
 }
 
@@ -1428,11 +1428,11 @@ static int m88rs2000_frontend_attach(struct dvb_usb_adapter *d)
 	if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
 				&dw2104_ts2020_config,
 				&d->dev->i2c_adap)) {
-		info("Attached RS2000/TS2020!\n");
+		info("Attached RS2000/TS2020!");
 		return 0;
 	}
 
-	info("Failed to attach RS2000/TS2020!\n");
+	info("Failed to attach RS2000/TS2020!");
 	return -EIO;
 }
 
@@ -1641,6 +1641,7 @@ enum dw2102_table_entry {
 	TEVII_S421,
 	TEVII_S632,
 	TERRATEC_CINERGY_S2_R2,
+	TERRATEC_CINERGY_S2_R3,
 	GOTVIEW_SAT_HD,
 	GENIATECH_T220,
 	TECHNOTREND_S2_4600,
@@ -1669,6 +1670,7 @@ static struct usb_device_id dw2102_table[] = {
 	[TEVII_S421] = {USB_DEVICE(0x9022, USB_PID_TEVII_S421)},
 	[TEVII_S632] = {USB_DEVICE(0x9022, USB_PID_TEVII_S632)},
 	[TERRATEC_CINERGY_S2_R2] = {USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_S2_R2)},
+	[TERRATEC_CINERGY_S2_R3] = {USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_S2_R3)},
 	[GOTVIEW_SAT_HD] = {USB_DEVICE(0x1FE1, USB_PID_GOTVIEW_SAT_HD)},
 	[GENIATECH_T220] = {USB_DEVICE(0x1f4d, 0xD220)},
 	[TECHNOTREND_S2_4600] = {USB_DEVICE(USB_VID_TECHNOTREND,
@@ -2083,7 +2085,7 @@ static struct dvb_usb_device_properties su3000_properties = {
 		}},
 		}
 	},
-	.num_device_descs = 5,
+	.num_device_descs = 6,
 	.devices = {
 		{ "SU3000HD DVB-S USB2.0",
 			{ &dw2102_table[GENIATECH_SU3000], NULL },
@@ -2101,6 +2103,10 @@ static struct dvb_usb_device_properties su3000_properties = {
 			{ &dw2102_table[TERRATEC_CINERGY_S2_R2], NULL },
 			{ NULL },
 		},
+		{ "Terratec Cinergy S2 USB HD Rev.3",
+			{ &dw2102_table[TERRATEC_CINERGY_S2_R3], NULL },
+			{ NULL },
+		},
 		{ "GOTVIEW Satellite HD",
 			{ &dw2102_table[GOTVIEW_SAT_HD], NULL },
 			{ NULL },
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index 1a5c01202f73..8cedef0daae4 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -904,17 +904,6 @@ static struct tda18271_config c3tech_duo_tda18271_config = {
 	.small_i2c = TDA18271_03_BYTE_CHUNK_INIT,
 };
 
-static const struct m88ds3103_config pctv_461e_m88ds3103_config = {
-	.i2c_addr = 0x68,
-	.clock = 27000000,
-	.i2c_wr_max = 33,
-	.clock_out = 0,
-	.ts_mode = M88DS3103_TS_PARALLEL,
-	.ts_clk = 16000,
-	.ts_clk_pol = 1,
-	.agc = 0x99,
-};
-
 static struct tda18271_std_map drx_j_std_map = {
 	.atsc_6   = { .if_freq = 5000, .agc_mode = 3, .std = 0, .if_lvl = 1,
 		      .rfagc_top = 0x37, },
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index a19b5c8b56ff..1a9e1e556706 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -507,9 +507,8 @@ static int em28xx_i2c_xfer(struct i2c_adapter *i2c_adap,
 	if (dev->disconnected)
 		return -ENODEV;
 
-	rc = rt_mutex_trylock(&dev->i2c_bus_lock);
-	if (rc < 0)
-		return rc;
+	if (!rt_mutex_trylock(&dev->i2c_bus_lock))
+		return -EAGAIN;
 
 	/* Switch I2C bus if needed */
 	if (bus != dev->cur_i2c_bus &&
diff --git a/drivers/media/usb/em28xx/em28xx-vbi.c b/drivers/media/usb/em28xx/em28xx-vbi.c
index fe94c9225dd7..836c6b53b16c 100644
--- a/drivers/media/usb/em28xx/em28xx-vbi.c
+++ b/drivers/media/usb/em28xx/em28xx-vbi.c
@@ -33,7 +33,7 @@
 
 static int vbi_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct em28xx *dev = vb2_get_drv_priv(vq);
 	struct em28xx_v4l2 *v4l2 = dev->v4l2;
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 44834b2eff55..7968695217f3 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -1013,7 +1013,7 @@ static void em28xx_v4l2_create_entities(struct em28xx *dev)
 
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
-		       unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct em28xx *dev = vb2_get_drv_priv(vq);
 	struct em28xx_v4l2 *v4l2 = dev->v4l2;
diff --git a/drivers/media/usb/go7007/go7007-v4l2.c b/drivers/media/usb/go7007/go7007-v4l2.c
index ea01ee5df60a..af8458996d91 100644
--- a/drivers/media/usb/go7007/go7007-v4l2.c
+++ b/drivers/media/usb/go7007/go7007-v4l2.c
@@ -370,7 +370,7 @@ static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 
 static int go7007_queue_setup(struct vb2_queue *q,
 		unsigned int *num_buffers, unsigned int *num_planes,
-		unsigned int sizes[], void *alloc_ctxs[])
+		unsigned int sizes[], struct device *alloc_devs[])
 {
 	sizes[0] = GO7007_BUF_SIZE;
 	*num_planes = 1;
diff --git a/drivers/media/usb/gspca/cpia1.c b/drivers/media/usb/gspca/cpia1.c
index f23df4a9d8c5..52b88e9e656b 100644
--- a/drivers/media/usb/gspca/cpia1.c
+++ b/drivers/media/usb/gspca/cpia1.c
@@ -1624,7 +1624,7 @@ static int sd_start(struct gspca_dev *gspca_dev)
 
 static void sd_stopN(struct gspca_dev *gspca_dev)
 {
-	struct sd *sd = (struct sd *) gspca_dev;
+	struct sd *sd __maybe_unused = (struct sd *) gspca_dev;
 
 	command_pause(gspca_dev);
 
diff --git a/drivers/media/usb/gspca/gspca.c b/drivers/media/usb/gspca/gspca.c
index af5cd8213e8b..b17bd7ebcb47 100644
--- a/drivers/media/usb/gspca/gspca.c
+++ b/drivers/media/usb/gspca/gspca.c
@@ -522,7 +522,7 @@ static int frame_alloc(struct gspca_dev *gspca_dev, struct file *file,
 		frame = &gspca_dev->frame[i];
 		frame->v4l2_buf.index = i;
 		frame->v4l2_buf.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-		frame->v4l2_buf.flags = 0;
+		frame->v4l2_buf.flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		frame->v4l2_buf.field = V4L2_FIELD_NONE;
 		frame->v4l2_buf.length = frsz;
 		frame->v4l2_buf.memory = memory;
@@ -705,7 +705,7 @@ static int build_isoc_ep_tb(struct gspca_dev *gspca_dev,
 			psize = (psize & 0x07ff) * (1 + ((psize >> 11) & 3));
 			bandwidth = psize * 1000;
 			if (gspca_dev->dev->speed == USB_SPEED_HIGH
-			 || gspca_dev->dev->speed == USB_SPEED_SUPER)
+			 || gspca_dev->dev->speed >= USB_SPEED_SUPER)
 				bandwidth *= 8;
 			bandwidth /= 1 << (ep->desc.bInterval - 1);
 			if (bandwidth <= last_bw)
@@ -996,6 +996,19 @@ static int wxh_to_mode(struct gspca_dev *gspca_dev,
 {
 	int i;
 
+	for (i = 0; i < gspca_dev->cam.nmodes; i++) {
+		if (width == gspca_dev->cam.cam_mode[i].width
+		    && height == gspca_dev->cam.cam_mode[i].height)
+			return i;
+	}
+	return -EINVAL;
+}
+
+static int wxh_to_nearest_mode(struct gspca_dev *gspca_dev,
+			int width, int height)
+{
+	int i;
+
 	for (i = gspca_dev->cam.nmodes; --i > 0; ) {
 		if (width >= gspca_dev->cam.cam_mode[i].width
 		    && height >= gspca_dev->cam.cam_mode[i].height)
@@ -1125,8 +1138,8 @@ static int try_fmt_vid_cap(struct gspca_dev *gspca_dev,
 	PDEBUG_MODE(gspca_dev, D_CONF, "try fmt cap",
 		    fmt->fmt.pix.pixelformat, w, h);
 
-	/* search the closest mode for width and height */
-	mode = wxh_to_mode(gspca_dev, w, h);
+	/* search the nearest mode for width and height */
+	mode = wxh_to_nearest_mode(gspca_dev, w, h);
 
 	/* OK if right palette */
 	if (gspca_dev->cam.cam_mode[mode].pixelformat
@@ -1233,9 +1246,13 @@ static int vidioc_enum_frameintervals(struct file *filp, void *priv,
 				      struct v4l2_frmivalenum *fival)
 {
 	struct gspca_dev *gspca_dev = video_drvdata(filp);
-	int mode = wxh_to_mode(gspca_dev, fival->width, fival->height);
+	int mode;
 	__u32 i;
 
+	mode = wxh_to_mode(gspca_dev, fival->width, fival->height);
+	if (mode < 0)
+		return -EINVAL;
+
 	if (gspca_dev->cam.mode_framerates == NULL ||
 			gspca_dev->cam.mode_framerates[mode].nrates == 0)
 		return -EINVAL;
@@ -1246,7 +1263,7 @@ static int vidioc_enum_frameintervals(struct file *filp, void *priv,
 
 	for (i = 0; i < gspca_dev->cam.mode_framerates[mode].nrates; i++) {
 		if (fival->index == i) {
-			fival->type = V4L2_FRMSIZE_TYPE_DISCRETE;
+			fival->type = V4L2_FRMIVAL_TYPE_DISCRETE;
 			fival->discrete.numerator = 1;
 			fival->discrete.denominator =
 				gspca_dev->cam.mode_framerates[mode].rates[i];
diff --git a/drivers/media/usb/gspca/konica.c b/drivers/media/usb/gspca/konica.c
index 39c96bb4c985..0712b1bc90b4 100644
--- a/drivers/media/usb/gspca/konica.c
+++ b/drivers/media/usb/gspca/konica.c
@@ -243,7 +243,7 @@ static int sd_start(struct gspca_dev *gspca_dev)
 
 static void sd_stopN(struct gspca_dev *gspca_dev)
 {
-	struct sd *sd = (struct sd *) gspca_dev;
+	struct sd *sd __maybe_unused = (struct sd *) gspca_dev;
 
 	konica_stream_off(gspca_dev);
 #if IS_ENABLED(CONFIG_INPUT)
diff --git a/drivers/media/usb/gspca/m5602/m5602_bridge.h b/drivers/media/usb/gspca/m5602/m5602_bridge.h
index 19eb1a64f9d6..43ebc03d844d 100644
--- a/drivers/media/usb/gspca/m5602/m5602_bridge.h
+++ b/drivers/media/usb/gspca/m5602/m5602_bridge.h
@@ -115,21 +115,6 @@
 
 /*****************************************************************************/
 
-/* A skeleton used for sending messages to the m5602 bridge */
-static const unsigned char bridge_urb_skeleton[] = {
-	0x13, 0x00, 0x81, 0x00
-};
-
-/* A skeleton used for sending messages to the sensor */
-static const unsigned char sensor_urb_skeleton[] = {
-	0x23, M5602_XB_GPIO_EN_H, 0x81, 0x06,
-	0x23, M5602_XB_MISC_CTRL, 0x81, 0x80,
-	0x13, M5602_XB_I2C_DEV_ADDR, 0x81, 0x00,
-	0x13, M5602_XB_I2C_REG_ADDR, 0x81, 0x00,
-	0x13, M5602_XB_I2C_DATA, 0x81, 0x00,
-	0x13, M5602_XB_I2C_CTRL, 0x81, 0x11
-};
-
 struct sd {
 	struct gspca_dev gspca_dev;
 
diff --git a/drivers/media/usb/gspca/m5602/m5602_core.c b/drivers/media/usb/gspca/m5602/m5602_core.c
index d926e62cb80b..e4a0658e3f83 100644
--- a/drivers/media/usb/gspca/m5602/m5602_core.c
+++ b/drivers/media/usb/gspca/m5602/m5602_core.c
@@ -37,6 +37,21 @@ static const struct usb_device_id m5602_table[] = {
 
 MODULE_DEVICE_TABLE(usb, m5602_table);
 
+/* A skeleton used for sending messages to the sensor */
+static const unsigned char sensor_urb_skeleton[] = {
+	0x23, M5602_XB_GPIO_EN_H, 0x81, 0x06,
+	0x23, M5602_XB_MISC_CTRL, 0x81, 0x80,
+	0x13, M5602_XB_I2C_DEV_ADDR, 0x81, 0x00,
+	0x13, M5602_XB_I2C_REG_ADDR, 0x81, 0x00,
+	0x13, M5602_XB_I2C_DATA, 0x81, 0x00,
+	0x13, M5602_XB_I2C_CTRL, 0x81, 0x11
+};
+
+/* A skeleton used for sending messages to the m5602 bridge */
+static const unsigned char bridge_urb_skeleton[] = {
+	0x13, 0x00, 0x81, 0x00
+};
+
 /* Reads a byte from the m5602 */
 int m5602_read_bridge(struct sd *sd, const u8 address, u8 *i2c_data)
 {
diff --git a/drivers/media/usb/gspca/m5602/m5602_mt9m111.c b/drivers/media/usb/gspca/m5602/m5602_mt9m111.c
index 27fcef11aef4..7d01ddd7ed01 100644
--- a/drivers/media/usb/gspca/m5602/m5602_mt9m111.c
+++ b/drivers/media/usb/gspca/m5602/m5602_mt9m111.c
@@ -23,6 +23,150 @@
 static int mt9m111_s_ctrl(struct v4l2_ctrl *ctrl);
 static void mt9m111_dump_registers(struct sd *sd);
 
+static const unsigned char preinit_mt9m111[][4] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
+
+	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00},
+	{SENSOR, MT9M111_SC_RESET,
+		MT9M111_RESET |
+		MT9M111_RESTART |
+		MT9M111_ANALOG_STANDBY |
+		MT9M111_CHIP_DISABLE,
+		MT9M111_SHOW_BAD_FRAMES |
+		MT9M111_RESTART_BAD_FRAMES |
+		MT9M111_SYNCHRONIZE_CHANGES},
+
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3e, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3e, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
+
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x07, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x0b, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
+
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a, 0x00}
+};
+
+static const unsigned char init_mt9m111[][4] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
+
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3e, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x07, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x0b, 0x00},
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a, 0x00},
+
+	{SENSOR, MT9M111_SC_RESET, 0x00, 0x29},
+	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00},
+	{SENSOR, MT9M111_SC_RESET, 0x00, 0x08},
+	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x01},
+	{SENSOR, MT9M111_CP_OPERATING_MODE_CTL, 0x00,
+			MT9M111_CP_OPERATING_MODE_CTL},
+	{SENSOR, MT9M111_CP_LENS_CORRECTION_1, 0x04, 0x2a},
+	{SENSOR, MT9M111_CP_DEFECT_CORR_CONTEXT_A, 0x00,
+				MT9M111_2D_DEFECT_CORRECTION_ENABLE},
+	{SENSOR, MT9M111_CP_DEFECT_CORR_CONTEXT_B, 0x00,
+				MT9M111_2D_DEFECT_CORRECTION_ENABLE},
+	{SENSOR, MT9M111_CP_LUMA_OFFSET, 0x00, 0x00},
+	{SENSOR, MT9M111_CP_LUMA_CLIP, 0xff, 0x00},
+	{SENSOR, MT9M111_CP_OUTPUT_FORMAT_CTL2_CONTEXT_A, 0x14, 0x00},
+	{SENSOR, MT9M111_CP_OUTPUT_FORMAT_CTL2_CONTEXT_B, 0x14, 0x00},
+	{SENSOR, 0xcd, 0x00, 0x0e},
+	{SENSOR, 0xd0, 0x00, 0x40},
+
+	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x02},
+	{SENSOR, MT9M111_CC_AUTO_EXPOSURE_PARAMETER_18, 0x00, 0x00},
+	{SENSOR, MT9M111_CC_AWB_PARAMETER_7, 0xef, 0x03},
+
+	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00},
+	{SENSOR, 0x33, 0x03, 0x49},
+	{SENSOR, 0x34, 0xc0, 0x19},
+	{SENSOR, 0x3f, 0x20, 0x20},
+	{SENSOR, 0x40, 0x20, 0x20},
+	{SENSOR, 0x5a, 0xc0, 0x0a},
+	{SENSOR, 0x70, 0x7b, 0x0a},
+	{SENSOR, 0x71, 0xff, 0x00},
+	{SENSOR, 0x72, 0x19, 0x0e},
+	{SENSOR, 0x73, 0x18, 0x0f},
+	{SENSOR, 0x74, 0x57, 0x32},
+	{SENSOR, 0x75, 0x56, 0x34},
+	{SENSOR, 0x76, 0x73, 0x35},
+	{SENSOR, 0x77, 0x30, 0x12},
+	{SENSOR, 0x78, 0x79, 0x02},
+	{SENSOR, 0x79, 0x75, 0x06},
+	{SENSOR, 0x7a, 0x77, 0x0a},
+	{SENSOR, 0x7b, 0x78, 0x09},
+	{SENSOR, 0x7c, 0x7d, 0x06},
+	{SENSOR, 0x7d, 0x31, 0x10},
+	{SENSOR, 0x7e, 0x00, 0x7e},
+	{SENSOR, 0x80, 0x59, 0x04},
+	{SENSOR, 0x81, 0x59, 0x04},
+	{SENSOR, 0x82, 0x57, 0x0a},
+	{SENSOR, 0x83, 0x58, 0x0b},
+	{SENSOR, 0x84, 0x47, 0x0c},
+	{SENSOR, 0x85, 0x48, 0x0e},
+	{SENSOR, 0x86, 0x5b, 0x02},
+	{SENSOR, 0x87, 0x00, 0x5c},
+	{SENSOR, MT9M111_CONTEXT_CONTROL, 0x00, MT9M111_SEL_CONTEXT_B},
+	{SENSOR, 0x60, 0x00, 0x80},
+	{SENSOR, 0x61, 0x00, 0x00},
+	{SENSOR, 0x62, 0x00, 0x00},
+	{SENSOR, 0x63, 0x00, 0x00},
+	{SENSOR, 0x64, 0x00, 0x00},
+
+	{SENSOR, MT9M111_SC_ROWSTART, 0x00, 0x0d}, /* 13 */
+	{SENSOR, MT9M111_SC_COLSTART, 0x00, 0x12}, /* 18 */
+	{SENSOR, MT9M111_SC_WINDOW_HEIGHT, 0x04, 0x00}, /* 1024 */
+	{SENSOR, MT9M111_SC_WINDOW_WIDTH, 0x05, 0x10}, /* 1296 */
+	{SENSOR, MT9M111_SC_HBLANK_CONTEXT_B, 0x01, 0x60}, /* 352 */
+	{SENSOR, MT9M111_SC_VBLANK_CONTEXT_B, 0x00, 0x11}, /* 17 */
+	{SENSOR, MT9M111_SC_HBLANK_CONTEXT_A, 0x01, 0x60}, /* 352 */
+	{SENSOR, MT9M111_SC_VBLANK_CONTEXT_A, 0x00, 0x11}, /* 17 */
+	{SENSOR, MT9M111_SC_R_MODE_CONTEXT_A, 0x01, 0x0f}, /* 271 */
+	{SENSOR, 0x30, 0x04, 0x00},
+	/* Set number of blank rows chosen to 400 */
+	{SENSOR, MT9M111_SC_SHUTTER_WIDTH, 0x01, 0x90},
+};
+
+static const unsigned char start_mt9m111[][4] = {
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
+	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
+	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+};
+
 static struct v4l2_pix_format mt9m111_modes[] = {
 	{
 		640,
diff --git a/drivers/media/usb/gspca/m5602/m5602_mt9m111.h b/drivers/media/usb/gspca/m5602/m5602_mt9m111.h
index 07448d35e3cd..781a16311822 100644
--- a/drivers/media/usb/gspca/m5602/m5602_mt9m111.h
+++ b/drivers/media/usb/gspca/m5602/m5602_mt9m111.h
@@ -126,148 +126,4 @@ static const struct m5602_sensor mt9m111 = {
 	.disconnect = mt9m111_disconnect,
 	.start = mt9m111_start,
 };
-
-static const unsigned char preinit_mt9m111[][4] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
-
-	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00},
-	{SENSOR, MT9M111_SC_RESET,
-		MT9M111_RESET |
-		MT9M111_RESTART |
-		MT9M111_ANALOG_STANDBY |
-		MT9M111_CHIP_DISABLE,
-		MT9M111_SHOW_BAD_FRAMES |
-		MT9M111_RESTART_BAD_FRAMES |
-		MT9M111_SYNCHRONIZE_CHANGES},
-
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3e, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3e, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
-
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x07, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x0b, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
-
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a, 0x00}
-};
-
-static const unsigned char init_mt9m111[][4] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
-
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3e, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x07, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x0b, 0x00},
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a, 0x00},
-
-	{SENSOR, MT9M111_SC_RESET, 0x00, 0x29},
-	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00},
-	{SENSOR, MT9M111_SC_RESET, 0x00, 0x08},
-	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x01},
-	{SENSOR, MT9M111_CP_OPERATING_MODE_CTL, 0x00,
-			MT9M111_CP_OPERATING_MODE_CTL},
-	{SENSOR, MT9M111_CP_LENS_CORRECTION_1, 0x04, 0x2a},
-	{SENSOR, MT9M111_CP_DEFECT_CORR_CONTEXT_A, 0x00,
-				MT9M111_2D_DEFECT_CORRECTION_ENABLE},
-	{SENSOR, MT9M111_CP_DEFECT_CORR_CONTEXT_B, 0x00,
-				MT9M111_2D_DEFECT_CORRECTION_ENABLE},
-	{SENSOR, MT9M111_CP_LUMA_OFFSET, 0x00, 0x00},
-	{SENSOR, MT9M111_CP_LUMA_CLIP, 0xff, 0x00},
-	{SENSOR, MT9M111_CP_OUTPUT_FORMAT_CTL2_CONTEXT_A, 0x14, 0x00},
-	{SENSOR, MT9M111_CP_OUTPUT_FORMAT_CTL2_CONTEXT_B, 0x14, 0x00},
-	{SENSOR, 0xcd, 0x00, 0x0e},
-	{SENSOR, 0xd0, 0x00, 0x40},
-
-	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x02},
-	{SENSOR, MT9M111_CC_AUTO_EXPOSURE_PARAMETER_18, 0x00, 0x00},
-	{SENSOR, MT9M111_CC_AWB_PARAMETER_7, 0xef, 0x03},
-
-	{SENSOR, MT9M111_PAGE_MAP, 0x00, 0x00},
-	{SENSOR, 0x33, 0x03, 0x49},
-	{SENSOR, 0x34, 0xc0, 0x19},
-	{SENSOR, 0x3f, 0x20, 0x20},
-	{SENSOR, 0x40, 0x20, 0x20},
-	{SENSOR, 0x5a, 0xc0, 0x0a},
-	{SENSOR, 0x70, 0x7b, 0x0a},
-	{SENSOR, 0x71, 0xff, 0x00},
-	{SENSOR, 0x72, 0x19, 0x0e},
-	{SENSOR, 0x73, 0x18, 0x0f},
-	{SENSOR, 0x74, 0x57, 0x32},
-	{SENSOR, 0x75, 0x56, 0x34},
-	{SENSOR, 0x76, 0x73, 0x35},
-	{SENSOR, 0x77, 0x30, 0x12},
-	{SENSOR, 0x78, 0x79, 0x02},
-	{SENSOR, 0x79, 0x75, 0x06},
-	{SENSOR, 0x7a, 0x77, 0x0a},
-	{SENSOR, 0x7b, 0x78, 0x09},
-	{SENSOR, 0x7c, 0x7d, 0x06},
-	{SENSOR, 0x7d, 0x31, 0x10},
-	{SENSOR, 0x7e, 0x00, 0x7e},
-	{SENSOR, 0x80, 0x59, 0x04},
-	{SENSOR, 0x81, 0x59, 0x04},
-	{SENSOR, 0x82, 0x57, 0x0a},
-	{SENSOR, 0x83, 0x58, 0x0b},
-	{SENSOR, 0x84, 0x47, 0x0c},
-	{SENSOR, 0x85, 0x48, 0x0e},
-	{SENSOR, 0x86, 0x5b, 0x02},
-	{SENSOR, 0x87, 0x00, 0x5c},
-	{SENSOR, MT9M111_CONTEXT_CONTROL, 0x00, MT9M111_SEL_CONTEXT_B},
-	{SENSOR, 0x60, 0x00, 0x80},
-	{SENSOR, 0x61, 0x00, 0x00},
-	{SENSOR, 0x62, 0x00, 0x00},
-	{SENSOR, 0x63, 0x00, 0x00},
-	{SENSOR, 0x64, 0x00, 0x00},
-
-	{SENSOR, MT9M111_SC_ROWSTART, 0x00, 0x0d}, /* 13 */
-	{SENSOR, MT9M111_SC_COLSTART, 0x00, 0x12}, /* 18 */
-	{SENSOR, MT9M111_SC_WINDOW_HEIGHT, 0x04, 0x00}, /* 1024 */
-	{SENSOR, MT9M111_SC_WINDOW_WIDTH, 0x05, 0x10}, /* 1296 */
-	{SENSOR, MT9M111_SC_HBLANK_CONTEXT_B, 0x01, 0x60}, /* 352 */
-	{SENSOR, MT9M111_SC_VBLANK_CONTEXT_B, 0x00, 0x11}, /* 17 */
-	{SENSOR, MT9M111_SC_HBLANK_CONTEXT_A, 0x01, 0x60}, /* 352 */
-	{SENSOR, MT9M111_SC_VBLANK_CONTEXT_A, 0x00, 0x11}, /* 17 */
-	{SENSOR, MT9M111_SC_R_MODE_CONTEXT_A, 0x01, 0x0f}, /* 271 */
-	{SENSOR, 0x30, 0x04, 0x00},
-	/* Set number of blank rows chosen to 400 */
-	{SENSOR, MT9M111_SC_SHUTTER_WIDTH, 0x01, 0x90},
-};
-
-static const unsigned char start_mt9m111[][4] = {
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
-	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
-	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-};
 #endif
diff --git a/drivers/media/usb/gspca/m5602/m5602_ov7660.c b/drivers/media/usb/gspca/m5602/m5602_ov7660.c
index 64b3b03a9141..672b7a520695 100644
--- a/drivers/media/usb/gspca/m5602/m5602_ov7660.c
+++ b/drivers/media/usb/gspca/m5602/m5602_ov7660.c
@@ -23,6 +23,159 @@
 static int ov7660_s_ctrl(struct v4l2_ctrl *ctrl);
 static void ov7660_dump_registers(struct sd *sd);
 
+static const unsigned char preinit_ov7660[][4] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x03},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x03},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+
+	{SENSOR, OV7660_OFON, 0x0c},
+	{SENSOR, OV7660_COM2, 0x11},
+	{SENSOR, OV7660_COM7, 0x05},
+
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00}
+};
+
+static const unsigned char init_ov7660[][4] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
+	{SENSOR, OV7660_COM7, 0x80},
+	{SENSOR, OV7660_CLKRC, 0x80},
+	{SENSOR, OV7660_COM9, 0x4c},
+	{SENSOR, OV7660_OFON, 0x43},
+	{SENSOR, OV7660_COM12, 0x28},
+	{SENSOR, OV7660_COM8, 0x00},
+	{SENSOR, OV7660_COM10, 0x40},
+	{SENSOR, OV7660_HSTART, 0x0c},
+	{SENSOR, OV7660_HSTOP, 0x61},
+	{SENSOR, OV7660_HREF, 0xa4},
+	{SENSOR, OV7660_PSHFT, 0x0b},
+	{SENSOR, OV7660_VSTART, 0x01},
+	{SENSOR, OV7660_VSTOP, 0x7a},
+	{SENSOR, OV7660_VSTOP, 0x00},
+	{SENSOR, OV7660_COM7, 0x05},
+	{SENSOR, OV7660_COM6, 0x42},
+	{SENSOR, OV7660_BBIAS, 0x94},
+	{SENSOR, OV7660_GbBIAS, 0x94},
+	{SENSOR, OV7660_RSVD29, 0x94},
+	{SENSOR, OV7660_RBIAS, 0x94},
+	{SENSOR, OV7660_COM1, 0x00},
+	{SENSOR, OV7660_AECH, 0x00},
+	{SENSOR, OV7660_AECHH, 0x00},
+	{SENSOR, OV7660_ADC, 0x05},
+	{SENSOR, OV7660_COM13, 0x00},
+	{SENSOR, OV7660_RSVDA1, 0x23},
+	{SENSOR, OV7660_TSLB, 0x0d},
+	{SENSOR, OV7660_HV, 0x80},
+	{SENSOR, OV7660_LCC1, 0x00},
+	{SENSOR, OV7660_LCC2, 0x00},
+	{SENSOR, OV7660_LCC3, 0x10},
+	{SENSOR, OV7660_LCC4, 0x40},
+	{SENSOR, OV7660_LCC5, 0x01},
+
+	{SENSOR, OV7660_AECH, 0x20},
+	{SENSOR, OV7660_COM1, 0x00},
+	{SENSOR, OV7660_OFON, 0x0c},
+	{SENSOR, OV7660_COM2, 0x11},
+	{SENSOR, OV7660_COM7, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
+	{SENSOR, OV7660_AECH, 0x5f},
+	{SENSOR, OV7660_COM1, 0x03},
+	{SENSOR, OV7660_OFON, 0x0c},
+	{SENSOR, OV7660_COM2, 0x11},
+	{SENSOR, OV7660_COM7, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
+
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81},
+	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82},
+	{BRIDGE, M5602_XB_SIG_INI, 0x01},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x08},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x01},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0xec},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x02},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x27},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x02},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0xa7},
+	{BRIDGE, M5602_XB_SIG_INI, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+};
+
 static struct v4l2_pix_format ov7660_modes[] = {
 	{
 		640,
diff --git a/drivers/media/usb/gspca/m5602/m5602_ov7660.h b/drivers/media/usb/gspca/m5602/m5602_ov7660.h
index 6fece1ce1232..72445d5df195 100644
--- a/drivers/media/usb/gspca/m5602/m5602_ov7660.h
+++ b/drivers/media/usb/gspca/m5602/m5602_ov7660.h
@@ -107,157 +107,4 @@ static const struct m5602_sensor ov7660 = {
 	.stop = ov7660_stop,
 	.disconnect = ov7660_disconnect,
 };
-
-static const unsigned char preinit_ov7660[][4] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x03},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x03},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-
-	{SENSOR, OV7660_OFON, 0x0c},
-	{SENSOR, OV7660_COM2, 0x11},
-	{SENSOR, OV7660_COM7, 0x05},
-
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00}
-};
-
-static const unsigned char init_ov7660[][4] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
-	{SENSOR, OV7660_COM7, 0x80},
-	{SENSOR, OV7660_CLKRC, 0x80},
-	{SENSOR, OV7660_COM9, 0x4c},
-	{SENSOR, OV7660_OFON, 0x43},
-	{SENSOR, OV7660_COM12, 0x28},
-	{SENSOR, OV7660_COM8, 0x00},
-	{SENSOR, OV7660_COM10, 0x40},
-	{SENSOR, OV7660_HSTART, 0x0c},
-	{SENSOR, OV7660_HSTOP, 0x61},
-	{SENSOR, OV7660_HREF, 0xa4},
-	{SENSOR, OV7660_PSHFT, 0x0b},
-	{SENSOR, OV7660_VSTART, 0x01},
-	{SENSOR, OV7660_VSTOP, 0x7a},
-	{SENSOR, OV7660_VSTOP, 0x00},
-	{SENSOR, OV7660_COM7, 0x05},
-	{SENSOR, OV7660_COM6, 0x42},
-	{SENSOR, OV7660_BBIAS, 0x94},
-	{SENSOR, OV7660_GbBIAS, 0x94},
-	{SENSOR, OV7660_RSVD29, 0x94},
-	{SENSOR, OV7660_RBIAS, 0x94},
-	{SENSOR, OV7660_COM1, 0x00},
-	{SENSOR, OV7660_AECH, 0x00},
-	{SENSOR, OV7660_AECHH, 0x00},
-	{SENSOR, OV7660_ADC, 0x05},
-	{SENSOR, OV7660_COM13, 0x00},
-	{SENSOR, OV7660_RSVDA1, 0x23},
-	{SENSOR, OV7660_TSLB, 0x0d},
-	{SENSOR, OV7660_HV, 0x80},
-	{SENSOR, OV7660_LCC1, 0x00},
-	{SENSOR, OV7660_LCC2, 0x00},
-	{SENSOR, OV7660_LCC3, 0x10},
-	{SENSOR, OV7660_LCC4, 0x40},
-	{SENSOR, OV7660_LCC5, 0x01},
-
-	{SENSOR, OV7660_AECH, 0x20},
-	{SENSOR, OV7660_COM1, 0x00},
-	{SENSOR, OV7660_OFON, 0x0c},
-	{SENSOR, OV7660_COM2, 0x11},
-	{SENSOR, OV7660_COM7, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
-	{SENSOR, OV7660_AECH, 0x5f},
-	{SENSOR, OV7660_COM1, 0x03},
-	{SENSOR, OV7660_OFON, 0x0c},
-	{SENSOR, OV7660_COM2, 0x11},
-	{SENSOR, OV7660_COM7, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x01},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
-
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81},
-	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82},
-	{BRIDGE, M5602_XB_SIG_INI, 0x01},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x08},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x01},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0xec},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x02},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x27},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x02},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0xa7},
-	{BRIDGE, M5602_XB_SIG_INI, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-};
 #endif
diff --git a/drivers/media/usb/gspca/m5602/m5602_ov9650.c b/drivers/media/usb/gspca/m5602/m5602_ov9650.c
index 59bc62bfae26..4544d3a1ad58 100644
--- a/drivers/media/usb/gspca/m5602/m5602_ov9650.c
+++ b/drivers/media/usb/gspca/m5602/m5602_ov9650.c
@@ -1,3 +1,4 @@
+
 /*
  * Driver for the ov9650 sensor
  *
@@ -23,6 +24,157 @@
 static int ov9650_s_ctrl(struct v4l2_ctrl *ctrl);
 static void ov9650_dump_registers(struct sd *sd);
 
+static const unsigned char preinit_ov9650[][3] = {
+	/* [INITCAM] */
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
+
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a},
+	/* Reset chip */
+	{SENSOR, OV9650_COM7, OV9650_REGISTER_RESET},
+	/* Enable double clock */
+	{SENSOR, OV9650_CLKRC, 0x80},
+	/* Do something out of spec with the power */
+	{SENSOR, OV9650_OFON, 0x40}
+};
+
+static const unsigned char init_ov9650[][3] = {
+	/* [INITCAM] */
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
+
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a},
+
+	/* Reset chip */
+	{SENSOR, OV9650_COM7, OV9650_REGISTER_RESET},
+	/* One extra reset is needed in order to make the sensor behave
+	   properly when resuming from ram, could be a timing issue */
+	{SENSOR, OV9650_COM7, OV9650_REGISTER_RESET},
+
+	/* Enable double clock */
+	{SENSOR, OV9650_CLKRC, 0x80},
+	/* Do something out of spec with the power */
+	{SENSOR, OV9650_OFON, 0x40},
+
+	/* Set fast AGC/AEC algorithm with unlimited step size */
+	{SENSOR, OV9650_COM8, OV9650_FAST_AGC_AEC |
+			      OV9650_AEC_UNLIM_STEP_SIZE},
+
+	{SENSOR, OV9650_CHLF, 0x10},
+	{SENSOR, OV9650_ARBLM, 0xbf},
+	{SENSOR, OV9650_ACOM38, 0x81},
+	/* Turn off color matrix coefficient double option */
+	{SENSOR, OV9650_COM16, 0x00},
+	/* Enable color matrix for RGB/YUV, Delay Y channel,
+	set output Y/UV delay to 1 */
+	{SENSOR, OV9650_COM13, 0x19},
+	/* Enable digital BLC, Set output mode to U Y V Y */
+	{SENSOR, OV9650_TSLB, 0x0c},
+	/* Limit the AGC/AEC stable upper region */
+	{SENSOR, OV9650_COM24, 0x00},
+	/* Enable HREF and some out of spec things */
+	{SENSOR, OV9650_COM12, 0x73},
+	/* Set all DBLC offset signs to positive and
+	do some out of spec stuff */
+	{SENSOR, OV9650_DBLC1, 0xdf},
+	{SENSOR, OV9650_COM21, 0x06},
+	{SENSOR, OV9650_RSVD35, 0x91},
+	/* Necessary, no camera stream without it */
+	{SENSOR, OV9650_RSVD16, 0x06},
+	{SENSOR, OV9650_RSVD94, 0x99},
+	{SENSOR, OV9650_RSVD95, 0x99},
+	{SENSOR, OV9650_RSVD96, 0x04},
+	/* Enable full range output */
+	{SENSOR, OV9650_COM15, 0x0},
+	/* Enable HREF at optical black, enable ADBLC bias,
+	enable ADBLC, reset timings at format change */
+	{SENSOR, OV9650_COM6, 0x4b},
+	/* Subtract 32 from the B channel bias */
+	{SENSOR, OV9650_BBIAS, 0xa0},
+	/* Subtract 32 from the Gb channel bias */
+	{SENSOR, OV9650_GbBIAS, 0xa0},
+	/* Do not bypass the analog BLC and to some out of spec stuff */
+	{SENSOR, OV9650_Gr_COM, 0x00},
+	/* Subtract 32 from the R channel bias */
+	{SENSOR, OV9650_RBIAS, 0xa0},
+	/* Subtract 32 from the R channel bias */
+	{SENSOR, OV9650_RBIAS, 0x0},
+	{SENSOR, OV9650_COM26, 0x80},
+	{SENSOR, OV9650_ACOMA9, 0x98},
+	/* Set the AGC/AEC stable region upper limit */
+	{SENSOR, OV9650_AEW, 0x68},
+	/* Set the AGC/AEC stable region lower limit */
+	{SENSOR, OV9650_AEB, 0x5c},
+	/* Set the high and low limit nibbles to 3 */
+	{SENSOR, OV9650_VPT, 0xc3},
+	/* Set the Automatic Gain Ceiling (AGC) to 128x,
+	drop VSYNC at frame drop,
+	limit exposure timing,
+	drop frame when the AEC step is larger than the exposure gap */
+	{SENSOR, OV9650_COM9, 0x6e},
+	/* Set VSYNC negative, Set RESET to SLHS (slave mode horizontal sync)
+	and set PWDN to SLVS (slave mode vertical sync) */
+	{SENSOR, OV9650_COM10, 0x42},
+	/* Set horizontal column start high to default value */
+	{SENSOR, OV9650_HSTART, 0x1a}, /* 210 */
+	/* Set horizontal column end */
+	{SENSOR, OV9650_HSTOP, 0xbf}, /* 1534 */
+	/* Complementing register to the two writes above */
+	{SENSOR, OV9650_HREF, 0xb2},
+	/* Set vertical row start high bits */
+	{SENSOR, OV9650_VSTRT, 0x02},
+	/* Set vertical row end low bits */
+	{SENSOR, OV9650_VSTOP, 0x7e},
+	/* Set complementing vertical frame control */
+	{SENSOR, OV9650_VREF, 0x10},
+	{SENSOR, OV9650_ADC, 0x04},
+	{SENSOR, OV9650_HV, 0x40},
+
+	/* Enable denoise, and white-pixel erase */
+	{SENSOR, OV9650_COM22, OV9650_DENOISE_ENABLE |
+		 OV9650_WHITE_PIXEL_ENABLE |
+		 OV9650_WHITE_PIXEL_OPTION},
+
+	/* Enable VARIOPIXEL */
+	{SENSOR, OV9650_COM3, OV9650_VARIOPIXEL},
+	{SENSOR, OV9650_COM4, OV9650_QVGA_VARIOPIXEL},
+
+	/* Put the sensor in soft sleep mode */
+	{SENSOR, OV9650_COM2, OV9650_SOFT_SLEEP | OV9650_OUTPUT_DRIVE_2X},
+};
+
+static const unsigned char res_init_ov9650[][3] = {
+	{SENSOR, OV9650_COM2, OV9650_OUTPUT_DRIVE_2X},
+
+	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x82},
+	{BRIDGE, M5602_XB_LINE_OF_FRAME_L, 0x00},
+	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82},
+	{BRIDGE, M5602_XB_PIX_OF_LINE_L, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x01}
+};
+
 /* Vertically and horizontally flips the image if matched, needed for machines
    where the sensor is mounted upside down */
 static
diff --git a/drivers/media/usb/gspca/m5602/m5602_ov9650.h b/drivers/media/usb/gspca/m5602/m5602_ov9650.h
index f9f5870da60f..ce3db062c740 100644
--- a/drivers/media/usb/gspca/m5602/m5602_ov9650.h
+++ b/drivers/media/usb/gspca/m5602/m5602_ov9650.h
@@ -156,154 +156,4 @@ static const struct m5602_sensor ov9650 = {
 	.disconnect = ov9650_disconnect,
 };
 
-static const unsigned char preinit_ov9650[][3] = {
-	/* [INITCAM] */
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
-
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a},
-	/* Reset chip */
-	{SENSOR, OV9650_COM7, OV9650_REGISTER_RESET},
-	/* Enable double clock */
-	{SENSOR, OV9650_CLKRC, 0x80},
-	/* Do something out of spec with the power */
-	{SENSOR, OV9650_OFON, 0x40}
-};
-
-static const unsigned char init_ov9650[][3] = {
-	/* [INITCAM] */
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
-
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a},
-
-	/* Reset chip */
-	{SENSOR, OV9650_COM7, OV9650_REGISTER_RESET},
-	/* One extra reset is needed in order to make the sensor behave
-	   properly when resuming from ram, could be a timing issue */
-	{SENSOR, OV9650_COM7, OV9650_REGISTER_RESET},
-
-	/* Enable double clock */
-	{SENSOR, OV9650_CLKRC, 0x80},
-	/* Do something out of spec with the power */
-	{SENSOR, OV9650_OFON, 0x40},
-
-	/* Set fast AGC/AEC algorithm with unlimited step size */
-	{SENSOR, OV9650_COM8, OV9650_FAST_AGC_AEC |
-			      OV9650_AEC_UNLIM_STEP_SIZE},
-
-	{SENSOR, OV9650_CHLF, 0x10},
-	{SENSOR, OV9650_ARBLM, 0xbf},
-	{SENSOR, OV9650_ACOM38, 0x81},
-	/* Turn off color matrix coefficient double option */
-	{SENSOR, OV9650_COM16, 0x00},
-	/* Enable color matrix for RGB/YUV, Delay Y channel,
-	set output Y/UV delay to 1 */
-	{SENSOR, OV9650_COM13, 0x19},
-	/* Enable digital BLC, Set output mode to U Y V Y */
-	{SENSOR, OV9650_TSLB, 0x0c},
-	/* Limit the AGC/AEC stable upper region */
-	{SENSOR, OV9650_COM24, 0x00},
-	/* Enable HREF and some out of spec things */
-	{SENSOR, OV9650_COM12, 0x73},
-	/* Set all DBLC offset signs to positive and
-	do some out of spec stuff */
-	{SENSOR, OV9650_DBLC1, 0xdf},
-	{SENSOR, OV9650_COM21, 0x06},
-	{SENSOR, OV9650_RSVD35, 0x91},
-	/* Necessary, no camera stream without it */
-	{SENSOR, OV9650_RSVD16, 0x06},
-	{SENSOR, OV9650_RSVD94, 0x99},
-	{SENSOR, OV9650_RSVD95, 0x99},
-	{SENSOR, OV9650_RSVD96, 0x04},
-	/* Enable full range output */
-	{SENSOR, OV9650_COM15, 0x0},
-	/* Enable HREF at optical black, enable ADBLC bias,
-	enable ADBLC, reset timings at format change */
-	{SENSOR, OV9650_COM6, 0x4b},
-	/* Subtract 32 from the B channel bias */
-	{SENSOR, OV9650_BBIAS, 0xa0},
-	/* Subtract 32 from the Gb channel bias */
-	{SENSOR, OV9650_GbBIAS, 0xa0},
-	/* Do not bypass the analog BLC and to some out of spec stuff */
-	{SENSOR, OV9650_Gr_COM, 0x00},
-	/* Subtract 32 from the R channel bias */
-	{SENSOR, OV9650_RBIAS, 0xa0},
-	/* Subtract 32 from the R channel bias */
-	{SENSOR, OV9650_RBIAS, 0x0},
-	{SENSOR, OV9650_COM26, 0x80},
-	{SENSOR, OV9650_ACOMA9, 0x98},
-	/* Set the AGC/AEC stable region upper limit */
-	{SENSOR, OV9650_AEW, 0x68},
-	/* Set the AGC/AEC stable region lower limit */
-	{SENSOR, OV9650_AEB, 0x5c},
-	/* Set the high and low limit nibbles to 3 */
-	{SENSOR, OV9650_VPT, 0xc3},
-	/* Set the Automatic Gain Ceiling (AGC) to 128x,
-	drop VSYNC at frame drop,
-	limit exposure timing,
-	drop frame when the AEC step is larger than the exposure gap */
-	{SENSOR, OV9650_COM9, 0x6e},
-	/* Set VSYNC negative, Set RESET to SLHS (slave mode horizontal sync)
-	and set PWDN to SLVS (slave mode vertical sync) */
-	{SENSOR, OV9650_COM10, 0x42},
-	/* Set horizontal column start high to default value */
-	{SENSOR, OV9650_HSTART, 0x1a}, /* 210 */
-	/* Set horizontal column end */
-	{SENSOR, OV9650_HSTOP, 0xbf}, /* 1534 */
-	/* Complementing register to the two writes above */
-	{SENSOR, OV9650_HREF, 0xb2},
-	/* Set vertical row start high bits */
-	{SENSOR, OV9650_VSTRT, 0x02},
-	/* Set vertical row end low bits */
-	{SENSOR, OV9650_VSTOP, 0x7e},
-	/* Set complementing vertical frame control */
-	{SENSOR, OV9650_VREF, 0x10},
-	{SENSOR, OV9650_ADC, 0x04},
-	{SENSOR, OV9650_HV, 0x40},
-
-	/* Enable denoise, and white-pixel erase */
-	{SENSOR, OV9650_COM22, OV9650_DENOISE_ENABLE |
-		 OV9650_WHITE_PIXEL_ENABLE |
-		 OV9650_WHITE_PIXEL_OPTION},
-
-	/* Enable VARIOPIXEL */
-	{SENSOR, OV9650_COM3, OV9650_VARIOPIXEL},
-	{SENSOR, OV9650_COM4, OV9650_QVGA_VARIOPIXEL},
-
-	/* Put the sensor in soft sleep mode */
-	{SENSOR, OV9650_COM2, OV9650_SOFT_SLEEP | OV9650_OUTPUT_DRIVE_2X},
-};
-
-static const unsigned char res_init_ov9650[][3] = {
-	{SENSOR, OV9650_COM2, OV9650_OUTPUT_DRIVE_2X},
-
-	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x82},
-	{BRIDGE, M5602_XB_LINE_OF_FRAME_L, 0x00},
-	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82},
-	{BRIDGE, M5602_XB_PIX_OF_LINE_L, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x01}
-};
 #endif
diff --git a/drivers/media/usb/gspca/m5602/m5602_po1030.c b/drivers/media/usb/gspca/m5602/m5602_po1030.c
index 4bf5c43424b7..a0a90dd34ca8 100644
--- a/drivers/media/usb/gspca/m5602/m5602_po1030.c
+++ b/drivers/media/usb/gspca/m5602/m5602_po1030.c
@@ -23,6 +23,110 @@
 static int po1030_s_ctrl(struct v4l2_ctrl *ctrl);
 static void po1030_dump_registers(struct sd *sd);
 
+static const unsigned char preinit_po1030[][3] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02},
+
+	{SENSOR, PO1030_AUTOCTRL2, PO1030_SENSOR_RESET | (1 << 2)},
+
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x04},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00}
+};
+
+static const unsigned char init_po1030[][3] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
+
+	{SENSOR, PO1030_AUTOCTRL2, PO1030_SENSOR_RESET | (1 << 2)},
+
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x04},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+
+	{SENSOR, PO1030_AUTOCTRL2, 0x04},
+
+	{SENSOR, PO1030_OUTFORMCTRL2, PO1030_RAW_RGB_BAYER},
+	{SENSOR, PO1030_AUTOCTRL1, PO1030_WEIGHT_WIN_2X},
+
+	{SENSOR, PO1030_CONTROL2, 0x03},
+	{SENSOR, 0x21, 0x90},
+	{SENSOR, PO1030_YTARGET, 0x60},
+	{SENSOR, 0x59, 0x13},
+	{SENSOR, PO1030_OUTFORMCTRL1, PO1030_HREF_ENABLE},
+	{SENSOR, PO1030_EDGE_ENH_OFF, 0x00},
+	{SENSOR, PO1030_EGA, 0x80},
+	{SENSOR, 0x78, 0x14},
+	{SENSOR, 0x6f, 0x01},
+	{SENSOR, PO1030_GLOBALGAINMAX, 0x14},
+	{SENSOR, PO1030_Cb_U_GAIN, 0x38},
+	{SENSOR, PO1030_Cr_V_GAIN, 0x38},
+	{SENSOR, PO1030_CONTROL1, PO1030_SHUTTER_MODE |
+				  PO1030_AUTO_SUBSAMPLING |
+				  PO1030_FRAME_EQUAL},
+	{SENSOR, PO1030_GC0, 0x10},
+	{SENSOR, PO1030_GC1, 0x20},
+	{SENSOR, PO1030_GC2, 0x40},
+	{SENSOR, PO1030_GC3, 0x60},
+	{SENSOR, PO1030_GC4, 0x80},
+	{SENSOR, PO1030_GC5, 0xa0},
+	{SENSOR, PO1030_GC6, 0xc0},
+	{SENSOR, PO1030_GC7, 0xff},
+
+	/* Set the width to 751 */
+	{SENSOR, PO1030_FRAMEWIDTH_H, 0x02},
+	{SENSOR, PO1030_FRAMEWIDTH_L, 0xef},
+
+	/* Set the height to 540 */
+	{SENSOR, PO1030_FRAMEHEIGHT_H, 0x02},
+	{SENSOR, PO1030_FRAMEHEIGHT_L, 0x1c},
+
+	/* Set the x window to 1 */
+	{SENSOR, PO1030_WINDOWX_H, 0x00},
+	{SENSOR, PO1030_WINDOWX_L, 0x01},
+
+	/* Set the y window to 1 */
+	{SENSOR, PO1030_WINDOWY_H, 0x00},
+	{SENSOR, PO1030_WINDOWY_L, 0x01},
+
+	/* with a very low lighted environment increase the exposure but
+	 * decrease the FPS (Frame Per Second) */
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
+
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
+};
+
 static struct v4l2_pix_format po1030_modes[] = {
 	{
 		640,
diff --git a/drivers/media/usb/gspca/m5602/m5602_po1030.h b/drivers/media/usb/gspca/m5602/m5602_po1030.h
index a6ab76149bd0..981a91aa7450 100644
--- a/drivers/media/usb/gspca/m5602/m5602_po1030.h
+++ b/drivers/media/usb/gspca/m5602/m5602_po1030.h
@@ -167,108 +167,4 @@ static const struct m5602_sensor po1030 = {
 	.start = po1030_start,
 	.disconnect = po1030_disconnect,
 };
-
-static const unsigned char preinit_po1030[][3] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02},
-
-	{SENSOR, PO1030_AUTOCTRL2, PO1030_SENSOR_RESET | (1 << 2)},
-
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x04},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00}
-};
-
-static const unsigned char init_po1030[][3] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c},
-
-	{SENSOR, PO1030_AUTOCTRL2, PO1030_SENSOR_RESET | (1 << 2)},
-
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x04},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x02},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x04},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-
-	{SENSOR, PO1030_AUTOCTRL2, 0x04},
-
-	{SENSOR, PO1030_OUTFORMCTRL2, PO1030_RAW_RGB_BAYER},
-	{SENSOR, PO1030_AUTOCTRL1, PO1030_WEIGHT_WIN_2X},
-
-	{SENSOR, PO1030_CONTROL2, 0x03},
-	{SENSOR, 0x21, 0x90},
-	{SENSOR, PO1030_YTARGET, 0x60},
-	{SENSOR, 0x59, 0x13},
-	{SENSOR, PO1030_OUTFORMCTRL1, PO1030_HREF_ENABLE},
-	{SENSOR, PO1030_EDGE_ENH_OFF, 0x00},
-	{SENSOR, PO1030_EGA, 0x80},
-	{SENSOR, 0x78, 0x14},
-	{SENSOR, 0x6f, 0x01},
-	{SENSOR, PO1030_GLOBALGAINMAX, 0x14},
-	{SENSOR, PO1030_Cb_U_GAIN, 0x38},
-	{SENSOR, PO1030_Cr_V_GAIN, 0x38},
-	{SENSOR, PO1030_CONTROL1, PO1030_SHUTTER_MODE |
-				  PO1030_AUTO_SUBSAMPLING |
-				  PO1030_FRAME_EQUAL},
-	{SENSOR, PO1030_GC0, 0x10},
-	{SENSOR, PO1030_GC1, 0x20},
-	{SENSOR, PO1030_GC2, 0x40},
-	{SENSOR, PO1030_GC3, 0x60},
-	{SENSOR, PO1030_GC4, 0x80},
-	{SENSOR, PO1030_GC5, 0xa0},
-	{SENSOR, PO1030_GC6, 0xc0},
-	{SENSOR, PO1030_GC7, 0xff},
-
-	/* Set the width to 751 */
-	{SENSOR, PO1030_FRAMEWIDTH_H, 0x02},
-	{SENSOR, PO1030_FRAMEWIDTH_L, 0xef},
-
-	/* Set the height to 540 */
-	{SENSOR, PO1030_FRAMEHEIGHT_H, 0x02},
-	{SENSOR, PO1030_FRAMEHEIGHT_L, 0x1c},
-
-	/* Set the x window to 1 */
-	{SENSOR, PO1030_WINDOWX_H, 0x00},
-	{SENSOR, PO1030_WINDOWX_L, 0x01},
-
-	/* Set the y window to 1 */
-	{SENSOR, PO1030_WINDOWY_H, 0x00},
-	{SENSOR, PO1030_WINDOWY_L, 0x01},
-
-	/* with a very low lighted environment increase the exposure but
-	 * decrease the FPS (Frame Per Second) */
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0},
-
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x05},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00},
-};
 #endif
diff --git a/drivers/media/usb/gspca/m5602/m5602_s5k4aa.c b/drivers/media/usb/gspca/m5602/m5602_s5k4aa.c
index 7d12599458e2..8447b9c5f8e0 100644
--- a/drivers/media/usb/gspca/m5602/m5602_s5k4aa.c
+++ b/drivers/media/usb/gspca/m5602/m5602_s5k4aa.c
@@ -20,6 +20,205 @@
 
 #include "m5602_s5k4aa.h"
 
+static const unsigned char preinit_s5k4aa[][4] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
+
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
+
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x14, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x1c, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
+
+	{SENSOR, S5K4AA_PAGE_MAP, 0x00, 0x00}
+};
+
+static const unsigned char init_s5k4aa[][4] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
+
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
+
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x14, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x1c, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
+
+	{SENSOR, S5K4AA_PAGE_MAP, 0x07, 0x00},
+	{SENSOR, 0x36, 0x01, 0x00},
+	{SENSOR, S5K4AA_PAGE_MAP, 0x00, 0x00},
+	{SENSOR, 0x7b, 0xff, 0x00},
+	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
+	{SENSOR, 0x0c, 0x05, 0x00},
+	{SENSOR, 0x02, 0x0e, 0x00},
+	{SENSOR, S5K4AA_READ_MODE, 0xa0, 0x00},
+	{SENSOR, 0x37, 0x00, 0x00},
+};
+
+static const unsigned char VGA_s5k4aa[][4] = {
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
+	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
+	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	/* VSYNC_PARA, VSYNC_PARA : img height 480 = 0x01e0 */
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x01, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0xe0, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x02, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
+	/* HSYNC_PARA, HSYNC_PARA : img width 640 = 0x0280 */
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x02, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x80, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xa0, 0x00}, /* 48 MHz */
+
+	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
+	{SENSOR, S5K4AA_READ_MODE, S5K4AA_RM_H_FLIP | S5K4AA_RM_ROW_SKIP_2X
+		| S5K4AA_RM_COL_SKIP_2X, 0x00},
+	/* 0x37 : Fix image stability when light is too bright and improves
+	 * image quality in 640x480, but worsens it in 1280x1024 */
+	{SENSOR, 0x37, 0x01, 0x00},
+	/* ROWSTART_HI, ROWSTART_LO : 10 + (1024-960)/2 = 42 = 0x002a */
+	{SENSOR, S5K4AA_ROWSTART_HI, 0x00, 0x00},
+	{SENSOR, S5K4AA_ROWSTART_LO, 0x29, 0x00},
+	{SENSOR, S5K4AA_COLSTART_HI, 0x00, 0x00},
+	{SENSOR, S5K4AA_COLSTART_LO, 0x0c, 0x00},
+	/* window_height_hi, window_height_lo : 960 = 0x03c0 */
+	{SENSOR, S5K4AA_WINDOW_HEIGHT_HI, 0x03, 0x00},
+	{SENSOR, S5K4AA_WINDOW_HEIGHT_LO, 0xc0, 0x00},
+	/* window_width_hi, window_width_lo : 1280 = 0x0500 */
+	{SENSOR, S5K4AA_WINDOW_WIDTH_HI, 0x05, 0x00},
+	{SENSOR, S5K4AA_WINDOW_WIDTH_LO, 0x00, 0x00},
+	{SENSOR, S5K4AA_H_BLANK_HI__, 0x00, 0x00},
+	{SENSOR, S5K4AA_H_BLANK_LO__, 0xa8, 0x00}, /* helps to sync... */
+	{SENSOR, S5K4AA_EXPOSURE_HI, 0x01, 0x00},
+	{SENSOR, S5K4AA_EXPOSURE_LO, 0x00, 0x00},
+	{SENSOR, 0x11, 0x04, 0x00},
+	{SENSOR, 0x12, 0xc3, 0x00},
+	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
+	{SENSOR, 0x02, 0x0e, 0x00},
+};
+
+static const unsigned char SXGA_s5k4aa[][4] = {
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
+	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
+	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	/* VSYNC_PARA, VSYNC_PARA : img height 1024 = 0x0400 */
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x04, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x02, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
+	/* HSYNC_PARA, HSYNC_PARA : img width 1280 = 0x0500 */
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x05, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xa0, 0x00}, /* 48 MHz */
+
+	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
+	{SENSOR, S5K4AA_READ_MODE, S5K4AA_RM_H_FLIP, 0x00},
+	{SENSOR, 0x37, 0x01, 0x00},
+	{SENSOR, S5K4AA_ROWSTART_HI, 0x00, 0x00},
+	{SENSOR, S5K4AA_ROWSTART_LO, 0x09, 0x00},
+	{SENSOR, S5K4AA_COLSTART_HI, 0x00, 0x00},
+	{SENSOR, S5K4AA_COLSTART_LO, 0x0a, 0x00},
+	{SENSOR, S5K4AA_WINDOW_HEIGHT_HI, 0x04, 0x00},
+	{SENSOR, S5K4AA_WINDOW_HEIGHT_LO, 0x00, 0x00},
+	{SENSOR, S5K4AA_WINDOW_WIDTH_HI, 0x05, 0x00},
+	{SENSOR, S5K4AA_WINDOW_WIDTH_LO, 0x00, 0x00},
+	{SENSOR, S5K4AA_H_BLANK_HI__, 0x01, 0x00},
+	{SENSOR, S5K4AA_H_BLANK_LO__, 0xa8, 0x00},
+	{SENSOR, S5K4AA_EXPOSURE_HI, 0x01, 0x00},
+	{SENSOR, S5K4AA_EXPOSURE_LO, 0x00, 0x00},
+	{SENSOR, 0x11, 0x04, 0x00},
+	{SENSOR, 0x12, 0xc3, 0x00},
+	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
+	{SENSOR, 0x02, 0x0e, 0x00},
+};
+
+
 static int s5k4aa_s_ctrl(struct v4l2_ctrl *ctrl);
 static void s5k4aa_dump_registers(struct sd *sd);
 
diff --git a/drivers/media/usb/gspca/m5602/m5602_s5k4aa.h b/drivers/media/usb/gspca/m5602/m5602_s5k4aa.h
index 9953e9766954..8407682d6823 100644
--- a/drivers/media/usb/gspca/m5602/m5602_s5k4aa.h
+++ b/drivers/media/usb/gspca/m5602/m5602_s5k4aa.h
@@ -85,201 +85,4 @@ static const struct m5602_sensor s5k4aa = {
 	.disconnect = s5k4aa_disconnect,
 };
 
-static const unsigned char preinit_s5k4aa[][4] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
-
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
-
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x14, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x1c, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
-
-	{SENSOR, S5K4AA_PAGE_MAP, 0x00, 0x00}
-};
-
-static const unsigned char init_s5k4aa[][4] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
-
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
-
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x14, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x1c, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
-
-	{SENSOR, S5K4AA_PAGE_MAP, 0x07, 0x00},
-	{SENSOR, 0x36, 0x01, 0x00},
-	{SENSOR, S5K4AA_PAGE_MAP, 0x00, 0x00},
-	{SENSOR, 0x7b, 0xff, 0x00},
-	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
-	{SENSOR, 0x0c, 0x05, 0x00},
-	{SENSOR, 0x02, 0x0e, 0x00},
-	{SENSOR, S5K4AA_READ_MODE, 0xa0, 0x00},
-	{SENSOR, 0x37, 0x00, 0x00},
-};
-
-static const unsigned char VGA_s5k4aa[][4] = {
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
-	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
-	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	/* VSYNC_PARA, VSYNC_PARA : img height 480 = 0x01e0 */
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x01, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0xe0, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x02, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
-	/* HSYNC_PARA, HSYNC_PARA : img width 640 = 0x0280 */
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x02, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x80, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xa0, 0x00}, /* 48 MHz */
-
-	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
-	{SENSOR, S5K4AA_READ_MODE, S5K4AA_RM_H_FLIP | S5K4AA_RM_ROW_SKIP_2X
-		| S5K4AA_RM_COL_SKIP_2X, 0x00},
-	/* 0x37 : Fix image stability when light is too bright and improves
-	 * image quality in 640x480, but worsens it in 1280x1024 */
-	{SENSOR, 0x37, 0x01, 0x00},
-	/* ROWSTART_HI, ROWSTART_LO : 10 + (1024-960)/2 = 42 = 0x002a */
-	{SENSOR, S5K4AA_ROWSTART_HI, 0x00, 0x00},
-	{SENSOR, S5K4AA_ROWSTART_LO, 0x29, 0x00},
-	{SENSOR, S5K4AA_COLSTART_HI, 0x00, 0x00},
-	{SENSOR, S5K4AA_COLSTART_LO, 0x0c, 0x00},
-	/* window_height_hi, window_height_lo : 960 = 0x03c0 */
-	{SENSOR, S5K4AA_WINDOW_HEIGHT_HI, 0x03, 0x00},
-	{SENSOR, S5K4AA_WINDOW_HEIGHT_LO, 0xc0, 0x00},
-	/* window_width_hi, window_width_lo : 1280 = 0x0500 */
-	{SENSOR, S5K4AA_WINDOW_WIDTH_HI, 0x05, 0x00},
-	{SENSOR, S5K4AA_WINDOW_WIDTH_LO, 0x00, 0x00},
-	{SENSOR, S5K4AA_H_BLANK_HI__, 0x00, 0x00},
-	{SENSOR, S5K4AA_H_BLANK_LO__, 0xa8, 0x00}, /* helps to sync... */
-	{SENSOR, S5K4AA_EXPOSURE_HI, 0x01, 0x00},
-	{SENSOR, S5K4AA_EXPOSURE_LO, 0x00, 0x00},
-	{SENSOR, 0x11, 0x04, 0x00},
-	{SENSOR, 0x12, 0xc3, 0x00},
-	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
-	{SENSOR, 0x02, 0x0e, 0x00},
-};
-
-static const unsigned char SXGA_s5k4aa[][4] = {
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x08, 0x00},
-	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
-	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	/* VSYNC_PARA, VSYNC_PARA : img height 1024 = 0x0400 */
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x04, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x02, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
-	/* HSYNC_PARA, HSYNC_PARA : img width 1280 = 0x0500 */
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x05, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xa0, 0x00}, /* 48 MHz */
-
-	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
-	{SENSOR, S5K4AA_READ_MODE, S5K4AA_RM_H_FLIP, 0x00},
-	{SENSOR, 0x37, 0x01, 0x00},
-	{SENSOR, S5K4AA_ROWSTART_HI, 0x00, 0x00},
-	{SENSOR, S5K4AA_ROWSTART_LO, 0x09, 0x00},
-	{SENSOR, S5K4AA_COLSTART_HI, 0x00, 0x00},
-	{SENSOR, S5K4AA_COLSTART_LO, 0x0a, 0x00},
-	{SENSOR, S5K4AA_WINDOW_HEIGHT_HI, 0x04, 0x00},
-	{SENSOR, S5K4AA_WINDOW_HEIGHT_LO, 0x00, 0x00},
-	{SENSOR, S5K4AA_WINDOW_WIDTH_HI, 0x05, 0x00},
-	{SENSOR, S5K4AA_WINDOW_WIDTH_LO, 0x00, 0x00},
-	{SENSOR, S5K4AA_H_BLANK_HI__, 0x01, 0x00},
-	{SENSOR, S5K4AA_H_BLANK_LO__, 0xa8, 0x00},
-	{SENSOR, S5K4AA_EXPOSURE_HI, 0x01, 0x00},
-	{SENSOR, S5K4AA_EXPOSURE_LO, 0x00, 0x00},
-	{SENSOR, 0x11, 0x04, 0x00},
-	{SENSOR, 0x12, 0xc3, 0x00},
-	{SENSOR, S5K4AA_PAGE_MAP, 0x02, 0x00},
-	{SENSOR, 0x02, 0x0e, 0x00},
-};
 #endif
diff --git a/drivers/media/usb/gspca/m5602/m5602_s5k83a.c b/drivers/media/usb/gspca/m5602/m5602_s5k83a.c
index bf6b215438e3..be5e25d1a2e8 100644
--- a/drivers/media/usb/gspca/m5602/m5602_s5k83a.c
+++ b/drivers/media/usb/gspca/m5602/m5602_s5k83a.c
@@ -41,6 +41,130 @@ static struct v4l2_pix_format s5k83a_modes[] = {
 	}
 };
 
+static const unsigned char preinit_s5k83a[][4] = {
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
+
+	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x1c, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
+};
+
+/* This could probably be considerably shortened.
+   I don't have the hardware to experiment with it, patches welcome
+*/
+static const unsigned char init_s5k83a[][4] = {
+	/* The following sequence is useless after a clean boot
+	   but is necessary after resume from suspend */
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
+	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
+	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
+	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
+	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
+
+	{SENSOR, S5K83A_PAGE_MAP, 0x04, 0x00},
+	{SENSOR, 0xaf, 0x01, 0x00},
+	{SENSOR, S5K83A_PAGE_MAP, 0x00, 0x00},
+	{SENSOR, 0x7b, 0xff, 0x00},
+	{SENSOR, S5K83A_PAGE_MAP, 0x05, 0x00},
+	{SENSOR, 0x01, 0x50, 0x00},
+	{SENSOR, 0x12, 0x20, 0x00},
+	{SENSOR, 0x17, 0x40, 0x00},
+	{SENSOR, 0x1c, 0x00, 0x00},
+	{SENSOR, 0x02, 0x70, 0x00},
+	{SENSOR, 0x03, 0x0b, 0x00},
+	{SENSOR, 0x04, 0xf0, 0x00},
+	{SENSOR, 0x05, 0x0b, 0x00},
+	{SENSOR, 0x06, 0x71, 0x00},
+	{SENSOR, 0x07, 0xe8, 0x00}, /* 488 */
+	{SENSOR, 0x08, 0x02, 0x00},
+	{SENSOR, 0x09, 0x88, 0x00}, /* 648 */
+	{SENSOR, 0x14, 0x00, 0x00},
+	{SENSOR, 0x15, 0x20, 0x00}, /* 32 */
+	{SENSOR, 0x19, 0x00, 0x00},
+	{SENSOR, 0x1a, 0x98, 0x00}, /* 152 */
+	{SENSOR, 0x0f, 0x02, 0x00},
+	{SENSOR, 0x10, 0xe5, 0x00}, /* 741 */
+	/* normal colors
+	(this is value after boot, but after tries can be different) */
+	{SENSOR, 0x00, 0x06, 0x00},
+};
+
+static const unsigned char start_s5k83a[][4] = {
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
+	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
+	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
+	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x01, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0xe4, 0x00}, /* 484 */
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SIG_INI, 0x02, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x02, 0x00},
+	{BRIDGE, M5602_XB_HSYNC_PARA, 0x7f, 0x00}, /* 639 */
+	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
+	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
+};
+
 static void s5k83a_dump_registers(struct sd *sd);
 static int s5k83a_get_rotation(struct sd *sd, u8 *reg_data);
 static int s5k83a_set_led_indication(struct sd *sd, u8 val);
diff --git a/drivers/media/usb/gspca/m5602/m5602_s5k83a.h b/drivers/media/usb/gspca/m5602/m5602_s5k83a.h
index d61b918228df..3212bfe53d22 100644
--- a/drivers/media/usb/gspca/m5602/m5602_s5k83a.h
+++ b/drivers/media/usb/gspca/m5602/m5602_s5k83a.h
@@ -61,128 +61,4 @@ static const struct m5602_sensor s5k83a = {
 	.i2c_slave_id = 0x5a,
 	.i2c_regW = 2,
 };
-
-static const unsigned char preinit_s5k83a[][4] = {
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_CTRL, 0x00, 0x00},
-
-	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x1c, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
-};
-
-/* This could probably be considerably shortened.
-   I don't have the hardware to experiment with it, patches welcome
-*/
-static const unsigned char init_s5k83a[][4] = {
-	/* The following sequence is useless after a clean boot
-	   but is necessary after resume from suspend */
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x3f, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_L, 0xff, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0x80, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02, 0x00},
-	{BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xf0, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR, 0x1d, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT, 0x08, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DIR_H, 0x06, 0x00},
-	{BRIDGE, M5602_XB_GPIO_DAT_H, 0x00, 0x00},
-	{BRIDGE, M5602_XB_GPIO_EN_L, 0x00, 0x00},
-	{BRIDGE, M5602_XB_I2C_CLK_DIV, 0x20, 0x00},
-
-	{SENSOR, S5K83A_PAGE_MAP, 0x04, 0x00},
-	{SENSOR, 0xaf, 0x01, 0x00},
-	{SENSOR, S5K83A_PAGE_MAP, 0x00, 0x00},
-	{SENSOR, 0x7b, 0xff, 0x00},
-	{SENSOR, S5K83A_PAGE_MAP, 0x05, 0x00},
-	{SENSOR, 0x01, 0x50, 0x00},
-	{SENSOR, 0x12, 0x20, 0x00},
-	{SENSOR, 0x17, 0x40, 0x00},
-	{SENSOR, 0x1c, 0x00, 0x00},
-	{SENSOR, 0x02, 0x70, 0x00},
-	{SENSOR, 0x03, 0x0b, 0x00},
-	{SENSOR, 0x04, 0xf0, 0x00},
-	{SENSOR, 0x05, 0x0b, 0x00},
-	{SENSOR, 0x06, 0x71, 0x00},
-	{SENSOR, 0x07, 0xe8, 0x00}, /* 488 */
-	{SENSOR, 0x08, 0x02, 0x00},
-	{SENSOR, 0x09, 0x88, 0x00}, /* 648 */
-	{SENSOR, 0x14, 0x00, 0x00},
-	{SENSOR, 0x15, 0x20, 0x00}, /* 32 */
-	{SENSOR, 0x19, 0x00, 0x00},
-	{SENSOR, 0x1a, 0x98, 0x00}, /* 152 */
-	{SENSOR, 0x0f, 0x02, 0x00},
-	{SENSOR, 0x10, 0xe5, 0x00}, /* 741 */
-	/* normal colors
-	(this is value after boot, but after tries can be different) */
-	{SENSOR, 0x00, 0x06, 0x00},
-};
-
-static const unsigned char start_s5k83a[][4] = {
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-	{BRIDGE, M5602_XB_ADC_CTRL, 0xc0, 0x00},
-	{BRIDGE, M5602_XB_SENSOR_TYPE, 0x09, 0x00},
-	{BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81, 0x00},
-	{BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x01, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x01, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0xe4, 0x00}, /* 484 */
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_VSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SIG_INI, 0x02, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x00, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x02, 0x00},
-	{BRIDGE, M5602_XB_HSYNC_PARA, 0x7f, 0x00}, /* 639 */
-	{BRIDGE, M5602_XB_SIG_INI, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00, 0x00},
-	{BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0, 0x00},
-};
 #endif
diff --git a/drivers/media/usb/gspca/ov534.c b/drivers/media/usb/gspca/ov534.c
index bfff1d1c70ab..9266a5c9abc5 100644
--- a/drivers/media/usb/gspca/ov534.c
+++ b/drivers/media/usb/gspca/ov534.c
@@ -51,6 +51,7 @@
 #define OV534_OP_READ_2		0xf9
 
 #define CTRL_TIMEOUT 500
+#define DEFAULT_FRAME_RATE 30
 
 MODULE_AUTHOR("Antonio Ospite <ospite@studenti.unina.it>");
 MODULE_DESCRIPTION("GSPCA/OV534 USB Camera Driver");
@@ -1061,7 +1062,7 @@ static int sd_config(struct gspca_dev *gspca_dev,
 	cam->cam_mode = ov772x_mode;
 	cam->nmodes = ARRAY_SIZE(ov772x_mode);
 
-	sd->frame_rate = 30;
+	sd->frame_rate = DEFAULT_FRAME_RATE;
 
 	return 0;
 }
@@ -1492,10 +1493,8 @@ static void sd_set_streamparm(struct gspca_dev *gspca_dev,
 	struct sd *sd = (struct sd *) gspca_dev;
 
 	if (tpf->numerator == 0 || tpf->denominator == 0)
-		/* Set default framerate */
-		sd->frame_rate = 30;
+		sd->frame_rate = DEFAULT_FRAME_RATE;
 	else
-		/* Set requested framerate */
 		sd->frame_rate = tpf->denominator / tpf->numerator;
 
 	if (gspca_dev->streaming)
diff --git a/drivers/media/usb/gspca/sn9c20x.c b/drivers/media/usb/gspca/sn9c20x.c
index d0ee899584a9..10269dad9d20 100644
--- a/drivers/media/usb/gspca/sn9c20x.c
+++ b/drivers/media/usb/gspca/sn9c20x.c
@@ -92,7 +92,6 @@ struct sd {
 	struct v4l2_ctrl *jpegqual;
 
 	struct work_struct work;
-	struct workqueue_struct *work_thread;
 
 	u32 pktsz;			/* (used by pkt_scan) */
 	u16 npkt;
@@ -2051,8 +2050,6 @@ static int sd_start(struct gspca_dev *gspca_dev)
 	if (mode & MODE_JPEG) {
 		sd->pktsz = sd->npkt = 0;
 		sd->nchg = 0;
-		sd->work_thread =
-			create_singlethread_workqueue(KBUILD_MODNAME);
 	}
 
 	return gspca_dev->usb_err;
@@ -2070,12 +2067,9 @@ static void sd_stop0(struct gspca_dev *gspca_dev)
 {
 	struct sd *sd = (struct sd *) gspca_dev;
 
-	if (sd->work_thread != NULL) {
-		mutex_unlock(&gspca_dev->usb_lock);
-		destroy_workqueue(sd->work_thread);
-		mutex_lock(&gspca_dev->usb_lock);
-		sd->work_thread = NULL;
-	}
+	mutex_unlock(&gspca_dev->usb_lock);
+	flush_work(&sd->work);
+	mutex_lock(&gspca_dev->usb_lock);
 }
 
 static void do_autoexposure(struct gspca_dev *gspca_dev, u16 avg_lum)
@@ -2228,7 +2222,7 @@ static void transfer_check(struct gspca_dev *gspca_dev,
 				new_qual = sd->jpegqual->maximum;
 			if (new_qual != curqual) {
 				sd->jpegqual->cur.val = new_qual;
-				queue_work(sd->work_thread, &sd->work);
+				schedule_work(&sd->work);
 			}
 		}
 	} else {
diff --git a/drivers/media/usb/gspca/t613.c b/drivers/media/usb/gspca/t613.c
index e2cc4e5a0ccb..bb52fc1fe598 100644
--- a/drivers/media/usb/gspca/t613.c
+++ b/drivers/media/usb/gspca/t613.c
@@ -837,7 +837,7 @@ static void sd_pkt_scan(struct gspca_dev *gspca_dev,
 			u8 *data,			/* isoc packet */
 			int len)			/* iso packet length */
 {
-	struct sd *sd = (struct sd *) gspca_dev;
+	struct sd *sd __maybe_unused = (struct sd *) gspca_dev;
 	int pkt_type;
 
 	if (data[0] == 0x5a) {
diff --git a/drivers/media/usb/gspca/topro.c b/drivers/media/usb/gspca/topro.c
index c028a5c2438e..15eb069ab60b 100644
--- a/drivers/media/usb/gspca/topro.c
+++ b/drivers/media/usb/gspca/topro.c
@@ -175,6 +175,8 @@ static const u8 jpeg_q[17] = {
 #error "USB buffer too small"
 #endif
 
+#define DEFAULT_FRAME_RATE 30
+
 static const u8 rates[] = {30, 20, 15, 10, 7, 5};
 static const struct framerates framerates[] = {
 	{
@@ -4020,7 +4022,7 @@ static int sd_config(struct gspca_dev *gspca_dev,
 	gspca_dev->cam.mode_framerates = sd->bridge == BRIDGE_TP6800 ?
 			framerates : framerates_6810;
 
-	sd->framerate = 30;		/* default: 30 fps */
+	sd->framerate = DEFAULT_FRAME_RATE;
 	return 0;
 }
 
@@ -4803,7 +4805,7 @@ static void sd_set_streamparm(struct gspca_dev *gspca_dev,
 	int fr, i;
 
 	if (tpf->numerator == 0 || tpf->denominator == 0)
-		sd->framerate = 30;
+		sd->framerate = DEFAULT_FRAME_RATE;
 	else
 		sd->framerate = tpf->denominator / tpf->numerator;
 
diff --git a/drivers/media/usb/gspca/zc3xx.c b/drivers/media/usb/gspca/zc3xx.c
index c5d8ee6fa3c7..5f7254d2bc9a 100644
--- a/drivers/media/usb/gspca/zc3xx.c
+++ b/drivers/media/usb/gspca/zc3xx.c
@@ -53,7 +53,6 @@ struct sd {
 	struct v4l2_ctrl *jpegqual;
 
 	struct work_struct work;
-	struct workqueue_struct *work_thread;
 
 	u8 reg08;		/* webcam compression quality */
 
@@ -6826,8 +6825,7 @@ static int sd_start(struct gspca_dev *gspca_dev)
 		return gspca_dev->usb_err;
 
 	/* Start the transfer parameters update thread */
-	sd->work_thread = create_singlethread_workqueue(KBUILD_MODNAME);
-	queue_work(sd->work_thread, &sd->work);
+	schedule_work(&sd->work);
 
 	return 0;
 }
@@ -6838,12 +6836,9 @@ static void sd_stop0(struct gspca_dev *gspca_dev)
 {
 	struct sd *sd = (struct sd *) gspca_dev;
 
-	if (sd->work_thread != NULL) {
-		mutex_unlock(&gspca_dev->usb_lock);
-		destroy_workqueue(sd->work_thread);
-		mutex_lock(&gspca_dev->usb_lock);
-		sd->work_thread = NULL;
-	}
+	mutex_unlock(&gspca_dev->usb_lock);
+	flush_work(&sd->work);
+	mutex_lock(&gspca_dev->usb_lock);
 	if (!gspca_dev->present)
 		return;
 	send_unknown(gspca_dev, sd->sensor);
diff --git a/drivers/media/usb/hackrf/hackrf.c b/drivers/media/usb/hackrf/hackrf.c
index 9e700caf0d66..b1e229a44192 100644
--- a/drivers/media/usb/hackrf/hackrf.c
+++ b/drivers/media/usb/hackrf/hackrf.c
@@ -760,7 +760,7 @@ static void hackrf_return_all_buffers(struct vb2_queue *vq,
 
 static int hackrf_queue_setup(struct vb2_queue *vq,
 		unsigned int *nbuffers,
-		unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
+		unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct hackrf_dev *dev = vb2_get_drv_priv(vq);
 
diff --git a/drivers/media/usb/hdpvr/hdpvr-core.c b/drivers/media/usb/hdpvr/hdpvr-core.c
index 08f0ca7aa012..a61d8fd63c12 100644
--- a/drivers/media/usb/hdpvr/hdpvr-core.c
+++ b/drivers/media/usb/hdpvr/hdpvr-core.c
@@ -310,10 +310,6 @@ static int hdpvr_probe(struct usb_interface *interface,
 	init_waitqueue_head(&dev->wait_buffer);
 	init_waitqueue_head(&dev->wait_data);
 
-	dev->workqueue = create_singlethread_workqueue("hdpvr_buffer");
-	if (!dev->workqueue)
-		goto error;
-
 	dev->options = hdpvr_default_options;
 
 	if (default_video_input < HDPVR_VIDEO_INPUTS)
@@ -404,9 +400,7 @@ reg_fail:
 #endif
 error:
 	if (dev) {
-		/* Destroy single thread */
-		if (dev->workqueue)
-			destroy_workqueue(dev->workqueue);
+		flush_work(&dev->worker);
 		/* this frees allocated memory */
 		hdpvr_delete(dev);
 	}
@@ -427,7 +421,7 @@ static void hdpvr_disconnect(struct usb_interface *interface)
 	mutex_unlock(&dev->io_mutex);
 	v4l2_device_disconnect(&dev->v4l2_dev);
 	msleep(100);
-	flush_workqueue(dev->workqueue);
+	flush_work(&dev->worker);
 	mutex_lock(&dev->io_mutex);
 	hdpvr_cancel_queue(dev);
 	mutex_unlock(&dev->io_mutex);
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index ba7f02270c83..2a3a8b470555 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -316,7 +316,7 @@ static int hdpvr_start_streaming(struct hdpvr_device *dev)
 	dev->status = STATUS_STREAMING;
 
 	INIT_WORK(&dev->worker, hdpvr_transmit_buffers);
-	queue_work(dev->workqueue, &dev->worker);
+	schedule_work(&dev->worker);
 
 	v4l2_dbg(MSG_BUFFER, hdpvr_debug, &dev->v4l2_dev,
 			"streaming started\n");
@@ -350,7 +350,7 @@ static int hdpvr_stop_streaming(struct hdpvr_device *dev)
 	wake_up_interruptible(&dev->wait_buffer);
 	msleep(50);
 
-	flush_workqueue(dev->workqueue);
+	flush_work(&dev->worker);
 
 	mutex_lock(&dev->io_mutex);
 	/* kill the still outstanding urbs */
@@ -1123,7 +1123,7 @@ static void hdpvr_device_release(struct video_device *vdev)
 
 	hdpvr_delete(dev);
 	mutex_lock(&dev->io_mutex);
-	destroy_workqueue(dev->workqueue);
+	flush_work(&dev->worker);
 	mutex_unlock(&dev->io_mutex);
 
 	v4l2_device_unregister(&dev->v4l2_dev);
diff --git a/drivers/media/usb/hdpvr/hdpvr.h b/drivers/media/usb/hdpvr/hdpvr.h
index 78e815441f95..a12e0af1d4e1 100644
--- a/drivers/media/usb/hdpvr/hdpvr.h
+++ b/drivers/media/usb/hdpvr/hdpvr.h
@@ -107,8 +107,6 @@ struct hdpvr_device {
 	/* waitqueue for data */
 	wait_queue_head_t	wait_data;
 	/**/
-	struct workqueue_struct	*workqueue;
-	/**/
 	struct work_struct	worker;
 	/* current stream owner */
 	struct v4l2_fh		*owner;
diff --git a/drivers/media/usb/msi2500/msi2500.c b/drivers/media/usb/msi2500/msi2500.c
index 2d33033682af..e7f167d44c61 100644
--- a/drivers/media/usb/msi2500/msi2500.c
+++ b/drivers/media/usb/msi2500/msi2500.c
@@ -618,7 +618,7 @@ static int msi2500_querycap(struct file *file, void *fh,
 static int msi2500_queue_setup(struct vb2_queue *vq,
 			       unsigned int *nbuffers,
 			       unsigned int *nplanes, unsigned int sizes[],
-			       void *alloc_ctxs[])
+			       struct device *alloc_devs[])
 {
 	struct msi2500_dev *dev = vb2_get_drv_priv(vq);
 
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
index 83e9a3eb3859..fe20fe4f2330 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
@@ -2856,11 +2856,15 @@ static void pvr2_subdev_set_control(struct pvr2_hdw *hdw, int id,
 				    const char *name, int val)
 {
 	struct v4l2_control ctrl;
+	struct v4l2_subdev *sd;
+
 	pvr2_trace(PVR2_TRACE_CHIPS, "subdev v4l2 %s=%d", name, val);
 	memset(&ctrl, 0, sizeof(ctrl));
 	ctrl.id = id;
 	ctrl.value = val;
-	v4l2_device_call_all(&hdw->v4l2_dev, 0, core, s_ctrl, &ctrl);
+
+	v4l2_device_for_each_subdev(sd, &hdw->v4l2_dev)
+		v4l2_s_ctrl(NULL, sd->ctrl_handler, &ctrl);
 }
 
 #define PVR2_SUBDEV_SET_CONTROL(hdw, id, lab) \
diff --git a/drivers/media/usb/pwc/pwc-if.c b/drivers/media/usb/pwc/pwc-if.c
index 18aed5dd325e..b51b27a3fd61 100644
--- a/drivers/media/usb/pwc/pwc-if.c
+++ b/drivers/media/usb/pwc/pwc-if.c
@@ -573,7 +573,7 @@ static void pwc_video_release(struct v4l2_device *v)
 
 static int queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct pwc_device *pdev = vb2_get_drv_priv(vq);
 	int size;
@@ -1118,8 +1118,10 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id
 
 	return 0;
 
+#ifdef CONFIG_USB_PWC_INPUT_EVDEV
 err_video_unreg:
 	video_unregister_device(&pdev->vdev);
+#endif
 err_unregister_v4l2_dev:
 	v4l2_device_unregister(&pdev->v4l2_dev);
 err_free_controls:
diff --git a/drivers/media/usb/s2255/s2255drv.c b/drivers/media/usb/s2255/s2255drv.c
index 9acdaa3716fb..43ba71a7d02b 100644
--- a/drivers/media/usb/s2255/s2255drv.c
+++ b/drivers/media/usb/s2255/s2255drv.c
@@ -662,7 +662,7 @@ static void s2255_fillbuff(struct s2255_vc *vc,
 
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
-		       unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct s2255_vc *vc = vb2_get_drv_priv(vq);
 	if (*nbuffers < S2255_MIN_BUFS)
diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c
index 77131fd614a5..5fab3bee8c74 100644
--- a/drivers/media/usb/stk1160/stk1160-v4l.c
+++ b/drivers/media/usb/stk1160/stk1160-v4l.c
@@ -666,7 +666,7 @@ static const struct v4l2_ioctl_ops stk1160_ioctl_ops = {
  */
 static int queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
+				unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct stk1160 *dev = vb2_get_drv_priv(vq);
 	unsigned long size;
@@ -680,6 +680,9 @@ static int queue_setup(struct vb2_queue *vq,
 	*nbuffers = clamp_t(unsigned int, *nbuffers,
 			STK1160_MIN_VIDEO_BUFFERS, STK1160_MAX_VIDEO_BUFFERS);
 
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
+
 	/* This means a packed colorformat */
 	*nplanes = 1;
 
diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index 78c12d22dfbb..1965ff1b1f12 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -1,13 +1,6 @@
 /*
- * Fushicai USBTV007 Audio-Video Grabber Driver
- *
- * Product web site:
- * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
- *
  * Copyright (c) 2013 Federico Simoncelli
  * All rights reserved.
- * No physical hardware was harmed running Windows during the
- * reverse-engineering activity
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
@@ -20,6 +13,27 @@
  *
  * Alternatively, this software may be distributed under the terms of the
  * GNU General Public License ("GPL").
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/*
+ * Fushicai USBTV007 Audio-Video Grabber Driver
+ *
+ * Product web site:
+ * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
+ *
+ * No physical hardware was harmed running Windows during the
+ * reverse-engineering activity
  */
 
 #include <sound/core.h>
@@ -278,6 +292,9 @@ static void snd_usbtv_trigger(struct work_struct *work)
 {
 	struct usbtv *chip = container_of(work, struct usbtv, snd_trigger);
 
+	if (!chip->snd)
+		return;
+
 	if (atomic_read(&chip->snd_stream))
 		usbtv_audio_start(chip);
 	else
@@ -378,6 +395,8 @@ err:
 
 void usbtv_audio_free(struct usbtv *usbtv)
 {
+	cancel_work_sync(&usbtv->snd_trigger);
+
 	if (usbtv->snd && usbtv->udev) {
 		snd_card_free(usbtv->snd);
 		usbtv->snd = NULL;
diff --git a/drivers/media/usb/usbtv/usbtv-core.c b/drivers/media/usb/usbtv/usbtv-core.c
index 29428bef272c..dc76fd41e00f 100644
--- a/drivers/media/usb/usbtv/usbtv-core.c
+++ b/drivers/media/usb/usbtv/usbtv-core.c
@@ -1,19 +1,6 @@
 /*
- * Fushicai USBTV007 Audio-Video Grabber Driver
- *
- * Product web site:
- * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
- *
- * Following LWN articles were very useful in construction of this driver:
- * Video4Linux2 API series: http://lwn.net/Articles/203924/
- * videobuf2 API explanation: http://lwn.net/Articles/447435/
- * Thanks go to Jonathan Corbet for providing this quality documentation.
- * He is awesome.
- *
  * Copyright (c) 2013 Lubomir Rintel
  * All rights reserved.
- * No physical hardware was harmed running Windows during the
- * reverse-engineering activity
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
@@ -26,6 +13,33 @@
  *
  * Alternatively, this software may be distributed under the terms of the
  * GNU General Public License ("GPL").
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/*
+ * Fushicai USBTV007 Audio-Video Grabber Driver
+ *
+ * Product web site:
+ * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
+ *
+ * Following LWN articles were very useful in construction of this driver:
+ * Video4Linux2 API series: http://lwn.net/Articles/203924/
+ * videobuf2 API explanation: http://lwn.net/Articles/447435/
+ * Thanks go to Jonathan Corbet for providing this quality documentation.
+ * He is awesome.
+ *
+ * No physical hardware was harmed running Windows during the
+ * reverse-engineering activity
  */
 
 #include "usbtv.h"
diff --git a/drivers/media/usb/usbtv/usbtv-video.c b/drivers/media/usb/usbtv/usbtv-video.c
index f6cfad46547e..2a089756c988 100644
--- a/drivers/media/usb/usbtv/usbtv-video.c
+++ b/drivers/media/usb/usbtv/usbtv-video.c
@@ -1,19 +1,6 @@
 /*
- * Fushicai USBTV007 Audio-Video Grabber Driver
- *
- * Product web site:
- * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
- *
- * Following LWN articles were very useful in construction of this driver:
- * Video4Linux2 API series: http://lwn.net/Articles/203924/
- * videobuf2 API explanation: http://lwn.net/Articles/447435/
- * Thanks go to Jonathan Corbet for providing this quality documentation.
- * He is awesome.
- *
  * Copyright (c) 2013 Lubomir Rintel
  * All rights reserved.
- * No physical hardware was harmed running Windows during the
- * reverse-engineering activity
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
@@ -26,6 +13,33 @@
  *
  * Alternatively, this software may be distributed under the terms of the
  * GNU General Public License ("GPL").
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/*
+ * Fushicai USBTV007 Audio-Video Grabber Driver
+ *
+ * Product web site:
+ * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
+ *
+ * Following LWN articles were very useful in construction of this driver:
+ * Video4Linux2 API series: http://lwn.net/Articles/203924/
+ * videobuf2 API explanation: http://lwn.net/Articles/447435/
+ * Thanks go to Jonathan Corbet for providing this quality documentation.
+ * He is awesome.
+ *
+ * No physical hardware was harmed running Windows during the
+ * reverse-engineering activity
  */
 
 #include <media/v4l2-ioctl.h>
@@ -251,8 +265,23 @@ static int usbtv_setup_capture(struct usbtv *usbtv)
 /* Copy data from chunk into a frame buffer, deinterlacing the data
  * into every second line. Unfortunately, they don't align nicely into
  * 720 pixel lines, as the chunk is 240 words long, which is 480 pixels.
- * Therefore, we break down the chunk into two halves before copyting,
- * so that we can interleave a line if needed. */
+ * Therefore, we break down the chunk into two halves before copying,
+ * so that we can interleave a line if needed.
+ *
+ * Each "chunk" is 240 words; a word in this context equals 4 bytes.
+ * Image format is YUYV/YUV 4:2:2, consisting of Y Cr Y Cb, defining two
+ * pixels, the Cr and Cb shared between the two pixels, but each having
+ * separate Y values. Thus, the 240 words equal 480 pixels. It therefore,
+ * takes 1.5 chunks to make a 720 pixel-wide line for the frame.
+ * The image is interlaced, so there is a "scan" of odd lines, followed
+ * by "scan" of even numbered lines.
+ *
+ * Following code is writing the chunks in correct sequence, skipping
+ * the rows based on "odd" value.
+ * line 1: chunk[0][  0..479] chunk[0][480..959] chunk[1][  0..479]
+ * line 3: chunk[1][480..959] chunk[2][  0..479] chunk[2][480..959]
+ * ...etc.
+ */
 static void usbtv_chunk_to_vbuf(u32 *frame, __be32 *src, int chunk_no, int odd)
 {
 	int half;
@@ -608,7 +637,7 @@ static struct v4l2_file_operations usbtv_fops = {
 
 static int usbtv_queue_setup(struct vb2_queue *vq,
 	unsigned int *nbuffers,
-	unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
+	unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct usbtv *usbtv = vb2_get_drv_priv(vq);
 	unsigned size = USBTV_CHUNK * usbtv->n_chunks * 2 * sizeof(u32);
diff --git a/drivers/media/usb/usbtv/usbtv.h b/drivers/media/usb/usbtv/usbtv.h
index 161b38d5cfa0..011f9fdc77a9 100644
--- a/drivers/media/usb/usbtv/usbtv.h
+++ b/drivers/media/usb/usbtv/usbtv.h
@@ -1,10 +1,6 @@
 /*
- * Fushicai USBTV007 Audio-Video Grabber Driver
- *
  * Copyright (c) 2013 Lubomir Rintel
  * All rights reserved.
- * No physical hardware was harmed running Windows during the
- * reverse-engineering activity
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
@@ -17,6 +13,24 @@
  *
  * Alternatively, this software may be distributed under the terms of the
  * GNU General Public License ("GPL").
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+/*
+ * Fushicai USBTV007 Audio-Video Grabber Driver
+ *
+ * No physical hardware was harmed running Windows during the
+ * reverse-engineering activity
  */
 
 #include <linux/module.h>
diff --git a/drivers/media/usb/usbvision/usbvision-core.c b/drivers/media/usb/usbvision/usbvision-core.c
index 1ea04e75fb36..52ac4391582c 100644
--- a/drivers/media/usb/usbvision/usbvision-core.c
+++ b/drivers/media/usb/usbvision/usbvision-core.c
@@ -88,11 +88,6 @@ MODULE_PARM_DESC(adjust_y_offset, "adjust Y offset display [core]");
 #define DBG_SCRATCH	(1 << 4)
 #define DBG_FUNC	(1 << 5)
 
-static const int max_imgwidth = MAX_FRAME_WIDTH;
-static const int max_imgheight = MAX_FRAME_HEIGHT;
-static const int min_imgwidth = MIN_FRAME_WIDTH;
-static const int min_imgheight = MIN_FRAME_HEIGHT;
-
 /* The value of 'scratch_buf_size' affects quality of the picture
  * in many ways. Shorter buffers may cause loss of data when client
  * is too slow. Larger buffers are memory-consuming and take longer
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c
index ad2f3d27b266..c8b4eb2ee7a2 100644
--- a/drivers/media/usb/usbvision/usbvision-video.c
+++ b/drivers/media/usb/usbvision/usbvision-video.c
@@ -188,12 +188,10 @@ static ssize_t show_hue(struct device *cd,
 {
 	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
-	struct v4l2_control ctrl;
-	ctrl.id = V4L2_CID_HUE;
-	ctrl.value = 0;
-	if (usbvision->user)
-		call_all(usbvision, core, g_ctrl, &ctrl);
-	return sprintf(buf, "%d\n", ctrl.value);
+	s32 val = v4l2_ctrl_g_ctrl(v4l2_ctrl_find(&usbvision->hdl,
+						  V4L2_CID_HUE));
+
+	return sprintf(buf, "%d\n", val);
 }
 static DEVICE_ATTR(hue, S_IRUGO, show_hue, NULL);
 
@@ -202,12 +200,10 @@ static ssize_t show_contrast(struct device *cd,
 {
 	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
-	struct v4l2_control ctrl;
-	ctrl.id = V4L2_CID_CONTRAST;
-	ctrl.value = 0;
-	if (usbvision->user)
-		call_all(usbvision, core, g_ctrl, &ctrl);
-	return sprintf(buf, "%d\n", ctrl.value);
+	s32 val = v4l2_ctrl_g_ctrl(v4l2_ctrl_find(&usbvision->hdl,
+						  V4L2_CID_CONTRAST));
+
+	return sprintf(buf, "%d\n", val);
 }
 static DEVICE_ATTR(contrast, S_IRUGO, show_contrast, NULL);
 
@@ -216,12 +212,10 @@ static ssize_t show_brightness(struct device *cd,
 {
 	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
-	struct v4l2_control ctrl;
-	ctrl.id = V4L2_CID_BRIGHTNESS;
-	ctrl.value = 0;
-	if (usbvision->user)
-		call_all(usbvision, core, g_ctrl, &ctrl);
-	return sprintf(buf, "%d\n", ctrl.value);
+	s32 val = v4l2_ctrl_g_ctrl(v4l2_ctrl_find(&usbvision->hdl,
+						  V4L2_CID_BRIGHTNESS));
+
+	return sprintf(buf, "%d\n", val);
 }
 static DEVICE_ATTR(brightness, S_IRUGO, show_brightness, NULL);
 
@@ -230,12 +224,10 @@ static ssize_t show_saturation(struct device *cd,
 {
 	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
-	struct v4l2_control ctrl;
-	ctrl.id = V4L2_CID_SATURATION;
-	ctrl.value = 0;
-	if (usbvision->user)
-		call_all(usbvision, core, g_ctrl, &ctrl);
-	return sprintf(buf, "%d\n", ctrl.value);
+	s32 val = v4l2_ctrl_g_ctrl(v4l2_ctrl_find(&usbvision->hdl,
+						  V4L2_CID_SATURATION));
+
+	return sprintf(buf, "%d\n", val);
 }
 static DEVICE_ATTR(saturation, S_IRUGO, show_saturation, NULL);
 
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 451e84e962e2..302e284a95eb 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -1674,7 +1674,7 @@ static void uvc_delete(struct uvc_device *dev)
 	if (dev->vdev.dev)
 		v4l2_device_unregister(&dev->vdev);
 #ifdef CONFIG_MEDIA_CONTROLLER
-	if (media_devnode_is_registered(&dev->mdev.devnode))
+	if (media_devnode_is_registered(dev->mdev.devnode))
 		media_device_unregister(&dev->mdev);
 	media_device_cleanup(&dev->mdev);
 #endif
diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c
index 54394722756f..773fefb52d7a 100644
--- a/drivers/media/usb/uvc/uvc_queue.c
+++ b/drivers/media/usb/uvc/uvc_queue.c
@@ -71,7 +71,7 @@ static void uvc_queue_return_buffers(struct uvc_video_queue *queue,
 
 static int uvc_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct uvc_video_queue *queue = vb2_get_drv_priv(vq);
 	struct uvc_streaming *stream = uvc_queue_to_stream(queue);
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index c04bc6afb965..05eed4be25df 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -142,6 +142,21 @@ static __u32 uvc_try_frame_interval(struct uvc_frame *frame, __u32 interval)
 	return interval;
 }
 
+static __u32 uvc_v4l2_get_bytesperline(const struct uvc_format *format,
+	const struct uvc_frame *frame)
+{
+	switch (format->fcc) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_YVU420:
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_M420:
+		return frame->wWidth;
+
+	default:
+		return format->bpp * frame->wWidth / 8;
+	}
+}
+
 static int uvc_v4l2_try_format(struct uvc_streaming *stream,
 	struct v4l2_format *fmt, struct uvc_streaming_control *probe,
 	struct uvc_format **uvc_format, struct uvc_frame **uvc_frame)
@@ -245,7 +260,7 @@ static int uvc_v4l2_try_format(struct uvc_streaming *stream,
 	fmt->fmt.pix.width = frame->wWidth;
 	fmt->fmt.pix.height = frame->wHeight;
 	fmt->fmt.pix.field = V4L2_FIELD_NONE;
-	fmt->fmt.pix.bytesperline = format->bpp * frame->wWidth / 8;
+	fmt->fmt.pix.bytesperline = uvc_v4l2_get_bytesperline(format, frame);
 	fmt->fmt.pix.sizeimage = probe->dwMaxVideoFrameSize;
 	fmt->fmt.pix.colorspace = format->colorspace;
 	fmt->fmt.pix.priv = 0;
@@ -282,7 +297,7 @@ static int uvc_v4l2_get_format(struct uvc_streaming *stream,
 	fmt->fmt.pix.width = frame->wWidth;
 	fmt->fmt.pix.height = frame->wHeight;
 	fmt->fmt.pix.field = V4L2_FIELD_NONE;
-	fmt->fmt.pix.bytesperline = format->bpp * frame->wWidth / 8;
+	fmt->fmt.pix.bytesperline = uvc_v4l2_get_bytesperline(format, frame);
 	fmt->fmt.pix.sizeimage = stream->ctrl.dwMaxVideoFrameSize;
 	fmt->fmt.pix.colorspace = format->colorspace;
 	fmt->fmt.pix.priv = 0;
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 075a0fe77485..b5589d5f5da4 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -1470,6 +1470,7 @@ static unsigned int uvc_endpoint_max_bpi(struct usb_device *dev,
 
 	switch (dev->speed) {
 	case USB_SPEED_SUPER:
+	case USB_SPEED_SUPER_PLUS:
 		return le16_to_cpu(ep->ss_ep_comp.wBytesPerInterval);
 	case USB_SPEED_HIGH:
 		psize = usb_endpoint_maxp(&ep->desc);
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 8b321e0aae62..f7abfad9ad23 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -2606,14 +2606,6 @@ int v4l2_queryctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_queryctrl *qc)
 }
 EXPORT_SYMBOL(v4l2_queryctrl);
 
-int v4l2_subdev_queryctrl(struct v4l2_subdev *sd, struct v4l2_queryctrl *qc)
-{
-	if (qc->id & (V4L2_CTRL_FLAG_NEXT_CTRL | V4L2_CTRL_FLAG_NEXT_COMPOUND))
-		return -EINVAL;
-	return v4l2_queryctrl(sd->ctrl_handler, qc);
-}
-EXPORT_SYMBOL(v4l2_subdev_queryctrl);
-
 /* Implement VIDIOC_QUERYMENU */
 int v4l2_querymenu(struct v4l2_ctrl_handler *hdl, struct v4l2_querymenu *qm)
 {
@@ -2657,13 +2649,6 @@ int v4l2_querymenu(struct v4l2_ctrl_handler *hdl, struct v4l2_querymenu *qm)
 }
 EXPORT_SYMBOL(v4l2_querymenu);
 
-int v4l2_subdev_querymenu(struct v4l2_subdev *sd, struct v4l2_querymenu *qm)
-{
-	return v4l2_querymenu(sd->ctrl_handler, qm);
-}
-EXPORT_SYMBOL(v4l2_subdev_querymenu);
-
-
 
 /* Some general notes on the atomic requirements of VIDIOC_G/TRY/S_EXT_CTRLS:
 
@@ -2890,12 +2875,6 @@ int v4l2_g_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *cs
 }
 EXPORT_SYMBOL(v4l2_g_ext_ctrls);
 
-int v4l2_subdev_g_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs)
-{
-	return v4l2_g_ext_ctrls(sd->ctrl_handler, cs);
-}
-EXPORT_SYMBOL(v4l2_subdev_g_ext_ctrls);
-
 /* Helper function to get a single control */
 static int get_ctrl(struct v4l2_ctrl *ctrl, struct v4l2_ext_control *c)
 {
@@ -2941,12 +2920,6 @@ int v4l2_g_ctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_control *control)
 }
 EXPORT_SYMBOL(v4l2_g_ctrl);
 
-int v4l2_subdev_g_ctrl(struct v4l2_subdev *sd, struct v4l2_control *control)
-{
-	return v4l2_g_ctrl(sd->ctrl_handler, control);
-}
-EXPORT_SYMBOL(v4l2_subdev_g_ctrl);
-
 s32 v4l2_ctrl_g_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct v4l2_ext_control c;
@@ -3194,18 +3167,6 @@ int v4l2_s_ext_ctrls(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl,
 }
 EXPORT_SYMBOL(v4l2_s_ext_ctrls);
 
-int v4l2_subdev_try_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs)
-{
-	return try_set_ext_ctrls(NULL, sd->ctrl_handler, cs, false);
-}
-EXPORT_SYMBOL(v4l2_subdev_try_ext_ctrls);
-
-int v4l2_subdev_s_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs)
-{
-	return try_set_ext_ctrls(NULL, sd->ctrl_handler, cs, true);
-}
-EXPORT_SYMBOL(v4l2_subdev_s_ext_ctrls);
-
 /* Helper function for VIDIOC_S_CTRL compatibility */
 static int set_ctrl(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, u32 ch_flags)
 {
@@ -3268,12 +3229,6 @@ int v4l2_s_ctrl(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl,
 }
 EXPORT_SYMBOL(v4l2_s_ctrl);
 
-int v4l2_subdev_s_ctrl(struct v4l2_subdev *sd, struct v4l2_control *control)
-{
-	return v4l2_s_ctrl(NULL, sd->ctrl_handler, control);
-}
-EXPORT_SYMBOL(v4l2_subdev_s_ctrl);
-
 int __v4l2_ctrl_s_ctrl(struct v4l2_ctrl *ctrl, s32 val)
 {
 	lockdep_assert_held(ctrl->handler->lock);
diff --git a/drivers/media/v4l2-core/v4l2-flash-led-class.c b/drivers/media/v4l2-core/v4l2-flash-led-class.c
index fc5ff8b215f9..ae7544d5469a 100644
--- a/drivers/media/v4l2-core/v4l2-flash-led-class.c
+++ b/drivers/media/v4l2-core/v4l2-flash-led-class.c
@@ -609,14 +609,7 @@ static const struct v4l2_subdev_internal_ops v4l2_flash_subdev_internal_ops = {
 	.close = v4l2_flash_close,
 };
 
-static const struct v4l2_subdev_core_ops v4l2_flash_core_ops = {
-	.queryctrl = v4l2_subdev_queryctrl,
-	.querymenu = v4l2_subdev_querymenu,
-};
-
-static const struct v4l2_subdev_ops v4l2_flash_subdev_ops = {
-	.core = &v4l2_flash_core_ops,
-};
+static const struct v4l2_subdev_ops v4l2_flash_subdev_ops;
 
 struct v4l2_flash *v4l2_flash_init(
 	struct device *dev, struct device_node *of_node,
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 528390f33b53..51a0fa144392 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -2541,14 +2541,14 @@ static struct v4l2_ioctl_info v4l2_ioctls[] = {
 	IOCTL_INFO_FNC(VIDIOC_DBG_S_REGISTER, v4l_dbg_s_register, v4l_print_dbg_register, 0),
 	IOCTL_INFO_FNC(VIDIOC_DBG_G_REGISTER, v4l_dbg_g_register, v4l_print_dbg_register, 0),
 	IOCTL_INFO_FNC(VIDIOC_S_HW_FREQ_SEEK, v4l_s_hw_freq_seek, v4l_print_hw_freq_seek, INFO_FL_PRIO),
-	IOCTL_INFO_STD(VIDIOC_S_DV_TIMINGS, vidioc_s_dv_timings, v4l_print_dv_timings, INFO_FL_PRIO),
+	IOCTL_INFO_STD(VIDIOC_S_DV_TIMINGS, vidioc_s_dv_timings, v4l_print_dv_timings, INFO_FL_PRIO | INFO_FL_CLEAR(v4l2_dv_timings, bt.flags)),
 	IOCTL_INFO_STD(VIDIOC_G_DV_TIMINGS, vidioc_g_dv_timings, v4l_print_dv_timings, 0),
 	IOCTL_INFO_FNC(VIDIOC_DQEVENT, v4l_dqevent, v4l_print_event, 0),
 	IOCTL_INFO_FNC(VIDIOC_SUBSCRIBE_EVENT, v4l_subscribe_event, v4l_print_event_subscription, 0),
 	IOCTL_INFO_FNC(VIDIOC_UNSUBSCRIBE_EVENT, v4l_unsubscribe_event, v4l_print_event_subscription, 0),
 	IOCTL_INFO_FNC(VIDIOC_CREATE_BUFS, v4l_create_bufs, v4l_print_create_buffers, INFO_FL_PRIO | INFO_FL_QUEUE),
 	IOCTL_INFO_FNC(VIDIOC_PREPARE_BUF, v4l_prepare_buf, v4l_print_buffer, INFO_FL_QUEUE),
-	IOCTL_INFO_STD(VIDIOC_ENUM_DV_TIMINGS, vidioc_enum_dv_timings, v4l_print_enum_dv_timings, 0),
+	IOCTL_INFO_STD(VIDIOC_ENUM_DV_TIMINGS, vidioc_enum_dv_timings, v4l_print_enum_dv_timings, INFO_FL_CLEAR(v4l2_enum_dv_timings, pad)),
 	IOCTL_INFO_STD(VIDIOC_QUERY_DV_TIMINGS, vidioc_query_dv_timings, v4l_print_dv_timings, 0),
 	IOCTL_INFO_STD(VIDIOC_DV_TIMINGS_CAP, vidioc_dv_timings_cap, v4l_print_dv_timings_cap, INFO_FL_CLEAR(v4l2_dv_timings_cap, type)),
 	IOCTL_INFO_FNC(VIDIOC_ENUM_FREQ_BANDS, v4l_enum_freq_bands, v4l_print_freq_band, 0),
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 9fbcb67a9ee6..ca8ffeb56d72 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -206,8 +206,9 @@ static int __vb2_buf_mem_alloc(struct vb2_buffer *vb)
 	for (plane = 0; plane < vb->num_planes; ++plane) {
 		unsigned long size = PAGE_ALIGN(vb->planes[plane].length);
 
-		mem_priv = call_ptr_memop(vb, alloc, q->alloc_ctx[plane],
-				      size, dma_dir, q->gfp_flags);
+		mem_priv = call_ptr_memop(vb, alloc,
+				q->alloc_devs[plane] ? : q->dev,
+				q->dma_attrs, size, dma_dir, q->gfp_flags);
 		if (IS_ERR_OR_NULL(mem_priv))
 			goto free;
 
@@ -737,7 +738,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 	 */
 	num_buffers = min_t(unsigned int, *count, VB2_MAX_FRAME);
 	num_buffers = max_t(unsigned int, num_buffers, q->min_buffers_needed);
-	memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
+	memset(q->alloc_devs, 0, sizeof(q->alloc_devs));
 	q->memory = memory;
 
 	/*
@@ -745,7 +746,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 	 * Driver also sets the size and allocator context for each plane.
 	 */
 	ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes,
-		       plane_sizes, q->alloc_ctx);
+		       plane_sizes, q->alloc_devs);
 	if (ret)
 		return ret;
 
@@ -778,7 +779,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 		num_planes = 0;
 
 		ret = call_qop(q, queue_setup, q, &num_buffers,
-			       &num_planes, plane_sizes, q->alloc_ctx);
+			       &num_planes, plane_sizes, q->alloc_devs);
 
 		if (!ret && allocated_buffers < num_buffers)
 			ret = -ENOMEM;
@@ -844,7 +845,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 	}
 
 	if (!q->num_buffers) {
-		memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
+		memset(q->alloc_devs, 0, sizeof(q->alloc_devs));
 		q->memory = memory;
 		q->waiting_for_buffers = !q->is_output;
 	}
@@ -861,7 +862,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 	 * buffer and their sizes are acceptable
 	 */
 	ret = call_qop(q, queue_setup, q, &num_buffers,
-		       &num_planes, plane_sizes, q->alloc_ctx);
+		       &num_planes, plane_sizes, q->alloc_devs);
 	if (ret)
 		return ret;
 
@@ -884,7 +885,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 		 * queue driver has set up
 		 */
 		ret = call_qop(q, queue_setup, q, &num_buffers,
-			       &num_planes, plane_sizes, q->alloc_ctx);
+			       &num_planes, plane_sizes, q->alloc_devs);
 
 		if (!ret && allocated_buffers < num_buffers)
 			ret = -ENOMEM;
@@ -1131,9 +1132,10 @@ static int __qbuf_userptr(struct vb2_buffer *vb, const void *pb)
 		vb->planes[plane].data_offset = 0;
 
 		/* Acquire each plane's memory */
-		mem_priv = call_ptr_memop(vb, get_userptr, q->alloc_ctx[plane],
-				      planes[plane].m.userptr,
-				      planes[plane].length, dma_dir);
+		mem_priv = call_ptr_memop(vb, get_userptr,
+				q->alloc_devs[plane] ? : q->dev,
+				planes[plane].m.userptr,
+				planes[plane].length, dma_dir);
 		if (IS_ERR_OR_NULL(mem_priv)) {
 			dprintk(1, "failed acquiring userspace "
 						"memory for plane %d\n", plane);
@@ -1256,8 +1258,8 @@ static int __qbuf_dmabuf(struct vb2_buffer *vb, const void *pb)
 
 		/* Acquire each plane's memory */
 		mem_priv = call_ptr_memop(vb, attach_dmabuf,
-			q->alloc_ctx[plane], dbuf, planes[plane].length,
-			dma_dir);
+				q->alloc_devs[plane] ? : q->dev,
+				dbuf, planes[plane].length, dma_dir);
 		if (IS_ERR(mem_priv)) {
 			dprintk(1, "failed to attach dmabuf\n");
 			ret = PTR_ERR(mem_priv);
@@ -1648,7 +1650,7 @@ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb,
 			     void *pb, int nonblocking)
 {
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	/*
 	 * Wait for at least one buffer to become available on the done_list.
@@ -1664,10 +1666,12 @@ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb,
 	spin_lock_irqsave(&q->done_lock, flags);
 	*vb = list_first_entry(&q->done_list, struct vb2_buffer, done_entry);
 	/*
-	 * Only remove the buffer from done_list if v4l2_buffer can handle all
-	 * the planes.
+	 * Only remove the buffer from done_list if all planes can be
+	 * handled. Some cases such as V4L2 file I/O and DVB have pb
+	 * == NULL; skip the check then as there's nothing to verify.
 	 */
-	ret = call_bufop(q, verify_planes_array, *vb, pb);
+	if (pb)
+		ret = call_bufop(q, verify_planes_array, *vb, pb);
 	if (!ret)
 		list_del(&(*vb)->done_entry);
 	spin_unlock_irqrestore(&q->done_lock, flags);
@@ -1843,7 +1847,7 @@ static void __vb2_queue_cancel(struct vb2_queue *q)
 	 * Make sure to call buf_finish for any queued buffers. Normally
 	 * that's done in dqbuf, but that's not going to happen when we
 	 * cancel the whole queue. Note: this code belongs here, not in
-	 * __vb2_dqbuf() since in vb2_internal_dqbuf() there is a critical
+	 * __vb2_dqbuf() since in vb2_core_dqbuf() there is a critical
 	 * call to __fill_user_buffer() after buf_finish(). That order can't
 	 * be changed, so we can't move the buf_finish() to __vb2_dqbuf().
 	 */
diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c
index 5361197f3e57..863f658a3fa1 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c
@@ -21,11 +21,6 @@
 #include <media/videobuf2-dma-contig.h>
 #include <media/videobuf2-memops.h>
 
-struct vb2_dc_conf {
-	struct device		*dev;
-	struct dma_attrs	attrs;
-};
-
 struct vb2_dc_buf {
 	struct device			*dev;
 	void				*vaddr;
@@ -140,18 +135,18 @@ static void vb2_dc_put(void *buf_priv)
 	kfree(buf);
 }
 
-static void *vb2_dc_alloc(void *alloc_ctx, unsigned long size,
-			  enum dma_data_direction dma_dir, gfp_t gfp_flags)
+static void *vb2_dc_alloc(struct device *dev, const struct dma_attrs *attrs,
+			  unsigned long size, enum dma_data_direction dma_dir,
+			  gfp_t gfp_flags)
 {
-	struct vb2_dc_conf *conf = alloc_ctx;
-	struct device *dev = conf->dev;
 	struct vb2_dc_buf *buf;
 
 	buf = kzalloc(sizeof *buf, GFP_KERNEL);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 
-	buf->attrs = conf->attrs;
+	if (attrs)
+		buf->attrs = *attrs;
 	buf->cookie = dma_alloc_attrs(dev, size, &buf->dma_addr,
 					GFP_KERNEL | gfp_flags, &buf->attrs);
 	if (!buf->cookie) {
@@ -478,10 +473,9 @@ static inline dma_addr_t vb2_dc_pfn_to_dma(struct device *dev, unsigned long pfn
 }
 #endif
 
-static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr,
+static void *vb2_dc_get_userptr(struct device *dev, unsigned long vaddr,
 	unsigned long size, enum dma_data_direction dma_dir)
 {
-	struct vb2_dc_conf *conf = alloc_ctx;
 	struct vb2_dc_buf *buf;
 	struct frame_vector *vec;
 	unsigned long offset;
@@ -509,7 +503,7 @@ static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr,
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 
-	buf->dev = conf->dev;
+	buf->dev = dev;
 	buf->dma_dir = dma_dir;
 
 	offset = vaddr & ~PAGE_MASK;
@@ -676,10 +670,9 @@ static void vb2_dc_detach_dmabuf(void *mem_priv)
 	kfree(buf);
 }
 
-static void *vb2_dc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
+static void *vb2_dc_attach_dmabuf(struct device *dev, struct dma_buf *dbuf,
 	unsigned long size, enum dma_data_direction dma_dir)
 {
-	struct vb2_dc_conf *conf = alloc_ctx;
 	struct vb2_dc_buf *buf;
 	struct dma_buf_attachment *dba;
 
@@ -690,7 +683,7 @@ static void *vb2_dc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 
-	buf->dev = conf->dev;
+	buf->dev = dev;
 	/* create attachment for the dmabuf with the user device */
 	dba = dma_buf_attach(dbuf, buf->dev);
 	if (IS_ERR(dba)) {
@@ -729,29 +722,58 @@ const struct vb2_mem_ops vb2_dma_contig_memops = {
 };
 EXPORT_SYMBOL_GPL(vb2_dma_contig_memops);
 
-void *vb2_dma_contig_init_ctx_attrs(struct device *dev,
-				    struct dma_attrs *attrs)
+/**
+ * vb2_dma_contig_set_max_seg_size() - configure DMA max segment size
+ * @dev:	device for configuring DMA parameters
+ * @size:	size of DMA max segment size to set
+ *
+ * To allow mapping the scatter-list into a single chunk in the DMA
+ * address space, the device is required to have the DMA max segment
+ * size parameter set to a value larger than the buffer size. Otherwise,
+ * the DMA-mapping subsystem will split the mapping into max segment
+ * size chunks. This function sets the DMA max segment size
+ * parameter to let DMA-mapping map a buffer as a single chunk in DMA
+ * address space.
+ * This code assumes that the DMA-mapping subsystem will merge all
+ * scatterlist segments if this is really possible (for example when
+ * an IOMMU is available and enabled).
+ * Ideally, this parameter should be set by the generic bus code, but it
+ * is left with the default 64KiB value due to historical litmiations in
+ * other subsystems (like limited USB host drivers) and there no good
+ * place to set it to the proper value.
+ * This function should be called from the drivers, which are known to
+ * operate on platforms with IOMMU and provide access to shared buffers
+ * (either USERPTR or DMABUF). This should be done before initializing
+ * videobuf2 queue.
+ */
+int vb2_dma_contig_set_max_seg_size(struct device *dev, unsigned int size)
 {
-	struct vb2_dc_conf *conf;
-
-	conf = kzalloc(sizeof *conf, GFP_KERNEL);
-	if (!conf)
-		return ERR_PTR(-ENOMEM);
-
-	conf->dev = dev;
-	if (attrs)
-		conf->attrs = *attrs;
+	if (!dev->dma_parms) {
+		dev->dma_parms = kzalloc(sizeof(dev->dma_parms), GFP_KERNEL);
+		if (!dev->dma_parms)
+			return -ENOMEM;
+	}
+	if (dma_get_max_seg_size(dev) < size)
+		return dma_set_max_seg_size(dev, size);
 
-	return conf;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(vb2_dma_contig_init_ctx_attrs);
+EXPORT_SYMBOL_GPL(vb2_dma_contig_set_max_seg_size);
 
-void vb2_dma_contig_cleanup_ctx(void *alloc_ctx)
+/*
+ * vb2_dma_contig_clear_max_seg_size() - release resources for DMA parameters
+ * @dev:	device for configuring DMA parameters
+ *
+ * This function releases resources allocated to configure DMA parameters
+ * (see vb2_dma_contig_set_max_seg_size() function). It should be called from
+ * device drivers on driver remove.
+ */
+void vb2_dma_contig_clear_max_seg_size(struct device *dev)
 {
-	if (!IS_ERR_OR_NULL(alloc_ctx))
-		kfree(alloc_ctx);
+	kfree(dev->dma_parms);
+	dev->dma_parms = NULL;
 }
-EXPORT_SYMBOL_GPL(vb2_dma_contig_cleanup_ctx);
+EXPORT_SYMBOL_GPL(vb2_dma_contig_clear_max_seg_size);
 
 MODULE_DESCRIPTION("DMA-contig memory handling routines for videobuf2");
 MODULE_AUTHOR("Pawel Osciak <pawel@osciak.com>");
diff --git a/drivers/media/v4l2-core/videobuf2-dma-sg.c b/drivers/media/v4l2-core/videobuf2-dma-sg.c
index 9985c89f0513..a39db8a6db7a 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-sg.c
@@ -30,10 +30,6 @@ module_param(debug, int, 0644);
 			printk(KERN_DEBUG "vb2-dma-sg: " fmt, ## arg);	\
 	} while (0)
 
-struct vb2_dma_sg_conf {
-	struct device		*dev;
-};
-
 struct vb2_dma_sg_buf {
 	struct device			*dev;
 	void				*vaddr;
@@ -99,10 +95,10 @@ static int vb2_dma_sg_alloc_compacted(struct vb2_dma_sg_buf *buf,
 	return 0;
 }
 
-static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size,
-			      enum dma_data_direction dma_dir, gfp_t gfp_flags)
+static void *vb2_dma_sg_alloc(struct device *dev, const struct dma_attrs *dma_attrs,
+			      unsigned long size, enum dma_data_direction dma_dir,
+			      gfp_t gfp_flags)
 {
-	struct vb2_dma_sg_conf *conf = alloc_ctx;
 	struct vb2_dma_sg_buf *buf;
 	struct sg_table *sgt;
 	int ret;
@@ -111,7 +107,7 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size,
 
 	dma_set_attr(DMA_ATTR_SKIP_CPU_SYNC, &attrs);
 
-	if (WARN_ON(alloc_ctx == NULL))
+	if (WARN_ON(dev == NULL))
 		return NULL;
 	buf = kzalloc(sizeof *buf, GFP_KERNEL);
 	if (!buf)
@@ -140,7 +136,7 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size,
 		goto fail_table_alloc;
 
 	/* Prevent the device from being released while the buffer is used */
-	buf->dev = get_device(conf->dev);
+	buf->dev = get_device(dev);
 
 	sgt = &buf->sg_table;
 	/*
@@ -226,11 +222,10 @@ static void vb2_dma_sg_finish(void *buf_priv)
 	dma_sync_sg_for_cpu(buf->dev, sgt->sgl, sgt->orig_nents, buf->dma_dir);
 }
 
-static void *vb2_dma_sg_get_userptr(void *alloc_ctx, unsigned long vaddr,
+static void *vb2_dma_sg_get_userptr(struct device *dev, unsigned long vaddr,
 				    unsigned long size,
 				    enum dma_data_direction dma_dir)
 {
-	struct vb2_dma_sg_conf *conf = alloc_ctx;
 	struct vb2_dma_sg_buf *buf;
 	struct sg_table *sgt;
 	DEFINE_DMA_ATTRS(attrs);
@@ -242,7 +237,7 @@ static void *vb2_dma_sg_get_userptr(void *alloc_ctx, unsigned long vaddr,
 		return NULL;
 
 	buf->vaddr = NULL;
-	buf->dev = conf->dev;
+	buf->dev = dev;
 	buf->dma_dir = dma_dir;
 	buf->offset = vaddr & ~PAGE_MASK;
 	buf->size = size;
@@ -616,10 +611,9 @@ static void vb2_dma_sg_detach_dmabuf(void *mem_priv)
 	kfree(buf);
 }
 
-static void *vb2_dma_sg_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
+static void *vb2_dma_sg_attach_dmabuf(struct device *dev, struct dma_buf *dbuf,
 	unsigned long size, enum dma_data_direction dma_dir)
 {
-	struct vb2_dma_sg_conf *conf = alloc_ctx;
 	struct vb2_dma_sg_buf *buf;
 	struct dma_buf_attachment *dba;
 
@@ -630,7 +624,7 @@ static void *vb2_dma_sg_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 
-	buf->dev = conf->dev;
+	buf->dev = dev;
 	/* create attachment for the dmabuf with the user device */
 	dba = dma_buf_attach(dbuf, buf->dev);
 	if (IS_ERR(dba)) {
@@ -672,27 +666,6 @@ const struct vb2_mem_ops vb2_dma_sg_memops = {
 };
 EXPORT_SYMBOL_GPL(vb2_dma_sg_memops);
 
-void *vb2_dma_sg_init_ctx(struct device *dev)
-{
-	struct vb2_dma_sg_conf *conf;
-
-	conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-	if (!conf)
-		return ERR_PTR(-ENOMEM);
-
-	conf->dev = dev;
-
-	return conf;
-}
-EXPORT_SYMBOL_GPL(vb2_dma_sg_init_ctx);
-
-void vb2_dma_sg_cleanup_ctx(void *alloc_ctx)
-{
-	if (!IS_ERR_OR_NULL(alloc_ctx))
-		kfree(alloc_ctx);
-}
-EXPORT_SYMBOL_GPL(vb2_dma_sg_cleanup_ctx);
-
 MODULE_DESCRIPTION("dma scatter/gather memory handling routines for videobuf2");
 MODULE_AUTHOR("Andrzej Pietrasiewicz");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c
index 0b1b8c7b6ce5..9cfbb6e4bc28 100644
--- a/drivers/media/v4l2-core/videobuf2-v4l2.c
+++ b/drivers/media/v4l2-core/videobuf2-v4l2.c
@@ -74,6 +74,11 @@ static int __verify_planes_array(struct vb2_buffer *vb, const struct v4l2_buffer
 	return 0;
 }
 
+static int __verify_planes_array_core(struct vb2_buffer *vb, const void *pb)
+{
+	return __verify_planes_array(vb, pb);
+}
+
 /**
  * __verify_length() - Verify that the bytesused value for each plane fits in
  * the plane length and that the data offset doesn't exceed the bytesused value.
@@ -422,7 +427,7 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb,
 	if (V4L2_TYPE_IS_OUTPUT(b->type)) {
 		/*
 		 * For output buffers mask out the timecode flag:
-		 * this will be handled later in vb2_internal_qbuf().
+		 * this will be handled later in vb2_qbuf().
 		 * The 'field' is valid metadata for this output buffer
 		 * and so that needs to be copied here.
 		 */
@@ -437,6 +442,7 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb,
 }
 
 static const struct vb2_buf_ops v4l2_buf_ops = {
+	.verify_planes_array	= __verify_planes_array_core,
 	.fill_user_buffer	= __fill_v4l2_buffer,
 	.fill_vb2_buffer	= __fill_vb2_buffer,
 	.copy_timestamp		= __copy_timestamp,
@@ -580,13 +586,6 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create)
 }
 EXPORT_SYMBOL_GPL(vb2_create_bufs);
 
-static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
-{
-	int ret = vb2_queue_or_prepare_buf(q, b, "qbuf");
-
-	return ret ? ret : vb2_core_qbuf(q, b->index, b);
-}
-
 /**
  * vb2_qbuf() - Queue a buffer from userspace
  * @q:		videobuf2 queue
@@ -606,30 +605,18 @@ static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
  */
 int vb2_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
 {
+	int ret;
+
 	if (vb2_fileio_is_active(q)) {
 		dprintk(1, "file io in progress\n");
 		return -EBUSY;
 	}
 
-	return vb2_internal_qbuf(q, b);
+	ret = vb2_queue_or_prepare_buf(q, b, "qbuf");
+	return ret ? ret : vb2_core_qbuf(q, b->index, b);
 }
 EXPORT_SYMBOL_GPL(vb2_qbuf);
 
-static int vb2_internal_dqbuf(struct vb2_queue *q, struct v4l2_buffer *b,
-		bool nonblocking)
-{
-	int ret;
-
-	if (b->type != q->type) {
-		dprintk(1, "invalid buffer type\n");
-		return -EINVAL;
-	}
-
-	ret = vb2_core_dqbuf(q, NULL, b, nonblocking);
-
-	return ret;
-}
-
 /**
  * vb2_dqbuf() - Dequeue a buffer to the userspace
  * @q:		videobuf2 queue
@@ -653,11 +640,27 @@ static int vb2_internal_dqbuf(struct vb2_queue *q, struct v4l2_buffer *b,
  */
 int vb2_dqbuf(struct vb2_queue *q, struct v4l2_buffer *b, bool nonblocking)
 {
+	int ret;
+
 	if (vb2_fileio_is_active(q)) {
 		dprintk(1, "file io in progress\n");
 		return -EBUSY;
 	}
-	return vb2_internal_dqbuf(q, b, nonblocking);
+
+	if (b->type != q->type) {
+		dprintk(1, "invalid buffer type\n");
+		return -EINVAL;
+	}
+
+	ret = vb2_core_dqbuf(q, NULL, b, nonblocking);
+
+	/*
+	 *  After calling the VIDIOC_DQBUF V4L2_BUF_FLAG_DONE must be
+	 *  cleared.
+	 */
+	b->flags &= ~V4L2_BUF_FLAG_DONE;
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(vb2_dqbuf);
 
diff --git a/drivers/media/v4l2-core/videobuf2-vmalloc.c b/drivers/media/v4l2-core/videobuf2-vmalloc.c
index 1c302743a1fd..7e8a07ed8d82 100644
--- a/drivers/media/v4l2-core/videobuf2-vmalloc.c
+++ b/drivers/media/v4l2-core/videobuf2-vmalloc.c
@@ -33,8 +33,9 @@ struct vb2_vmalloc_buf {
 
 static void vb2_vmalloc_put(void *buf_priv);
 
-static void *vb2_vmalloc_alloc(void *alloc_ctx, unsigned long size,
-			       enum dma_data_direction dma_dir, gfp_t gfp_flags)
+static void *vb2_vmalloc_alloc(struct device *dev, const struct dma_attrs *attrs,
+			       unsigned long size, enum dma_data_direction dma_dir,
+			       gfp_t gfp_flags)
 {
 	struct vb2_vmalloc_buf *buf;
 
@@ -69,7 +70,7 @@ static void vb2_vmalloc_put(void *buf_priv)
 	}
 }
 
-static void *vb2_vmalloc_get_userptr(void *alloc_ctx, unsigned long vaddr,
+static void *vb2_vmalloc_get_userptr(struct device *dev, unsigned long vaddr,
 				     unsigned long size,
 				     enum dma_data_direction dma_dir)
 {
@@ -403,7 +404,7 @@ static void vb2_vmalloc_detach_dmabuf(void *mem_priv)
 	kfree(buf);
 }
 
-static void *vb2_vmalloc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
+static void *vb2_vmalloc_attach_dmabuf(struct device *dev, struct dma_buf *dbuf,
 	unsigned long size, enum dma_data_direction dma_dir)
 {
 	struct vb2_vmalloc_buf *buf;
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 3cd68152ddf8..40bb8ae5853c 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -2002,8 +2002,7 @@ static int msb_bd_getgeo(struct block_device *bdev,
 
 static int msb_prepare_req(struct request_queue *q, struct request *req)
 {
-	if (req->cmd_type != REQ_TYPE_FS &&
-				req->cmd_type != REQ_TYPE_BLOCK_PC) {
+	if (req->cmd_type != REQ_TYPE_FS) {
 		blk_dump_rq_flags(req, "MS unsupported request");
 		return BLKPREP_KILL;
 	}
@@ -2146,7 +2145,6 @@ static int msb_init_disk(struct memstick_dev *card)
 	msb->disk->fops = &msb_bdops;
 	msb->disk->private_data = msb;
 	msb->disk->queue = msb->queue;
-	msb->disk->driverfs_dev = &card->dev;
 	msb->disk->flags |= GENHD_FL_EXT_DEVT;
 
 	capacity = msb->pages_in_block * msb->logical_block_count;
@@ -2163,7 +2161,7 @@ static int msb_init_disk(struct memstick_dev *card)
 		set_disk_ro(msb->disk, 1);
 
 	msb_start(card);
-	add_disk(msb->disk);
+	device_add_disk(&card->dev, msb->disk);
 	dbg("Disk added");
 	return 0;
 
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 0fb27d338811..c1472275fe57 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -829,8 +829,7 @@ static void mspro_block_start(struct memstick_dev *card)
 
 static int mspro_block_prepare_req(struct request_queue *q, struct request *req)
 {
-	if (req->cmd_type != REQ_TYPE_FS &&
-	    req->cmd_type != REQ_TYPE_BLOCK_PC) {
+	if (req->cmd_type != REQ_TYPE_FS) {
 		blk_dump_rq_flags(req, "MSPro unsupported request");
 		return BLKPREP_KILL;
 	}
@@ -1243,7 +1242,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 	msb->usage_count = 1;
 	msb->disk->private_data = msb;
 	msb->disk->queue = msb->queue;
-	msb->disk->driverfs_dev = &card->dev;
 
 	sprintf(msb->disk->disk_name, "mspblk%d", disk_id);
 
@@ -1255,7 +1253,7 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 	set_capacity(msb->disk, capacity);
 	dev_dbg(&card->dev, "capacity set %ld\n", capacity);
 
-	add_disk(msb->disk);
+	device_add_disk(&card->dev, msb->disk);
 	msb->active = 1;
 	return 0;
 
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 1bcf601de5bc..ff031a7735a5 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -852,13 +852,14 @@ config MFD_RK808
 	  including interrupts, RTC, LDO & DCDC regulators, and onkey.
 
 config MFD_RN5T618
-	tristate "Ricoh RN5T5618 PMIC"
+	tristate "Ricoh RN5T567/618 PMIC"
 	depends on I2C
+	depends on OF
 	select MFD_CORE
 	select REGMAP_I2C
 	help
-	  Say yes here to add support for the Ricoh RN5T618 PMIC. This
-	  driver provides common support for accessing the device,
+	  Say yes here to add support for the Ricoh RN5T567 or R5T618 PMIC.
+	  This driver provides common support for accessing the device,
 	  additional drivers must be enabled in order to use the
 	  functionality of the device.
 
diff --git a/drivers/mfd/rn5t618.c b/drivers/mfd/rn5t618.c
index 0ad51d792feb..ee94080e1cbb 100644
--- a/drivers/mfd/rn5t618.c
+++ b/drivers/mfd/rn5t618.c
@@ -2,6 +2,7 @@
  * MFD core driver for Ricoh RN5T618 PMIC
  *
  * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ * Copyright (C) 2016 Toradex AG
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -11,10 +12,13 @@
  * along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/delay.h>
 #include <linux/i2c.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/rn5t618.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/reboot.h>
 #include <linux/regmap.h>
 
 static const struct mfd_cell rn5t618_cells[] = {
@@ -48,28 +52,64 @@ static const struct regmap_config rn5t618_regmap_config = {
 };
 
 static struct rn5t618 *rn5t618_pm_power_off;
+static struct notifier_block rn5t618_restart_handler;
 
-static void rn5t618_power_off(void)
+static void rn5t618_trigger_poweroff_sequence(bool repower)
 {
 	/* disable automatic repower-on */
 	regmap_update_bits(rn5t618_pm_power_off->regmap, RN5T618_REPCNT,
-			   RN5T618_REPCNT_REPWRON, 0);
+			   RN5T618_REPCNT_REPWRON,
+			   repower ? RN5T618_REPCNT_REPWRON : 0);
 	/* start power-off sequence */
 	regmap_update_bits(rn5t618_pm_power_off->regmap, RN5T618_SLPCNT,
 			   RN5T618_SLPCNT_SWPWROFF, RN5T618_SLPCNT_SWPWROFF);
 }
 
+static void rn5t618_power_off(void)
+{
+	rn5t618_trigger_poweroff_sequence(false);
+}
+
+static int rn5t618_restart(struct notifier_block *this,
+			    unsigned long mode, void *cmd)
+{
+	rn5t618_trigger_poweroff_sequence(true);
+
+	/*
+	 * Re-power factor detection on PMIC side is not instant. 1ms
+	 * proved to be enough time until reset takes effect.
+	 */
+	mdelay(1);
+
+	return NOTIFY_DONE;
+}
+
+static const struct of_device_id rn5t618_of_match[] = {
+	{ .compatible = "ricoh,rn5t567", .data = (void *)RN5T567 },
+	{ .compatible = "ricoh,rn5t618", .data = (void *)RN5T618 },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, rn5t618_of_match);
+
 static int rn5t618_i2c_probe(struct i2c_client *i2c,
 			     const struct i2c_device_id *id)
 {
+	const struct of_device_id *of_id;
 	struct rn5t618 *priv;
 	int ret;
 
+	of_id = of_match_device(rn5t618_of_match, &i2c->dev);
+	if (!of_id) {
+		dev_err(&i2c->dev, "Failed to find matching DT ID\n");
+		return -EINVAL;
+	}
+
 	priv = devm_kzalloc(&i2c->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	i2c_set_clientdata(i2c, priv);
+	priv->variant = (long)of_id->data;
 
 	priv->regmap = devm_regmap_init_i2c(i2c, &rn5t618_regmap_config);
 	if (IS_ERR(priv->regmap)) {
@@ -85,9 +125,21 @@ static int rn5t618_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 
-	if (!pm_power_off) {
-		rn5t618_pm_power_off = priv;
-		pm_power_off = rn5t618_power_off;
+	rn5t618_pm_power_off = priv;
+	if (of_device_is_system_power_controller(i2c->dev.of_node)) {
+		if (!pm_power_off)
+			pm_power_off = rn5t618_power_off;
+		else
+			dev_warn(&i2c->dev, "Poweroff callback already assigned\n");
+	}
+
+	rn5t618_restart_handler.notifier_call = rn5t618_restart;
+	rn5t618_restart_handler.priority = 192;
+
+	ret = register_restart_handler(&rn5t618_restart_handler);
+	if (ret) {
+		dev_err(&i2c->dev, "cannot register restart handler, %d\n", ret);
+		return ret;
 	}
 
 	return 0;
@@ -105,12 +157,6 @@ static int rn5t618_i2c_remove(struct i2c_client *i2c)
 	return 0;
 }
 
-static const struct of_device_id rn5t618_of_match[] = {
-	{ .compatible = "ricoh,rn5t618" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, rn5t618_of_match);
-
 static const struct i2c_device_id rn5t618_i2c_id[] = {
 	{ }
 };
@@ -129,5 +175,5 @@ static struct i2c_driver rn5t618_i2c_driver = {
 module_i2c_driver(rn5t618_i2c_driver);
 
 MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
-MODULE_DESCRIPTION("Ricoh RN5T618 MFD driver");
+MODULE_DESCRIPTION("Ricoh RN5T567/618 MFD driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index c5472e3c9231..10b553765ee7 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -93,6 +93,7 @@ static DEFINE_SPINLOCK(mmc_blk_lock);
  */
 struct mmc_blk_data {
 	spinlock_t	lock;
+	struct device	*parent;
 	struct gendisk	*disk;
 	struct mmc_queue queue;
 	struct list_head part;
@@ -1724,8 +1725,8 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req)
 		    !IS_ALIGNED(blk_rq_sectors(next), 8))
 			break;
 
-		if (next->cmd_flags & REQ_DISCARD ||
-		    next->cmd_flags & REQ_FLUSH)
+		if (req_op(next) == REQ_OP_DISCARD ||
+		    req_op(next) == REQ_OP_FLUSH)
 			break;
 
 		if (rq_data_dir(cur) != rq_data_dir(next))
@@ -2150,7 +2151,6 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_card *card = md->queue.card;
 	struct mmc_host *host = card->host;
 	unsigned long flags;
-	unsigned int cmd_flags = req ? req->cmd_flags : 0;
 
 	if (req && !mq->mqrq_prev->req)
 		/* claim host only for the first request */
@@ -2166,15 +2166,17 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	}
 
 	mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
-	if (cmd_flags & REQ_DISCARD) {
+	if (req && req_op(req) == REQ_OP_DISCARD) {
 		/* complete ongoing async transfer before issuing discard */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
-		if (req->cmd_flags & REQ_SECURE)
-			ret = mmc_blk_issue_secdiscard_rq(mq, req);
-		else
-			ret = mmc_blk_issue_discard_rq(mq, req);
-	} else if (cmd_flags & REQ_FLUSH) {
+		ret = mmc_blk_issue_discard_rq(mq, req);
+	} else if (req && req_op(req) == REQ_OP_SECURE_ERASE) {
+		/* complete ongoing async transfer before issuing secure erase*/
+		if (card->host->areq)
+			mmc_blk_issue_rw_rq(mq, NULL);
+		ret = mmc_blk_issue_secdiscard_rq(mq, req);
+	} else if (req && req_op(req) == REQ_OP_FLUSH) {
 		/* complete ongoing async transfer before issuing flush */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
@@ -2190,7 +2192,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 
 out:
 	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
-	     (cmd_flags & MMC_REQ_SPECIAL_MASK))
+	    mmc_req_is_special(req))
 		/*
 		 * Release host when there are no more requests
 		 * and after special request(discard, flush) is done.
@@ -2271,7 +2273,7 @@ again:
 	md->disk->fops = &mmc_bdops;
 	md->disk->private_data = md;
 	md->disk->queue = md->queue.queue;
-	md->disk->driverfs_dev = parent;
+	md->parent = parent;
 	set_disk_ro(md->disk, md->read_only || default_ro);
 	md->disk->flags = GENHD_FL_EXT_DEVT;
 	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
@@ -2459,7 +2461,7 @@ static int mmc_add_disk(struct mmc_blk_data *md)
 	int ret;
 	struct mmc_card *card = md->queue.card;
 
-	add_disk(md->disk);
+	device_add_disk(md->parent, md->disk);
 	md->force_ro.show = force_ro_show;
 	md->force_ro.store = force_ro_store;
 	sysfs_attr_init(&md->force_ro.attr);
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 6f4323c6d653..bf14642a576a 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -33,7 +33,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 	/*
 	 * We only like normal block requests and discards.
 	 */
-	if (req->cmd_type != REQ_TYPE_FS && !(req->cmd_flags & REQ_DISCARD)) {
+	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) {
 		blk_dump_rq_flags(req, "MMC bad request");
 		return BLKPREP_KILL;
 	}
@@ -56,7 +56,6 @@ static int mmc_queue_thread(void *d)
 	down(&mq->thread_sem);
 	do {
 		struct request *req = NULL;
-		unsigned int cmd_flags = 0;
 
 		spin_lock_irq(q->queue_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -66,7 +65,6 @@ static int mmc_queue_thread(void *d)
 
 		if (req || mq->mqrq_prev->req) {
 			set_current_state(TASK_RUNNING);
-			cmd_flags = req ? req->cmd_flags : 0;
 			mq->issue_fn(mq, req);
 			cond_resched();
 			if (mq->flags & MMC_QUEUE_NEW_REQUEST) {
@@ -81,7 +79,7 @@ static int mmc_queue_thread(void *d)
 			 * has been finished. Do not assign it to previous
 			 * request.
 			 */
-			if (cmd_flags & MMC_REQ_SPECIAL_MASK)
+			if (mmc_req_is_special(req))
 				mq->mqrq_cur->req = NULL;
 
 			mq->mqrq_prev->brq.mrq.data = NULL;
@@ -173,7 +171,7 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (card->pref_erase > max_discard)
 		q->limits.discard_granularity = 0;
 	if (mmc_can_secure_erase_trim(card))
-		queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q);
+		queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q);
 }
 
 /**
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 36cddab57d77..d62531124d54 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -1,7 +1,11 @@
 #ifndef MMC_QUEUE_H
 #define MMC_QUEUE_H
 
-#define MMC_REQ_SPECIAL_MASK	(REQ_DISCARD | REQ_FLUSH)
+static inline bool mmc_req_is_special(struct request *req)
+{
+	return req &&
+		(req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD);
+}
 
 struct request;
 struct task_struct;
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 74ae24364a8d..8d58acf33021 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -87,14 +87,14 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	if (req->cmd_type != REQ_TYPE_FS)
 		return -EIO;
 
-	if (req->cmd_flags & REQ_FLUSH)
+	if (req_op(req) == REQ_OP_FLUSH)
 		return tr->flush(dev);
 
 	if (blk_rq_pos(req) + blk_rq_cur_sectors(req) >
 	    get_capacity(req->rq_disk))
 		return -EIO;
 
-	if (req->cmd_flags & REQ_DISCARD)
+	if (req_op(req) == REQ_OP_DISCARD)
 		return tr->discard(dev, block, nsect);
 
 	if (rq_data_dir(req) == READ) {
@@ -431,12 +431,10 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 		goto error4;
 	INIT_WORK(&new->work, mtd_blktrans_work);
 
-	gd->driverfs_dev = &new->mtd->dev;
-
 	if (new->readonly)
 		set_disk_ro(gd, 1);
 
-	add_disk(gd);
+	device_add_disk(&new->mtd->dev, gd);
 
 	if (new->disk_attributes) {
 		ret = sysfs_create_group(&disk_to_dev(gd)->kobj,
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 495e06d9f7e7..7e262ef06ede 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -287,14 +287,13 @@ static int nsblk_attach_disk(struct nd_namespace_blk *nsblk)
 		return -ENOMEM;
 	}
 
-	disk->driverfs_dev	= dev;
 	disk->first_minor	= 0;
 	disk->fops		= &nd_blk_fops;
 	disk->queue		= q;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	nvdimm_namespace_disk_name(&nsblk->common, disk->disk_name);
 	set_capacity(disk, 0);
-	add_disk(disk);
+	device_add_disk(dev, disk);
 
 	if (nsblk_meta_size(nsblk)) {
 		int rc = nd_integrity_init(disk, nsblk_meta_size(nsblk));
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 68a7c3c1eed9..9dce03f420eb 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1243,7 +1243,6 @@ static int btt_blk_init(struct btt *btt)
 	}
 
 	nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
-	btt->btt_disk->driverfs_dev = &btt->nd_btt->dev;
 	btt->btt_disk->first_minor = 0;
 	btt->btt_disk->fops = &btt_fops;
 	btt->btt_disk->private_data = btt;
@@ -1258,7 +1257,7 @@ static int btt_blk_init(struct btt *btt)
 	btt->btt_queue->queuedata = btt;
 
 	set_capacity(btt->btt_disk, 0);
-	add_disk(btt->btt_disk);
+	device_add_disk(&btt->nd_btt->dev, btt->btt_disk);
 	if (btt_meta_size(btt)) {
 		int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt));
 
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index f085f8bceae8..5e4e5c772ea5 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -312,7 +312,7 @@ EXPORT_SYMBOL(__nd_driver_register);
 
 int nvdimm_revalidate_disk(struct gendisk *disk)
 {
-	struct device *dev = disk->driverfs_dev;
+	struct device *dev = disk_to_dev(disk)->parent;
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	const char *pol = nd_region->ro ? "only" : "write";
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 608fc4464574..36cb39047d5b 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -283,6 +283,7 @@ static int pmem_attach_disk(struct device *dev,
 	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, q);
 	q->queuedata = pmem;
 
 	disk = alloc_disk_node(0, nid);
@@ -297,14 +298,13 @@ static int pmem_attach_disk(struct device *dev,
 	disk->queue		= q;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
-	disk->driverfs_dev = dev;
 	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
 			/ 512);
 	if (devm_init_badblocks(dev, &pmem->bb))
 		return -ENOMEM;
 	nvdimm_badblocks_populate(to_nd_region(dev->parent), &pmem->bb, res);
 	disk->bb = &pmem->bb;
-	add_disk(disk);
+	device_add_disk(dev, disk);
 	revalidate_disk(disk);
 
 	return 0;
diff --git a/drivers/nvme/Kconfig b/drivers/nvme/Kconfig
index a39d9431eaec..b7c78a5b1f7a 100644
--- a/drivers/nvme/Kconfig
+++ b/drivers/nvme/Kconfig
@@ -1 +1,2 @@
 source "drivers/nvme/host/Kconfig"
+source "drivers/nvme/target/Kconfig"
diff --git a/drivers/nvme/Makefile b/drivers/nvme/Makefile
index 9421e829d2a9..0096a7fd1431 100644
--- a/drivers/nvme/Makefile
+++ b/drivers/nvme/Makefile
@@ -1,2 +1,3 @@
 
 obj-y		+= host/
+obj-y		+= target/
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index d296fc3ae06e..db39d53cdfb9 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -24,3 +24,22 @@ config BLK_DEV_NVME_SCSI
 	  to say N here, unless you run a distro that abuses the SCSI
 	  emulation to provide stable device names for mount by id, like
 	  some OpenSuSE and SLES versions.
+
+config NVME_FABRICS
+	tristate
+
+config NVME_RDMA
+	tristate "NVM Express over Fabrics RDMA host driver"
+	depends on INFINIBAND
+	depends on BLK_DEV_NVME
+	select NVME_FABRICS
+	select SG_POOL
+	help
+	  This provides support for the NVMe over Fabrics protocol using
+	  the RDMA (Infiniband, RoCE, iWarp) transport.  This allows you
+	  to use remote block devices exported using the NVMe protocol set.
+
+	  To configure a NVMe over Fabrics controller use the nvme-cli tool
+	  from https://github.com/linux-nvme/nvme-cli.
+
+	  If unsure, say N.
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index 9a3ca892b4a7..47abcec23514 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -1,8 +1,14 @@
 obj-$(CONFIG_NVME_CORE)			+= nvme-core.o
 obj-$(CONFIG_BLK_DEV_NVME)		+= nvme.o
+obj-$(CONFIG_NVME_FABRICS)		+= nvme-fabrics.o
+obj-$(CONFIG_NVME_RDMA)			+= nvme-rdma.o
 
 nvme-core-y				:= core.o
 nvme-core-$(CONFIG_BLK_DEV_NVME_SCSI)	+= scsi.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
 
 nvme-y					+= pci.o
+
+nvme-fabrics-y				+= fabrics.o
+
+nvme-rdma-y				+= rdma.o
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d5fb55c0a9d9..7ff2e820bbf4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -30,6 +30,7 @@
 #include <asm/unaligned.h>
 
 #include "nvme.h"
+#include "fabrics.h"
 
 #define NVME_MINORS		(1U << MINORBITS)
 
@@ -47,8 +48,10 @@ unsigned char shutdown_timeout = 5;
 module_param(shutdown_timeout, byte, 0644);
 MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
 
-static int nvme_major;
-module_param(nvme_major, int, 0);
+unsigned int nvme_max_retries = 5;
+module_param_named(max_retries, nvme_max_retries, uint, 0644);
+MODULE_PARM_DESC(max_retries, "max number of retries a command may have");
+EXPORT_SYMBOL_GPL(nvme_max_retries);
 
 static int nvme_char_major;
 module_param(nvme_char_major, int, 0);
@@ -58,6 +61,23 @@ static DEFINE_SPINLOCK(dev_list_lock);
 
 static struct class *nvme_class;
 
+void nvme_cancel_request(struct request *req, void *data, bool reserved)
+{
+	int status;
+
+	if (!blk_mq_request_started(req))
+		return;
+
+	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
+				"Cancelling I/O %d", req->tag);
+
+	status = NVME_SC_ABORT_REQ;
+	if (blk_queue_dying(req->q))
+		status |= NVME_SC_DNR;
+	blk_mq_complete_request(req, status);
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_request);
+
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state)
 {
@@ -68,7 +88,9 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
+		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
+		case NVME_CTRL_RECONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -79,6 +101,16 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
+		case NVME_CTRL_RECONNECTING:
+			changed = true;
+			/* FALLTHRU */
+		default:
+			break;
+		}
+		break;
+	case NVME_CTRL_RECONNECTING:
+		switch (old_state) {
+		case NVME_CTRL_LIVE:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -89,6 +121,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
+		case NVME_CTRL_RECONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -174,21 +207,21 @@ void nvme_requeue_req(struct request *req)
 EXPORT_SYMBOL_GPL(nvme_requeue_req);
 
 struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, unsigned int flags)
+		struct nvme_command *cmd, unsigned int flags, int qid)
 {
-	bool write = cmd->common.opcode & 1;
 	struct request *req;
 
-	req = blk_mq_alloc_request(q, write, flags);
+	if (qid == NVME_QID_ANY) {
+		req = blk_mq_alloc_request(q, nvme_is_write(cmd), flags);
+	} else {
+		req = blk_mq_alloc_request_hctx(q, nvme_is_write(cmd), flags,
+				qid ? qid - 1 : 0);
+	}
 	if (IS_ERR(req))
 		return req;
 
 	req->cmd_type = REQ_TYPE_DRV_PRIV;
 	req->cmd_flags |= REQ_FAILFAST_DRIVER;
-	req->__data_len = 0;
-	req->__sector = (sector_t) -1;
-	req->bio = req->biotail = NULL;
-
 	req->cmd = (unsigned char *)cmd;
 	req->cmd_len = sizeof(struct nvme_command);
 
@@ -290,9 +323,9 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 
 	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
 		memcpy(cmd, req->cmd, sizeof(*cmd));
-	else if (req->cmd_flags & REQ_FLUSH)
+	else if (req_op(req) == REQ_OP_FLUSH)
 		nvme_setup_flush(ns, cmd);
-	else if (req->cmd_flags & REQ_DISCARD)
+	else if (req_op(req) == REQ_OP_DISCARD)
 		ret = nvme_setup_discard(ns, req, cmd);
 	else
 		nvme_setup_rw(ns, req, cmd);
@@ -307,12 +340,12 @@ EXPORT_SYMBOL_GPL(nvme_setup_cmd);
  */
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		struct nvme_completion *cqe, void *buffer, unsigned bufflen,
-		unsigned timeout)
+		unsigned timeout, int qid, int at_head, int flags)
 {
 	struct request *req;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, 0);
+	req = nvme_alloc_request(q, cmd, flags, qid);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -325,17 +358,19 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	blk_execute_rq(req->q, NULL, req, 0);
+	blk_execute_rq(req->q, NULL, req, at_head);
 	ret = req->errors;
  out:
 	blk_mq_free_request(req);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__nvme_submit_sync_cmd);
 
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buffer, unsigned bufflen)
 {
-	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0);
+	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0,
+			NVME_QID_ANY, 0, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
@@ -344,7 +379,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
 		u32 *result, unsigned timeout)
 {
-	bool write = cmd->common.opcode & 1;
+	bool write = nvme_is_write(cmd);
 	struct nvme_completion cqe;
 	struct nvme_ns *ns = q->queuedata;
 	struct gendisk *disk = ns ? ns->disk : NULL;
@@ -353,7 +388,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 	void *meta = NULL;
 	int ret;
 
-	req = nvme_alloc_request(q, cmd, 0);
+	req = nvme_alloc_request(q, cmd, 0, NVME_QID_ANY);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -439,6 +474,74 @@ int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 			result, timeout);
 }
 
+static void nvme_keep_alive_end_io(struct request *rq, int error)
+{
+	struct nvme_ctrl *ctrl = rq->end_io_data;
+
+	blk_mq_free_request(rq);
+
+	if (error) {
+		dev_err(ctrl->device,
+			"failed nvme_keep_alive_end_io error=%d\n", error);
+		return;
+	}
+
+	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+}
+
+static int nvme_keep_alive(struct nvme_ctrl *ctrl)
+{
+	struct nvme_command c;
+	struct request *rq;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = nvme_admin_keep_alive;
+
+	rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED,
+			NVME_QID_ANY);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	rq->timeout = ctrl->kato * HZ;
+	rq->end_io_data = ctrl;
+
+	blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io);
+
+	return 0;
+}
+
+static void nvme_keep_alive_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_ctrl, ka_work);
+
+	if (nvme_keep_alive(ctrl)) {
+		/* allocation failure, reset the controller */
+		dev_err(ctrl->device, "keep-alive failed\n");
+		ctrl->ops->reset_ctrl(ctrl);
+		return;
+	}
+}
+
+void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
+{
+	if (unlikely(ctrl->kato == 0))
+		return;
+
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+}
+EXPORT_SYMBOL_GPL(nvme_start_keep_alive);
+
+void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
+{
+	if (unlikely(ctrl->kato == 0))
+		return;
+
+	cancel_delayed_work_sync(&ctrl->ka_work);
+}
+EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
+
 int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 {
 	struct nvme_command c = { };
@@ -500,10 +603,11 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
 	memset(&c, 0, sizeof(c));
 	c.features.opcode = nvme_admin_get_features;
 	c.features.nsid = cpu_to_le32(nsid);
-	c.features.prp1 = cpu_to_le64(dma_addr);
+	c.features.dptr.prp1 = cpu_to_le64(dma_addr);
 	c.features.fid = cpu_to_le32(fid);
 
-	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0);
+	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
 	if (ret >= 0)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
@@ -518,11 +622,12 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
 
 	memset(&c, 0, sizeof(c));
 	c.features.opcode = nvme_admin_set_features;
-	c.features.prp1 = cpu_to_le64(dma_addr);
+	c.features.dptr.prp1 = cpu_to_le64(dma_addr);
 	c.features.fid = cpu_to_le32(fid);
 	c.features.dword11 = cpu_to_le32(dword11);
 
-	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0);
+	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
 	if (ret >= 0)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
@@ -558,11 +663,22 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 
 	status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, 0,
 			&result);
-	if (status)
+	if (status < 0)
 		return status;
 
-	nr_io_queues = min(result & 0xffff, result >> 16) + 1;
-	*count = min(*count, nr_io_queues);
+	/*
+	 * Degraded controllers might return an error when setting the queue
+	 * count.  We still want to be able to bring them online and offer
+	 * access to the admin queue, as that might be only way to fix them up.
+	 */
+	if (status > 0) {
+		dev_err(ctrl->dev, "Could not set queue count (%d)\n", status);
+		*count = 0;
+	} else {
+		nr_io_queues = min(result & 0xffff, result >> 16) + 1;
+		*count = min(*count, nr_io_queues);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
@@ -726,6 +842,7 @@ static void nvme_init_integrity(struct nvme_ns *ns)
 {
 	struct blk_integrity integrity;
 
+	memset(&integrity, 0, sizeof(integrity));
 	switch (ns->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
 		integrity.profile = &t10_pi_type3_crc;
@@ -764,7 +881,7 @@ static void nvme_config_discard(struct nvme_ns *ns)
 
 	ns->queue->limits.discard_alignment = logical_block_size;
 	ns->queue->limits.discard_granularity = logical_block_size;
-	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
+	blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
@@ -991,6 +1108,15 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap)
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
+
+	/* Checking for ctrl->tagset is a trick to avoid sleeping on module
+	 * load, since we only need the quirk on reset_controller. Notice
+	 * that the HGST device needs this delay only in firmware activation
+	 * procedure; unfortunately we have no (easy) way to verify this.
+	 */
+	if ((ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) && ctrl->tagset)
+		msleep(NVME_QUIRK_DELAY_AMOUNT);
+
 	return nvme_wait_ready(ctrl, cap, false);
 }
 EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
@@ -1088,6 +1214,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	struct nvme_id_ctrl *id;
 	u64 cap;
 	int ret, page_shift;
+	u32 max_hw_sectors;
 
 	ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
 	if (ret) {
@@ -1120,9 +1247,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	memcpy(ctrl->model, id->mn, sizeof(id->mn));
 	memcpy(ctrl->firmware_rev, id->fr, sizeof(id->fr));
 	if (id->mdts)
-		ctrl->max_hw_sectors = 1 << (id->mdts + page_shift - 9);
+		max_hw_sectors = 1 << (id->mdts + page_shift - 9);
 	else
-		ctrl->max_hw_sectors = UINT_MAX;
+		max_hw_sectors = UINT_MAX;
+	ctrl->max_hw_sectors =
+		min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);
 
 	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) && id->vs[3]) {
 		unsigned int max_hw_sectors;
@@ -1138,9 +1267,33 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	nvme_set_queue_limits(ctrl, ctrl->admin_q);
+	ctrl->sgls = le32_to_cpu(id->sgls);
+	ctrl->kas = le16_to_cpu(id->kas);
+
+	if (ctrl->ops->is_fabrics) {
+		ctrl->icdoff = le16_to_cpu(id->icdoff);
+		ctrl->ioccsz = le32_to_cpu(id->ioccsz);
+		ctrl->iorcsz = le32_to_cpu(id->iorcsz);
+		ctrl->maxcmd = le16_to_cpu(id->maxcmd);
+
+		/*
+		 * In fabrics we need to verify the cntlid matches the
+		 * admin connect
+		 */
+		if (ctrl->cntlid != le16_to_cpu(id->cntlid))
+			ret = -EINVAL;
+
+		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+			dev_err(ctrl->dev,
+				"keep-alive support is mandatory for fabrics\n");
+			ret = -EINVAL;
+		}
+	} else {
+		ctrl->cntlid = le16_to_cpu(id->cntlid);
+	}
 
 	kfree(id);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_init_identify);
 
@@ -1322,7 +1475,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	NULL,
 };
 
-static umode_t nvme_attrs_are_visible(struct kobject *kobj,
+static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 		struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -1341,7 +1494,7 @@ static umode_t nvme_attrs_are_visible(struct kobject *kobj,
 
 static const struct attribute_group nvme_ns_attr_group = {
 	.attrs		= nvme_ns_attrs,
-	.is_visible	= nvme_attrs_are_visible,
+	.is_visible	= nvme_ns_attrs_are_visible,
 };
 
 #define nvme_show_str_function(field)						\
@@ -1367,6 +1520,49 @@ nvme_show_str_function(serial);
 nvme_show_str_function(firmware_rev);
 nvme_show_int_function(cntlid);
 
+static ssize_t nvme_sysfs_delete(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (device_remove_file_self(dev, attr))
+		ctrl->ops->delete_ctrl(ctrl);
+	return count;
+}
+static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete);
+
+static ssize_t nvme_sysfs_show_transport(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name);
+}
+static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);
+
+static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%s\n",
+			ctrl->ops->get_subsysnqn(ctrl));
+}
+static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);
+
+static ssize_t nvme_sysfs_show_address(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE);
+}
+static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL);
+
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
 	&dev_attr_rescan_controller.attr,
@@ -1374,11 +1570,38 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_serial.attr,
 	&dev_attr_firmware_rev.attr,
 	&dev_attr_cntlid.attr,
+	&dev_attr_delete_controller.attr,
+	&dev_attr_transport.attr,
+	&dev_attr_subsysnqn.attr,
+	&dev_attr_address.attr,
 	NULL
 };
 
+#define CHECK_ATTR(ctrl, a, name)		\
+	if ((a) == &dev_attr_##name.attr &&	\
+	    !(ctrl)->ops->get_##name)		\
+		return 0
+
+static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
+		struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (a == &dev_attr_delete_controller.attr) {
+		if (!ctrl->ops->delete_ctrl)
+			return 0;
+	}
+
+	CHECK_ATTR(ctrl, a, subsysnqn);
+	CHECK_ATTR(ctrl, a, address);
+
+	return a->mode;
+}
+
 static struct attribute_group nvme_dev_attrs_group = {
-	.attrs = nvme_dev_attrs,
+	.attrs		= nvme_dev_attrs,
+	.is_visible	= nvme_dev_attrs_are_visible,
 };
 
 static const struct attribute_group *nvme_dev_attr_groups[] = {
@@ -1446,12 +1669,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	nvme_set_queue_limits(ctrl, ns->queue);
 
-	disk->major = nvme_major;
-	disk->first_minor = 0;
 	disk->fops = &nvme_fops;
 	disk->private_data = ns;
 	disk->queue = ns->queue;
-	disk->driverfs_dev = ctrl->device;
 	disk->flags = GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
 
@@ -1466,7 +1686,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (ns->type == NVME_NS_LIGHTNVM)
 		return;
 
-	add_disk(ns->disk);
+	device_add_disk(ctrl->device, ns->disk);
 	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_attr_group))
 		pr_warn("%s: failed to create sysfs group for identification\n",
@@ -1517,6 +1737,17 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		nvme_alloc_ns(ctrl, nsid);
 }
 
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+					unsigned nsid)
+{
+	struct nvme_ns *ns, *next;
+
+	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
+		if (ns->ns_id > nsid)
+			nvme_ns_remove(ns);
+	}
+}
+
 static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 {
 	struct nvme_ns *ns;
@@ -1531,7 +1762,7 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 	for (i = 0; i < num_lists; i++) {
 		ret = nvme_identify_ns_list(ctrl, prev, ns_list);
 		if (ret)
-			goto out;
+			goto free;
 
 		for (j = 0; j < min(nn, 1024U); j++) {
 			nsid = le32_to_cpu(ns_list[j]);
@@ -1551,22 +1782,20 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 		nn -= j;
 	}
  out:
+	nvme_remove_invalid_namespaces(ctrl, prev);
+ free:
 	kfree(ns_list);
 	return ret;
 }
 
 static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
 {
-	struct nvme_ns *ns, *next;
 	unsigned i;
 
 	for (i = 1; i <= nn; i++)
 		nvme_validate_ns(ctrl, i);
 
-	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->ns_id > nn)
-			nvme_ns_remove(ns);
-	}
+	nvme_remove_invalid_namespaces(ctrl, nn);
 }
 
 static void nvme_scan_work(struct work_struct *work)
@@ -1852,16 +2081,10 @@ int __init nvme_core_init(void)
 {
 	int result;
 
-	result = register_blkdev(nvme_major, "nvme");
-	if (result < 0)
-		return result;
-	else if (result > 0)
-		nvme_major = result;
-
 	result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
 							&nvme_dev_fops);
 	if (result < 0)
-		goto unregister_blkdev;
+		return result;
 	else if (result > 0)
 		nvme_char_major = result;
 
@@ -1875,8 +2098,6 @@ int __init nvme_core_init(void)
 
  unregister_chrdev:
 	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
- unregister_blkdev:
-	unregister_blkdev(nvme_major, "nvme");
 	return result;
 }
 
@@ -1884,7 +2105,6 @@ void nvme_core_exit(void)
 {
 	class_destroy(nvme_class);
 	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
-	unregister_blkdev(nvme_major, "nvme");
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
new file mode 100644
index 000000000000..dc996761042f
--- /dev/null
+++ b/drivers/nvme/host/fabrics.c
@@ -0,0 +1,952 @@
+/*
+ * NVMe over Fabrics common host code.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/init.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/parser.h>
+#include <linux/seq_file.h>
+#include "nvme.h"
+#include "fabrics.h"
+
+static LIST_HEAD(nvmf_transports);
+static DEFINE_MUTEX(nvmf_transports_mutex);
+
+static LIST_HEAD(nvmf_hosts);
+static DEFINE_MUTEX(nvmf_hosts_mutex);
+
+static struct nvmf_host *nvmf_default_host;
+
+static struct nvmf_host *__nvmf_host_find(const char *hostnqn)
+{
+	struct nvmf_host *host;
+
+	list_for_each_entry(host, &nvmf_hosts, list) {
+		if (!strcmp(host->nqn, hostnqn))
+			return host;
+	}
+
+	return NULL;
+}
+
+static struct nvmf_host *nvmf_host_add(const char *hostnqn)
+{
+	struct nvmf_host *host;
+
+	mutex_lock(&nvmf_hosts_mutex);
+	host = __nvmf_host_find(hostnqn);
+	if (host)
+		goto out_unlock;
+
+	host = kmalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
+		goto out_unlock;
+
+	kref_init(&host->ref);
+	memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
+	uuid_le_gen(&host->id);
+
+	list_add_tail(&host->list, &nvmf_hosts);
+out_unlock:
+	mutex_unlock(&nvmf_hosts_mutex);
+	return host;
+}
+
+static struct nvmf_host *nvmf_host_default(void)
+{
+	struct nvmf_host *host;
+
+	host = kmalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return NULL;
+
+	kref_init(&host->ref);
+	uuid_le_gen(&host->id);
+	snprintf(host->nqn, NVMF_NQN_SIZE,
+		"nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUl", &host->id);
+
+	mutex_lock(&nvmf_hosts_mutex);
+	list_add_tail(&host->list, &nvmf_hosts);
+	mutex_unlock(&nvmf_hosts_mutex);
+
+	return host;
+}
+
+static void nvmf_host_destroy(struct kref *ref)
+{
+	struct nvmf_host *host = container_of(ref, struct nvmf_host, ref);
+
+	mutex_lock(&nvmf_hosts_mutex);
+	list_del(&host->list);
+	mutex_unlock(&nvmf_hosts_mutex);
+
+	kfree(host);
+}
+
+static void nvmf_host_put(struct nvmf_host *host)
+{
+	if (host)
+		kref_put(&host->ref, nvmf_host_destroy);
+}
+
+/**
+ * nvmf_get_address() -  Get address/port
+ * @ctrl:	Host NVMe controller instance which we got the address
+ * @buf:	OUTPUT parameter that will contain the address/port
+ * @size:	buffer size
+ */
+int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
+{
+	return snprintf(buf, size, "traddr=%s,trsvcid=%s\n",
+			ctrl->opts->traddr, ctrl->opts->trsvcid);
+}
+EXPORT_SYMBOL_GPL(nvmf_get_address);
+
+/**
+ * nvmf_get_subsysnqn() - Get subsystem NQN
+ * @ctrl:	Host NVMe controller instance which we got the NQN
+ */
+const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl)
+{
+	return ctrl->opts->subsysnqn;
+}
+EXPORT_SYMBOL_GPL(nvmf_get_subsysnqn);
+
+/**
+ * nvmf_reg_read32() -  NVMe Fabrics "Property Get" API function.
+ * @ctrl:	Host NVMe controller instance maintaining the admin
+ *		queue used to submit the property read command to
+ *		the allocated NVMe controller resource on the target system.
+ * @off:	Starting offset value of the targeted property
+ *		register (see the fabrics section of the NVMe standard).
+ * @val:	OUTPUT parameter that will contain the value of
+ *		the property after a successful read.
+ *
+ * Used by the host system to retrieve a 32-bit capsule property value
+ * from an NVMe controller on the target system.
+ *
+ * ("Capsule property" is an "PCIe register concept" applied to the
+ * NVMe fabrics space.)
+ *
+ * Return:
+ *	0: successful read
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
+{
+	struct nvme_command cmd;
+	struct nvme_completion cqe;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.prop_get.opcode = nvme_fabrics_command;
+	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
+	cmd.prop_get.offset = cpu_to_le32(off);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
+
+	if (ret >= 0)
+		*val = le64_to_cpu(cqe.result64);
+	if (unlikely(ret != 0))
+		dev_err(ctrl->device,
+			"Property Get error: %d, offset %#x\n",
+			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_reg_read32);
+
+/**
+ * nvmf_reg_read64() -  NVMe Fabrics "Property Get" API function.
+ * @ctrl:	Host NVMe controller instance maintaining the admin
+ *		queue used to submit the property read command to
+ *		the allocated controller resource on the target system.
+ * @off:	Starting offset value of the targeted property
+ *		register (see the fabrics section of the NVMe standard).
+ * @val:	OUTPUT parameter that will contain the value of
+ *		the property after a successful read.
+ *
+ * Used by the host system to retrieve a 64-bit capsule property value
+ * from an NVMe controller on the target system.
+ *
+ * ("Capsule property" is an "PCIe register concept" applied to the
+ * NVMe fabrics space.)
+ *
+ * Return:
+ *	0: successful read
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
+{
+	struct nvme_command cmd;
+	struct nvme_completion cqe;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.prop_get.opcode = nvme_fabrics_command;
+	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
+	cmd.prop_get.attrib = 1;
+	cmd.prop_get.offset = cpu_to_le32(off);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &cqe, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
+
+	if (ret >= 0)
+		*val = le64_to_cpu(cqe.result64);
+	if (unlikely(ret != 0))
+		dev_err(ctrl->device,
+			"Property Get error: %d, offset %#x\n",
+			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_reg_read64);
+
+/**
+ * nvmf_reg_write32() -  NVMe Fabrics "Property Write" API function.
+ * @ctrl:	Host NVMe controller instance maintaining the admin
+ *		queue used to submit the property read command to
+ *		the allocated NVMe controller resource on the target system.
+ * @off:	Starting offset value of the targeted property
+ *		register (see the fabrics section of the NVMe standard).
+ * @val:	Input parameter that contains the value to be
+ *		written to the property.
+ *
+ * Used by the NVMe host system to write a 32-bit capsule property value
+ * to an NVMe controller on the target system.
+ *
+ * ("Capsule property" is an "PCIe register concept" applied to the
+ * NVMe fabrics space.)
+ *
+ * Return:
+ *	0: successful write
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
+{
+	struct nvme_command cmd;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.prop_set.opcode = nvme_fabrics_command;
+	cmd.prop_set.fctype = nvme_fabrics_type_property_set;
+	cmd.prop_set.attrib = 0;
+	cmd.prop_set.offset = cpu_to_le32(off);
+	cmd.prop_set.value = cpu_to_le64(val);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, NULL, 0, 0,
+			NVME_QID_ANY, 0, 0);
+	if (unlikely(ret))
+		dev_err(ctrl->device,
+			"Property Set error: %d, offset %#x\n",
+			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_reg_write32);
+
+/**
+ * nvmf_log_connect_error() - Error-parsing-diagnostic print
+ * out function for connect() errors.
+ *
+ * @ctrl: the specific /dev/nvmeX device that had the error.
+ *
+ * @errval: Error code to be decoded in a more human-friendly
+ *	    printout.
+ *
+ * @offset: For use with the NVMe error code NVME_SC_CONNECT_INVALID_PARAM.
+ *
+ * @cmd: This is the SQE portion of a submission capsule.
+ *
+ * @data: This is the "Data" portion of a submission capsule.
+ */
+static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
+		int errval, int offset, struct nvme_command *cmd,
+		struct nvmf_connect_data *data)
+{
+	int err_sctype = errval & (~NVME_SC_DNR);
+
+	switch (err_sctype) {
+
+	case (NVME_SC_CONNECT_INVALID_PARAM):
+		if (offset >> 16) {
+			char *inv_data = "Connect Invalid Data Parameter";
+
+			switch (offset & 0xffff) {
+			case (offsetof(struct nvmf_connect_data, cntlid)):
+				dev_err(ctrl->device,
+					"%s, cntlid: %d\n",
+					inv_data, data->cntlid);
+				break;
+			case (offsetof(struct nvmf_connect_data, hostnqn)):
+				dev_err(ctrl->device,
+					"%s, hostnqn \"%s\"\n",
+					inv_data, data->hostnqn);
+				break;
+			case (offsetof(struct nvmf_connect_data, subsysnqn)):
+				dev_err(ctrl->device,
+					"%s, subsysnqn \"%s\"\n",
+					inv_data, data->subsysnqn);
+				break;
+			default:
+				dev_err(ctrl->device,
+					"%s, starting byte offset: %d\n",
+				       inv_data, offset & 0xffff);
+				break;
+			}
+		} else {
+			char *inv_sqe = "Connect Invalid SQE Parameter";
+
+			switch (offset) {
+			case (offsetof(struct nvmf_connect_command, qid)):
+				dev_err(ctrl->device,
+				       "%s, qid %d\n",
+					inv_sqe, cmd->connect.qid);
+				break;
+			default:
+				dev_err(ctrl->device,
+					"%s, starting byte offset: %d\n",
+					inv_sqe, offset);
+			}
+		}
+		break;
+	default:
+		dev_err(ctrl->device,
+			"Connect command failed, error wo/DNR bit: %d\n",
+			err_sctype);
+		break;
+	} /* switch (err_sctype) */
+}
+
+/**
+ * nvmf_connect_admin_queue() - NVMe Fabrics Admin Queue "Connect"
+ *				API function.
+ * @ctrl:	Host nvme controller instance used to request
+ *              a new NVMe controller allocation on the target
+ *              system and  establish an NVMe Admin connection to
+ *              that controller.
+ *
+ * This function enables an NVMe host device to request a new allocation of
+ * an NVMe controller resource on a target system as well establish a
+ * fabrics-protocol connection of the NVMe Admin queue between the
+ * host system device and the allocated NVMe controller on the
+ * target system via a NVMe Fabrics "Connect" command.
+ *
+ * Return:
+ *	0: success
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ *
+ */
+int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
+{
+	struct nvme_command cmd;
+	struct nvme_completion cqe;
+	struct nvmf_connect_data *data;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.connect.opcode = nvme_fabrics_command;
+	cmd.connect.fctype = nvme_fabrics_type_connect;
+	cmd.connect.qid = 0;
+	cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize);
+	/*
+	 * Set keep-alive timeout in seconds granularity (ms * 1000)
+	 * and add a grace period for controller kato enforcement
+	 */
+	cmd.connect.kato = ctrl->opts->discovery_nqn ? 0 :
+		cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000);
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le));
+	data->cntlid = cpu_to_le16(0xffff);
+	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
+	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
+
+	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &cqe,
+			data, sizeof(*data), 0, NVME_QID_ANY, 1,
+			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+	if (ret) {
+		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(cqe.result),
+				       &cmd, data);
+		goto out_free_data;
+	}
+
+	ctrl->cntlid = le16_to_cpu(cqe.result16);
+
+out_free_data:
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue);
+
+/**
+ * nvmf_connect_io_queue() - NVMe Fabrics I/O Queue "Connect"
+ *			     API function.
+ * @ctrl:	Host nvme controller instance used to establish an
+ *		NVMe I/O queue connection to the already allocated NVMe
+ *		controller on the target system.
+ * @qid:	NVMe I/O queue number for the new I/O connection between
+ *		host and target (note qid == 0 is illegal as this is
+ *		the Admin queue, per NVMe standard).
+ *
+ * This function issues a fabrics-protocol connection
+ * of a NVMe I/O queue (via NVMe Fabrics "Connect" command)
+ * between the host system device and the allocated NVMe controller
+ * on the target system.
+ *
+ * Return:
+ *	0: success
+ *	> 0: NVMe error status code
+ *	< 0: Linux errno error code
+ */
+int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
+{
+	struct nvme_command cmd;
+	struct nvmf_connect_data *data;
+	struct nvme_completion cqe;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.connect.opcode = nvme_fabrics_command;
+	cmd.connect.fctype = nvme_fabrics_type_connect;
+	cmd.connect.qid = cpu_to_le16(qid);
+	cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize);
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le));
+	data->cntlid = cpu_to_le16(ctrl->cntlid);
+	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
+	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
+
+	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &cqe,
+			data, sizeof(*data), 0, qid, 1,
+			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+	if (ret) {
+		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(cqe.result),
+				       &cmd, data);
+	}
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
+
+/**
+ * nvmf_register_transport() - NVMe Fabrics Library registration function.
+ * @ops:	Transport ops instance to be registered to the
+ *		common fabrics library.
+ *
+ * API function that registers the type of specific transport fabric
+ * being implemented to the common NVMe fabrics library. Part of
+ * the overall init sequence of starting up a fabrics driver.
+ */
+void nvmf_register_transport(struct nvmf_transport_ops *ops)
+{
+	mutex_lock(&nvmf_transports_mutex);
+	list_add_tail(&ops->entry, &nvmf_transports);
+	mutex_unlock(&nvmf_transports_mutex);
+}
+EXPORT_SYMBOL_GPL(nvmf_register_transport);
+
+/**
+ * nvmf_unregister_transport() - NVMe Fabrics Library unregistration function.
+ * @ops:	Transport ops instance to be unregistered from the
+ *		common fabrics library.
+ *
+ * Fabrics API function that unregisters the type of specific transport
+ * fabric being implemented from the common NVMe fabrics library.
+ * Part of the overall exit sequence of unloading the implemented driver.
+ */
+void nvmf_unregister_transport(struct nvmf_transport_ops *ops)
+{
+	mutex_lock(&nvmf_transports_mutex);
+	list_del(&ops->entry);
+	mutex_unlock(&nvmf_transports_mutex);
+}
+EXPORT_SYMBOL_GPL(nvmf_unregister_transport);
+
+static struct nvmf_transport_ops *nvmf_lookup_transport(
+		struct nvmf_ctrl_options *opts)
+{
+	struct nvmf_transport_ops *ops;
+
+	lockdep_assert_held(&nvmf_transports_mutex);
+
+	list_for_each_entry(ops, &nvmf_transports, entry) {
+		if (strcmp(ops->name, opts->transport) == 0)
+			return ops;
+	}
+
+	return NULL;
+}
+
+static const match_table_t opt_tokens = {
+	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},
+	{ NVMF_OPT_TRADDR,		"traddr=%s"		},
+	{ NVMF_OPT_TRSVCID,		"trsvcid=%s"		},
+	{ NVMF_OPT_NQN,			"nqn=%s"		},
+	{ NVMF_OPT_QUEUE_SIZE,		"queue_size=%d"		},
+	{ NVMF_OPT_NR_IO_QUEUES,	"nr_io_queues=%d"	},
+	{ NVMF_OPT_RECONNECT_DELAY,	"reconnect_delay=%d"	},
+	{ NVMF_OPT_KATO,		"keep_alive_tmo=%d"	},
+	{ NVMF_OPT_HOSTNQN,		"hostnqn=%s"		},
+	{ NVMF_OPT_ERR,			NULL			}
+};
+
+static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
+		const char *buf)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *options, *o, *p;
+	int token, ret = 0;
+	size_t nqnlen  = 0;
+
+	/* Set defaults */
+	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
+	opts->nr_io_queues = num_online_cpus();
+	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
+
+	options = o = kstrdup(buf, GFP_KERNEL);
+	if (!options)
+		return -ENOMEM;
+
+	while ((p = strsep(&o, ",\n")) != NULL) {
+		if (!*p)
+			continue;
+
+		token = match_token(p, opt_tokens, args);
+		opts->mask |= token;
+		switch (token) {
+		case NVMF_OPT_TRANSPORT:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->transport = p;
+			break;
+		case NVMF_OPT_NQN:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->subsysnqn = p;
+			nqnlen = strlen(opts->subsysnqn);
+			if (nqnlen >= NVMF_NQN_SIZE) {
+				pr_err("%s needs to be < %d bytes\n",
+				opts->subsysnqn, NVMF_NQN_SIZE);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->discovery_nqn =
+				!(strcmp(opts->subsysnqn,
+					 NVME_DISC_SUBSYS_NAME));
+			if (opts->discovery_nqn)
+				opts->nr_io_queues = 0;
+			break;
+		case NVMF_OPT_TRADDR:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->traddr = p;
+			break;
+		case NVMF_OPT_TRSVCID:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			opts->trsvcid = p;
+			break;
+		case NVMF_OPT_QUEUE_SIZE:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token < NVMF_MIN_QUEUE_SIZE ||
+			    token > NVMF_MAX_QUEUE_SIZE) {
+				pr_err("Invalid queue_size %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->queue_size = token;
+			break;
+		case NVMF_OPT_NR_IO_QUEUES:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token <= 0) {
+				pr_err("Invalid number of IOQs %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->nr_io_queues = min_t(unsigned int,
+					num_online_cpus(), token);
+			break;
+		case NVMF_OPT_KATO:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			if (opts->discovery_nqn) {
+				pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n");
+				ret = -EINVAL;
+				goto out;
+			}
+
+			if (token < 0) {
+				pr_err("Invalid keep_alive_tmo %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			} else if (token == 0) {
+				/* Allowed for debug */
+				pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
+			}
+			opts->kato = token;
+			break;
+		case NVMF_OPT_HOSTNQN:
+			if (opts->host) {
+				pr_err("hostnqn already user-assigned: %s\n",
+				       opts->host->nqn);
+				ret = -EADDRINUSE;
+				goto out;
+			}
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			nqnlen = strlen(p);
+			if (nqnlen >= NVMF_NQN_SIZE) {
+				pr_err("%s needs to be < %d bytes\n",
+					p, NVMF_NQN_SIZE);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->host = nvmf_host_add(p);
+			if (!opts->host) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			break;
+		case NVMF_OPT_RECONNECT_DELAY:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token <= 0) {
+				pr_err("Invalid reconnect_delay %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->reconnect_delay = token;
+			break;
+		default:
+			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
+				p);
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	if (!opts->host) {
+		kref_get(&nvmf_default_host->ref);
+		opts->host = nvmf_default_host;
+	}
+
+out:
+	if (!opts->discovery_nqn && !opts->kato)
+		opts->kato = NVME_DEFAULT_KATO;
+	kfree(options);
+	return ret;
+}
+
+static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts,
+		unsigned int required_opts)
+{
+	if ((opts->mask & required_opts) != required_opts) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
+			if ((opt_tokens[i].token & required_opts) &&
+			    !(opt_tokens[i].token & opts->mask)) {
+				pr_warn("missing parameter '%s'\n",
+					opt_tokens[i].pattern);
+			}
+		}
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts,
+		unsigned int allowed_opts)
+{
+	if (opts->mask & ~allowed_opts) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
+			if (opt_tokens[i].token & ~allowed_opts) {
+				pr_warn("invalid parameter '%s'\n",
+					opt_tokens[i].pattern);
+			}
+		}
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void nvmf_free_options(struct nvmf_ctrl_options *opts)
+{
+	nvmf_host_put(opts->host);
+	kfree(opts->transport);
+	kfree(opts->traddr);
+	kfree(opts->trsvcid);
+	kfree(opts->subsysnqn);
+	kfree(opts);
+}
+EXPORT_SYMBOL_GPL(nvmf_free_options);
+
+#define NVMF_REQUIRED_OPTS	(NVMF_OPT_TRANSPORT | NVMF_OPT_NQN)
+#define NVMF_ALLOWED_OPTS	(NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
+				 NVMF_OPT_KATO | NVMF_OPT_HOSTNQN)
+
+static struct nvme_ctrl *
+nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
+{
+	struct nvmf_ctrl_options *opts;
+	struct nvmf_transport_ops *ops;
+	struct nvme_ctrl *ctrl;
+	int ret;
+
+	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
+	if (!opts)
+		return ERR_PTR(-ENOMEM);
+
+	ret = nvmf_parse_options(opts, buf);
+	if (ret)
+		goto out_free_opts;
+
+	/*
+	 * Check the generic options first as we need a valid transport for
+	 * the lookup below.  Then clear the generic flags so that transport
+	 * drivers don't have to care about them.
+	 */
+	ret = nvmf_check_required_opts(opts, NVMF_REQUIRED_OPTS);
+	if (ret)
+		goto out_free_opts;
+	opts->mask &= ~NVMF_REQUIRED_OPTS;
+
+	mutex_lock(&nvmf_transports_mutex);
+	ops = nvmf_lookup_transport(opts);
+	if (!ops) {
+		pr_info("no handler found for transport %s.\n",
+			opts->transport);
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ret = nvmf_check_required_opts(opts, ops->required_opts);
+	if (ret)
+		goto out_unlock;
+	ret = nvmf_check_allowed_opts(opts, NVMF_ALLOWED_OPTS |
+				ops->allowed_opts | ops->required_opts);
+	if (ret)
+		goto out_unlock;
+
+	ctrl = ops->create_ctrl(dev, opts);
+	if (IS_ERR(ctrl)) {
+		ret = PTR_ERR(ctrl);
+		goto out_unlock;
+	}
+
+	mutex_unlock(&nvmf_transports_mutex);
+	return ctrl;
+
+out_unlock:
+	mutex_unlock(&nvmf_transports_mutex);
+out_free_opts:
+	nvmf_host_put(opts->host);
+	kfree(opts);
+	return ERR_PTR(ret);
+}
+
+static struct class *nvmf_class;
+static struct device *nvmf_device;
+static DEFINE_MUTEX(nvmf_dev_mutex);
+
+static ssize_t nvmf_dev_write(struct file *file, const char __user *ubuf,
+		size_t count, loff_t *pos)
+{
+	struct seq_file *seq_file = file->private_data;
+	struct nvme_ctrl *ctrl;
+	const char *buf;
+	int ret = 0;
+
+	if (count > PAGE_SIZE)
+		return -ENOMEM;
+
+	buf = memdup_user_nul(ubuf, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	mutex_lock(&nvmf_dev_mutex);
+	if (seq_file->private) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ctrl = nvmf_create_ctrl(nvmf_device, buf, count);
+	if (IS_ERR(ctrl)) {
+		ret = PTR_ERR(ctrl);
+		goto out_unlock;
+	}
+
+	seq_file->private = ctrl;
+
+out_unlock:
+	mutex_unlock(&nvmf_dev_mutex);
+	kfree(buf);
+	return ret ? ret : count;
+}
+
+static int nvmf_dev_show(struct seq_file *seq_file, void *private)
+{
+	struct nvme_ctrl *ctrl;
+	int ret = 0;
+
+	mutex_lock(&nvmf_dev_mutex);
+	ctrl = seq_file->private;
+	if (!ctrl) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	seq_printf(seq_file, "instance=%d,cntlid=%d\n",
+			ctrl->instance, ctrl->cntlid);
+
+out_unlock:
+	mutex_unlock(&nvmf_dev_mutex);
+	return ret;
+}
+
+static int nvmf_dev_open(struct inode *inode, struct file *file)
+{
+	/*
+	 * The miscdevice code initializes file->private_data, but doesn't
+	 * make use of it later.
+	 */
+	file->private_data = NULL;
+	return single_open(file, nvmf_dev_show, NULL);
+}
+
+static int nvmf_dev_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq_file = file->private_data;
+	struct nvme_ctrl *ctrl = seq_file->private;
+
+	if (ctrl)
+		nvme_put_ctrl(ctrl);
+	return single_release(inode, file);
+}
+
+static const struct file_operations nvmf_dev_fops = {
+	.owner		= THIS_MODULE,
+	.write		= nvmf_dev_write,
+	.read		= seq_read,
+	.open		= nvmf_dev_open,
+	.release	= nvmf_dev_release,
+};
+
+static struct miscdevice nvmf_misc = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name           = "nvme-fabrics",
+	.fops		= &nvmf_dev_fops,
+};
+
+static int __init nvmf_init(void)
+{
+	int ret;
+
+	nvmf_default_host = nvmf_host_default();
+	if (!nvmf_default_host)
+		return -ENOMEM;
+
+	nvmf_class = class_create(THIS_MODULE, "nvme-fabrics");
+	if (IS_ERR(nvmf_class)) {
+		pr_err("couldn't register class nvme-fabrics\n");
+		ret = PTR_ERR(nvmf_class);
+		goto out_free_host;
+	}
+
+	nvmf_device =
+		device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
+	if (IS_ERR(nvmf_device)) {
+		pr_err("couldn't create nvme-fabris device!\n");
+		ret = PTR_ERR(nvmf_device);
+		goto out_destroy_class;
+	}
+
+	ret = misc_register(&nvmf_misc);
+	if (ret) {
+		pr_err("couldn't register misc device: %d\n", ret);
+		goto out_destroy_device;
+	}
+
+	return 0;
+
+out_destroy_device:
+	device_destroy(nvmf_class, MKDEV(0, 0));
+out_destroy_class:
+	class_destroy(nvmf_class);
+out_free_host:
+	nvmf_host_put(nvmf_default_host);
+	return ret;
+}
+
+static void __exit nvmf_exit(void)
+{
+	misc_deregister(&nvmf_misc);
+	device_destroy(nvmf_class, MKDEV(0, 0));
+	class_destroy(nvmf_class);
+	nvmf_host_put(nvmf_default_host);
+
+	BUILD_BUG_ON(sizeof(struct nvmf_connect_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvmf_property_get_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvmf_property_set_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvmf_connect_data) != 1024);
+}
+
+MODULE_LICENSE("GPL v2");
+
+module_init(nvmf_init);
+module_exit(nvmf_exit);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
new file mode 100644
index 000000000000..89df52c8be97
--- /dev/null
+++ b/drivers/nvme/host/fabrics.h
@@ -0,0 +1,132 @@
+/*
+ * NVMe over Fabrics common host code.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#ifndef _NVME_FABRICS_H
+#define _NVME_FABRICS_H 1
+
+#include <linux/in.h>
+#include <linux/inet.h>
+
+#define NVMF_MIN_QUEUE_SIZE	16
+#define NVMF_MAX_QUEUE_SIZE	1024
+#define NVMF_DEF_QUEUE_SIZE	128
+#define NVMF_DEF_RECONNECT_DELAY	10
+
+/*
+ * Define a host as seen by the target.  We allocate one at boot, but also
+ * allow the override it when creating controllers.  This is both to provide
+ * persistence of the Host NQN over multiple boots, and to allow using
+ * multiple ones, for example in a container scenario.  Because we must not
+ * use different Host NQNs with the same Host ID we generate a Host ID and
+ * use this structure to keep track of the relation between the two.
+ */
+struct nvmf_host {
+	struct kref		ref;
+	struct list_head	list;
+	char			nqn[NVMF_NQN_SIZE];
+	uuid_le			id;
+};
+
+/**
+ * enum nvmf_parsing_opts - used to define the sysfs parsing options used.
+ */
+enum {
+	NVMF_OPT_ERR		= 0,
+	NVMF_OPT_TRANSPORT	= 1 << 0,
+	NVMF_OPT_NQN		= 1 << 1,
+	NVMF_OPT_TRADDR		= 1 << 2,
+	NVMF_OPT_TRSVCID	= 1 << 3,
+	NVMF_OPT_QUEUE_SIZE	= 1 << 4,
+	NVMF_OPT_NR_IO_QUEUES	= 1 << 5,
+	NVMF_OPT_TL_RETRY_COUNT	= 1 << 6,
+	NVMF_OPT_KATO		= 1 << 7,
+	NVMF_OPT_HOSTNQN	= 1 << 8,
+	NVMF_OPT_RECONNECT_DELAY = 1 << 9,
+};
+
+/**
+ * struct nvmf_ctrl_options - Used to hold the options specified
+ *			      with the parsing opts enum.
+ * @mask:	Used by the fabrics library to parse through sysfs options
+ *		on adding a NVMe controller.
+ * @transport:	Holds the fabric transport "technology name" (for a lack of
+ *		better description) that will be used by an NVMe controller
+ *		being added.
+ * @subsysnqn:	Hold the fully qualified NQN subystem name (format defined
+ *		in the NVMe specification, "NVMe Qualified Names").
+ * @traddr:	network address that will be used by the host to communicate
+ *		to the added NVMe controller.
+ * @trsvcid:	network port used for host-controller communication.
+ * @queue_size: Number of IO queue elements.
+ * @nr_io_queues: Number of controller IO queues that will be established.
+ * @reconnect_delay: Time between two consecutive reconnect attempts.
+ * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN.
+ * @kato:	Keep-alive timeout.
+ * @host:	Virtual NVMe host, contains the NQN and Host ID.
+ */
+struct nvmf_ctrl_options {
+	unsigned		mask;
+	char			*transport;
+	char			*subsysnqn;
+	char			*traddr;
+	char			*trsvcid;
+	size_t			queue_size;
+	unsigned int		nr_io_queues;
+	unsigned int		reconnect_delay;
+	bool			discovery_nqn;
+	unsigned int		kato;
+	struct nvmf_host	*host;
+};
+
+/*
+ * struct nvmf_transport_ops - used to register a specific
+ *			       fabric implementation of NVMe fabrics.
+ * @entry:		Used by the fabrics library to add the new
+ *			registration entry to its linked-list internal tree.
+ * @name:		Name of the NVMe fabric driver implementation.
+ * @required_opts:	sysfs command-line options that must be specified
+ *			when adding a new NVMe controller.
+ * @allowed_opts:	sysfs command-line options that can be specified
+ *			when adding a new NVMe controller.
+ * @create_ctrl():	function pointer that points to a non-NVMe
+ *			implementation-specific fabric technology
+ *			that would go into starting up that fabric
+ *			for the purpose of conneciton to an NVMe controller
+ *			using that fabric technology.
+ *
+ * Notes:
+ *	1. At minimum, 'required_opts' and 'allowed_opts' should
+ *	   be set to the same enum parsing options defined earlier.
+ *	2. create_ctrl() must be defined (even if it does nothing)
+ */
+struct nvmf_transport_ops {
+	struct list_head	entry;
+	const char		*name;
+	int			required_opts;
+	int			allowed_opts;
+	struct nvme_ctrl	*(*create_ctrl)(struct device *dev,
+					struct nvmf_ctrl_options *opts);
+};
+
+int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
+int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
+int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
+int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl);
+int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid);
+void nvmf_register_transport(struct nvmf_transport_ops *ops);
+void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
+void nvmf_free_options(struct nvmf_ctrl_options *opts);
+const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl);
+int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
+
+#endif /* _NVME_FABRICS_H */
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index a0af0558354c..63f483daf930 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -156,7 +156,7 @@ struct nvme_nvm_completion {
 
 #define NVME_NVM_LP_MLC_PAIRS 886
 struct nvme_nvm_lp_mlc {
-	__u16			num_pairs;
+	__le16			num_pairs;
 	__u8			pairs[NVME_NVM_LP_MLC_PAIRS];
 };
 
@@ -500,7 +500,7 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	struct bio *bio = rqd->bio;
 	struct nvme_nvm_command *cmd;
 
-	rq = blk_mq_alloc_request(q, bio_rw(bio), 0);
+	rq = blk_mq_alloc_request(q, bio_data_dir(bio), 0);
 	if (IS_ERR(rq))
 		return -ENOMEM;
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 1daa0482de0e..ab18b78102bf 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -38,6 +38,11 @@ extern unsigned char admin_timeout;
 extern unsigned char shutdown_timeout;
 #define SHUTDOWN_TIMEOUT	(shutdown_timeout * HZ)
 
+#define NVME_DEFAULT_KATO	5
+#define NVME_KATO_GRACE		10
+
+extern unsigned int nvme_max_retries;
+
 enum {
 	NVME_NS_LBA		= 0,
 	NVME_NS_LIGHTNVM	= 1,
@@ -65,12 +70,26 @@ enum nvme_quirks {
 	 * logical blocks.
 	 */
 	NVME_QUIRK_DISCARD_ZEROES		= (1 << 2),
+
+	/*
+	 * The controller needs a delay before starts checking the device
+	 * readiness, which is done by reading the NVME_CSTS_RDY bit.
+	 */
+	NVME_QUIRK_DELAY_BEFORE_CHK_RDY		= (1 << 3),
 };
 
+/* The below value is the specific amount of delay needed before checking
+ * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
+ * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
+ * found empirically.
+ */
+#define NVME_QUIRK_DELAY_AMOUNT		2000
+
 enum nvme_ctrl_state {
 	NVME_CTRL_NEW,
 	NVME_CTRL_LIVE,
 	NVME_CTRL_RESETTING,
+	NVME_CTRL_RECONNECTING,
 	NVME_CTRL_DELETING,
 	NVME_CTRL_DEAD,
 };
@@ -80,6 +99,7 @@ struct nvme_ctrl {
 	spinlock_t lock;
 	const struct nvme_ctrl_ops *ops;
 	struct request_queue *admin_q;
+	struct request_queue *connect_q;
 	struct device *dev;
 	struct kref kref;
 	int instance;
@@ -107,10 +127,22 @@ struct nvme_ctrl {
 	u8 event_limit;
 	u8 vwc;
 	u32 vs;
+	u32 sgls;
+	u16 kas;
+	unsigned int kato;
 	bool subsystem;
 	unsigned long quirks;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
+	struct delayed_work ka_work;
+
+	/* Fabrics only */
+	u16 sqsize;
+	u32 ioccsz;
+	u32 iorcsz;
+	u16 icdoff;
+	u16 maxcmd;
+	struct nvmf_ctrl_options *opts;
 };
 
 /*
@@ -144,7 +176,9 @@ struct nvme_ns {
 };
 
 struct nvme_ctrl_ops {
+	const char *name;
 	struct module *module;
+	bool is_fabrics;
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
@@ -152,6 +186,9 @@ struct nvme_ctrl_ops {
 	void (*free_ctrl)(struct nvme_ctrl *ctrl);
 	void (*post_scan)(struct nvme_ctrl *ctrl);
 	void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx);
+	int (*delete_ctrl)(struct nvme_ctrl *ctrl);
+	const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl);
+	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
 };
 
 static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl)
@@ -177,7 +214,7 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
 
 static inline unsigned nvme_map_len(struct request *rq)
 {
-	if (rq->cmd_flags & REQ_DISCARD)
+	if (req_op(rq) == REQ_OP_DISCARD)
 		return sizeof(struct nvme_dsm_range);
 	else
 		return blk_rq_bytes(rq);
@@ -185,7 +222,7 @@ static inline unsigned nvme_map_len(struct request *rq)
 
 static inline void nvme_cleanup_cmd(struct request *req)
 {
-	if (req->cmd_flags & REQ_DISCARD)
+	if (req_op(req) == REQ_OP_DISCARD)
 		kfree(req->completion_data);
 }
 
@@ -204,9 +241,11 @@ static inline int nvme_error_status(u16 status)
 static inline bool nvme_req_needs_retry(struct request *req, u16 status)
 {
 	return !(status & NVME_SC_DNR || blk_noretry_request(req)) &&
-		(jiffies - req->start_time) < req->timeout;
+		(jiffies - req->start_time) < req->timeout &&
+		req->retries < nvme_max_retries;
 }
 
+void nvme_cancel_request(struct request *req, void *data, bool reserved);
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state);
 int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap);
@@ -230,8 +269,9 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
 
+#define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, unsigned int flags);
+		struct nvme_command *cmd, unsigned int flags, int qid);
 void nvme_requeue_req(struct request *req);
 int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
@@ -239,7 +279,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		struct nvme_completion *cqe, void *buffer, unsigned bufflen,
-		unsigned timeout);
+		unsigned timeout, int qid, int at_head, int flags);
 int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void __user *ubuffer, unsigned bufflen, u32 *result,
 		unsigned timeout);
@@ -256,6 +296,8 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
 int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
 			dma_addr_t dma_addr, u32 *result);
 int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
+void nvme_start_keep_alive(struct nvme_ctrl *ctrl);
+void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
 
 struct sg_io_hdr;
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index befac5b19490..4cb9b156cab7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -310,6 +310,11 @@ static int nvme_init_iod(struct request *rq, unsigned size,
 	iod->npages = -1;
 	iod->nents = 0;
 	iod->length = size;
+
+	if (!(rq->cmd_flags & REQ_DONTPREP)) {
+		rq->retries = 0;
+		rq->cmd_flags |= REQ_DONTPREP;
+	}
 	return 0;
 }
 
@@ -520,8 +525,8 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
 			goto out_unmap;
 	}
 
-	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
+	cmnd->rw.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd->rw.dptr.prp2 = cpu_to_le64(iod->first_dma);
 	if (blk_integrity_rq(req))
 		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg));
 	return BLK_MQ_RQ_QUEUE_OK;
@@ -623,6 +628,7 @@ static void nvme_complete_rq(struct request *req)
 
 	if (unlikely(req->errors)) {
 		if (nvme_req_needs_retry(req, req->errors)) {
+			req->retries++;
 			nvme_requeue_req(req);
 			return;
 		}
@@ -901,7 +907,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		 req->tag, nvmeq->qid);
 
 	abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
-			BLK_MQ_REQ_NOWAIT);
+			BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(abort_req)) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
@@ -919,22 +925,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	return BLK_EH_RESET_TIMER;
 }
 
-static void nvme_cancel_io(struct request *req, void *data, bool reserved)
-{
-	int status;
-
-	if (!blk_mq_request_started(req))
-		return;
-
-	dev_dbg_ratelimited(((struct nvme_dev *) data)->ctrl.device,
-				"Cancelling I/O %d", req->tag);
-
-	status = NVME_SC_ABORT_REQ;
-	if (blk_queue_dying(req->q))
-		status |= NVME_SC_DNR;
-	blk_mq_complete_request(req, status);
-}
-
 static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
@@ -1399,16 +1389,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (result < 0)
 		return result;
 
-	/*
-	 * Degraded controllers might return an error when setting the queue
-	 * count.  We still want to be able to bring them online and offer
-	 * access to the admin queue, as that might be only way to fix them up.
-	 */
-	if (result > 0) {
-		dev_err(dev->ctrl.device,
-			"Could not set queue count (%d)\n", result);
+	if (nr_io_queues == 0)
 		return 0;
-	}
 
 	if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
@@ -1536,7 +1518,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	cmd.delete_queue.opcode = opcode;
 	cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
-	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT);
+	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1727,8 +1709,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	}
 	nvme_pci_disable(dev);
 
-	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_io, dev);
-	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_io, dev);
+	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
+	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
 	mutex_unlock(&dev->shutdown_lock);
 }
 
@@ -1902,6 +1884,7 @@ static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 }
 
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
+	.name			= "pcie",
 	.module			= THIS_MODULE,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
@@ -1940,7 +1923,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	node = dev_to_node(&pdev->dev);
 	if (node == NUMA_NO_NODE)
-		set_dev_node(&pdev->dev, 0);
+		set_dev_node(&pdev->dev, first_memory_node);
 
 	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
@@ -2037,6 +2020,24 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_put_ctrl(&dev->ctrl);
 }
 
+static int nvme_pci_sriov_configure(struct pci_dev *pdev, int numvfs)
+{
+	int ret = 0;
+
+	if (numvfs == 0) {
+		if (pci_vfs_assigned(pdev)) {
+			dev_warn(&pdev->dev,
+				"Cannot disable SR-IOV VFs while assigned\n");
+			return -EPERM;
+		}
+		pci_disable_sriov(pdev);
+		return 0;
+	}
+
+	ret = pci_enable_sriov(pdev, numvfs);
+	return ret ? ret : numvfs;
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int nvme_suspend(struct device *dev)
 {
@@ -2122,6 +2123,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DISCARD_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
+	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ 0, }
@@ -2137,6 +2140,7 @@ static struct pci_driver nvme_driver = {
 	.driver		= {
 		.pm	= &nvme_dev_pm_ops,
 	},
+	.sriov_configure = nvme_pci_sriov_configure,
 	.err_handler	= &nvme_err_handler,
 };
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
new file mode 100644
index 000000000000..3e3ce2b0424e
--- /dev/null
+++ b/drivers/nvme/host/rdma.c
@@ -0,0 +1,2018 @@
+/*
+ * NVMe over Fabrics RDMA host code.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/jiffies.h>
+#include <linux/atomic.h>
+#include <linux/blk-mq.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/scatterlist.h>
+#include <linux/nvme.h>
+#include <linux/t10-pi.h>
+#include <asm/unaligned.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+#include <rdma/ib_cm.h>
+#include <linux/nvme-rdma.h>
+
+#include "nvme.h"
+#include "fabrics.h"
+
+
+#define NVME_RDMA_CONNECT_TIMEOUT_MS	1000		/* 1 second */
+
+#define NVME_RDMA_MAX_SEGMENT_SIZE	0xffffff	/* 24-bit SGL field */
+
+#define NVME_RDMA_MAX_SEGMENTS		256
+
+#define NVME_RDMA_MAX_INLINE_SEGMENTS	1
+
+#define NVME_RDMA_MAX_PAGES_PER_MR	512
+
+#define NVME_RDMA_DEF_RECONNECT_DELAY	20
+
+/*
+ * We handle AEN commands ourselves and don't even let the
+ * block layer know about them.
+ */
+#define NVME_RDMA_NR_AEN_COMMANDS      1
+#define NVME_RDMA_AQ_BLKMQ_DEPTH       \
+	(NVMF_AQ_DEPTH - NVME_RDMA_NR_AEN_COMMANDS)
+
+struct nvme_rdma_device {
+	struct ib_device       *dev;
+	struct ib_pd	       *pd;
+	struct ib_mr	       *mr;
+	struct kref		ref;
+	struct list_head	entry;
+};
+
+struct nvme_rdma_qe {
+	struct ib_cqe		cqe;
+	void			*data;
+	u64			dma;
+};
+
+struct nvme_rdma_queue;
+struct nvme_rdma_request {
+	struct ib_mr		*mr;
+	struct nvme_rdma_qe	sqe;
+	struct ib_sge		sge[1 + NVME_RDMA_MAX_INLINE_SEGMENTS];
+	u32			num_sge;
+	int			nents;
+	bool			inline_data;
+	bool			need_inval;
+	struct ib_reg_wr	reg_wr;
+	struct ib_cqe		reg_cqe;
+	struct nvme_rdma_queue  *queue;
+	struct sg_table		sg_table;
+	struct scatterlist	first_sgl[];
+};
+
+enum nvme_rdma_queue_flags {
+	NVME_RDMA_Q_CONNECTED = (1 << 0),
+};
+
+struct nvme_rdma_queue {
+	struct nvme_rdma_qe	*rsp_ring;
+	u8			sig_count;
+	int			queue_size;
+	size_t			cmnd_capsule_len;
+	struct nvme_rdma_ctrl	*ctrl;
+	struct nvme_rdma_device	*device;
+	struct ib_cq		*ib_cq;
+	struct ib_qp		*qp;
+
+	unsigned long		flags;
+	struct rdma_cm_id	*cm_id;
+	int			cm_error;
+	struct completion	cm_done;
+};
+
+struct nvme_rdma_ctrl {
+	/* read and written in the hot path */
+	spinlock_t		lock;
+
+	/* read only in the hot path */
+	struct nvme_rdma_queue	*queues;
+	u32			queue_count;
+
+	/* other member variables */
+	struct blk_mq_tag_set	tag_set;
+	struct work_struct	delete_work;
+	struct work_struct	reset_work;
+	struct work_struct	err_work;
+
+	struct nvme_rdma_qe	async_event_sqe;
+
+	int			reconnect_delay;
+	struct delayed_work	reconnect_work;
+
+	struct list_head	list;
+
+	struct blk_mq_tag_set	admin_tag_set;
+	struct nvme_rdma_device	*device;
+
+	u64			cap;
+	u32			max_fr_pages;
+
+	union {
+		struct sockaddr addr;
+		struct sockaddr_in addr_in;
+	};
+
+	struct nvme_ctrl	ctrl;
+};
+
+static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
+{
+	return container_of(ctrl, struct nvme_rdma_ctrl, ctrl);
+}
+
+static LIST_HEAD(device_list);
+static DEFINE_MUTEX(device_list_mutex);
+
+static LIST_HEAD(nvme_rdma_ctrl_list);
+static DEFINE_MUTEX(nvme_rdma_ctrl_mutex);
+
+static struct workqueue_struct *nvme_rdma_wq;
+
+/*
+ * Disabling this option makes small I/O goes faster, but is fundamentally
+ * unsafe.  With it turned off we will have to register a global rkey that
+ * allows read and write access to all physical memory.
+ */
+static bool register_always = true;
+module_param(register_always, bool, 0444);
+MODULE_PARM_DESC(register_always,
+	 "Use memory registration even for contiguous memory regions");
+
+static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
+		struct rdma_cm_event *event);
+static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
+static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl);
+
+/* XXX: really should move to a generic header sooner or later.. */
+static inline void put_unaligned_le24(u32 val, u8 *p)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+	*p++ = val >> 16;
+}
+
+static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue)
+{
+	return queue - queue->ctrl->queues;
+}
+
+static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue)
+{
+	return queue->cmnd_capsule_len - sizeof(struct nvme_command);
+}
+
+static void nvme_rdma_free_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe,
+		size_t capsule_size, enum dma_data_direction dir)
+{
+	ib_dma_unmap_single(ibdev, qe->dma, capsule_size, dir);
+	kfree(qe->data);
+}
+
+static int nvme_rdma_alloc_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe,
+		size_t capsule_size, enum dma_data_direction dir)
+{
+	qe->data = kzalloc(capsule_size, GFP_KERNEL);
+	if (!qe->data)
+		return -ENOMEM;
+
+	qe->dma = ib_dma_map_single(ibdev, qe->data, capsule_size, dir);
+	if (ib_dma_mapping_error(ibdev, qe->dma)) {
+		kfree(qe->data);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void nvme_rdma_free_ring(struct ib_device *ibdev,
+		struct nvme_rdma_qe *ring, size_t ib_queue_size,
+		size_t capsule_size, enum dma_data_direction dir)
+{
+	int i;
+
+	for (i = 0; i < ib_queue_size; i++)
+		nvme_rdma_free_qe(ibdev, &ring[i], capsule_size, dir);
+	kfree(ring);
+}
+
+static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev,
+		size_t ib_queue_size, size_t capsule_size,
+		enum dma_data_direction dir)
+{
+	struct nvme_rdma_qe *ring;
+	int i;
+
+	ring = kcalloc(ib_queue_size, sizeof(struct nvme_rdma_qe), GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	for (i = 0; i < ib_queue_size; i++) {
+		if (nvme_rdma_alloc_qe(ibdev, &ring[i], capsule_size, dir))
+			goto out_free_ring;
+	}
+
+	return ring;
+
+out_free_ring:
+	nvme_rdma_free_ring(ibdev, ring, i, capsule_size, dir);
+	return NULL;
+}
+
+static void nvme_rdma_qp_event(struct ib_event *event, void *context)
+{
+	pr_debug("QP event %d\n", event->event);
+}
+
+static int nvme_rdma_wait_for_cm(struct nvme_rdma_queue *queue)
+{
+	wait_for_completion_interruptible_timeout(&queue->cm_done,
+			msecs_to_jiffies(NVME_RDMA_CONNECT_TIMEOUT_MS) + 1);
+	return queue->cm_error;
+}
+
+static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
+{
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_qp_init_attr init_attr;
+	int ret;
+
+	memset(&init_attr, 0, sizeof(init_attr));
+	init_attr.event_handler = nvme_rdma_qp_event;
+	/* +1 for drain */
+	init_attr.cap.max_send_wr = factor * queue->queue_size + 1;
+	/* +1 for drain */
+	init_attr.cap.max_recv_wr = queue->queue_size + 1;
+	init_attr.cap.max_recv_sge = 1;
+	init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS;
+	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+	init_attr.qp_type = IB_QPT_RC;
+	init_attr.send_cq = queue->ib_cq;
+	init_attr.recv_cq = queue->ib_cq;
+
+	ret = rdma_create_qp(queue->cm_id, dev->pd, &init_attr);
+
+	queue->qp = queue->cm_id->qp;
+	return ret;
+}
+
+static int nvme_rdma_reinit_request(void *data, struct request *rq)
+{
+	struct nvme_rdma_ctrl *ctrl = data;
+	struct nvme_rdma_device *dev = ctrl->device;
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	int ret = 0;
+
+	if (!req->need_inval)
+		goto out;
+
+	ib_dereg_mr(req->mr);
+
+	req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
+			ctrl->max_fr_pages);
+	if (IS_ERR(req->mr)) {
+		ret = PTR_ERR(req->mr);
+		req->mr = NULL;
+	}
+
+	req->need_inval = false;
+
+out:
+	return ret;
+}
+
+static void __nvme_rdma_exit_request(struct nvme_rdma_ctrl *ctrl,
+		struct request *rq, unsigned int queue_idx)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
+	struct nvme_rdma_device *dev = queue->device;
+
+	if (req->mr)
+		ib_dereg_mr(req->mr);
+
+	nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+}
+
+static void nvme_rdma_exit_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx)
+{
+	return __nvme_rdma_exit_request(data, rq, hctx_idx + 1);
+}
+
+static void nvme_rdma_exit_admin_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx)
+{
+	return __nvme_rdma_exit_request(data, rq, 0);
+}
+
+static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl,
+		struct request *rq, unsigned int queue_idx)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx];
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+	int ret;
+
+	BUG_ON(queue_idx >= ctrl->queue_count);
+
+	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+	if (ret)
+		return ret;
+
+	req->mr = ib_alloc_mr(dev->pd, IB_MR_TYPE_MEM_REG,
+			ctrl->max_fr_pages);
+	if (IS_ERR(req->mr)) {
+		ret = PTR_ERR(req->mr);
+		goto out_free_qe;
+	}
+
+	req->queue = queue;
+
+	return 0;
+
+out_free_qe:
+	nvme_rdma_free_qe(dev->dev, &req->sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+	return -ENOMEM;
+}
+
+static int nvme_rdma_init_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
+{
+	return __nvme_rdma_init_request(data, rq, hctx_idx + 1);
+}
+
+static int nvme_rdma_init_admin_request(void *data, struct request *rq,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
+{
+	return __nvme_rdma_init_request(data, rq, 0);
+}
+
+static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+		unsigned int hctx_idx)
+{
+	struct nvme_rdma_ctrl *ctrl = data;
+	struct nvme_rdma_queue *queue = &ctrl->queues[hctx_idx + 1];
+
+	BUG_ON(hctx_idx >= ctrl->queue_count);
+
+	hctx->driver_data = queue;
+	return 0;
+}
+
+static int nvme_rdma_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+		unsigned int hctx_idx)
+{
+	struct nvme_rdma_ctrl *ctrl = data;
+	struct nvme_rdma_queue *queue = &ctrl->queues[0];
+
+	BUG_ON(hctx_idx != 0);
+
+	hctx->driver_data = queue;
+	return 0;
+}
+
+static void nvme_rdma_free_dev(struct kref *ref)
+{
+	struct nvme_rdma_device *ndev =
+		container_of(ref, struct nvme_rdma_device, ref);
+
+	mutex_lock(&device_list_mutex);
+	list_del(&ndev->entry);
+	mutex_unlock(&device_list_mutex);
+
+	if (!register_always)
+		ib_dereg_mr(ndev->mr);
+	ib_dealloc_pd(ndev->pd);
+
+	kfree(ndev);
+}
+
+static void nvme_rdma_dev_put(struct nvme_rdma_device *dev)
+{
+	kref_put(&dev->ref, nvme_rdma_free_dev);
+}
+
+static int nvme_rdma_dev_get(struct nvme_rdma_device *dev)
+{
+	return kref_get_unless_zero(&dev->ref);
+}
+
+static struct nvme_rdma_device *
+nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
+{
+	struct nvme_rdma_device *ndev;
+
+	mutex_lock(&device_list_mutex);
+	list_for_each_entry(ndev, &device_list, entry) {
+		if (ndev->dev->node_guid == cm_id->device->node_guid &&
+		    nvme_rdma_dev_get(ndev))
+			goto out_unlock;
+	}
+
+	ndev = kzalloc(sizeof(*ndev), GFP_KERNEL);
+	if (!ndev)
+		goto out_err;
+
+	ndev->dev = cm_id->device;
+	kref_init(&ndev->ref);
+
+	ndev->pd = ib_alloc_pd(ndev->dev);
+	if (IS_ERR(ndev->pd))
+		goto out_free_dev;
+
+	if (!register_always) {
+		ndev->mr = ib_get_dma_mr(ndev->pd,
+					    IB_ACCESS_LOCAL_WRITE |
+					    IB_ACCESS_REMOTE_READ |
+					    IB_ACCESS_REMOTE_WRITE);
+		if (IS_ERR(ndev->mr))
+			goto out_free_pd;
+	}
+
+	if (!(ndev->dev->attrs.device_cap_flags &
+	      IB_DEVICE_MEM_MGT_EXTENSIONS)) {
+		dev_err(&ndev->dev->dev,
+			"Memory registrations not supported.\n");
+		goto out_free_mr;
+	}
+
+	list_add(&ndev->entry, &device_list);
+out_unlock:
+	mutex_unlock(&device_list_mutex);
+	return ndev;
+
+out_free_mr:
+	if (!register_always)
+		ib_dereg_mr(ndev->mr);
+out_free_pd:
+	ib_dealloc_pd(ndev->pd);
+out_free_dev:
+	kfree(ndev);
+out_err:
+	mutex_unlock(&device_list_mutex);
+	return NULL;
+}
+
+static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+
+	rdma_destroy_qp(queue->cm_id);
+	ib_free_cq(queue->ib_cq);
+
+	nvme_rdma_free_ring(ibdev, queue->rsp_ring, queue->queue_size,
+			sizeof(struct nvme_completion), DMA_FROM_DEVICE);
+
+	nvme_rdma_dev_put(dev);
+}
+
+static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_device *dev)
+{
+	struct ib_device *ibdev = dev->dev;
+	const int send_wr_factor = 3;			/* MR, SEND, INV */
+	const int cq_factor = send_wr_factor + 1;	/* + RECV */
+	int comp_vector, idx = nvme_rdma_queue_idx(queue);
+
+	int ret;
+
+	queue->device = dev;
+
+	/*
+	 * The admin queue is barely used once the controller is live, so don't
+	 * bother to spread it out.
+	 */
+	if (idx == 0)
+		comp_vector = 0;
+	else
+		comp_vector = idx % ibdev->num_comp_vectors;
+
+
+	/* +1 for ib_stop_cq */
+	queue->ib_cq = ib_alloc_cq(dev->dev, queue,
+				cq_factor * queue->queue_size + 1, comp_vector,
+				IB_POLL_SOFTIRQ);
+	if (IS_ERR(queue->ib_cq)) {
+		ret = PTR_ERR(queue->ib_cq);
+		goto out;
+	}
+
+	ret = nvme_rdma_create_qp(queue, send_wr_factor);
+	if (ret)
+		goto out_destroy_ib_cq;
+
+	queue->rsp_ring = nvme_rdma_alloc_ring(ibdev, queue->queue_size,
+			sizeof(struct nvme_completion), DMA_FROM_DEVICE);
+	if (!queue->rsp_ring) {
+		ret = -ENOMEM;
+		goto out_destroy_qp;
+	}
+
+	return 0;
+
+out_destroy_qp:
+	ib_destroy_qp(queue->qp);
+out_destroy_ib_cq:
+	ib_free_cq(queue->ib_cq);
+out:
+	return ret;
+}
+
+static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
+		int idx, size_t queue_size)
+{
+	struct nvme_rdma_queue *queue;
+	int ret;
+
+	queue = &ctrl->queues[idx];
+	queue->ctrl = ctrl;
+	init_completion(&queue->cm_done);
+
+	if (idx > 0)
+		queue->cmnd_capsule_len = ctrl->ctrl.ioccsz * 16;
+	else
+		queue->cmnd_capsule_len = sizeof(struct nvme_command);
+
+	queue->queue_size = queue_size;
+
+	queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue,
+			RDMA_PS_TCP, IB_QPT_RC);
+	if (IS_ERR(queue->cm_id)) {
+		dev_info(ctrl->ctrl.device,
+			"failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id));
+		return PTR_ERR(queue->cm_id);
+	}
+
+	queue->cm_error = -ETIMEDOUT;
+	ret = rdma_resolve_addr(queue->cm_id, NULL, &ctrl->addr,
+			NVME_RDMA_CONNECT_TIMEOUT_MS);
+	if (ret) {
+		dev_info(ctrl->ctrl.device,
+			"rdma_resolve_addr failed (%d).\n", ret);
+		goto out_destroy_cm_id;
+	}
+
+	ret = nvme_rdma_wait_for_cm(queue);
+	if (ret) {
+		dev_info(ctrl->ctrl.device,
+			"rdma_resolve_addr wait failed (%d).\n", ret);
+		goto out_destroy_cm_id;
+	}
+
+	set_bit(NVME_RDMA_Q_CONNECTED, &queue->flags);
+
+	return 0;
+
+out_destroy_cm_id:
+	rdma_destroy_id(queue->cm_id);
+	return ret;
+}
+
+static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
+{
+	rdma_disconnect(queue->cm_id);
+	ib_drain_qp(queue->qp);
+}
+
+static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
+{
+	nvme_rdma_destroy_queue_ib(queue);
+	rdma_destroy_id(queue->cm_id);
+}
+
+static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue)
+{
+	if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
+		return;
+	nvme_rdma_stop_queue(queue);
+	nvme_rdma_free_queue(queue);
+}
+
+static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	int i;
+
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
+}
+
+static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	int i, ret = 0;
+
+	for (i = 1; i < ctrl->queue_count; i++) {
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	int i, ret;
+
+	for (i = 1; i < ctrl->queue_count; i++) {
+		ret = nvme_rdma_init_queue(ctrl, i, ctrl->ctrl.sqsize);
+		if (ret) {
+			dev_info(ctrl->ctrl.device,
+				"failed to initialize i/o queue: %d\n", ret);
+			goto out_free_queues;
+		}
+	}
+
+	return 0;
+
+out_free_queues:
+	for (; i >= 1; i--)
+		nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
+
+	return ret;
+}
+
+static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl)
+{
+	nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+	nvme_rdma_stop_and_free_queue(&ctrl->queues[0]);
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+	nvme_rdma_dev_put(ctrl->device);
+}
+
+static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+	if (list_empty(&ctrl->list))
+		goto free_ctrl;
+
+	mutex_lock(&nvme_rdma_ctrl_mutex);
+	list_del(&ctrl->list);
+	mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+	if (ctrl->ctrl.tagset) {
+		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_free_tag_set(&ctrl->tag_set);
+		nvme_rdma_dev_put(ctrl->device);
+	}
+	kfree(ctrl->queues);
+	nvmf_free_options(nctrl->opts);
+free_ctrl:
+	kfree(ctrl);
+}
+
+static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_rdma_ctrl, reconnect_work);
+	bool changed;
+	int ret;
+
+	if (ctrl->queue_count > 1) {
+		nvme_rdma_free_io_queues(ctrl);
+
+		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+		if (ret)
+			goto requeue;
+	}
+
+	nvme_rdma_stop_and_free_queue(&ctrl->queues[0]);
+
+	ret = blk_mq_reinit_tagset(&ctrl->admin_tag_set);
+	if (ret)
+		goto requeue;
+
+	ret = nvme_rdma_init_queue(ctrl, 0, NVMF_AQ_DEPTH);
+	if (ret)
+		goto requeue;
+
+	blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
+
+	ret = nvmf_connect_admin_queue(&ctrl->ctrl);
+	if (ret)
+		goto stop_admin_q;
+
+	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
+	if (ret)
+		goto stop_admin_q;
+
+	nvme_start_keep_alive(&ctrl->ctrl);
+
+	if (ctrl->queue_count > 1) {
+		ret = nvme_rdma_init_io_queues(ctrl);
+		if (ret)
+			goto stop_admin_q;
+
+		ret = nvme_rdma_connect_io_queues(ctrl);
+		if (ret)
+			goto stop_admin_q;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	if (ctrl->queue_count > 1)
+		nvme_start_queues(&ctrl->ctrl);
+
+	dev_info(ctrl->ctrl.device, "Successfully reconnected\n");
+
+	return;
+
+stop_admin_q:
+	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
+requeue:
+	/* Make sure we are not resetting/deleting */
+	if (ctrl->ctrl.state == NVME_CTRL_RECONNECTING) {
+		dev_info(ctrl->ctrl.device,
+			"Failed reconnect attempt, requeueing...\n");
+		queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+					ctrl->reconnect_delay * HZ);
+	}
+}
+
+static void nvme_rdma_error_recovery_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+			struct nvme_rdma_ctrl, err_work);
+
+	nvme_stop_keep_alive(&ctrl->ctrl);
+	if (ctrl->queue_count > 1)
+		nvme_stop_queues(&ctrl->ctrl);
+	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
+
+	/* We must take care of fastfail/requeue all our inflight requests */
+	if (ctrl->queue_count > 1)
+		blk_mq_tagset_busy_iter(&ctrl->tag_set,
+					nvme_cancel_request, &ctrl->ctrl);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+				nvme_cancel_request, &ctrl->ctrl);
+
+	dev_info(ctrl->ctrl.device, "reconnecting in %d seconds\n",
+		ctrl->reconnect_delay);
+
+	queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+				ctrl->reconnect_delay * HZ);
+}
+
+static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
+{
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING))
+		return;
+
+	queue_work(nvme_rdma_wq, &ctrl->err_work);
+}
+
+static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
+		const char *op)
+{
+	struct nvme_rdma_queue *queue = cq->cq_context;
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+
+	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+		dev_info(ctrl->ctrl.device,
+			     "%s for CQE 0x%p failed with status %s (%d)\n",
+			     op, wc->wr_cqe,
+			     ib_wc_status_msg(wc->status), wc->status);
+	nvme_rdma_error_recovery(ctrl);
+}
+
+static void nvme_rdma_memreg_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		nvme_rdma_wr_error(cq, wc, "MEMREG");
+}
+
+static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		nvme_rdma_wr_error(cq, wc, "LOCAL_INV");
+}
+
+static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req)
+{
+	struct ib_send_wr *bad_wr;
+	struct ib_send_wr wr = {
+		.opcode		    = IB_WR_LOCAL_INV,
+		.next		    = NULL,
+		.num_sge	    = 0,
+		.send_flags	    = 0,
+		.ex.invalidate_rkey = req->mr->rkey,
+	};
+
+	req->reg_cqe.done = nvme_rdma_inv_rkey_done;
+	wr.wr_cqe = &req->reg_cqe;
+
+	return ib_post_send(queue->qp, &wr, &bad_wr);
+}
+
+static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
+		struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+	int res;
+
+	if (!blk_rq_bytes(rq))
+		return;
+
+	if (req->need_inval) {
+		res = nvme_rdma_inv_rkey(queue, req);
+		if (res < 0) {
+			dev_err(ctrl->ctrl.device,
+				"Queueing INV WR for rkey %#x failed (%d)\n",
+				req->mr->rkey, res);
+			nvme_rdma_error_recovery(queue->ctrl);
+		}
+	}
+
+	ib_dma_unmap_sg(ibdev, req->sg_table.sgl,
+			req->nents, rq_data_dir(rq) ==
+				    WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+
+	nvme_cleanup_cmd(rq);
+	sg_free_table_chained(&req->sg_table, true);
+}
+
+static int nvme_rdma_set_sg_null(struct nvme_command *c)
+{
+	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+
+	sg->addr = 0;
+	put_unaligned_le24(0, sg->length);
+	put_unaligned_le32(0, sg->key);
+	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
+	return 0;
+}
+
+static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req, struct nvme_command *c)
+{
+	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;
+
+	req->sge[1].addr = sg_dma_address(req->sg_table.sgl);
+	req->sge[1].length = sg_dma_len(req->sg_table.sgl);
+	req->sge[1].lkey = queue->device->pd->local_dma_lkey;
+
+	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);
+	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));
+	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;
+
+	req->inline_data = true;
+	req->num_sge++;
+	return 0;
+}
+
+static int nvme_rdma_map_sg_single(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req, struct nvme_command *c)
+{
+	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+
+	sg->addr = cpu_to_le64(sg_dma_address(req->sg_table.sgl));
+	put_unaligned_le24(sg_dma_len(req->sg_table.sgl), sg->length);
+	put_unaligned_le32(queue->device->mr->rkey, sg->key);
+	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
+	return 0;
+}
+
+static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_request *req, struct nvme_command *c,
+		int count)
+{
+	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+	int nr;
+
+	nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, PAGE_SIZE);
+	if (nr < count) {
+		if (nr < 0)
+			return nr;
+		return -EINVAL;
+	}
+
+	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
+
+	req->reg_cqe.done = nvme_rdma_memreg_done;
+	memset(&req->reg_wr, 0, sizeof(req->reg_wr));
+	req->reg_wr.wr.opcode = IB_WR_REG_MR;
+	req->reg_wr.wr.wr_cqe = &req->reg_cqe;
+	req->reg_wr.wr.num_sge = 0;
+	req->reg_wr.mr = req->mr;
+	req->reg_wr.key = req->mr->rkey;
+	req->reg_wr.access = IB_ACCESS_LOCAL_WRITE |
+			     IB_ACCESS_REMOTE_READ |
+			     IB_ACCESS_REMOTE_WRITE;
+
+	req->need_inval = true;
+
+	sg->addr = cpu_to_le64(req->mr->iova);
+	put_unaligned_le24(req->mr->length, sg->length);
+	put_unaligned_le32(req->mr->rkey, sg->key);
+	sg->type = (NVME_KEY_SGL_FMT_DATA_DESC << 4) |
+			NVME_SGL_FMT_INVALIDATE;
+
+	return 0;
+}
+
+static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
+		struct request *rq, unsigned int map_len,
+		struct nvme_command *c)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_device *dev = queue->device;
+	struct ib_device *ibdev = dev->dev;
+	int nents, count;
+	int ret;
+
+	req->num_sge = 1;
+	req->inline_data = false;
+	req->need_inval = false;
+
+	c->common.flags |= NVME_CMD_SGL_METABUF;
+
+	if (!blk_rq_bytes(rq))
+		return nvme_rdma_set_sg_null(c);
+
+	req->sg_table.sgl = req->first_sgl;
+	ret = sg_alloc_table_chained(&req->sg_table, rq->nr_phys_segments,
+				req->sg_table.sgl);
+	if (ret)
+		return -ENOMEM;
+
+	nents = blk_rq_map_sg(rq->q, rq, req->sg_table.sgl);
+	BUG_ON(nents > rq->nr_phys_segments);
+	req->nents = nents;
+
+	count = ib_dma_map_sg(ibdev, req->sg_table.sgl, nents,
+		    rq_data_dir(rq) == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+	if (unlikely(count <= 0)) {
+		sg_free_table_chained(&req->sg_table, true);
+		return -EIO;
+	}
+
+	if (count == 1) {
+		if (rq_data_dir(rq) == WRITE &&
+		    map_len <= nvme_rdma_inline_data_size(queue) &&
+		    nvme_rdma_queue_idx(queue))
+			return nvme_rdma_map_sg_inline(queue, req, c);
+
+		if (!register_always)
+			return nvme_rdma_map_sg_single(queue, req, c);
+	}
+
+	return nvme_rdma_map_sg_fr(queue, req, c, count);
+}
+
+static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	if (unlikely(wc->status != IB_WC_SUCCESS))
+		nvme_rdma_wr_error(cq, wc, "SEND");
+}
+
+static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
+		struct ib_send_wr *first, bool flush)
+{
+	struct ib_send_wr wr, *bad_wr;
+	int ret;
+
+	sge->addr   = qe->dma;
+	sge->length = sizeof(struct nvme_command),
+	sge->lkey   = queue->device->pd->local_dma_lkey;
+
+	qe->cqe.done = nvme_rdma_send_done;
+
+	wr.next       = NULL;
+	wr.wr_cqe     = &qe->cqe;
+	wr.sg_list    = sge;
+	wr.num_sge    = num_sge;
+	wr.opcode     = IB_WR_SEND;
+	wr.send_flags = 0;
+
+	/*
+	 * Unsignalled send completions are another giant desaster in the
+	 * IB Verbs spec:  If we don't regularly post signalled sends
+	 * the send queue will fill up and only a QP reset will rescue us.
+	 * Would have been way to obvious to handle this in hardware or
+	 * at least the RDMA stack..
+	 *
+	 * This messy and racy code sniplet is copy and pasted from the iSER
+	 * initiator, and the magic '32' comes from there as well.
+	 *
+	 * Always signal the flushes. The magic request used for the flush
+	 * sequencer is not allocated in our driver's tagset and it's
+	 * triggered to be freed by blk_cleanup_queue(). So we need to
+	 * always mark it as signaled to ensure that the "wr_cqe", which is
+	 * embeded in request's payload, is not freed when __ib_process_cq()
+	 * calls wr_cqe->done().
+	 */
+	if ((++queue->sig_count % 32) == 0 || flush)
+		wr.send_flags |= IB_SEND_SIGNALED;
+
+	if (first)
+		first->next = &wr;
+	else
+		first = &wr;
+
+	ret = ib_post_send(queue->qp, first, &bad_wr);
+	if (ret) {
+		dev_err(queue->ctrl->ctrl.device,
+			     "%s failed with error code %d\n", __func__, ret);
+	}
+	return ret;
+}
+
+static int nvme_rdma_post_recv(struct nvme_rdma_queue *queue,
+		struct nvme_rdma_qe *qe)
+{
+	struct ib_recv_wr wr, *bad_wr;
+	struct ib_sge list;
+	int ret;
+
+	list.addr   = qe->dma;
+	list.length = sizeof(struct nvme_completion);
+	list.lkey   = queue->device->pd->local_dma_lkey;
+
+	qe->cqe.done = nvme_rdma_recv_done;
+
+	wr.next     = NULL;
+	wr.wr_cqe   = &qe->cqe;
+	wr.sg_list  = &list;
+	wr.num_sge  = 1;
+
+	ret = ib_post_recv(queue->qp, &wr, &bad_wr);
+	if (ret) {
+		dev_err(queue->ctrl->ctrl.device,
+			"%s failed with error code %d\n", __func__, ret);
+	}
+	return ret;
+}
+
+static struct blk_mq_tags *nvme_rdma_tagset(struct nvme_rdma_queue *queue)
+{
+	u32 queue_idx = nvme_rdma_queue_idx(queue);
+
+	if (queue_idx == 0)
+		return queue->ctrl->admin_tag_set.tags[queue_idx];
+	return queue->ctrl->tag_set.tags[queue_idx - 1];
+}
+
+static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg);
+	struct nvme_rdma_queue *queue = &ctrl->queues[0];
+	struct ib_device *dev = queue->device->dev;
+	struct nvme_rdma_qe *sqe = &ctrl->async_event_sqe;
+	struct nvme_command *cmd = sqe->data;
+	struct ib_sge sge;
+	int ret;
+
+	if (WARN_ON_ONCE(aer_idx != 0))
+		return;
+
+	ib_dma_sync_single_for_cpu(dev, sqe->dma, sizeof(*cmd), DMA_TO_DEVICE);
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->common.opcode = nvme_admin_async_event;
+	cmd->common.command_id = NVME_RDMA_AQ_BLKMQ_DEPTH;
+	cmd->common.flags |= NVME_CMD_SGL_METABUF;
+	nvme_rdma_set_sg_null(cmd);
+
+	ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(*cmd),
+			DMA_TO_DEVICE);
+
+	ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL, false);
+	WARN_ON_ONCE(ret);
+}
+
+static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
+		struct nvme_completion *cqe, struct ib_wc *wc, int tag)
+{
+	u16 status = le16_to_cpu(cqe->status);
+	struct request *rq;
+	struct nvme_rdma_request *req;
+	int ret = 0;
+
+	status >>= 1;
+
+	rq = blk_mq_tag_to_rq(nvme_rdma_tagset(queue), cqe->command_id);
+	if (!rq) {
+		dev_err(queue->ctrl->ctrl.device,
+			"tag 0x%x on QP %#x not found\n",
+			cqe->command_id, queue->qp->qp_num);
+		nvme_rdma_error_recovery(queue->ctrl);
+		return ret;
+	}
+	req = blk_mq_rq_to_pdu(rq);
+
+	if (rq->cmd_type == REQ_TYPE_DRV_PRIV && rq->special)
+		memcpy(rq->special, cqe, sizeof(*cqe));
+
+	if (rq->tag == tag)
+		ret = 1;
+
+	if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) &&
+	    wc->ex.invalidate_rkey == req->mr->rkey)
+		req->need_inval = false;
+
+	blk_mq_complete_request(rq, status);
+
+	return ret;
+}
+
+static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag)
+{
+	struct nvme_rdma_qe *qe =
+		container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe);
+	struct nvme_rdma_queue *queue = cq->cq_context;
+	struct ib_device *ibdev = queue->device->dev;
+	struct nvme_completion *cqe = qe->data;
+	const size_t len = sizeof(struct nvme_completion);
+	int ret = 0;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		nvme_rdma_wr_error(cq, wc, "RECV");
+		return 0;
+	}
+
+	ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
+	/*
+	 * AEN requests are special as they don't time out and can
+	 * survive any kind of queue freeze and often don't respond to
+	 * aborts.  We don't even bother to allocate a struct request
+	 * for them but rather special case them here.
+	 */
+	if (unlikely(nvme_rdma_queue_idx(queue) == 0 &&
+			cqe->command_id >= NVME_RDMA_AQ_BLKMQ_DEPTH))
+		nvme_complete_async_event(&queue->ctrl->ctrl, cqe);
+	else
+		ret = nvme_rdma_process_nvme_rsp(queue, cqe, wc, tag);
+	ib_dma_sync_single_for_device(ibdev, qe->dma, len, DMA_FROM_DEVICE);
+
+	nvme_rdma_post_recv(queue, qe);
+	return ret;
+}
+
+static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	__nvme_rdma_recv_done(cq, wc, -1);
+}
+
+static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue)
+{
+	int ret, i;
+
+	for (i = 0; i < queue->queue_size; i++) {
+		ret = nvme_rdma_post_recv(queue, &queue->rsp_ring[i]);
+		if (ret)
+			goto out_destroy_queue_ib;
+	}
+
+	return 0;
+
+out_destroy_queue_ib:
+	nvme_rdma_destroy_queue_ib(queue);
+	return ret;
+}
+
+static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue,
+		struct rdma_cm_event *ev)
+{
+	if (ev->param.conn.private_data_len) {
+		struct nvme_rdma_cm_rej *rej =
+			(struct nvme_rdma_cm_rej *)ev->param.conn.private_data;
+
+		dev_err(queue->ctrl->ctrl.device,
+			"Connect rejected, status %d.", le16_to_cpu(rej->sts));
+		/* XXX: Think of something clever to do here... */
+	} else {
+		dev_err(queue->ctrl->ctrl.device,
+			"Connect rejected, no private data.\n");
+	}
+
+	return -ECONNRESET;
+}
+
+static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_device *dev;
+	int ret;
+
+	dev = nvme_rdma_find_get_device(queue->cm_id);
+	if (!dev) {
+		dev_err(queue->cm_id->device->dma_device,
+			"no client data found!\n");
+		return -ECONNREFUSED;
+	}
+
+	ret = nvme_rdma_create_queue_ib(queue, dev);
+	if (ret) {
+		nvme_rdma_dev_put(dev);
+		goto out;
+	}
+
+	ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CONNECT_TIMEOUT_MS);
+	if (ret) {
+		dev_err(queue->ctrl->ctrl.device,
+			"rdma_resolve_route failed (%d).\n",
+			queue->cm_error);
+		goto out_destroy_queue;
+	}
+
+	return 0;
+
+out_destroy_queue:
+	nvme_rdma_destroy_queue_ib(queue);
+out:
+	return ret;
+}
+
+static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	struct rdma_conn_param param = { };
+	struct nvme_rdma_cm_req priv;
+	int ret;
+
+	param.qp_num = queue->qp->qp_num;
+	param.flow_control = 1;
+
+	param.responder_resources = queue->device->dev->attrs.max_qp_rd_atom;
+	/* maximum retry count */
+	param.retry_count = 7;
+	param.rnr_retry_count = 7;
+	param.private_data = &priv;
+	param.private_data_len = sizeof(priv);
+
+	priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
+	priv.qid = cpu_to_le16(nvme_rdma_queue_idx(queue));
+	priv.hrqsize = cpu_to_le16(queue->queue_size);
+	priv.hsqsize = cpu_to_le16(queue->queue_size);
+
+	ret = rdma_connect(queue->cm_id, &param);
+	if (ret) {
+		dev_err(ctrl->ctrl.device,
+			"rdma_connect failed (%d).\n", ret);
+		goto out_destroy_queue_ib;
+	}
+
+	return 0;
+
+out_destroy_queue_ib:
+	nvme_rdma_destroy_queue_ib(queue);
+	return ret;
+}
+
+/**
+ * nvme_rdma_device_unplug() - Handle RDMA device unplug
+ * @queue:      Queue that owns the cm_id that caught the event
+ *
+ * DEVICE_REMOVAL event notifies us that the RDMA device is about
+ * to unplug so we should take care of destroying our RDMA resources.
+ * This event will be generated for each allocated cm_id.
+ *
+ * In our case, the RDMA resources are managed per controller and not
+ * only per queue. So the way we handle this is we trigger an implicit
+ * controller deletion upon the first DEVICE_REMOVAL event we see, and
+ * hold the event inflight until the controller deletion is completed.
+ *
+ * One exception that we need to handle is the destruction of the cm_id
+ * that caught the event. Since we hold the callout until the controller
+ * deletion is completed, we'll deadlock if the controller deletion will
+ * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership
+ * of destroying this queue before-hand, destroy the queue resources
+ * after the controller deletion completed with the exception of destroying
+ * the cm_id implicitely by returning a non-zero rc to the callout.
+ */
+static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue)
+{
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+	int ret, ctrl_deleted = 0;
+
+	/* First disable the queue so ctrl delete won't free it */
+	if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
+		goto out;
+
+	/* delete the controller */
+	ret = __nvme_rdma_del_ctrl(ctrl);
+	if (!ret) {
+		dev_warn(ctrl->ctrl.device,
+			"Got rdma device removal event, deleting ctrl\n");
+		flush_work(&ctrl->delete_work);
+
+		/* Return non-zero so the cm_id will destroy implicitly */
+		ctrl_deleted = 1;
+
+		/* Free this queue ourselves */
+		rdma_disconnect(queue->cm_id);
+		ib_drain_qp(queue->qp);
+		nvme_rdma_destroy_queue_ib(queue);
+	}
+
+out:
+	return ctrl_deleted;
+}
+
+static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
+		struct rdma_cm_event *ev)
+{
+	struct nvme_rdma_queue *queue = cm_id->context;
+	int cm_error = 0;
+
+	dev_dbg(queue->ctrl->ctrl.device, "%s (%d): status %d id %p\n",
+		rdma_event_msg(ev->event), ev->event,
+		ev->status, cm_id);
+
+	switch (ev->event) {
+	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		cm_error = nvme_rdma_addr_resolved(queue);
+		break;
+	case RDMA_CM_EVENT_ROUTE_RESOLVED:
+		cm_error = nvme_rdma_route_resolved(queue);
+		break;
+	case RDMA_CM_EVENT_ESTABLISHED:
+		queue->cm_error = nvme_rdma_conn_established(queue);
+		/* complete cm_done regardless of success/failure */
+		complete(&queue->cm_done);
+		return 0;
+	case RDMA_CM_EVENT_REJECTED:
+		cm_error = nvme_rdma_conn_rejected(queue, ev);
+		break;
+	case RDMA_CM_EVENT_ADDR_ERROR:
+	case RDMA_CM_EVENT_ROUTE_ERROR:
+	case RDMA_CM_EVENT_CONNECT_ERROR:
+	case RDMA_CM_EVENT_UNREACHABLE:
+		dev_dbg(queue->ctrl->ctrl.device,
+			"CM error event %d\n", ev->event);
+		cm_error = -ECONNRESET;
+		break;
+	case RDMA_CM_EVENT_DISCONNECTED:
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
+		dev_dbg(queue->ctrl->ctrl.device,
+			"disconnect received - connection closed\n");
+		nvme_rdma_error_recovery(queue->ctrl);
+		break;
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+		/* return 1 means impliciy CM ID destroy */
+		return nvme_rdma_device_unplug(queue);
+	default:
+		dev_err(queue->ctrl->ctrl.device,
+			"Unexpected RDMA CM event (%d)\n", ev->event);
+		nvme_rdma_error_recovery(queue->ctrl);
+		break;
+	}
+
+	if (cm_error) {
+		queue->cm_error = cm_error;
+		complete(&queue->cm_done);
+	}
+
+	return 0;
+}
+
+static enum blk_eh_timer_return
+nvme_rdma_timeout(struct request *rq, bool reserved)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+
+	/* queue error recovery */
+	nvme_rdma_error_recovery(req->queue->ctrl);
+
+	/* fail with DNR on cmd timeout */
+	rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+
+	return BLK_EH_HANDLED;
+}
+
+static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
+{
+	struct nvme_ns *ns = hctx->queue->queuedata;
+	struct nvme_rdma_queue *queue = hctx->driver_data;
+	struct request *rq = bd->rq;
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_qe *sqe = &req->sqe;
+	struct nvme_command *c = sqe->data;
+	bool flush = false;
+	struct ib_device *dev;
+	unsigned int map_len;
+	int ret;
+
+	WARN_ON_ONCE(rq->tag < 0);
+
+	dev = queue->device->dev;
+	ib_dma_sync_single_for_cpu(dev, sqe->dma,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+
+	ret = nvme_setup_cmd(ns, rq, c);
+	if (ret)
+		return ret;
+
+	c->common.command_id = rq->tag;
+	blk_mq_start_request(rq);
+
+	map_len = nvme_map_len(rq);
+	ret = nvme_rdma_map_data(queue, rq, map_len, c);
+	if (ret < 0) {
+		dev_err(queue->ctrl->ctrl.device,
+			     "Failed to map data (%d)\n", ret);
+		nvme_cleanup_cmd(rq);
+		goto err;
+	}
+
+	ib_dma_sync_single_for_device(dev, sqe->dma,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+
+	if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH)
+		flush = true;
+	ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
+			req->need_inval ? &req->reg_wr.wr : NULL, flush);
+	if (ret) {
+		nvme_rdma_unmap_data(queue, rq);
+		goto err;
+	}
+
+	return BLK_MQ_RQ_QUEUE_OK;
+err:
+	return (ret == -ENOMEM || ret == -EAGAIN) ?
+		BLK_MQ_RQ_QUEUE_BUSY : BLK_MQ_RQ_QUEUE_ERROR;
+}
+
+static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+{
+	struct nvme_rdma_queue *queue = hctx->driver_data;
+	struct ib_cq *cq = queue->ib_cq;
+	struct ib_wc wc;
+	int found = 0;
+
+	ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
+	while (ib_poll_cq(cq, 1, &wc) > 0) {
+		struct ib_cqe *cqe = wc.wr_cqe;
+
+		if (cqe) {
+			if (cqe->done == nvme_rdma_recv_done)
+				found |= __nvme_rdma_recv_done(cq, &wc, tag);
+			else
+				cqe->done(cq, &wc);
+		}
+	}
+
+	return found;
+}
+
+static void nvme_rdma_complete_rq(struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = req->queue;
+	int error = 0;
+
+	nvme_rdma_unmap_data(queue, rq);
+
+	if (unlikely(rq->errors)) {
+		if (nvme_req_needs_retry(rq, rq->errors)) {
+			nvme_requeue_req(rq);
+			return;
+		}
+
+		if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+			error = rq->errors;
+		else
+			error = nvme_error_status(rq->errors);
+	}
+
+	blk_mq_end_request(rq, error);
+}
+
+static struct blk_mq_ops nvme_rdma_mq_ops = {
+	.queue_rq	= nvme_rdma_queue_rq,
+	.complete	= nvme_rdma_complete_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= nvme_rdma_init_request,
+	.exit_request	= nvme_rdma_exit_request,
+	.reinit_request	= nvme_rdma_reinit_request,
+	.init_hctx	= nvme_rdma_init_hctx,
+	.poll		= nvme_rdma_poll,
+	.timeout	= nvme_rdma_timeout,
+};
+
+static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
+	.queue_rq	= nvme_rdma_queue_rq,
+	.complete	= nvme_rdma_complete_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= nvme_rdma_init_admin_request,
+	.exit_request	= nvme_rdma_exit_admin_request,
+	.reinit_request	= nvme_rdma_reinit_request,
+	.init_hctx	= nvme_rdma_init_admin_hctx,
+	.timeout	= nvme_rdma_timeout,
+};
+
+static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl)
+{
+	int error;
+
+	error = nvme_rdma_init_queue(ctrl, 0, NVMF_AQ_DEPTH);
+	if (error)
+		return error;
+
+	ctrl->device = ctrl->queues[0].device;
+
+	/*
+	 * We need a reference on the device as long as the tag_set is alive,
+	 * as the MRs in the request structures need a valid ib_device.
+	 */
+	error = -EINVAL;
+	if (!nvme_rdma_dev_get(ctrl->device))
+		goto out_free_queue;
+
+	ctrl->max_fr_pages = min_t(u32, NVME_RDMA_MAX_SEGMENTS,
+		ctrl->device->dev->attrs.max_fast_reg_page_list_len);
+
+	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
+	ctrl->admin_tag_set.ops = &nvme_rdma_admin_mq_ops;
+	ctrl->admin_tag_set.queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH;
+	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
+	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_rdma_request) +
+		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+	ctrl->admin_tag_set.driver_data = ctrl;
+	ctrl->admin_tag_set.nr_hw_queues = 1;
+	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
+
+	error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
+	if (error)
+		goto out_put_dev;
+
+	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+	if (IS_ERR(ctrl->ctrl.admin_q)) {
+		error = PTR_ERR(ctrl->ctrl.admin_q);
+		goto out_free_tagset;
+	}
+
+	error = nvmf_connect_admin_queue(&ctrl->ctrl);
+	if (error)
+		goto out_cleanup_queue;
+
+	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
+	if (error) {
+		dev_err(ctrl->ctrl.device,
+			"prop_get NVME_REG_CAP failed\n");
+		goto out_cleanup_queue;
+	}
+
+	ctrl->ctrl.sqsize =
+		min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
+
+	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
+	if (error)
+		goto out_cleanup_queue;
+
+	ctrl->ctrl.max_hw_sectors =
+		(ctrl->max_fr_pages - 1) << (PAGE_SHIFT - 9);
+
+	error = nvme_init_identify(&ctrl->ctrl);
+	if (error)
+		goto out_cleanup_queue;
+
+	error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
+			&ctrl->async_event_sqe, sizeof(struct nvme_command),
+			DMA_TO_DEVICE);
+	if (error)
+		goto out_cleanup_queue;
+
+	nvme_start_keep_alive(&ctrl->ctrl);
+
+	return 0;
+
+out_cleanup_queue:
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_free_tagset:
+	/* disconnect and drain the queue before freeing the tagset */
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+out_put_dev:
+	nvme_rdma_dev_put(ctrl->device);
+out_free_queue:
+	nvme_rdma_free_queue(&ctrl->queues[0]);
+	return error;
+}
+
+static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl)
+{
+	nvme_stop_keep_alive(&ctrl->ctrl);
+	cancel_work_sync(&ctrl->err_work);
+	cancel_delayed_work_sync(&ctrl->reconnect_work);
+
+	if (ctrl->queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set,
+					nvme_cancel_request, &ctrl->ctrl);
+		nvme_rdma_free_io_queues(ctrl);
+	}
+
+	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+		nvme_shutdown_ctrl(&ctrl->ctrl);
+
+	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+				nvme_cancel_request, &ctrl->ctrl);
+	nvme_rdma_destroy_admin_queue(ctrl);
+}
+
+static void nvme_rdma_del_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+				struct nvme_rdma_ctrl, delete_work);
+
+	nvme_remove_namespaces(&ctrl->ctrl);
+	nvme_rdma_shutdown_ctrl(ctrl);
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+}
+
+static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl)
+{
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
+		return -EBUSY;
+
+	if (!queue_work(nvme_rdma_wq, &ctrl->delete_work))
+		return -EBUSY;
+
+	return 0;
+}
+
+static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+	int ret;
+
+	ret = __nvme_rdma_del_ctrl(ctrl);
+	if (ret)
+		return ret;
+
+	flush_work(&ctrl->delete_work);
+
+	return 0;
+}
+
+static void nvme_rdma_remove_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+				struct nvme_rdma_ctrl, delete_work);
+
+	nvme_remove_namespaces(&ctrl->ctrl);
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+}
+
+static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(work,
+					struct nvme_rdma_ctrl, reset_work);
+	int ret;
+	bool changed;
+
+	nvme_rdma_shutdown_ctrl(ctrl);
+
+	ret = nvme_rdma_configure_admin_queue(ctrl);
+	if (ret) {
+		/* ctrl is already shutdown, just remove the ctrl */
+		INIT_WORK(&ctrl->delete_work, nvme_rdma_remove_ctrl_work);
+		goto del_dead_ctrl;
+	}
+
+	if (ctrl->queue_count > 1) {
+		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+		if (ret)
+			goto del_dead_ctrl;
+
+		ret = nvme_rdma_init_io_queues(ctrl);
+		if (ret)
+			goto del_dead_ctrl;
+
+		ret = nvme_rdma_connect_io_queues(ctrl);
+		if (ret)
+			goto del_dead_ctrl;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	if (ctrl->queue_count > 1) {
+		nvme_start_queues(&ctrl->ctrl);
+		nvme_queue_scan(&ctrl->ctrl);
+	}
+
+	return;
+
+del_dead_ctrl:
+	/* Deleting this dead controller... */
+	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
+	WARN_ON(!queue_work(nvme_rdma_wq, &ctrl->delete_work));
+}
+
+static int nvme_rdma_reset_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
+		return -EBUSY;
+
+	if (!queue_work(nvme_rdma_wq, &ctrl->reset_work))
+		return -EBUSY;
+
+	flush_work(&ctrl->reset_work);
+
+	return 0;
+}
+
+static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
+	.name			= "rdma",
+	.module			= THIS_MODULE,
+	.is_fabrics		= true,
+	.reg_read32		= nvmf_reg_read32,
+	.reg_read64		= nvmf_reg_read64,
+	.reg_write32		= nvmf_reg_write32,
+	.reset_ctrl		= nvme_rdma_reset_ctrl,
+	.free_ctrl		= nvme_rdma_free_ctrl,
+	.submit_async_event	= nvme_rdma_submit_async_event,
+	.delete_ctrl		= nvme_rdma_del_ctrl,
+	.get_subsysnqn		= nvmf_get_subsysnqn,
+	.get_address		= nvmf_get_address,
+};
+
+static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl)
+{
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	int ret;
+
+	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
+	if (ret)
+		return ret;
+
+	ctrl->queue_count = opts->nr_io_queues + 1;
+	if (ctrl->queue_count < 2)
+		return 0;
+
+	dev_info(ctrl->ctrl.device,
+		"creating %d I/O queues.\n", opts->nr_io_queues);
+
+	ret = nvme_rdma_init_io_queues(ctrl);
+	if (ret)
+		return ret;
+
+	/*
+	 * We need a reference on the device as long as the tag_set is alive,
+	 * as the MRs in the request structures need a valid ib_device.
+	 */
+	ret = -EINVAL;
+	if (!nvme_rdma_dev_get(ctrl->device))
+		goto out_free_io_queues;
+
+	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
+	ctrl->tag_set.ops = &nvme_rdma_mq_ops;
+	ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize;
+	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+	ctrl->tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	ctrl->tag_set.cmd_size = sizeof(struct nvme_rdma_request) +
+		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+	ctrl->tag_set.driver_data = ctrl;
+	ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
+	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
+
+	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
+	if (ret)
+		goto out_put_dev;
+	ctrl->ctrl.tagset = &ctrl->tag_set;
+
+	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
+	if (IS_ERR(ctrl->ctrl.connect_q)) {
+		ret = PTR_ERR(ctrl->ctrl.connect_q);
+		goto out_free_tag_set;
+	}
+
+	ret = nvme_rdma_connect_io_queues(ctrl);
+	if (ret)
+		goto out_cleanup_connect_q;
+
+	return 0;
+
+out_cleanup_connect_q:
+	blk_cleanup_queue(ctrl->ctrl.connect_q);
+out_free_tag_set:
+	blk_mq_free_tag_set(&ctrl->tag_set);
+out_put_dev:
+	nvme_rdma_dev_put(ctrl->device);
+out_free_io_queues:
+	nvme_rdma_free_io_queues(ctrl);
+	return ret;
+}
+
+static int nvme_rdma_parse_ipaddr(struct sockaddr_in *in_addr, char *p)
+{
+	u8 *addr = (u8 *)&in_addr->sin_addr.s_addr;
+	size_t buflen = strlen(p);
+
+	/* XXX: handle IPv6 addresses */
+
+	if (buflen > INET_ADDRSTRLEN)
+		return -EINVAL;
+	if (in4_pton(p, buflen, addr, '\0', NULL) == 0)
+		return -EINVAL;
+	in_addr->sin_family = AF_INET;
+	return 0;
+}
+
+static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
+		struct nvmf_ctrl_options *opts)
+{
+	struct nvme_rdma_ctrl *ctrl;
+	int ret;
+	bool changed;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return ERR_PTR(-ENOMEM);
+	ctrl->ctrl.opts = opts;
+	INIT_LIST_HEAD(&ctrl->list);
+
+	ret = nvme_rdma_parse_ipaddr(&ctrl->addr_in, opts->traddr);
+	if (ret) {
+		pr_err("malformed IP address passed: %s\n", opts->traddr);
+		goto out_free_ctrl;
+	}
+
+	if (opts->mask & NVMF_OPT_TRSVCID) {
+		u16 port;
+
+		ret = kstrtou16(opts->trsvcid, 0, &port);
+		if (ret)
+			goto out_free_ctrl;
+
+		ctrl->addr_in.sin_port = cpu_to_be16(port);
+	} else {
+		ctrl->addr_in.sin_port = cpu_to_be16(NVME_RDMA_IP_PORT);
+	}
+
+	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
+				0 /* no quirks, we're perfect! */);
+	if (ret)
+		goto out_free_ctrl;
+
+	ctrl->reconnect_delay = opts->reconnect_delay;
+	INIT_DELAYED_WORK(&ctrl->reconnect_work,
+			nvme_rdma_reconnect_ctrl_work);
+	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
+	INIT_WORK(&ctrl->delete_work, nvme_rdma_del_ctrl_work);
+	INIT_WORK(&ctrl->reset_work, nvme_rdma_reset_ctrl_work);
+	spin_lock_init(&ctrl->lock);
+
+	ctrl->queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */
+	ctrl->ctrl.sqsize = opts->queue_size;
+	ctrl->ctrl.kato = opts->kato;
+
+	ret = -ENOMEM;
+	ctrl->queues = kcalloc(ctrl->queue_count, sizeof(*ctrl->queues),
+				GFP_KERNEL);
+	if (!ctrl->queues)
+		goto out_uninit_ctrl;
+
+	ret = nvme_rdma_configure_admin_queue(ctrl);
+	if (ret)
+		goto out_kfree_queues;
+
+	/* sanity check icdoff */
+	if (ctrl->ctrl.icdoff) {
+		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
+		goto out_remove_admin_queue;
+	}
+
+	/* sanity check keyed sgls */
+	if (!(ctrl->ctrl.sgls & (1 << 20))) {
+		dev_err(ctrl->ctrl.device, "Mandatory keyed sgls are not support\n");
+		goto out_remove_admin_queue;
+	}
+
+	if (opts->queue_size > ctrl->ctrl.maxcmd) {
+		/* warn if maxcmd is lower than queue_size */
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl maxcmd %u, clamping down\n",
+			opts->queue_size, ctrl->ctrl.maxcmd);
+		opts->queue_size = ctrl->ctrl.maxcmd;
+	}
+
+	if (opts->nr_io_queues) {
+		ret = nvme_rdma_create_io_queues(ctrl);
+		if (ret)
+			goto out_remove_admin_queue;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
+		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+
+	kref_get(&ctrl->ctrl.kref);
+
+	mutex_lock(&nvme_rdma_ctrl_mutex);
+	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
+	mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+	if (opts->nr_io_queues) {
+		nvme_queue_scan(&ctrl->ctrl);
+		nvme_queue_async_events(&ctrl->ctrl);
+	}
+
+	return &ctrl->ctrl;
+
+out_remove_admin_queue:
+	nvme_stop_keep_alive(&ctrl->ctrl);
+	nvme_rdma_destroy_admin_queue(ctrl);
+out_kfree_queues:
+	kfree(ctrl->queues);
+out_uninit_ctrl:
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+	if (ret > 0)
+		ret = -EIO;
+	return ERR_PTR(ret);
+out_free_ctrl:
+	kfree(ctrl);
+	return ERR_PTR(ret);
+}
+
+static struct nvmf_transport_ops nvme_rdma_transport = {
+	.name		= "rdma",
+	.required_opts	= NVMF_OPT_TRADDR,
+	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY,
+	.create_ctrl	= nvme_rdma_create_ctrl,
+};
+
+static int __init nvme_rdma_init_module(void)
+{
+	nvme_rdma_wq = create_workqueue("nvme_rdma_wq");
+	if (!nvme_rdma_wq)
+		return -ENOMEM;
+
+	nvmf_register_transport(&nvme_rdma_transport);
+	return 0;
+}
+
+static void __exit nvme_rdma_cleanup_module(void)
+{
+	struct nvme_rdma_ctrl *ctrl;
+
+	nvmf_unregister_transport(&nvme_rdma_transport);
+
+	mutex_lock(&nvme_rdma_ctrl_mutex);
+	list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list)
+		__nvme_rdma_del_ctrl(ctrl);
+	mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+	destroy_workqueue(nvme_rdma_wq);
+}
+
+module_init(nvme_rdma_init_module);
+module_exit(nvme_rdma_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
new file mode 100644
index 000000000000..a5c31cbeb481
--- /dev/null
+++ b/drivers/nvme/target/Kconfig
@@ -0,0 +1,36 @@
+
+config NVME_TARGET
+	tristate "NVMe Target support"
+	depends on BLOCK
+	depends on CONFIGFS_FS
+	help
+	  This enabled target side support for the NVMe protocol, that is
+	  it allows the Linux kernel to implement NVMe subsystems and
+	  controllers and export Linux block devices as NVMe namespaces.
+	  You need to select at least one of the transports below to make this
+	  functionality useful.
+
+	  To configure the NVMe target you probably want to use the nvmetcli
+	  tool from http://git.infradead.org/users/hch/nvmetcli.git.
+
+config NVME_TARGET_LOOP
+	tristate "NVMe loopback device support"
+	depends on BLK_DEV_NVME
+	depends on NVME_TARGET
+	select NVME_FABRICS
+	select SG_POOL
+	help
+	  This enables the NVMe loopback device support, which can be useful
+	  to test NVMe host and target side features.
+
+	  If unsure, say N.
+
+config NVME_TARGET_RDMA
+	tristate "NVMe over Fabrics RDMA target support"
+	depends on INFINIBAND
+	depends on NVME_TARGET
+	help
+	  This enables the NVMe RDMA target support, which allows exporting NVMe
+	  devices over RDMA.
+
+	  If unsure, say N.
diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile
new file mode 100644
index 000000000000..b7a06232c9da
--- /dev/null
+++ b/drivers/nvme/target/Makefile
@@ -0,0 +1,9 @@
+
+obj-$(CONFIG_NVME_TARGET)		+= nvmet.o
+obj-$(CONFIG_NVME_TARGET_LOOP)		+= nvme-loop.o
+obj-$(CONFIG_NVME_TARGET_RDMA)		+= nvmet-rdma.o
+
+nvmet-y		+= core.o configfs.o admin-cmd.o io-cmd.o fabrics-cmd.o \
+			discovery.o
+nvme-loop-y	+= loop.o
+nvmet-rdma-y	+= rdma.o
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
new file mode 100644
index 000000000000..2fac17a5ad53
--- /dev/null
+++ b/drivers/nvme/target/admin-cmd.c
@@ -0,0 +1,465 @@
+/*
+ * NVMe admin command implementation.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/random.h>
+#include <generated/utsrelease.h>
+#include "nvmet.h"
+
+u32 nvmet_get_log_page_len(struct nvme_command *cmd)
+{
+	u32 len = le16_to_cpu(cmd->get_log_page.numdu);
+
+	len <<= 16;
+	len += le16_to_cpu(cmd->get_log_page.numdl);
+	/* NUMD is a 0's based value */
+	len += 1;
+	len *= sizeof(u32);
+
+	return len;
+}
+
+static void nvmet_execute_get_log_page(struct nvmet_req *req)
+{
+	size_t data_len = nvmet_get_log_page_len(req->cmd);
+	void *buf;
+	u16 status = 0;
+
+	buf = kzalloc(data_len, GFP_KERNEL);
+	if (!buf) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	switch (req->cmd->get_log_page.lid) {
+	case 0x01:
+		/*
+		 * We currently never set the More bit in the status field,
+		 * so all error log entries are invalid and can be zeroed out.
+		 * This is called a minum viable implementation (TM) of this
+		 * mandatory log page.
+		 */
+		break;
+	case 0x02:
+		/*
+		 * XXX: fill out actual smart log
+		 *
+		 * We might have a hard time coming up with useful values for
+		 * many of the fields, and even when we have useful data
+		 * available (e.g. units or commands read/written) those aren't
+		 * persistent over power loss.
+		 */
+		break;
+	case 0x03:
+		/*
+		 * We only support a single firmware slot which always is
+		 * active, so we can zero out the whole firmware slot log and
+		 * still claim to fully implement this mandatory log page.
+		 */
+		break;
+	default:
+		BUG();
+	}
+
+	status = nvmet_copy_to_sgl(req, 0, buf, data_len);
+
+	kfree(buf);
+out:
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvme_id_ctrl *id;
+	u64 serial;
+	u16 status = 0;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	/* XXX: figure out how to assign real vendors IDs. */
+	id->vid = 0;
+	id->ssvid = 0;
+
+	/* generate a random serial number as our controllers are ephemeral: */
+	get_random_bytes(&serial, sizeof(serial));
+	memset(id->sn, ' ', sizeof(id->sn));
+	snprintf(id->sn, sizeof(id->sn), "%llx", serial);
+
+	memset(id->mn, ' ', sizeof(id->mn));
+	strncpy((char *)id->mn, "Linux", sizeof(id->mn));
+
+	memset(id->fr, ' ', sizeof(id->fr));
+	strncpy((char *)id->fr, UTS_RELEASE, sizeof(id->fr));
+
+	id->rab = 6;
+
+	/*
+	 * XXX: figure out how we can assign a IEEE OUI, but until then
+	 * the safest is to leave it as zeroes.
+	 */
+
+	/* we support multiple ports and multiples hosts: */
+	id->mic = (1 << 0) | (1 << 1);
+
+	/* no limit on data transfer sizes for now */
+	id->mdts = 0;
+	id->cntlid = cpu_to_le16(ctrl->cntlid);
+	id->ver = cpu_to_le32(ctrl->subsys->ver);
+
+	/* XXX: figure out what to do about RTD3R/RTD3 */
+	id->oaes = cpu_to_le32(1 << 8);
+	id->ctratt = cpu_to_le32(1 << 0);
+
+	id->oacs = 0;
+
+	/*
+	 * We don't really have a practical limit on the number of abort
+	 * comands.  But we don't do anything useful for abort either, so
+	 * no point in allowing more abort commands than the spec requires.
+	 */
+	id->acl = 3;
+
+	id->aerl = NVMET_ASYNC_EVENTS - 1;
+
+	/* first slot is read-only, only one slot supported */
+	id->frmw = (1 << 0) | (1 << 1);
+	id->lpa = (1 << 0) | (1 << 2);
+	id->elpe = NVMET_ERROR_LOG_SLOTS - 1;
+	id->npss = 0;
+
+	/* We support keep-alive timeout in granularity of seconds */
+	id->kas = cpu_to_le16(NVMET_KAS);
+
+	id->sqes = (0x6 << 4) | 0x6;
+	id->cqes = (0x4 << 4) | 0x4;
+
+	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+
+	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
+	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM);
+
+	/* XXX: don't report vwc if the underlying device is write through */
+	id->vwc = NVME_CTRL_VWC_PRESENT;
+
+	/*
+	 * We can't support atomic writes bigger than a LBA without support
+	 * from the backend device.
+	 */
+	id->awun = 0;
+	id->awupf = 0;
+
+	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
+	if (ctrl->ops->has_keyed_sgls)
+		id->sgls |= cpu_to_le32(1 << 2);
+	if (ctrl->ops->sqe_inline_size)
+		id->sgls |= cpu_to_le32(1 << 20);
+
+	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
+
+	/* Max command capsule size is sqe + single page of in-capsule data */
+	id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) +
+				  ctrl->ops->sqe_inline_size) / 16);
+	/* Max response capsule size is cqe */
+	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);
+
+	id->msdbd = ctrl->ops->msdbd;
+
+	/*
+	 * Meh, we don't really support any power state.  Fake up the same
+	 * values that qemu does.
+	 */
+	id->psd[0].max_power = cpu_to_le16(0x9c4);
+	id->psd[0].entry_lat = cpu_to_le32(0x10);
+	id->psd[0].exit_lat = cpu_to_le32(0x4);
+
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+
+	kfree(id);
+out:
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_identify_ns(struct nvmet_req *req)
+{
+	struct nvmet_ns *ns;
+	struct nvme_id_ns *id;
+	u16 status = 0;
+
+	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid);
+	if (!ns) {
+		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+		goto out;
+	}
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id) {
+		status = NVME_SC_INTERNAL;
+		goto out_put_ns;
+	}
+
+	/*
+	 * nuse = ncap = nsze isn't aways true, but we have no way to find
+	 * that out from the underlying device.
+	 */
+	id->ncap = id->nuse = id->nsze =
+		cpu_to_le64(ns->size >> ns->blksize_shift);
+
+	/*
+	 * We just provide a single LBA format that matches what the
+	 * underlying device reports.
+	 */
+	id->nlbaf = 0;
+	id->flbas = 0;
+
+	/*
+	 * Our namespace might always be shared.  Not just with other
+	 * controllers, but also with any other user of the block device.
+	 */
+	id->nmic = (1 << 0);
+
+	memcpy(&id->nguid, &ns->nguid, sizeof(uuid_le));
+
+	id->lbaf[0].ds = ns->blksize_shift;
+
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+
+	kfree(id);
+out_put_ns:
+	nvmet_put_namespace(ns);
+out:
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_identify_nslist(struct nvmet_req *req)
+{
+	static const int buf_size = 4096;
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmet_ns *ns;
+	u32 min_nsid = le32_to_cpu(req->cmd->identify.nsid);
+	__le32 *list;
+	u16 status = 0;
+	int i = 0;
+
+	list = kzalloc(buf_size, GFP_KERNEL);
+	if (!list) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+		if (ns->nsid <= min_nsid)
+			continue;
+		list[i++] = cpu_to_le32(ns->nsid);
+		if (i == buf_size / sizeof(__le32))
+			break;
+	}
+	rcu_read_unlock();
+
+	status = nvmet_copy_to_sgl(req, 0, list, buf_size);
+
+	kfree(list);
+out:
+	nvmet_req_complete(req, status);
+}
+
+/*
+ * A "mimimum viable" abort implementation: the command is mandatory in the
+ * spec, but we are not required to do any useful work.  We couldn't really
+ * do a useful abort, so don't bother even with waiting for the command
+ * to be exectuted and return immediately telling the command to abort
+ * wasn't found.
+ */
+static void nvmet_execute_abort(struct nvmet_req *req)
+{
+	nvmet_set_result(req, 1);
+	nvmet_req_complete(req, 0);
+}
+
+static void nvmet_execute_set_features(struct nvmet_req *req)
+{
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
+	u64 val;
+	u32 val32;
+	u16 status = 0;
+
+	switch (cdw10 & 0xf) {
+	case NVME_FEAT_NUM_QUEUES:
+		nvmet_set_result(req,
+			(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
+		break;
+	case NVME_FEAT_KATO:
+		val = le64_to_cpu(req->cmd->prop_set.value);
+		val32 = val & 0xffff;
+		req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
+		nvmet_set_result(req, req->sq->ctrl->kato);
+		break;
+	default:
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		break;
+	}
+
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_get_features(struct nvmet_req *req)
+{
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
+	u16 status = 0;
+
+	switch (cdw10 & 0xf) {
+	/*
+	 * These features are mandatory in the spec, but we don't
+	 * have a useful way to implement them.  We'll eventually
+	 * need to come up with some fake values for these.
+	 */
+#if 0
+	case NVME_FEAT_ARBITRATION:
+		break;
+	case NVME_FEAT_POWER_MGMT:
+		break;
+	case NVME_FEAT_TEMP_THRESH:
+		break;
+	case NVME_FEAT_ERR_RECOVERY:
+		break;
+	case NVME_FEAT_IRQ_COALESCE:
+		break;
+	case NVME_FEAT_IRQ_CONFIG:
+		break;
+	case NVME_FEAT_WRITE_ATOMIC:
+		break;
+	case NVME_FEAT_ASYNC_EVENT:
+		break;
+#endif
+	case NVME_FEAT_VOLATILE_WC:
+		nvmet_set_result(req, 1);
+		break;
+	case NVME_FEAT_NUM_QUEUES:
+		nvmet_set_result(req,
+			(subsys->max_qid-1) | ((subsys->max_qid-1) << 16));
+		break;
+	case NVME_FEAT_KATO:
+		nvmet_set_result(req, req->sq->ctrl->kato * 1000);
+		break;
+	default:
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		break;
+	}
+
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_async_event(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+
+	mutex_lock(&ctrl->lock);
+	if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) {
+		mutex_unlock(&ctrl->lock);
+		nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_SC_DNR);
+		return;
+	}
+	ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
+	mutex_unlock(&ctrl->lock);
+
+	schedule_work(&ctrl->async_event_work);
+}
+
+static void nvmet_execute_keep_alive(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+
+	pr_debug("ctrl %d update keep-alive timer for %d secs\n",
+		ctrl->cntlid, ctrl->kato);
+
+	mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
+	nvmet_req_complete(req, 0);
+}
+
+int nvmet_parse_admin_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+
+	req->ns = NULL;
+
+	if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
+		pr_err("nvmet: got admin cmd %d while CC.EN == 0\n",
+				cmd->common.opcode);
+		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+	}
+	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
+		pr_err("nvmet: got admin cmd %d while CSTS.RDY == 0\n",
+				cmd->common.opcode);
+		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+	}
+
+	switch (cmd->common.opcode) {
+	case nvme_admin_get_log_page:
+		req->data_len = nvmet_get_log_page_len(cmd);
+
+		switch (cmd->get_log_page.lid) {
+		case 0x01:
+		case 0x02:
+		case 0x03:
+			req->execute = nvmet_execute_get_log_page;
+			return 0;
+		}
+		break;
+	case nvme_admin_identify:
+		req->data_len = 4096;
+		switch (le32_to_cpu(cmd->identify.cns)) {
+		case 0x00:
+			req->execute = nvmet_execute_identify_ns;
+			return 0;
+		case 0x01:
+			req->execute = nvmet_execute_identify_ctrl;
+			return 0;
+		case 0x02:
+			req->execute = nvmet_execute_identify_nslist;
+			return 0;
+		}
+		break;
+	case nvme_admin_abort_cmd:
+		req->execute = nvmet_execute_abort;
+		req->data_len = 0;
+		return 0;
+	case nvme_admin_set_features:
+		req->execute = nvmet_execute_set_features;
+		req->data_len = 0;
+		return 0;
+	case nvme_admin_get_features:
+		req->execute = nvmet_execute_get_features;
+		req->data_len = 0;
+		return 0;
+	case nvme_admin_async_event:
+		req->execute = nvmet_execute_async_event;
+		req->data_len = 0;
+		return 0;
+	case nvme_admin_keep_alive:
+		req->execute = nvmet_execute_keep_alive;
+		req->data_len = 0;
+		return 0;
+	}
+
+	pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+}
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
new file mode 100644
index 000000000000..af5e2dc4a3d5
--- /dev/null
+++ b/drivers/nvme/target/configfs.c
@@ -0,0 +1,917 @@
+/*
+ * Configfs interface for the NVMe target.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/ctype.h>
+
+#include "nvmet.h"
+
+static struct config_item_type nvmet_host_type;
+static struct config_item_type nvmet_subsys_type;
+
+/*
+ * nvmet_port Generic ConfigFS definitions.
+ * Used in any place in the ConfigFS tree that refers to an address.
+ */
+static ssize_t nvmet_addr_adrfam_show(struct config_item *item,
+		char *page)
+{
+	switch (to_nvmet_port(item)->disc_addr.adrfam) {
+	case NVMF_ADDR_FAMILY_IP4:
+		return sprintf(page, "ipv4\n");
+	case NVMF_ADDR_FAMILY_IP6:
+		return sprintf(page, "ipv6\n");
+	case NVMF_ADDR_FAMILY_IB:
+		return sprintf(page, "ib\n");
+	default:
+		return sprintf(page, "\n");
+	}
+}
+
+static ssize_t nvmet_addr_adrfam_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	if (port->enabled) {
+		pr_err("Cannot modify address while enabled\n");
+		pr_err("Disable the address before modifying\n");
+		return -EACCES;
+	}
+
+	if (sysfs_streq(page, "ipv4")) {
+		port->disc_addr.adrfam = NVMF_ADDR_FAMILY_IP4;
+	} else if (sysfs_streq(page, "ipv6")) {
+		port->disc_addr.adrfam = NVMF_ADDR_FAMILY_IP6;
+	} else if (sysfs_streq(page, "ib")) {
+		port->disc_addr.adrfam = NVMF_ADDR_FAMILY_IB;
+	} else {
+		pr_err("Invalid value '%s' for adrfam\n", page);
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, addr_adrfam);
+
+static ssize_t nvmet_addr_portid_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%d\n",
+			le16_to_cpu(port->disc_addr.portid));
+}
+
+static ssize_t nvmet_addr_portid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	u16 portid = 0;
+
+	if (kstrtou16(page, 0, &portid)) {
+		pr_err("Invalid value '%s' for portid\n", page);
+		return -EINVAL;
+	}
+
+	if (port->enabled) {
+		pr_err("Cannot modify address while enabled\n");
+		pr_err("Disable the address before modifying\n");
+		return -EACCES;
+	}
+	port->disc_addr.portid = cpu_to_le16(portid);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, addr_portid);
+
+static ssize_t nvmet_addr_traddr_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%s\n",
+			port->disc_addr.traddr);
+}
+
+static ssize_t nvmet_addr_traddr_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	if (count > NVMF_TRADDR_SIZE) {
+		pr_err("Invalid value '%s' for traddr\n", page);
+		return -EINVAL;
+	}
+
+	if (port->enabled) {
+		pr_err("Cannot modify address while enabled\n");
+		pr_err("Disable the address before modifying\n");
+		return -EACCES;
+	}
+	return snprintf(port->disc_addr.traddr,
+			sizeof(port->disc_addr.traddr), "%s", page);
+}
+
+CONFIGFS_ATTR(nvmet_, addr_traddr);
+
+static ssize_t nvmet_addr_treq_show(struct config_item *item,
+		char *page)
+{
+	switch (to_nvmet_port(item)->disc_addr.treq) {
+	case NVMF_TREQ_NOT_SPECIFIED:
+		return sprintf(page, "not specified\n");
+	case NVMF_TREQ_REQUIRED:
+		return sprintf(page, "required\n");
+	case NVMF_TREQ_NOT_REQUIRED:
+		return sprintf(page, "not required\n");
+	default:
+		return sprintf(page, "\n");
+	}
+}
+
+static ssize_t nvmet_addr_treq_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	if (port->enabled) {
+		pr_err("Cannot modify address while enabled\n");
+		pr_err("Disable the address before modifying\n");
+		return -EACCES;
+	}
+
+	if (sysfs_streq(page, "not specified")) {
+		port->disc_addr.treq = NVMF_TREQ_NOT_SPECIFIED;
+	} else if (sysfs_streq(page, "required")) {
+		port->disc_addr.treq = NVMF_TREQ_REQUIRED;
+	} else if (sysfs_streq(page, "not required")) {
+		port->disc_addr.treq = NVMF_TREQ_NOT_REQUIRED;
+	} else {
+		pr_err("Invalid value '%s' for treq\n", page);
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, addr_treq);
+
+static ssize_t nvmet_addr_trsvcid_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%s\n",
+			port->disc_addr.trsvcid);
+}
+
+static ssize_t nvmet_addr_trsvcid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	if (count > NVMF_TRSVCID_SIZE) {
+		pr_err("Invalid value '%s' for trsvcid\n", page);
+		return -EINVAL;
+	}
+	if (port->enabled) {
+		pr_err("Cannot modify address while enabled\n");
+		pr_err("Disable the address before modifying\n");
+		return -EACCES;
+	}
+	return snprintf(port->disc_addr.trsvcid,
+			sizeof(port->disc_addr.trsvcid), "%s", page);
+}
+
+CONFIGFS_ATTR(nvmet_, addr_trsvcid);
+
+static ssize_t nvmet_addr_trtype_show(struct config_item *item,
+		char *page)
+{
+	switch (to_nvmet_port(item)->disc_addr.trtype) {
+	case NVMF_TRTYPE_RDMA:
+		return sprintf(page, "rdma\n");
+	case NVMF_TRTYPE_LOOP:
+		return sprintf(page, "loop\n");
+	default:
+		return sprintf(page, "\n");
+	}
+}
+
+static void nvmet_port_init_tsas_rdma(struct nvmet_port *port)
+{
+	port->disc_addr.trtype = NVMF_TRTYPE_RDMA;
+	memset(&port->disc_addr.tsas.rdma, 0, NVMF_TSAS_SIZE);
+	port->disc_addr.tsas.rdma.qptype = NVMF_RDMA_QPTYPE_CONNECTED;
+	port->disc_addr.tsas.rdma.prtype = NVMF_RDMA_PRTYPE_NOT_SPECIFIED;
+	port->disc_addr.tsas.rdma.cms = NVMF_RDMA_CMS_RDMA_CM;
+}
+
+static void nvmet_port_init_tsas_loop(struct nvmet_port *port)
+{
+	port->disc_addr.trtype = NVMF_TRTYPE_LOOP;
+	memset(&port->disc_addr.tsas, 0, NVMF_TSAS_SIZE);
+}
+
+static ssize_t nvmet_addr_trtype_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	if (port->enabled) {
+		pr_err("Cannot modify address while enabled\n");
+		pr_err("Disable the address before modifying\n");
+		return -EACCES;
+	}
+
+	if (sysfs_streq(page, "rdma")) {
+		nvmet_port_init_tsas_rdma(port);
+	} else if (sysfs_streq(page, "loop")) {
+		nvmet_port_init_tsas_loop(port);
+	} else {
+		pr_err("Invalid value '%s' for trtype\n", page);
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, addr_trtype);
+
+/*
+ * Namespace structures & file operation functions below
+ */
+static ssize_t nvmet_ns_device_path_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%s\n", to_nvmet_ns(item)->device_path);
+}
+
+static ssize_t nvmet_ns_device_path_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	struct nvmet_subsys *subsys = ns->subsys;
+	int ret;
+
+	mutex_lock(&subsys->lock);
+	ret = -EBUSY;
+	if (nvmet_ns_enabled(ns))
+		goto out_unlock;
+
+	kfree(ns->device_path);
+
+	ret = -ENOMEM;
+	ns->device_path = kstrdup(page, GFP_KERNEL);
+	if (!ns->device_path)
+		goto out_unlock;
+
+	mutex_unlock(&subsys->lock);
+	return count;
+
+out_unlock:
+	mutex_unlock(&subsys->lock);
+	return ret;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, device_path);
+
+static ssize_t nvmet_ns_device_nguid_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%pUb\n", &to_nvmet_ns(item)->nguid);
+}
+
+static ssize_t nvmet_ns_device_nguid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	struct nvmet_subsys *subsys = ns->subsys;
+	u8 nguid[16];
+	const char *p = page;
+	int i;
+	int ret = 0;
+
+	mutex_lock(&subsys->lock);
+	if (nvmet_ns_enabled(ns)) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	for (i = 0; i < 16; i++) {
+		if (p + 2 > page + count) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+		if (!isxdigit(p[0]) || !isxdigit(p[1])) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		nguid[i] = (hex_to_bin(p[0]) << 4) | hex_to_bin(p[1]);
+		p += 2;
+
+		if (*p == '-' || *p == ':')
+			p++;
+	}
+
+	memcpy(&ns->nguid, nguid, sizeof(nguid));
+out_unlock:
+	mutex_unlock(&subsys->lock);
+	return ret ? ret : count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, device_nguid);
+
+static ssize_t nvmet_ns_enable_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", nvmet_ns_enabled(to_nvmet_ns(item)));
+}
+
+static ssize_t nvmet_ns_enable_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	bool enable;
+	int ret = 0;
+
+	if (strtobool(page, &enable))
+		return -EINVAL;
+
+	if (enable)
+		ret = nvmet_ns_enable(ns);
+	else
+		nvmet_ns_disable(ns);
+
+	return ret ? ret : count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, enable);
+
+static struct configfs_attribute *nvmet_ns_attrs[] = {
+	&nvmet_ns_attr_device_path,
+	&nvmet_ns_attr_device_nguid,
+	&nvmet_ns_attr_enable,
+	NULL,
+};
+
+static void nvmet_ns_release(struct config_item *item)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+
+	nvmet_ns_free(ns);
+}
+
+static struct configfs_item_operations nvmet_ns_item_ops = {
+	.release		= nvmet_ns_release,
+};
+
+static struct config_item_type nvmet_ns_type = {
+	.ct_item_ops		= &nvmet_ns_item_ops,
+	.ct_attrs		= nvmet_ns_attrs,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_ns_make(struct config_group *group,
+		const char *name)
+{
+	struct nvmet_subsys *subsys = namespaces_to_subsys(&group->cg_item);
+	struct nvmet_ns *ns;
+	int ret;
+	u32 nsid;
+
+	ret = kstrtou32(name, 0, &nsid);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (nsid == 0 || nsid == 0xffffffff)
+		goto out;
+
+	ret = -ENOMEM;
+	ns = nvmet_ns_alloc(subsys, nsid);
+	if (!ns)
+		goto out;
+	config_group_init_type_name(&ns->group, name, &nvmet_ns_type);
+
+	pr_info("adding nsid %d to subsystem %s\n", nsid, subsys->subsysnqn);
+
+	return &ns->group;
+out:
+	return ERR_PTR(ret);
+}
+
+static struct configfs_group_operations nvmet_namespaces_group_ops = {
+	.make_group		= nvmet_ns_make,
+};
+
+static struct config_item_type nvmet_namespaces_type = {
+	.ct_group_ops		= &nvmet_namespaces_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static int nvmet_port_subsys_allow_link(struct config_item *parent,
+		struct config_item *target)
+{
+	struct nvmet_port *port = to_nvmet_port(parent->ci_parent);
+	struct nvmet_subsys *subsys;
+	struct nvmet_subsys_link *link, *p;
+	int ret;
+
+	if (target->ci_type != &nvmet_subsys_type) {
+		pr_err("can only link subsystems into the subsystems dir.!\n");
+		return -EINVAL;
+	}
+	subsys = to_subsys(target);
+	link = kmalloc(sizeof(*link), GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+	link->subsys = subsys;
+
+	down_write(&nvmet_config_sem);
+	ret = -EEXIST;
+	list_for_each_entry(p, &port->subsystems, entry) {
+		if (p->subsys == subsys)
+			goto out_free_link;
+	}
+
+	if (list_empty(&port->subsystems)) {
+		ret = nvmet_enable_port(port);
+		if (ret)
+			goto out_free_link;
+	}
+
+	list_add_tail(&link->entry, &port->subsystems);
+	nvmet_genctr++;
+	up_write(&nvmet_config_sem);
+	return 0;
+
+out_free_link:
+	up_write(&nvmet_config_sem);
+	kfree(link);
+	return ret;
+}
+
+static int nvmet_port_subsys_drop_link(struct config_item *parent,
+		struct config_item *target)
+{
+	struct nvmet_port *port = to_nvmet_port(parent->ci_parent);
+	struct nvmet_subsys *subsys = to_subsys(target);
+	struct nvmet_subsys_link *p;
+
+	down_write(&nvmet_config_sem);
+	list_for_each_entry(p, &port->subsystems, entry) {
+		if (p->subsys == subsys)
+			goto found;
+	}
+	up_write(&nvmet_config_sem);
+	return -EINVAL;
+
+found:
+	list_del(&p->entry);
+	nvmet_genctr++;
+	if (list_empty(&port->subsystems))
+		nvmet_disable_port(port);
+	up_write(&nvmet_config_sem);
+	kfree(p);
+	return 0;
+}
+
+static struct configfs_item_operations nvmet_port_subsys_item_ops = {
+	.allow_link		= nvmet_port_subsys_allow_link,
+	.drop_link		= nvmet_port_subsys_drop_link,
+};
+
+static struct config_item_type nvmet_port_subsys_type = {
+	.ct_item_ops		= &nvmet_port_subsys_item_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static int nvmet_allowed_hosts_allow_link(struct config_item *parent,
+		struct config_item *target)
+{
+	struct nvmet_subsys *subsys = to_subsys(parent->ci_parent);
+	struct nvmet_host *host;
+	struct nvmet_host_link *link, *p;
+	int ret;
+
+	if (target->ci_type != &nvmet_host_type) {
+		pr_err("can only link hosts into the allowed_hosts directory!\n");
+		return -EINVAL;
+	}
+
+	host = to_host(target);
+	link = kmalloc(sizeof(*link), GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+	link->host = host;
+
+	down_write(&nvmet_config_sem);
+	ret = -EINVAL;
+	if (subsys->allow_any_host) {
+		pr_err("can't add hosts when allow_any_host is set!\n");
+		goto out_free_link;
+	}
+
+	ret = -EEXIST;
+	list_for_each_entry(p, &subsys->hosts, entry) {
+		if (!strcmp(nvmet_host_name(p->host), nvmet_host_name(host)))
+			goto out_free_link;
+	}
+	list_add_tail(&link->entry, &subsys->hosts);
+	nvmet_genctr++;
+	up_write(&nvmet_config_sem);
+	return 0;
+out_free_link:
+	up_write(&nvmet_config_sem);
+	kfree(link);
+	return ret;
+}
+
+static int nvmet_allowed_hosts_drop_link(struct config_item *parent,
+		struct config_item *target)
+{
+	struct nvmet_subsys *subsys = to_subsys(parent->ci_parent);
+	struct nvmet_host *host = to_host(target);
+	struct nvmet_host_link *p;
+
+	down_write(&nvmet_config_sem);
+	list_for_each_entry(p, &subsys->hosts, entry) {
+		if (!strcmp(nvmet_host_name(p->host), nvmet_host_name(host)))
+			goto found;
+	}
+	up_write(&nvmet_config_sem);
+	return -EINVAL;
+
+found:
+	list_del(&p->entry);
+	nvmet_genctr++;
+	up_write(&nvmet_config_sem);
+	kfree(p);
+	return 0;
+}
+
+static struct configfs_item_operations nvmet_allowed_hosts_item_ops = {
+	.allow_link		= nvmet_allowed_hosts_allow_link,
+	.drop_link		= nvmet_allowed_hosts_drop_link,
+};
+
+static struct config_item_type nvmet_allowed_hosts_type = {
+	.ct_item_ops		= &nvmet_allowed_hosts_item_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static ssize_t nvmet_subsys_attr_allow_any_host_show(struct config_item *item,
+		char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%d\n",
+		to_subsys(item)->allow_any_host);
+}
+
+static ssize_t nvmet_subsys_attr_allow_any_host_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+	bool allow_any_host;
+	int ret = 0;
+
+	if (strtobool(page, &allow_any_host))
+		return -EINVAL;
+
+	down_write(&nvmet_config_sem);
+	if (allow_any_host && !list_empty(&subsys->hosts)) {
+		pr_err("Can't set allow_any_host when explicit hosts are set!\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	subsys->allow_any_host = allow_any_host;
+out_unlock:
+	up_write(&nvmet_config_sem);
+	return ret ? ret : count;
+}
+
+CONFIGFS_ATTR(nvmet_subsys_, attr_allow_any_host);
+
+static struct configfs_attribute *nvmet_subsys_attrs[] = {
+	&nvmet_subsys_attr_attr_allow_any_host,
+	NULL,
+};
+
+/*
+ * Subsystem structures & folder operation functions below
+ */
+static void nvmet_subsys_release(struct config_item *item)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+
+	nvmet_subsys_put(subsys);
+}
+
+static struct configfs_item_operations nvmet_subsys_item_ops = {
+	.release		= nvmet_subsys_release,
+};
+
+static struct config_item_type nvmet_subsys_type = {
+	.ct_item_ops		= &nvmet_subsys_item_ops,
+	.ct_attrs		= nvmet_subsys_attrs,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_subsys_make(struct config_group *group,
+		const char *name)
+{
+	struct nvmet_subsys *subsys;
+
+	if (sysfs_streq(name, NVME_DISC_SUBSYS_NAME)) {
+		pr_err("can't create discovery subsystem through configfs\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	subsys = nvmet_subsys_alloc(name, NVME_NQN_NVME);
+	if (!subsys)
+		return ERR_PTR(-ENOMEM);
+
+	config_group_init_type_name(&subsys->group, name, &nvmet_subsys_type);
+
+	config_group_init_type_name(&subsys->namespaces_group,
+			"namespaces", &nvmet_namespaces_type);
+	configfs_add_default_group(&subsys->namespaces_group, &subsys->group);
+
+	config_group_init_type_name(&subsys->allowed_hosts_group,
+			"allowed_hosts", &nvmet_allowed_hosts_type);
+	configfs_add_default_group(&subsys->allowed_hosts_group,
+			&subsys->group);
+
+	return &subsys->group;
+}
+
+static struct configfs_group_operations nvmet_subsystems_group_ops = {
+	.make_group		= nvmet_subsys_make,
+};
+
+static struct config_item_type nvmet_subsystems_type = {
+	.ct_group_ops		= &nvmet_subsystems_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static ssize_t nvmet_referral_enable_show(struct config_item *item,
+		char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%d\n", to_nvmet_port(item)->enabled);
+}
+
+static ssize_t nvmet_referral_enable_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *parent = to_nvmet_port(item->ci_parent->ci_parent);
+	struct nvmet_port *port = to_nvmet_port(item);
+	bool enable;
+
+	if (strtobool(page, &enable))
+		goto inval;
+
+	if (enable)
+		nvmet_referral_enable(parent, port);
+	else
+		nvmet_referral_disable(port);
+
+	return count;
+inval:
+	pr_err("Invalid value '%s' for enable\n", page);
+	return -EINVAL;
+}
+
+CONFIGFS_ATTR(nvmet_referral_, enable);
+
+/*
+ * Discovery Service subsystem definitions
+ */
+static struct configfs_attribute *nvmet_referral_attrs[] = {
+	&nvmet_attr_addr_adrfam,
+	&nvmet_attr_addr_portid,
+	&nvmet_attr_addr_treq,
+	&nvmet_attr_addr_traddr,
+	&nvmet_attr_addr_trsvcid,
+	&nvmet_attr_addr_trtype,
+	&nvmet_referral_attr_enable,
+	NULL,
+};
+
+static void nvmet_referral_release(struct config_item *item)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	nvmet_referral_disable(port);
+	kfree(port);
+}
+
+static struct configfs_item_operations nvmet_referral_item_ops = {
+	.release	= nvmet_referral_release,
+};
+
+static struct config_item_type nvmet_referral_type = {
+	.ct_owner	= THIS_MODULE,
+	.ct_attrs	= nvmet_referral_attrs,
+	.ct_item_ops	= &nvmet_referral_item_ops,
+};
+
+static struct config_group *nvmet_referral_make(
+		struct config_group *group, const char *name)
+{
+	struct nvmet_port *port;
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&port->entry);
+	config_group_init_type_name(&port->group, name, &nvmet_referral_type);
+
+	return &port->group;
+}
+
+static struct configfs_group_operations nvmet_referral_group_ops = {
+	.make_group		= nvmet_referral_make,
+};
+
+static struct config_item_type nvmet_referrals_type = {
+	.ct_owner	= THIS_MODULE,
+	.ct_group_ops	= &nvmet_referral_group_ops,
+};
+
+/*
+ * Ports definitions.
+ */
+static void nvmet_port_release(struct config_item *item)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	kfree(port);
+}
+
+static struct configfs_attribute *nvmet_port_attrs[] = {
+	&nvmet_attr_addr_adrfam,
+	&nvmet_attr_addr_treq,
+	&nvmet_attr_addr_traddr,
+	&nvmet_attr_addr_trsvcid,
+	&nvmet_attr_addr_trtype,
+	NULL,
+};
+
+static struct configfs_item_operations nvmet_port_item_ops = {
+	.release		= nvmet_port_release,
+};
+
+static struct config_item_type nvmet_port_type = {
+	.ct_attrs		= nvmet_port_attrs,
+	.ct_item_ops		= &nvmet_port_item_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_ports_make(struct config_group *group,
+		const char *name)
+{
+	struct nvmet_port *port;
+	u16 portid;
+
+	if (kstrtou16(name, 0, &portid))
+		return ERR_PTR(-EINVAL);
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&port->entry);
+	INIT_LIST_HEAD(&port->subsystems);
+	INIT_LIST_HEAD(&port->referrals);
+
+	port->disc_addr.portid = cpu_to_le16(portid);
+	config_group_init_type_name(&port->group, name, &nvmet_port_type);
+
+	config_group_init_type_name(&port->subsys_group,
+			"subsystems", &nvmet_port_subsys_type);
+	configfs_add_default_group(&port->subsys_group, &port->group);
+
+	config_group_init_type_name(&port->referrals_group,
+			"referrals", &nvmet_referrals_type);
+	configfs_add_default_group(&port->referrals_group, &port->group);
+
+	return &port->group;
+}
+
+static struct configfs_group_operations nvmet_ports_group_ops = {
+	.make_group		= nvmet_ports_make,
+};
+
+static struct config_item_type nvmet_ports_type = {
+	.ct_group_ops		= &nvmet_ports_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group nvmet_subsystems_group;
+static struct config_group nvmet_ports_group;
+
+static void nvmet_host_release(struct config_item *item)
+{
+	struct nvmet_host *host = to_host(item);
+
+	kfree(host);
+}
+
+static struct configfs_item_operations nvmet_host_item_ops = {
+	.release		= nvmet_host_release,
+};
+
+static struct config_item_type nvmet_host_type = {
+	.ct_item_ops		= &nvmet_host_item_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_hosts_make_group(struct config_group *group,
+		const char *name)
+{
+	struct nvmet_host *host;
+
+	host = kzalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return ERR_PTR(-ENOMEM);
+
+	config_group_init_type_name(&host->group, name, &nvmet_host_type);
+
+	return &host->group;
+}
+
+static struct configfs_group_operations nvmet_hosts_group_ops = {
+	.make_group		= nvmet_hosts_make_group,
+};
+
+static struct config_item_type nvmet_hosts_type = {
+	.ct_group_ops		= &nvmet_hosts_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group nvmet_hosts_group;
+
+static struct config_item_type nvmet_root_type = {
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct configfs_subsystem nvmet_configfs_subsystem = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf	= "nvmet",
+			.ci_type	= &nvmet_root_type,
+		},
+	},
+};
+
+int __init nvmet_init_configfs(void)
+{
+	int ret;
+
+	config_group_init(&nvmet_configfs_subsystem.su_group);
+	mutex_init(&nvmet_configfs_subsystem.su_mutex);
+
+	config_group_init_type_name(&nvmet_subsystems_group,
+			"subsystems", &nvmet_subsystems_type);
+	configfs_add_default_group(&nvmet_subsystems_group,
+			&nvmet_configfs_subsystem.su_group);
+
+	config_group_init_type_name(&nvmet_ports_group,
+			"ports", &nvmet_ports_type);
+	configfs_add_default_group(&nvmet_ports_group,
+			&nvmet_configfs_subsystem.su_group);
+
+	config_group_init_type_name(&nvmet_hosts_group,
+			"hosts", &nvmet_hosts_type);
+	configfs_add_default_group(&nvmet_hosts_group,
+			&nvmet_configfs_subsystem.su_group);
+
+	ret = configfs_register_subsystem(&nvmet_configfs_subsystem);
+	if (ret) {
+		pr_err("configfs_register_subsystem: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+void __exit nvmet_exit_configfs(void)
+{
+	configfs_unregister_subsystem(&nvmet_configfs_subsystem);
+}
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
new file mode 100644
index 000000000000..8a891ca53367
--- /dev/null
+++ b/drivers/nvme/target/core.c
@@ -0,0 +1,964 @@
+/*
+ * Common code for the NVMe target.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include "nvmet.h"
+
+static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
+
+/*
+ * This read/write semaphore is used to synchronize access to configuration
+ * information on a target system that will result in discovery log page
+ * information change for at least one host.
+ * The full list of resources to protected by this semaphore is:
+ *
+ *  - subsystems list
+ *  - per-subsystem allowed hosts list
+ *  - allow_any_host subsystem attribute
+ *  - nvmet_genctr
+ *  - the nvmet_transports array
+ *
+ * When updating any of those lists/structures write lock should be obtained,
+ * while when reading (popolating discovery log page or checking host-subsystem
+ * link) read lock is obtained to allow concurrent reads.
+ */
+DECLARE_RWSEM(nvmet_config_sem);
+
+static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
+		const char *subsysnqn);
+
+u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
+		size_t len)
+{
+	if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
+		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	return 0;
+}
+
+u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
+{
+	if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
+		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	return 0;
+}
+
+static u32 nvmet_async_event_result(struct nvmet_async_event *aen)
+{
+	return aen->event_type | (aen->event_info << 8) | (aen->log_page << 16);
+}
+
+static void nvmet_async_events_free(struct nvmet_ctrl *ctrl)
+{
+	struct nvmet_req *req;
+
+	while (1) {
+		mutex_lock(&ctrl->lock);
+		if (!ctrl->nr_async_event_cmds) {
+			mutex_unlock(&ctrl->lock);
+			return;
+		}
+
+		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
+		mutex_unlock(&ctrl->lock);
+		nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
+	}
+}
+
+static void nvmet_async_event_work(struct work_struct *work)
+{
+	struct nvmet_ctrl *ctrl =
+		container_of(work, struct nvmet_ctrl, async_event_work);
+	struct nvmet_async_event *aen;
+	struct nvmet_req *req;
+
+	while (1) {
+		mutex_lock(&ctrl->lock);
+		aen = list_first_entry_or_null(&ctrl->async_events,
+				struct nvmet_async_event, entry);
+		if (!aen || !ctrl->nr_async_event_cmds) {
+			mutex_unlock(&ctrl->lock);
+			return;
+		}
+
+		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
+		nvmet_set_result(req, nvmet_async_event_result(aen));
+
+		list_del(&aen->entry);
+		kfree(aen);
+
+		mutex_unlock(&ctrl->lock);
+		nvmet_req_complete(req, 0);
+	}
+}
+
+static void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
+		u8 event_info, u8 log_page)
+{
+	struct nvmet_async_event *aen;
+
+	aen = kmalloc(sizeof(*aen), GFP_KERNEL);
+	if (!aen)
+		return;
+
+	aen->event_type = event_type;
+	aen->event_info = event_info;
+	aen->log_page = log_page;
+
+	mutex_lock(&ctrl->lock);
+	list_add_tail(&aen->entry, &ctrl->async_events);
+	mutex_unlock(&ctrl->lock);
+
+	schedule_work(&ctrl->async_event_work);
+}
+
+int nvmet_register_transport(struct nvmet_fabrics_ops *ops)
+{
+	int ret = 0;
+
+	down_write(&nvmet_config_sem);
+	if (nvmet_transports[ops->type])
+		ret = -EINVAL;
+	else
+		nvmet_transports[ops->type] = ops;
+	up_write(&nvmet_config_sem);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nvmet_register_transport);
+
+void nvmet_unregister_transport(struct nvmet_fabrics_ops *ops)
+{
+	down_write(&nvmet_config_sem);
+	nvmet_transports[ops->type] = NULL;
+	up_write(&nvmet_config_sem);
+}
+EXPORT_SYMBOL_GPL(nvmet_unregister_transport);
+
+int nvmet_enable_port(struct nvmet_port *port)
+{
+	struct nvmet_fabrics_ops *ops;
+	int ret;
+
+	lockdep_assert_held(&nvmet_config_sem);
+
+	ops = nvmet_transports[port->disc_addr.trtype];
+	if (!ops) {
+		up_write(&nvmet_config_sem);
+		request_module("nvmet-transport-%d", port->disc_addr.trtype);
+		down_write(&nvmet_config_sem);
+		ops = nvmet_transports[port->disc_addr.trtype];
+		if (!ops) {
+			pr_err("transport type %d not supported\n",
+				port->disc_addr.trtype);
+			return -EINVAL;
+		}
+	}
+
+	if (!try_module_get(ops->owner))
+		return -EINVAL;
+
+	ret = ops->add_port(port);
+	if (ret) {
+		module_put(ops->owner);
+		return ret;
+	}
+
+	port->enabled = true;
+	return 0;
+}
+
+void nvmet_disable_port(struct nvmet_port *port)
+{
+	struct nvmet_fabrics_ops *ops;
+
+	lockdep_assert_held(&nvmet_config_sem);
+
+	port->enabled = false;
+
+	ops = nvmet_transports[port->disc_addr.trtype];
+	ops->remove_port(port);
+	module_put(ops->owner);
+}
+
+static void nvmet_keep_alive_timer(struct work_struct *work)
+{
+	struct nvmet_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvmet_ctrl, ka_work);
+
+	pr_err("ctrl %d keep-alive timer (%d seconds) expired!\n",
+		ctrl->cntlid, ctrl->kato);
+
+	ctrl->ops->delete_ctrl(ctrl);
+}
+
+static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
+{
+	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
+		ctrl->cntlid, ctrl->kato);
+
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer);
+	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+}
+
+static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
+{
+	pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid);
+
+	cancel_delayed_work_sync(&ctrl->ka_work);
+}
+
+static struct nvmet_ns *__nvmet_find_namespace(struct nvmet_ctrl *ctrl,
+		__le32 nsid)
+{
+	struct nvmet_ns *ns;
+
+	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+		if (ns->nsid == le32_to_cpu(nsid))
+			return ns;
+	}
+
+	return NULL;
+}
+
+struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid)
+{
+	struct nvmet_ns *ns;
+
+	rcu_read_lock();
+	ns = __nvmet_find_namespace(ctrl, nsid);
+	if (ns)
+		percpu_ref_get(&ns->ref);
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static void nvmet_destroy_namespace(struct percpu_ref *ref)
+{
+	struct nvmet_ns *ns = container_of(ref, struct nvmet_ns, ref);
+
+	complete(&ns->disable_done);
+}
+
+void nvmet_put_namespace(struct nvmet_ns *ns)
+{
+	percpu_ref_put(&ns->ref);
+}
+
+int nvmet_ns_enable(struct nvmet_ns *ns)
+{
+	struct nvmet_subsys *subsys = ns->subsys;
+	struct nvmet_ctrl *ctrl;
+	int ret = 0;
+
+	mutex_lock(&subsys->lock);
+	if (!list_empty(&ns->dev_link))
+		goto out_unlock;
+
+	ns->bdev = blkdev_get_by_path(ns->device_path, FMODE_READ | FMODE_WRITE,
+			NULL);
+	if (IS_ERR(ns->bdev)) {
+		pr_err("nvmet: failed to open block device %s: (%ld)\n",
+			ns->device_path, PTR_ERR(ns->bdev));
+		ret = PTR_ERR(ns->bdev);
+		ns->bdev = NULL;
+		goto out_unlock;
+	}
+
+	ns->size = i_size_read(ns->bdev->bd_inode);
+	ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
+
+	ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace,
+				0, GFP_KERNEL);
+	if (ret)
+		goto out_blkdev_put;
+
+	if (ns->nsid > subsys->max_nsid)
+		subsys->max_nsid = ns->nsid;
+
+	/*
+	 * The namespaces list needs to be sorted to simplify the implementation
+	 * of the Identify Namepace List subcommand.
+	 */
+	if (list_empty(&subsys->namespaces)) {
+		list_add_tail_rcu(&ns->dev_link, &subsys->namespaces);
+	} else {
+		struct nvmet_ns *old;
+
+		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link) {
+			BUG_ON(ns->nsid == old->nsid);
+			if (ns->nsid < old->nsid)
+				break;
+		}
+
+		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
+	}
+
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
+
+	ret = 0;
+out_unlock:
+	mutex_unlock(&subsys->lock);
+	return ret;
+out_blkdev_put:
+	blkdev_put(ns->bdev, FMODE_WRITE|FMODE_READ);
+	ns->bdev = NULL;
+	goto out_unlock;
+}
+
+void nvmet_ns_disable(struct nvmet_ns *ns)
+{
+	struct nvmet_subsys *subsys = ns->subsys;
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	if (list_empty(&ns->dev_link)) {
+		mutex_unlock(&subsys->lock);
+		return;
+	}
+	list_del_init(&ns->dev_link);
+	mutex_unlock(&subsys->lock);
+
+	/*
+	 * Now that we removed the namespaces from the lookup list, we
+	 * can kill the per_cpu ref and wait for any remaining references
+	 * to be dropped, as well as a RCU grace period for anyone only
+	 * using the namepace under rcu_read_lock().  Note that we can't
+	 * use call_rcu here as we need to ensure the namespaces have
+	 * been fully destroyed before unloading the module.
+	 */
+	percpu_ref_kill(&ns->ref);
+	synchronize_rcu();
+	wait_for_completion(&ns->disable_done);
+	percpu_ref_exit(&ns->ref);
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
+
+	if (ns->bdev)
+		blkdev_put(ns->bdev, FMODE_WRITE|FMODE_READ);
+	mutex_unlock(&subsys->lock);
+}
+
+void nvmet_ns_free(struct nvmet_ns *ns)
+{
+	nvmet_ns_disable(ns);
+
+	kfree(ns->device_path);
+	kfree(ns);
+}
+
+struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
+{
+	struct nvmet_ns *ns;
+
+	ns = kzalloc(sizeof(*ns), GFP_KERNEL);
+	if (!ns)
+		return NULL;
+
+	INIT_LIST_HEAD(&ns->dev_link);
+	init_completion(&ns->disable_done);
+
+	ns->nsid = nsid;
+	ns->subsys = subsys;
+
+	return ns;
+}
+
+static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
+{
+	if (status)
+		nvmet_set_status(req, status);
+
+	/* XXX: need to fill in something useful for sq_head */
+	req->rsp->sq_head = 0;
+	if (likely(req->sq)) /* may happen during early failure */
+		req->rsp->sq_id = cpu_to_le16(req->sq->qid);
+	req->rsp->command_id = req->cmd->common.command_id;
+
+	if (req->ns)
+		nvmet_put_namespace(req->ns);
+	req->ops->queue_response(req);
+}
+
+void nvmet_req_complete(struct nvmet_req *req, u16 status)
+{
+	__nvmet_req_complete(req, status);
+	percpu_ref_put(&req->sq->ref);
+}
+EXPORT_SYMBOL_GPL(nvmet_req_complete);
+
+void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq,
+		u16 qid, u16 size)
+{
+	cq->qid = qid;
+	cq->size = size;
+
+	ctrl->cqs[qid] = cq;
+}
+
+void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
+		u16 qid, u16 size)
+{
+	sq->qid = qid;
+	sq->size = size;
+
+	ctrl->sqs[qid] = sq;
+}
+
+void nvmet_sq_destroy(struct nvmet_sq *sq)
+{
+	/*
+	 * If this is the admin queue, complete all AERs so that our
+	 * queue doesn't have outstanding requests on it.
+	 */
+	if (sq->ctrl && sq->ctrl->sqs && sq->ctrl->sqs[0] == sq)
+		nvmet_async_events_free(sq->ctrl);
+	percpu_ref_kill(&sq->ref);
+	wait_for_completion(&sq->free_done);
+	percpu_ref_exit(&sq->ref);
+
+	if (sq->ctrl) {
+		nvmet_ctrl_put(sq->ctrl);
+		sq->ctrl = NULL; /* allows reusing the queue later */
+	}
+}
+EXPORT_SYMBOL_GPL(nvmet_sq_destroy);
+
+static void nvmet_sq_free(struct percpu_ref *ref)
+{
+	struct nvmet_sq *sq = container_of(ref, struct nvmet_sq, ref);
+
+	complete(&sq->free_done);
+}
+
+int nvmet_sq_init(struct nvmet_sq *sq)
+{
+	int ret;
+
+	ret = percpu_ref_init(&sq->ref, nvmet_sq_free, 0, GFP_KERNEL);
+	if (ret) {
+		pr_err("percpu_ref init failed!\n");
+		return ret;
+	}
+	init_completion(&sq->free_done);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvmet_sq_init);
+
+bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
+		struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops)
+{
+	u8 flags = req->cmd->common.flags;
+	u16 status;
+
+	req->cq = cq;
+	req->sq = sq;
+	req->ops = ops;
+	req->sg = NULL;
+	req->sg_cnt = 0;
+	req->rsp->status = 0;
+
+	/* no support for fused commands yet */
+	if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto fail;
+	}
+
+	/* either variant of SGLs is fine, as we don't support metadata */
+	if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF &&
+		     (flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METASEG)) {
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto fail;
+	}
+
+	if (unlikely(!req->sq->ctrl))
+		/* will return an error for any Non-connect command: */
+		status = nvmet_parse_connect_cmd(req);
+	else if (likely(req->sq->qid != 0))
+		status = nvmet_parse_io_cmd(req);
+	else if (req->cmd->common.opcode == nvme_fabrics_command)
+		status = nvmet_parse_fabrics_cmd(req);
+	else if (req->sq->ctrl->subsys->type == NVME_NQN_DISC)
+		status = nvmet_parse_discovery_cmd(req);
+	else
+		status = nvmet_parse_admin_cmd(req);
+
+	if (status)
+		goto fail;
+
+	if (unlikely(!percpu_ref_tryget_live(&sq->ref))) {
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto fail;
+	}
+
+	return true;
+
+fail:
+	__nvmet_req_complete(req, status);
+	return false;
+}
+EXPORT_SYMBOL_GPL(nvmet_req_init);
+
+static inline bool nvmet_cc_en(u32 cc)
+{
+	return cc & 0x1;
+}
+
+static inline u8 nvmet_cc_css(u32 cc)
+{
+	return (cc >> 4) & 0x7;
+}
+
+static inline u8 nvmet_cc_mps(u32 cc)
+{
+	return (cc >> 7) & 0xf;
+}
+
+static inline u8 nvmet_cc_ams(u32 cc)
+{
+	return (cc >> 11) & 0x7;
+}
+
+static inline u8 nvmet_cc_shn(u32 cc)
+{
+	return (cc >> 14) & 0x3;
+}
+
+static inline u8 nvmet_cc_iosqes(u32 cc)
+{
+	return (cc >> 16) & 0xf;
+}
+
+static inline u8 nvmet_cc_iocqes(u32 cc)
+{
+	return (cc >> 20) & 0xf;
+}
+
+static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
+{
+	lockdep_assert_held(&ctrl->lock);
+
+	if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
+	    nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES ||
+	    nvmet_cc_mps(ctrl->cc) != 0 ||
+	    nvmet_cc_ams(ctrl->cc) != 0 ||
+	    nvmet_cc_css(ctrl->cc) != 0) {
+		ctrl->csts = NVME_CSTS_CFS;
+		return;
+	}
+
+	ctrl->csts = NVME_CSTS_RDY;
+}
+
+static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)
+{
+	lockdep_assert_held(&ctrl->lock);
+
+	/* XXX: tear down queues? */
+	ctrl->csts &= ~NVME_CSTS_RDY;
+	ctrl->cc = 0;
+}
+
+void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new)
+{
+	u32 old;
+
+	mutex_lock(&ctrl->lock);
+	old = ctrl->cc;
+	ctrl->cc = new;
+
+	if (nvmet_cc_en(new) && !nvmet_cc_en(old))
+		nvmet_start_ctrl(ctrl);
+	if (!nvmet_cc_en(new) && nvmet_cc_en(old))
+		nvmet_clear_ctrl(ctrl);
+	if (nvmet_cc_shn(new) && !nvmet_cc_shn(old)) {
+		nvmet_clear_ctrl(ctrl);
+		ctrl->csts |= NVME_CSTS_SHST_CMPLT;
+	}
+	if (!nvmet_cc_shn(new) && nvmet_cc_shn(old))
+		ctrl->csts &= ~NVME_CSTS_SHST_CMPLT;
+	mutex_unlock(&ctrl->lock);
+}
+
+static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
+{
+	/* command sets supported: NVMe command set: */
+	ctrl->cap = (1ULL << 37);
+	/* CC.EN timeout in 500msec units: */
+	ctrl->cap |= (15ULL << 24);
+	/* maximum queue entries supported: */
+	ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+}
+
+u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid,
+		struct nvmet_req *req, struct nvmet_ctrl **ret)
+{
+	struct nvmet_subsys *subsys;
+	struct nvmet_ctrl *ctrl;
+	u16 status = 0;
+
+	subsys = nvmet_find_get_subsys(req->port, subsysnqn);
+	if (!subsys) {
+		pr_warn("connect request for invalid subsystem %s!\n",
+			subsysnqn);
+		req->rsp->result = IPO_IATTR_CONNECT_DATA(subsysnqn);
+		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+	}
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (ctrl->cntlid == cntlid) {
+			if (strncmp(hostnqn, ctrl->hostnqn, NVMF_NQN_SIZE)) {
+				pr_warn("hostnqn mismatch.\n");
+				continue;
+			}
+			if (!kref_get_unless_zero(&ctrl->ref))
+				continue;
+
+			*ret = ctrl;
+			goto out;
+		}
+	}
+
+	pr_warn("could not find controller %d for subsys %s / host %s\n",
+		cntlid, subsysnqn, hostnqn);
+	req->rsp->result = IPO_IATTR_CONNECT_DATA(cntlid);
+	status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+
+out:
+	mutex_unlock(&subsys->lock);
+	nvmet_subsys_put(subsys);
+	return status;
+}
+
+static bool __nvmet_host_allowed(struct nvmet_subsys *subsys,
+		const char *hostnqn)
+{
+	struct nvmet_host_link *p;
+
+	if (subsys->allow_any_host)
+		return true;
+
+	list_for_each_entry(p, &subsys->hosts, entry) {
+		if (!strcmp(nvmet_host_name(p->host), hostnqn))
+			return true;
+	}
+
+	return false;
+}
+
+static bool nvmet_host_discovery_allowed(struct nvmet_req *req,
+		const char *hostnqn)
+{
+	struct nvmet_subsys_link *s;
+
+	list_for_each_entry(s, &req->port->subsystems, entry) {
+		if (__nvmet_host_allowed(s->subsys, hostnqn))
+			return true;
+	}
+
+	return false;
+}
+
+bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
+		const char *hostnqn)
+{
+	lockdep_assert_held(&nvmet_config_sem);
+
+	if (subsys->type == NVME_NQN_DISC)
+		return nvmet_host_discovery_allowed(req, hostnqn);
+	else
+		return __nvmet_host_allowed(subsys, hostnqn);
+}
+
+u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
+		struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp)
+{
+	struct nvmet_subsys *subsys;
+	struct nvmet_ctrl *ctrl;
+	int ret;
+	u16 status;
+
+	status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+	subsys = nvmet_find_get_subsys(req->port, subsysnqn);
+	if (!subsys) {
+		pr_warn("connect request for invalid subsystem %s!\n",
+			subsysnqn);
+		req->rsp->result = IPO_IATTR_CONNECT_DATA(subsysnqn);
+		goto out;
+	}
+
+	status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+	down_read(&nvmet_config_sem);
+	if (!nvmet_host_allowed(req, subsys, hostnqn)) {
+		pr_info("connect by host %s for subsystem %s not allowed\n",
+			hostnqn, subsysnqn);
+		req->rsp->result = IPO_IATTR_CONNECT_DATA(hostnqn);
+		up_read(&nvmet_config_sem);
+		goto out_put_subsystem;
+	}
+	up_read(&nvmet_config_sem);
+
+	status = NVME_SC_INTERNAL;
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		goto out_put_subsystem;
+	mutex_init(&ctrl->lock);
+
+	nvmet_init_cap(ctrl);
+
+	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
+	INIT_LIST_HEAD(&ctrl->async_events);
+
+	memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
+	memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);
+
+	kref_init(&ctrl->ref);
+	ctrl->subsys = subsys;
+
+	ctrl->cqs = kcalloc(subsys->max_qid + 1,
+			sizeof(struct nvmet_cq *),
+			GFP_KERNEL);
+	if (!ctrl->cqs)
+		goto out_free_ctrl;
+
+	ctrl->sqs = kcalloc(subsys->max_qid + 1,
+			sizeof(struct nvmet_sq *),
+			GFP_KERNEL);
+	if (!ctrl->sqs)
+		goto out_free_cqs;
+
+	ret = ida_simple_get(&subsys->cntlid_ida,
+			     NVME_CNTLID_MIN, NVME_CNTLID_MAX,
+			     GFP_KERNEL);
+	if (ret < 0) {
+		status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
+		goto out_free_sqs;
+	}
+	ctrl->cntlid = ret;
+
+	ctrl->ops = req->ops;
+	if (ctrl->subsys->type == NVME_NQN_DISC) {
+		/* Don't accept keep-alive timeout for discovery controllers */
+		if (kato) {
+			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+			goto out_free_sqs;
+		}
+
+		/*
+		 * Discovery controllers use some arbitrary high value in order
+		 * to cleanup stale discovery sessions
+		 *
+		 * From the latest base diff RC:
+		 * "The Keep Alive command is not supported by
+		 * Discovery controllers. A transport may specify a
+		 * fixed Discovery controller activity timeout value
+		 * (e.g., 2 minutes).  If no commands are received
+		 * by a Discovery controller within that time
+		 * period, the controller may perform the
+		 * actions for Keep Alive Timer expiration".
+		 */
+		ctrl->kato = NVMET_DISC_KATO;
+	} else {
+		/* keep-alive timeout in seconds */
+		ctrl->kato = DIV_ROUND_UP(kato, 1000);
+	}
+	nvmet_start_keep_alive_timer(ctrl);
+
+	mutex_lock(&subsys->lock);
+	list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
+	mutex_unlock(&subsys->lock);
+
+	*ctrlp = ctrl;
+	return 0;
+
+out_free_sqs:
+	kfree(ctrl->sqs);
+out_free_cqs:
+	kfree(ctrl->cqs);
+out_free_ctrl:
+	kfree(ctrl);
+out_put_subsystem:
+	nvmet_subsys_put(subsys);
+out:
+	return status;
+}
+
+static void nvmet_ctrl_free(struct kref *ref)
+{
+	struct nvmet_ctrl *ctrl = container_of(ref, struct nvmet_ctrl, ref);
+	struct nvmet_subsys *subsys = ctrl->subsys;
+
+	nvmet_stop_keep_alive_timer(ctrl);
+
+	mutex_lock(&subsys->lock);
+	list_del(&ctrl->subsys_entry);
+	mutex_unlock(&subsys->lock);
+
+	ida_simple_remove(&subsys->cntlid_ida, ctrl->cntlid);
+	nvmet_subsys_put(subsys);
+
+	kfree(ctrl->sqs);
+	kfree(ctrl->cqs);
+	kfree(ctrl);
+}
+
+void nvmet_ctrl_put(struct nvmet_ctrl *ctrl)
+{
+	kref_put(&ctrl->ref, nvmet_ctrl_free);
+}
+
+static void nvmet_fatal_error_handler(struct work_struct *work)
+{
+	struct nvmet_ctrl *ctrl =
+			container_of(work, struct nvmet_ctrl, fatal_err_work);
+
+	pr_err("ctrl %d fatal error occurred!\n", ctrl->cntlid);
+	ctrl->ops->delete_ctrl(ctrl);
+}
+
+void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl)
+{
+	ctrl->csts |= NVME_CSTS_CFS;
+	INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler);
+	schedule_work(&ctrl->fatal_err_work);
+}
+EXPORT_SYMBOL_GPL(nvmet_ctrl_fatal_error);
+
+static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
+		const char *subsysnqn)
+{
+	struct nvmet_subsys_link *p;
+
+	if (!port)
+		return NULL;
+
+	if (!strncmp(NVME_DISC_SUBSYS_NAME, subsysnqn,
+			NVMF_NQN_SIZE)) {
+		if (!kref_get_unless_zero(&nvmet_disc_subsys->ref))
+			return NULL;
+		return nvmet_disc_subsys;
+	}
+
+	down_read(&nvmet_config_sem);
+	list_for_each_entry(p, &port->subsystems, entry) {
+		if (!strncmp(p->subsys->subsysnqn, subsysnqn,
+				NVMF_NQN_SIZE)) {
+			if (!kref_get_unless_zero(&p->subsys->ref))
+				break;
+			up_read(&nvmet_config_sem);
+			return p->subsys;
+		}
+	}
+	up_read(&nvmet_config_sem);
+	return NULL;
+}
+
+struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
+		enum nvme_subsys_type type)
+{
+	struct nvmet_subsys *subsys;
+
+	subsys = kzalloc(sizeof(*subsys), GFP_KERNEL);
+	if (!subsys)
+		return NULL;
+
+	subsys->ver = (1 << 16) | (2 << 8) | 1; /* NVMe 1.2.1 */
+
+	switch (type) {
+	case NVME_NQN_NVME:
+		subsys->max_qid = NVMET_NR_QUEUES;
+		break;
+	case NVME_NQN_DISC:
+		subsys->max_qid = 0;
+		break;
+	default:
+		pr_err("%s: Unknown Subsystem type - %d\n", __func__, type);
+		kfree(subsys);
+		return NULL;
+	}
+	subsys->type = type;
+	subsys->subsysnqn = kstrndup(subsysnqn, NVMF_NQN_SIZE,
+			GFP_KERNEL);
+	if (!subsys->subsysnqn) {
+		kfree(subsys);
+		return NULL;
+	}
+
+	kref_init(&subsys->ref);
+
+	mutex_init(&subsys->lock);
+	INIT_LIST_HEAD(&subsys->namespaces);
+	INIT_LIST_HEAD(&subsys->ctrls);
+
+	ida_init(&subsys->cntlid_ida);
+
+	INIT_LIST_HEAD(&subsys->hosts);
+
+	return subsys;
+}
+
+static void nvmet_subsys_free(struct kref *ref)
+{
+	struct nvmet_subsys *subsys =
+		container_of(ref, struct nvmet_subsys, ref);
+
+	WARN_ON_ONCE(!list_empty(&subsys->namespaces));
+
+	ida_destroy(&subsys->cntlid_ida);
+	kfree(subsys->subsysnqn);
+	kfree(subsys);
+}
+
+void nvmet_subsys_put(struct nvmet_subsys *subsys)
+{
+	kref_put(&subsys->ref, nvmet_subsys_free);
+}
+
+static int __init nvmet_init(void)
+{
+	int error;
+
+	error = nvmet_init_discovery();
+	if (error)
+		goto out;
+
+	error = nvmet_init_configfs();
+	if (error)
+		goto out_exit_discovery;
+	return 0;
+
+out_exit_discovery:
+	nvmet_exit_discovery();
+out:
+	return error;
+}
+
+static void __exit nvmet_exit(void)
+{
+	nvmet_exit_configfs();
+	nvmet_exit_discovery();
+
+	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
+	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);
+}
+
+module_init(nvmet_init);
+module_exit(nvmet_exit);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
new file mode 100644
index 000000000000..6f65646e89cf
--- /dev/null
+++ b/drivers/nvme/target/discovery.c
@@ -0,0 +1,221 @@
+/*
+ * Discovery service for the NVMe over Fabrics target.
+ * Copyright (C) 2016 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/slab.h>
+#include <generated/utsrelease.h>
+#include "nvmet.h"
+
+struct nvmet_subsys *nvmet_disc_subsys;
+
+u64 nvmet_genctr;
+
+void nvmet_referral_enable(struct nvmet_port *parent, struct nvmet_port *port)
+{
+	down_write(&nvmet_config_sem);
+	if (list_empty(&port->entry)) {
+		list_add_tail(&port->entry, &parent->referrals);
+		port->enabled = true;
+		nvmet_genctr++;
+	}
+	up_write(&nvmet_config_sem);
+}
+
+void nvmet_referral_disable(struct nvmet_port *port)
+{
+	down_write(&nvmet_config_sem);
+	if (!list_empty(&port->entry)) {
+		port->enabled = false;
+		list_del_init(&port->entry);
+		nvmet_genctr++;
+	}
+	up_write(&nvmet_config_sem);
+}
+
+static void nvmet_format_discovery_entry(struct nvmf_disc_rsp_page_hdr *hdr,
+		struct nvmet_port *port, char *subsys_nqn, u8 type, u32 numrec)
+{
+	struct nvmf_disc_rsp_page_entry *e = &hdr->entries[numrec];
+
+	e->trtype = port->disc_addr.trtype;
+	e->adrfam = port->disc_addr.adrfam;
+	e->treq = port->disc_addr.treq;
+	e->portid = port->disc_addr.portid;
+	/* we support only dynamic controllers */
+	e->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC);
+	e->asqsz = cpu_to_le16(NVMF_AQ_DEPTH);
+	e->nqntype = type;
+	memcpy(e->trsvcid, port->disc_addr.trsvcid, NVMF_TRSVCID_SIZE);
+	memcpy(e->traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
+	memcpy(e->tsas.common, port->disc_addr.tsas.common, NVMF_TSAS_SIZE);
+	memcpy(e->subnqn, subsys_nqn, NVMF_NQN_SIZE);
+}
+
+static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
+{
+	const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry);
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmf_disc_rsp_page_hdr *hdr;
+	size_t data_len = nvmet_get_log_page_len(req->cmd);
+	size_t alloc_len = max(data_len, sizeof(*hdr));
+	int residual_len = data_len - sizeof(*hdr);
+	struct nvmet_subsys_link *p;
+	struct nvmet_port *r;
+	u32 numrec = 0;
+	u16 status = 0;
+
+	/*
+	 * Make sure we're passing at least a buffer of response header size.
+	 * If host provided data len is less than the header size, only the
+	 * number of bytes requested by host will be sent to host.
+	 */
+	hdr = kzalloc(alloc_len, GFP_KERNEL);
+	if (!hdr) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	down_read(&nvmet_config_sem);
+	list_for_each_entry(p, &req->port->subsystems, entry) {
+		if (!nvmet_host_allowed(req, p->subsys, ctrl->hostnqn))
+			continue;
+		if (residual_len >= entry_size) {
+			nvmet_format_discovery_entry(hdr, req->port,
+					p->subsys->subsysnqn,
+					NVME_NQN_NVME, numrec);
+			residual_len -= entry_size;
+		}
+		numrec++;
+	}
+
+	list_for_each_entry(r, &req->port->referrals, entry) {
+		if (residual_len >= entry_size) {
+			nvmet_format_discovery_entry(hdr, r,
+					NVME_DISC_SUBSYS_NAME,
+					NVME_NQN_DISC, numrec);
+			residual_len -= entry_size;
+		}
+		numrec++;
+	}
+
+	hdr->genctr = cpu_to_le64(nvmet_genctr);
+	hdr->numrec = cpu_to_le64(numrec);
+	hdr->recfmt = cpu_to_le16(0);
+
+	up_read(&nvmet_config_sem);
+
+	status = nvmet_copy_to_sgl(req, 0, hdr, data_len);
+	kfree(hdr);
+out:
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvme_id_ctrl *id;
+	u16 status = 0;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	memset(id->fr, ' ', sizeof(id->fr));
+	strncpy((char *)id->fr, UTS_RELEASE, sizeof(id->fr));
+
+	/* no limit on data transfer sizes for now */
+	id->mdts = 0;
+	id->cntlid = cpu_to_le16(ctrl->cntlid);
+	id->ver = cpu_to_le32(ctrl->subsys->ver);
+	id->lpa = (1 << 2);
+
+	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+
+	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
+	if (ctrl->ops->has_keyed_sgls)
+		id->sgls |= cpu_to_le32(1 << 2);
+	if (ctrl->ops->sqe_inline_size)
+		id->sgls |= cpu_to_le32(1 << 20);
+
+	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
+
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+
+	kfree(id);
+out:
+	nvmet_req_complete(req, status);
+}
+
+int nvmet_parse_discovery_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+
+	req->ns = NULL;
+
+	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
+		pr_err("nvmet: got cmd %d while not ready\n",
+				cmd->common.opcode);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+
+	switch (cmd->common.opcode) {
+	case nvme_admin_get_log_page:
+		req->data_len = nvmet_get_log_page_len(cmd);
+
+		switch (cmd->get_log_page.lid) {
+		case NVME_LOG_DISC:
+			req->execute = nvmet_execute_get_disc_log_page;
+			return 0;
+		default:
+			pr_err("nvmet: unsupported get_log_page lid %d\n",
+				cmd->get_log_page.lid);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		}
+	case nvme_admin_identify:
+		req->data_len = 4096;
+		switch (le32_to_cpu(cmd->identify.cns)) {
+		case 0x01:
+			req->execute =
+				nvmet_execute_identify_disc_ctrl;
+			return 0;
+		default:
+			pr_err("nvmet: unsupported identify cns %d\n",
+				le32_to_cpu(cmd->identify.cns));
+			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		}
+	default:
+		pr_err("nvmet: unsupported cmd %d\n",
+				cmd->common.opcode);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+
+	pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+}
+
+int __init nvmet_init_discovery(void)
+{
+	nvmet_disc_subsys =
+		nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC);
+	if (!nvmet_disc_subsys)
+		return -ENOMEM;
+	return 0;
+}
+
+void nvmet_exit_discovery(void)
+{
+	nvmet_subsys_put(nvmet_disc_subsys);
+}
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
new file mode 100644
index 000000000000..9a97ae67e656
--- /dev/null
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -0,0 +1,240 @@
+/*
+ * NVMe Fabrics command implementation.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/blkdev.h>
+#include "nvmet.h"
+
+static void nvmet_execute_prop_set(struct nvmet_req *req)
+{
+	u16 status = 0;
+
+	if (!(req->cmd->prop_set.attrib & 1)) {
+		u64 val = le64_to_cpu(req->cmd->prop_set.value);
+
+		switch (le32_to_cpu(req->cmd->prop_set.offset)) {
+		case NVME_REG_CC:
+			nvmet_update_cc(req->sq->ctrl, val);
+			break;
+		default:
+			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+			break;
+		}
+	} else {
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_prop_get(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	u16 status = 0;
+	u64 val = 0;
+
+	if (req->cmd->prop_get.attrib & 1) {
+		switch (le32_to_cpu(req->cmd->prop_get.offset)) {
+		case NVME_REG_CAP:
+			val = ctrl->cap;
+			break;
+		default:
+			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+			break;
+		}
+	} else {
+		switch (le32_to_cpu(req->cmd->prop_get.offset)) {
+		case NVME_REG_VS:
+			val = ctrl->subsys->ver;
+			break;
+		case NVME_REG_CC:
+			val = ctrl->cc;
+			break;
+		case NVME_REG_CSTS:
+			val = ctrl->csts;
+			break;
+		default:
+			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+			break;
+		}
+	}
+
+	req->rsp->result64 = cpu_to_le64(val);
+	nvmet_req_complete(req, status);
+}
+
+int nvmet_parse_fabrics_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+
+	req->ns = NULL;
+
+	switch (cmd->fabrics.fctype) {
+	case nvme_fabrics_type_property_set:
+		req->data_len = 0;
+		req->execute = nvmet_execute_prop_set;
+		break;
+	case nvme_fabrics_type_property_get:
+		req->data_len = 0;
+		req->execute = nvmet_execute_prop_get;
+		break;
+	default:
+		pr_err("received unknown capsule type 0x%x\n",
+			cmd->fabrics.fctype);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+
+	return 0;
+}
+
+static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
+{
+	struct nvmf_connect_command *c = &req->cmd->connect;
+	u16 qid = le16_to_cpu(c->qid);
+	u16 sqsize = le16_to_cpu(c->sqsize);
+	struct nvmet_ctrl *old;
+
+	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
+	if (old) {
+		pr_warn("queue already connected!\n");
+		return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
+	}
+
+	nvmet_cq_setup(ctrl, req->cq, qid, sqsize);
+	nvmet_sq_setup(ctrl, req->sq, qid, sqsize);
+	return 0;
+}
+
+static void nvmet_execute_admin_connect(struct nvmet_req *req)
+{
+	struct nvmf_connect_command *c = &req->cmd->connect;
+	struct nvmf_connect_data *d;
+	struct nvmet_ctrl *ctrl = NULL;
+	u16 status = 0;
+
+	d = kmap(sg_page(req->sg)) + req->sg->offset;
+
+	/* zero out initial completion result, assign values as needed */
+	req->rsp->result = 0;
+
+	if (c->recfmt != 0) {
+		pr_warn("invalid connect version (%d).\n",
+			le16_to_cpu(c->recfmt));
+		status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
+		goto out;
+	}
+
+	if (unlikely(d->cntlid != cpu_to_le16(0xffff))) {
+		pr_warn("connect attempt for invalid controller ID %#x\n",
+			d->cntlid);
+		status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		req->rsp->result = IPO_IATTR_CONNECT_DATA(cntlid);
+		goto out;
+	}
+
+	status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
+			le32_to_cpu(c->kato), &ctrl);
+	if (status)
+		goto out;
+
+	status = nvmet_install_queue(ctrl, req);
+	if (status) {
+		nvmet_ctrl_put(ctrl);
+		goto out;
+	}
+
+	pr_info("creating controller %d for NQN %s.\n",
+			ctrl->cntlid, ctrl->hostnqn);
+	req->rsp->result16 = cpu_to_le16(ctrl->cntlid);
+
+out:
+	kunmap(sg_page(req->sg));
+	nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_io_connect(struct nvmet_req *req)
+{
+	struct nvmf_connect_command *c = &req->cmd->connect;
+	struct nvmf_connect_data *d;
+	struct nvmet_ctrl *ctrl = NULL;
+	u16 qid = le16_to_cpu(c->qid);
+	u16 status = 0;
+
+	d = kmap(sg_page(req->sg)) + req->sg->offset;
+
+	/* zero out initial completion result, assign values as needed */
+	req->rsp->result = 0;
+
+	if (c->recfmt != 0) {
+		pr_warn("invalid connect version (%d).\n",
+			le16_to_cpu(c->recfmt));
+		status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
+		goto out;
+	}
+
+	status = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
+			le16_to_cpu(d->cntlid),
+			req, &ctrl);
+	if (status)
+		goto out;
+
+	if (unlikely(qid > ctrl->subsys->max_qid)) {
+		pr_warn("invalid queue id (%d)\n", qid);
+		status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		req->rsp->result = IPO_IATTR_CONNECT_SQE(qid);
+		goto out_ctrl_put;
+	}
+
+	status = nvmet_install_queue(ctrl, req);
+	if (status) {
+		/* pass back cntlid that had the issue of installing queue */
+		req->rsp->result16 = cpu_to_le16(ctrl->cntlid);
+		goto out_ctrl_put;
+	}
+
+	pr_info("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid);
+
+out:
+	kunmap(sg_page(req->sg));
+	nvmet_req_complete(req, status);
+	return;
+
+out_ctrl_put:
+	nvmet_ctrl_put(ctrl);
+	goto out;
+}
+
+int nvmet_parse_connect_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+
+	req->ns = NULL;
+
+	if (req->cmd->common.opcode != nvme_fabrics_command) {
+		pr_err("invalid command 0x%x on unconnected queue.\n",
+			cmd->fabrics.opcode);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+	if (cmd->fabrics.fctype != nvme_fabrics_type_connect) {
+		pr_err("invalid capsule type 0x%x on unconnected queue.\n",
+			cmd->fabrics.fctype);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+
+	req->data_len = sizeof(struct nvmf_connect_data);
+	if (cmd->connect.qid == 0)
+		req->execute = nvmet_execute_admin_connect;
+	else
+		req->execute = nvmet_execute_io_connect;
+	return 0;
+}
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
new file mode 100644
index 000000000000..2cd069b691ae
--- /dev/null
+++ b/drivers/nvme/target/io-cmd.c
@@ -0,0 +1,215 @@
+/*
+ * NVMe I/O command implementation.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/blkdev.h>
+#include <linux/module.h>
+#include "nvmet.h"
+
+static void nvmet_bio_done(struct bio *bio)
+{
+	struct nvmet_req *req = bio->bi_private;
+
+	nvmet_req_complete(req,
+		bio->bi_error ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+
+	if (bio != &req->inline_bio)
+		bio_put(bio);
+}
+
+static inline u32 nvmet_rw_len(struct nvmet_req *req)
+{
+	return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) <<
+			req->ns->blksize_shift;
+}
+
+static void nvmet_inline_bio_init(struct nvmet_req *req)
+{
+	struct bio *bio = &req->inline_bio;
+
+	bio_init(bio);
+	bio->bi_max_vecs = NVMET_MAX_INLINE_BIOVEC;
+	bio->bi_io_vec = req->inline_bvec;
+}
+
+static void nvmet_execute_rw(struct nvmet_req *req)
+{
+	int sg_cnt = req->sg_cnt;
+	struct scatterlist *sg;
+	struct bio *bio;
+	sector_t sector;
+	blk_qc_t cookie;
+	int op, op_flags = 0, i;
+
+	if (!req->sg_cnt) {
+		nvmet_req_complete(req, 0);
+		return;
+	}
+
+	if (req->cmd->rw.opcode == nvme_cmd_write) {
+		op = REQ_OP_WRITE;
+		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
+			op_flags |= REQ_FUA;
+	} else {
+		op = REQ_OP_READ;
+	}
+
+	sector = le64_to_cpu(req->cmd->rw.slba);
+	sector <<= (req->ns->blksize_shift - 9);
+
+	nvmet_inline_bio_init(req);
+	bio = &req->inline_bio;
+	bio->bi_bdev = req->ns->bdev;
+	bio->bi_iter.bi_sector = sector;
+	bio->bi_private = req;
+	bio->bi_end_io = nvmet_bio_done;
+	bio_set_op_attrs(bio, op, op_flags);
+
+	for_each_sg(req->sg, sg, req->sg_cnt, i) {
+		while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset)
+				!= sg->length) {
+			struct bio *prev = bio;
+
+			bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
+			bio->bi_bdev = req->ns->bdev;
+			bio->bi_iter.bi_sector = sector;
+			bio_set_op_attrs(bio, op, op_flags);
+
+			bio_chain(bio, prev);
+			cookie = submit_bio(prev);
+		}
+
+		sector += sg->length >> 9;
+		sg_cnt--;
+	}
+
+	cookie = submit_bio(bio);
+
+	blk_poll(bdev_get_queue(req->ns->bdev), cookie);
+}
+
+static void nvmet_execute_flush(struct nvmet_req *req)
+{
+	struct bio *bio;
+
+	nvmet_inline_bio_init(req);
+	bio = &req->inline_bio;
+
+	bio->bi_bdev = req->ns->bdev;
+	bio->bi_private = req;
+	bio->bi_end_io = nvmet_bio_done;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+
+	submit_bio(bio);
+}
+
+static u16 nvmet_discard_range(struct nvmet_ns *ns,
+		struct nvme_dsm_range *range, struct bio **bio)
+{
+	if (__blkdev_issue_discard(ns->bdev,
+			le64_to_cpu(range->slba) << (ns->blksize_shift - 9),
+			le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
+			GFP_KERNEL, 0, bio))
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
+static void nvmet_execute_discard(struct nvmet_req *req)
+{
+	struct nvme_dsm_range range;
+	struct bio *bio = NULL;
+	int i;
+	u16 status;
+
+	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
+		status = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+				sizeof(range));
+		if (status)
+			break;
+
+		status = nvmet_discard_range(req->ns, &range, &bio);
+		if (status)
+			break;
+	}
+
+	if (bio) {
+		bio->bi_private = req;
+		bio->bi_end_io = nvmet_bio_done;
+		if (status) {
+			bio->bi_error = -EIO;
+			bio_endio(bio);
+		} else {
+			submit_bio(bio);
+		}
+	} else {
+		nvmet_req_complete(req, status);
+	}
+}
+
+static void nvmet_execute_dsm(struct nvmet_req *req)
+{
+	switch (le32_to_cpu(req->cmd->dsm.attributes)) {
+	case NVME_DSMGMT_AD:
+		nvmet_execute_discard(req);
+		return;
+	case NVME_DSMGMT_IDR:
+	case NVME_DSMGMT_IDW:
+	default:
+		/* Not supported yet */
+		nvmet_req_complete(req, 0);
+		return;
+	}
+}
+
+int nvmet_parse_io_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+
+	if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
+		pr_err("nvmet: got io cmd %d while CC.EN == 0\n",
+				cmd->common.opcode);
+		req->ns = NULL;
+		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+	}
+
+	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
+		pr_err("nvmet: got io cmd %d while CSTS.RDY == 0\n",
+				cmd->common.opcode);
+		req->ns = NULL;
+		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+	}
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
+	if (!req->ns)
+		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+	switch (cmd->common.opcode) {
+	case nvme_cmd_read:
+	case nvme_cmd_write:
+		req->execute = nvmet_execute_rw;
+		req->data_len = nvmet_rw_len(req);
+		return 0;
+	case nvme_cmd_flush:
+		req->execute = nvmet_execute_flush;
+		req->data_len = 0;
+		return 0;
+	case nvme_cmd_dsm:
+		req->execute = nvmet_execute_dsm;
+		req->data_len = le32_to_cpu(cmd->dsm.nr) *
+			sizeof(struct nvme_dsm_range);
+		return 0;
+	default:
+		pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+	}
+}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
new file mode 100644
index 000000000000..94e782987cc9
--- /dev/null
+++ b/drivers/nvme/target/loop.c
@@ -0,0 +1,754 @@
+/*
+ * NVMe over Fabrics loopback device.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/scatterlist.h>
+#include <linux/delay.h>
+#include <linux/blk-mq.h>
+#include <linux/nvme.h>
+#include <linux/module.h>
+#include <linux/parser.h>
+#include <linux/t10-pi.h>
+#include "nvmet.h"
+#include "../host/nvme.h"
+#include "../host/fabrics.h"
+
+#define NVME_LOOP_AQ_DEPTH		256
+
+#define NVME_LOOP_MAX_SEGMENTS		256
+
+/*
+ * We handle AEN commands ourselves and don't even let the
+ * block layer know about them.
+ */
+#define NVME_LOOP_NR_AEN_COMMANDS	1
+#define NVME_LOOP_AQ_BLKMQ_DEPTH	\
+	(NVME_LOOP_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS)
+
+struct nvme_loop_iod {
+	struct nvme_command	cmd;
+	struct nvme_completion	rsp;
+	struct nvmet_req	req;
+	struct nvme_loop_queue	*queue;
+	struct work_struct	work;
+	struct sg_table		sg_table;
+	struct scatterlist	first_sgl[];
+};
+
+struct nvme_loop_ctrl {
+	spinlock_t		lock;
+	struct nvme_loop_queue	*queues;
+	u32			queue_count;
+
+	struct blk_mq_tag_set	admin_tag_set;
+
+	struct list_head	list;
+	u64			cap;
+	struct blk_mq_tag_set	tag_set;
+	struct nvme_loop_iod	async_event_iod;
+	struct nvme_ctrl	ctrl;
+
+	struct nvmet_ctrl	*target_ctrl;
+	struct work_struct	delete_work;
+	struct work_struct	reset_work;
+};
+
+static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
+{
+	return container_of(ctrl, struct nvme_loop_ctrl, ctrl);
+}
+
+struct nvme_loop_queue {
+	struct nvmet_cq		nvme_cq;
+	struct nvmet_sq		nvme_sq;
+	struct nvme_loop_ctrl	*ctrl;
+};
+
+static struct nvmet_port *nvmet_loop_port;
+
+static LIST_HEAD(nvme_loop_ctrl_list);
+static DEFINE_MUTEX(nvme_loop_ctrl_mutex);
+
+static void nvme_loop_queue_response(struct nvmet_req *nvme_req);
+static void nvme_loop_delete_ctrl(struct nvmet_ctrl *ctrl);
+
+static struct nvmet_fabrics_ops nvme_loop_ops;
+
+static inline int nvme_loop_queue_idx(struct nvme_loop_queue *queue)
+{
+	return queue - queue->ctrl->queues;
+}
+
+static void nvme_loop_complete_rq(struct request *req)
+{
+	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
+	int error = 0;
+
+	nvme_cleanup_cmd(req);
+	sg_free_table_chained(&iod->sg_table, true);
+
+	if (unlikely(req->errors)) {
+		if (nvme_req_needs_retry(req, req->errors)) {
+			nvme_requeue_req(req);
+			return;
+		}
+
+		if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+			error = req->errors;
+		else
+			error = nvme_error_status(req->errors);
+	}
+
+	blk_mq_end_request(req, error);
+}
+
+static void nvme_loop_queue_response(struct nvmet_req *nvme_req)
+{
+	struct nvme_loop_iod *iod =
+		container_of(nvme_req, struct nvme_loop_iod, req);
+	struct nvme_completion *cqe = &iod->rsp;
+
+	/*
+	 * AEN requests are special as they don't time out and can
+	 * survive any kind of queue freeze and often don't respond to
+	 * aborts.  We don't even bother to allocate a struct request
+	 * for them but rather special case them here.
+	 */
+	if (unlikely(nvme_loop_queue_idx(iod->queue) == 0 &&
+			cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) {
+		nvme_complete_async_event(&iod->queue->ctrl->ctrl, cqe);
+	} else {
+		struct request *req = blk_mq_rq_from_pdu(iod);
+
+		if (req->cmd_type == REQ_TYPE_DRV_PRIV && req->special)
+			memcpy(req->special, cqe, sizeof(*cqe));
+		blk_mq_complete_request(req, le16_to_cpu(cqe->status) >> 1);
+	}
+}
+
+static void nvme_loop_execute_work(struct work_struct *work)
+{
+	struct nvme_loop_iod *iod =
+		container_of(work, struct nvme_loop_iod, work);
+
+	iod->req.execute(&iod->req);
+}
+
+static enum blk_eh_timer_return
+nvme_loop_timeout(struct request *rq, bool reserved)
+{
+	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(rq);
+
+	/* queue error recovery */
+	schedule_work(&iod->queue->ctrl->reset_work);
+
+	/* fail with DNR on admin cmd timeout */
+	rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+
+	return BLK_EH_HANDLED;
+}
+
+static int nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
+{
+	struct nvme_ns *ns = hctx->queue->queuedata;
+	struct nvme_loop_queue *queue = hctx->driver_data;
+	struct request *req = bd->rq;
+	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
+	int ret;
+
+	ret = nvme_setup_cmd(ns, req, &iod->cmd);
+	if (ret)
+		return ret;
+
+	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
+	iod->req.port = nvmet_loop_port;
+	if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
+			&queue->nvme_sq, &nvme_loop_ops)) {
+		nvme_cleanup_cmd(req);
+		blk_mq_start_request(req);
+		nvme_loop_queue_response(&iod->req);
+		return 0;
+	}
+
+	if (blk_rq_bytes(req)) {
+		iod->sg_table.sgl = iod->first_sgl;
+		ret = sg_alloc_table_chained(&iod->sg_table,
+			req->nr_phys_segments, iod->sg_table.sgl);
+		if (ret)
+			return BLK_MQ_RQ_QUEUE_BUSY;
+
+		iod->req.sg = iod->sg_table.sgl;
+		iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
+		BUG_ON(iod->req.sg_cnt > req->nr_phys_segments);
+	}
+
+	iod->cmd.common.command_id = req->tag;
+	blk_mq_start_request(req);
+
+	schedule_work(&iod->work);
+	return 0;
+}
+
+static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
+{
+	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(arg);
+	struct nvme_loop_queue *queue = &ctrl->queues[0];
+	struct nvme_loop_iod *iod = &ctrl->async_event_iod;
+
+	memset(&iod->cmd, 0, sizeof(iod->cmd));
+	iod->cmd.common.opcode = nvme_admin_async_event;
+	iod->cmd.common.command_id = NVME_LOOP_AQ_BLKMQ_DEPTH;
+	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
+
+	if (!nvmet_req_init(&iod->req, &queue->nvme_cq, &queue->nvme_sq,
+			&nvme_loop_ops)) {
+		dev_err(ctrl->ctrl.device, "failed async event work\n");
+		return;
+	}
+
+	schedule_work(&iod->work);
+}
+
+static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl,
+		struct nvme_loop_iod *iod, unsigned int queue_idx)
+{
+	BUG_ON(queue_idx >= ctrl->queue_count);
+
+	iod->req.cmd = &iod->cmd;
+	iod->req.rsp = &iod->rsp;
+	iod->queue = &ctrl->queues[queue_idx];
+	INIT_WORK(&iod->work, nvme_loop_execute_work);
+	return 0;
+}
+
+static int nvme_loop_init_request(void *data, struct request *req,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
+{
+	return nvme_loop_init_iod(data, blk_mq_rq_to_pdu(req), hctx_idx + 1);
+}
+
+static int nvme_loop_init_admin_request(void *data, struct request *req,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
+{
+	return nvme_loop_init_iod(data, blk_mq_rq_to_pdu(req), 0);
+}
+
+static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+		unsigned int hctx_idx)
+{
+	struct nvme_loop_ctrl *ctrl = data;
+	struct nvme_loop_queue *queue = &ctrl->queues[hctx_idx + 1];
+
+	BUG_ON(hctx_idx >= ctrl->queue_count);
+
+	hctx->driver_data = queue;
+	return 0;
+}
+
+static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+		unsigned int hctx_idx)
+{
+	struct nvme_loop_ctrl *ctrl = data;
+	struct nvme_loop_queue *queue = &ctrl->queues[0];
+
+	BUG_ON(hctx_idx != 0);
+
+	hctx->driver_data = queue;
+	return 0;
+}
+
+static struct blk_mq_ops nvme_loop_mq_ops = {
+	.queue_rq	= nvme_loop_queue_rq,
+	.complete	= nvme_loop_complete_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= nvme_loop_init_request,
+	.init_hctx	= nvme_loop_init_hctx,
+	.timeout	= nvme_loop_timeout,
+};
+
+static struct blk_mq_ops nvme_loop_admin_mq_ops = {
+	.queue_rq	= nvme_loop_queue_rq,
+	.complete	= nvme_loop_complete_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= nvme_loop_init_admin_request,
+	.init_hctx	= nvme_loop_init_admin_hctx,
+	.timeout	= nvme_loop_timeout,
+};
+
+static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
+{
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
+}
+
+static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl);
+
+	if (list_empty(&ctrl->list))
+		goto free_ctrl;
+
+	mutex_lock(&nvme_loop_ctrl_mutex);
+	list_del(&ctrl->list);
+	mutex_unlock(&nvme_loop_ctrl_mutex);
+
+	if (nctrl->tagset) {
+		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_free_tag_set(&ctrl->tag_set);
+	}
+	kfree(ctrl->queues);
+	nvmf_free_options(nctrl->opts);
+free_ctrl:
+	kfree(ctrl);
+}
+
+static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
+{
+	int error;
+
+	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
+	ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops;
+	ctrl->admin_tag_set.queue_depth = NVME_LOOP_AQ_BLKMQ_DEPTH;
+	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
+	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
+		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+	ctrl->admin_tag_set.driver_data = ctrl;
+	ctrl->admin_tag_set.nr_hw_queues = 1;
+	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
+
+	ctrl->queues[0].ctrl = ctrl;
+	error = nvmet_sq_init(&ctrl->queues[0].nvme_sq);
+	if (error)
+		return error;
+	ctrl->queue_count = 1;
+
+	error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
+	if (error)
+		goto out_free_sq;
+
+	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+	if (IS_ERR(ctrl->ctrl.admin_q)) {
+		error = PTR_ERR(ctrl->ctrl.admin_q);
+		goto out_free_tagset;
+	}
+
+	error = nvmf_connect_admin_queue(&ctrl->ctrl);
+	if (error)
+		goto out_cleanup_queue;
+
+	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
+	if (error) {
+		dev_err(ctrl->ctrl.device,
+			"prop_get NVME_REG_CAP failed\n");
+		goto out_cleanup_queue;
+	}
+
+	ctrl->ctrl.sqsize =
+		min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
+
+	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
+	if (error)
+		goto out_cleanup_queue;
+
+	ctrl->ctrl.max_hw_sectors =
+		(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
+
+	error = nvme_init_identify(&ctrl->ctrl);
+	if (error)
+		goto out_cleanup_queue;
+
+	nvme_start_keep_alive(&ctrl->ctrl);
+
+	return 0;
+
+out_cleanup_queue:
+	blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_free_tagset:
+	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+out_free_sq:
+	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
+	return error;
+}
+
+static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
+{
+	int i;
+
+	nvme_stop_keep_alive(&ctrl->ctrl);
+
+	if (ctrl->queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set,
+					nvme_cancel_request, &ctrl->ctrl);
+
+		for (i = 1; i < ctrl->queue_count; i++)
+			nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+	}
+
+	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+		nvme_shutdown_ctrl(&ctrl->ctrl);
+
+	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+				nvme_cancel_request, &ctrl->ctrl);
+	nvme_loop_destroy_admin_queue(ctrl);
+}
+
+static void nvme_loop_del_ctrl_work(struct work_struct *work)
+{
+	struct nvme_loop_ctrl *ctrl = container_of(work,
+				struct nvme_loop_ctrl, delete_work);
+
+	nvme_remove_namespaces(&ctrl->ctrl);
+	nvme_loop_shutdown_ctrl(ctrl);
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+}
+
+static int __nvme_loop_del_ctrl(struct nvme_loop_ctrl *ctrl)
+{
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
+		return -EBUSY;
+
+	if (!schedule_work(&ctrl->delete_work))
+		return -EBUSY;
+
+	return 0;
+}
+
+static int nvme_loop_del_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl);
+	int ret;
+
+	ret = __nvme_loop_del_ctrl(ctrl);
+	if (ret)
+		return ret;
+
+	flush_work(&ctrl->delete_work);
+
+	return 0;
+}
+
+static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl)
+{
+	struct nvme_loop_ctrl *ctrl;
+
+	mutex_lock(&nvme_loop_ctrl_mutex);
+	list_for_each_entry(ctrl, &nvme_loop_ctrl_list, list) {
+		if (ctrl->ctrl.cntlid == nctrl->cntlid)
+			__nvme_loop_del_ctrl(ctrl);
+	}
+	mutex_unlock(&nvme_loop_ctrl_mutex);
+}
+
+static void nvme_loop_reset_ctrl_work(struct work_struct *work)
+{
+	struct nvme_loop_ctrl *ctrl = container_of(work,
+					struct nvme_loop_ctrl, reset_work);
+	bool changed;
+	int i, ret;
+
+	nvme_loop_shutdown_ctrl(ctrl);
+
+	ret = nvme_loop_configure_admin_queue(ctrl);
+	if (ret)
+		goto out_disable;
+
+	for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
+		ctrl->queues[i].ctrl = ctrl;
+		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
+		if (ret)
+			goto out_free_queues;
+
+		ctrl->queue_count++;
+	}
+
+	for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+		if (ret)
+			goto out_free_queues;
+	}
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	nvme_queue_scan(&ctrl->ctrl);
+	nvme_queue_async_events(&ctrl->ctrl);
+
+	nvme_start_queues(&ctrl->ctrl);
+
+	return;
+
+out_free_queues:
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+	nvme_loop_destroy_admin_queue(ctrl);
+out_disable:
+	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
+	nvme_remove_namespaces(&ctrl->ctrl);
+	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
+}
+
+static int nvme_loop_reset_ctrl(struct nvme_ctrl *nctrl)
+{
+	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl);
+
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
+		return -EBUSY;
+
+	if (!schedule_work(&ctrl->reset_work))
+		return -EBUSY;
+
+	flush_work(&ctrl->reset_work);
+
+	return 0;
+}
+
+static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
+	.name			= "loop",
+	.module			= THIS_MODULE,
+	.is_fabrics		= true,
+	.reg_read32		= nvmf_reg_read32,
+	.reg_read64		= nvmf_reg_read64,
+	.reg_write32		= nvmf_reg_write32,
+	.reset_ctrl		= nvme_loop_reset_ctrl,
+	.free_ctrl		= nvme_loop_free_ctrl,
+	.submit_async_event	= nvme_loop_submit_async_event,
+	.delete_ctrl		= nvme_loop_del_ctrl,
+	.get_subsysnqn		= nvmf_get_subsysnqn,
+};
+
+static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	int ret, i;
+
+	ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
+	if (ret || !opts->nr_io_queues)
+		return ret;
+
+	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
+		opts->nr_io_queues);
+
+	for (i = 1; i <= opts->nr_io_queues; i++) {
+		ctrl->queues[i].ctrl = ctrl;
+		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
+		if (ret)
+			goto out_destroy_queues;
+
+		ctrl->queue_count++;
+	}
+
+	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
+	ctrl->tag_set.ops = &nvme_loop_mq_ops;
+	ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize;
+	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+	ctrl->tag_set.numa_node = NUMA_NO_NODE;
+	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
+		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+	ctrl->tag_set.driver_data = ctrl;
+	ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
+	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
+	ctrl->ctrl.tagset = &ctrl->tag_set;
+
+	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
+	if (ret)
+		goto out_destroy_queues;
+
+	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
+	if (IS_ERR(ctrl->ctrl.connect_q)) {
+		ret = PTR_ERR(ctrl->ctrl.connect_q);
+		goto out_free_tagset;
+	}
+
+	for (i = 1; i <= opts->nr_io_queues; i++) {
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+		if (ret)
+			goto out_cleanup_connect_q;
+	}
+
+	return 0;
+
+out_cleanup_connect_q:
+	blk_cleanup_queue(ctrl->ctrl.connect_q);
+out_free_tagset:
+	blk_mq_free_tag_set(&ctrl->tag_set);
+out_destroy_queues:
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+	return ret;
+}
+
+static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
+		struct nvmf_ctrl_options *opts)
+{
+	struct nvme_loop_ctrl *ctrl;
+	bool changed;
+	int ret;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return ERR_PTR(-ENOMEM);
+	ctrl->ctrl.opts = opts;
+	INIT_LIST_HEAD(&ctrl->list);
+
+	INIT_WORK(&ctrl->delete_work, nvme_loop_del_ctrl_work);
+	INIT_WORK(&ctrl->reset_work, nvme_loop_reset_ctrl_work);
+
+	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops,
+				0 /* no quirks, we're perfect! */);
+	if (ret)
+		goto out_put_ctrl;
+
+	spin_lock_init(&ctrl->lock);
+
+	ret = -ENOMEM;
+
+	ctrl->ctrl.sqsize = opts->queue_size;
+	ctrl->ctrl.kato = opts->kato;
+
+	ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
+			GFP_KERNEL);
+	if (!ctrl->queues)
+		goto out_uninit_ctrl;
+
+	ret = nvme_loop_configure_admin_queue(ctrl);
+	if (ret)
+		goto out_free_queues;
+
+	if (opts->queue_size > ctrl->ctrl.maxcmd) {
+		/* warn if maxcmd is lower than queue_size */
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl maxcmd %u, clamping down\n",
+			opts->queue_size, ctrl->ctrl.maxcmd);
+		opts->queue_size = ctrl->ctrl.maxcmd;
+	}
+
+	if (opts->nr_io_queues) {
+		ret = nvme_loop_create_io_queues(ctrl);
+		if (ret)
+			goto out_remove_admin_queue;
+	}
+
+	nvme_loop_init_iod(ctrl, &ctrl->async_event_iod, 0);
+
+	dev_info(ctrl->ctrl.device,
+		 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
+
+	kref_get(&ctrl->ctrl.kref);
+
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	WARN_ON_ONCE(!changed);
+
+	mutex_lock(&nvme_loop_ctrl_mutex);
+	list_add_tail(&ctrl->list, &nvme_loop_ctrl_list);
+	mutex_unlock(&nvme_loop_ctrl_mutex);
+
+	if (opts->nr_io_queues) {
+		nvme_queue_scan(&ctrl->ctrl);
+		nvme_queue_async_events(&ctrl->ctrl);
+	}
+
+	return &ctrl->ctrl;
+
+out_remove_admin_queue:
+	nvme_loop_destroy_admin_queue(ctrl);
+out_free_queues:
+	kfree(ctrl->queues);
+out_uninit_ctrl:
+	nvme_uninit_ctrl(&ctrl->ctrl);
+out_put_ctrl:
+	nvme_put_ctrl(&ctrl->ctrl);
+	if (ret > 0)
+		ret = -EIO;
+	return ERR_PTR(ret);
+}
+
+static int nvme_loop_add_port(struct nvmet_port *port)
+{
+	/*
+	 * XXX: disalow adding more than one port so
+	 * there is no connection rejections when a
+	 * a subsystem is assigned to a port for which
+	 * loop doesn't have a pointer.
+	 * This scenario would be possible if we allowed
+	 * more than one port to be added and a subsystem
+	 * was assigned to a port other than nvmet_loop_port.
+	 */
+
+	if (nvmet_loop_port)
+		return -EPERM;
+
+	nvmet_loop_port = port;
+	return 0;
+}
+
+static void nvme_loop_remove_port(struct nvmet_port *port)
+{
+	if (port == nvmet_loop_port)
+		nvmet_loop_port = NULL;
+}
+
+static struct nvmet_fabrics_ops nvme_loop_ops = {
+	.owner		= THIS_MODULE,
+	.type		= NVMF_TRTYPE_LOOP,
+	.add_port	= nvme_loop_add_port,
+	.remove_port	= nvme_loop_remove_port,
+	.queue_response = nvme_loop_queue_response,
+	.delete_ctrl	= nvme_loop_delete_ctrl,
+};
+
+static struct nvmf_transport_ops nvme_loop_transport = {
+	.name		= "loop",
+	.create_ctrl	= nvme_loop_create_ctrl,
+};
+
+static int __init nvme_loop_init_module(void)
+{
+	int ret;
+
+	ret = nvmet_register_transport(&nvme_loop_ops);
+	if (ret)
+		return ret;
+	nvmf_register_transport(&nvme_loop_transport);
+	return 0;
+}
+
+static void __exit nvme_loop_cleanup_module(void)
+{
+	struct nvme_loop_ctrl *ctrl, *next;
+
+	nvmf_unregister_transport(&nvme_loop_transport);
+	nvmet_unregister_transport(&nvme_loop_ops);
+
+	mutex_lock(&nvme_loop_ctrl_mutex);
+	list_for_each_entry_safe(ctrl, next, &nvme_loop_ctrl_list, list)
+		__nvme_loop_del_ctrl(ctrl);
+	mutex_unlock(&nvme_loop_ctrl_mutex);
+
+	flush_scheduled_work();
+}
+
+module_init(nvme_loop_init_module);
+module_exit(nvme_loop_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
new file mode 100644
index 000000000000..57dd6d834c28
--- /dev/null
+++ b/drivers/nvme/target/nvmet.h
@@ -0,0 +1,331 @@
+/*
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _NVMET_H
+#define _NVMET_H
+
+#include <linux/dma-mapping.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/kref.h>
+#include <linux/percpu-refcount.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/nvme.h>
+#include <linux/configfs.h>
+#include <linux/rcupdate.h>
+#include <linux/blkdev.h>
+
+#define NVMET_ASYNC_EVENTS		4
+#define NVMET_ERROR_LOG_SLOTS		128
+
+/* Helper Macros when NVMe error is NVME_SC_CONNECT_INVALID_PARAM
+ * The 16 bit shift is to set IATTR bit to 1, which means offending
+ * offset starts in the data section of connect()
+ */
+#define IPO_IATTR_CONNECT_DATA(x)	\
+	(cpu_to_le32((1 << 16) | (offsetof(struct nvmf_connect_data, x))))
+#define IPO_IATTR_CONNECT_SQE(x)	\
+	(cpu_to_le32(offsetof(struct nvmf_connect_command, x)))
+
+struct nvmet_ns {
+	struct list_head	dev_link;
+	struct percpu_ref	ref;
+	struct block_device	*bdev;
+	u32			nsid;
+	u32			blksize_shift;
+	loff_t			size;
+	u8			nguid[16];
+
+	struct nvmet_subsys	*subsys;
+	const char		*device_path;
+
+	struct config_group	device_group;
+	struct config_group	group;
+
+	struct completion	disable_done;
+};
+
+static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_ns, group);
+}
+
+static inline bool nvmet_ns_enabled(struct nvmet_ns *ns)
+{
+	return !list_empty_careful(&ns->dev_link);
+}
+
+struct nvmet_cq {
+	u16			qid;
+	u16			size;
+};
+
+struct nvmet_sq {
+	struct nvmet_ctrl	*ctrl;
+	struct percpu_ref	ref;
+	u16			qid;
+	u16			size;
+	struct completion	free_done;
+};
+
+/**
+ * struct nvmet_port -	Common structure to keep port
+ *				information for the target.
+ * @entry:		List head for holding a list of these elements.
+ * @disc_addr:		Address information is stored in a format defined
+ *				for a discovery log page entry.
+ * @group:		ConfigFS group for this element's folder.
+ * @priv:		Private data for the transport.
+ */
+struct nvmet_port {
+	struct list_head		entry;
+	struct nvmf_disc_rsp_page_entry	disc_addr;
+	struct config_group		group;
+	struct config_group		subsys_group;
+	struct list_head		subsystems;
+	struct config_group		referrals_group;
+	struct list_head		referrals;
+	void				*priv;
+	bool				enabled;
+};
+
+static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_port,
+			group);
+}
+
+struct nvmet_ctrl {
+	struct nvmet_subsys	*subsys;
+	struct nvmet_cq		**cqs;
+	struct nvmet_sq		**sqs;
+
+	struct mutex		lock;
+	u64			cap;
+	u32			cc;
+	u32			csts;
+
+	u16			cntlid;
+	u32			kato;
+
+	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
+	unsigned int		nr_async_event_cmds;
+	struct list_head	async_events;
+	struct work_struct	async_event_work;
+
+	struct list_head	subsys_entry;
+	struct kref		ref;
+	struct delayed_work	ka_work;
+	struct work_struct	fatal_err_work;
+
+	struct nvmet_fabrics_ops *ops;
+
+	char			subsysnqn[NVMF_NQN_FIELD_LEN];
+	char			hostnqn[NVMF_NQN_FIELD_LEN];
+};
+
+struct nvmet_subsys {
+	enum nvme_subsys_type	type;
+
+	struct mutex		lock;
+	struct kref		ref;
+
+	struct list_head	namespaces;
+	unsigned int		max_nsid;
+
+	struct list_head	ctrls;
+	struct ida		cntlid_ida;
+
+	struct list_head	hosts;
+	bool			allow_any_host;
+
+	u16			max_qid;
+
+	u64			ver;
+	char			*subsysnqn;
+
+	struct config_group	group;
+
+	struct config_group	namespaces_group;
+	struct config_group	allowed_hosts_group;
+};
+
+static inline struct nvmet_subsys *to_subsys(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_subsys, group);
+}
+
+static inline struct nvmet_subsys *namespaces_to_subsys(
+		struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_subsys,
+			namespaces_group);
+}
+
+struct nvmet_host {
+	struct config_group	group;
+};
+
+static inline struct nvmet_host *to_host(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_host, group);
+}
+
+static inline char *nvmet_host_name(struct nvmet_host *host)
+{
+	return config_item_name(&host->group.cg_item);
+}
+
+struct nvmet_host_link {
+	struct list_head	entry;
+	struct nvmet_host	*host;
+};
+
+struct nvmet_subsys_link {
+	struct list_head	entry;
+	struct nvmet_subsys	*subsys;
+};
+
+struct nvmet_req;
+struct nvmet_fabrics_ops {
+	struct module *owner;
+	unsigned int type;
+	unsigned int sqe_inline_size;
+	unsigned int msdbd;
+	bool has_keyed_sgls : 1;
+	void (*queue_response)(struct nvmet_req *req);
+	int (*add_port)(struct nvmet_port *port);
+	void (*remove_port)(struct nvmet_port *port);
+	void (*delete_ctrl)(struct nvmet_ctrl *ctrl);
+};
+
+#define NVMET_MAX_INLINE_BIOVEC	8
+
+struct nvmet_req {
+	struct nvme_command	*cmd;
+	struct nvme_completion	*rsp;
+	struct nvmet_sq		*sq;
+	struct nvmet_cq		*cq;
+	struct nvmet_ns		*ns;
+	struct scatterlist	*sg;
+	struct bio		inline_bio;
+	struct bio_vec		inline_bvec[NVMET_MAX_INLINE_BIOVEC];
+	int			sg_cnt;
+	size_t			data_len;
+
+	struct nvmet_port	*port;
+
+	void (*execute)(struct nvmet_req *req);
+	struct nvmet_fabrics_ops *ops;
+};
+
+static inline void nvmet_set_status(struct nvmet_req *req, u16 status)
+{
+	req->rsp->status = cpu_to_le16(status << 1);
+}
+
+static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
+{
+	req->rsp->result = cpu_to_le32(result);
+}
+
+/*
+ * NVMe command writes actually are DMA reads for us on the target side.
+ */
+static inline enum dma_data_direction
+nvmet_data_dir(struct nvmet_req *req)
+{
+	return nvme_is_write(req->cmd) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+}
+
+struct nvmet_async_event {
+	struct list_head	entry;
+	u8			event_type;
+	u8			event_info;
+	u8			log_page;
+};
+
+int nvmet_parse_connect_cmd(struct nvmet_req *req);
+int nvmet_parse_io_cmd(struct nvmet_req *req);
+int nvmet_parse_admin_cmd(struct nvmet_req *req);
+int nvmet_parse_discovery_cmd(struct nvmet_req *req);
+int nvmet_parse_fabrics_cmd(struct nvmet_req *req);
+
+bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
+		struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops);
+void nvmet_req_complete(struct nvmet_req *req, u16 status);
+
+void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
+		u16 size);
+void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid,
+		u16 size);
+void nvmet_sq_destroy(struct nvmet_sq *sq);
+int nvmet_sq_init(struct nvmet_sq *sq);
+
+void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl);
+
+void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new);
+u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
+		struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp);
+u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid,
+		struct nvmet_req *req, struct nvmet_ctrl **ret);
+void nvmet_ctrl_put(struct nvmet_ctrl *ctrl);
+
+struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
+		enum nvme_subsys_type type);
+void nvmet_subsys_put(struct nvmet_subsys *subsys);
+
+struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid);
+void nvmet_put_namespace(struct nvmet_ns *ns);
+int nvmet_ns_enable(struct nvmet_ns *ns);
+void nvmet_ns_disable(struct nvmet_ns *ns);
+struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid);
+void nvmet_ns_free(struct nvmet_ns *ns);
+
+int nvmet_register_transport(struct nvmet_fabrics_ops *ops);
+void nvmet_unregister_transport(struct nvmet_fabrics_ops *ops);
+
+int nvmet_enable_port(struct nvmet_port *port);
+void nvmet_disable_port(struct nvmet_port *port);
+
+void nvmet_referral_enable(struct nvmet_port *parent, struct nvmet_port *port);
+void nvmet_referral_disable(struct nvmet_port *port);
+
+u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
+		size_t len);
+u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf,
+		size_t len);
+
+u32 nvmet_get_log_page_len(struct nvme_command *cmd);
+
+#define NVMET_QUEUE_SIZE	1024
+#define NVMET_NR_QUEUES		64
+#define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+#define NVMET_KAS		10
+#define NVMET_DISC_KATO		120
+
+int __init nvmet_init_configfs(void);
+void __exit nvmet_exit_configfs(void);
+
+int __init nvmet_init_discovery(void);
+void nvmet_exit_discovery(void);
+
+extern struct nvmet_subsys *nvmet_disc_subsys;
+extern u64 nvmet_genctr;
+extern struct rw_semaphore nvmet_config_sem;
+
+bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
+		const char *hostnqn);
+
+#endif /* _NVMET_H */
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
new file mode 100644
index 000000000000..e06d504bdf0c
--- /dev/null
+++ b/drivers/nvme/target/rdma.c
@@ -0,0 +1,1448 @@
+/*
+ * NVMe over Fabrics RDMA target.
+ * Copyright (c) 2015-2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/atomic.h>
+#include <linux/ctype.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/nvme.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/wait.h>
+#include <linux/inet.h>
+#include <asm/unaligned.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+#include <rdma/rw.h>
+
+#include <linux/nvme-rdma.h>
+#include "nvmet.h"
+
+/*
+ * We allow up to a page of inline data to go with the SQE
+ */
+#define NVMET_RDMA_INLINE_DATA_SIZE	PAGE_SIZE
+
+struct nvmet_rdma_cmd {
+	struct ib_sge		sge[2];
+	struct ib_cqe		cqe;
+	struct ib_recv_wr	wr;
+	struct scatterlist	inline_sg;
+	struct page		*inline_page;
+	struct nvme_command     *nvme_cmd;
+	struct nvmet_rdma_queue	*queue;
+};
+
+enum {
+	NVMET_RDMA_REQ_INLINE_DATA	= (1 << 0),
+	NVMET_RDMA_REQ_INVALIDATE_RKEY	= (1 << 1),
+};
+
+struct nvmet_rdma_rsp {
+	struct ib_sge		send_sge;
+	struct ib_cqe		send_cqe;
+	struct ib_send_wr	send_wr;
+
+	struct nvmet_rdma_cmd	*cmd;
+	struct nvmet_rdma_queue	*queue;
+
+	struct ib_cqe		read_cqe;
+	struct rdma_rw_ctx	rw;
+
+	struct nvmet_req	req;
+
+	u8			n_rdma;
+	u32			flags;
+	u32			invalidate_rkey;
+
+	struct list_head	wait_list;
+	struct list_head	free_list;
+};
+
+enum nvmet_rdma_queue_state {
+	NVMET_RDMA_Q_CONNECTING,
+	NVMET_RDMA_Q_LIVE,
+	NVMET_RDMA_Q_DISCONNECTING,
+};
+
+struct nvmet_rdma_queue {
+	struct rdma_cm_id	*cm_id;
+	struct nvmet_port	*port;
+	struct ib_cq		*cq;
+	atomic_t		sq_wr_avail;
+	struct nvmet_rdma_device *dev;
+	spinlock_t		state_lock;
+	enum nvmet_rdma_queue_state state;
+	struct nvmet_cq		nvme_cq;
+	struct nvmet_sq		nvme_sq;
+
+	struct nvmet_rdma_rsp	*rsps;
+	struct list_head	free_rsps;
+	spinlock_t		rsps_lock;
+	struct nvmet_rdma_cmd	*cmds;
+
+	struct work_struct	release_work;
+	struct list_head	rsp_wait_list;
+	struct list_head	rsp_wr_wait_list;
+	spinlock_t		rsp_wr_wait_lock;
+
+	int			idx;
+	int			host_qid;
+	int			recv_queue_size;
+	int			send_queue_size;
+
+	struct list_head	queue_list;
+};
+
+struct nvmet_rdma_device {
+	struct ib_device	*device;
+	struct ib_pd		*pd;
+	struct ib_srq		*srq;
+	struct nvmet_rdma_cmd	*srq_cmds;
+	size_t			srq_size;
+	struct kref		ref;
+	struct list_head	entry;
+};
+
+static bool nvmet_rdma_use_srq;
+module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444);
+MODULE_PARM_DESC(use_srq, "Use shared receive queue.");
+
+static DEFINE_IDA(nvmet_rdma_queue_ida);
+static LIST_HEAD(nvmet_rdma_queue_list);
+static DEFINE_MUTEX(nvmet_rdma_queue_mutex);
+
+static LIST_HEAD(device_list);
+static DEFINE_MUTEX(device_list_mutex);
+
+static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp);
+static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc);
+static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
+static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc);
+static void nvmet_rdma_qp_event(struct ib_event *event, void *priv);
+static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
+
+static struct nvmet_fabrics_ops nvmet_rdma_ops;
+
+/* XXX: really should move to a generic header sooner or later.. */
+static inline u32 get_unaligned_le24(const u8 *p)
+{
+	return (u32)p[0] | (u32)p[1] << 8 | (u32)p[2] << 16;
+}
+
+static inline bool nvmet_rdma_need_data_in(struct nvmet_rdma_rsp *rsp)
+{
+	return nvme_is_write(rsp->req.cmd) &&
+		rsp->req.data_len &&
+		!(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA);
+}
+
+static inline bool nvmet_rdma_need_data_out(struct nvmet_rdma_rsp *rsp)
+{
+	return !nvme_is_write(rsp->req.cmd) &&
+		rsp->req.data_len &&
+		!rsp->req.rsp->status &&
+		!(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA);
+}
+
+static inline struct nvmet_rdma_rsp *
+nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
+{
+	struct nvmet_rdma_rsp *rsp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&queue->rsps_lock, flags);
+	rsp = list_first_entry(&queue->free_rsps,
+				struct nvmet_rdma_rsp, free_list);
+	list_del(&rsp->free_list);
+	spin_unlock_irqrestore(&queue->rsps_lock, flags);
+
+	return rsp;
+}
+
+static inline void
+nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rsp->queue->rsps_lock, flags);
+	list_add_tail(&rsp->free_list, &rsp->queue->free_rsps);
+	spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
+}
+
+static void nvmet_rdma_free_sgl(struct scatterlist *sgl, unsigned int nents)
+{
+	struct scatterlist *sg;
+	int count;
+
+	if (!sgl || !nents)
+		return;
+
+	for_each_sg(sgl, sg, nents, count)
+		__free_page(sg_page(sg));
+	kfree(sgl);
+}
+
+static int nvmet_rdma_alloc_sgl(struct scatterlist **sgl, unsigned int *nents,
+		u32 length)
+{
+	struct scatterlist *sg;
+	struct page *page;
+	unsigned int nent;
+	int i = 0;
+
+	nent = DIV_ROUND_UP(length, PAGE_SIZE);
+	sg = kmalloc_array(nent, sizeof(struct scatterlist), GFP_KERNEL);
+	if (!sg)
+		goto out;
+
+	sg_init_table(sg, nent);
+
+	while (length) {
+		u32 page_len = min_t(u32, length, PAGE_SIZE);
+
+		page = alloc_page(GFP_KERNEL);
+		if (!page)
+			goto out_free_pages;
+
+		sg_set_page(&sg[i], page, page_len, 0);
+		length -= page_len;
+		i++;
+	}
+	*sgl = sg;
+	*nents = nent;
+	return 0;
+
+out_free_pages:
+	while (i > 0) {
+		i--;
+		__free_page(sg_page(&sg[i]));
+	}
+	kfree(sg);
+out:
+	return NVME_SC_INTERNAL;
+}
+
+static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
+			struct nvmet_rdma_cmd *c, bool admin)
+{
+	/* NVMe command / RDMA RECV */
+	c->nvme_cmd = kmalloc(sizeof(*c->nvme_cmd), GFP_KERNEL);
+	if (!c->nvme_cmd)
+		goto out;
+
+	c->sge[0].addr = ib_dma_map_single(ndev->device, c->nvme_cmd,
+			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
+	if (ib_dma_mapping_error(ndev->device, c->sge[0].addr))
+		goto out_free_cmd;
+
+	c->sge[0].length = sizeof(*c->nvme_cmd);
+	c->sge[0].lkey = ndev->pd->local_dma_lkey;
+
+	if (!admin) {
+		c->inline_page = alloc_pages(GFP_KERNEL,
+				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
+		if (!c->inline_page)
+			goto out_unmap_cmd;
+		c->sge[1].addr = ib_dma_map_page(ndev->device,
+				c->inline_page, 0, NVMET_RDMA_INLINE_DATA_SIZE,
+				DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(ndev->device, c->sge[1].addr))
+			goto out_free_inline_page;
+		c->sge[1].length = NVMET_RDMA_INLINE_DATA_SIZE;
+		c->sge[1].lkey = ndev->pd->local_dma_lkey;
+	}
+
+	c->cqe.done = nvmet_rdma_recv_done;
+
+	c->wr.wr_cqe = &c->cqe;
+	c->wr.sg_list = c->sge;
+	c->wr.num_sge = admin ? 1 : 2;
+
+	return 0;
+
+out_free_inline_page:
+	if (!admin) {
+		__free_pages(c->inline_page,
+				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
+	}
+out_unmap_cmd:
+	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
+			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
+out_free_cmd:
+	kfree(c->nvme_cmd);
+
+out:
+	return -ENOMEM;
+}
+
+static void nvmet_rdma_free_cmd(struct nvmet_rdma_device *ndev,
+		struct nvmet_rdma_cmd *c, bool admin)
+{
+	if (!admin) {
+		ib_dma_unmap_page(ndev->device, c->sge[1].addr,
+				NVMET_RDMA_INLINE_DATA_SIZE, DMA_FROM_DEVICE);
+		__free_pages(c->inline_page,
+				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
+	}
+	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
+				sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
+	kfree(c->nvme_cmd);
+}
+
+static struct nvmet_rdma_cmd *
+nvmet_rdma_alloc_cmds(struct nvmet_rdma_device *ndev,
+		int nr_cmds, bool admin)
+{
+	struct nvmet_rdma_cmd *cmds;
+	int ret = -EINVAL, i;
+
+	cmds = kcalloc(nr_cmds, sizeof(struct nvmet_rdma_cmd), GFP_KERNEL);
+	if (!cmds)
+		goto out;
+
+	for (i = 0; i < nr_cmds; i++) {
+		ret = nvmet_rdma_alloc_cmd(ndev, cmds + i, admin);
+		if (ret)
+			goto out_free;
+	}
+
+	return cmds;
+
+out_free:
+	while (--i >= 0)
+		nvmet_rdma_free_cmd(ndev, cmds + i, admin);
+	kfree(cmds);
+out:
+	return ERR_PTR(ret);
+}
+
+static void nvmet_rdma_free_cmds(struct nvmet_rdma_device *ndev,
+		struct nvmet_rdma_cmd *cmds, int nr_cmds, bool admin)
+{
+	int i;
+
+	for (i = 0; i < nr_cmds; i++)
+		nvmet_rdma_free_cmd(ndev, cmds + i, admin);
+	kfree(cmds);
+}
+
+static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
+		struct nvmet_rdma_rsp *r)
+{
+	/* NVMe CQE / RDMA SEND */
+	r->req.rsp = kmalloc(sizeof(*r->req.rsp), GFP_KERNEL);
+	if (!r->req.rsp)
+		goto out;
+
+	r->send_sge.addr = ib_dma_map_single(ndev->device, r->req.rsp,
+			sizeof(*r->req.rsp), DMA_TO_DEVICE);
+	if (ib_dma_mapping_error(ndev->device, r->send_sge.addr))
+		goto out_free_rsp;
+
+	r->send_sge.length = sizeof(*r->req.rsp);
+	r->send_sge.lkey = ndev->pd->local_dma_lkey;
+
+	r->send_cqe.done = nvmet_rdma_send_done;
+
+	r->send_wr.wr_cqe = &r->send_cqe;
+	r->send_wr.sg_list = &r->send_sge;
+	r->send_wr.num_sge = 1;
+	r->send_wr.send_flags = IB_SEND_SIGNALED;
+
+	/* Data In / RDMA READ */
+	r->read_cqe.done = nvmet_rdma_read_data_done;
+	return 0;
+
+out_free_rsp:
+	kfree(r->req.rsp);
+out:
+	return -ENOMEM;
+}
+
+static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev,
+		struct nvmet_rdma_rsp *r)
+{
+	ib_dma_unmap_single(ndev->device, r->send_sge.addr,
+				sizeof(*r->req.rsp), DMA_TO_DEVICE);
+	kfree(r->req.rsp);
+}
+
+static int
+nvmet_rdma_alloc_rsps(struct nvmet_rdma_queue *queue)
+{
+	struct nvmet_rdma_device *ndev = queue->dev;
+	int nr_rsps = queue->recv_queue_size * 2;
+	int ret = -EINVAL, i;
+
+	queue->rsps = kcalloc(nr_rsps, sizeof(struct nvmet_rdma_rsp),
+			GFP_KERNEL);
+	if (!queue->rsps)
+		goto out;
+
+	for (i = 0; i < nr_rsps; i++) {
+		struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
+
+		ret = nvmet_rdma_alloc_rsp(ndev, rsp);
+		if (ret)
+			goto out_free;
+
+		list_add_tail(&rsp->free_list, &queue->free_rsps);
+	}
+
+	return 0;
+
+out_free:
+	while (--i >= 0) {
+		struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
+
+		list_del(&rsp->free_list);
+		nvmet_rdma_free_rsp(ndev, rsp);
+	}
+	kfree(queue->rsps);
+out:
+	return ret;
+}
+
+static void nvmet_rdma_free_rsps(struct nvmet_rdma_queue *queue)
+{
+	struct nvmet_rdma_device *ndev = queue->dev;
+	int i, nr_rsps = queue->recv_queue_size * 2;
+
+	for (i = 0; i < nr_rsps; i++) {
+		struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
+
+		list_del(&rsp->free_list);
+		nvmet_rdma_free_rsp(ndev, rsp);
+	}
+	kfree(queue->rsps);
+}
+
+static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
+		struct nvmet_rdma_cmd *cmd)
+{
+	struct ib_recv_wr *bad_wr;
+
+	if (ndev->srq)
+		return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
+	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
+}
+
+static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
+{
+	spin_lock(&queue->rsp_wr_wait_lock);
+	while (!list_empty(&queue->rsp_wr_wait_list)) {
+		struct nvmet_rdma_rsp *rsp;
+		bool ret;
+
+		rsp = list_entry(queue->rsp_wr_wait_list.next,
+				struct nvmet_rdma_rsp, wait_list);
+		list_del(&rsp->wait_list);
+
+		spin_unlock(&queue->rsp_wr_wait_lock);
+		ret = nvmet_rdma_execute_command(rsp);
+		spin_lock(&queue->rsp_wr_wait_lock);
+
+		if (!ret) {
+			list_add(&rsp->wait_list, &queue->rsp_wr_wait_list);
+			break;
+		}
+	}
+	spin_unlock(&queue->rsp_wr_wait_lock);
+}
+
+
+static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
+{
+	struct nvmet_rdma_queue *queue = rsp->queue;
+
+	atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail);
+
+	if (rsp->n_rdma) {
+		rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp,
+				queue->cm_id->port_num, rsp->req.sg,
+				rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
+	}
+
+	if (rsp->req.sg != &rsp->cmd->inline_sg)
+		nvmet_rdma_free_sgl(rsp->req.sg, rsp->req.sg_cnt);
+
+	if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
+		nvmet_rdma_process_wr_wait_list(queue);
+
+	nvmet_rdma_put_rsp(rsp);
+}
+
+static void nvmet_rdma_error_comp(struct nvmet_rdma_queue *queue)
+{
+	if (queue->nvme_sq.ctrl) {
+		nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl);
+	} else {
+		/*
+		 * we didn't setup the controller yet in case
+		 * of admin connect error, just disconnect and
+		 * cleanup the queue
+		 */
+		nvmet_rdma_queue_disconnect(queue);
+	}
+}
+
+static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct nvmet_rdma_rsp *rsp =
+		container_of(wc->wr_cqe, struct nvmet_rdma_rsp, send_cqe);
+
+	nvmet_rdma_release_rsp(rsp);
+
+	if (unlikely(wc->status != IB_WC_SUCCESS &&
+		     wc->status != IB_WC_WR_FLUSH_ERR)) {
+		pr_err("SEND for CQE 0x%p failed with status %s (%d).\n",
+			wc->wr_cqe, ib_wc_status_msg(wc->status), wc->status);
+		nvmet_rdma_error_comp(rsp->queue);
+	}
+}
+
+static void nvmet_rdma_queue_response(struct nvmet_req *req)
+{
+	struct nvmet_rdma_rsp *rsp =
+		container_of(req, struct nvmet_rdma_rsp, req);
+	struct rdma_cm_id *cm_id = rsp->queue->cm_id;
+	struct ib_send_wr *first_wr, *bad_wr;
+
+	if (rsp->flags & NVMET_RDMA_REQ_INVALIDATE_RKEY) {
+		rsp->send_wr.opcode = IB_WR_SEND_WITH_INV;
+		rsp->send_wr.ex.invalidate_rkey = rsp->invalidate_rkey;
+	} else {
+		rsp->send_wr.opcode = IB_WR_SEND;
+	}
+
+	if (nvmet_rdma_need_data_out(rsp))
+		first_wr = rdma_rw_ctx_wrs(&rsp->rw, cm_id->qp,
+				cm_id->port_num, NULL, &rsp->send_wr);
+	else
+		first_wr = &rsp->send_wr;
+
+	nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd);
+	if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
+		pr_err("sending cmd response failed\n");
+		nvmet_rdma_release_rsp(rsp);
+	}
+}
+
+static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct nvmet_rdma_rsp *rsp =
+		container_of(wc->wr_cqe, struct nvmet_rdma_rsp, read_cqe);
+	struct nvmet_rdma_queue *queue = cq->cq_context;
+
+	WARN_ON(rsp->n_rdma <= 0);
+	atomic_add(rsp->n_rdma, &queue->sq_wr_avail);
+	rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp,
+			queue->cm_id->port_num, rsp->req.sg,
+			rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
+	rsp->n_rdma = 0;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		nvmet_rdma_release_rsp(rsp);
+		if (wc->status != IB_WC_WR_FLUSH_ERR) {
+			pr_info("RDMA READ for CQE 0x%p failed with status %s (%d).\n",
+				wc->wr_cqe, ib_wc_status_msg(wc->status), wc->status);
+			nvmet_rdma_error_comp(queue);
+		}
+		return;
+	}
+
+	rsp->req.execute(&rsp->req);
+}
+
+static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
+		u64 off)
+{
+	sg_init_table(&rsp->cmd->inline_sg, 1);
+	sg_set_page(&rsp->cmd->inline_sg, rsp->cmd->inline_page, len, off);
+	rsp->req.sg = &rsp->cmd->inline_sg;
+	rsp->req.sg_cnt = 1;
+}
+
+static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
+{
+	struct nvme_sgl_desc *sgl = &rsp->req.cmd->common.dptr.sgl;
+	u64 off = le64_to_cpu(sgl->addr);
+	u32 len = le32_to_cpu(sgl->length);
+
+	if (!nvme_is_write(rsp->req.cmd))
+		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+
+	if (off + len > NVMET_RDMA_INLINE_DATA_SIZE) {
+		pr_err("invalid inline data offset!\n");
+		return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
+	}
+
+	/* no data command? */
+	if (!len)
+		return 0;
+
+	nvmet_rdma_use_inline_sg(rsp, len, off);
+	rsp->flags |= NVMET_RDMA_REQ_INLINE_DATA;
+	return 0;
+}
+
+static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
+		struct nvme_keyed_sgl_desc *sgl, bool invalidate)
+{
+	struct rdma_cm_id *cm_id = rsp->queue->cm_id;
+	u64 addr = le64_to_cpu(sgl->addr);
+	u32 len = get_unaligned_le24(sgl->length);
+	u32 key = get_unaligned_le32(sgl->key);
+	int ret;
+	u16 status;
+
+	/* no data command? */
+	if (!len)
+		return 0;
+
+	/* use the already allocated data buffer if possible */
+	if (len <= NVMET_RDMA_INLINE_DATA_SIZE && rsp->queue->host_qid) {
+		nvmet_rdma_use_inline_sg(rsp, len, 0);
+	} else {
+		status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
+				len);
+		if (status)
+			return status;
+	}
+
+	ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
+			rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
+			nvmet_data_dir(&rsp->req));
+	if (ret < 0)
+		return NVME_SC_INTERNAL;
+	rsp->n_rdma += ret;
+
+	if (invalidate) {
+		rsp->invalidate_rkey = key;
+		rsp->flags |= NVMET_RDMA_REQ_INVALIDATE_RKEY;
+	}
+
+	return 0;
+}
+
+static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
+{
+	struct nvme_keyed_sgl_desc *sgl = &rsp->req.cmd->common.dptr.ksgl;
+
+	switch (sgl->type >> 4) {
+	case NVME_SGL_FMT_DATA_DESC:
+		switch (sgl->type & 0xf) {
+		case NVME_SGL_FMT_OFFSET:
+			return nvmet_rdma_map_sgl_inline(rsp);
+		default:
+			pr_err("invalid SGL subtype: %#x\n", sgl->type);
+			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		}
+	case NVME_KEY_SGL_FMT_DATA_DESC:
+		switch (sgl->type & 0xf) {
+		case NVME_SGL_FMT_ADDRESS | NVME_SGL_FMT_INVALIDATE:
+			return nvmet_rdma_map_sgl_keyed(rsp, sgl, true);
+		case NVME_SGL_FMT_ADDRESS:
+			return nvmet_rdma_map_sgl_keyed(rsp, sgl, false);
+		default:
+			pr_err("invalid SGL subtype: %#x\n", sgl->type);
+			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		}
+	default:
+		pr_err("invalid SGL type: %#x\n", sgl->type);
+		return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR;
+	}
+}
+
+static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp)
+{
+	struct nvmet_rdma_queue *queue = rsp->queue;
+
+	if (unlikely(atomic_sub_return(1 + rsp->n_rdma,
+			&queue->sq_wr_avail) < 0)) {
+		pr_debug("IB send queue full (needed %d): queue %u cntlid %u\n",
+				1 + rsp->n_rdma, queue->idx,
+				queue->nvme_sq.ctrl->cntlid);
+		atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail);
+		return false;
+	}
+
+	if (nvmet_rdma_need_data_in(rsp)) {
+		if (rdma_rw_ctx_post(&rsp->rw, queue->cm_id->qp,
+				queue->cm_id->port_num, &rsp->read_cqe, NULL))
+			nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR);
+	} else {
+		rsp->req.execute(&rsp->req);
+	}
+
+	return true;
+}
+
+static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
+		struct nvmet_rdma_rsp *cmd)
+{
+	u16 status;
+
+	cmd->queue = queue;
+	cmd->n_rdma = 0;
+	cmd->req.port = queue->port;
+
+	if (!nvmet_req_init(&cmd->req, &queue->nvme_cq,
+			&queue->nvme_sq, &nvmet_rdma_ops))
+		return;
+
+	status = nvmet_rdma_map_sgl(cmd);
+	if (status)
+		goto out_err;
+
+	if (unlikely(!nvmet_rdma_execute_command(cmd))) {
+		spin_lock(&queue->rsp_wr_wait_lock);
+		list_add_tail(&cmd->wait_list, &queue->rsp_wr_wait_list);
+		spin_unlock(&queue->rsp_wr_wait_lock);
+	}
+
+	return;
+
+out_err:
+	nvmet_req_complete(&cmd->req, status);
+}
+
+static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct nvmet_rdma_cmd *cmd =
+		container_of(wc->wr_cqe, struct nvmet_rdma_cmd, cqe);
+	struct nvmet_rdma_queue *queue = cq->cq_context;
+	struct nvmet_rdma_rsp *rsp;
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		if (wc->status != IB_WC_WR_FLUSH_ERR) {
+			pr_err("RECV for CQE 0x%p failed with status %s (%d)\n",
+				wc->wr_cqe, ib_wc_status_msg(wc->status),
+				wc->status);
+			nvmet_rdma_error_comp(queue);
+		}
+		return;
+	}
+
+	if (unlikely(wc->byte_len < sizeof(struct nvme_command))) {
+		pr_err("Ctrl Fatal Error: capsule size less than 64 bytes\n");
+		nvmet_rdma_error_comp(queue);
+		return;
+	}
+
+	cmd->queue = queue;
+	rsp = nvmet_rdma_get_rsp(queue);
+	rsp->cmd = cmd;
+	rsp->flags = 0;
+	rsp->req.cmd = cmd->nvme_cmd;
+
+	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&queue->state_lock, flags);
+		if (queue->state == NVMET_RDMA_Q_CONNECTING)
+			list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
+		else
+			nvmet_rdma_put_rsp(rsp);
+		spin_unlock_irqrestore(&queue->state_lock, flags);
+		return;
+	}
+
+	nvmet_rdma_handle_command(queue, rsp);
+}
+
+static void nvmet_rdma_destroy_srq(struct nvmet_rdma_device *ndev)
+{
+	if (!ndev->srq)
+		return;
+
+	nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
+	ib_destroy_srq(ndev->srq);
+}
+
+static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
+{
+	struct ib_srq_init_attr srq_attr = { NULL, };
+	struct ib_srq *srq;
+	size_t srq_size;
+	int ret, i;
+
+	srq_size = 4095;	/* XXX: tune */
+
+	srq_attr.attr.max_wr = srq_size;
+	srq_attr.attr.max_sge = 2;
+	srq_attr.attr.srq_limit = 0;
+	srq_attr.srq_type = IB_SRQT_BASIC;
+	srq = ib_create_srq(ndev->pd, &srq_attr);
+	if (IS_ERR(srq)) {
+		/*
+		 * If SRQs aren't supported we just go ahead and use normal
+		 * non-shared receive queues.
+		 */
+		pr_info("SRQ requested but not supported.\n");
+		return 0;
+	}
+
+	ndev->srq_cmds = nvmet_rdma_alloc_cmds(ndev, srq_size, false);
+	if (IS_ERR(ndev->srq_cmds)) {
+		ret = PTR_ERR(ndev->srq_cmds);
+		goto out_destroy_srq;
+	}
+
+	ndev->srq = srq;
+	ndev->srq_size = srq_size;
+
+	for (i = 0; i < srq_size; i++)
+		nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+
+	return 0;
+
+out_destroy_srq:
+	ib_destroy_srq(srq);
+	return ret;
+}
+
+static void nvmet_rdma_free_dev(struct kref *ref)
+{
+	struct nvmet_rdma_device *ndev =
+		container_of(ref, struct nvmet_rdma_device, ref);
+
+	mutex_lock(&device_list_mutex);
+	list_del(&ndev->entry);
+	mutex_unlock(&device_list_mutex);
+
+	nvmet_rdma_destroy_srq(ndev);
+	ib_dealloc_pd(ndev->pd);
+
+	kfree(ndev);
+}
+
+static struct nvmet_rdma_device *
+nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
+{
+	struct nvmet_rdma_device *ndev;
+	int ret;
+
+	mutex_lock(&device_list_mutex);
+	list_for_each_entry(ndev, &device_list, entry) {
+		if (ndev->device->node_guid == cm_id->device->node_guid &&
+		    kref_get_unless_zero(&ndev->ref))
+			goto out_unlock;
+	}
+
+	ndev = kzalloc(sizeof(*ndev), GFP_KERNEL);
+	if (!ndev)
+		goto out_err;
+
+	ndev->device = cm_id->device;
+	kref_init(&ndev->ref);
+
+	ndev->pd = ib_alloc_pd(ndev->device);
+	if (IS_ERR(ndev->pd))
+		goto out_free_dev;
+
+	if (nvmet_rdma_use_srq) {
+		ret = nvmet_rdma_init_srq(ndev);
+		if (ret)
+			goto out_free_pd;
+	}
+
+	list_add(&ndev->entry, &device_list);
+out_unlock:
+	mutex_unlock(&device_list_mutex);
+	pr_debug("added %s.\n", ndev->device->name);
+	return ndev;
+
+out_free_pd:
+	ib_dealloc_pd(ndev->pd);
+out_free_dev:
+	kfree(ndev);
+out_err:
+	mutex_unlock(&device_list_mutex);
+	return NULL;
+}
+
+static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
+{
+	struct ib_qp_init_attr qp_attr;
+	struct nvmet_rdma_device *ndev = queue->dev;
+	int comp_vector, nr_cqe, ret, i;
+
+	/*
+	 * Spread the io queues across completion vectors,
+	 * but still keep all admin queues on vector 0.
+	 */
+	comp_vector = !queue->host_qid ? 0 :
+		queue->idx % ndev->device->num_comp_vectors;
+
+	/*
+	 * Reserve CQ slots for RECV + RDMA_READ/RDMA_WRITE + RDMA_SEND.
+	 */
+	nr_cqe = queue->recv_queue_size + 2 * queue->send_queue_size;
+
+	queue->cq = ib_alloc_cq(ndev->device, queue,
+			nr_cqe + 1, comp_vector,
+			IB_POLL_WORKQUEUE);
+	if (IS_ERR(queue->cq)) {
+		ret = PTR_ERR(queue->cq);
+		pr_err("failed to create CQ cqe= %d ret= %d\n",
+		       nr_cqe + 1, ret);
+		goto out;
+	}
+
+	memset(&qp_attr, 0, sizeof(qp_attr));
+	qp_attr.qp_context = queue;
+	qp_attr.event_handler = nvmet_rdma_qp_event;
+	qp_attr.send_cq = queue->cq;
+	qp_attr.recv_cq = queue->cq;
+	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+	qp_attr.qp_type = IB_QPT_RC;
+	/* +1 for drain */
+	qp_attr.cap.max_send_wr = queue->send_queue_size + 1;
+	qp_attr.cap.max_rdma_ctxs = queue->send_queue_size;
+	qp_attr.cap.max_send_sge = max(ndev->device->attrs.max_sge_rd,
+					ndev->device->attrs.max_sge);
+
+	if (ndev->srq) {
+		qp_attr.srq = ndev->srq;
+	} else {
+		/* +1 for drain */
+		qp_attr.cap.max_recv_wr = 1 + queue->recv_queue_size;
+		qp_attr.cap.max_recv_sge = 2;
+	}
+
+	ret = rdma_create_qp(queue->cm_id, ndev->pd, &qp_attr);
+	if (ret) {
+		pr_err("failed to create_qp ret= %d\n", ret);
+		goto err_destroy_cq;
+	}
+
+	atomic_set(&queue->sq_wr_avail, qp_attr.cap.max_send_wr);
+
+	pr_debug("%s: max_cqe= %d max_sge= %d sq_size = %d cm_id= %p\n",
+		 __func__, queue->cq->cqe, qp_attr.cap.max_send_sge,
+		 qp_attr.cap.max_send_wr, queue->cm_id);
+
+	if (!ndev->srq) {
+		for (i = 0; i < queue->recv_queue_size; i++) {
+			queue->cmds[i].queue = queue;
+			nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+		}
+	}
+
+out:
+	return ret;
+
+err_destroy_cq:
+	ib_free_cq(queue->cq);
+	goto out;
+}
+
+static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue)
+{
+	rdma_destroy_qp(queue->cm_id);
+	ib_free_cq(queue->cq);
+}
+
+static void nvmet_rdma_free_queue(struct nvmet_rdma_queue *queue)
+{
+	pr_info("freeing queue %d\n", queue->idx);
+
+	nvmet_sq_destroy(&queue->nvme_sq);
+
+	nvmet_rdma_destroy_queue_ib(queue);
+	if (!queue->dev->srq) {
+		nvmet_rdma_free_cmds(queue->dev, queue->cmds,
+				queue->recv_queue_size,
+				!queue->host_qid);
+	}
+	nvmet_rdma_free_rsps(queue);
+	ida_simple_remove(&nvmet_rdma_queue_ida, queue->idx);
+	kfree(queue);
+}
+
+static void nvmet_rdma_release_queue_work(struct work_struct *w)
+{
+	struct nvmet_rdma_queue *queue =
+		container_of(w, struct nvmet_rdma_queue, release_work);
+	struct rdma_cm_id *cm_id = queue->cm_id;
+	struct nvmet_rdma_device *dev = queue->dev;
+
+	nvmet_rdma_free_queue(queue);
+	rdma_destroy_id(cm_id);
+	kref_put(&dev->ref, nvmet_rdma_free_dev);
+}
+
+static int
+nvmet_rdma_parse_cm_connect_req(struct rdma_conn_param *conn,
+				struct nvmet_rdma_queue *queue)
+{
+	struct nvme_rdma_cm_req *req;
+
+	req = (struct nvme_rdma_cm_req *)conn->private_data;
+	if (!req || conn->private_data_len == 0)
+		return NVME_RDMA_CM_INVALID_LEN;
+
+	if (le16_to_cpu(req->recfmt) != NVME_RDMA_CM_FMT_1_0)
+		return NVME_RDMA_CM_INVALID_RECFMT;
+
+	queue->host_qid = le16_to_cpu(req->qid);
+
+	/*
+	 * req->hsqsize corresponds to our recv queue size
+	 * req->hrqsize corresponds to our send queue size
+	 */
+	queue->recv_queue_size = le16_to_cpu(req->hsqsize);
+	queue->send_queue_size = le16_to_cpu(req->hrqsize);
+
+	if (!queue->host_qid && queue->recv_queue_size > NVMF_AQ_DEPTH)
+		return NVME_RDMA_CM_INVALID_HSQSIZE;
+
+	/* XXX: Should we enforce some kind of max for IO queues? */
+
+	return 0;
+}
+
+static int nvmet_rdma_cm_reject(struct rdma_cm_id *cm_id,
+				enum nvme_rdma_cm_status status)
+{
+	struct nvme_rdma_cm_rej rej;
+
+	rej.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
+	rej.sts = cpu_to_le16(status);
+
+	return rdma_reject(cm_id, (void *)&rej, sizeof(rej));
+}
+
+static struct nvmet_rdma_queue *
+nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
+		struct rdma_cm_id *cm_id,
+		struct rdma_cm_event *event)
+{
+	struct nvmet_rdma_queue *queue;
+	int ret;
+
+	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+	if (!queue) {
+		ret = NVME_RDMA_CM_NO_RSC;
+		goto out_reject;
+	}
+
+	ret = nvmet_sq_init(&queue->nvme_sq);
+	if (ret)
+		goto out_free_queue;
+
+	ret = nvmet_rdma_parse_cm_connect_req(&event->param.conn, queue);
+	if (ret)
+		goto out_destroy_sq;
+
+	/*
+	 * Schedules the actual release because calling rdma_destroy_id from
+	 * inside a CM callback would trigger a deadlock. (great API design..)
+	 */
+	INIT_WORK(&queue->release_work, nvmet_rdma_release_queue_work);
+	queue->dev = ndev;
+	queue->cm_id = cm_id;
+
+	spin_lock_init(&queue->state_lock);
+	queue->state = NVMET_RDMA_Q_CONNECTING;
+	INIT_LIST_HEAD(&queue->rsp_wait_list);
+	INIT_LIST_HEAD(&queue->rsp_wr_wait_list);
+	spin_lock_init(&queue->rsp_wr_wait_lock);
+	INIT_LIST_HEAD(&queue->free_rsps);
+	spin_lock_init(&queue->rsps_lock);
+
+	queue->idx = ida_simple_get(&nvmet_rdma_queue_ida, 0, 0, GFP_KERNEL);
+	if (queue->idx < 0) {
+		ret = NVME_RDMA_CM_NO_RSC;
+		goto out_free_queue;
+	}
+
+	ret = nvmet_rdma_alloc_rsps(queue);
+	if (ret) {
+		ret = NVME_RDMA_CM_NO_RSC;
+		goto out_ida_remove;
+	}
+
+	if (!ndev->srq) {
+		queue->cmds = nvmet_rdma_alloc_cmds(ndev,
+				queue->recv_queue_size,
+				!queue->host_qid);
+		if (IS_ERR(queue->cmds)) {
+			ret = NVME_RDMA_CM_NO_RSC;
+			goto out_free_responses;
+		}
+	}
+
+	ret = nvmet_rdma_create_queue_ib(queue);
+	if (ret) {
+		pr_err("%s: creating RDMA queue failed (%d).\n",
+			__func__, ret);
+		ret = NVME_RDMA_CM_NO_RSC;
+		goto out_free_cmds;
+	}
+
+	return queue;
+
+out_free_cmds:
+	if (!ndev->srq) {
+		nvmet_rdma_free_cmds(queue->dev, queue->cmds,
+				queue->recv_queue_size,
+				!queue->host_qid);
+	}
+out_free_responses:
+	nvmet_rdma_free_rsps(queue);
+out_ida_remove:
+	ida_simple_remove(&nvmet_rdma_queue_ida, queue->idx);
+out_destroy_sq:
+	nvmet_sq_destroy(&queue->nvme_sq);
+out_free_queue:
+	kfree(queue);
+out_reject:
+	nvmet_rdma_cm_reject(cm_id, ret);
+	return NULL;
+}
+
+static void nvmet_rdma_qp_event(struct ib_event *event, void *priv)
+{
+	struct nvmet_rdma_queue *queue = priv;
+
+	switch (event->event) {
+	case IB_EVENT_COMM_EST:
+		rdma_notify(queue->cm_id, event->event);
+		break;
+	default:
+		pr_err("received unrecognized IB QP event %d\n", event->event);
+		break;
+	}
+}
+
+static int nvmet_rdma_cm_accept(struct rdma_cm_id *cm_id,
+		struct nvmet_rdma_queue *queue,
+		struct rdma_conn_param *p)
+{
+	struct rdma_conn_param  param = { };
+	struct nvme_rdma_cm_rep priv = { };
+	int ret = -ENOMEM;
+
+	param.rnr_retry_count = 7;
+	param.flow_control = 1;
+	param.initiator_depth = min_t(u8, p->initiator_depth,
+		queue->dev->device->attrs.max_qp_init_rd_atom);
+	param.private_data = &priv;
+	param.private_data_len = sizeof(priv);
+	priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
+	priv.crqsize = cpu_to_le16(queue->recv_queue_size);
+
+	ret = rdma_accept(cm_id, &param);
+	if (ret)
+		pr_err("rdma_accept failed (error code = %d)\n", ret);
+
+	return ret;
+}
+
+static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
+		struct rdma_cm_event *event)
+{
+	struct nvmet_rdma_device *ndev;
+	struct nvmet_rdma_queue *queue;
+	int ret = -EINVAL;
+
+	ndev = nvmet_rdma_find_get_device(cm_id);
+	if (!ndev) {
+		pr_err("no client data!\n");
+		nvmet_rdma_cm_reject(cm_id, NVME_RDMA_CM_NO_RSC);
+		return -ECONNREFUSED;
+	}
+
+	queue = nvmet_rdma_alloc_queue(ndev, cm_id, event);
+	if (!queue) {
+		ret = -ENOMEM;
+		goto put_device;
+	}
+	queue->port = cm_id->context;
+
+	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
+	if (ret)
+		goto release_queue;
+
+	mutex_lock(&nvmet_rdma_queue_mutex);
+	list_add_tail(&queue->queue_list, &nvmet_rdma_queue_list);
+	mutex_unlock(&nvmet_rdma_queue_mutex);
+
+	return 0;
+
+release_queue:
+	nvmet_rdma_free_queue(queue);
+put_device:
+	kref_put(&ndev->ref, nvmet_rdma_free_dev);
+
+	return ret;
+}
+
+static void nvmet_rdma_queue_established(struct nvmet_rdma_queue *queue)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&queue->state_lock, flags);
+	if (queue->state != NVMET_RDMA_Q_CONNECTING) {
+		pr_warn("trying to establish a connected queue\n");
+		goto out_unlock;
+	}
+	queue->state = NVMET_RDMA_Q_LIVE;
+
+	while (!list_empty(&queue->rsp_wait_list)) {
+		struct nvmet_rdma_rsp *cmd;
+
+		cmd = list_first_entry(&queue->rsp_wait_list,
+					struct nvmet_rdma_rsp, wait_list);
+		list_del(&cmd->wait_list);
+
+		spin_unlock_irqrestore(&queue->state_lock, flags);
+		nvmet_rdma_handle_command(queue, cmd);
+		spin_lock_irqsave(&queue->state_lock, flags);
+	}
+
+out_unlock:
+	spin_unlock_irqrestore(&queue->state_lock, flags);
+}
+
+static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
+{
+	bool disconnect = false;
+	unsigned long flags;
+
+	pr_debug("cm_id= %p queue->state= %d\n", queue->cm_id, queue->state);
+
+	spin_lock_irqsave(&queue->state_lock, flags);
+	switch (queue->state) {
+	case NVMET_RDMA_Q_CONNECTING:
+	case NVMET_RDMA_Q_LIVE:
+		disconnect = true;
+		queue->state = NVMET_RDMA_Q_DISCONNECTING;
+		break;
+	case NVMET_RDMA_Q_DISCONNECTING:
+		break;
+	}
+	spin_unlock_irqrestore(&queue->state_lock, flags);
+
+	if (disconnect) {
+		rdma_disconnect(queue->cm_id);
+		ib_drain_qp(queue->cm_id->qp);
+		schedule_work(&queue->release_work);
+	}
+}
+
+static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
+{
+	bool disconnect = false;
+
+	mutex_lock(&nvmet_rdma_queue_mutex);
+	if (!list_empty(&queue->queue_list)) {
+		list_del_init(&queue->queue_list);
+		disconnect = true;
+	}
+	mutex_unlock(&nvmet_rdma_queue_mutex);
+
+	if (disconnect)
+		__nvmet_rdma_queue_disconnect(queue);
+}
+
+static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
+		struct nvmet_rdma_queue *queue)
+{
+	WARN_ON_ONCE(queue->state != NVMET_RDMA_Q_CONNECTING);
+
+	pr_err("failed to connect queue\n");
+	schedule_work(&queue->release_work);
+}
+
+static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
+		struct rdma_cm_event *event)
+{
+	struct nvmet_rdma_queue *queue = NULL;
+	int ret = 0;
+
+	if (cm_id->qp)
+		queue = cm_id->qp->qp_context;
+
+	pr_debug("%s (%d): status %d id %p\n",
+		rdma_event_msg(event->event), event->event,
+		event->status, cm_id);
+
+	switch (event->event) {
+	case RDMA_CM_EVENT_CONNECT_REQUEST:
+		ret = nvmet_rdma_queue_connect(cm_id, event);
+		break;
+	case RDMA_CM_EVENT_ESTABLISHED:
+		nvmet_rdma_queue_established(queue);
+		break;
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_DISCONNECTED:
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
+		/*
+		 * We can get the device removal callback even for a
+		 * CM ID that we aren't actually using.  In that case
+		 * the context pointer is NULL, so we shouldn't try
+		 * to disconnect a non-existing queue.  But we also
+		 * need to return 1 so that the core will destroy
+		 * it's own ID.  What a great API design..
+		 */
+		if (queue)
+			nvmet_rdma_queue_disconnect(queue);
+		else
+			ret = 1;
+		break;
+	case RDMA_CM_EVENT_REJECTED:
+	case RDMA_CM_EVENT_UNREACHABLE:
+	case RDMA_CM_EVENT_CONNECT_ERROR:
+		nvmet_rdma_queue_connect_fail(cm_id, queue);
+		break;
+	default:
+		pr_err("received unrecognized RDMA CM event %d\n",
+			event->event);
+		break;
+	}
+
+	return ret;
+}
+
+static void nvmet_rdma_delete_ctrl(struct nvmet_ctrl *ctrl)
+{
+	struct nvmet_rdma_queue *queue;
+
+restart:
+	mutex_lock(&nvmet_rdma_queue_mutex);
+	list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) {
+		if (queue->nvme_sq.ctrl == ctrl) {
+			list_del_init(&queue->queue_list);
+			mutex_unlock(&nvmet_rdma_queue_mutex);
+
+			__nvmet_rdma_queue_disconnect(queue);
+			goto restart;
+		}
+	}
+	mutex_unlock(&nvmet_rdma_queue_mutex);
+}
+
+static int nvmet_rdma_add_port(struct nvmet_port *port)
+{
+	struct rdma_cm_id *cm_id;
+	struct sockaddr_in addr_in;
+	u16 port_in;
+	int ret;
+
+	switch (port->disc_addr.adrfam) {
+	case NVMF_ADDR_FAMILY_IP4:
+		break;
+	default:
+		pr_err("address family %d not supported\n",
+				port->disc_addr.adrfam);
+		return -EINVAL;
+	}
+
+	ret = kstrtou16(port->disc_addr.trsvcid, 0, &port_in);
+	if (ret)
+		return ret;
+
+	addr_in.sin_family = AF_INET;
+	addr_in.sin_addr.s_addr = in_aton(port->disc_addr.traddr);
+	addr_in.sin_port = htons(port_in);
+
+	cm_id = rdma_create_id(&init_net, nvmet_rdma_cm_handler, port,
+			RDMA_PS_TCP, IB_QPT_RC);
+	if (IS_ERR(cm_id)) {
+		pr_err("CM ID creation failed\n");
+		return PTR_ERR(cm_id);
+	}
+
+	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr_in);
+	if (ret) {
+		pr_err("binding CM ID to %pISpc failed (%d)\n", &addr_in, ret);
+		goto out_destroy_id;
+	}
+
+	ret = rdma_listen(cm_id, 128);
+	if (ret) {
+		pr_err("listening to %pISpc failed (%d)\n", &addr_in, ret);
+		goto out_destroy_id;
+	}
+
+	pr_info("enabling port %d (%pISpc)\n",
+		le16_to_cpu(port->disc_addr.portid), &addr_in);
+	port->priv = cm_id;
+	return 0;
+
+out_destroy_id:
+	rdma_destroy_id(cm_id);
+	return ret;
+}
+
+static void nvmet_rdma_remove_port(struct nvmet_port *port)
+{
+	struct rdma_cm_id *cm_id = port->priv;
+
+	rdma_destroy_id(cm_id);
+}
+
+static struct nvmet_fabrics_ops nvmet_rdma_ops = {
+	.owner			= THIS_MODULE,
+	.type			= NVMF_TRTYPE_RDMA,
+	.sqe_inline_size	= NVMET_RDMA_INLINE_DATA_SIZE,
+	.msdbd			= 1,
+	.has_keyed_sgls		= 1,
+	.add_port		= nvmet_rdma_add_port,
+	.remove_port		= nvmet_rdma_remove_port,
+	.queue_response		= nvmet_rdma_queue_response,
+	.delete_ctrl		= nvmet_rdma_delete_ctrl,
+};
+
+static int __init nvmet_rdma_init(void)
+{
+	return nvmet_register_transport(&nvmet_rdma_ops);
+}
+
+static void __exit nvmet_rdma_exit(void)
+{
+	struct nvmet_rdma_queue *queue;
+
+	nvmet_unregister_transport(&nvmet_rdma_ops);
+
+	flush_scheduled_work();
+
+	mutex_lock(&nvmet_rdma_queue_mutex);
+	while ((queue = list_first_entry_or_null(&nvmet_rdma_queue_list,
+			struct nvmet_rdma_queue, queue_list))) {
+		list_del_init(&queue->queue_list);
+
+		mutex_unlock(&nvmet_rdma_queue_mutex);
+		__nvmet_rdma_queue_disconnect(queue);
+		mutex_lock(&nvmet_rdma_queue_mutex);
+	}
+	mutex_unlock(&nvmet_rdma_queue_mutex);
+
+	flush_scheduled_work();
+	ida_destroy(&nvmet_rdma_queue_ida);
+}
+
+module_init(nvmet_rdma_init);
+module_exit(nvmet_rdma_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("nvmet-transport-1"); /* 1 == NVMF_TRTYPE_RDMA */
diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c
index 0f2784bc1874..ed5a097f0801 100644
--- a/drivers/of/of_numa.c
+++ b/drivers/of/of_numa.c
@@ -91,8 +91,8 @@ static int __init of_numa_parse_memory_nodes(void)
 		pr_debug("NUMA:  base = %llx len = %llx, node = %u\n",
 			 rsrc.start, rsrc.end - rsrc.start + 1, nid);
 
-		r = numa_add_memblk(nid, rsrc.start,
-				    rsrc.end - rsrc.start + 1);
+
+		r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
 		if (r)
 			break;
 	}
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 216648233874..06af99f64ad8 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -21,6 +21,7 @@
 #include <linux/sizes.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/sort.h>
+#include <linux/slab.h>
 
 #define MAX_RESERVED_REGIONS	16
 static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
@@ -296,53 +297,95 @@ static inline struct reserved_mem *__find_rmem(struct device_node *node)
 	return NULL;
 }
 
+struct rmem_assigned_device {
+	struct device *dev;
+	struct reserved_mem *rmem;
+	struct list_head list;
+};
+
+static LIST_HEAD(of_rmem_assigned_device_list);
+static DEFINE_MUTEX(of_rmem_assigned_device_mutex);
+
 /**
- * of_reserved_mem_device_init() - assign reserved memory region to given device
+ * of_reserved_mem_device_init_by_idx() - assign reserved memory region to
+ *					  given device
+ * @dev:	Pointer to the device to configure
+ * @np:		Pointer to the device_node with 'reserved-memory' property
+ * @idx:	Index of selected region
  *
- * This function assign memory region pointed by "memory-region" device tree
- * property to the given device.
+ * This function assigns respective DMA-mapping operations based on reserved
+ * memory region specified by 'memory-region' property in @np node to the @dev
+ * device. When driver needs to use more than one reserved memory region, it
+ * should allocate child devices and initialize regions by name for each of
+ * child device.
+ *
+ * Returns error code or zero on success.
  */
-int of_reserved_mem_device_init(struct device *dev)
+int of_reserved_mem_device_init_by_idx(struct device *dev,
+				       struct device_node *np, int idx)
 {
+	struct rmem_assigned_device *rd;
+	struct device_node *target;
 	struct reserved_mem *rmem;
-	struct device_node *np;
 	int ret;
 
-	np = of_parse_phandle(dev->of_node, "memory-region", 0);
-	if (!np)
+	if (!np || !dev)
+		return -EINVAL;
+
+	target = of_parse_phandle(np, "memory-region", idx);
+	if (!target)
 		return -ENODEV;
 
-	rmem = __find_rmem(np);
-	of_node_put(np);
+	rmem = __find_rmem(target);
+	of_node_put(target);
 
 	if (!rmem || !rmem->ops || !rmem->ops->device_init)
 		return -EINVAL;
 
+	rd = kmalloc(sizeof(struct rmem_assigned_device), GFP_KERNEL);
+	if (!rd)
+		return -ENOMEM;
+
 	ret = rmem->ops->device_init(rmem, dev);
-	if (ret == 0)
+	if (ret == 0) {
+		rd->dev = dev;
+		rd->rmem = rmem;
+
+		mutex_lock(&of_rmem_assigned_device_mutex);
+		list_add(&rd->list, &of_rmem_assigned_device_list);
+		mutex_unlock(&of_rmem_assigned_device_mutex);
+
 		dev_info(dev, "assigned reserved memory node %s\n", rmem->name);
+	} else {
+		kfree(rd);
+	}
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(of_reserved_mem_device_init);
+EXPORT_SYMBOL_GPL(of_reserved_mem_device_init_by_idx);
 
 /**
  * of_reserved_mem_device_release() - release reserved memory device structures
+ * @dev:	Pointer to the device to deconfigure
  *
  * This function releases structures allocated for memory region handling for
  * the given device.
  */
 void of_reserved_mem_device_release(struct device *dev)
 {
-	struct reserved_mem *rmem;
-	struct device_node *np;
-
-	np = of_parse_phandle(dev->of_node, "memory-region", 0);
-	if (!np)
-		return;
-
-	rmem = __find_rmem(np);
-	of_node_put(np);
+	struct rmem_assigned_device *rd;
+	struct reserved_mem *rmem = NULL;
+
+	mutex_lock(&of_rmem_assigned_device_mutex);
+	list_for_each_entry(rd, &of_rmem_assigned_device_list, list) {
+		if (rd->dev == dev) {
+			rmem = rd->rmem;
+			list_del(&rd->list);
+			kfree(rd);
+			break;
+		}
+	}
+	mutex_unlock(&of_rmem_assigned_device_mutex);
 
 	if (!rmem || !rmem->ops || !rmem->ops->device_release)
 		return;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index c8b4dbdd1bdd..badbddc683f0 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -530,8 +530,8 @@ static const struct pci_platform_pm_ops *pci_platform_pm;
 
 int pci_set_platform_pm(const struct pci_platform_pm_ops *ops)
 {
-	if (!ops->is_manageable || !ops->set_state || !ops->choose_state
-	    || !ops->sleep_wake)
+	if (!ops->is_manageable || !ops->set_state || !ops->choose_state ||
+	    !ops->sleep_wake || !ops->run_wake || !ops->need_resume)
 		return -EINVAL;
 	pci_platform_pm = ops;
 	return 0;
diff --git a/drivers/phy/phy-brcm-sata.c b/drivers/phy/phy-brcm-sata.c
index 6c4c5cb791ca..18d662610075 100644
--- a/drivers/phy/phy-brcm-sata.c
+++ b/drivers/phy/phy-brcm-sata.c
@@ -45,6 +45,7 @@ enum brcm_sata_phy_version {
 	BRCM_SATA_PHY_STB_28NM,
 	BRCM_SATA_PHY_STB_40NM,
 	BRCM_SATA_PHY_IPROC_NS2,
+	BRCM_SATA_PHY_IPROC_NSP,
 };
 
 struct brcm_sata_port {
@@ -73,6 +74,13 @@ enum sata_phy_regs {
 
 	PLL_REG_BANK_0				= 0x050,
 	PLL_REG_BANK_0_PLLCONTROL_0		= 0x81,
+	PLLCONTROL_0_FREQ_DET_RESTART		= BIT(13),
+	PLLCONTROL_0_FREQ_MONITOR		= BIT(12),
+	PLLCONTROL_0_SEQ_START			= BIT(15),
+	PLL_CAP_CONTROL				= 0x85,
+	PLL_ACTRL2				= 0x8b,
+	PLL_ACTRL2_SELDIV_MASK			= 0x1f,
+	PLL_ACTRL2_SELDIV_SHIFT			= 9,
 
 	PLL1_REG_BANK				= 0x060,
 	PLL1_ACTRL2				= 0x82,
@@ -80,6 +88,7 @@ enum sata_phy_regs {
 	PLL1_ACTRL4				= 0x84,
 
 	OOB_REG_BANK				= 0x150,
+	OOB1_REG_BANK				= 0x160,
 	OOB_CTRL1				= 0x80,
 	OOB_CTRL1_BURST_MAX_MASK		= 0xf,
 	OOB_CTRL1_BURST_MAX_SHIFT		= 12,
@@ -271,6 +280,73 @@ static int brcm_ns2_sata_init(struct brcm_sata_port *port)
 	return 0;
 }
 
+static int brcm_nsp_sata_init(struct brcm_sata_port *port)
+{
+	struct brcm_sata_phy *priv = port->phy_priv;
+	struct device *dev = port->phy_priv->dev;
+	void __iomem *base = priv->phy_base;
+	unsigned int oob_bank;
+	unsigned int val, try;
+
+	/* Configure OOB control */
+	if (port->portnum == 0)
+		oob_bank = OOB_REG_BANK;
+	else if (port->portnum == 1)
+		oob_bank = OOB1_REG_BANK;
+	else
+		return -EINVAL;
+
+	val = 0x0;
+	val |= (0x0f << OOB_CTRL1_BURST_MAX_SHIFT);
+	val |= (0x06 << OOB_CTRL1_BURST_MIN_SHIFT);
+	val |= (0x0f << OOB_CTRL1_WAKE_IDLE_MAX_SHIFT);
+	val |= (0x06 << OOB_CTRL1_WAKE_IDLE_MIN_SHIFT);
+	brcm_sata_phy_wr(base, oob_bank, OOB_CTRL1, 0x0, val);
+
+	val = 0x0;
+	val |= (0x2e << OOB_CTRL2_RESET_IDLE_MAX_SHIFT);
+	val |= (0x02 << OOB_CTRL2_BURST_CNT_SHIFT);
+	val |= (0x16 << OOB_CTRL2_RESET_IDLE_MIN_SHIFT);
+	brcm_sata_phy_wr(base, oob_bank, OOB_CTRL2, 0x0, val);
+
+
+	brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_ACTRL2,
+		~(PLL_ACTRL2_SELDIV_MASK << PLL_ACTRL2_SELDIV_SHIFT),
+		0x0c << PLL_ACTRL2_SELDIV_SHIFT);
+
+	brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_CAP_CONTROL,
+						0xff0, 0x4f0);
+
+	val = PLLCONTROL_0_FREQ_DET_RESTART | PLLCONTROL_0_FREQ_MONITOR;
+	brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0,
+								~val, val);
+	val = PLLCONTROL_0_SEQ_START;
+	brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0,
+								~val, 0);
+	mdelay(10);
+	brcm_sata_phy_wr(base, PLL_REG_BANK_0, PLL_REG_BANK_0_PLLCONTROL_0,
+								~val, val);
+
+	/* Wait for pll_seq_done bit */
+	try = 50;
+	while (try--) {
+		val = brcm_sata_phy_rd(base, BLOCK0_REG_BANK,
+					BLOCK0_XGXSSTATUS);
+		if (val & BLOCK0_XGXSSTATUS_PLL_LOCK)
+			break;
+		msleep(20);
+	}
+	if (!try) {
+		/* PLL did not lock; give up */
+		dev_err(dev, "port%d PLL did not lock\n", port->portnum);
+		return -ETIMEDOUT;
+	}
+
+	dev_dbg(dev, "port%d initialized\n", port->portnum);
+
+	return 0;
+}
+
 static int brcm_sata_phy_init(struct phy *phy)
 {
 	int rc;
@@ -284,6 +360,9 @@ static int brcm_sata_phy_init(struct phy *phy)
 	case BRCM_SATA_PHY_IPROC_NS2:
 		rc = brcm_ns2_sata_init(port);
 		break;
+	case BRCM_SATA_PHY_IPROC_NSP:
+		rc = brcm_nsp_sata_init(port);
+		break;
 	default:
 		rc = -ENODEV;
 	};
@@ -303,6 +382,8 @@ static const struct of_device_id brcm_sata_phy_of_match[] = {
 	  .data = (void *)BRCM_SATA_PHY_STB_40NM },
 	{ .compatible	= "brcm,iproc-ns2-sata-phy",
 	  .data = (void *)BRCM_SATA_PHY_IPROC_NS2 },
+	{ .compatible = "brcm,iproc-nsp-sata-phy",
+	  .data = (void *)BRCM_SATA_PHY_IPROC_NSP },
 	{},
 };
 MODULE_DEVICE_TABLE(of, brcm_sata_phy_of_match);
diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c
index a13f2b6f6fc0..b9375544dff0 100644
--- a/drivers/pinctrl/pinctrl-xway.c
+++ b/drivers/pinctrl/pinctrl-xway.c
@@ -1724,9 +1724,9 @@ static int pinmux_xway_probe(struct platform_device *pdev)
 	}
 	xway_pctrl_desc.pins = xway_info.pads;
 
-	/* load the gpio chip */
+	/* register the gpio chip */
 	xway_chip.parent = &pdev->dev;
-	ret = gpiochip_add(&xway_chip);
+	ret = devm_gpiochip_add_data(&pdev->dev, &xway_chip, NULL);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to register gpio chip\n");
 		return ret;
@@ -1749,7 +1749,6 @@ static int pinmux_xway_probe(struct platform_device *pdev)
 	/* register with the generic lantiq layer */
 	ret = ltq_pinctrl_register(pdev, &xway_info);
 	if (ret) {
-		gpiochip_remove(&xway_chip);
 		dev_err(&pdev->dev, "Failed to register pinctrl driver\n");
 		return ret;
 	}
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 3ec0025d19e7..81b8dcca8891 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -603,6 +603,8 @@ config ASUS_WIRELESS
 	tristate "Asus Wireless Radio Control Driver"
 	depends on ACPI
 	depends on INPUT
+	select NEW_LEDS
+	select LEDS_CLASS
 	---help---
 	  The Asus Wireless Radio Control handles the airplane mode hotkey
 	  present on some Asus laptops.
@@ -668,6 +670,7 @@ config ACPI_TOSHIBA
 	depends on SERIO_I8042 || SERIO_I8042 = n
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
 	depends on RFKILL || RFKILL = n
+	depends on IIO
 	select INPUT_POLLDEV
 	select INPUT_SPARSEKMAP
 	---help---
@@ -770,6 +773,18 @@ config INTEL_HID_EVENT
 	  To compile this driver as a module, choose M here: the module will
 	  be called intel_hid.
 
+config INTEL_VBTN
+	tristate "INTEL VIRTUAL BUTTON"
+	depends on ACPI
+	depends on INPUT
+	select INPUT_SPARSEKMAP
+	help
+	  This driver provides support for the Intel Virtual Button interface.
+	  Some laptops require this driver for power button support.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called intel_vbtn.
+
 config INTEL_SCU_IPC
 	bool "Intel SCU IPC Support"
 	depends on X86_INTEL_MID
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 9b11b4073e03..2efa86d2a1a7 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_TOSHIBA_BT_RFKILL)	+= toshiba_bluetooth.o
 obj-$(CONFIG_TOSHIBA_HAPS)	+= toshiba_haps.o
 obj-$(CONFIG_TOSHIBA_WMI)	+= toshiba-wmi.o
 obj-$(CONFIG_INTEL_HID_EVENT)	+= intel-hid.o
+obj-$(CONFIG_INTEL_VBTN)	+= intel-vbtn.o
 obj-$(CONFIG_INTEL_SCU_IPC)	+= intel_scu_ipc.o
 obj-$(CONFIG_INTEL_SCU_IPC_UTIL) += intel_scu_ipcutil.o
 obj-$(CONFIG_INTEL_MFLD_THERMAL) += intel_mid_thermal.o
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 091ca7ada8fc..adecc1c555f0 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -78,6 +78,15 @@ static struct quirk_entry quirk_asus_x200ca = {
 	.wapf = 2,
 };
 
+static struct quirk_entry quirk_no_rfkill = {
+	.no_rfkill = true,
+};
+
+static struct quirk_entry quirk_no_rfkill_wapf4 = {
+	.wapf = 4,
+	.no_rfkill = true,
+};
+
 static int dmi_matched(const struct dmi_system_id *dmi)
 {
 	quirks = dmi->driver_data;
@@ -133,7 +142,7 @@ static const struct dmi_system_id asus_quirks[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "X456UA"),
 		},
-		.driver_data = &quirk_asus_wapf4,
+		.driver_data = &quirk_no_rfkill_wapf4,
 	},
 	{
 		.callback = dmi_matched,
@@ -142,7 +151,7 @@ static const struct dmi_system_id asus_quirks[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "X456UF"),
 		},
-		.driver_data = &quirk_asus_wapf4,
+		.driver_data = &quirk_no_rfkill_wapf4,
 	},
 	{
 		.callback = dmi_matched,
@@ -306,6 +315,42 @@ static const struct dmi_system_id asus_quirks[] = {
 		},
 		.driver_data = &quirk_asus_x200ca,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. X555UB",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X555UB"),
+		},
+		.driver_data = &quirk_no_rfkill,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. N552VW",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "N552VW"),
+		},
+		.driver_data = &quirk_no_rfkill,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. U303LB",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "U303LB"),
+		},
+		.driver_data = &quirk_no_rfkill,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. Z550MA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Z550MA"),
+		},
+		.driver_data = &quirk_no_rfkill,
+	},
 	{},
 };
 
@@ -356,6 +401,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
 	{ KE_KEY, 0x67, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + CRT + TV */
 	{ KE_KEY, 0x6B, { KEY_TOUCHPAD_TOGGLE } },
 	{ KE_IGNORE, 0x6E, },  /* Low Battery notification */
+	{ KE_KEY, 0x7a, { KEY_ALS_TOGGLE } }, /* Ambient Light Sensor Toggle */
 	{ KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */
 	{ KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */
 	{ KE_KEY, 0x82, { KEY_CAMERA } },
diff --git a/drivers/platform/x86/asus-wireless.c b/drivers/platform/x86/asus-wireless.c
index 9ec721e26532..9f31bc1a47d0 100644
--- a/drivers/platform/x86/asus-wireless.c
+++ b/drivers/platform/x86/asus-wireless.c
@@ -15,11 +15,78 @@
 #include <linux/acpi.h>
 #include <linux/input.h>
 #include <linux/pci_ids.h>
+#include <linux/leds.h>
+
+#define ASUS_WIRELESS_LED_STATUS 0x2
+#define ASUS_WIRELESS_LED_OFF 0x4
+#define ASUS_WIRELESS_LED_ON 0x5
 
 struct asus_wireless_data {
 	struct input_dev *idev;
+	struct acpi_device *adev;
+	struct workqueue_struct *wq;
+	struct work_struct led_work;
+	struct led_classdev led;
+	int led_state;
 };
 
+static u64 asus_wireless_method(acpi_handle handle, const char *method,
+				int param)
+{
+	struct acpi_object_list p;
+	union acpi_object obj;
+	acpi_status s;
+	u64 ret;
+
+	acpi_handle_debug(handle, "Evaluating method %s, parameter %#x\n",
+			  method, param);
+	obj.type = ACPI_TYPE_INTEGER;
+	obj.integer.value = param;
+	p.count = 1;
+	p.pointer = &obj;
+
+	s = acpi_evaluate_integer(handle, (acpi_string) method, &p, &ret);
+	if (ACPI_FAILURE(s))
+		acpi_handle_err(handle,
+				"Failed to eval method %s, param %#x (%d)\n",
+				method, param, s);
+	acpi_handle_debug(handle, "%s returned %#x\n", method, (uint) ret);
+	return ret;
+}
+
+static enum led_brightness led_state_get(struct led_classdev *led)
+{
+	struct asus_wireless_data *data;
+	int s;
+
+	data = container_of(led, struct asus_wireless_data, led);
+	s = asus_wireless_method(acpi_device_handle(data->adev), "HSWC",
+				 ASUS_WIRELESS_LED_STATUS);
+	if (s == ASUS_WIRELESS_LED_ON)
+		return LED_FULL;
+	return LED_OFF;
+}
+
+static void led_state_update(struct work_struct *work)
+{
+	struct asus_wireless_data *data;
+
+	data = container_of(work, struct asus_wireless_data, led_work);
+	asus_wireless_method(acpi_device_handle(data->adev), "HSWC",
+			     data->led_state);
+}
+
+static void led_state_set(struct led_classdev *led,
+				  enum led_brightness value)
+{
+	struct asus_wireless_data *data;
+
+	data = container_of(led, struct asus_wireless_data, led);
+	data->led_state = value == LED_OFF ? ASUS_WIRELESS_LED_OFF :
+					     ASUS_WIRELESS_LED_ON;
+	queue_work(data->wq, &data->led_work);
+}
+
 static void asus_wireless_notify(struct acpi_device *adev, u32 event)
 {
 	struct asus_wireless_data *data = acpi_driver_data(adev);
@@ -37,6 +104,7 @@ static void asus_wireless_notify(struct acpi_device *adev, u32 event)
 static int asus_wireless_add(struct acpi_device *adev)
 {
 	struct asus_wireless_data *data;
+	int err;
 
 	data = devm_kzalloc(&adev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -52,11 +120,32 @@ static int asus_wireless_add(struct acpi_device *adev)
 	data->idev->id.vendor = PCI_VENDOR_ID_ASUSTEK;
 	set_bit(EV_KEY, data->idev->evbit);
 	set_bit(KEY_RFKILL, data->idev->keybit);
-	return input_register_device(data->idev);
+	err = input_register_device(data->idev);
+	if (err)
+		return err;
+
+	data->adev = adev;
+	data->wq = create_singlethread_workqueue("asus_wireless_workqueue");
+	if (!data->wq)
+		return -ENOMEM;
+	INIT_WORK(&data->led_work, led_state_update);
+	data->led.name = "asus-wireless::airplane";
+	data->led.brightness_set = led_state_set;
+	data->led.brightness_get = led_state_get;
+	data->led.flags = LED_CORE_SUSPENDRESUME;
+	data->led.max_brightness = 1;
+	err = devm_led_classdev_register(&adev->dev, &data->led);
+	if (err)
+		destroy_workqueue(data->wq);
+	return err;
 }
 
 static int asus_wireless_remove(struct acpi_device *adev)
 {
+	struct asus_wireless_data *data = acpi_driver_data(adev);
+
+	if (data->wq)
+		destroy_workqueue(data->wq);
 	return 0;
 }
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index a26dca3640ea..7c093a0b78bb 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -2069,9 +2069,11 @@ static int asus_wmi_add(struct platform_device *pdev)
 	if (err)
 		goto fail_leds;
 
-	err = asus_wmi_rfkill_init(asus);
-	if (err)
-		goto fail_rfkill;
+	if (!asus->driver->quirks->no_rfkill) {
+		err = asus_wmi_rfkill_init(asus);
+		if (err)
+			goto fail_rfkill;
+	}
 
 	/* Some Asus desktop boards export an acpi-video backlight interface,
 	   stop this from showing up */
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index 4da4c8bafe70..5de1df510ebd 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -38,6 +38,7 @@ struct key_entry;
 struct asus_wmi;
 
 struct quirk_entry {
+	bool no_rfkill;
 	bool hotplug_wireless;
 	bool scalar_panel_brightness;
 	bool store_backlight_power;
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index 15c6f1191aec..d2bc092defd7 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -80,66 +80,115 @@ static const struct dmi_system_id dell_wmi_smbios_list[] __initconst = {
 };
 
 /*
+ * Keymap for WMI events of type 0x0000
+ *
  * Certain keys are flagged as KE_IGNORE. All of these are either
  * notifications (rather than requests for change) or are also sent
  * via the keyboard controller so should not be sent again.
  */
-
-static const struct key_entry dell_wmi_legacy_keymap[] __initconst = {
+static const struct key_entry dell_wmi_keymap_type_0000[] __initconst = {
 	{ KE_IGNORE, 0x003a, { KEY_CAPSLOCK } },
 
-	{ KE_KEY, 0xe045, { KEY_PROG1 } },
-	{ KE_KEY, 0xe009, { KEY_EJECTCD } },
-
-	/* These also contain the brightness level at offset 6 */
-	{ KE_KEY, 0xe006, { KEY_BRIGHTNESSUP } },
-	{ KE_KEY, 0xe005, { KEY_BRIGHTNESSDOWN } },
+	/* Key code is followed by brightness level */
+	{ KE_KEY,    0xe005, { KEY_BRIGHTNESSDOWN } },
+	{ KE_KEY,    0xe006, { KEY_BRIGHTNESSUP } },
 
 	/* Battery health status button */
-	{ KE_KEY, 0xe007, { KEY_BATTERY } },
+	{ KE_KEY,    0xe007, { KEY_BATTERY } },
 
-	/* Radio devices state change */
+	/* Radio devices state change, key code is followed by other values */
 	{ KE_IGNORE, 0xe008, { KEY_RFKILL } },
 
-	/* The next device is at offset 6, the active devices are at
-	   offset 8 and the attached devices at offset 10 */
-	{ KE_KEY, 0xe00b, { KEY_SWITCHVIDEOMODE } },
+	{ KE_KEY,    0xe009, { KEY_EJECTCD } },
 
+	/* Key code is followed by: next, active and attached devices */
+	{ KE_KEY,    0xe00b, { KEY_SWITCHVIDEOMODE } },
+
+	/* Key code is followed by keyboard illumination level */
 	{ KE_IGNORE, 0xe00c, { KEY_KBDILLUMTOGGLE } },
 
 	/* BIOS error detected */
 	{ KE_IGNORE, 0xe00d, { KEY_RESERVED } },
 
+	/* Unknown, defined in ACPI DSDT */
+	/* { KE_IGNORE, 0xe00e, { KEY_RESERVED } }, */
+
 	/* Wifi Catcher */
-	{ KE_KEY, 0xe011, {KEY_PROG2 } },
+	{ KE_KEY,    0xe011, { KEY_PROG2 } },
 
 	/* Ambient light sensor toggle */
 	{ KE_IGNORE, 0xe013, { KEY_RESERVED } },
 
 	{ KE_IGNORE, 0xe020, { KEY_MUTE } },
 
+	/* Unknown, defined in ACPI DSDT */
+	/* { KE_IGNORE, 0xe023, { KEY_RESERVED } }, */
+
+	/* Untested, Dell Instant Launch key on Inspiron 7520 */
+	/* { KE_IGNORE, 0xe024, { KEY_RESERVED } }, */
+
 	/* Dell Instant Launch key */
-	{ KE_KEY, 0xe025, { KEY_PROG4 } },
-	{ KE_KEY, 0xe029, { KEY_PROG4 } },
+	{ KE_KEY,    0xe025, { KEY_PROG4 } },
 
 	/* Audio panel key */
 	{ KE_IGNORE, 0xe026, { KEY_RESERVED } },
 
+	/* LCD Display On/Off Control key */
+	{ KE_KEY,    0xe027, { KEY_DISPLAYTOGGLE } },
+
+	/* Untested, Multimedia key on Dell Vostro 3560 */
+	/* { KE_IGNORE, 0xe028, { KEY_RESERVED } }, */
+
+	/* Dell Instant Launch key */
+	{ KE_KEY,    0xe029, { KEY_PROG4 } },
+
+	/* Untested, Windows Mobility Center button on Inspiron 7520 */
+	/* { KE_IGNORE, 0xe02a, { KEY_RESERVED } }, */
+
+	/* Unknown, defined in ACPI DSDT */
+	/* { KE_IGNORE, 0xe02b, { KEY_RESERVED } }, */
+
+	/* Untested, Dell Audio With Preset Switch button on Inspiron 7520 */
+	/* { KE_IGNORE, 0xe02c, { KEY_RESERVED } }, */
+
 	{ KE_IGNORE, 0xe02e, { KEY_VOLUMEDOWN } },
 	{ KE_IGNORE, 0xe030, { KEY_VOLUMEUP } },
 	{ KE_IGNORE, 0xe033, { KEY_KBDILLUMUP } },
 	{ KE_IGNORE, 0xe034, { KEY_KBDILLUMDOWN } },
 	{ KE_IGNORE, 0xe03a, { KEY_CAPSLOCK } },
+
+	/* NIC Link is Up */
+	{ KE_IGNORE, 0xe043, { KEY_RESERVED } },
+
+	/* NIC Link is Down */
+	{ KE_IGNORE, 0xe044, { KEY_RESERVED } },
+
+	/*
+	 * This entry is very suspicious!
+	 * Originally Matthew Garrett created this dell-wmi driver specially for
+	 * "button with a picture of a battery" which has event code 0xe045.
+	 * Later Mario Limonciello from Dell told us that event code 0xe045 is
+	 * reported by Num Lock and should be ignored because key is send also
+	 * by keyboard controller.
+	 * So for now we will ignore this event to prevent potential double
+	 * Num Lock key press.
+	 */
 	{ KE_IGNORE, 0xe045, { KEY_NUMLOCK } },
+
+	/* Scroll lock and also going to tablet mode on portable devices */
 	{ KE_IGNORE, 0xe046, { KEY_SCROLLLOCK } },
+
+	/* Untested, going from tablet mode on portable devices */
+	/* { KE_IGNORE, 0xe047, { KEY_RESERVED } }, */
+
+	/* Dell Support Center key */
+	{ KE_IGNORE, 0xe06e, { KEY_RESERVED } },
+
 	{ KE_IGNORE, 0xe0f7, { KEY_MUTE } },
 	{ KE_IGNORE, 0xe0f8, { KEY_VOLUMEDOWN } },
 	{ KE_IGNORE, 0xe0f9, { KEY_VOLUMEUP } },
-	{ KE_END, 0 }
 };
 
-static bool dell_new_hk_type;
-
 struct dell_bios_keymap_entry {
 	u16 scancode;
 	u16 keycode;
@@ -153,6 +202,7 @@ struct dell_bios_hotkey_table {
 
 struct dell_dmi_results {
 	int err;
+	int keymap_size;
 	struct key_entry *keymap;
 };
 
@@ -201,10 +251,12 @@ static const u16 bios_to_linux_keycode[256] __initconst = {
 };
 
 /*
+ * Keymap for WMI events of type 0x0010
+ *
  * These are applied if the 0xB2 DMI hotkey table is present and doesn't
  * override them.
  */
-static const struct key_entry dell_wmi_extra_keymap[] __initconst = {
+static const struct key_entry dell_wmi_keymap_type_0010[] __initconst = {
 	/* Fn-lock */
 	{ KE_IGNORE, 0x151, { KEY_RESERVED } },
 
@@ -224,21 +276,39 @@ static const struct key_entry dell_wmi_extra_keymap[] __initconst = {
 	{ KE_IGNORE, 0x155, { KEY_RESERVED } },
 };
 
+/*
+ * Keymap for WMI events of type 0x0011
+ */
+static const struct key_entry dell_wmi_keymap_type_0011[] __initconst = {
+	/* Battery unplugged */
+	{ KE_IGNORE, 0xfff0, { KEY_RESERVED } },
+
+	/* Battery inserted */
+	{ KE_IGNORE, 0xfff1, { KEY_RESERVED } },
+
+	/* Keyboard backlight level changed */
+	{ KE_IGNORE, 0x01e1, { KEY_RESERVED } },
+	{ KE_IGNORE, 0x02ea, { KEY_RESERVED } },
+	{ KE_IGNORE, 0x02eb, { KEY_RESERVED } },
+	{ KE_IGNORE, 0x02ec, { KEY_RESERVED } },
+	{ KE_IGNORE, 0x02f6, { KEY_RESERVED } },
+};
+
 static struct input_dev *dell_wmi_input_dev;
 
-static void dell_wmi_process_key(int reported_key)
+static void dell_wmi_process_key(int type, int code)
 {
 	const struct key_entry *key;
 
 	key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
-						reported_key);
+						(type << 16) | code);
 	if (!key) {
-		pr_info("Unknown key with scancode 0x%x pressed\n",
-			reported_key);
+		pr_info("Unknown key with type 0x%04x and code 0x%04x pressed\n",
+			type, code);
 		return;
 	}
 
-	pr_debug("Key %x pressed\n", reported_key);
+	pr_debug("Key with type 0x%04x and code 0x%04x pressed\n", type, code);
 
 	/* Don't report brightness notifications that will also come via ACPI */
 	if ((key->keycode == KEY_BRIGHTNESSUP ||
@@ -246,7 +316,7 @@ static void dell_wmi_process_key(int reported_key)
 	    acpi_video_handles_brightness_key_presses())
 		return;
 
-	if (reported_key == 0xe025 && !wmi_requires_smbios_request)
+	if (type == 0x0000 && code == 0xe025 && !wmi_requires_smbios_request)
 		return;
 
 	sparse_keymap_report_entry(dell_wmi_input_dev, key, 1, true);
@@ -284,18 +354,6 @@ static void dell_wmi_notify(u32 value, void *context)
 
 	buffer_entry = (u16 *)obj->buffer.pointer;
 	buffer_size = obj->buffer.length/2;
-
-	if (!dell_new_hk_type) {
-		if (buffer_size >= 3 && buffer_entry[1] == 0x0)
-			dell_wmi_process_key(buffer_entry[2]);
-		else if (buffer_size >= 2)
-			dell_wmi_process_key(buffer_entry[1]);
-		else
-			pr_info("Received unknown WMI event\n");
-		kfree(obj);
-		return;
-	}
-
 	buffer_end = buffer_entry + buffer_size;
 
 	/*
@@ -330,62 +388,18 @@ static void dell_wmi_notify(u32 value, void *context)
 		pr_debug("Process buffer (%*ph)\n", len*2, buffer_entry);
 
 		switch (buffer_entry[1]) {
-		case 0x00:
-			for (i = 2; i < len; ++i) {
-				switch (buffer_entry[i]) {
-				case 0xe043:
-					/* NIC Link is Up */
-					pr_debug("NIC Link is Up\n");
-					break;
-				case 0xe044:
-					/* NIC Link is Down */
-					pr_debug("NIC Link is Down\n");
-					break;
-				case 0xe045:
-					/* Unknown event but defined in DSDT */
-				default:
-					/* Unknown event */
-					pr_info("Unknown WMI event type 0x00: "
-						"0x%x\n", (int)buffer_entry[i]);
-					break;
-				}
-			}
+		case 0x0000: /* One key pressed or event occurred */
+			if (len > 2)
+				dell_wmi_process_key(0x0000, buffer_entry[2]);
+			/* Other entries could contain additional information */
 			break;
-		case 0x10:
-			/* Keys pressed */
+		case 0x0010: /* Sequence of keys pressed */
+		case 0x0011: /* Sequence of events occurred */
 			for (i = 2; i < len; ++i)
-				dell_wmi_process_key(buffer_entry[i]);
-			break;
-		case 0x11:
-			for (i = 2; i < len; ++i) {
-				switch (buffer_entry[i]) {
-				case 0xfff0:
-					/* Battery unplugged */
-					pr_debug("Battery unplugged\n");
-					break;
-				case 0xfff1:
-					/* Battery inserted */
-					pr_debug("Battery inserted\n");
-					break;
-				case 0x01e1:
-				case 0x02ea:
-				case 0x02eb:
-				case 0x02ec:
-				case 0x02f6:
-					/* Keyboard backlight level changed */
-					pr_debug("Keyboard backlight level "
-						 "changed\n");
-					break;
-				default:
-					/* Unknown event */
-					pr_info("Unknown WMI event type 0x11: "
-						"0x%x\n", (int)buffer_entry[i]);
-					break;
-				}
-			}
+				dell_wmi_process_key(buffer_entry[1],
+						     buffer_entry[i]);
 			break;
-		default:
-			/* Unknown event */
+		default: /* Unknown event */
 			pr_info("Unknown WMI event type 0x%x\n",
 				(int)buffer_entry[1]);
 			break;
@@ -410,7 +424,6 @@ static bool have_scancode(u32 scancode, const struct key_entry *keymap, int len)
 }
 
 static void __init handle_dmi_entry(const struct dmi_header *dm,
-
 				    void *opaque)
 
 {
@@ -418,7 +431,6 @@ static void __init handle_dmi_entry(const struct dmi_header *dm,
 	struct dell_bios_hotkey_table *table;
 	int hotkey_num, i, pos = 0;
 	struct key_entry *keymap;
-	int num_bios_keys;
 
 	if (results->err || results->keymap)
 		return;		/* We already found the hotkey table. */
@@ -442,8 +454,7 @@ static void __init handle_dmi_entry(const struct dmi_header *dm,
 		return;
 	}
 
-	keymap = kcalloc(hotkey_num + ARRAY_SIZE(dell_wmi_extra_keymap) + 1,
-			 sizeof(struct key_entry), GFP_KERNEL);
+	keymap = kcalloc(hotkey_num, sizeof(struct key_entry), GFP_KERNEL);
 	if (!keymap) {
 		results->err = -ENOMEM;
 		return;
@@ -480,31 +491,15 @@ static void __init handle_dmi_entry(const struct dmi_header *dm,
 		pos++;
 	}
 
-	num_bios_keys = pos;
-
-	for (i = 0; i < ARRAY_SIZE(dell_wmi_extra_keymap); i++) {
-		const struct key_entry *entry = &dell_wmi_extra_keymap[i];
-
-		/*
-		 * Check if we've already found this scancode.  This takes
-		 * quadratic time, but it doesn't matter unless the list
-		 * of extra keys gets very long.
-		 */
-		if (!have_scancode(entry->code, keymap, num_bios_keys)) {
-			keymap[pos] = *entry;
-			pos++;
-		}
-	}
-
-	keymap[pos].type = KE_END;
-
 	results->keymap = keymap;
+	results->keymap_size = pos;
 }
 
 static int __init dell_wmi_input_setup(void)
 {
 	struct dell_dmi_results dmi_results = {};
-	int err;
+	struct key_entry *keymap;
+	int err, i, pos = 0;
 
 	dell_wmi_input_dev = input_allocate_device();
 	if (!dell_wmi_input_dev)
@@ -528,21 +523,71 @@ static int __init dell_wmi_input_setup(void)
 		goto err_free_dev;
 	}
 
-	if (dmi_results.keymap) {
-		dell_new_hk_type = true;
+	keymap = kcalloc(dmi_results.keymap_size +
+			 ARRAY_SIZE(dell_wmi_keymap_type_0000) +
+			 ARRAY_SIZE(dell_wmi_keymap_type_0010) +
+			 ARRAY_SIZE(dell_wmi_keymap_type_0011) +
+			 1,
+			 sizeof(struct key_entry), GFP_KERNEL);
+	if (!keymap) {
+		kfree(dmi_results.keymap);
+		err = -ENOMEM;
+		goto err_free_dev;
+	}
+
+	/* Append table with events of type 0x0010 which comes from DMI */
+	for (i = 0; i < dmi_results.keymap_size; i++) {
+		keymap[pos] = dmi_results.keymap[i];
+		keymap[pos].code |= (0x0010 << 16);
+		pos++;
+	}
+
+	kfree(dmi_results.keymap);
 
-		err = sparse_keymap_setup(dell_wmi_input_dev,
-					  dmi_results.keymap, NULL);
+	/* Append table with extra events of type 0x0010 which are not in DMI */
+	for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0010); i++) {
+		const struct key_entry *entry = &dell_wmi_keymap_type_0010[i];
 
 		/*
-		 * Sparse keymap library makes a copy of keymap so we
-		 * don't need the original one that was allocated.
+		 * Check if we've already found this scancode.  This takes
+		 * quadratic time, but it doesn't matter unless the list
+		 * of extra keys gets very long.
 		 */
-		kfree(dmi_results.keymap);
-	} else {
-		err = sparse_keymap_setup(dell_wmi_input_dev,
-					  dell_wmi_legacy_keymap, NULL);
+		if (dmi_results.keymap_size &&
+		    have_scancode(entry->code | (0x0010 << 16),
+				  keymap, dmi_results.keymap_size)
+		   )
+			continue;
+
+		keymap[pos] = *entry;
+		keymap[pos].code |= (0x0010 << 16);
+		pos++;
+	}
+
+	/* Append table with events of type 0x0011 */
+	for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0011); i++) {
+		keymap[pos] = dell_wmi_keymap_type_0011[i];
+		keymap[pos].code |= (0x0011 << 16);
+		pos++;
 	}
+
+	/*
+	 * Now append also table with "legacy" events of type 0x0000. Some of
+	 * them are reported also on laptops which have scancodes in DMI.
+	 */
+	for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0000); i++) {
+		keymap[pos] = dell_wmi_keymap_type_0000[i];
+		pos++;
+	}
+
+	keymap[pos].type = KE_END;
+
+	err = sparse_keymap_setup(dell_wmi_input_dev, keymap, NULL);
+	/*
+	 * Sparse keymap library makes a copy of keymap so we don't need the
+	 * original one that was allocated.
+	 */
+	kfree(keymap);
 	if (err)
 		goto err_free_dev;
 
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index ce41bc34288d..61f39abf5dc8 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -88,9 +88,6 @@
 
 #define ACPI_FUJITSU_NOTIFY_CODE1     0x80
 
-#define ACPI_VIDEO_NOTIFY_INC_BRIGHTNESS     0x86
-#define ACPI_VIDEO_NOTIFY_DEC_BRIGHTNESS     0x87
-
 /* FUNC interface - command values */
 #define FUNC_RFKILL	0x1000
 #define FUNC_LEDS	0x1001
@@ -108,6 +105,8 @@
 #define LOGOLAMP_POWERON 0x2000
 #define LOGOLAMP_ALWAYS  0x4000
 #define RADIO_LED_ON	0x20
+#define ECO_LED	0x10000
+#define ECO_LED_ON	0x80000
 #endif
 
 /* Hotkey details */
@@ -121,13 +120,6 @@
 #define RINGBUFFERSIZE 40
 
 /* Debugging */
-#define FUJLAPTOP_LOG	   ACPI_FUJITSU_HID ": "
-#define FUJLAPTOP_ERR	   KERN_ERR FUJLAPTOP_LOG
-#define FUJLAPTOP_NOTICE   KERN_NOTICE FUJLAPTOP_LOG
-#define FUJLAPTOP_INFO	   KERN_INFO FUJLAPTOP_LOG
-#define FUJLAPTOP_DEBUG    KERN_DEBUG FUJLAPTOP_LOG
-
-#define FUJLAPTOP_DBG_ALL	  0xffff
 #define FUJLAPTOP_DBG_ERROR	  0x0001
 #define FUJLAPTOP_DBG_WARN	  0x0002
 #define FUJLAPTOP_DBG_INFO	  0x0004
@@ -136,7 +128,7 @@
 #ifdef CONFIG_FUJITSU_LAPTOP_DEBUG
 #define vdbg_printk(a_dbg_level, format, arg...) \
 	do { if (dbg_level & a_dbg_level) \
-		printk(FUJLAPTOP_DEBUG "%s: " format, __func__ , ## arg); \
+		printk(KERN_DEBUG pr_fmt("%s: " format), __func__, ## arg); \
 	} while (0)
 #else
 #define vdbg_printk(a_dbg_level, format, arg...) \
@@ -176,6 +168,7 @@ struct fujitsu_hotkey_t {
 	int logolamp_registered;
 	int kblamps_registered;
 	int radio_led_registered;
+	int eco_led_registered;
 };
 
 static struct fujitsu_hotkey_t *fujitsu_hotkey;
@@ -212,6 +205,16 @@ static struct led_classdev radio_led = {
  .brightness_get = radio_led_get,
  .brightness_set = radio_led_set
 };
+
+static enum led_brightness eco_led_get(struct led_classdev *cdev);
+static void eco_led_set(struct led_classdev *cdev,
+			       enum led_brightness brightness);
+
+static struct led_classdev eco_led = {
+ .name = "fujitsu::eco_led",
+ .brightness_get = eco_led_get,
+ .brightness_set = eco_led_set
+};
 #endif
 
 #ifdef CONFIG_FUJITSU_LAPTOP_DEBUG
@@ -296,6 +299,18 @@ static void radio_led_set(struct led_classdev *cdev,
 		call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0);
 }
 
+static void eco_led_set(struct led_classdev *cdev,
+				enum led_brightness brightness)
+{
+	int curr;
+
+	curr = call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0);
+	if (brightness >= LED_FULL)
+		call_fext_func(FUNC_LEDS, 0x1, ECO_LED, curr | ECO_LED_ON);
+	else
+		call_fext_func(FUNC_LEDS, 0x1, ECO_LED, curr & ~ECO_LED_ON);
+}
+
 static enum led_brightness logolamp_get(struct led_classdev *cdev)
 {
 	enum led_brightness brightness = LED_OFF;
@@ -330,6 +345,16 @@ static enum led_brightness radio_led_get(struct led_classdev *cdev)
 
 	return brightness;
 }
+
+static enum led_brightness eco_led_get(struct led_classdev *cdev)
+{
+	enum led_brightness brightness = LED_OFF;
+
+	if (call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0) & ECO_LED_ON)
+		brightness = LED_FULL;
+
+	return brightness;
+}
 #endif
 
 /* Hardware access for LCD brightness control */
@@ -856,6 +881,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 	set_bit(fujitsu->keycode3, input->keybit);
 	set_bit(fujitsu->keycode4, input->keybit);
 	set_bit(fujitsu->keycode5, input->keybit);
+	set_bit(KEY_TOUCHPAD_TOGGLE, input->keybit);
 	set_bit(KEY_UNKNOWN, input->keybit);
 
 	error = input_register_device(input);
@@ -943,6 +969,23 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 			       result);
 		}
 	}
+
+	/* Support for eco led is not always signaled in bit corresponding
+	 * to the bit used to control the led. According to the DSDT table,
+	 * bit 14 seems to indicate presence of said led as well.
+	 * Confirm by testing the status.
+	*/
+	if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & BIT(14)) &&
+	   (call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0) != UNSUPPORTED_CMD)) {
+		result = led_classdev_register(&fujitsu->pf_device->dev,
+						&eco_led);
+		if (result == 0) {
+			fujitsu_hotkey->eco_led_registered = 1;
+		} else {
+			pr_err("Could not register LED handler for eco LED, error %i\n",
+			       result);
+		}
+	}
 #endif
 
 	return result;
@@ -972,6 +1015,9 @@ static int acpi_fujitsu_hotkey_remove(struct acpi_device *device)
 
 	if (fujitsu_hotkey->radio_led_registered)
 		led_classdev_unregister(&radio_led);
+
+	if (fujitsu_hotkey->eco_led_registered)
+		led_classdev_unregister(&eco_led);
 #endif
 
 	input_unregister_device(input);
@@ -1060,6 +1106,19 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
 			}
 		}
 
+		/* On some models (first seen on the Skylake-based Lifebook
+		 * E736/E746/E756), the touchpad toggle hotkey (Fn+F4) is
+		 * handled in software; its state is queried using FUNC_RFKILL
+		 */
+		if ((fujitsu_hotkey->rfkill_supported & BIT(26)) &&
+		    (call_fext_func(FUNC_RFKILL, 0x1, 0x0, 0x0) & BIT(26))) {
+			keycode = KEY_TOUCHPAD_TOGGLE;
+			input_report_key(input, keycode, 1);
+			input_sync(input);
+			input_report_key(input, keycode, 0);
+			input_sync(input);
+		}
+
 		break;
 	default:
 		keycode = KEY_UNKNOWN;
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 6f145f2d004d..96ffda493266 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -718,6 +718,11 @@ static int __init hp_wmi_rfkill_setup(struct platform_device *device)
 	if (err)
 		return err;
 
+	err = hp_wmi_perform_query(HPWMI_WIRELESS_QUERY, 1, &wireless,
+				   sizeof(wireless), 0);
+	if (err)
+		return err;
+
 	if (wireless & 0x1) {
 		wifi_rfkill = rfkill_alloc("hp-wifi", &device->dev,
 					   RFKILL_TYPE_WLAN,
@@ -882,7 +887,7 @@ static int __init hp_wmi_bios_setup(struct platform_device *device)
 	wwan_rfkill = NULL;
 	rfkill2_count = 0;
 
-	if (hp_wmi_bios_2009_later() || hp_wmi_rfkill_setup(device))
+	if (hp_wmi_rfkill_setup(device))
 		hp_wmi_rfkill2_setup(device);
 
 	err = device_create_file(&device->dev, &dev_attr_display);
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index a818db6aa08f..ed5874217ee7 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -122,8 +122,8 @@ static int intel_hid_input_setup(struct platform_device *device)
 	return 0;
 
 err_free_device:
-		input_free_device(priv->input_dev);
-		return ret;
+	input_free_device(priv->input_dev);
+	return ret;
 }
 
 static void intel_hid_input_destroy(struct platform_device *device)
@@ -224,7 +224,6 @@ static int intel_hid_remove(struct platform_device *device)
 	acpi_remove_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler);
 	intel_hid_input_destroy(device);
 	intel_hid_set_enable(&device->dev, 0);
-	acpi_remove_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler);
 
 	/*
 	 * Even if we failed to shut off the event stream, we can still
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
new file mode 100644
index 000000000000..146d02f8c9bc
--- /dev/null
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -0,0 +1,188 @@
+/*
+ *  Intel Virtual Button driver for Windows 8.1+
+ *
+ *  Copyright (C) 2016 AceLan Kao <acelan.kao@canonical.com>
+ *  Copyright (C) 2016 Alex Hung <alex.hung@canonical.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/input.h>
+#include <linux/platform_device.h>
+#include <linux/input/sparse-keymap.h>
+#include <linux/acpi.h>
+#include <acpi/acpi_bus.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("AceLan Kao");
+
+static const struct acpi_device_id intel_vbtn_ids[] = {
+	{"INT33D6", 0},
+	{"", 0},
+};
+
+/* In theory, these are HID usages. */
+static const struct key_entry intel_vbtn_keymap[] = {
+	{ KE_IGNORE, 0xC0, { KEY_POWER } },	/* power key press */
+	{ KE_KEY, 0xC1, { KEY_POWER } },	/* power key release */
+	{ KE_END },
+};
+
+struct intel_vbtn_priv {
+	struct input_dev *input_dev;
+};
+
+static int intel_vbtn_input_setup(struct platform_device *device)
+{
+	struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
+	int ret;
+
+	priv->input_dev = input_allocate_device();
+	if (!priv->input_dev)
+		return -ENOMEM;
+
+	ret = sparse_keymap_setup(priv->input_dev, intel_vbtn_keymap, NULL);
+	if (ret)
+		goto err_free_device;
+
+	priv->input_dev->dev.parent = &device->dev;
+	priv->input_dev->name = "Intel Virtual Button driver";
+	priv->input_dev->id.bustype = BUS_HOST;
+
+	ret = input_register_device(priv->input_dev);
+	if (ret)
+		goto err_free_device;
+
+	return 0;
+
+err_free_device:
+	input_free_device(priv->input_dev);
+	return ret;
+}
+
+static void intel_vbtn_input_destroy(struct platform_device *device)
+{
+	struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
+
+	input_unregister_device(priv->input_dev);
+}
+
+static void notify_handler(acpi_handle handle, u32 event, void *context)
+{
+	struct platform_device *device = context;
+	struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
+
+	if (!sparse_keymap_report_event(priv->input_dev, event, 1, true))
+		dev_info(&device->dev, "unknown event index 0x%x\n",
+			 event);
+}
+
+static int intel_vbtn_probe(struct platform_device *device)
+{
+	acpi_handle handle = ACPI_HANDLE(&device->dev);
+	struct intel_vbtn_priv *priv;
+	acpi_status status;
+	int err;
+
+	status = acpi_evaluate_object(handle, "VBDL", NULL, NULL);
+	if (!ACPI_SUCCESS(status)) {
+		dev_warn(&device->dev, "failed to read Intel Virtual Button driver\n");
+		return -ENODEV;
+	}
+
+	priv = devm_kzalloc(&device->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	dev_set_drvdata(&device->dev, priv);
+
+	err = intel_vbtn_input_setup(device);
+	if (err) {
+		pr_err("Failed to setup Intel Virtual Button\n");
+		return err;
+	}
+
+	status = acpi_install_notify_handler(handle,
+					     ACPI_DEVICE_NOTIFY,
+					     notify_handler,
+					     device);
+	if (ACPI_FAILURE(status)) {
+		err = -EBUSY;
+		goto err_remove_input;
+	}
+
+	return 0;
+
+err_remove_input:
+	intel_vbtn_input_destroy(device);
+
+	return err;
+}
+
+static int intel_vbtn_remove(struct platform_device *device)
+{
+	acpi_handle handle = ACPI_HANDLE(&device->dev);
+
+	intel_vbtn_input_destroy(device);
+	acpi_remove_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler);
+
+	/*
+	 * Even if we failed to shut off the event stream, we can still
+	 * safely detach from the device.
+	 */
+	return 0;
+}
+
+static struct platform_driver intel_vbtn_pl_driver = {
+	.driver = {
+		.name = "intel-vbtn",
+		.acpi_match_table = intel_vbtn_ids,
+	},
+	.probe = intel_vbtn_probe,
+	.remove = intel_vbtn_remove,
+};
+MODULE_DEVICE_TABLE(acpi, intel_vbtn_ids);
+
+static acpi_status __init
+check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	const struct acpi_device_id *ids = context;
+	struct acpi_device *dev;
+
+	if (acpi_bus_get_device(handle, &dev) != 0)
+		return AE_OK;
+
+	if (acpi_match_device_ids(dev, ids) == 0)
+		if (acpi_create_platform_device(dev))
+			dev_info(&dev->dev,
+				 "intel-vbtn: created platform device\n");
+
+	return AE_OK;
+}
+
+static int __init intel_vbtn_init(void)
+{
+	acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
+			    ACPI_UINT32_MAX, check_acpi_dev, NULL,
+			    (void *)intel_vbtn_ids, NULL);
+
+	return platform_driver_register(&intel_vbtn_pl_driver);
+}
+module_init(intel_vbtn_init);
+
+static void __exit intel_vbtn_exit(void)
+{
+	platform_driver_unregister(&intel_vbtn_pl_driver);
+}
+module_exit(intel_vbtn_exit);
diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c
index e57f923eea0b..520b58a04daa 100644
--- a/drivers/platform/x86/intel_pmc_core.c
+++ b/drivers/platform/x86/intel_pmc_core.c
@@ -23,7 +23,6 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/pci.h>
-#include <linux/seq_file.h>
 
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
@@ -78,30 +77,18 @@ int intel_pmc_slp_s0_counter_read(u32 *data)
 }
 EXPORT_SYMBOL_GPL(intel_pmc_slp_s0_counter_read);
 
-#if IS_ENABLED(CONFIG_DEBUG_FS)
-static int pmc_core_dev_state_show(struct seq_file *s, void *unused)
+static int pmc_core_dev_state_get(void *data, u64 *val)
 {
-	struct pmc_dev *pmcdev = s->private;
-	u32 counter_val;
+	struct pmc_dev *pmcdev = data;
+	u32 value;
 
-	counter_val = pmc_core_reg_read(pmcdev,
-					SPT_PMC_SLP_S0_RES_COUNTER_OFFSET);
-	seq_printf(s, "%u\n", pmc_core_adjust_slp_s0_step(counter_val));
+	value = pmc_core_reg_read(pmcdev, SPT_PMC_SLP_S0_RES_COUNTER_OFFSET);
+	*val = pmc_core_adjust_slp_s0_step(value);
 
 	return 0;
 }
 
-static int pmc_core_dev_state_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pmc_core_dev_state_show, inode->i_private);
-}
-
-static const struct file_operations pmc_core_dev_state_ops = {
-	.open           = pmc_core_dev_state_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = single_release,
-};
+DEFINE_DEBUGFS_ATTRIBUTE(pmc_core_dev_state, pmc_core_dev_state_get, NULL, "%llu\n");
 
 static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
 {
@@ -113,12 +100,12 @@ static int pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
 	struct dentry *dir, *file;
 
 	dir = debugfs_create_dir("pmc_core", NULL);
-	if (!dir)
+	if (IS_ERR_OR_NULL(dir))
 		return -ENOMEM;
 
 	pmcdev->dbgfs_dir = dir;
 	file = debugfs_create_file("slp_s0_residency_usec", S_IFREG | S_IRUGO,
-				   dir, pmcdev, &pmc_core_dev_state_ops);
+				   dir, pmcdev, &pmc_core_dev_state);
 
 	if (!file) {
 		pmc_core_dbgfs_unregister(pmcdev);
@@ -127,16 +114,6 @@ static int pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
 
 	return 0;
 }
-#else
-static inline int pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
-{
-	return 0;
-}
-
-static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
-{
-}
-#endif /* CONFIG_DEBUG_FS */
 
 static const struct x86_cpu_id intel_pmc_core_ids[] = {
 	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_MOBILE, X86_FEATURE_MWAIT,
@@ -183,10 +160,8 @@ static int pmc_core_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	err = pmc_core_dbgfs_register(pmcdev);
-	if (err < 0) {
-		dev_err(&dev->dev, "PMC Core: debugfs register failed.\n");
-		return err;
-	}
+	if (err < 0)
+		dev_warn(&dev->dev, "PMC Core: debugfs register failed.\n");
 
 	pmc.has_slp_s0_res = true;
 	return 0;
diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h
index a9dadaf787c1..e3f671f4d122 100644
--- a/drivers/platform/x86/intel_pmc_core.h
+++ b/drivers/platform/x86/intel_pmc_core.h
@@ -23,6 +23,7 @@
 
 /* Sunrise Point Power Management Controller PCI Device ID */
 #define SPT_PMC_PCI_DEVICE_ID			0x9d21
+
 #define SPT_PMC_BASE_ADDR_OFFSET		0x48
 #define SPT_PMC_SLP_S0_RES_COUNTER_OFFSET	0x13c
 #define SPT_PMC_MMIO_REG_LEN			0x100
@@ -42,9 +43,7 @@
 struct pmc_dev {
 	u32 base_addr;
 	void __iomem *regbase;
-#if IS_ENABLED(CONFIG_DEBUG_FS)
 	struct dentry *dbgfs_dir;
-#endif /* CONFIG_DEBUG_FS */
 	bool has_slp_s0_res;
 };
 
diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c
index 815a7c5e9566..ef29f18b1951 100644
--- a/drivers/platform/x86/intel_telemetry_debugfs.c
+++ b/drivers/platform/x86/intel_telemetry_debugfs.c
@@ -79,7 +79,7 @@
 #define TELEM_EVT_LEN(x) (sizeof(x)/sizeof((x)[0]))
 
 #define TELEM_DEBUGFS_CPU(model, data) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&data}
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&data}
 
 #define TELEM_CHECK_AND_PARSE_EVTS(EVTID, EVTNUM, BUF, EVTLOG, EVTDAT, MASK) { \
 	if (evtlog[index].telem_evtid == (EVTID)) { \
diff --git a/drivers/platform/x86/intel_telemetry_pltdrv.c b/drivers/platform/x86/intel_telemetry_pltdrv.c
index 6d884f7d1b9f..6ebdbd2b04fc 100644
--- a/drivers/platform/x86/intel_telemetry_pltdrv.c
+++ b/drivers/platform/x86/intel_telemetry_pltdrv.c
@@ -83,7 +83,7 @@
 #define TELEM_SET_VERBOSITY_BITS(x, y)	((x) |= ((y) << 27))
 
 #define TELEM_CPU(model, data) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&data }
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&data }
 
 enum telemetry_action {
 	TELEM_UPDATE = 0,
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 01e12d221a8b..9d60a40d8b3f 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -4,7 +4,7 @@
  *  Copyright (C) 2002-2004 John Belmonte
  *  Copyright (C) 2008 Philip Langdale
  *  Copyright (C) 2010 Pierre Ducroquet
- *  Copyright (C) 2014-2015 Azael Avalos
+ *  Copyright (C) 2014-2016 Azael Avalos
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -31,7 +31,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#define TOSHIBA_ACPI_VERSION	"0.23"
+#define TOSHIBA_ACPI_VERSION	"0.24"
 #define PROC_INTERFACE_VERSION	1
 
 #include <linux/kernel.h>
@@ -53,6 +53,7 @@
 #include <linux/uaccess.h>
 #include <linux/miscdevice.h>
 #include <linux/rfkill.h>
+#include <linux/iio/iio.h>
 #include <linux/toshiba.h>
 #include <acpi/video.h>
 
@@ -134,6 +135,7 @@ MODULE_LICENSE("GPL");
 
 /* Field definitions */
 #define HCI_ACCEL_MASK			0x7fff
+#define HCI_ACCEL_DIRECTION_MASK	0x8000
 #define HCI_HOTKEY_DISABLE		0x0b
 #define HCI_HOTKEY_ENABLE		0x09
 #define HCI_HOTKEY_SPECIAL_FUNCTIONS	0x10
@@ -178,6 +180,7 @@ struct toshiba_acpi_dev {
 	struct led_classdev eco_led;
 	struct miscdevice miscdev;
 	struct rfkill *wwan_rfk;
+	struct iio_dev *indio_dev;
 
 	int force_fan;
 	int last_key_event;
@@ -1958,28 +1961,6 @@ static ssize_t touchpad_show(struct device *dev,
 }
 static DEVICE_ATTR_RW(touchpad);
 
-static ssize_t position_show(struct device *dev,
-			     struct device_attribute *attr, char *buf)
-{
-	struct toshiba_acpi_dev *toshiba = dev_get_drvdata(dev);
-	u32 xyval, zval, tmp;
-	u16 x, y, z;
-	int ret;
-
-	xyval = zval = 0;
-	ret = toshiba_accelerometer_get(toshiba, &xyval, &zval);
-	if (ret < 0)
-		return ret;
-
-	x = xyval & HCI_ACCEL_MASK;
-	tmp = xyval >> HCI_MISC_SHIFT;
-	y = tmp & HCI_ACCEL_MASK;
-	z = zval & HCI_ACCEL_MASK;
-
-	return sprintf(buf, "%d %d %d\n", x, y, z);
-}
-static DEVICE_ATTR_RO(position);
-
 static ssize_t usb_sleep_charge_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
@@ -2350,7 +2331,6 @@ static struct attribute *toshiba_attributes[] = {
 	&dev_attr_available_kbd_modes.attr,
 	&dev_attr_kbd_backlight_timeout.attr,
 	&dev_attr_touchpad.attr,
-	&dev_attr_position.attr,
 	&dev_attr_usb_sleep_charge.attr,
 	&dev_attr_sleep_functions_on_battery.attr,
 	&dev_attr_usb_rapid_charge.attr,
@@ -2377,8 +2357,6 @@ static umode_t toshiba_sysfs_is_visible(struct kobject *kobj,
 		exists = (drv->kbd_mode == SCI_KBD_MODE_AUTO) ? true : false;
 	else if (attr == &dev_attr_touchpad.attr)
 		exists = (drv->touchpad_supported) ? true : false;
-	else if (attr == &dev_attr_position.attr)
-		exists = (drv->accelerometer_supported) ? true : false;
 	else if (attr == &dev_attr_usb_sleep_charge.attr)
 		exists = (drv->usb_sleep_charge_supported) ? true : false;
 	else if (attr == &dev_attr_sleep_functions_on_battery.attr)
@@ -2420,6 +2398,81 @@ static void toshiba_acpi_kbd_bl_work(struct work_struct *work)
 }
 
 /*
+ * IIO device
+ */
+
+enum toshiba_iio_accel_chan {
+	AXIS_X,
+	AXIS_Y,
+	AXIS_Z
+};
+
+static int toshiba_iio_accel_get_axis(enum toshiba_iio_accel_chan chan)
+{
+	u32 xyval, zval;
+	int ret;
+
+	ret = toshiba_accelerometer_get(toshiba_acpi, &xyval, &zval);
+	if (ret < 0)
+		return ret;
+
+	switch (chan) {
+	case AXIS_X:
+		return xyval & HCI_ACCEL_DIRECTION_MASK ?
+			-(xyval & HCI_ACCEL_MASK) : xyval & HCI_ACCEL_MASK;
+	case AXIS_Y:
+		return (xyval >> HCI_MISC_SHIFT) & HCI_ACCEL_DIRECTION_MASK ?
+			-((xyval >> HCI_MISC_SHIFT) & HCI_ACCEL_MASK) :
+			(xyval >> HCI_MISC_SHIFT) & HCI_ACCEL_MASK;
+	case AXIS_Z:
+		return zval & HCI_ACCEL_DIRECTION_MASK ?
+			-(zval & HCI_ACCEL_MASK) : zval & HCI_ACCEL_MASK;
+	}
+
+	return ret;
+}
+
+static int toshiba_iio_accel_read_raw(struct iio_dev *indio_dev,
+				      struct iio_chan_spec const *chan,
+				      int *val, int *val2, long mask)
+{
+	int ret;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		ret = toshiba_iio_accel_get_axis(chan->channel);
+		if (ret == -EIO || ret == -ENODEV)
+			return ret;
+
+		*val = ret;
+
+		return IIO_VAL_INT;
+	}
+
+	return -EINVAL;
+}
+
+#define TOSHIBA_IIO_ACCEL_CHANNEL(axis, chan) { \
+	.type = IIO_ACCEL, \
+	.modified = 1, \
+	.channel = chan, \
+	.channel2 = IIO_MOD_##axis, \
+	.output = 1, \
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
+}
+
+static const struct iio_chan_spec toshiba_iio_accel_channels[] = {
+	TOSHIBA_IIO_ACCEL_CHANNEL(X, AXIS_X),
+	TOSHIBA_IIO_ACCEL_CHANNEL(Y, AXIS_Y),
+	TOSHIBA_IIO_ACCEL_CHANNEL(Z, AXIS_Z),
+};
+
+static const struct iio_info toshiba_iio_accel_info = {
+	.driver_module = THIS_MODULE,
+	.read_raw = &toshiba_iio_accel_read_raw,
+};
+
+/*
  * Misc device
  */
 static int toshiba_acpi_smm_bridge(SMMRegisters *regs)
@@ -2904,6 +2957,11 @@ static int toshiba_acpi_remove(struct acpi_device *acpi_dev)
 
 	remove_toshiba_proc_entries(dev);
 
+	if (dev->accelerometer_supported && dev->indio_dev) {
+		iio_device_unregister(dev->indio_dev);
+		iio_device_free(dev->indio_dev);
+	}
+
 	if (dev->sysfs_created)
 		sysfs_remove_group(&dev->acpi_dev->dev.kobj,
 				   &toshiba_attr_group);
@@ -3051,6 +3109,30 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev)
 	dev->touchpad_supported = !ret;
 
 	toshiba_accelerometer_available(dev);
+	if (dev->accelerometer_supported) {
+		dev->indio_dev = iio_device_alloc(sizeof(*dev));
+		if (!dev->indio_dev) {
+			pr_err("Unable to allocate iio device\n");
+			goto iio_error;
+		}
+
+		pr_info("Registering Toshiba accelerometer iio device\n");
+
+		dev->indio_dev->info = &toshiba_iio_accel_info;
+		dev->indio_dev->name = "Toshiba accelerometer";
+		dev->indio_dev->dev.parent = &acpi_dev->dev;
+		dev->indio_dev->modes = INDIO_DIRECT_MODE;
+		dev->indio_dev->channels = toshiba_iio_accel_channels;
+		dev->indio_dev->num_channels =
+					ARRAY_SIZE(toshiba_iio_accel_channels);
+
+		ret = iio_device_register(dev->indio_dev);
+		if (ret < 0) {
+			pr_err("Unable to register iio device\n");
+			iio_device_free(dev->indio_dev);
+		}
+	}
+iio_error:
 
 	toshiba_usb_sleep_charge_available(dev);
 
diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c
index 81603d99082b..bedb361746a0 100644
--- a/drivers/pnp/pnpbios/core.c
+++ b/drivers/pnp/pnpbios/core.c
@@ -46,7 +46,6 @@
  */
 
 #include <linux/types.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/kernel.h>
@@ -587,6 +586,6 @@ static int __init pnpbios_thread_init(void)
 }
 
 /* Start the kernel thread later: */
-module_init(pnpbios_thread_init);
+device_initcall(pnpbios_thread_init);
 
 EXPORT_SYMBOL(pnpbios_protocol);
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 0f11a0f4c369..acd4a1524a1e 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -394,6 +394,7 @@ config CHARGER_QCOM_SMBB
 	tristate "Qualcomm Switch-Mode Battery Charger and Boost"
 	depends on MFD_SPMI_PMIC || COMPILE_TEST
 	depends on OF
+	depends on EXTCON
 	help
 	  Say Y to include support for the Switch-Mode Battery Charger and
 	  Boost (SMBB) hardware found in Qualcomm PM8941 PMICs.  The charger
diff --git a/drivers/power/axp20x_usb_power.c b/drivers/power/axp20x_usb_power.c
index 421a90b83567..6af6feb7058d 100644
--- a/drivers/power/axp20x_usb_power.c
+++ b/drivers/power/axp20x_usb_power.c
@@ -42,6 +42,7 @@
 #define AXP20X_VBUS_MON_VBUS_VALID	BIT(3)
 
 struct axp20x_usb_power {
+	struct device_node *np;
 	struct regmap *regmap;
 	struct power_supply *supply;
 };
@@ -85,7 +86,12 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 
 		switch (v & AXP20X_VBUS_CLIMIT_MASK) {
 		case AXP20X_VBUC_CLIMIT_100mA:
-			val->intval = 100000;
+			if (of_device_is_compatible(power->np,
+					"x-powers,axp202-usb-power-supply")) {
+				val->intval = 100000;
+			} else {
+				val->intval = -1; /* No 100mA limit */
+			}
 			break;
 		case AXP20X_VBUC_CLIMIT_500mA:
 			val->intval = 500000;
@@ -122,16 +128,19 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 			break;
 		}
 
-		ret = regmap_read(power->regmap, AXP20X_USB_OTG_STATUS, &v);
-		if (ret)
-			return ret;
+		val->intval = POWER_SUPPLY_HEALTH_GOOD;
 
-		if (!(v & AXP20X_USB_STATUS_VBUS_VALID)) {
-			val->intval = POWER_SUPPLY_HEALTH_UNSPEC_FAILURE;
-			break;
-		}
+		if (of_device_is_compatible(power->np,
+				"x-powers,axp202-usb-power-supply")) {
+			ret = regmap_read(power->regmap,
+					  AXP20X_USB_OTG_STATUS, &v);
+			if (ret)
+				return ret;
 
-		val->intval = POWER_SUPPLY_HEALTH_GOOD;
+			if (!(v & AXP20X_USB_STATUS_VBUS_VALID))
+				val->intval =
+					POWER_SUPPLY_HEALTH_UNSPEC_FAILURE;
+		}
 		break;
 	case POWER_SUPPLY_PROP_PRESENT:
 		val->intval = !!(input & AXP20X_PWR_STATUS_VBUS_PRESENT);
@@ -156,6 +165,14 @@ static enum power_supply_property axp20x_usb_power_properties[] = {
 	POWER_SUPPLY_PROP_CURRENT_NOW,
 };
 
+static enum power_supply_property axp22x_usb_power_properties[] = {
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN,
+	POWER_SUPPLY_PROP_CURRENT_MAX,
+};
+
 static const struct power_supply_desc axp20x_usb_power_desc = {
 	.name = "axp20x-usb",
 	.type = POWER_SUPPLY_TYPE_USB,
@@ -164,13 +181,25 @@ static const struct power_supply_desc axp20x_usb_power_desc = {
 	.get_property = axp20x_usb_power_get_property,
 };
 
+static const struct power_supply_desc axp22x_usb_power_desc = {
+	.name = "axp20x-usb",
+	.type = POWER_SUPPLY_TYPE_USB,
+	.properties = axp22x_usb_power_properties,
+	.num_properties = ARRAY_SIZE(axp22x_usb_power_properties),
+	.get_property = axp20x_usb_power_get_property,
+};
+
 static int axp20x_usb_power_probe(struct platform_device *pdev)
 {
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
 	struct power_supply_config psy_cfg = {};
 	struct axp20x_usb_power *power;
-	static const char * const irq_names[] = { "VBUS_PLUGIN",
-		"VBUS_REMOVAL", "VBUS_VALID", "VBUS_NOT_VALID" };
+	static const char * const axp20x_irq_names[] = { "VBUS_PLUGIN",
+		"VBUS_REMOVAL", "VBUS_VALID", "VBUS_NOT_VALID", NULL };
+	static const char * const axp22x_irq_names[] = {
+		"VBUS_PLUGIN", "VBUS_REMOVAL", NULL };
+	static const char * const *irq_names;
+	const struct power_supply_desc *usb_power_desc;
 	int i, irq, ret;
 
 	if (!of_device_is_available(pdev->dev.of_node))
@@ -185,31 +214,47 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 	if (!power)
 		return -ENOMEM;
 
+	power->np = pdev->dev.of_node;
 	power->regmap = axp20x->regmap;
 
-	/* Enable vbus valid checking */
-	ret = regmap_update_bits(power->regmap, AXP20X_VBUS_MON,
-		    AXP20X_VBUS_MON_VBUS_VALID, AXP20X_VBUS_MON_VBUS_VALID);
-	if (ret)
-		return ret;
+	if (of_device_is_compatible(power->np,
+			"x-powers,axp202-usb-power-supply")) {
+		/* Enable vbus valid checking */
+		ret = regmap_update_bits(power->regmap, AXP20X_VBUS_MON,
+					 AXP20X_VBUS_MON_VBUS_VALID,
+					 AXP20X_VBUS_MON_VBUS_VALID);
+		if (ret)
+			return ret;
 
-	/* Enable vbus voltage and current measurement */
-	ret = regmap_update_bits(power->regmap, AXP20X_ADC_EN1,
+		/* Enable vbus voltage and current measurement */
+		ret = regmap_update_bits(power->regmap, AXP20X_ADC_EN1,
 			AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT,
 			AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT);
-	if (ret)
-		return ret;
+		if (ret)
+			return ret;
+
+		usb_power_desc = &axp20x_usb_power_desc;
+		irq_names = axp20x_irq_names;
+	} else if (of_device_is_compatible(power->np,
+			"x-powers,axp221-usb-power-supply")) {
+		usb_power_desc = &axp22x_usb_power_desc;
+		irq_names = axp22x_irq_names;
+	} else {
+		dev_err(&pdev->dev, "Unsupported AXP variant: %ld\n",
+			axp20x->variant);
+		return -EINVAL;
+	}
 
 	psy_cfg.of_node = pdev->dev.of_node;
 	psy_cfg.drv_data = power;
 
-	power->supply = devm_power_supply_register(&pdev->dev,
-					&axp20x_usb_power_desc, &psy_cfg);
+	power->supply = devm_power_supply_register(&pdev->dev, usb_power_desc,
+						   &psy_cfg);
 	if (IS_ERR(power->supply))
 		return PTR_ERR(power->supply);
 
 	/* Request irqs after registering, as irqs may trigger immediately */
-	for (i = 0; i < ARRAY_SIZE(irq_names); i++) {
+	for (i = 0; irq_names[i]; i++) {
 		irq = platform_get_irq_byname(pdev, irq_names[i]);
 		if (irq < 0) {
 			dev_warn(&pdev->dev, "No IRQ for %s: %d\n",
@@ -229,6 +274,7 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 
 static const struct of_device_id axp20x_usb_power_match[] = {
 	{ .compatible = "x-powers,axp202-usb-power-supply" },
+	{ .compatible = "x-powers,axp221-usb-power-supply" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, axp20x_usb_power_match);
diff --git a/drivers/power/bq27xxx_battery.c b/drivers/power/bq27xxx_battery.c
index e90b3f307e0f..323d05a12f9b 100644
--- a/drivers/power/bq27xxx_battery.c
+++ b/drivers/power/bq27xxx_battery.c
@@ -82,6 +82,7 @@
  *
  * These are indexes into a device's register mapping array.
  */
+
 enum bq27xxx_reg_index {
 	BQ27XXX_REG_CTRL = 0,	/* Control */
 	BQ27XXX_REG_TEMP,	/* Temperature */
@@ -100,157 +101,144 @@ enum bq27xxx_reg_index {
 	BQ27XXX_REG_SOC,	/* State-of-Charge */
 	BQ27XXX_REG_DCAP,	/* Design Capacity */
 	BQ27XXX_REG_AP,		/* Average Power */
+	BQ27XXX_REG_MAX,	/* sentinel */
 };
 
 /* Register mappings */
-static u8 bq27000_regs[] = {
-	0x00,	/* CONTROL	*/
-	0x06,	/* TEMP		*/
-	INVALID_REG_ADDR,	/* INT TEMP - NA*/
-	0x08,	/* VOLT		*/
-	0x14,	/* AVG CURR	*/
-	0x0a,	/* FLAGS	*/
-	0x16,	/* TTE		*/
-	0x18,	/* TTF		*/
-	0x1c,	/* TTES		*/
-	0x26,	/* TTECP	*/
-	0x0c,	/* NAC		*/
-	0x12,	/* LMD(FCC)	*/
-	0x2a,	/* CYCT		*/
-	0x22,	/* AE		*/
-	0x0b,	/* SOC(RSOC)	*/
-	0x76,	/* DCAP(ILMD)	*/
-	0x24,	/* AP		*/
-};
-
-static u8 bq27010_regs[] = {
-	0x00,	/* CONTROL	*/
-	0x06,	/* TEMP		*/
-	INVALID_REG_ADDR,	/* INT TEMP - NA*/
-	0x08,	/* VOLT		*/
-	0x14,	/* AVG CURR	*/
-	0x0a,	/* FLAGS	*/
-	0x16,	/* TTE		*/
-	0x18,	/* TTF		*/
-	0x1c,	/* TTES		*/
-	0x26,	/* TTECP	*/
-	0x0c,	/* NAC		*/
-	0x12,	/* LMD(FCC)	*/
-	0x2a,	/* CYCT		*/
-	INVALID_REG_ADDR,	/* AE - NA	*/
-	0x0b,	/* SOC(RSOC)	*/
-	0x76,	/* DCAP(ILMD)	*/
-	INVALID_REG_ADDR,	/* AP - NA	*/
-};
-
-static u8 bq27500_regs[] = {
-	0x00,	/* CONTROL	*/
-	0x06,	/* TEMP		*/
-	0x28,	/* INT TEMP	*/
-	0x08,	/* VOLT		*/
-	0x14,	/* AVG CURR	*/
-	0x0a,	/* FLAGS	*/
-	0x16,	/* TTE		*/
-	INVALID_REG_ADDR,	/* TTF - NA	*/
-	0x1a,	/* TTES		*/
-	INVALID_REG_ADDR,	/* TTECP - NA	*/
-	0x0c,	/* NAC		*/
-	0x12,	/* LMD(FCC)	*/
-	0x2a,	/* CYCT		*/
-	INVALID_REG_ADDR,	/* AE - NA	*/
-	0x2c,	/* SOC(RSOC)	*/
-	0x3c,	/* DCAP(ILMD)	*/
-	INVALID_REG_ADDR,	/* AP - NA	*/
-};
-
-static u8 bq27530_regs[] = {
-	0x00,	/* CONTROL	*/
-	0x06,	/* TEMP		*/
-	0x32,	/* INT TEMP	*/
-	0x08,	/* VOLT		*/
-	0x14,	/* AVG CURR	*/
-	0x0a,	/* FLAGS	*/
-	0x16,	/* TTE		*/
-	INVALID_REG_ADDR,	/* TTF - NA	*/
-	INVALID_REG_ADDR,	/* TTES - NA	*/
-	INVALID_REG_ADDR,	/* TTECP - NA	*/
-	0x0c,	/* NAC		*/
-	0x12,	/* LMD(FCC)	*/
-	0x2a,	/* CYCT		*/
-	INVALID_REG_ADDR,	/* AE - NA	*/
-	0x2c,	/* SOC(RSOC)	*/
-	INVALID_REG_ADDR,	/* DCAP - NA	*/
-	0x24,	/* AP		*/
-};
-
-static u8 bq27541_regs[] = {
-	0x00,	/* CONTROL	*/
-	0x06,	/* TEMP		*/
-	0x28,	/* INT TEMP	*/
-	0x08,	/* VOLT		*/
-	0x14,	/* AVG CURR	*/
-	0x0a,	/* FLAGS	*/
-	0x16,	/* TTE		*/
-	INVALID_REG_ADDR,	/* TTF - NA	*/
-	INVALID_REG_ADDR,	/* TTES - NA	*/
-	INVALID_REG_ADDR,	/* TTECP - NA	*/
-	0x0c,	/* NAC		*/
-	0x12,	/* LMD(FCC)	*/
-	0x2a,	/* CYCT		*/
-	INVALID_REG_ADDR,	/* AE - NA	*/
-	0x2c,	/* SOC(RSOC)	*/
-	0x3c,	/* DCAP		*/
-	0x24,	/* AP		*/
-};
-
-static u8 bq27545_regs[] = {
-	0x00,	/* CONTROL	*/
-	0x06,	/* TEMP		*/
-	0x28,	/* INT TEMP	*/
-	0x08,	/* VOLT		*/
-	0x14,	/* AVG CURR	*/
-	0x0a,	/* FLAGS	*/
-	0x16,	/* TTE		*/
-	INVALID_REG_ADDR,	/* TTF - NA	*/
-	INVALID_REG_ADDR,	/* TTES - NA	*/
-	INVALID_REG_ADDR,	/* TTECP - NA	*/
-	0x0c,	/* NAC		*/
-	0x12,	/* LMD(FCC)	*/
-	0x2a,	/* CYCT		*/
-	INVALID_REG_ADDR,	/* AE - NA	*/
-	0x2c,	/* SOC(RSOC)	*/
-	INVALID_REG_ADDR,	/* DCAP - NA */
-	0x24,	/* AP		*/
-};
-
-static u8 bq27421_regs[] = {
-	0x00,	/* CONTROL	*/
-	0x02,	/* TEMP		*/
-	0x1e,	/* INT TEMP	*/
-	0x04,	/* VOLT		*/
-	0x10,	/* AVG CURR	*/
-	0x06,	/* FLAGS	*/
-	INVALID_REG_ADDR,	/* TTE - NA	*/
-	INVALID_REG_ADDR,	/* TTF - NA	*/
-	INVALID_REG_ADDR,	/* TTES - NA	*/
-	INVALID_REG_ADDR,	/* TTECP - NA	*/
-	0x08,	/* NAC		*/
-	0x0e,	/* FCC		*/
-	INVALID_REG_ADDR,	/* CYCT - NA	*/
-	INVALID_REG_ADDR,	/* AE - NA	*/
-	0x1c,	/* SOC		*/
-	0x3c,	/* DCAP		*/
-	0x18,	/* AP		*/
-};
-
-static u8 *bq27xxx_regs[] = {
-	[BQ27000] = bq27000_regs,
-	[BQ27010] = bq27010_regs,
-	[BQ27500] = bq27500_regs,
-	[BQ27530] = bq27530_regs,
-	[BQ27541] = bq27541_regs,
-	[BQ27545] = bq27545_regs,
-	[BQ27421] = bq27421_regs,
+static u8 bq27xxx_regs[][BQ27XXX_REG_MAX] = {
+	[BQ27000] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x0b,
+		[BQ27XXX_REG_DCAP] = 0x76,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27010] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x0b,
+		[BQ27XXX_REG_DCAP] = 0x76,
+		[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
+	},
+	[BQ27500] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x28,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = 0x1a,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
+	},
+	[BQ27530] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x32,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27541] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x28,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27545] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x28,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27421] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x02,
+		[BQ27XXX_REG_INT_TEMP] = 0x1e,
+		[BQ27XXX_REG_VOLT] = 0x04,
+		[BQ27XXX_REG_AI] = 0x10,
+		[BQ27XXX_REG_FLAGS] = 0x06,
+		[BQ27XXX_REG_TTE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x08,
+		[BQ27XXX_REG_FCC] = 0x0e,
+		[BQ27XXX_REG_CYCT] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x1c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x18,
+	},
 };
 
 static enum power_supply_property bq27000_battery_props[] = {
diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c
index b8f8d3ade31b..85d4ea2a9c20 100644
--- a/drivers/power/bq27xxx_battery_i2c.c
+++ b/drivers/power/bq27xxx_battery_i2c.c
@@ -1,5 +1,5 @@
 /*
- * SCI Reset driver for Keystone based devices
+ * BQ27xxx battery monitor I2C driver
  *
  * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/
  *	Andrew F. Davis <afd@ti.com>
diff --git a/drivers/power/max8903_charger.c b/drivers/power/max8903_charger.c
index 17876caf31e5..fdc73d686153 100644
--- a/drivers/power/max8903_charger.c
+++ b/drivers/power/max8903_charger.c
@@ -23,13 +23,16 @@
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/slab.h>
 #include <linux/power_supply.h>
 #include <linux/platform_device.h>
 #include <linux/power/max8903_charger.h>
 
 struct max8903_data {
-	struct max8903_pdata pdata;
+	struct max8903_pdata *pdata;
 	struct device *dev;
 	struct power_supply *psy;
 	struct power_supply_desc psy_desc;
@@ -53,8 +56,8 @@ static int max8903_get_property(struct power_supply *psy,
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
 		val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
-		if (data->pdata.chg) {
-			if (gpio_get_value(data->pdata.chg) == 0)
+		if (gpio_is_valid(data->pdata->chg)) {
+			if (gpio_get_value(data->pdata->chg) == 0)
 				val->intval = POWER_SUPPLY_STATUS_CHARGING;
 			else if (data->usb_in || data->ta_in)
 				val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
@@ -75,13 +78,14 @@ static int max8903_get_property(struct power_supply *psy,
 	default:
 		return -EINVAL;
 	}
+
 	return 0;
 }
 
 static irqreturn_t max8903_dcin(int irq, void *_data)
 {
 	struct max8903_data *data = _data;
-	struct max8903_pdata *pdata = &data->pdata;
+	struct max8903_pdata *pdata = data->pdata;
 	bool ta_in;
 	enum power_supply_type old_type;
 
@@ -93,11 +97,11 @@ static irqreturn_t max8903_dcin(int irq, void *_data)
 	data->ta_in = ta_in;
 
 	/* Set Current-Limit-Mode 1:DC 0:USB */
-	if (pdata->dcm)
+	if (gpio_is_valid(pdata->dcm))
 		gpio_set_value(pdata->dcm, ta_in ? 1 : 0);
 
 	/* Charger Enable / Disable (cen is negated) */
-	if (pdata->cen)
+	if (gpio_is_valid(pdata->cen))
 		gpio_set_value(pdata->cen, ta_in ? 0 :
 				(data->usb_in ? 0 : 1));
 
@@ -122,7 +126,7 @@ static irqreturn_t max8903_dcin(int irq, void *_data)
 static irqreturn_t max8903_usbin(int irq, void *_data)
 {
 	struct max8903_data *data = _data;
-	struct max8903_pdata *pdata = &data->pdata;
+	struct max8903_pdata *pdata = data->pdata;
 	bool usb_in;
 	enum power_supply_type old_type;
 
@@ -136,7 +140,7 @@ static irqreturn_t max8903_usbin(int irq, void *_data)
 	/* Do not touch Current-Limit-Mode */
 
 	/* Charger Enable / Disable (cen is negated) */
-	if (pdata->cen)
+	if (gpio_is_valid(pdata->cen))
 		gpio_set_value(pdata->cen, usb_in ? 0 :
 				(data->ta_in ? 0 : 1));
 
@@ -161,7 +165,7 @@ static irqreturn_t max8903_usbin(int irq, void *_data)
 static irqreturn_t max8903_fault(int irq, void *_data)
 {
 	struct max8903_data *data = _data;
-	struct max8903_pdata *pdata = &data->pdata;
+	struct max8903_pdata *pdata = data->pdata;
 	bool fault;
 
 	fault = gpio_get_value(pdata->flt) ? false : true;
@@ -179,57 +183,109 @@ static irqreturn_t max8903_fault(int irq, void *_data)
 	return IRQ_HANDLED;
 }
 
-static int max8903_probe(struct platform_device *pdev)
+static struct max8903_pdata *max8903_parse_dt_data(struct device *dev)
 {
-	struct max8903_data *data;
+	struct device_node *np = dev->of_node;
+	struct max8903_pdata *pdata = NULL;
+
+	if (!np)
+		return NULL;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	pdata->dc_valid = false;
+	pdata->usb_valid = false;
+
+	pdata->cen = of_get_named_gpio(np, "cen-gpios", 0);
+	if (!gpio_is_valid(pdata->cen))
+		pdata->cen = -EINVAL;
+
+	pdata->chg = of_get_named_gpio(np, "chg-gpios", 0);
+	if (!gpio_is_valid(pdata->chg))
+		pdata->chg = -EINVAL;
+
+	pdata->flt = of_get_named_gpio(np, "flt-gpios", 0);
+	if (!gpio_is_valid(pdata->flt))
+		pdata->flt = -EINVAL;
+
+	pdata->usus = of_get_named_gpio(np, "usus-gpios", 0);
+	if (!gpio_is_valid(pdata->usus))
+		pdata->usus = -EINVAL;
+
+	pdata->dcm = of_get_named_gpio(np, "dcm-gpios", 0);
+	if (!gpio_is_valid(pdata->dcm))
+		pdata->dcm = -EINVAL;
+
+	pdata->dok = of_get_named_gpio(np, "dok-gpios", 0);
+	if (!gpio_is_valid(pdata->dok))
+		pdata->dok = -EINVAL;
+	else
+		pdata->dc_valid = true;
+
+	pdata->uok = of_get_named_gpio(np, "uok-gpios", 0);
+	if (!gpio_is_valid(pdata->uok))
+		pdata->uok = -EINVAL;
+	else
+		pdata->usb_valid = true;
+
+	return pdata;
+}
+
+static int max8903_setup_gpios(struct platform_device *pdev)
+{
+	struct max8903_data *data = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
 	struct max8903_pdata *pdata = pdev->dev.platform_data;
-	struct power_supply_config psy_cfg = {};
 	int ret = 0;
 	int gpio;
 	int ta_in = 0;
 	int usb_in = 0;
 
-	data = devm_kzalloc(dev, sizeof(struct max8903_data), GFP_KERNEL);
-	if (data == NULL) {
-		dev_err(dev, "Cannot allocate memory.\n");
-		return -ENOMEM;
-	}
-	memcpy(&data->pdata, pdata, sizeof(struct max8903_pdata));
-	data->dev = dev;
-	platform_set_drvdata(pdev, data);
-
-	if (pdata->dc_valid == false && pdata->usb_valid == false) {
-		dev_err(dev, "No valid power sources.\n");
-		return -EINVAL;
-	}
-
 	if (pdata->dc_valid) {
-		if (pdata->dok && gpio_is_valid(pdata->dok) &&
-				pdata->dcm && gpio_is_valid(pdata->dcm)) {
+		if (gpio_is_valid(pdata->dok)) {
+			ret = devm_gpio_request(dev, pdata->dok,
+						data->psy_desc.name);
+			if (ret) {
+				dev_err(dev,
+					"Failed GPIO request for dok: %d err %d\n",
+					pdata->dok, ret);
+				return ret;
+			}
+
 			gpio = pdata->dok; /* PULL_UPed Interrupt */
 			ta_in = gpio_get_value(gpio) ? 0 : 1;
-
-			gpio = pdata->dcm; /* Output */
-			gpio_set_value(gpio, ta_in);
 		} else {
-			dev_err(dev, "When DC is wired, DOK and DCM should"
-					" be wired as well.\n");
+			dev_err(dev, "When DC is wired, DOK should be wired as well.\n");
 			return -EINVAL;
 		}
-	} else {
-		if (pdata->dcm) {
-			if (gpio_is_valid(pdata->dcm))
-				gpio_set_value(pdata->dcm, 0);
-			else {
-				dev_err(dev, "Invalid pin: dcm.\n");
-				return -EINVAL;
-			}
+	}
+
+	if (gpio_is_valid(pdata->dcm)) {
+		ret = devm_gpio_request(dev, pdata->dcm, data->psy_desc.name);
+		if (ret) {
+			dev_err(dev,
+				"Failed GPIO request for dcm: %d err %d\n",
+				pdata->dcm, ret);
+			return ret;
 		}
+
+		gpio = pdata->dcm; /* Output */
+		gpio_set_value(gpio, ta_in);
 	}
 
 	if (pdata->usb_valid) {
-		if (pdata->uok && gpio_is_valid(pdata->uok)) {
+		if (gpio_is_valid(pdata->uok)) {
+			ret = devm_gpio_request(dev, pdata->uok,
+						data->psy_desc.name);
+			if (ret) {
+				dev_err(dev,
+					"Failed GPIO request for uok: %d err %d\n",
+					pdata->uok, ret);
+				return ret;
+			}
+
 			gpio = pdata->uok;
 			usb_in = gpio_get_value(gpio) ? 0 : 1;
 		} else {
@@ -239,33 +295,45 @@ static int max8903_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (pdata->cen) {
-		if (gpio_is_valid(pdata->cen)) {
-			gpio_set_value(pdata->cen, (ta_in || usb_in) ? 0 : 1);
-		} else {
-			dev_err(dev, "Invalid pin: cen.\n");
-			return -EINVAL;
+	if (gpio_is_valid(pdata->cen)) {
+		ret = devm_gpio_request(dev, pdata->cen, data->psy_desc.name);
+		if (ret) {
+			dev_err(dev,
+				"Failed GPIO request for cen: %d err %d\n",
+				pdata->cen, ret);
+			return ret;
 		}
+
+		gpio_set_value(pdata->cen, (ta_in || usb_in) ? 0 : 1);
 	}
 
-	if (pdata->chg) {
-		if (!gpio_is_valid(pdata->chg)) {
-			dev_err(dev, "Invalid pin: chg.\n");
-			return -EINVAL;
+	if (gpio_is_valid(pdata->chg)) {
+		ret = devm_gpio_request(dev, pdata->chg, data->psy_desc.name);
+		if (ret) {
+			dev_err(dev,
+				"Failed GPIO request for chg: %d err %d\n",
+				pdata->chg, ret);
+			return ret;
 		}
 	}
 
-	if (pdata->flt) {
-		if (!gpio_is_valid(pdata->flt)) {
-			dev_err(dev, "Invalid pin: flt.\n");
-			return -EINVAL;
+	if (gpio_is_valid(pdata->flt)) {
+		ret = devm_gpio_request(dev, pdata->flt, data->psy_desc.name);
+		if (ret) {
+			dev_err(dev,
+				"Failed GPIO request for flt: %d err %d\n",
+				pdata->flt, ret);
+			return ret;
 		}
 	}
 
-	if (pdata->usus) {
-		if (!gpio_is_valid(pdata->usus)) {
-			dev_err(dev, "Invalid pin: usus.\n");
-			return -EINVAL;
+	if (gpio_is_valid(pdata->usus)) {
+		ret = devm_gpio_request(dev, pdata->usus, data->psy_desc.name);
+		if (ret) {
+			dev_err(dev,
+				"Failed GPIO request for usus: %d err %d\n",
+				pdata->usus, ret);
+			return ret;
 		}
 	}
 
@@ -273,14 +341,52 @@ static int max8903_probe(struct platform_device *pdev)
 	data->ta_in = ta_in;
 	data->usb_in = usb_in;
 
+	return 0;
+}
+
+static int max8903_probe(struct platform_device *pdev)
+{
+	struct max8903_data *data;
+	struct device *dev = &pdev->dev;
+	struct max8903_pdata *pdata = pdev->dev.platform_data;
+	struct power_supply_config psy_cfg = {};
+	int ret = 0;
+
+	data = devm_kzalloc(dev, sizeof(struct max8903_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	if (IS_ENABLED(CONFIG_OF) && !pdata && dev->of_node)
+		pdata = max8903_parse_dt_data(dev);
+
+	if (!pdata) {
+		dev_err(dev, "No platform data.\n");
+		return -EINVAL;
+	}
+
+	pdev->dev.platform_data = pdata;
+	data->pdata = pdata;
+	data->dev = dev;
+	platform_set_drvdata(pdev, data);
+
+	if (pdata->dc_valid == false && pdata->usb_valid == false) {
+		dev_err(dev, "No valid power sources.\n");
+		return -EINVAL;
+	}
+
+	ret = max8903_setup_gpios(pdev);
+	if (ret)
+		return ret;
+
 	data->psy_desc.name = "max8903_charger";
-	data->psy_desc.type = (ta_in) ? POWER_SUPPLY_TYPE_MAINS :
-			((usb_in) ? POWER_SUPPLY_TYPE_USB :
+	data->psy_desc.type = (data->ta_in) ? POWER_SUPPLY_TYPE_MAINS :
+			((data->usb_in) ? POWER_SUPPLY_TYPE_USB :
 			 POWER_SUPPLY_TYPE_BATTERY);
 	data->psy_desc.get_property = max8903_get_property;
 	data->psy_desc.properties = max8903_charger_props;
 	data->psy_desc.num_properties = ARRAY_SIZE(max8903_charger_props);
 
+	psy_cfg.of_node = dev->of_node;
 	psy_cfg.drv_data = data;
 
 	data->psy = devm_power_supply_register(dev, &data->psy_desc, &psy_cfg);
@@ -315,7 +421,7 @@ static int max8903_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (pdata->flt) {
+	if (gpio_is_valid(pdata->flt)) {
 		ret = devm_request_threaded_irq(dev, gpio_to_irq(pdata->flt),
 					NULL, max8903_fault,
 					IRQF_TRIGGER_FALLING |
@@ -331,10 +437,17 @@ static int max8903_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id max8903_match_ids[] = {
+	{ .compatible = "maxim,max8903", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, max8903_match_ids);
+
 static struct platform_driver max8903_driver = {
 	.probe	= max8903_probe,
 	.driver = {
 		.name	= "max8903-charger",
+		.of_match_table = max8903_match_ids
 	},
 };
 
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index b13cd074c52a..a74d8ca383a1 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -491,8 +491,11 @@ int power_supply_get_property(struct power_supply *psy,
 			    enum power_supply_property psp,
 			    union power_supply_propval *val)
 {
-	if (atomic_read(&psy->use_cnt) <= 0)
+	if (atomic_read(&psy->use_cnt) <= 0) {
+		if (!psy->initialized)
+			return -EAGAIN;
 		return -ENODEV;
+	}
 
 	return psy->desc->get_property(psy, psp, val);
 }
@@ -785,6 +788,7 @@ __power_supply_register(struct device *parent,
 	 *    after calling power_supply_register()).
 	 */
 	atomic_inc(&psy->use_cnt);
+	psy->initialized = true;
 
 	queue_delayed_work(system_power_efficient_wq,
 			   &psy->deferred_register_work,
diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index 80fed98832f9..bcde8d13476a 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -83,7 +83,7 @@ static ssize_t power_supply_show_property(struct device *dev,
 			if (ret == -ENODATA)
 				dev_dbg(dev, "driver has no data for `%s' property\n",
 					attr->attr.name);
-			else if (ret != -ENODEV)
+			else if (ret != -ENODEV && ret != -EAGAIN)
 				dev_err(dev, "driver failed to report `%s' property: %zd\n",
 					attr->attr.name, ret);
 			return ret;
diff --git a/drivers/power/qcom_smbb.c b/drivers/power/qcom_smbb.c
index 5eb1e9e543e2..b5896ba2a602 100644
--- a/drivers/power/qcom_smbb.c
+++ b/drivers/power/qcom_smbb.c
@@ -34,6 +34,7 @@
 #include <linux/power_supply.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
+#include <linux/extcon.h>
 
 #define SMBB_CHG_VMAX		0x040
 #define SMBB_CHG_VSAFE		0x041
@@ -111,6 +112,7 @@ struct smbb_charger {
 	unsigned int revision;
 	unsigned int addr;
 	struct device *dev;
+	struct extcon_dev *edev;
 
 	bool dc_disabled;
 	bool jeita_ext_temp;
@@ -125,6 +127,11 @@ struct smbb_charger {
 	struct regmap *regmap;
 };
 
+static const unsigned int smbb_usb_extcon_cable[] = {
+	EXTCON_USB,
+	EXTCON_NONE,
+};
+
 static int smbb_vbat_weak_fn(unsigned int index)
 {
 	return 2100000 + index * 100000;
@@ -371,6 +378,8 @@ static irqreturn_t smbb_usb_valid_handler(int irq, void *_data)
 	struct smbb_charger *chg = _data;
 
 	smbb_set_line_flag(chg, irq, STATUS_USBIN_VALID);
+	extcon_set_cable_state_(chg->edev, EXTCON_USB,
+				chg->status & STATUS_USBIN_VALID);
 	power_supply_changed(chg->usb_psy);
 
 	return IRQ_HANDLED;
@@ -849,6 +858,18 @@ static int smbb_charger_probe(struct platform_device *pdev)
 		return PTR_ERR(chg->usb_psy);
 	}
 
+	chg->edev = devm_extcon_dev_allocate(&pdev->dev, smbb_usb_extcon_cable);
+	if (IS_ERR(chg->edev)) {
+		dev_err(&pdev->dev, "failed to allocate extcon device\n");
+		return -ENOMEM;
+	}
+
+	rc = devm_extcon_dev_register(&pdev->dev, chg->edev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "failed to register extcon device\n");
+		return rc;
+	}
+
 	if (!chg->dc_disabled) {
 		dc_cfg.drv_data = chg;
 		dc_cfg.supplied_to = smbb_bif;
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index 9bb2622c23bf..7053abced0bc 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -148,7 +148,8 @@ config POWER_RESET_XGENE
 
 config POWER_RESET_KEYSTONE
 	bool "Keystone reset driver"
-	depends on ARCH_KEYSTONE
+	depends on ARCH_KEYSTONE || COMPILE_TEST
+	depends on HAS_IOMEM
 	select MFD_SYSCON
 	help
 	  Reboot support for the KEYSTONE SoCs.
@@ -183,5 +184,19 @@ config POWER_RESET_ZX
 	help
 	  Reboot support for ZTE SoCs.
 
+config REBOOT_MODE
+	tristate
+
+config SYSCON_REBOOT_MODE
+	tristate "Generic SYSCON regmap reboot mode driver"
+	depends on OF
+	select REBOOT_MODE
+	select MFD_SYSCON
+	help
+	  Say y here will enable reboot mode driver. This will
+	  get reboot mode arguments and store it in SYSCON mapped
+	  register, then the bootloader can read it to take different
+	  action according to the mode.
+
 endif
 
diff --git a/drivers/power/reset/Makefile b/drivers/power/reset/Makefile
index ab7aa8614d1f..d6b2560d5c4a 100644
--- a/drivers/power/reset/Makefile
+++ b/drivers/power/reset/Makefile
@@ -21,3 +21,5 @@ obj-$(CONFIG_POWER_RESET_SYSCON) += syscon-reboot.o
 obj-$(CONFIG_POWER_RESET_SYSCON_POWEROFF) += syscon-poweroff.o
 obj-$(CONFIG_POWER_RESET_RMOBILE) += rmobile-reset.o
 obj-$(CONFIG_POWER_RESET_ZX) += zx-reboot.o
+obj-$(CONFIG_REBOOT_MODE) += reboot-mode.o
+obj-$(CONFIG_SYSCON_REBOOT_MODE) += syscon-reboot-mode.o
diff --git a/drivers/power/reset/reboot-mode.c b/drivers/power/reset/reboot-mode.c
new file mode 100644
index 000000000000..2dfbbce0f817
--- /dev/null
+++ b/drivers/power/reset/reboot-mode.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright (c) 2016, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/reboot.h>
+#include "reboot-mode.h"
+
+#define PREFIX "mode-"
+
+struct mode_info {
+	const char *mode;
+	u32 magic;
+	struct list_head list;
+};
+
+static unsigned int get_reboot_mode_magic(struct reboot_mode_driver *reboot,
+					  const char *cmd)
+{
+	const char *normal = "normal";
+	int magic = 0;
+	struct mode_info *info;
+
+	if (!cmd)
+		cmd = normal;
+
+	list_for_each_entry(info, &reboot->head, list) {
+		if (!strcmp(info->mode, cmd)) {
+			magic = info->magic;
+			break;
+		}
+	}
+
+	return magic;
+}
+
+static int reboot_mode_notify(struct notifier_block *this,
+			      unsigned long mode, void *cmd)
+{
+	struct reboot_mode_driver *reboot;
+	unsigned int magic;
+
+	reboot = container_of(this, struct reboot_mode_driver, reboot_notifier);
+	magic = get_reboot_mode_magic(reboot, cmd);
+	if (magic)
+		reboot->write(reboot, magic);
+
+	return NOTIFY_DONE;
+}
+
+/**
+ * reboot_mode_register - register a reboot mode driver
+ * @reboot: reboot mode driver
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int reboot_mode_register(struct reboot_mode_driver *reboot)
+{
+	struct mode_info *info;
+	struct property *prop;
+	struct device_node *np = reboot->dev->of_node;
+	size_t len = strlen(PREFIX);
+	int ret;
+
+	INIT_LIST_HEAD(&reboot->head);
+
+	for_each_property_of_node(np, prop) {
+		if (strncmp(prop->name, PREFIX, len))
+			continue;
+
+		info = devm_kzalloc(reboot->dev, sizeof(*info), GFP_KERNEL);
+		if (!info) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		if (of_property_read_u32(np, prop->name, &info->magic)) {
+			dev_err(reboot->dev, "reboot mode %s without magic number\n",
+				info->mode);
+			devm_kfree(reboot->dev, info);
+			continue;
+		}
+
+		info->mode = kstrdup_const(prop->name + len, GFP_KERNEL);
+		if (!info->mode) {
+			ret =  -ENOMEM;
+			goto error;
+		} else if (info->mode[0] == '\0') {
+			kfree_const(info->mode);
+			ret = -EINVAL;
+			dev_err(reboot->dev, "invalid mode name(%s): too short!\n",
+				prop->name);
+			goto error;
+		}
+
+		list_add_tail(&info->list, &reboot->head);
+	}
+
+	reboot->reboot_notifier.notifier_call = reboot_mode_notify;
+	register_reboot_notifier(&reboot->reboot_notifier);
+
+	return 0;
+
+error:
+	list_for_each_entry(info, &reboot->head, list)
+		kfree_const(info->mode);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(reboot_mode_register);
+
+/**
+ * reboot_mode_unregister - unregister a reboot mode driver
+ * @reboot: reboot mode driver
+ */
+int reboot_mode_unregister(struct reboot_mode_driver *reboot)
+{
+	struct mode_info *info;
+
+	unregister_reboot_notifier(&reboot->reboot_notifier);
+
+	list_for_each_entry(info, &reboot->head, list)
+		kfree_const(info->mode);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(reboot_mode_unregister);
+
+MODULE_AUTHOR("Andy Yan <andy.yan@rock-chips.com");
+MODULE_DESCRIPTION("System reboot mode core library");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/reset/reboot-mode.h b/drivers/power/reset/reboot-mode.h
new file mode 100644
index 000000000000..2491bb71f591
--- /dev/null
+++ b/drivers/power/reset/reboot-mode.h
@@ -0,0 +1,14 @@
+#ifndef __REBOOT_MODE_H__
+#define __REBOOT_MODE_H__
+
+struct reboot_mode_driver {
+	struct device *dev;
+	struct list_head head;
+	int (*write)(struct reboot_mode_driver *reboot, unsigned int magic);
+	struct notifier_block reboot_notifier;
+};
+
+int reboot_mode_register(struct reboot_mode_driver *reboot);
+int reboot_mode_unregister(struct reboot_mode_driver *reboot);
+
+#endif
diff --git a/drivers/power/reset/syscon-poweroff.c b/drivers/power/reset/syscon-poweroff.c
index 5560b0dbc180..b68338399e5e 100644
--- a/drivers/power/reset/syscon-poweroff.c
+++ b/drivers/power/reset/syscon-poweroff.c
@@ -30,7 +30,7 @@ static struct regmap *map;
 static u32 offset;
 static u32 mask;
 
-void syscon_poweroff(void)
+static void syscon_poweroff(void)
 {
 	/* Issue the poweroff */
 	regmap_write(map, offset, mask);
diff --git a/drivers/power/reset/syscon-reboot-mode.c b/drivers/power/reset/syscon-reboot-mode.c
new file mode 100644
index 000000000000..9e1cba5dd58e
--- /dev/null
+++ b/drivers/power/reset/syscon-reboot-mode.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright (c) 2016, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+#include "reboot-mode.h"
+
+struct syscon_reboot_mode {
+	struct regmap *map;
+	struct reboot_mode_driver reboot;
+	u32 offset;
+	u32 mask;
+};
+
+static int syscon_reboot_mode_write(struct reboot_mode_driver *reboot,
+				    unsigned int magic)
+{
+	struct syscon_reboot_mode *syscon_rbm;
+	int ret;
+
+	syscon_rbm = container_of(reboot, struct syscon_reboot_mode, reboot);
+
+	ret = regmap_update_bits(syscon_rbm->map, syscon_rbm->offset,
+				 syscon_rbm->mask, magic);
+	if (ret < 0)
+		dev_err(reboot->dev, "update reboot mode bits failed\n");
+
+	return ret;
+}
+
+static int syscon_reboot_mode_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct syscon_reboot_mode *syscon_rbm;
+
+	syscon_rbm = devm_kzalloc(&pdev->dev, sizeof(*syscon_rbm), GFP_KERNEL);
+	if (!syscon_rbm)
+		return -ENOMEM;
+
+	syscon_rbm->reboot.dev = &pdev->dev;
+	syscon_rbm->reboot.write = syscon_reboot_mode_write;
+	syscon_rbm->mask = 0xffffffff;
+
+	dev_set_drvdata(&pdev->dev, syscon_rbm);
+
+	syscon_rbm->map = syscon_node_to_regmap(pdev->dev.parent->of_node);
+	if (IS_ERR(syscon_rbm->map))
+		return PTR_ERR(syscon_rbm->map);
+
+	if (of_property_read_u32(pdev->dev.of_node, "offset",
+	    &syscon_rbm->offset))
+		return -EINVAL;
+
+	of_property_read_u32(pdev->dev.of_node, "mask", &syscon_rbm->mask);
+
+	ret = reboot_mode_register(&syscon_rbm->reboot);
+	if (ret)
+		dev_err(&pdev->dev, "can't register reboot mode\n");
+
+	return ret;
+}
+
+static int syscon_reboot_mode_remove(struct platform_device *pdev)
+{
+	struct syscon_reboot_mode *syscon_rbm = dev_get_drvdata(&pdev->dev);
+
+	return reboot_mode_unregister(&syscon_rbm->reboot);
+}
+
+static const struct of_device_id syscon_reboot_mode_of_match[] = {
+	{ .compatible = "syscon-reboot-mode" },
+	{}
+};
+
+static struct platform_driver syscon_reboot_mode_driver = {
+	.probe = syscon_reboot_mode_probe,
+	.remove = syscon_reboot_mode_remove,
+	.driver = {
+		.name = "syscon-reboot-mode",
+		.of_match_table = syscon_reboot_mode_of_match,
+	},
+};
+module_platform_driver(syscon_reboot_mode_driver);
+
+MODULE_AUTHOR("Andy Yan <andy.yan@rock-chips.com");
+MODULE_DESCRIPTION("SYSCON reboot mode driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 2e8f2be5b6f9..fbab29dfa793 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -336,14 +336,14 @@ static int release_zone(struct powercap_zone *power_zone)
 
 static int find_nr_power_limit(struct rapl_domain *rd)
 {
-	int i;
+	int i, nr_pl = 0;
 
 	for (i = 0; i < NR_POWER_LIMITS; i++) {
-		if (rd->rpl[i].name == NULL)
-			break;
+		if (rd->rpl[i].name)
+			nr_pl++;
 	}
 
-	return i;
+	return nr_pl;
 }
 
 static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
@@ -426,15 +426,38 @@ static const struct powercap_zone_ops zone_ops[] = {
 	},
 };
 
-static int set_power_limit(struct powercap_zone *power_zone, int id,
+
+/*
+ * Constraint index used by powercap can be different than power limit (PL)
+ * index in that some  PLs maybe missing due to non-existant MSRs. So we
+ * need to convert here by finding the valid PLs only (name populated).
+ */
+static int contraint_to_pl(struct rapl_domain *rd, int cid)
+{
+	int i, j;
+
+	for (i = 0, j = 0; i < NR_POWER_LIMITS; i++) {
+		if ((rd->rpl[i].name) && j++ == cid) {
+			pr_debug("%s: index %d\n", __func__, i);
+			return i;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int set_power_limit(struct powercap_zone *power_zone, int cid,
 			u64 power_limit)
 {
 	struct rapl_domain *rd;
 	struct rapl_package *rp;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
+
 	rp = rd->rp;
 
 	if (rd->state & DOMAIN_STATE_BIOS_LOCKED) {
@@ -461,16 +484,18 @@ set_exit:
 	return ret;
 }
 
-static int get_current_power_limit(struct powercap_zone *power_zone, int id,
+static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 					u64 *data)
 {
 	struct rapl_domain *rd;
 	u64 val;
 	int prim;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
 		prim = POWER_LIMIT1;
@@ -492,14 +517,17 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int id,
 	return ret;
 }
 
-static int set_time_window(struct powercap_zone *power_zone, int id,
+static int set_time_window(struct powercap_zone *power_zone, int cid,
 								u64 window)
 {
 	struct rapl_domain *rd;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
+
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
 		rapl_write_data_raw(rd, TIME_WINDOW1, window);
@@ -514,14 +542,17 @@ static int set_time_window(struct powercap_zone *power_zone, int id,
 	return ret;
 }
 
-static int get_time_window(struct powercap_zone *power_zone, int id, u64 *data)
+static int get_time_window(struct powercap_zone *power_zone, int cid, u64 *data)
 {
 	struct rapl_domain *rd;
 	u64 val;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
+
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
 		ret = rapl_read_data_raw(rd, TIME_WINDOW1, true, &val);
@@ -540,15 +571,17 @@ static int get_time_window(struct powercap_zone *power_zone, int id, u64 *data)
 	return ret;
 }
 
-static const char *get_constraint_name(struct powercap_zone *power_zone, int id)
+static const char *get_constraint_name(struct powercap_zone *power_zone, int cid)
 {
-	struct rapl_power_limit *rpl;
 	struct rapl_domain *rd;
+	int id;
 
 	rd = power_zone_to_rapl_domain(power_zone);
-	rpl = (struct rapl_power_limit *) &rd->rpl[id];
+	id = contraint_to_pl(rd, cid);
+	if (id >= 0)
+		return rd->rpl[id].name;
 
-	return rpl->name;
+	return NULL;
 }
 
 
@@ -1101,6 +1134,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	RAPL_CPU(INTEL_FAM6_SANDYBRIDGE_X,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_IVYBRIDGE,		rapl_defaults_core),
+	RAPL_CPU(INTEL_FAM6_IVYBRIDGE_X,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_HASWELL_CORE,	rapl_defaults_core),
 	RAPL_CPU(INTEL_FAM6_HASWELL_ULT,	rapl_defaults_core),
@@ -1123,6 +1157,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD1,	rapl_defaults_tng),
 	RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD2,	rapl_defaults_ann),
 	RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT,	rapl_defaults_core),
+	RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL,	rapl_defaults_hsw_server),
 	{}
@@ -1381,6 +1416,37 @@ static int rapl_check_domain(int cpu, int domain)
 	return 0;
 }
 
+
+/*
+ * Check if power limits are available. Two cases when they are not available:
+ * 1. Locked by BIOS, in this case we still provide read-only access so that
+ *    users can see what limit is set by the BIOS.
+ * 2. Some CPUs make some domains monitoring only which means PLx MSRs may not
+ *    exist at all. In this case, we do not show the contraints in powercap.
+ *
+ * Called after domains are detected and initialized.
+ */
+static void rapl_detect_powerlimit(struct rapl_domain *rd)
+{
+	u64 val64;
+	int i;
+
+	/* check if the domain is locked by BIOS, ignore if MSR doesn't exist */
+	if (!rapl_read_data_raw(rd, FW_LOCK, false, &val64)) {
+		if (val64) {
+			pr_info("RAPL package %d domain %s locked by BIOS\n",
+				rd->rp->id, rd->name);
+			rd->state |= DOMAIN_STATE_BIOS_LOCKED;
+		}
+	}
+	/* check if power limit MSRs exists, otherwise domain is monitoring only */
+	for (i = 0; i < NR_POWER_LIMITS; i++) {
+		int prim = rd->rpl[i].prim_id;
+		if (rapl_read_data_raw(rd, prim, false, &val64))
+			rd->rpl[i].name = NULL;
+	}
+}
+
 /* Detect active and valid domains for the given CPU, caller must
  * ensure the CPU belongs to the targeted package and CPU hotlug is disabled.
  */
@@ -1389,7 +1455,6 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 	int i;
 	int ret = 0;
 	struct rapl_domain *rd;
-	u64 locked;
 
 	for (i = 0; i < RAPL_DOMAIN_MAX; i++) {
 		/* use physical package id to read counters */
@@ -1400,7 +1465,7 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 	}
 	rp->nr_domains = bitmap_weight(&rp->domain_map,	RAPL_DOMAIN_MAX);
 	if (!rp->nr_domains) {
-		pr_err("no valid rapl domains found in package %d\n", rp->id);
+		pr_debug("no valid rapl domains found in package %d\n", rp->id);
 		ret = -ENODEV;
 		goto done;
 	}
@@ -1414,17 +1479,9 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 	}
 	rapl_init_domains(rp);
 
-	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
-		/* check if the domain is locked by BIOS */
-		ret = rapl_read_data_raw(rd, FW_LOCK, false, &locked);
-		if (ret)
-			return ret;
-		if (locked) {
-			pr_info("RAPL package %d domain %s locked by BIOS\n",
-				rp->id, rd->name);
-			rd->state |= DOMAIN_STATE_BIOS_LOCKED;
-		}
-	}
+	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++)
+		rapl_detect_powerlimit(rd);
+
 
 
 done:
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 144cbf5b3e5a..6c88e31c01f7 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -498,6 +498,15 @@ config REGULATOR_MT6311
 	  This driver supports the control of different power rails of device
 	  through regulator interface.
 
+config REGULATOR_MT6323
+	tristate "MediaTek MT6323 PMIC"
+	depends on MFD_MT6397
+	help
+	  Say y here to select this option to enable the power regulator of
+	  MediaTek MT6323 PMIC.
+	  This driver supports the control of different power rails of device
+	  through regulator interface.
+
 config REGULATOR_MT6397
 	tristate "MediaTek MT6397 PMIC"
 	depends on MFD_MT6397
@@ -543,12 +552,12 @@ config REGULATOR_PCF50633
 	 on PCF50633
 
 config REGULATOR_PFUZE100
-	tristate "Freescale PFUZE100/PFUZE200 regulator driver"
+	tristate "Freescale PFUZE100/200/3000 regulator driver"
 	depends on I2C
 	select REGMAP_I2C
 	help
 	  Say y here to support the regulators found on the Freescale
-	  PFUZE100/PFUZE200 PMIC.
+	  PFUZE100/200/3000 PMIC.
 
 config REGULATOR_PV88060
 	tristate "Powerventure Semiconductor PV88060 regulator"
@@ -636,10 +645,11 @@ config REGULATOR_RK808
 	  outputs which can be controlled by i2c communication.
 
 config REGULATOR_RN5T618
-	tristate "Ricoh RN5T618 voltage regulators"
+	tristate "Ricoh RN5T567/618 voltage regulators"
 	depends on MFD_RN5T618
 	help
-	  Say y here to support the regulators found on Ricoh RN5T618 PMIC.
+	  Say y here to support the regulators found on Ricoh RN5T567 or
+	  RN5T618 PMIC.
 
 config REGULATOR_RT5033
 	tristate "Richtek RT5033 Regulators"
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 85a1d44a3939..f3da9eea9ab6 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o
 obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o
 obj-$(CONFIG_REGULATOR_MC13XXX_CORE) +=  mc13xxx-regulator-core.o
 obj-$(CONFIG_REGULATOR_MT6311) += mt6311-regulator.o
+obj-$(CONFIG_REGULATOR_MT6323)	+= mt6323-regulator.o
 obj-$(CONFIG_REGULATOR_MT6397)	+= mt6397-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_SMD_RPM) += qcom_smd-regulator.o
diff --git a/drivers/regulator/act8865-regulator.c b/drivers/regulator/act8865-regulator.c
index a1cd0d4f8257..7652477e6a9d 100644
--- a/drivers/regulator/act8865-regulator.c
+++ b/drivers/regulator/act8865-regulator.c
@@ -395,12 +395,6 @@ static int act8865_pdata_from_dt(struct device *dev,
 	struct act8865_regulator_data *regulator;
 	struct of_regulator_match *matches;
 
-	np = of_get_child_by_name(dev->of_node, "regulators");
-	if (!np) {
-		dev_err(dev, "missing 'regulators' subnode in DT\n");
-		return -EINVAL;
-	}
-
 	switch (type) {
 	case ACT8600:
 		matches = act8600_matches;
@@ -419,6 +413,12 @@ static int act8865_pdata_from_dt(struct device *dev,
 		return -EINVAL;
 	}
 
+	np = of_get_child_by_name(dev->of_node, "regulators");
+	if (!np) {
+		dev_err(dev, "missing 'regulators' subnode in DT\n");
+		return -EINVAL;
+	}
+
 	matched = of_regulator_match(dev, np, matches, num_matches);
 	of_node_put(np);
 	if (matched <= 0)
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index 514a5e8fdbab..6d9ac76a772f 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -36,6 +36,8 @@
 
 #define AXP20X_FREQ_DCDC_MASK		0x0f
 
+#define AXP22X_MISC_N_VBUSEN_FUNC	BIT(4)
+
 #define AXP_DESC_IO(_family, _id, _match, _supply, _min, _max, _step, _vreg,	\
 		    _vmask, _ereg, _emask, _enable_val, _disable_val)		\
 	[_family##_##_id] = {							\
@@ -230,6 +232,73 @@ static const struct regulator_desc axp22x_regulators[] = {
 	AXP_DESC_FIXED(AXP22X, RTC_LDO, "rtc_ldo", "ips", 3000),
 };
 
+static const struct regulator_desc axp22x_drivevbus_regulator = {
+	.name		= "drivevbus",
+	.supply_name	= "drivevbus",
+	.of_match	= of_match_ptr("drivevbus"),
+	.regulators_node = of_match_ptr("regulators"),
+	.type		= REGULATOR_VOLTAGE,
+	.owner		= THIS_MODULE,
+	.enable_reg	= AXP20X_VBUS_IPSOUT_MGMT,
+	.enable_mask	= BIT(2),
+	.ops		= &axp20x_ops_sw,
+};
+
+static const struct regulator_linear_range axp809_dcdc4_ranges[] = {
+	REGULATOR_LINEAR_RANGE(600000, 0x0, 0x2f, 20000),
+	REGULATOR_LINEAR_RANGE(1800000, 0x30, 0x38, 100000),
+};
+
+static const struct regulator_linear_range axp809_dldo1_ranges[] = {
+	REGULATOR_LINEAR_RANGE(700000, 0x0, 0x1a, 100000),
+	REGULATOR_LINEAR_RANGE(3400000, 0x1b, 0x1f, 200000),
+};
+
+static const struct regulator_desc axp809_regulators[] = {
+	AXP_DESC(AXP809, DCDC1, "dcdc1", "vin1", 1600, 3400, 100,
+		 AXP22X_DCDC1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(1)),
+	AXP_DESC(AXP809, DCDC2, "dcdc2", "vin2", 600, 1540, 20,
+		 AXP22X_DCDC2_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(2)),
+	AXP_DESC(AXP809, DCDC3, "dcdc3", "vin3", 600, 1860, 20,
+		 AXP22X_DCDC3_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(3)),
+	AXP_DESC_RANGES(AXP809, DCDC4, "dcdc4", "vin4", axp809_dcdc4_ranges,
+			57, AXP22X_DCDC4_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1,
+			BIT(4)),
+	AXP_DESC(AXP809, DCDC5, "dcdc5", "vin5", 1000, 2550, 50,
+		 AXP22X_DCDC5_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(5)),
+	/* secondary switchable output of DCDC1 */
+	AXP_DESC_SW(AXP809, DC1SW, "dc1sw", NULL, AXP22X_PWR_OUT_CTRL2,
+		    BIT(7)),
+	/* LDO regulator internally chained to DCDC5 */
+	AXP_DESC(AXP809, DC5LDO, "dc5ldo", NULL, 700, 1400, 100,
+		 AXP22X_DC5LDO_V_OUT, 0x7, AXP22X_PWR_OUT_CTRL1, BIT(0)),
+	AXP_DESC(AXP809, ALDO1, "aldo1", "aldoin", 700, 3300, 100,
+		 AXP22X_ALDO1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(6)),
+	AXP_DESC(AXP809, ALDO2, "aldo2", "aldoin", 700, 3300, 100,
+		 AXP22X_ALDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(7)),
+	AXP_DESC(AXP809, ALDO3, "aldo3", "aldoin", 700, 3300, 100,
+		 AXP22X_ALDO3_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(5)),
+	AXP_DESC_RANGES(AXP809, DLDO1, "dldo1", "dldoin", axp809_dldo1_ranges,
+			32, AXP22X_DLDO1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2,
+			BIT(3)),
+	AXP_DESC(AXP809, DLDO2, "dldo2", "dldoin", 700, 3300, 100,
+		 AXP22X_DLDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(4)),
+	AXP_DESC(AXP809, ELDO1, "eldo1", "eldoin", 700, 3300, 100,
+		 AXP22X_ELDO1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(0)),
+	AXP_DESC(AXP809, ELDO2, "eldo2", "eldoin", 700, 3300, 100,
+		 AXP22X_ELDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(1)),
+	AXP_DESC(AXP809, ELDO3, "eldo3", "eldoin", 700, 3300, 100,
+		 AXP22X_ELDO3_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(2)),
+	AXP_DESC_IO(AXP809, LDO_IO0, "ldo_io0", "ips", 700, 3300, 100,
+		    AXP22X_LDO_IO0_V_OUT, 0x1f, AXP20X_GPIO0_CTRL, 0x07,
+		    AXP22X_IO_ENABLED, AXP22X_IO_DISABLED),
+	AXP_DESC_IO(AXP809, LDO_IO1, "ldo_io1", "ips", 700, 3300, 100,
+		    AXP22X_LDO_IO1_V_OUT, 0x1f, AXP20X_GPIO1_CTRL, 0x07,
+		    AXP22X_IO_ENABLED, AXP22X_IO_DISABLED),
+	AXP_DESC_FIXED(AXP809, RTC_LDO, "rtc_ldo", "ips", 1800),
+	AXP_DESC_SW(AXP809, SW, "sw", "swin", AXP22X_PWR_OUT_CTRL2, BIT(6)),
+};
+
 static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq)
 {
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
@@ -245,6 +314,7 @@ static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq)
 		break;
 	case AXP221_ID:
 	case AXP223_ID:
+	case AXP809_ID:
 		min = 1800;
 		max = 4050;
 		def = 3000;
@@ -324,6 +394,7 @@ static int axp20x_set_dcdc_workmode(struct regulator_dev *rdev, int id, u32 work
 
 	case AXP221_ID:
 	case AXP223_ID:
+	case AXP809_ID:
 		if (id < AXP22X_DCDC1 || id > AXP22X_DCDC5)
 			return -EINVAL;
 
@@ -352,8 +423,9 @@ static int axp20x_regulator_probe(struct platform_device *pdev)
 	};
 	int ret, i, nregulators;
 	u32 workmode;
-	const char *axp22x_dc1_name = axp22x_regulators[AXP22X_DCDC1].name;
-	const char *axp22x_dc5_name = axp22x_regulators[AXP22X_DCDC5].name;
+	const char *dcdc1_name = axp22x_regulators[AXP22X_DCDC1].name;
+	const char *dcdc5_name = axp22x_regulators[AXP22X_DCDC5].name;
+	bool drivevbus = false;
 
 	switch (axp20x->variant) {
 	case AXP202_ID:
@@ -365,6 +437,12 @@ static int axp20x_regulator_probe(struct platform_device *pdev)
 	case AXP223_ID:
 		regulators = axp22x_regulators;
 		nregulators = AXP22X_REG_ID_MAX;
+		drivevbus = of_property_read_bool(pdev->dev.parent->of_node,
+						  "x-powers,drive-vbus-en");
+		break;
+	case AXP809_ID:
+		regulators = axp809_regulators;
+		nregulators = AXP809_REG_ID_MAX;
 		break;
 	default:
 		dev_err(&pdev->dev, "Unsupported AXP variant: %ld\n",
@@ -388,22 +466,22 @@ static int axp20x_regulator_probe(struct platform_device *pdev)
 		 * part of this loop to see where we save the DT defined
 		 * name.
 		 */
-		if (regulators == axp22x_regulators) {
-			if (i == AXP22X_DC1SW) {
-				new_desc = devm_kzalloc(&pdev->dev,
-							sizeof(*desc),
-							GFP_KERNEL);
-				*new_desc = regulators[i];
-				new_desc->supply_name = axp22x_dc1_name;
-				desc = new_desc;
-			} else if (i == AXP22X_DC5LDO) {
-				new_desc = devm_kzalloc(&pdev->dev,
-							sizeof(*desc),
-							GFP_KERNEL);
-				*new_desc = regulators[i];
-				new_desc->supply_name = axp22x_dc5_name;
-				desc = new_desc;
-			}
+		if ((regulators == axp22x_regulators && i == AXP22X_DC1SW) ||
+		    (regulators == axp809_regulators && i == AXP809_DC1SW)) {
+			new_desc = devm_kzalloc(&pdev->dev, sizeof(*desc),
+						GFP_KERNEL);
+			*new_desc = regulators[i];
+			new_desc->supply_name = dcdc1_name;
+			desc = new_desc;
+		}
+
+		if ((regulators == axp22x_regulators && i == AXP22X_DC5LDO) ||
+		    (regulators == axp809_regulators && i == AXP809_DC5LDO)) {
+			new_desc = devm_kzalloc(&pdev->dev, sizeof(*desc),
+						GFP_KERNEL);
+			*new_desc = regulators[i];
+			new_desc->supply_name = dcdc5_name;
+			desc = new_desc;
 		}
 
 		rdev = devm_regulator_register(&pdev->dev, desc, &config);
@@ -426,16 +504,29 @@ static int axp20x_regulator_probe(struct platform_device *pdev)
 		/*
 		 * Save AXP22X DCDC1 / DCDC5 regulator names for later.
 		 */
-		if (regulators == axp22x_regulators) {
-			/* Can we use rdev->constraints->name instead? */
-			if (i == AXP22X_DCDC1)
-				of_property_read_string(rdev->dev.of_node,
-							"regulator-name",
-							&axp22x_dc1_name);
-			else if (i == AXP22X_DCDC5)
-				of_property_read_string(rdev->dev.of_node,
-							"regulator-name",
-							&axp22x_dc5_name);
+		if ((regulators == axp22x_regulators && i == AXP22X_DCDC1) ||
+		    (regulators == axp809_regulators && i == AXP809_DCDC1))
+			of_property_read_string(rdev->dev.of_node,
+						"regulator-name",
+						&dcdc1_name);
+
+		if ((regulators == axp22x_regulators && i == AXP22X_DCDC5) ||
+		    (regulators == axp809_regulators && i == AXP809_DCDC5))
+			of_property_read_string(rdev->dev.of_node,
+						"regulator-name",
+						&dcdc5_name);
+	}
+
+	if (drivevbus) {
+		/* Change N_VBUSEN sense pin to DRIVEVBUS output pin */
+		regmap_update_bits(axp20x->regmap, AXP20X_OVER_TMP,
+				   AXP22X_MISC_N_VBUSEN_FUNC, 0);
+		rdev = devm_regulator_register(&pdev->dev,
+					       &axp22x_drivevbus_regulator,
+					       &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "Failed to register drivevbus\n");
+			return PTR_ERR(rdev);
 		}
 	}
 
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index ec8184d53f13..db320e8fa865 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2509,33 +2509,6 @@ int regulator_is_enabled(struct regulator *regulator)
 EXPORT_SYMBOL_GPL(regulator_is_enabled);
 
 /**
- * regulator_can_change_voltage - check if regulator can change voltage
- * @regulator: regulator source
- *
- * Returns positive if the regulator driver backing the source/client
- * can change its voltage, false otherwise. Useful for detecting fixed
- * or dummy regulators and disabling voltage change logic in the client
- * driver.
- */
-int regulator_can_change_voltage(struct regulator *regulator)
-{
-	struct regulator_dev	*rdev = regulator->rdev;
-
-	if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) {
-		if (rdev->desc->n_voltages - rdev->desc->linear_min_sel > 1)
-			return 1;
-
-		if (rdev->desc->continuous_voltage_range &&
-		    rdev->constraints->min_uV && rdev->constraints->max_uV &&
-		    rdev->constraints->min_uV != rdev->constraints->max_uV)
-			return 1;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(regulator_can_change_voltage);
-
-/**
  * regulator_count_voltages - count regulator_list_voltage() selectors
  * @regulator: regulator source
  *
diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c
index 1050cb77561a..9ececfef42d6 100644
--- a/drivers/regulator/da9052-regulator.c
+++ b/drivers/regulator/da9052-regulator.c
@@ -333,7 +333,7 @@ static const struct regulator_ops da9052_ldo_ops = {
 static struct da9052_regulator_info da9052_regulator_info[] = {
 	DA9052_DCDC(BUCK1, 25, 500, 2075, 6, 6, DA9052_SUPPLY_VBCOREGO),
 	DA9052_DCDC(BUCK2, 25, 500, 2075, 6, 6, DA9052_SUPPLY_VBPROGO),
-	DA9052_DCDC(BUCK3, 25, 925, 2500, 6, 6, DA9052_SUPPLY_VBMEMGO),
+	DA9052_DCDC(BUCK3, 25, 950, 2525, 6, 6, DA9052_SUPPLY_VBMEMGO),
 	DA9052_DCDC(BUCK4, 50, 1800, 3600, 5, 6, 0),
 	DA9052_LDO(LDO1, 50, 600, 1800, 5, 6, 0),
 	DA9052_LDO(LDO2, 25, 600, 1800, 6, 6, DA9052_SUPPLY_VLDO2GO),
@@ -350,8 +350,8 @@ static struct da9052_regulator_info da9052_regulator_info[] = {
 static struct da9052_regulator_info da9053_regulator_info[] = {
 	DA9052_DCDC(BUCK1, 25, 500, 2075, 6, 6, DA9052_SUPPLY_VBCOREGO),
 	DA9052_DCDC(BUCK2, 25, 500, 2075, 6, 6, DA9052_SUPPLY_VBPROGO),
-	DA9052_DCDC(BUCK3, 25, 925, 2500, 6, 6, DA9052_SUPPLY_VBMEMGO),
-	DA9052_DCDC(BUCK4, 25, 925, 2500, 6, 6, 0),
+	DA9052_DCDC(BUCK3, 25, 950, 2525, 6, 6, DA9052_SUPPLY_VBMEMGO),
+	DA9052_DCDC(BUCK4, 25, 950, 2525, 6, 6, 0),
 	DA9052_LDO(LDO1, 50, 600, 1800, 5, 6, 0),
 	DA9052_LDO(LDO2, 25, 600, 1800, 6, 6, DA9052_SUPPLY_VLDO2GO),
 	DA9052_LDO(LDO3, 25, 1725, 3300, 6, 6, DA9052_SUPPLY_VLDO3GO),
diff --git a/drivers/regulator/da9210-regulator.c b/drivers/regulator/da9210-regulator.c
index 01c0e3709b66..d0496d6b0934 100644
--- a/drivers/regulator/da9210-regulator.c
+++ b/drivers/regulator/da9210-regulator.c
@@ -21,12 +21,11 @@
 #include <linux/err.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/slab.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
+#include <linux/of_device.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regmap.h>
 
@@ -179,6 +178,13 @@ error_i2c:
 /*
  * I2C driver interface functions
  */
+
+static const struct of_device_id da9210_dt_ids[] = {
+	{ .compatible = "dlg,da9210", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, da9210_dt_ids);
+
 static int da9210_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
 {
@@ -188,6 +194,16 @@ static int da9210_i2c_probe(struct i2c_client *i2c,
 	struct regulator_dev *rdev = NULL;
 	struct regulator_config config = { };
 	int error;
+	const struct of_device_id *match;
+
+	if (i2c->dev.of_node && !pdata) {
+		match = of_match_device(of_match_ptr(da9210_dt_ids),
+						&i2c->dev);
+		if (!match) {
+			dev_err(&i2c->dev, "Error: No device match found\n");
+			return -ENODEV;
+		}
+	}
 
 	chip = devm_kzalloc(&i2c->dev, sizeof(struct da9210), GFP_KERNEL);
 	if (!chip)
@@ -264,6 +280,7 @@ MODULE_DEVICE_TABLE(i2c, da9210_i2c_id);
 static struct i2c_driver da9210_regulator_driver = {
 	.driver = {
 		.name = "da9210",
+		.of_match_table = of_match_ptr(da9210_dt_ids),
 	},
 	.probe = da9210_i2c_probe,
 	.id_table = da9210_i2c_id,
diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index 236abf473db5..aa47280efd32 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -1,5 +1,6 @@
 /*
- * da9211-regulator.c - Regulator device driver for DA9211/DA9213/DA9215
+ * da9211-regulator.c - Regulator device driver for DA9211/DA9212
+ * /DA9213/DA9214/DA9215
  * Copyright (C) 2015  Dialog Semiconductor Ltd.
  *
  * This library is free software; you can redistribute it and/or
@@ -493,7 +494,9 @@ static int da9211_i2c_probe(struct i2c_client *i2c,
 
 static const struct i2c_device_id da9211_i2c_id[] = {
 	{"da9211", DA9211},
+	{"da9212", DA9212},
 	{"da9213", DA9213},
+	{"da9214", DA9214},
 	{"da9215", DA9215},
 	{},
 };
@@ -502,8 +505,10 @@ MODULE_DEVICE_TABLE(i2c, da9211_i2c_id);
 #ifdef CONFIG_OF
 static const struct of_device_id da9211_dt_ids[] = {
 	{ .compatible = "dlg,da9211", .data = &da9211_i2c_id[0] },
-	{ .compatible = "dlg,da9213", .data = &da9211_i2c_id[1] },
-	{ .compatible = "dlg,da9215", .data = &da9211_i2c_id[2] },
+	{ .compatible = "dlg,da9212", .data = &da9211_i2c_id[1] },
+	{ .compatible = "dlg,da9213", .data = &da9211_i2c_id[2] },
+	{ .compatible = "dlg,da9214", .data = &da9211_i2c_id[3] },
+	{ .compatible = "dlg,da9215", .data = &da9211_i2c_id[4] },
 	{},
 };
 MODULE_DEVICE_TABLE(of, da9211_dt_ids);
@@ -521,5 +526,5 @@ static struct i2c_driver da9211_regulator_driver = {
 module_i2c_driver(da9211_regulator_driver);
 
 MODULE_AUTHOR("James Ban <James.Ban.opensource@diasemi.com>");
-MODULE_DESCRIPTION("Regulator device driver for Dialog DA9211/DA9213/DA9215");
+MODULE_DESCRIPTION("DA9211/DA9212/DA9213/DA9214/DA9215 regulator driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/regulator/da9211-regulator.h b/drivers/regulator/da9211-regulator.h
index d6ad96fc64d3..b841bbf330cc 100644
--- a/drivers/regulator/da9211-regulator.h
+++ b/drivers/regulator/da9211-regulator.h
@@ -1,5 +1,6 @@
 /*
- * da9211-regulator.h - Regulator definitions for DA9211/DA9213/DA9215
+ * da9211-regulator.h - Regulator definitions for DA9211/DA9212
+ * /DA9213/DA9214/DA9215
  * Copyright (C) 2015  Dialog Semiconductor Ltd.
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index ff62d69ba0be..988a7472c2ab 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -79,18 +79,8 @@ of_get_fixed_voltage_config(struct device *dev,
 		config->enabled_at_boot = true;
 
 	config->gpio = of_get_named_gpio(np, "gpio", 0);
-	/*
-	 * of_get_named_gpio() currently returns ENODEV rather than
-	 * EPROBE_DEFER. This code attempts to be compatible with both
-	 * for now; the ENODEV check can be removed once the API is fixed.
-	 * of_get_named_gpio() doesn't differentiate between a missing
-	 * property (which would be fine here, since the GPIO is optional)
-	 * and some other error. Patches have been posted for both issues.
-	 * Once they are check in, we should replace this with:
-	 * if (config->gpio < 0 && config->gpio != -ENOENT)
-	 */
-	if ((config->gpio == -ENODEV) || (config->gpio == -EPROBE_DEFER))
-		return ERR_PTR(-EPROBE_DEFER);
+	if ((config->gpio < 0) && (config->gpio != -ENOENT))
+		return ERR_PTR(config->gpio);
 
 	of_property_read_u32(np, "startup-delay-us", &config->startup_delay);
 
diff --git a/drivers/regulator/lp873x-regulator.c b/drivers/regulator/lp873x-regulator.c
index b4ffd113ba21..e504b9148226 100644
--- a/drivers/regulator/lp873x-regulator.c
+++ b/drivers/regulator/lp873x-regulator.c
@@ -20,7 +20,7 @@
 #include <linux/mfd/lp873x.h>
 
 #define LP873X_REGULATOR(_name, _id, _of, _ops, _n, _vr, _vm, _er, _em, \
-			 _delay, _lr, _nlr, _cr)			\
+			 _delay, _lr, _cr)				\
 	[_id] = {							\
 		.desc = {						\
 			.name			= _name,		\
@@ -37,7 +37,7 @@
 			.enable_mask		= _em,			\
 			.ramp_delay		= _delay,		\
 			.linear_ranges		= _lr,			\
-			.n_linear_ranges	= _nlr,			\
+			.n_linear_ranges	= ARRAY_SIZE(_lr),	\
 		},							\
 		.ctrl2_reg = _cr,					\
 	}
@@ -175,22 +175,20 @@ static const struct lp873x_regulator regulators[] = {
 			 256, LP873X_REG_BUCK0_VOUT,
 			 LP873X_BUCK0_VOUT_BUCK0_VSET, LP873X_REG_BUCK0_CTRL_1,
 			 LP873X_BUCK0_CTRL_1_BUCK0_EN, 10000,
-			 buck0_buck1_ranges, 4, LP873X_REG_BUCK0_CTRL_2),
+			 buck0_buck1_ranges, LP873X_REG_BUCK0_CTRL_2),
 	LP873X_REGULATOR("BUCK1", LP873X_BUCK_1, "buck1", lp873x_buck01_ops,
 			 256, LP873X_REG_BUCK1_VOUT,
 			 LP873X_BUCK1_VOUT_BUCK1_VSET, LP873X_REG_BUCK1_CTRL_1,
 			 LP873X_BUCK1_CTRL_1_BUCK1_EN, 10000,
-			 buck0_buck1_ranges, 4, LP873X_REG_BUCK1_CTRL_2),
+			 buck0_buck1_ranges, LP873X_REG_BUCK1_CTRL_2),
 	LP873X_REGULATOR("LDO0", LP873X_LDO_0, "ldo0", lp873x_ldo01_ops, 26,
 			 LP873X_REG_LDO0_VOUT, LP873X_LDO0_VOUT_LDO0_VSET,
 			 LP873X_REG_LDO0_CTRL,
-			 LP873X_LDO0_CTRL_LDO0_EN, 0, ldo0_ldo1_ranges, 1,
-			 0xFF),
+			 LP873X_LDO0_CTRL_LDO0_EN, 0, ldo0_ldo1_ranges, 0xFF),
 	LP873X_REGULATOR("LDO1", LP873X_LDO_1, "ldo1", lp873x_ldo01_ops, 26,
 			 LP873X_REG_LDO1_VOUT, LP873X_LDO1_VOUT_LDO1_VSET,
 			 LP873X_REG_LDO1_CTRL,
-			 LP873X_LDO1_CTRL_LDO1_EN, 0, ldo0_ldo1_ranges, 1,
-			 0xFF),
+			 LP873X_LDO1_CTRL_LDO1_EN, 0, ldo0_ldo1_ranges, 0xFF),
 };
 
 static int lp873x_regulator_probe(struct platform_device *pdev)
diff --git a/drivers/regulator/max8973-regulator.c b/drivers/regulator/max8973-regulator.c
index 08d2f13eca00..3958f50c5975 100644
--- a/drivers/regulator/max8973-regulator.c
+++ b/drivers/regulator/max8973-regulator.c
@@ -271,22 +271,18 @@ static int max8973_set_ramp_delay(struct regulator_dev *rdev,
 	struct max8973_chip *max = rdev_get_drvdata(rdev);
 	unsigned int control;
 	int ret;
-	int ret_val;
 
 	/* Set ramp delay */
-	if (ramp_delay < 25000) {
+	if (ramp_delay <= 12000)
 		control = MAX8973_RAMP_12mV_PER_US;
-		ret_val = 12000;
-	} else if (ramp_delay < 50000) {
+	else if (ramp_delay <= 25000)
 		control = MAX8973_RAMP_25mV_PER_US;
-		ret_val = 25000;
-	} else if (ramp_delay < 200000) {
+	else if (ramp_delay <= 50000)
 		control = MAX8973_RAMP_50mV_PER_US;
-		ret_val = 50000;
-	} else {
+	else if (ramp_delay <= 200000)
 		control = MAX8973_RAMP_200mV_PER_US;
-		ret_val = 200000;
-	}
+	else
+		return -EINVAL;
 
 	ret = regmap_update_bits(max->regmap, MAX8973_CONTROL1,
 			MAX8973_RAMP_MASK, control);
diff --git a/drivers/regulator/mt6323-regulator.c b/drivers/regulator/mt6323-regulator.c
new file mode 100644
index 000000000000..b7b9670f0979
--- /dev/null
+++ b/drivers/regulator/mt6323-regulator.c
@@ -0,0 +1,425 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Chen Zhong <chen.zhong@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/mt6397/core.h>
+#include <linux/mfd/mt6323/registers.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/mt6323-regulator.h>
+#include <linux/regulator/of_regulator.h>
+
+#define MT6323_LDO_MODE_NORMAL	0
+#define MT6323_LDO_MODE_LP	1
+
+/*
+ * MT6323 regulators' information
+ *
+ * @desc: standard fields of regulator description.
+ * @qi: Mask for query enable signal status of regulators
+ * @vselon_reg: Register sections for hardware control mode of bucks
+ * @vselctrl_reg: Register for controlling the buck control mode.
+ * @vselctrl_mask: Mask for query buck's voltage control mode.
+ */
+struct mt6323_regulator_info {
+	struct regulator_desc desc;
+	u32 qi;
+	u32 vselon_reg;
+	u32 vselctrl_reg;
+	u32 vselctrl_mask;
+	u32 modeset_reg;
+	u32 modeset_mask;
+};
+
+#define MT6323_BUCK(match, vreg, min, max, step, volt_ranges, enreg,	\
+		vosel, vosel_mask, voselon, vosel_ctrl)			\
+[MT6323_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6323_volt_range_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6323_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = (max - min)/step + 1,			\
+		.linear_ranges = volt_ranges,				\
+		.n_linear_ranges = ARRAY_SIZE(volt_ranges),		\
+		.vsel_reg = vosel,					\
+		.vsel_mask = vosel_mask,				\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(0),					\
+	},								\
+	.qi = BIT(13),							\
+	.vselon_reg = voselon,						\
+	.vselctrl_reg = vosel_ctrl,					\
+	.vselctrl_mask = BIT(1),					\
+}
+
+#define MT6323_LDO(match, vreg, ldo_volt_table, enreg, enbit, vosel,	\
+		vosel_mask, _modeset_reg, _modeset_mask)		\
+[MT6323_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6323_volt_table_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6323_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = ARRAY_SIZE(ldo_volt_table),		\
+		.volt_table = ldo_volt_table,				\
+		.vsel_reg = vosel,					\
+		.vsel_mask = vosel_mask,				\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(enbit),				\
+	},								\
+	.qi = BIT(15),							\
+	.modeset_reg = _modeset_reg,					\
+	.modeset_mask = _modeset_mask,					\
+}
+
+#define MT6323_REG_FIXED(match, vreg, enreg, enbit, volt,		\
+		_modeset_reg, _modeset_mask)				\
+[MT6323_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6323_volt_fixed_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6323_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = 1,					\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(enbit),				\
+		.min_uV = volt,						\
+	},								\
+	.qi = BIT(15),							\
+	.modeset_reg = _modeset_reg,					\
+	.modeset_mask = _modeset_mask,					\
+}
+
+static const struct regulator_linear_range buck_volt_range1[] = {
+	REGULATOR_LINEAR_RANGE(700000, 0, 0x7f, 6250),
+};
+
+static const struct regulator_linear_range buck_volt_range2[] = {
+	REGULATOR_LINEAR_RANGE(1400000, 0, 0x7f, 12500),
+};
+
+static const struct regulator_linear_range buck_volt_range3[] = {
+	REGULATOR_LINEAR_RANGE(500000, 0, 0x3f, 50000),
+};
+
+static const u32 ldo_volt_table1[] = {
+	3300000, 3400000, 3500000, 3600000,
+};
+
+static const u32 ldo_volt_table2[] = {
+	1500000, 1800000, 2500000, 2800000,
+};
+
+static const u32 ldo_volt_table3[] = {
+	1800000, 3300000,
+};
+
+static const u32 ldo_volt_table4[] = {
+	3000000, 3300000,
+};
+
+static const u32 ldo_volt_table5[] = {
+	1200000, 1300000, 1500000, 1800000, 2000000, 2800000, 3000000, 3300000,
+};
+
+static const u32 ldo_volt_table6[] = {
+	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 2000000,
+};
+
+static const u32 ldo_volt_table7[] = {
+	1200000, 1300000, 1500000, 1800000,
+};
+
+static const u32 ldo_volt_table8[] = {
+	1800000, 3000000,
+};
+
+static const u32 ldo_volt_table9[] = {
+	1200000, 1350000, 1500000, 1800000,
+};
+
+static const u32 ldo_volt_table10[] = {
+	1200000, 1300000, 1500000, 1800000,
+};
+
+static int mt6323_get_status(struct regulator_dev *rdev)
+{
+	int ret;
+	u32 regval;
+	struct mt6323_regulator_info *info = rdev_get_drvdata(rdev);
+
+	ret = regmap_read(rdev->regmap, info->desc.enable_reg, &regval);
+	if (ret != 0) {
+		dev_err(&rdev->dev, "Failed to get enable reg: %d\n", ret);
+		return ret;
+	}
+
+	return (regval & info->qi) ? REGULATOR_STATUS_ON : REGULATOR_STATUS_OFF;
+}
+
+static int mt6323_ldo_set_mode(struct regulator_dev *rdev, unsigned int mode)
+{
+	int ret, val = 0;
+	struct mt6323_regulator_info *info = rdev_get_drvdata(rdev);
+
+	if (!info->modeset_mask) {
+		dev_err(&rdev->dev, "regulator %s doesn't support set_mode\n",
+			info->desc.name);
+		return -EINVAL;
+	}
+
+	switch (mode) {
+	case REGULATOR_MODE_STANDBY:
+		val = MT6323_LDO_MODE_LP;
+		break;
+	case REGULATOR_MODE_NORMAL:
+		val = MT6323_LDO_MODE_NORMAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	val <<= ffs(info->modeset_mask) - 1;
+
+	ret = regmap_update_bits(rdev->regmap, info->modeset_reg,
+				  info->modeset_mask, val);
+
+	return ret;
+}
+
+static unsigned int mt6323_ldo_get_mode(struct regulator_dev *rdev)
+{
+	unsigned int val;
+	unsigned int mode;
+	int ret;
+	struct mt6323_regulator_info *info = rdev_get_drvdata(rdev);
+
+	if (!info->modeset_mask) {
+		dev_err(&rdev->dev, "regulator %s doesn't support get_mode\n",
+			info->desc.name);
+		return -EINVAL;
+	}
+
+	ret = regmap_read(rdev->regmap, info->modeset_reg, &val);
+	if (ret < 0)
+		return ret;
+
+	val &= info->modeset_mask;
+	val >>= ffs(info->modeset_mask) - 1;
+
+	if (val & 0x1)
+		mode = REGULATOR_MODE_STANDBY;
+	else
+		mode = REGULATOR_MODE_NORMAL;
+
+	return mode;
+}
+
+static const struct regulator_ops mt6323_volt_range_ops = {
+	.list_voltage = regulator_list_voltage_linear_range,
+	.map_voltage = regulator_map_voltage_linear_range,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6323_get_status,
+};
+
+static const struct regulator_ops mt6323_volt_table_ops = {
+	.list_voltage = regulator_list_voltage_table,
+	.map_voltage = regulator_map_voltage_iterate,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6323_get_status,
+	.set_mode = mt6323_ldo_set_mode,
+	.get_mode = mt6323_ldo_get_mode,
+};
+
+static const struct regulator_ops mt6323_volt_fixed_ops = {
+	.list_voltage = regulator_list_voltage_linear,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6323_get_status,
+	.set_mode = mt6323_ldo_set_mode,
+	.get_mode = mt6323_ldo_get_mode,
+};
+
+/* The array is indexed by id(MT6323_ID_XXX) */
+static struct mt6323_regulator_info mt6323_regulators[] = {
+	MT6323_BUCK("buck_vproc", VPROC, 700000, 1493750, 6250,
+		buck_volt_range1, MT6323_VPROC_CON7, MT6323_VPROC_CON9, 0x7f,
+		MT6323_VPROC_CON10, MT6323_VPROC_CON5),
+	MT6323_BUCK("buck_vsys", VSYS, 1400000, 2987500, 12500,
+		buck_volt_range2, MT6323_VSYS_CON7, MT6323_VSYS_CON9, 0x7f,
+		MT6323_VSYS_CON10, MT6323_VSYS_CON5),
+	MT6323_BUCK("buck_vpa", VPA, 500000, 3650000, 50000,
+		buck_volt_range3, MT6323_VPA_CON7, MT6323_VPA_CON9,
+		0x3f, MT6323_VPA_CON10, MT6323_VPA_CON5),
+	MT6323_REG_FIXED("ldo_vtcxo", VTCXO, MT6323_ANALDO_CON1, 10, 2800000,
+		MT6323_ANALDO_CON1, 0x2),
+	MT6323_REG_FIXED("ldo_vcn28", VCN28, MT6323_ANALDO_CON19, 12, 2800000,
+		MT6323_ANALDO_CON20, 0x2),
+	MT6323_LDO("ldo_vcn33_bt", VCN33_BT, ldo_volt_table1,
+		MT6323_ANALDO_CON16, 7, MT6323_ANALDO_CON16, 0xC,
+		MT6323_ANALDO_CON21, 0x2),
+	MT6323_LDO("ldo_vcn33_wifi", VCN33_WIFI, ldo_volt_table1,
+		MT6323_ANALDO_CON17, 12, MT6323_ANALDO_CON16, 0xC,
+		MT6323_ANALDO_CON21, 0x2),
+	MT6323_REG_FIXED("ldo_va", VA, MT6323_ANALDO_CON2, 14, 2800000,
+		MT6323_ANALDO_CON2, 0x2),
+	MT6323_LDO("ldo_vcama", VCAMA, ldo_volt_table2,
+		MT6323_ANALDO_CON4, 15, MT6323_ANALDO_CON10, 0x60, -1, 0),
+	MT6323_REG_FIXED("ldo_vio28", VIO28, MT6323_DIGLDO_CON0, 14, 2800000,
+		MT6323_DIGLDO_CON0, 0x2),
+	MT6323_REG_FIXED("ldo_vusb", VUSB, MT6323_DIGLDO_CON2, 14, 3300000,
+		MT6323_DIGLDO_CON2, 0x2),
+	MT6323_LDO("ldo_vmc", VMC, ldo_volt_table3,
+		MT6323_DIGLDO_CON3, 12, MT6323_DIGLDO_CON24, 0x10,
+		MT6323_DIGLDO_CON3, 0x2),
+	MT6323_LDO("ldo_vmch", VMCH, ldo_volt_table4,
+		MT6323_DIGLDO_CON5, 14, MT6323_DIGLDO_CON26, 0x80,
+		MT6323_DIGLDO_CON5, 0x2),
+	MT6323_LDO("ldo_vemc3v3", VEMC3V3, ldo_volt_table4,
+		MT6323_DIGLDO_CON6, 14, MT6323_DIGLDO_CON27, 0x80,
+		MT6323_DIGLDO_CON6, 0x2),
+	MT6323_LDO("ldo_vgp1", VGP1, ldo_volt_table5,
+		MT6323_DIGLDO_CON7, 15, MT6323_DIGLDO_CON28, 0xE0,
+		MT6323_DIGLDO_CON7, 0x2),
+	MT6323_LDO("ldo_vgp2", VGP2, ldo_volt_table6,
+		MT6323_DIGLDO_CON8, 15, MT6323_DIGLDO_CON29, 0xE0,
+		MT6323_DIGLDO_CON8, 0x2),
+	MT6323_LDO("ldo_vgp3", VGP3, ldo_volt_table7,
+		MT6323_DIGLDO_CON9, 15, MT6323_DIGLDO_CON30, 0x60,
+		MT6323_DIGLDO_CON9, 0x2),
+	MT6323_REG_FIXED("ldo_vcn18", VCN18, MT6323_DIGLDO_CON11, 14, 1800000,
+		MT6323_DIGLDO_CON11, 0x2),
+	MT6323_LDO("ldo_vsim1", VSIM1, ldo_volt_table8,
+		MT6323_DIGLDO_CON13, 15, MT6323_DIGLDO_CON34, 0x20,
+		MT6323_DIGLDO_CON13, 0x2),
+	MT6323_LDO("ldo_vsim2", VSIM2, ldo_volt_table8,
+		MT6323_DIGLDO_CON14, 15, MT6323_DIGLDO_CON35, 0x20,
+		MT6323_DIGLDO_CON14, 0x2),
+	MT6323_REG_FIXED("ldo_vrtc", VRTC, MT6323_DIGLDO_CON15, 8, 2800000,
+		-1, 0),
+	MT6323_LDO("ldo_vcamaf", VCAMAF, ldo_volt_table5,
+		MT6323_DIGLDO_CON31, 15, MT6323_DIGLDO_CON32, 0xE0,
+		MT6323_DIGLDO_CON31, 0x2),
+	MT6323_LDO("ldo_vibr", VIBR, ldo_volt_table5,
+		MT6323_DIGLDO_CON39, 15, MT6323_DIGLDO_CON40, 0xE0,
+		MT6323_DIGLDO_CON39, 0x2),
+	MT6323_REG_FIXED("ldo_vrf18", VRF18, MT6323_DIGLDO_CON45, 15, 1825000,
+		MT6323_DIGLDO_CON45, 0x2),
+	MT6323_LDO("ldo_vm", VM, ldo_volt_table9,
+		MT6323_DIGLDO_CON47, 14, MT6323_DIGLDO_CON48, 0x30,
+		MT6323_DIGLDO_CON47, 0x2),
+	MT6323_REG_FIXED("ldo_vio18", VIO18, MT6323_DIGLDO_CON49, 14, 1800000,
+		MT6323_DIGLDO_CON49, 0x2),
+	MT6323_LDO("ldo_vcamd", VCAMD, ldo_volt_table10,
+		MT6323_DIGLDO_CON51, 14, MT6323_DIGLDO_CON52, 0x60,
+		MT6323_DIGLDO_CON51, 0x2),
+	MT6323_REG_FIXED("ldo_vcamio", VCAMIO, MT6323_DIGLDO_CON53, 14, 1800000,
+		MT6323_DIGLDO_CON53, 0x2),
+};
+
+static int mt6323_set_buck_vosel_reg(struct platform_device *pdev)
+{
+	struct mt6397_chip *mt6323 = dev_get_drvdata(pdev->dev.parent);
+	int i;
+	u32 regval;
+
+	for (i = 0; i < MT6323_MAX_REGULATOR; i++) {
+		if (mt6323_regulators[i].vselctrl_reg) {
+			if (regmap_read(mt6323->regmap,
+				mt6323_regulators[i].vselctrl_reg,
+				&regval) < 0) {
+				dev_err(&pdev->dev,
+					"Failed to read buck ctrl\n");
+				return -EIO;
+			}
+
+			if (regval & mt6323_regulators[i].vselctrl_mask) {
+				mt6323_regulators[i].desc.vsel_reg =
+				mt6323_regulators[i].vselon_reg;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int mt6323_regulator_probe(struct platform_device *pdev)
+{
+	struct mt6397_chip *mt6323 = dev_get_drvdata(pdev->dev.parent);
+	struct regulator_config config = {};
+	struct regulator_dev *rdev;
+	int i;
+	u32 reg_value;
+
+	/* Query buck controller to select activated voltage register part */
+	if (mt6323_set_buck_vosel_reg(pdev))
+		return -EIO;
+
+	/* Read PMIC chip revision to update constraints and voltage table */
+	if (regmap_read(mt6323->regmap, MT6323_CID, &reg_value) < 0) {
+		dev_err(&pdev->dev, "Failed to read Chip ID\n");
+		return -EIO;
+	}
+	dev_info(&pdev->dev, "Chip ID = 0x%x\n", reg_value);
+
+	for (i = 0; i < MT6323_MAX_REGULATOR; i++) {
+		config.dev = &pdev->dev;
+		config.driver_data = &mt6323_regulators[i];
+		config.regmap = mt6323->regmap;
+		rdev = devm_regulator_register(&pdev->dev,
+				&mt6323_regulators[i].desc, &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to register %s\n",
+				mt6323_regulators[i].desc.name);
+			return PTR_ERR(rdev);
+		}
+	}
+	return 0;
+}
+
+static const struct platform_device_id mt6323_platform_ids[] = {
+	{"mt6323-regulator", 0},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(platform, mt6323_platform_ids);
+
+static struct platform_driver mt6323_regulator_driver = {
+	.driver = {
+		.name = "mt6323-regulator",
+	},
+	.probe = mt6323_regulator_probe,
+	.id_table = mt6323_platform_ids,
+};
+
+module_platform_driver(mt6323_regulator_driver);
+
+MODULE_AUTHOR("Chen Zhong <chen.zhong@mediatek.com>");
+MODULE_DESCRIPTION("Regulator Driver for MediaTek MT6323 PMIC");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c
index 17a5b6c2d6a9..c6c6aa85e4e8 100644
--- a/drivers/regulator/mt6397-regulator.c
+++ b/drivers/regulator/mt6397-regulator.c
@@ -23,6 +23,9 @@
 #include <linux/regulator/mt6397-regulator.h>
 #include <linux/regulator/of_regulator.h>
 
+#define MT6397_BUCK_MODE_AUTO	0
+#define MT6397_BUCK_MODE_FORCE_PWM	1
+
 /*
  * MT6397 regulators' information
  *
@@ -38,10 +41,14 @@ struct mt6397_regulator_info {
 	u32 vselon_reg;
 	u32 vselctrl_reg;
 	u32 vselctrl_mask;
+	u32 modeset_reg;
+	u32 modeset_mask;
+	u32 modeset_shift;
 };
 
 #define MT6397_BUCK(match, vreg, min, max, step, volt_ranges, enreg,	\
-		vosel, vosel_mask, voselon, vosel_ctrl)			\
+		vosel, vosel_mask, voselon, vosel_ctrl, _modeset_reg,	\
+		_modeset_shift)					\
 [MT6397_ID_##vreg] = {							\
 	.desc = {							\
 		.name = #vreg,						\
@@ -62,6 +69,9 @@ struct mt6397_regulator_info {
 	.vselon_reg = voselon,						\
 	.vselctrl_reg = vosel_ctrl,					\
 	.vselctrl_mask = BIT(1),					\
+	.modeset_reg = _modeset_reg,					\
+	.modeset_mask = BIT(_modeset_shift),				\
+	.modeset_shift = _modeset_shift					\
 }
 
 #define MT6397_LDO(match, vreg, ldo_volt_table, enreg, enbit, vosel,	\
@@ -145,6 +155,63 @@ static const u32 ldo_volt_table7[] = {
 	1300000, 1500000, 1800000, 2000000, 2500000, 2800000, 3000000, 3300000,
 };
 
+static int mt6397_regulator_set_mode(struct regulator_dev *rdev,
+				     unsigned int mode)
+{
+	struct mt6397_regulator_info *info = rdev_get_drvdata(rdev);
+	int ret, val;
+
+	switch (mode) {
+	case REGULATOR_MODE_FAST:
+		val = MT6397_BUCK_MODE_FORCE_PWM;
+		break;
+	case REGULATOR_MODE_NORMAL:
+		val = MT6397_BUCK_MODE_AUTO;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err_mode;
+	}
+
+	dev_dbg(&rdev->dev, "mt6397 buck set_mode %#x, %#x, %#x, %#x\n",
+		info->modeset_reg, info->modeset_mask,
+		info->modeset_shift, val);
+
+	val <<= info->modeset_shift;
+	ret = regmap_update_bits(rdev->regmap, info->modeset_reg,
+				 info->modeset_mask, val);
+err_mode:
+	if (ret != 0) {
+		dev_err(&rdev->dev,
+			"Failed to set mt6397 buck mode: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static unsigned int mt6397_regulator_get_mode(struct regulator_dev *rdev)
+{
+	struct mt6397_regulator_info *info = rdev_get_drvdata(rdev);
+	int ret, regval;
+
+	ret = regmap_read(rdev->regmap, info->modeset_reg, &regval);
+	if (ret != 0) {
+		dev_err(&rdev->dev,
+			"Failed to get mt6397 buck mode: %d\n", ret);
+		return ret;
+	}
+
+	switch ((regval & info->modeset_mask) >> info->modeset_shift) {
+	case MT6397_BUCK_MODE_AUTO:
+		return REGULATOR_MODE_NORMAL;
+	case MT6397_BUCK_MODE_FORCE_PWM:
+		return REGULATOR_MODE_FAST;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int mt6397_get_status(struct regulator_dev *rdev)
 {
 	int ret;
@@ -160,7 +227,7 @@ static int mt6397_get_status(struct regulator_dev *rdev)
 	return (regval & info->qi) ? REGULATOR_STATUS_ON : REGULATOR_STATUS_OFF;
 }
 
-static struct regulator_ops mt6397_volt_range_ops = {
+static const struct regulator_ops mt6397_volt_range_ops = {
 	.list_voltage = regulator_list_voltage_linear_range,
 	.map_voltage = regulator_map_voltage_linear_range,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
@@ -170,9 +237,11 @@ static struct regulator_ops mt6397_volt_range_ops = {
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
 	.get_status = mt6397_get_status,
+	.set_mode = mt6397_regulator_set_mode,
+	.get_mode = mt6397_regulator_get_mode,
 };
 
-static struct regulator_ops mt6397_volt_table_ops = {
+static const struct regulator_ops mt6397_volt_table_ops = {
 	.list_voltage = regulator_list_voltage_table,
 	.map_voltage = regulator_map_voltage_iterate,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
@@ -184,7 +253,7 @@ static struct regulator_ops mt6397_volt_table_ops = {
 	.get_status = mt6397_get_status,
 };
 
-static struct regulator_ops mt6397_volt_fixed_ops = {
+static const struct regulator_ops mt6397_volt_fixed_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -196,28 +265,30 @@ static struct regulator_ops mt6397_volt_fixed_ops = {
 static struct mt6397_regulator_info mt6397_regulators[] = {
 	MT6397_BUCK("buck_vpca15", VPCA15, 700000, 1493750, 6250,
 		buck_volt_range1, MT6397_VCA15_CON7, MT6397_VCA15_CON9, 0x7f,
-		MT6397_VCA15_CON10, MT6397_VCA15_CON5),
+		MT6397_VCA15_CON10, MT6397_VCA15_CON5, MT6397_VCA15_CON2, 11),
 	MT6397_BUCK("buck_vpca7", VPCA7, 700000, 1493750, 6250,
 		buck_volt_range1, MT6397_VPCA7_CON7, MT6397_VPCA7_CON9, 0x7f,
-		MT6397_VPCA7_CON10, MT6397_VPCA7_CON5),
+		MT6397_VPCA7_CON10, MT6397_VPCA7_CON5, MT6397_VPCA7_CON2, 8),
 	MT6397_BUCK("buck_vsramca15", VSRAMCA15, 700000, 1493750, 6250,
 		buck_volt_range1, MT6397_VSRMCA15_CON7, MT6397_VSRMCA15_CON9,
-		0x7f, MT6397_VSRMCA15_CON10, MT6397_VSRMCA15_CON5),
+		0x7f, MT6397_VSRMCA15_CON10, MT6397_VSRMCA15_CON5,
+		MT6397_VSRMCA15_CON2, 8),
 	MT6397_BUCK("buck_vsramca7", VSRAMCA7, 700000, 1493750, 6250,
 		buck_volt_range1, MT6397_VSRMCA7_CON7, MT6397_VSRMCA7_CON9,
-		0x7f, MT6397_VSRMCA7_CON10, MT6397_VSRMCA7_CON5),
+		0x7f, MT6397_VSRMCA7_CON10, MT6397_VSRMCA7_CON5,
+		MT6397_VSRMCA7_CON2, 8),
 	MT6397_BUCK("buck_vcore", VCORE, 700000, 1493750, 6250,
 		buck_volt_range1, MT6397_VCORE_CON7, MT6397_VCORE_CON9, 0x7f,
-		MT6397_VCORE_CON10, MT6397_VCORE_CON5),
+		MT6397_VCORE_CON10, MT6397_VCORE_CON5, MT6397_VCORE_CON2, 8),
 	MT6397_BUCK("buck_vgpu", VGPU, 700000, 1493750, 6250, buck_volt_range1,
 		MT6397_VGPU_CON7, MT6397_VGPU_CON9, 0x7f,
-		MT6397_VGPU_CON10, MT6397_VGPU_CON5),
+		MT6397_VGPU_CON10, MT6397_VGPU_CON5, MT6397_VGPU_CON2, 8),
 	MT6397_BUCK("buck_vdrm", VDRM, 800000, 1593750, 6250, buck_volt_range2,
 		MT6397_VDRM_CON7, MT6397_VDRM_CON9, 0x7f,
-		MT6397_VDRM_CON10, MT6397_VDRM_CON5),
+		MT6397_VDRM_CON10, MT6397_VDRM_CON5, MT6397_VDRM_CON2, 8),
 	MT6397_BUCK("buck_vio18", VIO18, 1500000, 2120000, 20000,
 		buck_volt_range3, MT6397_VIO18_CON7, MT6397_VIO18_CON9, 0x1f,
-		MT6397_VIO18_CON10, MT6397_VIO18_CON5),
+		MT6397_VIO18_CON10, MT6397_VIO18_CON5, MT6397_VIO18_CON2, 8),
 	MT6397_REG_FIXED("ldo_vtcxo", VTCXO, MT6397_ANALDO_CON0, 10, 2800000),
 	MT6397_REG_FIXED("ldo_va28", VA28, MT6397_ANALDO_CON1, 14, 2800000),
 	MT6397_LDO("ldo_vcama", VCAMA, ldo_volt_table1,
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index cd828dbf9d52..4f613ec99500 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -163,6 +163,9 @@ static void of_get_regulation_constraints(struct device_node *np,
 					"regulator-suspend-microvolt", &pval))
 			suspend_state->uV = pval;
 
+		if (i == PM_SUSPEND_MEM)
+			constraints->initial_state = PM_SUSPEND_MEM;
+
 		of_node_put(suspend_np);
 		suspend_state = NULL;
 		suspend_np = NULL;
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 2a44e5dd9c2a..cb18b5c4f2db 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -70,6 +70,7 @@ struct pfuze_chip {
 	struct device *dev;
 	struct pfuze_regulator regulator_descs[PFUZE100_MAX_REGULATOR];
 	struct regulator_dev *regulators[PFUZE100_MAX_REGULATOR];
+	struct pfuze_regulator *pfuze_regulators;
 };
 
 static const int pfuze100_swbst[] = {
@@ -334,8 +335,6 @@ static struct pfuze_regulator pfuze3000_regulators[] = {
 	PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
-static struct pfuze_regulator *pfuze_regulators;
-
 #ifdef CONFIG_OF
 /* PFUZE100 */
 static struct of_regulator_match pfuze100_matches[] = {
@@ -563,21 +562,21 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	/* use the right regulators after identify the right device */
 	switch (pfuze_chip->chip_id) {
 	case PFUZE3000:
-		pfuze_regulators = pfuze3000_regulators;
+		pfuze_chip->pfuze_regulators = pfuze3000_regulators;
 		regulator_num = ARRAY_SIZE(pfuze3000_regulators);
 		sw_check_start = PFUZE3000_SW2;
 		sw_check_end = PFUZE3000_SW2;
 		sw_hi = 1 << 3;
 		break;
 	case PFUZE200:
-		pfuze_regulators = pfuze200_regulators;
+		pfuze_chip->pfuze_regulators = pfuze200_regulators;
 		regulator_num = ARRAY_SIZE(pfuze200_regulators);
 		sw_check_start = PFUZE200_SW2;
 		sw_check_end = PFUZE200_SW3B;
 		break;
 	case PFUZE100:
 	default:
-		pfuze_regulators = pfuze100_regulators;
+		pfuze_chip->pfuze_regulators = pfuze100_regulators;
 		regulator_num = ARRAY_SIZE(pfuze100_regulators);
 		sw_check_start = PFUZE100_SW2;
 		sw_check_end = PFUZE100_SW4;
@@ -587,7 +586,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		(pfuze_chip->chip_id == PFUZE100) ? "100" :
 		((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000"));
 
-	memcpy(pfuze_chip->regulator_descs, pfuze_regulators,
+	memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators,
 		sizeof(pfuze_chip->regulator_descs));
 
 	ret = pfuze_parse_regulators_dt(pfuze_chip);
@@ -631,7 +630,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 			devm_regulator_register(&client->dev, desc, &config);
 		if (IS_ERR(pfuze_chip->regulators[i])) {
 			dev_err(&client->dev, "register regulator%s failed\n",
-				pfuze_regulators[i].desc.name);
+				pfuze_chip->pfuze_regulators[i].desc.name);
 			return PTR_ERR(pfuze_chip->regulators[i]);
 		}
 	}
@@ -650,5 +649,5 @@ static struct i2c_driver pfuze_driver = {
 module_i2c_driver(pfuze_driver);
 
 MODULE_AUTHOR("Robin Gong <b38343@freescale.com>");
-MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/PFUZE200 PMIC");
+MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000 PMIC");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/pv88060-regulator.c b/drivers/regulator/pv88060-regulator.c
index c448b727f5f8..6c4afc73ecac 100644
--- a/drivers/regulator/pv88060-regulator.c
+++ b/drivers/regulator/pv88060-regulator.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -25,8 +24,6 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/regulator/of_regulator.h>
-#include <linux/proc_fs.h>
-#include <linux/uaccess.h>
 #include "pv88060-regulator.h"
 
 #define PV88060_MAX_REGULATORS	14
diff --git a/drivers/regulator/pv88080-regulator.c b/drivers/regulator/pv88080-regulator.c
index d7107566c429..81950bdb1cc4 100644
--- a/drivers/regulator/pv88080-regulator.c
+++ b/drivers/regulator/pv88080-regulator.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -25,8 +24,6 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/regulator/of_regulator.h>
-#include <linux/proc_fs.h>
-#include <linux/uaccess.h>
 #include "pv88080-regulator.h"
 
 #define PV88080_MAX_REGULATORS	3
diff --git a/drivers/regulator/pv88090-regulator.c b/drivers/regulator/pv88090-regulator.c
index 0057c6740d6f..421641175352 100644
--- a/drivers/regulator/pv88090-regulator.c
+++ b/drivers/regulator/pv88090-regulator.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -25,8 +24,6 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/regulator/of_regulator.h>
-#include <linux/proc_fs.h>
-#include <linux/uaccess.h>
 #include "pv88090-regulator.h"
 
 #define PV88090_MAX_REGULATORS	5
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index fafa3488e960..666bc3bb52ef 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pwm.h>
+#include <linux/gpio/consumer.h>
 
 struct pwm_regulator_data {
 	/*  Shared */
@@ -38,6 +39,9 @@ struct pwm_regulator_data {
 
 	/* Continuous voltage */
 	int volt_uV;
+
+	/* Enable GPIO */
+	struct gpio_desc *enb_gpio;
 };
 
 struct pwm_voltages {
@@ -94,6 +98,9 @@ static int pwm_regulator_enable(struct regulator_dev *dev)
 {
 	struct pwm_regulator_data *drvdata = rdev_get_drvdata(dev);
 
+	if (drvdata->enb_gpio)
+		gpiod_set_value_cansleep(drvdata->enb_gpio, 1);
+
 	return pwm_enable(drvdata->pwm);
 }
 
@@ -103,6 +110,9 @@ static int pwm_regulator_disable(struct regulator_dev *dev)
 
 	pwm_disable(drvdata->pwm);
 
+	if (drvdata->enb_gpio)
+		gpiod_set_value_cansleep(drvdata->enb_gpio, 0);
+
 	return 0;
 }
 
@@ -110,6 +120,9 @@ static int pwm_regulator_is_enabled(struct regulator_dev *dev)
 {
 	struct pwm_regulator_data *drvdata = rdev_get_drvdata(dev);
 
+	if (drvdata->enb_gpio && !gpiod_get_value_cansleep(drvdata->enb_gpio))
+		return false;
+
 	return pwm_is_enabled(drvdata->pwm);
 }
 
@@ -132,6 +145,7 @@ static int pwm_regulator_set_voltage(struct regulator_dev *rdev,
 	unsigned int duty_pulse;
 	u64 req_period;
 	u32 rem;
+	int old_uV = pwm_regulator_get_voltage(rdev);
 	int ret;
 
 	pwm_get_args(drvdata->pwm, &pargs);
@@ -159,15 +173,14 @@ static int pwm_regulator_set_voltage(struct regulator_dev *rdev,
 		return ret;
 	}
 
-	ret = pwm_enable(drvdata->pwm);
-	if (ret) {
-		dev_err(&rdev->dev, "Failed to enable PWM: %d\n", ret);
-		return ret;
-	}
 	drvdata->volt_uV = min_uV;
 
-	/* Delay required by PWM regulator to settle to the new voltage */
-	usleep_range(ramp_delay, ramp_delay + 1000);
+	if ((ramp_delay == 0) || !pwm_regulator_is_enabled(rdev))
+		return 0;
+
+	/* Ramp delay is in uV/uS. Adjust to uS and delay */
+	ramp_delay = DIV_ROUND_UP(abs(min_uV - old_uV), ramp_delay);
+	usleep_range(ramp_delay, ramp_delay + DIV_ROUND_UP(ramp_delay, 10));
 
 	return 0;
 }
@@ -253,6 +266,7 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 	struct regulator_dev *regulator;
 	struct regulator_config config = { };
 	struct device_node *np = pdev->dev.of_node;
+	enum gpiod_flags gpio_flags;
 	int ret;
 
 	if (!np) {
@@ -290,6 +304,18 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	if (init_data->constraints.boot_on || init_data->constraints.always_on)
+		gpio_flags = GPIOD_OUT_HIGH;
+	else
+		gpio_flags = GPIOD_OUT_LOW;
+	drvdata->enb_gpio = devm_gpiod_get_optional(&pdev->dev, "enable",
+						    gpio_flags);
+	if (IS_ERR(drvdata->enb_gpio)) {
+		ret = PTR_ERR(drvdata->enb_gpio);
+		dev_err(&pdev->dev, "Failed to get enable GPIO: %d\n", ret);
+		return ret;
+	}
+
 	/*
 	 * FIXME: pwm_apply_args() should be removed when switching to the
 	 * atomic PWM API.
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index 6c7fe4778793..5022fa8d10c6 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -211,7 +211,7 @@ static const struct regulator_desc pma8084_switch = {
 static const struct regulator_desc pm8x41_hfsmps = {
 	.linear_ranges = (struct regulator_linear_range[]) {
 		REGULATOR_LINEAR_RANGE( 375000,  0,  95, 12500),
-		REGULATOR_LINEAR_RANGE(1550000, 96, 158, 25000),
+		REGULATOR_LINEAR_RANGE(1575000, 96, 158, 25000),
 	},
 	.n_linear_ranges = 2,
 	.n_voltages = 159,
diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 84cce21e98cd..16c5f84e06a7 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1085,6 +1085,8 @@ static struct regulator_ops spmi_vs_ops = {
 	.set_pull_down		= spmi_regulator_common_set_pull_down,
 	.set_soft_start		= spmi_regulator_common_set_soft_start,
 	.set_over_current_protection = spmi_regulator_vs_ocp,
+	.set_mode		= spmi_regulator_common_set_mode,
+	.get_mode		= spmi_regulator_common_get_mode,
 };
 
 static struct regulator_ops spmi_boost_ops = {
@@ -1496,6 +1498,7 @@ static const struct spmi_regulator_data pm8941_regulators[] = {
 	{ "s1", 0x1400, "vdd_s1", },
 	{ "s2", 0x1700, "vdd_s2", },
 	{ "s3", 0x1a00, "vdd_s3", },
+	{ "s4", 0xa000, },
 	{ "l1", 0x4000, "vdd_l1_l3", },
 	{ "l2", 0x4100, "vdd_l2_lvs_1_2_3", },
 	{ "l3", 0x4200, "vdd_l1_l3", },
@@ -1523,8 +1526,8 @@ static const struct spmi_regulator_data pm8941_regulators[] = {
 	{ "lvs1", 0x8000, "vdd_l2_lvs_1_2_3", },
 	{ "lvs2", 0x8100, "vdd_l2_lvs_1_2_3", },
 	{ "lvs3", 0x8200, "vdd_l2_lvs_1_2_3", },
-	{ "mvs1", 0x8300, "vin_5vs", },
-	{ "mvs2", 0x8400, "vin_5vs", },
+	{ "5vs1", 0x8300, "vin_5vs", "ocp-5vs1", },
+	{ "5vs2", 0x8400, "vin_5vs", "ocp-5vs2", },
 	{ }
 };
 
diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c
index b85ceb8ff911..9c930eb68cda 100644
--- a/drivers/regulator/rn5t618-regulator.c
+++ b/drivers/regulator/rn5t618-regulator.c
@@ -46,6 +46,23 @@ static struct regulator_ops rn5t618_reg_ops = {
 		.vsel_mask	= (vmask),				\
 	}
 
+static struct regulator_desc rn5t567_regulators[] = {
+	/* DCDC */
+	REG(DCDC1, DC1CTL, BIT(0), DC1DAC, 0xff, 600000, 3500000, 12500),
+	REG(DCDC2, DC2CTL, BIT(0), DC2DAC, 0xff, 600000, 3500000, 12500),
+	REG(DCDC3, DC3CTL, BIT(0), DC3DAC, 0xff, 600000, 3500000, 12500),
+	REG(DCDC4, DC4CTL, BIT(0), DC4DAC, 0xff, 600000, 3500000, 12500),
+	/* LDO */
+	REG(LDO1, LDOEN1, BIT(0), LDO1DAC, 0x7f, 900000, 3500000, 25000),
+	REG(LDO2, LDOEN1, BIT(1), LDO2DAC, 0x7f, 900000, 3500000, 25000),
+	REG(LDO3, LDOEN1, BIT(2), LDO3DAC, 0x7f, 600000, 3500000, 25000),
+	REG(LDO4, LDOEN1, BIT(3), LDO4DAC, 0x7f, 900000, 3500000, 25000),
+	REG(LDO5, LDOEN1, BIT(4), LDO5DAC, 0x7f, 900000, 3500000, 25000),
+	/* LDO RTC */
+	REG(LDORTC1, LDOEN2, BIT(4), LDORTCDAC, 0x7f, 1200000, 3500000, 25000),
+	REG(LDORTC2, LDOEN2, BIT(5), LDORTC2DAC, 0x7f, 900000, 3500000, 25000),
+};
+
 static struct regulator_desc rn5t618_regulators[] = {
 	/* DCDC */
 	REG(DCDC1, DC1CTL, BIT(0), DC1DAC, 0xff, 600000, 3500000, 12500),
@@ -67,18 +84,33 @@ static int rn5t618_regulator_probe(struct platform_device *pdev)
 	struct rn5t618 *rn5t618 = dev_get_drvdata(pdev->dev.parent);
 	struct regulator_config config = { };
 	struct regulator_dev *rdev;
+	struct regulator_desc *regulators;
 	int i;
 
+	switch (rn5t618->variant) {
+	case RN5T567:
+		regulators = rn5t567_regulators;
+		break;
+	case RN5T618:
+		regulators = rn5t618_regulators;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	config.dev = pdev->dev.parent;
+	config.regmap = rn5t618->regmap;
+
 	for (i = 0; i < RN5T618_REG_NUM; i++) {
-		config.dev = pdev->dev.parent;
-		config.regmap = rn5t618->regmap;
+		if (!regulators[i].name)
+			continue;
 
 		rdev = devm_regulator_register(&pdev->dev,
-					       &rn5t618_regulators[i],
+					       &regulators[i],
 					       &config);
 		if (IS_ERR(rdev)) {
 			dev_err(&pdev->dev, "failed to register %s regulator\n",
-				rn5t618_regulators[i].name);
+				regulators[i].name);
 			return PTR_ERR(rdev);
 		}
 	}
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 02fb6b4ea820..d838e77dd947 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -750,7 +750,7 @@ static const struct regulator_linear_range s2mps15_ldo_voltage_ranges3[] = {
 
 /* voltage range for s2mps15 LDO 7, 8, 9 and 10 */
 static const struct regulator_linear_range s2mps15_ldo_voltage_ranges4[] = {
-	REGULATOR_LINEAR_RANGE(700000, 0xc, 0x18, 25000),
+	REGULATOR_LINEAR_RANGE(700000, 0x10, 0x20, 25000),
 };
 
 /* voltage range for s2mps15 LDO 1 */
@@ -760,12 +760,12 @@ static const struct regulator_linear_range s2mps15_ldo_voltage_ranges5[] = {
 
 /* voltage range for s2mps15 BUCK 1, 2, 3, 4, 5, 6 and 7 */
 static const struct regulator_linear_range s2mps15_buck_voltage_ranges1[] = {
-	REGULATOR_LINEAR_RANGE(500000, 0x20, 0xb0, 6250),
+	REGULATOR_LINEAR_RANGE(500000, 0x20, 0xc0, 6250),
 };
 
 /* voltage range for s2mps15 BUCK 8, 9 and 10 */
 static const struct regulator_linear_range s2mps15_buck_voltage_ranges2[] = {
-	REGULATOR_LINEAR_RANGE(1000000, 0x20, 0xc0, 12500),
+	REGULATOR_LINEAR_RANGE(1000000, 0x20, 0x78, 12500),
 };
 
 static const struct regulator_desc s2mps15_regulators[] = {
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index adbe4fc5cf07..2d12b9af3540 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -28,7 +28,7 @@
 #include <linux/mfd/tps65217.h>
 
 #define TPS65217_REGULATOR(_name, _id, _of_match, _ops, _n, _vr, _vm, _em, \
-                           _t, _lr, _nlr) \
+			   _t, _lr, _nlr,  _sr, _sm)	\
 	{						\
 		.name		= _name,		\
 		.id		= _id,			\
@@ -45,6 +45,8 @@
 		.volt_table	= _t,			\
 		.linear_ranges	= _lr,			\
 		.n_linear_ranges = _nlr,		\
+		.bypass_reg	= _sr,			\
+		.bypass_mask	= _sm,			\
 	}						\
 
 static const unsigned int LDO1_VSEL_table[] = {
@@ -118,6 +120,35 @@ static int tps65217_pmic_set_voltage_sel(struct regulator_dev *dev,
 	return ret;
 }
 
+static int tps65217_pmic_set_suspend_enable(struct regulator_dev *dev)
+{
+	struct tps65217 *tps = rdev_get_drvdata(dev);
+	unsigned int rid = rdev_get_id(dev);
+
+	if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4)
+		return -EINVAL;
+
+	return tps65217_clear_bits(tps, dev->desc->bypass_reg,
+				   dev->desc->bypass_mask,
+				   TPS65217_PROTECT_L1);
+}
+
+static int tps65217_pmic_set_suspend_disable(struct regulator_dev *dev)
+{
+	struct tps65217 *tps = rdev_get_drvdata(dev);
+	unsigned int rid = rdev_get_id(dev);
+
+	if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4)
+		return -EINVAL;
+
+	if (!tps->strobes[rid])
+		return -EINVAL;
+
+	return tps65217_set_bits(tps, dev->desc->bypass_reg,
+				 dev->desc->bypass_mask,
+				 tps->strobes[rid], TPS65217_PROTECT_L1);
+}
+
 /* Operations permitted on DCDCx, LDO2, LDO3 and LDO4 */
 static struct regulator_ops tps65217_pmic_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -127,6 +158,8 @@ static struct regulator_ops tps65217_pmic_ops = {
 	.set_voltage_sel	= tps65217_pmic_set_voltage_sel,
 	.list_voltage		= regulator_list_voltage_linear_range,
 	.map_voltage		= regulator_map_voltage_linear_range,
+	.set_suspend_enable	= tps65217_pmic_set_suspend_enable,
+	.set_suspend_disable	= tps65217_pmic_set_suspend_disable,
 };
 
 /* Operations permitted on LDO1 */
@@ -138,41 +171,50 @@ static struct regulator_ops tps65217_pmic_ldo1_ops = {
 	.set_voltage_sel	= tps65217_pmic_set_voltage_sel,
 	.list_voltage		= regulator_list_voltage_table,
 	.map_voltage		= regulator_map_voltage_ascend,
+	.set_suspend_enable	= tps65217_pmic_set_suspend_enable,
+	.set_suspend_disable	= tps65217_pmic_set_suspend_disable,
 };
 
 static const struct regulator_desc regulators[] = {
 	TPS65217_REGULATOR("DCDC1", TPS65217_DCDC_1, "dcdc1",
 			   tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC1,
 			   TPS65217_DEFDCDCX_DCDC_MASK, TPS65217_ENABLE_DC1_EN,
-			   NULL, tps65217_uv1_ranges, 2),
+			   NULL, tps65217_uv1_ranges, 2, TPS65217_REG_SEQ1,
+			   TPS65217_SEQ1_DC1_SEQ_MASK),
 	TPS65217_REGULATOR("DCDC2", TPS65217_DCDC_2, "dcdc2",
 			   tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC2,
 			   TPS65217_DEFDCDCX_DCDC_MASK, TPS65217_ENABLE_DC2_EN,
 			   NULL, tps65217_uv1_ranges,
-			   ARRAY_SIZE(tps65217_uv1_ranges)),
+			   ARRAY_SIZE(tps65217_uv1_ranges), TPS65217_REG_SEQ1,
+			   TPS65217_SEQ1_DC2_SEQ_MASK),
 	TPS65217_REGULATOR("DCDC3", TPS65217_DCDC_3, "dcdc3",
 			   tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC3,
 			   TPS65217_DEFDCDCX_DCDC_MASK, TPS65217_ENABLE_DC3_EN,
-			   NULL, tps65217_uv1_ranges, 1),
+			   NULL, tps65217_uv1_ranges, 1, TPS65217_REG_SEQ2,
+			   TPS65217_SEQ2_DC3_SEQ_MASK),
 	TPS65217_REGULATOR("LDO1", TPS65217_LDO_1, "ldo1",
 			   tps65217_pmic_ldo1_ops, 16, TPS65217_REG_DEFLDO1,
 			   TPS65217_DEFLDO1_LDO1_MASK, TPS65217_ENABLE_LDO1_EN,
-			   LDO1_VSEL_table, NULL, 0),
+			   LDO1_VSEL_table, NULL, 0, TPS65217_REG_SEQ2,
+			   TPS65217_SEQ2_LDO1_SEQ_MASK),
 	TPS65217_REGULATOR("LDO2", TPS65217_LDO_2, "ldo2", tps65217_pmic_ops,
 			   64, TPS65217_REG_DEFLDO2,
 			   TPS65217_DEFLDO2_LDO2_MASK, TPS65217_ENABLE_LDO2_EN,
 			   NULL, tps65217_uv1_ranges,
-			   ARRAY_SIZE(tps65217_uv1_ranges)),
+			   ARRAY_SIZE(tps65217_uv1_ranges), TPS65217_REG_SEQ3,
+			   TPS65217_SEQ3_LDO2_SEQ_MASK),
 	TPS65217_REGULATOR("LDO3", TPS65217_LDO_3, "ldo3", tps65217_pmic_ops,
 			   32, TPS65217_REG_DEFLS1, TPS65217_DEFLDO3_LDO3_MASK,
 			   TPS65217_ENABLE_LS1_EN | TPS65217_DEFLDO3_LDO3_EN,
 			   NULL, tps65217_uv2_ranges,
-			   ARRAY_SIZE(tps65217_uv2_ranges)),
+			   ARRAY_SIZE(tps65217_uv2_ranges), TPS65217_REG_SEQ3,
+			   TPS65217_SEQ3_LDO3_SEQ_MASK),
 	TPS65217_REGULATOR("LDO4", TPS65217_LDO_4, "ldo4", tps65217_pmic_ops,
 			   32, TPS65217_REG_DEFLS2, TPS65217_DEFLDO4_LDO4_MASK,
 			   TPS65217_ENABLE_LS2_EN | TPS65217_DEFLDO4_LDO4_EN,
 			   NULL, tps65217_uv2_ranges,
-			   ARRAY_SIZE(tps65217_uv2_ranges)),
+			   ARRAY_SIZE(tps65217_uv2_ranges), TPS65217_REG_SEQ4,
+			   TPS65217_SEQ4_LDO4_SEQ_MASK),
 };
 
 static int tps65217_regulator_probe(struct platform_device *pdev)
@@ -181,13 +223,18 @@ static int tps65217_regulator_probe(struct platform_device *pdev)
 	struct tps65217_board *pdata = dev_get_platdata(tps->dev);
 	struct regulator_dev *rdev;
 	struct regulator_config config = { };
-	int i;
+	int i, ret;
+	unsigned int val;
 
 	if (tps65217_chip_id(tps) != TPS65217) {
 		dev_err(&pdev->dev, "Invalid tps chip version\n");
 		return -ENODEV;
 	}
 
+	/* Allocate memory for strobes */
+	tps->strobes = devm_kzalloc(&pdev->dev, sizeof(u8) *
+				    TPS65217_NUM_REGULATOR, GFP_KERNEL);
+
 	platform_set_drvdata(pdev, tps);
 
 	for (i = 0; i < TPS65217_NUM_REGULATOR; i++) {
@@ -205,6 +252,10 @@ static int tps65217_regulator_probe(struct platform_device *pdev)
 				pdev->name);
 			return PTR_ERR(rdev);
 		}
+
+		/* Store default strobe info */
+		ret = tps65217_reg_read(tps, regulators[i].bypass_reg, &val);
+		tps->strobes[i] = val & regulators[i].bypass_mask;
 	}
 
 	return 0;
diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c
index a5e5634eeb9e..d1e631d64a20 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -31,7 +31,7 @@ enum tps65218_regulators { DCDC1, DCDC2, DCDC3, DCDC4,
 			   DCDC5, DCDC6, LDO1, LS3 };
 
 #define TPS65218_REGULATOR(_name, _id, _type, _ops, _n, _vr, _vm, _er, _em, \
-			    _cr, _cm, _lr, _nlr, _delay, _fuv)		\
+			   _cr, _cm, _lr, _nlr, _delay, _fuv, _sr, _sm)	\
 	{							\
 		.name			= _name,		\
 		.id			= _id,			\
@@ -49,7 +49,9 @@ enum tps65218_regulators { DCDC1, DCDC2, DCDC3, DCDC4,
 		.linear_ranges		= _lr,			\
 		.n_linear_ranges	= _nlr,			\
 		.ramp_delay		= _delay,		\
-		.fixed_uV		= _fuv			\
+		.fixed_uV		= _fuv,			\
+		.bypass_reg	= _sr,				\
+		.bypass_mask	= _sm,				\
 	}							\
 
 #define TPS65218_INFO(_id, _nm, _min, _max)	\
@@ -157,6 +159,40 @@ static int tps65218_pmic_disable(struct regulator_dev *dev)
 				   dev->desc->enable_mask, TPS65218_PROTECT_L1);
 }
 
+static int tps65218_pmic_set_suspend_enable(struct regulator_dev *dev)
+{
+	struct tps65218 *tps = rdev_get_drvdata(dev);
+	unsigned int rid = rdev_get_id(dev);
+
+	if (rid < TPS65218_DCDC_1 || rid > TPS65218_LDO_1)
+		return -EINVAL;
+
+	return tps65218_clear_bits(tps, dev->desc->bypass_reg,
+				   dev->desc->bypass_mask,
+				   TPS65218_PROTECT_L1);
+}
+
+static int tps65218_pmic_set_suspend_disable(struct regulator_dev *dev)
+{
+	struct tps65218 *tps = rdev_get_drvdata(dev);
+	unsigned int rid = rdev_get_id(dev);
+
+	if (rid < TPS65218_DCDC_1 || rid > TPS65218_LDO_1)
+		return -EINVAL;
+
+	if (!tps->info[rid]->strobe) {
+		if (rid == TPS65218_DCDC_3)
+			tps->info[rid]->strobe = 3;
+		else
+			return -EINVAL;
+	}
+
+	return tps65218_set_bits(tps, dev->desc->bypass_reg,
+				 dev->desc->bypass_mask,
+				 tps->info[rid]->strobe,
+				 TPS65218_PROTECT_L1);
+}
+
 /* Operations permitted on DCDC1, DCDC2 */
 static struct regulator_ops tps65218_dcdc12_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -167,6 +203,8 @@ static struct regulator_ops tps65218_dcdc12_ops = {
 	.list_voltage		= regulator_list_voltage_linear_range,
 	.map_voltage		= regulator_map_voltage_linear_range,
 	.set_voltage_time_sel	= regulator_set_voltage_time_sel,
+	.set_suspend_enable	= tps65218_pmic_set_suspend_enable,
+	.set_suspend_disable	= tps65218_pmic_set_suspend_disable,
 };
 
 /* Operations permitted on DCDC3, DCDC4 and LDO1 */
@@ -178,6 +216,8 @@ static struct regulator_ops tps65218_ldo1_dcdc34_ops = {
 	.set_voltage_sel	= tps65218_pmic_set_voltage_sel,
 	.list_voltage		= regulator_list_voltage_linear_range,
 	.map_voltage		= regulator_map_voltage_linear_range,
+	.set_suspend_enable	= tps65218_pmic_set_suspend_enable,
+	.set_suspend_disable	= tps65218_pmic_set_suspend_disable,
 };
 
 static const int ls3_currents[] = { 100, 200, 500, 1000 };
@@ -247,6 +287,8 @@ static struct regulator_ops tps65218_dcdc56_pmic_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= tps65218_pmic_enable,
 	.disable		= tps65218_pmic_disable,
+	.set_suspend_enable	= tps65218_pmic_set_suspend_enable,
+	.set_suspend_disable	= tps65218_pmic_set_suspend_disable,
 };
 
 static const struct regulator_desc regulators[] = {
@@ -254,42 +296,47 @@ static const struct regulator_desc regulators[] = {
 			   tps65218_dcdc12_ops, 64, TPS65218_REG_CONTROL_DCDC1,
 			   TPS65218_CONTROL_DCDC1_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC1_EN, 0, 0, dcdc1_dcdc2_ranges,
-			   2, 4000, 0),
+			   2, 4000, 0, TPS65218_REG_SEQ3,
+			   TPS65218_SEQ3_DC1_SEQ_MASK),
 	TPS65218_REGULATOR("DCDC2", TPS65218_DCDC_2, REGULATOR_VOLTAGE,
 			   tps65218_dcdc12_ops, 64, TPS65218_REG_CONTROL_DCDC2,
 			   TPS65218_CONTROL_DCDC2_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC2_EN, 0, 0, dcdc1_dcdc2_ranges,
-			   2, 4000, 0),
+			   2, 4000, 0, TPS65218_REG_SEQ3,
+			   TPS65218_SEQ3_DC2_SEQ_MASK),
 	TPS65218_REGULATOR("DCDC3", TPS65218_DCDC_3, REGULATOR_VOLTAGE,
 			   tps65218_ldo1_dcdc34_ops, 64,
 			   TPS65218_REG_CONTROL_DCDC3,
 			   TPS65218_CONTROL_DCDC3_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC3_EN, 0, 0, ldo1_dcdc3_ranges, 2,
-			   0, 0),
+			   0, 0, TPS65218_REG_SEQ4, TPS65218_SEQ4_DC3_SEQ_MASK),
 	TPS65218_REGULATOR("DCDC4", TPS65218_DCDC_4, REGULATOR_VOLTAGE,
 			   tps65218_ldo1_dcdc34_ops, 53,
 			   TPS65218_REG_CONTROL_DCDC4,
 			   TPS65218_CONTROL_DCDC4_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC4_EN, 0, 0, dcdc4_ranges, 2,
-			   0, 0),
+			   0, 0, TPS65218_REG_SEQ4, TPS65218_SEQ4_DC4_SEQ_MASK),
 	TPS65218_REGULATOR("DCDC5", TPS65218_DCDC_5, REGULATOR_VOLTAGE,
 			   tps65218_dcdc56_pmic_ops, 1, -1, -1,
 			   TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC5_EN, 0, 0,
-			   NULL, 0, 0, 1000000),
+			   NULL, 0, 0, 1000000, TPS65218_REG_SEQ5,
+			   TPS65218_SEQ5_DC5_SEQ_MASK),
 	TPS65218_REGULATOR("DCDC6", TPS65218_DCDC_6, REGULATOR_VOLTAGE,
 			   tps65218_dcdc56_pmic_ops, 1, -1, -1,
 			   TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC6_EN, 0, 0,
-			   NULL, 0, 0, 1800000),
+			   NULL, 0, 0, 1800000, TPS65218_REG_SEQ5,
+			   TPS65218_SEQ5_DC6_SEQ_MASK),
 	TPS65218_REGULATOR("LDO1", TPS65218_LDO_1, REGULATOR_VOLTAGE,
 			   tps65218_ldo1_dcdc34_ops, 64,
 			   TPS65218_REG_CONTROL_LDO1,
 			   TPS65218_CONTROL_LDO1_MASK, TPS65218_REG_ENABLE2,
 			   TPS65218_ENABLE2_LDO1_EN, 0, 0, ldo1_dcdc3_ranges,
-			   2, 0, 0),
+			   2, 0, 0, TPS65218_REG_SEQ6,
+			   TPS65218_SEQ6_LDO1_SEQ_MASK),
 	TPS65218_REGULATOR("LS3", TPS65218_LS_3, REGULATOR_CURRENT,
 			   tps65218_ls3_ops, 0, 0, 0, TPS65218_REG_ENABLE2,
 			   TPS65218_ENABLE2_LS3_EN, TPS65218_REG_CONFIG2,
-			   TPS65218_CONFIG2_LS3ILIM_MASK, NULL, 0, 0, 0),
+			   TPS65218_CONFIG2_LS3ILIM_MASK, NULL, 0, 0, 0, 0, 0),
 };
 
 static int tps65218_regulator_probe(struct platform_device *pdev)
@@ -300,7 +347,8 @@ static int tps65218_regulator_probe(struct platform_device *pdev)
 	struct regulator_dev *rdev;
 	const struct of_device_id	*match;
 	struct regulator_config config = { };
-	int id;
+	int id, ret;
+	unsigned int val;
 
 	match = of_match_device(tps65218_of_match, &pdev->dev);
 	if (!match)
@@ -327,6 +375,12 @@ static int tps65218_regulator_probe(struct platform_device *pdev)
 		return PTR_ERR(rdev);
 	}
 
+	ret = tps65218_reg_read(tps, regulators[id].bypass_reg, &val);
+	if (ret)
+		return ret;
+
+	tps->info[id]->strobe = val & regulators[id].bypass_mask;
+
 	return 0;
 }
 
diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c
index faeb5ee92c9e..210681d6b743 100644
--- a/drivers/regulator/twl-regulator.c
+++ b/drivers/regulator/twl-regulator.c
@@ -905,7 +905,7 @@ static struct regulator_ops twlsmps_ops = {
 			twl4030reg_map_mode)
 #define TWL6030_FIXED_LDO(label, offset, mVolts, turnon_delay) \
 		TWL_FIXED_LDO(label, offset, mVolts, 0x0, turnon_delay, \
-			0x0, TWL6030, twl6030fixed_ops, 0x0)
+			0x0, TWL6030, twl6030fixed_ops, NULL)
 
 #define TWL4030_ADJUSTABLE_LDO(label, offset, num, turnon_delay, remap_conf) \
 static const struct twlreg_info TWL4030_INFO_##label = { \
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 42b34cd1f002..fd2eff440098 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -228,7 +228,7 @@ check_XRC (struct ccw1         *de_ccw,
 	data->ga_extended |= 0x08; /* switch on 'Time Stamp Valid'   */
 	data->ga_extended |= 0x02; /* switch on 'Extended Parameter' */
 
-	rc = get_sync_clock(&data->ep_sys_time);
+	rc = get_phys_clock(&data->ep_sys_time);
 	/* Ignore return code if sync clock is switched off. */
 	if (rc == -EOPNOTSUPP || rc == -EACCES)
 		rc = 0;
@@ -339,7 +339,7 @@ static int check_XRC_on_prefix(struct PFX_eckd_data *pfxdata,
 	pfxdata->define_extent.ga_extended |= 0x02; /* 'Extended Parameter' */
 	pfxdata->validity.time_stamp = 1;	    /* 'Time Stamp Valid'   */
 
-	rc = get_sync_clock(&pfxdata->define_extent.ep_sys_time);
+	rc = get_phys_clock(&pfxdata->define_extent.ep_sys_time);
 	/* Ignore return code if sync clock is switched off. */
 	if (rc == -EOPNOTSUPP || rc == -EACCES)
 		rc = 0;
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 31d544a87ba9..e2fa759bf2ad 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -45,7 +45,6 @@ int dasd_gendisk_alloc(struct dasd_block *block)
 	gdp->major = DASD_MAJOR;
 	gdp->first_minor = base->devindex << DASD_PARTN_BITS;
 	gdp->fops = &dasd_device_operations;
-	gdp->driverfs_dev = &base->cdev->dev;
 
 	/*
 	 * Set device name.
@@ -76,7 +75,7 @@ int dasd_gendisk_alloc(struct dasd_block *block)
 	gdp->queue = block->request_queue;
 	block->gdp = gdp;
 	set_capacity(block->gdp, 0);
-	add_disk(block->gdp);
+	device_add_disk(&base->cdev->dev, block->gdp);
 	return 0;
 }
 
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index bed53c46dd90..fac1b51ea0de 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -615,9 +615,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->dcssblk_queue = blk_alloc_queue(GFP_KERNEL);
 	dev_info->gd->queue = dev_info->dcssblk_queue;
 	dev_info->gd->private_data = dev_info;
-	dev_info->gd->driverfs_dev = &dev_info->dev;
 	blk_queue_make_request(dev_info->dcssblk_queue, dcssblk_make_request);
 	blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, dev_info->dcssblk_queue);
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
 	set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors
@@ -655,7 +655,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 		goto put_dev;
 
 	get_device(&dev_info->dev);
-	add_disk(dev_info->gd);
+	device_add_disk(&dev_info->dev, dev_info->gd);
 
 	switch (dev_info->segment_type) {
 		case SEG_TYPE_SR:
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index e6f54d3b8969..9f16ea6964ec 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -512,7 +512,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 		goto out_queue;
 
 	rq->queuedata = scmdev;
-	bdev->gendisk->driverfs_dev = &scmdev->dev;
 	bdev->gendisk->private_data = scmdev;
 	bdev->gendisk->fops = &scm_blk_devops;
 	bdev->gendisk->queue = rq;
@@ -531,7 +530,7 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 
 	/* 512 byte sectors */
 	set_capacity(bdev->gendisk, scmdev->size >> 9);
-	add_disk(bdev->gendisk);
+	device_add_disk(&scmdev->dev, bdev->gendisk);
 	return 0;
 
 out_queue:
diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c
index ef04a9f7a704..7b9c50aa4cc9 100644
--- a/drivers/s390/char/keyboard.c
+++ b/drivers/s390/char/keyboard.c
@@ -438,18 +438,9 @@ do_kdgkb_ioctl(struct kbd_data *kbd, struct kbsentry __user *u_kbs,
 			return -EFAULT;
 		if (len > sizeof(u_kbs->kb_string))
 			return -EINVAL;
-		p = kmalloc(len, GFP_KERNEL);
-		if (!p)
-			return -ENOMEM;
-		if (copy_from_user(p, u_kbs->kb_string, len)) {
-			kfree(p);
-			return -EFAULT;
-		}
-		/*
-		 * Make sure the string is terminated by 0. User could have
-		 * modified it between us running strnlen_user() and copying it.
-		 */
-		p[len - 1] = 0;
+		p = memdup_user_nul(u_kbs->kb_string, len);
+		if (IS_ERR(p))
+			return PTR_ERR(p);
 		kfree(kbd->func_table[kb_func]);
 		kbd->func_table[kb_func] = p;
 		break;
diff --git a/drivers/s390/char/sclp_con.c b/drivers/s390/char/sclp_con.c
index 5880def98fc1..6037bc87e767 100644
--- a/drivers/s390/char/sclp_con.c
+++ b/drivers/s390/char/sclp_con.c
@@ -319,7 +319,8 @@ sclp_console_init(void)
 	int i;
 	int rc;
 
-	if (!CONSOLE_IS_SCLP)
+	/* SCLP consoles are handled together */
+	if (!(CONSOLE_IS_SCLP || CONSOLE_IS_VT220))
 		return 0;
 	rc = sclp_rw_init();
 	if (rc)
diff --git a/drivers/s390/char/sclp_config.c b/drivers/s390/char/sclp_config.c
index 2ced50ccca63..1406fb688a26 100644
--- a/drivers/s390/char/sclp_config.c
+++ b/drivers/s390/char/sclp_config.c
@@ -47,7 +47,7 @@ static void sclp_cpu_capability_notify(struct work_struct *work)
 	int cpu;
 	struct device *dev;
 
-	s390_adjust_jiffies();
+	s390_update_cpu_mhz();
 	pr_info("CPU capability may have changed\n");
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 5043ecfa1fbc..16992e2a40ad 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -185,7 +185,7 @@ static ssize_t zcore_reipl_write(struct file *filp, const char __user *buf,
 {
 	if (ipl_block) {
 		diag308(DIAG308_SET, ipl_block);
-		diag308(DIAG308_IPL, NULL);
+		diag308(DIAG308_LOAD_CLEAR, NULL);
 	}
 	return count;
 }
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index 50597f9522fe..e96aced58627 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -47,8 +47,6 @@ static DEFINE_MUTEX(info_lock);
 /* Time after which channel-path status may be outdated. */
 static unsigned long chp_info_expires;
 
-/* Workqueue to perform pending configure tasks. */
-static struct workqueue_struct *chp_wq;
 static struct work_struct cfg_work;
 
 /* Wait queue for configure completion events. */
@@ -428,11 +426,14 @@ int chp_update_desc(struct channel_path *chp)
 	if (rc)
 		return rc;
 
-	rc = chsc_determine_fmt1_channel_path_desc(chp->chpid, &chp->desc_fmt1);
-	if (rc)
-		return rc;
+	/*
+	 * Fetching the following data is optional. Not all machines or
+	 * hypervisors implement the required chsc commands.
+	 */
+	chsc_determine_fmt1_channel_path_desc(chp->chpid, &chp->desc_fmt1);
+	chsc_get_channel_measurement_chars(chp);
 
-	return chsc_get_channel_measurement_chars(chp);
+	return 0;
 }
 
 /**
@@ -714,7 +715,7 @@ static void cfg_func(struct work_struct *work)
 		wake_up_interruptible(&cfg_wait_queue);
 		return;
 	}
-	queue_work(chp_wq, &cfg_work);
+	schedule_work(&cfg_work);
 }
 
 /**
@@ -732,7 +733,7 @@ void chp_cfg_schedule(struct chp_id chpid, int configure)
 	cfg_set_task(chpid, configure ? cfg_configure : cfg_deconfigure);
 	cfg_busy = 1;
 	mutex_unlock(&cfg_lock);
-	queue_work(chp_wq, &cfg_work);
+	schedule_work(&cfg_work);
 }
 
 /**
@@ -766,11 +767,6 @@ static int __init chp_init(void)
 	ret = crw_register_handler(CRW_RSC_CPATH, chp_process_crw);
 	if (ret)
 		return ret;
-	chp_wq = create_singlethread_workqueue("cio_chp");
-	if (!chp_wq) {
-		crw_unregister_handler(CRW_RSC_CPATH);
-		return -ENOMEM;
-	}
 	INIT_WORK(&cfg_work, cfg_func);
 	init_waitqueue_head(&cfg_wait_queue);
 	if (info_update())
diff --git a/drivers/s390/cio/chp.h b/drivers/s390/cio/chp.h
index af0232290dc4..bb5a68226cda 100644
--- a/drivers/s390/cio/chp.h
+++ b/drivers/s390/cio/chp.h
@@ -4,7 +4,7 @@
  */
 
 #ifndef S390_CHP_H
-#define S390_CHP_H S390_CHP_H
+#define S390_CHP_H
 
 #include <linux/types.h>
 #include <linux/device.h>
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index c424c0c7367e..940e725bde1e 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -907,7 +907,8 @@ int chsc_determine_channel_path_desc(struct chp_id chpid, int fmt, int rfmt,
 	struct chsc_scpd *scpd_area;
 	int ccode, ret;
 
-	if ((rfmt == 1) && !css_general_characteristics.fcs)
+	if ((rfmt == 1 || rfmt == 0) && c == 1 &&
+	    !css_general_characteristics.fcs)
 		return -EINVAL;
 	if ((rfmt == 2) && !css_general_characteristics.cib)
 		return -EINVAL;
@@ -939,7 +940,6 @@ EXPORT_SYMBOL_GPL(chsc_determine_channel_path_desc);
 int chsc_determine_base_channel_path_desc(struct chp_id chpid,
 					  struct channel_path_desc *desc)
 {
-	struct chsc_response_struct *chsc_resp;
 	struct chsc_scpd *scpd_area;
 	unsigned long flags;
 	int ret;
@@ -949,8 +949,8 @@ int chsc_determine_base_channel_path_desc(struct chp_id chpid,
 	ret = chsc_determine_channel_path_desc(chpid, 0, 0, 0, 0, scpd_area);
 	if (ret)
 		goto out;
-	chsc_resp = (void *)&scpd_area->response;
-	memcpy(desc, &chsc_resp->data, sizeof(*desc));
+
+	memcpy(desc, scpd_area->data, sizeof(*desc));
 out:
 	spin_unlock_irqrestore(&chsc_page_lock, flags);
 	return ret;
@@ -959,18 +959,17 @@ out:
 int chsc_determine_fmt1_channel_path_desc(struct chp_id chpid,
 					  struct channel_path_desc_fmt1 *desc)
 {
-	struct chsc_response_struct *chsc_resp;
 	struct chsc_scpd *scpd_area;
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&chsc_page_lock, flags);
 	scpd_area = chsc_page;
-	ret = chsc_determine_channel_path_desc(chpid, 0, 0, 1, 0, scpd_area);
+	ret = chsc_determine_channel_path_desc(chpid, 0, 1, 1, 0, scpd_area);
 	if (ret)
 		goto out;
-	chsc_resp = (void *)&scpd_area->response;
-	memcpy(desc, &chsc_resp->data, sizeof(*desc));
+
+	memcpy(desc, scpd_area->data, sizeof(*desc));
 out:
 	spin_unlock_irqrestore(&chsc_page_lock, flags);
 	return ret;
@@ -1020,7 +1019,7 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 	chp->cmg = -1;
 
 	if (!css_chsc_characteristics.scmc || !css_chsc_characteristics.secm)
-		return 0;
+		return -EINVAL;
 
 	spin_lock_irq(&chsc_page_lock);
 	memset(chsc_page, 0, PAGE_SIZE);
@@ -1176,7 +1175,7 @@ exit:
 EXPORT_SYMBOL_GPL(css_general_characteristics);
 EXPORT_SYMBOL_GPL(css_chsc_characteristics);
 
-int chsc_sstpc(void *page, unsigned int op, u16 ctrl)
+int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta)
 {
 	struct {
 		struct chsc_header request;
@@ -1186,7 +1185,9 @@ int chsc_sstpc(void *page, unsigned int op, u16 ctrl)
 		unsigned int ctrl : 16;
 		unsigned int rsvd2[5];
 		struct chsc_header response;
-		unsigned int rsvd3[7];
+		unsigned int rsvd3[3];
+		u64 clock_delta;
+		unsigned int rsvd4[2];
 	} __attribute__ ((packed)) *rr;
 	int rc;
 
@@ -1200,6 +1201,8 @@ int chsc_sstpc(void *page, unsigned int op, u16 ctrl)
 	if (rc)
 		return -EIO;
 	rc = (rr->response.code == 0x0001) ? 0 : -EIO;
+	if (clock_delta)
+		*clock_delta = rr->clock_delta;
 	return rc;
 }
 
diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h
index 0de134c3a204..67c87b6e63ec 100644
--- a/drivers/s390/cio/chsc.h
+++ b/drivers/s390/cio/chsc.h
@@ -112,8 +112,9 @@ struct chsc_scpd {
 	u32 last_chpid:8;
 	u32 zeroes1;
 	struct chsc_header response;
-	u8 data[PAGE_SIZE - 20];
-} __attribute__ ((packed));
+	u32:32;
+	u8 data[0];
+} __packed;
 
 struct chsc_sda_area {
 	struct chsc_header request;
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index b6f12c2bb114..735052ecd3e5 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -552,7 +552,7 @@ static int chsc_ioctl_info_cu(void __user *user_cd)
 		goto out_free;
 	}
 	scucd_area->request.length = 0x0010;
-	scucd_area->request.code = 0x0028;
+	scucd_area->request.code = 0x0026;
 	scucd_area->m = cd->m;
 	scucd_area->fmt1 = cd->fmt;
 	scucd_area->cssid = cd->cssid;
diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c
index b2afad5a5682..268aa23afa01 100644
--- a/drivers/s390/cio/cmf.c
+++ b/drivers/s390/cio/cmf.c
@@ -164,6 +164,9 @@ static inline u64 time_to_avg_nsec(u32 value, u32 count)
 	return ret;
 }
 
+#define CMF_OFF 0
+#define CMF_ON	2
+
 /*
  * Activate or deactivate the channel monitor. When area is NULL,
  * the monitor is deactivated. The channel monitor needs to
@@ -176,7 +179,7 @@ static inline void cmf_activate(void *area, unsigned int onoff)
 	register long __gpr1 asm("1");
 
 	__gpr2 = area;
-	__gpr1 = onoff ? 2 : 0;
+	__gpr1 = onoff;
 	/* activate channel measurement */
 	asm("schm" : : "d" (__gpr2), "d" (__gpr1) );
 }
@@ -587,7 +590,7 @@ static int alloc_cmb(struct ccw_device *cdev)
 			/* everything ok */
 			memset(mem, 0, size);
 			cmb_area.mem = mem;
-			cmf_activate(cmb_area.mem, 1);
+			cmf_activate(cmb_area.mem, CMF_ON);
 		}
 	}
 
@@ -621,7 +624,7 @@ static void free_cmb(struct ccw_device *cdev)
 	if (list_empty(&cmb_area.list)) {
 		ssize_t size;
 		size = sizeof(struct cmb) * cmb_area.num_channels;
-		cmf_activate(NULL, 0);
+		cmf_activate(NULL, CMF_OFF);
 		free_pages((unsigned long)cmb_area.mem, get_order(size));
 		cmb_area.mem = NULL;
 	}
@@ -753,6 +756,17 @@ static void reset_cmb(struct ccw_device *cdev)
 	cmf_generic_reset(cdev);
 }
 
+static int cmf_enabled(struct ccw_device *cdev)
+{
+	int enabled;
+
+	spin_lock_irq(cdev->ccwlock);
+	enabled = !!cdev->private->cmb;
+	spin_unlock_irq(cdev->ccwlock);
+
+	return enabled;
+}
+
 static struct attribute_group cmf_attr_group;
 
 static struct cmb_operations cmbops_basic = {
@@ -830,7 +844,7 @@ static int alloc_cmbe(struct ccw_device *cdev)
 
 	/* activate global measurement if this is the first channel */
 	if (list_empty(&cmb_area.list))
-		cmf_activate(NULL, 1);
+		cmf_activate(NULL, CMF_ON);
 	list_add_tail(&cdev->private->cmb_list, &cmb_area.list);
 
 	spin_unlock_irq(cdev->ccwlock);
@@ -867,7 +881,7 @@ static void free_cmbe(struct ccw_device *cdev)
 	/* deactivate global measurement if this is the last channel */
 	list_del_init(&cdev->private->cmb_list);
 	if (list_empty(&cmb_area.list))
-		cmf_activate(NULL, 0);
+		cmf_activate(NULL, CMF_OFF);
 	spin_unlock_irq(cdev->ccwlock);
 	spin_unlock(&cmb_area.lock);
 }
@@ -1153,13 +1167,8 @@ static ssize_t cmb_enable_show(struct device *dev,
 			       char *buf)
 {
 	struct ccw_device *cdev = to_ccwdev(dev);
-	int enabled;
 
-	spin_lock_irq(cdev->ccwlock);
-	enabled = !!cdev->private->cmb;
-	spin_unlock_irq(cdev->ccwlock);
-
-	return sprintf(buf, "%d\n", enabled);
+	return sprintf(buf, "%d\n", cmf_enabled(cdev));
 }
 
 static ssize_t cmb_enable_store(struct device *dev,
@@ -1199,15 +1208,20 @@ int ccw_set_cmf(struct ccw_device *cdev, int enable)
  *  @cdev:	The ccw device to be enabled
  *
  *  Returns %0 for success or a negative error value.
- *
+ *  Note: If this is called on a device for which channel measurement is already
+ *	  enabled a reset of the measurement data is triggered.
  *  Context:
  *    non-atomic
  */
 int enable_cmf(struct ccw_device *cdev)
 {
-	int ret;
+	int ret = 0;
 
 	device_lock(&cdev->dev);
+	if (cmf_enabled(cdev)) {
+		cmbops->reset(cdev);
+		goto out_unlock;
+	}
 	get_device(&cdev->dev);
 	ret = cmbops->alloc(cdev);
 	if (ret)
@@ -1226,7 +1240,7 @@ int enable_cmf(struct ccw_device *cdev)
 out:
 	if (ret)
 		put_device(&cdev->dev);
-
+out_unlock:
 	device_unlock(&cdev->dev);
 	return ret;
 }
@@ -1321,7 +1335,7 @@ void cmf_reactivate(void)
 {
 	spin_lock(&cmb_area.lock);
 	if (!list_empty(&cmb_area.list))
-		cmf_activate(cmb_area.mem, 1);
+		cmf_activate(cmb_area.mem, CMF_ON);
 	spin_unlock(&cmb_area.lock);
 }
 
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index a69f702a2fcc..877d9f601e63 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -97,7 +97,7 @@ void ccw_device_clear_options(struct ccw_device *cdev, unsigned long flags)
 }
 
 /**
- * ccw_device_is_pathgroup - determine if paths to this device are grouped
+ * ccw_device_is_pathgroup() - determine if paths to this device are grouped
  * @cdev: ccw device
  *
  * Return non-zero if there is a path group, zero otherwise.
@@ -109,7 +109,7 @@ int ccw_device_is_pathgroup(struct ccw_device *cdev)
 EXPORT_SYMBOL(ccw_device_is_pathgroup);
 
 /**
- * ccw_device_is_multipath - determine if device is operating in multipath mode
+ * ccw_device_is_multipath() - determine if device is operating in multipath mode
  * @cdev: ccw device
  *
  * Return non-zero if device is operating in multipath mode, zero otherwise.
@@ -457,7 +457,7 @@ __u8 ccw_device_get_path_mask(struct ccw_device *cdev)
 }
 
 /**
- * chp_get_chp_desc - return newly allocated channel-path descriptor
+ * ccw_device_get_chp_desc() - return newly allocated channel-path descriptor
  * @cdev: device to obtain the descriptor for
  * @chp_idx: index of the channel path
  *
@@ -477,7 +477,7 @@ struct channel_path_desc *ccw_device_get_chp_desc(struct ccw_device *cdev,
 }
 
 /**
- * ccw_device_get_id - obtain a ccw device id
+ * ccw_device_get_id() - obtain a ccw device id
  * @cdev: device to obtain the id for
  * @dev_id: where to fill in the values
  */
@@ -488,7 +488,7 @@ void ccw_device_get_id(struct ccw_device *cdev, struct ccw_dev_id *dev_id)
 EXPORT_SYMBOL(ccw_device_get_id);
 
 /**
- * ccw_device_tm_start_key - perform start function
+ * ccw_device_tm_start_key() - perform start function
  * @cdev: ccw device on which to perform the start function
  * @tcw: transport-command word to be started
  * @intparm: user defined parameter to be passed to the interrupt handler
@@ -533,7 +533,7 @@ int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw,
 EXPORT_SYMBOL(ccw_device_tm_start_key);
 
 /**
- * ccw_device_tm_start_timeout_key - perform start function
+ * ccw_device_tm_start_timeout_key() - perform start function
  * @cdev: ccw device on which to perform the start function
  * @tcw: transport-command word to be started
  * @intparm: user defined parameter to be passed to the interrupt handler
@@ -559,7 +559,7 @@ int ccw_device_tm_start_timeout_key(struct ccw_device *cdev, struct tcw *tcw,
 EXPORT_SYMBOL(ccw_device_tm_start_timeout_key);
 
 /**
- * ccw_device_tm_start - perform start function
+ * ccw_device_tm_start() - perform start function
  * @cdev: ccw device on which to perform the start function
  * @tcw: transport-command word to be started
  * @intparm: user defined parameter to be passed to the interrupt handler
@@ -577,7 +577,7 @@ int ccw_device_tm_start(struct ccw_device *cdev, struct tcw *tcw,
 EXPORT_SYMBOL(ccw_device_tm_start);
 
 /**
- * ccw_device_tm_start_timeout - perform start function
+ * ccw_device_tm_start_timeout() - perform start function
  * @cdev: ccw device on which to perform the start function
  * @tcw: transport-command word to be started
  * @intparm: user defined parameter to be passed to the interrupt handler
@@ -596,7 +596,7 @@ int ccw_device_tm_start_timeout(struct ccw_device *cdev, struct tcw *tcw,
 EXPORT_SYMBOL(ccw_device_tm_start_timeout);
 
 /**
- * ccw_device_get_mdc - accumulate max data count
+ * ccw_device_get_mdc() - accumulate max data count
  * @cdev: ccw device for which the max data count is accumulated
  * @mask: mask of paths to use
  *
@@ -642,7 +642,7 @@ int ccw_device_get_mdc(struct ccw_device *cdev, u8 mask)
 EXPORT_SYMBOL(ccw_device_get_mdc);
 
 /**
- * ccw_device_tm_intrg - perform interrogate function
+ * ccw_device_tm_intrg() - perform interrogate function
  * @cdev: ccw device on which to perform the interrogate function
  *
  * Perform an interrogate function on the given ccw device. Return zero on
@@ -664,7 +664,7 @@ int ccw_device_tm_intrg(struct ccw_device *cdev)
 EXPORT_SYMBOL(ccw_device_tm_intrg);
 
 /**
- * ccw_device_get_schid - obtain a subchannel id
+ * ccw_device_get_schid() - obtain a subchannel id
  * @cdev: device to obtain the id for
  * @schid: where to fill in the values
  */
diff --git a/drivers/s390/cio/idset.h b/drivers/s390/cio/idset.h
index 22b58104683b..89a787790888 100644
--- a/drivers/s390/cio/idset.h
+++ b/drivers/s390/cio/idset.h
@@ -4,7 +4,7 @@
  */
 
 #ifndef S390_IDSET_H
-#define S390_IDSET_H S390_IDSET_H
+#define S390_IDSET_H
 
 #include <asm/schid.h>
 
diff --git a/drivers/s390/cio/ioasm.c b/drivers/s390/cio/ioasm.c
index 98984818618f..8225da619014 100644
--- a/drivers/s390/cio/ioasm.c
+++ b/drivers/s390/cio/ioasm.c
@@ -12,7 +12,7 @@
 #include "orb.h"
 #include "cio.h"
 
-int stsch(struct subchannel_id schid, struct schib *addr)
+static inline int __stsch(struct subchannel_id schid, struct schib *addr)
 {
 	register struct subchannel_id reg1 asm ("1") = schid;
 	int ccode = -EIO;
@@ -26,13 +26,21 @@ int stsch(struct subchannel_id schid, struct schib *addr)
 		: "+d" (ccode), "=m" (*addr)
 		: "d" (reg1), "a" (addr)
 		: "cc");
+	return ccode;
+}
+
+int stsch(struct subchannel_id schid, struct schib *addr)
+{
+	int ccode;
+
+	ccode = __stsch(schid, addr);
 	trace_s390_cio_stsch(schid, addr, ccode);
 
 	return ccode;
 }
 EXPORT_SYMBOL(stsch);
 
-int msch(struct subchannel_id schid, struct schib *addr)
+static inline int __msch(struct subchannel_id schid, struct schib *addr)
 {
 	register struct subchannel_id reg1 asm ("1") = schid;
 	int ccode = -EIO;
@@ -46,12 +54,20 @@ int msch(struct subchannel_id schid, struct schib *addr)
 		: "+d" (ccode)
 		: "d" (reg1), "a" (addr), "m" (*addr)
 		: "cc");
+	return ccode;
+}
+
+int msch(struct subchannel_id schid, struct schib *addr)
+{
+	int ccode;
+
+	ccode = __msch(schid, addr);
 	trace_s390_cio_msch(schid, addr, ccode);
 
 	return ccode;
 }
 
-int tsch(struct subchannel_id schid, struct irb *addr)
+static inline int __tsch(struct subchannel_id schid, struct irb *addr)
 {
 	register struct subchannel_id reg1 asm ("1") = schid;
 	int ccode;
@@ -63,12 +79,20 @@ int tsch(struct subchannel_id schid, struct irb *addr)
 		: "=d" (ccode), "=m" (*addr)
 		: "d" (reg1), "a" (addr)
 		: "cc");
+	return ccode;
+}
+
+int tsch(struct subchannel_id schid, struct irb *addr)
+{
+	int ccode;
+
+	ccode = __tsch(schid, addr);
 	trace_s390_cio_tsch(schid, addr, ccode);
 
 	return ccode;
 }
 
-int ssch(struct subchannel_id schid, union orb *addr)
+static inline int __ssch(struct subchannel_id schid, union orb *addr)
 {
 	register struct subchannel_id reg1 asm("1") = schid;
 	int ccode = -EIO;
@@ -82,13 +106,21 @@ int ssch(struct subchannel_id schid, union orb *addr)
 		: "+d" (ccode)
 		: "d" (reg1), "a" (addr), "m" (*addr)
 		: "cc", "memory");
+	return ccode;
+}
+
+int ssch(struct subchannel_id schid, union orb *addr)
+{
+	int ccode;
+
+	ccode = __ssch(schid, addr);
 	trace_s390_cio_ssch(schid, addr, ccode);
 
 	return ccode;
 }
 EXPORT_SYMBOL(ssch);
 
-int csch(struct subchannel_id schid)
+static inline int __csch(struct subchannel_id schid)
 {
 	register struct subchannel_id reg1 asm("1") = schid;
 	int ccode;
@@ -100,6 +132,14 @@ int csch(struct subchannel_id schid)
 		: "=d" (ccode)
 		: "d" (reg1)
 		: "cc");
+	return ccode;
+}
+
+int csch(struct subchannel_id schid)
+{
+	int ccode;
+
+	ccode = __csch(schid);
 	trace_s390_cio_csch(schid, ccode);
 
 	return ccode;
@@ -140,7 +180,7 @@ int chsc(void *chsc_area)
 }
 EXPORT_SYMBOL(chsc);
 
-int rchp(struct chp_id chpid)
+static inline int __rchp(struct chp_id chpid)
 {
 	register struct chp_id reg1 asm ("1") = chpid;
 	int ccode;
@@ -151,12 +191,20 @@ int rchp(struct chp_id chpid)
 		"	ipm	%0\n"
 		"	srl	%0,28"
 		: "=d" (ccode) : "d" (reg1) : "cc");
+	return ccode;
+}
+
+int rchp(struct chp_id chpid)
+{
+	int ccode;
+
+	ccode = __rchp(chpid);
 	trace_s390_cio_rchp(chpid, ccode);
 
 	return ccode;
 }
 
-int rsch(struct subchannel_id schid)
+static inline int __rsch(struct subchannel_id schid)
 {
 	register struct subchannel_id reg1 asm("1") = schid;
 	int ccode;
@@ -168,12 +216,21 @@ int rsch(struct subchannel_id schid)
 		: "=d" (ccode)
 		: "d" (reg1)
 		: "cc", "memory");
+
+	return ccode;
+}
+
+int rsch(struct subchannel_id schid)
+{
+	int ccode;
+
+	ccode = __rsch(schid);
 	trace_s390_cio_rsch(schid, ccode);
 
 	return ccode;
 }
 
-int hsch(struct subchannel_id schid)
+static inline int __hsch(struct subchannel_id schid)
 {
 	register struct subchannel_id reg1 asm("1") = schid;
 	int ccode;
@@ -185,12 +242,20 @@ int hsch(struct subchannel_id schid)
 		: "=d" (ccode)
 		: "d" (reg1)
 		: "cc");
+	return ccode;
+}
+
+int hsch(struct subchannel_id schid)
+{
+	int ccode;
+
+	ccode = __hsch(schid);
 	trace_s390_cio_hsch(schid, ccode);
 
 	return ccode;
 }
 
-int xsch(struct subchannel_id schid)
+static inline int __xsch(struct subchannel_id schid)
 {
 	register struct subchannel_id reg1 asm("1") = schid;
 	int ccode;
@@ -202,6 +267,14 @@ int xsch(struct subchannel_id schid)
 		: "=d" (ccode)
 		: "d" (reg1)
 		: "cc");
+	return ccode;
+}
+
+int xsch(struct subchannel_id schid)
+{
+	int ccode;
+
+	ccode = __xsch(schid);
 	trace_s390_cio_xsch(schid, ccode);
 
 	return ccode;
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 327255da115a..4feb27215ab6 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -169,6 +169,19 @@ static int ap_configuration_available(void)
 	return test_facility(12);
 }
 
+static inline struct ap_queue_status
+__pqap_tapq(ap_qid_t qid, unsigned long *info)
+{
+	register unsigned long reg0 asm ("0") = qid;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2") = 0UL;
+
+	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
+		     : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
+	*info = reg2;
+	return reg1;
+}
+
 /**
  * ap_test_queue(): Test adjunct processor queue.
  * @qid: The AP queue number
@@ -179,17 +192,15 @@ static int ap_configuration_available(void)
 static inline struct ap_queue_status
 ap_test_queue(ap_qid_t qid, unsigned long *info)
 {
-	register unsigned long reg0 asm ("0") = qid;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
+	struct ap_queue_status aqs;
+	unsigned long _info;
 
 	if (test_facility(15))
-		reg0 |= 1UL << 23;		/* set APFT T bit*/
-	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
-		     : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
+		qid |= 1UL << 23;		/* set APFT T bit*/
+	aqs = __pqap_tapq(qid, &_info);
 	if (info)
-		*info = reg2;
-	return reg1;
+		*info = _info;
+	return aqs;
 }
 
 /**
@@ -237,14 +248,12 @@ ap_queue_interruption_control(ap_qid_t qid, void *ind)
  *
  * Returns 0 on success, or -EOPNOTSUPP.
  */
-static inline int ap_query_configuration(void)
+static inline int __ap_query_configuration(void)
 {
 	register unsigned long reg0 asm ("0") = 0x04000000UL;
 	register unsigned long reg1 asm ("1") = -EINVAL;
 	register void *reg2 asm ("2") = (void *) ap_configuration;
 
-	if (!ap_configuration)
-		return -EOPNOTSUPP;
 	asm volatile(
 		".long 0xb2af0000\n"		/* PQAP(QCI) */
 		"0: la    %1,0\n"
@@ -257,6 +266,13 @@ static inline int ap_query_configuration(void)
 	return reg1;
 }
 
+static inline int ap_query_configuration(void)
+{
+	if (!ap_configuration)
+		return -EOPNOTSUPP;
+	return __ap_query_configuration();
+}
+
 /**
  * ap_init_configuration(): Allocate and query configuration array.
  */
@@ -346,6 +362,26 @@ static int ap_queue_enable_interruption(struct ap_device *ap_dev, void *ind)
 	}
 }
 
+static inline struct ap_queue_status
+__nqap(ap_qid_t qid, unsigned long long psmid, void *msg, size_t length)
+{
+	typedef struct { char _[length]; } msgblock;
+	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2") = (unsigned long) msg;
+	register unsigned long reg3 asm ("3") = (unsigned long) length;
+	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
+	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
+
+	asm volatile (
+		"0: .long 0xb2ad0042\n"		/* NQAP */
+		"   brc   2,0b"
+		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
+		: "d" (reg4), "d" (reg5), "m" (*(msgblock *) msg)
+		: "cc");
+	return reg1;
+}
+
 /**
  * __ap_send(): Send message to adjunct processor queue.
  * @qid: The AP queue number
@@ -363,24 +399,9 @@ static inline struct ap_queue_status
 __ap_send(ap_qid_t qid, unsigned long long psmid, void *msg, size_t length,
 	  unsigned int special)
 {
-	typedef struct { char _[length]; } msgblock;
-	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = (unsigned long) msg;
-	register unsigned long reg3 asm ("3") = (unsigned long) length;
-	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
-	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
-
 	if (special == 1)
-		reg0 |= 0x400000UL;
-
-	asm volatile (
-		"0: .long 0xb2ad0042\n"		/* NQAP */
-		"   brc   2,0b"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
-		: "d" (reg4), "d" (reg5), "m" (*(msgblock *) msg)
-		: "cc" );
-	return reg1;
+		qid |= 0x400000UL;
+	return __nqap(qid, psmid, msg, length);
 }
 
 int ap_send(ap_qid_t qid, unsigned long long psmid, void *msg, size_t length)
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 935c43095109..497bc1558377 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -233,15 +233,8 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 	task->task_state_flags = SAS_TASK_STATE_PENDING;
 	qc->lldd_task = task;
 
-	switch (qc->tf.protocol) {
-	case ATA_PROT_NCQ:
-		task->ata_task.use_ncq = 1;
-		/* fall through */
-	case ATAPI_PROT_DMA:
-	case ATA_PROT_DMA:
-		task->ata_task.dma_xfer = 1;
-		break;
-	}
+	task->ata_task.use_ncq = ata_is_ncq(qc->tf.protocol);
+	task->ata_task.dma_xfer = ata_is_dma(qc->tf.protocol);
 
 	if (qc->scsicmd)
 		ASSIGN_SAS_TASK(qc->scsicmd, task);
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index 3b11aad03752..2f2a9910e30e 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -726,7 +726,7 @@ static int _osd_req_list_objects(struct osd_request *or,
 		return PTR_ERR(bio);
 	}
 
-	bio->bi_rw &= ~REQ_WRITE;
+	bio_set_op_attrs(bio, REQ_OP_READ, 0);
 	or->in.bio = bio;
 	or->in.total_bytes = bio->bi_iter.bi_size;
 	return 0;
@@ -824,7 +824,7 @@ void osd_req_write(struct osd_request *or,
 {
 	_osd_req_encode_common(or, OSD_ACT_WRITE, obj, offset, len);
 	WARN_ON(or->out.bio || or->out.total_bytes);
-	WARN_ON(0 == (bio->bi_rw & REQ_WRITE));
+	WARN_ON(!op_is_write(bio_op(bio)));
 	or->out.bio = bio;
 	or->out.total_bytes = len;
 }
@@ -839,7 +839,7 @@ int osd_req_write_kern(struct osd_request *or,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	bio->bi_rw |= REQ_WRITE; /* FIXME: bio_set_dir() */
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	osd_req_write(or, obj, offset, bio, len);
 	return 0;
 }
@@ -875,7 +875,7 @@ void osd_req_read(struct osd_request *or,
 {
 	_osd_req_encode_common(or, OSD_ACT_READ, obj, offset, len);
 	WARN_ON(or->in.bio || or->in.total_bytes);
-	WARN_ON(bio->bi_rw & REQ_WRITE);
+	WARN_ON(op_is_write(bio_op(bio)));
 	or->in.bio = bio;
 	or->in.total_bytes = len;
 }
@@ -956,7 +956,7 @@ static int _osd_req_finalize_cdb_cont(struct osd_request *or, const u8 *cap_key)
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	bio->bi_rw |= REQ_WRITE;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	/* integrity check the continuation before the bio is linked
 	 * with the other data segments since the continuation
@@ -1077,7 +1077,7 @@ int osd_req_write_sg_kern(struct osd_request *or,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	bio->bi_rw |= REQ_WRITE;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	osd_req_write_sg(or, obj, bio, sglist, numentries);
 
 	return 0;
@@ -1558,18 +1558,25 @@ static int _osd_req_finalize_data_integrity(struct osd_request *or,
 static struct request *_make_request(struct request_queue *q, bool has_write,
 			      struct _osd_io_info *oii, gfp_t flags)
 {
-	if (oii->bio)
-		return blk_make_request(q, oii->bio, flags);
-	else {
-		struct request *req;
-
-		req = blk_get_request(q, has_write ? WRITE : READ, flags);
-		if (IS_ERR(req))
-			return req;
+	struct request *req;
+	struct bio *bio = oii->bio;
+	int ret;
 
-		blk_rq_set_block_pc(req);
+	req = blk_get_request(q, has_write ? WRITE : READ, flags);
+	if (IS_ERR(req))
 		return req;
+	blk_rq_set_block_pc(req);
+
+	for_each_bio(bio) {
+		struct bio *bounce_bio = bio;
+
+		blk_queue_bounce(req->q, &bounce_bio);
+		ret = blk_rq_append_bio(req, bounce_bio);
+		if (ret)
+			return ERR_PTR(ret);
 	}
+
+	return req;
 }
 
 static int _init_blk_request(struct osd_request *or,
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 60bff78e9ead..d3e852ad5aa3 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1012,7 +1012,8 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
 	} else {
-		scmd_printk(KERN_ERR, SCpnt, "Unknown command %llx\n", (unsigned long long) rq->cmd_flags);
+		scmd_printk(KERN_ERR, SCpnt, "Unknown command %llu,%llx\n",
+			    req_op(rq), (unsigned long long) rq->cmd_flags);
 		goto out;
 	}
 
@@ -1137,21 +1138,26 @@ static int sd_init_command(struct scsi_cmnd *cmd)
 {
 	struct request *rq = cmd->request;
 
-	if (rq->cmd_flags & REQ_DISCARD)
+	switch (req_op(rq)) {
+	case REQ_OP_DISCARD:
 		return sd_setup_discard_cmnd(cmd);
-	else if (rq->cmd_flags & REQ_WRITE_SAME)
+	case REQ_OP_WRITE_SAME:
 		return sd_setup_write_same_cmnd(cmd);
-	else if (rq->cmd_flags & REQ_FLUSH)
+	case REQ_OP_FLUSH:
 		return sd_setup_flush_cmnd(cmd);
-	else
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
 		return sd_setup_read_write_cmnd(cmd);
+	default:
+		BUG();
+	}
 }
 
 static void sd_uninit_command(struct scsi_cmnd *SCpnt)
 {
 	struct request *rq = SCpnt->request;
 
-	if (rq->cmd_flags & REQ_DISCARD)
+	if (req_op(rq) == REQ_OP_DISCARD)
 		__free_page(rq->completion_data);
 
 	if (SCpnt->cmnd != rq->cmd) {
@@ -1613,8 +1619,7 @@ static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
 		return -EOPNOTSUPP;
 	return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
 			old_key, new_key, 0,
-			(1 << 0) /* APTPL */ |
-			(1 << 2) /* ALL_TG_PT */);
+			(1 << 0) /* APTPL */);
 }
 
 static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
@@ -1774,7 +1779,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 	unsigned char op = SCpnt->cmnd[0];
 	unsigned char unmap = SCpnt->cmnd[1] & 8;
 
-	if (req->cmd_flags & REQ_DISCARD || req->cmd_flags & REQ_WRITE_SAME) {
+	if (req_op(req) == REQ_OP_DISCARD || req_op(req) == REQ_OP_WRITE_SAME) {
 		if (!result) {
 			good_bytes = blk_rq_bytes(req);
 			scsi_set_resid(SCpnt, 0);
@@ -2988,7 +2993,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 
 	sd_revalidate_disk(gd);
 
-	gd->driverfs_dev = &sdp->sdev_gendev;
 	gd->flags = GENHD_FL_EXT_DEVT;
 	if (sdp->removable) {
 		gd->flags |= GENHD_FL_REMOVABLE;
@@ -2996,7 +3000,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 	}
 
 	blk_pm_runtime_init(sdp->request_queue, dev);
-	add_disk(gd);
+	device_add_disk(dev, gd);
 	if (sdkp->capacity)
 		sd_dif_config_host(sdkp);
 
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 64c867405ad4..ed179348de80 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -713,7 +713,6 @@ static int sr_probe(struct device *dev)
 	get_capabilities(cd);
 	sr_vendor_init(cd);
 
-	disk->driverfs_dev = &sdev->sdev_gendev;
 	set_capacity(disk, cd->capacity);
 	disk->private_data = &cd->driver;
 	disk->queue = sdev->request_queue;
@@ -730,7 +729,7 @@ static int sr_probe(struct device *dev)
 
 	dev_set_drvdata(dev, cd);
 	disk->flags |= GENHD_FL_REMOVABLE;
-	add_disk(disk);
+	device_add_disk(&sdev->sdev_gendev, disk);
 
 	sdev_printk(KERN_DEBUG, sdev,
 		    "Attached scsi CD-ROM %s\n", cd->cdi.name);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 77e6e45951f4..7589c8af4368 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -622,6 +622,8 @@ void spi_unregister_device(struct spi_device *spi)
 
 	if (spi->dev.of_node)
 		of_node_clear_flag(spi->dev.of_node, OF_POPULATED);
+	if (ACPI_COMPANION(&spi->dev))
+		acpi_device_clear_enumerated(ACPI_COMPANION(&spi->dev));
 	device_unregister(&spi->dev);
 }
 EXPORT_SYMBOL_GPL(spi_unregister_device);
@@ -1646,18 +1648,15 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 	return 1;
 }
 
-static acpi_status acpi_spi_add_device(acpi_handle handle, u32 level,
-				       void *data, void **return_value)
+static acpi_status acpi_register_spi_device(struct spi_master *master,
+					    struct acpi_device *adev)
 {
-	struct spi_master *master = data;
 	struct list_head resource_list;
-	struct acpi_device *adev;
 	struct spi_device *spi;
 	int ret;
 
-	if (acpi_bus_get_device(handle, &adev))
-		return AE_OK;
-	if (acpi_bus_get_status(adev) || !adev->status.present)
+	if (acpi_bus_get_status(adev) || !adev->status.present ||
+	    acpi_device_enumerated(adev))
 		return AE_OK;
 
 	spi = spi_alloc_device(master);
@@ -1683,6 +1682,8 @@ static acpi_status acpi_spi_add_device(acpi_handle handle, u32 level,
 	if (spi->irq < 0)
 		spi->irq = acpi_dev_gpio_irq_get(adev, 0);
 
+	acpi_device_set_enumerated(adev);
+
 	adev->power.flags.ignore_parent = true;
 	strlcpy(spi->modalias, acpi_device_hid(adev), sizeof(spi->modalias));
 	if (spi_add_device(spi)) {
@@ -1695,6 +1696,18 @@ static acpi_status acpi_spi_add_device(acpi_handle handle, u32 level,
 	return AE_OK;
 }
 
+static acpi_status acpi_spi_add_device(acpi_handle handle, u32 level,
+				       void *data, void **return_value)
+{
+	struct spi_master *master = data;
+	struct acpi_device *adev;
+
+	if (acpi_bus_get_device(handle, &adev))
+		return AE_OK;
+
+	return acpi_register_spi_device(master, adev);
+}
+
 static void acpi_register_spi_devices(struct spi_master *master)
 {
 	acpi_status status;
@@ -3107,6 +3120,77 @@ static struct notifier_block spi_of_notifier = {
 extern struct notifier_block spi_of_notifier;
 #endif /* IS_ENABLED(CONFIG_OF_DYNAMIC) */
 
+#if IS_ENABLED(CONFIG_ACPI)
+static int spi_acpi_master_match(struct device *dev, const void *data)
+{
+	return ACPI_COMPANION(dev->parent) == data;
+}
+
+static int spi_acpi_device_match(struct device *dev, void *data)
+{
+	return ACPI_COMPANION(dev) == data;
+}
+
+static struct spi_master *acpi_spi_find_master_by_adev(struct acpi_device *adev)
+{
+	struct device *dev;
+
+	dev = class_find_device(&spi_master_class, NULL, adev,
+				spi_acpi_master_match);
+	if (!dev)
+		return NULL;
+
+	return container_of(dev, struct spi_master, dev);
+}
+
+static struct spi_device *acpi_spi_find_device_by_adev(struct acpi_device *adev)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&spi_bus_type, NULL, adev, spi_acpi_device_match);
+
+	return dev ? to_spi_device(dev) : NULL;
+}
+
+static int acpi_spi_notify(struct notifier_block *nb, unsigned long value,
+			   void *arg)
+{
+	struct acpi_device *adev = arg;
+	struct spi_master *master;
+	struct spi_device *spi;
+
+	switch (value) {
+	case ACPI_RECONFIG_DEVICE_ADD:
+		master = acpi_spi_find_master_by_adev(adev->parent);
+		if (!master)
+			break;
+
+		acpi_register_spi_device(master, adev);
+		put_device(&master->dev);
+		break;
+	case ACPI_RECONFIG_DEVICE_REMOVE:
+		if (!acpi_device_enumerated(adev))
+			break;
+
+		spi = acpi_spi_find_device_by_adev(adev);
+		if (!spi)
+			break;
+
+		spi_unregister_device(spi);
+		put_device(&spi->dev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block spi_acpi_notifier = {
+	.notifier_call = acpi_spi_notify,
+};
+#else
+extern struct notifier_block spi_acpi_notifier;
+#endif
+
 static int __init spi_init(void)
 {
 	int	status;
@@ -3127,6 +3211,8 @@ static int __init spi_init(void)
 
 	if (IS_ENABLED(CONFIG_OF_DYNAMIC))
 		WARN_ON(of_reconfig_notifier_register(&spi_of_notifier));
+	if (IS_ENABLED(CONFIG_ACPI))
+		WARN_ON(acpi_reconfig_notifier_register(&spi_acpi_notifier));
 
 	return 0;
 
diff --git a/drivers/staging/media/Kconfig b/drivers/staging/media/Kconfig
index de7e9f52e7eb..cae42e56f270 100644
--- a/drivers/staging/media/Kconfig
+++ b/drivers/staging/media/Kconfig
@@ -21,24 +21,20 @@ if STAGING_MEDIA
 # Please keep them in alphabetic order
 source "drivers/staging/media/bcm2048/Kconfig"
 
+source "drivers/staging/media/cec/Kconfig"
+
 source "drivers/staging/media/cxd2099/Kconfig"
 
 source "drivers/staging/media/davinci_vpfe/Kconfig"
 
-source "drivers/staging/media/mn88472/Kconfig"
-
-source "drivers/staging/media/mx2/Kconfig"
-
-source "drivers/staging/media/mx3/Kconfig"
-
-source "drivers/staging/media/omap1/Kconfig"
-
 source "drivers/staging/media/omap4iss/Kconfig"
 
-source "drivers/staging/media/timb/Kconfig"
+source "drivers/staging/media/pulse8-cec/Kconfig"
 
 source "drivers/staging/media/tw686x-kh/Kconfig"
 
+source "drivers/staging/media/s5p-cec/Kconfig"
+
 # Keep LIRC at the end, as it has sub-menus
 source "drivers/staging/media/lirc/Kconfig"
 
diff --git a/drivers/staging/media/Makefile b/drivers/staging/media/Makefile
index 60a35b3a47e7..87ce8ad1e22a 100644
--- a/drivers/staging/media/Makefile
+++ b/drivers/staging/media/Makefile
@@ -1,11 +1,9 @@
 obj-$(CONFIG_I2C_BCM2048)	+= bcm2048/
+obj-$(CONFIG_MEDIA_CEC)		+= cec/
+obj-$(CONFIG_VIDEO_SAMSUNG_S5P_CEC) += s5p-cec/
 obj-$(CONFIG_DVB_CXD2099)	+= cxd2099/
 obj-$(CONFIG_LIRC_STAGING)	+= lirc/
 obj-$(CONFIG_VIDEO_DM365_VPFE)	+= davinci_vpfe/
-obj-$(CONFIG_VIDEO_MX2)		+= mx2/
-obj-$(CONFIG_VIDEO_MX3)		+= mx3/
-obj-$(CONFIG_VIDEO_OMAP1)	+= omap1/
 obj-$(CONFIG_VIDEO_OMAP4)	+= omap4iss/
-obj-$(CONFIG_DVB_MN88472)       += mn88472/
-obj-$(CONFIG_VIDEO_TIMBERDALE)  += timb/
+obj-$(CONFIG_USB_PULSE8_CEC)    += pulse8-cec/
 obj-$(CONFIG_VIDEO_TW686X_KH)	+= tw686x-kh/
diff --git a/drivers/staging/media/cec/Kconfig b/drivers/staging/media/cec/Kconfig
new file mode 100644
index 000000000000..21457a1f6c9f
--- /dev/null
+++ b/drivers/staging/media/cec/Kconfig
@@ -0,0 +1,15 @@
+config MEDIA_CEC
+	bool "CEC API (EXPERIMENTAL)"
+	depends on MEDIA_SUPPORT
+	select MEDIA_CEC_EDID
+	---help---
+	  Enable the CEC API.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called cec.
+
+config MEDIA_CEC_DEBUG
+	bool "CEC debugfs interface (EXPERIMENTAL)"
+	depends on MEDIA_CEC && DEBUG_FS
+	---help---
+	  Turns on the DebugFS interface for CEC devices.
diff --git a/drivers/staging/media/cec/Makefile b/drivers/staging/media/cec/Makefile
new file mode 100644
index 000000000000..bd7f3c593468
--- /dev/null
+++ b/drivers/staging/media/cec/Makefile
@@ -0,0 +1,5 @@
+cec-objs := cec-core.o cec-adap.o cec-api.o
+
+ifeq ($(CONFIG_MEDIA_CEC),y)
+  obj-$(CONFIG_MEDIA_SUPPORT) += cec.o
+endif
diff --git a/drivers/staging/media/cec/TODO b/drivers/staging/media/cec/TODO
new file mode 100644
index 000000000000..a10d4f82b954
--- /dev/null
+++ b/drivers/staging/media/cec/TODO
@@ -0,0 +1,31 @@
+The reason why cec.c is still in staging is that I would like
+to have a bit more confidence in the uABI. The kABI is fine,
+no problem there, but I would like to let the public API mature
+a bit.
+
+Once I'm confident that I didn't miss anything then the cec.c source
+can move to drivers/media and the linux/cec.h and linux/cec-funcs.h
+headers can move to uapi/linux and added to uapi/linux/Kbuild to make
+them public.
+
+Hopefully this will happen later in 2016.
+
+Other TODOs:
+
+- Add a flag to inhibit passing CEC RC messages to the rc subsystem.
+  Applications should be able to choose this when calling S_LOG_ADDRS.
+- If the reply field of cec_msg is set then when the reply arrives it
+  is only sent to the filehandle that transmitted the original message
+  and not to any followers. Should this behavior change or perhaps
+  controlled through a cec_msg flag?
+- Should CEC_LOG_ADDR_TYPE_SPECIFIC be replaced by TYPE_2ND_TV and TYPE_PROCESSOR?
+  And also TYPE_SWITCH and TYPE_CDC_ONLY in addition to the TYPE_UNREGISTERED?
+  This should give the framework more information about the device type
+  since SPECIFIC and UNREGISTERED give no useful information.
+- Once this is out of staging this should no longer be a separate
+  config option, instead it should be selected by drivers that want it.
+- Revisit the IS_REACHABLE(RC_CORE): perhaps the RC_CORE support should
+  be enabled through a separate config option in drivers/media/Kconfig
+  or rc/Kconfig?
+
+Hans Verkuil <hans.verkuil@cisco.com>
diff --git a/drivers/staging/media/cec/cec-adap.c b/drivers/staging/media/cec/cec-adap.c
new file mode 100644
index 000000000000..9fffddb7ac7e
--- /dev/null
+++ b/drivers/staging/media/cec/cec-adap.c
@@ -0,0 +1,1654 @@
+/*
+ * cec-adap.c - HDMI Consumer Electronics Control framework - CEC adapter
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kmod.h>
+#include <linux/ktime.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "cec-priv.h"
+
+static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx);
+static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx);
+
+/*
+ * 400 ms is the time it takes for one 16 byte message to be
+ * transferred and 5 is the maximum number of retries. Add
+ * another 100 ms as a margin. So if the transmit doesn't
+ * finish before that time something is really wrong and we
+ * have to time out.
+ *
+ * This is a sign that something it really wrong and a warning
+ * will be issued.
+ */
+#define CEC_XFER_TIMEOUT_MS (5 * 400 + 100)
+
+#define call_op(adap, op, arg...) \
+	(adap->ops->op ? adap->ops->op(adap, ## arg) : 0)
+
+#define call_void_op(adap, op, arg...)			\
+	do {						\
+		if (adap->ops->op)			\
+			adap->ops->op(adap, ## arg);	\
+	} while (0)
+
+static int cec_log_addr2idx(const struct cec_adapter *adap, u8 log_addr)
+{
+	int i;
+
+	for (i = 0; i < adap->log_addrs.num_log_addrs; i++)
+		if (adap->log_addrs.log_addr[i] == log_addr)
+			return i;
+	return -1;
+}
+
+static unsigned int cec_log_addr2dev(const struct cec_adapter *adap, u8 log_addr)
+{
+	int i = cec_log_addr2idx(adap, log_addr);
+
+	return adap->log_addrs.primary_device_type[i < 0 ? 0 : i];
+}
+
+/*
+ * Queue a new event for this filehandle. If ts == 0, then set it
+ * to the current time.
+ *
+ * The two events that are currently defined do not need to keep track
+ * of intermediate events, so no actual queue of events is needed,
+ * instead just store the latest state and the total number of lost
+ * messages.
+ *
+ * Should new events be added in the future that require intermediate
+ * results to be queued as well, then a proper queue data structure is
+ * required. But until then, just keep it simple.
+ */
+void cec_queue_event_fh(struct cec_fh *fh,
+			const struct cec_event *new_ev, u64 ts)
+{
+	struct cec_event *ev = &fh->events[new_ev->event - 1];
+
+	if (ts == 0)
+		ts = ktime_get_ns();
+
+	mutex_lock(&fh->lock);
+	if (new_ev->event == CEC_EVENT_LOST_MSGS &&
+	    fh->pending_events & (1 << new_ev->event)) {
+		/*
+		 * If there is already a lost_msgs event, then just
+		 * update the lost_msgs count. This effectively
+		 * merges the old and new events into one.
+		 */
+		ev->lost_msgs.lost_msgs += new_ev->lost_msgs.lost_msgs;
+		goto unlock;
+	}
+
+	/*
+	 * Intermediate states are not interesting, so just
+	 * overwrite any older event.
+	 */
+	*ev = *new_ev;
+	ev->ts = ts;
+	fh->pending_events |= 1 << new_ev->event;
+
+unlock:
+	mutex_unlock(&fh->lock);
+	wake_up_interruptible(&fh->wait);
+}
+
+/* Queue a new event for all open filehandles. */
+static void cec_queue_event(struct cec_adapter *adap,
+			    const struct cec_event *ev)
+{
+	u64 ts = ktime_get_ns();
+	struct cec_fh *fh;
+
+	mutex_lock(&adap->devnode.fhs_lock);
+	list_for_each_entry(fh, &adap->devnode.fhs, list)
+		cec_queue_event_fh(fh, ev, ts);
+	mutex_unlock(&adap->devnode.fhs_lock);
+}
+
+/*
+ * Queue a new message for this filehandle. If there is no more room
+ * in the queue, then send the LOST_MSGS event instead.
+ */
+static void cec_queue_msg_fh(struct cec_fh *fh, const struct cec_msg *msg)
+{
+	static const struct cec_event ev_lost_msg = {
+		.ts = 0,
+		.event = CEC_EVENT_LOST_MSGS,
+		.flags = 0,
+		{
+			.lost_msgs.lost_msgs = 1,
+		},
+	};
+	struct cec_msg_entry *entry;
+
+	mutex_lock(&fh->lock);
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		goto lost_msgs;
+
+	entry->msg = *msg;
+	/* Add new msg at the end of the queue */
+	list_add_tail(&entry->list, &fh->msgs);
+
+	/*
+	 * if the queue now has more than CEC_MAX_MSG_RX_QUEUE_SZ
+	 * messages, drop the oldest one and send a lost message event.
+	 */
+	if (fh->queued_msgs == CEC_MAX_MSG_RX_QUEUE_SZ) {
+		list_del(&entry->list);
+		goto lost_msgs;
+	}
+	fh->queued_msgs++;
+	mutex_unlock(&fh->lock);
+	wake_up_interruptible(&fh->wait);
+	return;
+
+lost_msgs:
+	mutex_unlock(&fh->lock);
+	cec_queue_event_fh(fh, &ev_lost_msg, 0);
+}
+
+/*
+ * Queue the message for those filehandles that are in monitor mode.
+ * If valid_la is true (this message is for us or was sent by us),
+ * then pass it on to any monitoring filehandle. If this message
+ * isn't for us or from us, then only give it to filehandles that
+ * are in MONITOR_ALL mode.
+ *
+ * This can only happen if the CEC_CAP_MONITOR_ALL capability is
+ * set and the CEC adapter was placed in 'monitor all' mode.
+ */
+static void cec_queue_msg_monitor(struct cec_adapter *adap,
+				  const struct cec_msg *msg,
+				  bool valid_la)
+{
+	struct cec_fh *fh;
+	u32 monitor_mode = valid_la ? CEC_MODE_MONITOR :
+				      CEC_MODE_MONITOR_ALL;
+
+	mutex_lock(&adap->devnode.fhs_lock);
+	list_for_each_entry(fh, &adap->devnode.fhs, list) {
+		if (fh->mode_follower >= monitor_mode)
+			cec_queue_msg_fh(fh, msg);
+	}
+	mutex_unlock(&adap->devnode.fhs_lock);
+}
+
+/*
+ * Queue the message for follower filehandles.
+ */
+static void cec_queue_msg_followers(struct cec_adapter *adap,
+				    const struct cec_msg *msg)
+{
+	struct cec_fh *fh;
+
+	mutex_lock(&adap->devnode.fhs_lock);
+	list_for_each_entry(fh, &adap->devnode.fhs, list) {
+		if (fh->mode_follower == CEC_MODE_FOLLOWER)
+			cec_queue_msg_fh(fh, msg);
+	}
+	mutex_unlock(&adap->devnode.fhs_lock);
+}
+
+/* Notify userspace of an adapter state change. */
+static void cec_post_state_event(struct cec_adapter *adap)
+{
+	struct cec_event ev = {
+		.event = CEC_EVENT_STATE_CHANGE,
+	};
+
+	ev.state_change.phys_addr = adap->phys_addr;
+	ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask;
+	cec_queue_event(adap, &ev);
+}
+
+/*
+ * A CEC transmit (and a possible wait for reply) completed.
+ * If this was in blocking mode, then complete it, otherwise
+ * queue the message for userspace to dequeue later.
+ *
+ * This function is called with adap->lock held.
+ */
+static void cec_data_completed(struct cec_data *data)
+{
+	/*
+	 * Delete this transmit from the filehandle's xfer_list since
+	 * we're done with it.
+	 *
+	 * Note that if the filehandle is closed before this transmit
+	 * finished, then the release() function will set data->fh to NULL.
+	 * Without that we would be referring to a closed filehandle.
+	 */
+	if (data->fh)
+		list_del(&data->xfer_list);
+
+	if (data->blocking) {
+		/*
+		 * Someone is blocking so mark the message as completed
+		 * and call complete.
+		 */
+		data->completed = true;
+		complete(&data->c);
+	} else {
+		/*
+		 * No blocking, so just queue the message if needed and
+		 * free the memory.
+		 */
+		if (data->fh)
+			cec_queue_msg_fh(data->fh, &data->msg);
+		kfree(data);
+	}
+}
+
+/*
+ * A pending CEC transmit needs to be cancelled, either because the CEC
+ * adapter is disabled or the transmit takes an impossibly long time to
+ * finish.
+ *
+ * This function is called with adap->lock held.
+ */
+static void cec_data_cancel(struct cec_data *data)
+{
+	/*
+	 * It's either the current transmit, or it is a pending
+	 * transmit. Take the appropriate action to clear it.
+	 */
+	if (data->adap->transmitting == data) {
+		data->adap->transmitting = NULL;
+	} else {
+		list_del_init(&data->list);
+		if (!(data->msg.tx_status & CEC_TX_STATUS_OK))
+			data->adap->transmit_queue_sz--;
+	}
+
+	/* Mark it as an error */
+	data->msg.tx_ts = ktime_get_ns();
+	data->msg.tx_status = CEC_TX_STATUS_ERROR |
+			      CEC_TX_STATUS_MAX_RETRIES;
+	data->attempts = 0;
+	data->msg.tx_error_cnt = 1;
+	/* Queue transmitted message for monitoring purposes */
+	cec_queue_msg_monitor(data->adap, &data->msg, 1);
+
+	cec_data_completed(data);
+}
+
+/*
+ * Main CEC state machine
+ *
+ * Wait until the thread should be stopped, or we are not transmitting and
+ * a new transmit message is queued up, in which case we start transmitting
+ * that message. When the adapter finished transmitting the message it will
+ * call cec_transmit_done().
+ *
+ * If the adapter is disabled, then remove all queued messages instead.
+ *
+ * If the current transmit times out, then cancel that transmit.
+ */
+int cec_thread_func(void *_adap)
+{
+	struct cec_adapter *adap = _adap;
+
+	for (;;) {
+		unsigned int signal_free_time;
+		struct cec_data *data;
+		bool timeout = false;
+		u8 attempts;
+
+		if (adap->transmitting) {
+			int err;
+
+			/*
+			 * We are transmitting a message, so add a timeout
+			 * to prevent the state machine to get stuck waiting
+			 * for this message to finalize and add a check to
+			 * see if the adapter is disabled in which case the
+			 * transmit should be canceled.
+			 */
+			err = wait_event_interruptible_timeout(adap->kthread_waitq,
+				kthread_should_stop() ||
+				(!adap->is_configured && !adap->is_configuring) ||
+				(!adap->transmitting &&
+				 !list_empty(&adap->transmit_queue)),
+				msecs_to_jiffies(CEC_XFER_TIMEOUT_MS));
+			timeout = err == 0;
+		} else {
+			/* Otherwise we just wait for something to happen. */
+			wait_event_interruptible(adap->kthread_waitq,
+				kthread_should_stop() ||
+				(!adap->transmitting &&
+				 !list_empty(&adap->transmit_queue)));
+		}
+
+		mutex_lock(&adap->lock);
+
+		if ((!adap->is_configured && !adap->is_configuring) ||
+		    kthread_should_stop()) {
+			/*
+			 * If the adapter is disabled, or we're asked to stop,
+			 * then cancel any pending transmits.
+			 */
+			while (!list_empty(&adap->transmit_queue)) {
+				data = list_first_entry(&adap->transmit_queue,
+							struct cec_data, list);
+				cec_data_cancel(data);
+			}
+			if (adap->transmitting)
+				cec_data_cancel(adap->transmitting);
+
+			/*
+			 * Cancel the pending timeout work. We have to unlock
+			 * the mutex when flushing the work since
+			 * cec_wait_timeout() will take it. This is OK since
+			 * no new entries can be added to wait_queue as long
+			 * as adap->transmitting is NULL, which it is due to
+			 * the cec_data_cancel() above.
+			 */
+			while (!list_empty(&adap->wait_queue)) {
+				data = list_first_entry(&adap->wait_queue,
+							struct cec_data, list);
+
+				if (!cancel_delayed_work(&data->work)) {
+					mutex_unlock(&adap->lock);
+					flush_scheduled_work();
+					mutex_lock(&adap->lock);
+				}
+				cec_data_cancel(data);
+			}
+			goto unlock;
+		}
+
+		if (adap->transmitting && timeout) {
+			/*
+			 * If we timeout, then log that. This really shouldn't
+			 * happen and is an indication of a faulty CEC adapter
+			 * driver, or the CEC bus is in some weird state.
+			 */
+			dprintk(0, "message %*ph timed out!\n",
+				adap->transmitting->msg.len,
+				adap->transmitting->msg.msg);
+			/* Just give up on this. */
+			cec_data_cancel(adap->transmitting);
+			goto unlock;
+		}
+
+		/*
+		 * If we are still transmitting, or there is nothing new to
+		 * transmit, then just continue waiting.
+		 */
+		if (adap->transmitting || list_empty(&adap->transmit_queue))
+			goto unlock;
+
+		/* Get a new message to transmit */
+		data = list_first_entry(&adap->transmit_queue,
+					struct cec_data, list);
+		list_del_init(&data->list);
+		adap->transmit_queue_sz--;
+		/* Make this the current transmitting message */
+		adap->transmitting = data;
+
+		/*
+		 * Suggested number of attempts as per the CEC 2.0 spec:
+		 * 4 attempts is the default, except for 'secondary poll
+		 * messages', i.e. poll messages not sent during the adapter
+		 * configuration phase when it allocates logical addresses.
+		 */
+		if (data->msg.len == 1 && adap->is_configured)
+			attempts = 2;
+		else
+			attempts = 4;
+
+		/* Set the suggested signal free time */
+		if (data->attempts) {
+			/* should be >= 3 data bit periods for a retry */
+			signal_free_time = CEC_SIGNAL_FREE_TIME_RETRY;
+		} else if (data->new_initiator) {
+			/* should be >= 5 data bit periods for new initiator */
+			signal_free_time = CEC_SIGNAL_FREE_TIME_NEW_INITIATOR;
+		} else {
+			/*
+			 * should be >= 7 data bit periods for sending another
+			 * frame immediately after another.
+			 */
+			signal_free_time = CEC_SIGNAL_FREE_TIME_NEXT_XFER;
+		}
+		if (data->attempts == 0)
+			data->attempts = attempts;
+
+		/* Tell the adapter to transmit, cancel on error */
+		if (adap->ops->adap_transmit(adap, data->attempts,
+					     signal_free_time, &data->msg))
+			cec_data_cancel(data);
+
+unlock:
+		mutex_unlock(&adap->lock);
+
+		if (kthread_should_stop())
+			break;
+	}
+	return 0;
+}
+
+/*
+ * Called by the CEC adapter if a transmit finished.
+ */
+void cec_transmit_done(struct cec_adapter *adap, u8 status, u8 arb_lost_cnt,
+		       u8 nack_cnt, u8 low_drive_cnt, u8 error_cnt)
+{
+	struct cec_data *data;
+	struct cec_msg *msg;
+	u64 ts = ktime_get_ns();
+
+	dprintk(2, "cec_transmit_done %02x\n", status);
+	mutex_lock(&adap->lock);
+	data = adap->transmitting;
+	if (!data) {
+		/*
+		 * This can happen if a transmit was issued and the cable is
+		 * unplugged while the transmit is ongoing. Ignore this
+		 * transmit in that case.
+		 */
+		dprintk(1, "cec_transmit_done without an ongoing transmit!\n");
+		goto unlock;
+	}
+
+	msg = &data->msg;
+
+	/* Drivers must fill in the status! */
+	WARN_ON(status == 0);
+	msg->tx_ts = ts;
+	msg->tx_status |= status;
+	msg->tx_arb_lost_cnt += arb_lost_cnt;
+	msg->tx_nack_cnt += nack_cnt;
+	msg->tx_low_drive_cnt += low_drive_cnt;
+	msg->tx_error_cnt += error_cnt;
+
+	/* Mark that we're done with this transmit */
+	adap->transmitting = NULL;
+
+	/*
+	 * If there are still retry attempts left and there was an error and
+	 * the hardware didn't signal that it retried itself (by setting
+	 * CEC_TX_STATUS_MAX_RETRIES), then we will retry ourselves.
+	 */
+	if (data->attempts > 1 &&
+	    !(status & (CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_OK))) {
+		/* Retry this message */
+		data->attempts--;
+		/* Add the message in front of the transmit queue */
+		list_add(&data->list, &adap->transmit_queue);
+		adap->transmit_queue_sz++;
+		goto wake_thread;
+	}
+
+	data->attempts = 0;
+
+	/* Always set CEC_TX_STATUS_MAX_RETRIES on error */
+	if (!(status & CEC_TX_STATUS_OK))
+		msg->tx_status |= CEC_TX_STATUS_MAX_RETRIES;
+
+	/* Queue transmitted message for monitoring purposes */
+	cec_queue_msg_monitor(adap, msg, 1);
+
+	if ((status & CEC_TX_STATUS_OK) && adap->is_configured &&
+	    msg->timeout) {
+		/*
+		 * Queue the message into the wait queue if we want to wait
+		 * for a reply.
+		 */
+		list_add_tail(&data->list, &adap->wait_queue);
+		schedule_delayed_work(&data->work,
+				      msecs_to_jiffies(msg->timeout));
+	} else {
+		/* Otherwise we're done */
+		cec_data_completed(data);
+	}
+
+wake_thread:
+	/*
+	 * Wake up the main thread to see if another message is ready
+	 * for transmitting or to retry the current message.
+	 */
+	wake_up_interruptible(&adap->kthread_waitq);
+unlock:
+	mutex_unlock(&adap->lock);
+}
+EXPORT_SYMBOL_GPL(cec_transmit_done);
+
+/*
+ * Called when waiting for a reply times out.
+ */
+static void cec_wait_timeout(struct work_struct *work)
+{
+	struct cec_data *data = container_of(work, struct cec_data, work.work);
+	struct cec_adapter *adap = data->adap;
+
+	mutex_lock(&adap->lock);
+	/*
+	 * Sanity check in case the timeout and the arrival of the message
+	 * happened at the same time.
+	 */
+	if (list_empty(&data->list))
+		goto unlock;
+
+	/* Mark the message as timed out */
+	list_del_init(&data->list);
+	data->msg.rx_ts = ktime_get_ns();
+	data->msg.rx_status = CEC_RX_STATUS_TIMEOUT;
+	cec_data_completed(data);
+unlock:
+	mutex_unlock(&adap->lock);
+}
+
+/*
+ * Transmit a message. The fh argument may be NULL if the transmit is not
+ * associated with a specific filehandle.
+ *
+ * This function is called with adap->lock held.
+ */
+int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg,
+			struct cec_fh *fh, bool block)
+{
+	struct cec_data *data;
+	u8 last_initiator = 0xff;
+	unsigned int timeout;
+	int res = 0;
+
+	msg->rx_ts = 0;
+	msg->tx_ts = 0;
+	msg->rx_status = 0;
+	msg->tx_status = 0;
+	msg->tx_arb_lost_cnt = 0;
+	msg->tx_nack_cnt = 0;
+	msg->tx_low_drive_cnt = 0;
+	msg->tx_error_cnt = 0;
+	msg->flags = 0;
+	msg->sequence = ++adap->sequence;
+	if (!msg->sequence)
+		msg->sequence = ++adap->sequence;
+
+	if (msg->reply && msg->timeout == 0) {
+		/* Make sure the timeout isn't 0. */
+		msg->timeout = 1000;
+	}
+
+	/* Sanity checks */
+	if (msg->len == 0 || msg->len > CEC_MAX_MSG_SIZE) {
+		dprintk(1, "cec_transmit_msg: invalid length %d\n", msg->len);
+		return -EINVAL;
+	}
+	if (msg->timeout && msg->len == 1) {
+		dprintk(1, "cec_transmit_msg: can't reply for poll msg\n");
+		return -EINVAL;
+	}
+	memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len);
+	if (msg->len == 1) {
+		if (cec_msg_initiator(msg) != 0xf ||
+		    cec_msg_destination(msg) == 0xf) {
+			dprintk(1, "cec_transmit_msg: invalid poll message\n");
+			return -EINVAL;
+		}
+		if (cec_has_log_addr(adap, cec_msg_destination(msg))) {
+			/*
+			 * If the destination is a logical address our adapter
+			 * has already claimed, then just NACK this.
+			 * It depends on the hardware what it will do with a
+			 * POLL to itself (some OK this), so it is just as
+			 * easy to handle it here so the behavior will be
+			 * consistent.
+			 */
+			msg->tx_ts = ktime_get_ns();
+			msg->tx_status = CEC_TX_STATUS_NACK |
+					 CEC_TX_STATUS_MAX_RETRIES;
+			msg->tx_nack_cnt = 1;
+			return 0;
+		}
+	}
+	if (msg->len > 1 && !cec_msg_is_broadcast(msg) &&
+	    cec_has_log_addr(adap, cec_msg_destination(msg))) {
+		dprintk(1, "cec_transmit_msg: destination is the adapter itself\n");
+		return -EINVAL;
+	}
+	if (cec_msg_initiator(msg) != 0xf &&
+	    !cec_has_log_addr(adap, cec_msg_initiator(msg))) {
+		dprintk(1, "cec_transmit_msg: initiator has unknown logical address %d\n",
+			cec_msg_initiator(msg));
+		return -EINVAL;
+	}
+	if (!adap->is_configured && !adap->is_configuring)
+		return -ENONET;
+
+	if (adap->transmit_queue_sz >= CEC_MAX_MSG_TX_QUEUE_SZ)
+		return -EBUSY;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	if (msg->len > 1 && msg->msg[1] == CEC_MSG_CDC_MESSAGE) {
+		msg->msg[2] = adap->phys_addr >> 8;
+		msg->msg[3] = adap->phys_addr & 0xff;
+	}
+
+	if (msg->timeout)
+		dprintk(2, "cec_transmit_msg: %*ph (wait for 0x%02x%s)\n",
+			msg->len, msg->msg, msg->reply, !block ? ", nb" : "");
+	else
+		dprintk(2, "cec_transmit_msg: %*ph%s\n",
+			msg->len, msg->msg, !block ? " (nb)" : "");
+
+	data->msg = *msg;
+	data->fh = fh;
+	data->adap = adap;
+	data->blocking = block;
+
+	/*
+	 * Determine if this message follows a message from the same
+	 * initiator. Needed to determine the free signal time later on.
+	 */
+	if (msg->len > 1) {
+		if (!(list_empty(&adap->transmit_queue))) {
+			const struct cec_data *last;
+
+			last = list_last_entry(&adap->transmit_queue,
+					       const struct cec_data, list);
+			last_initiator = cec_msg_initiator(&last->msg);
+		} else if (adap->transmitting) {
+			last_initiator =
+				cec_msg_initiator(&adap->transmitting->msg);
+		}
+	}
+	data->new_initiator = last_initiator != cec_msg_initiator(msg);
+	init_completion(&data->c);
+	INIT_DELAYED_WORK(&data->work, cec_wait_timeout);
+
+	if (fh)
+		list_add_tail(&data->xfer_list, &fh->xfer_list);
+	list_add_tail(&data->list, &adap->transmit_queue);
+	adap->transmit_queue_sz++;
+	if (!adap->transmitting)
+		wake_up_interruptible(&adap->kthread_waitq);
+
+	/* All done if we don't need to block waiting for completion */
+	if (!block)
+		return 0;
+
+	/*
+	 * If we don't get a completion before this time something is really
+	 * wrong and we time out.
+	 */
+	timeout = CEC_XFER_TIMEOUT_MS;
+	/* Add the requested timeout if we have to wait for a reply as well */
+	if (msg->timeout)
+		timeout += msg->timeout;
+
+	/*
+	 * Release the lock and wait, retake the lock afterwards.
+	 */
+	mutex_unlock(&adap->lock);
+	res = wait_for_completion_killable_timeout(&data->c,
+						   msecs_to_jiffies(timeout));
+	mutex_lock(&adap->lock);
+
+	if (data->completed) {
+		/* The transmit completed (possibly with an error) */
+		*msg = data->msg;
+		kfree(data);
+		return 0;
+	}
+	/*
+	 * The wait for completion timed out or was interrupted, so mark this
+	 * as non-blocking and disconnect from the filehandle since it is
+	 * still 'in flight'. When it finally completes it will just drop the
+	 * result silently.
+	 */
+	data->blocking = false;
+	if (data->fh)
+		list_del(&data->xfer_list);
+	data->fh = NULL;
+
+	if (res == 0) { /* timed out */
+		/* Check if the reply or the transmit failed */
+		if (msg->timeout && (msg->tx_status & CEC_TX_STATUS_OK))
+			msg->rx_status = CEC_RX_STATUS_TIMEOUT;
+		else
+			msg->tx_status = CEC_TX_STATUS_MAX_RETRIES;
+	}
+	return res > 0 ? 0 : res;
+}
+
+/* Helper function to be used by drivers and this framework. */
+int cec_transmit_msg(struct cec_adapter *adap, struct cec_msg *msg,
+		     bool block)
+{
+	int ret;
+
+	mutex_lock(&adap->lock);
+	ret = cec_transmit_msg_fh(adap, msg, NULL, block);
+	mutex_unlock(&adap->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cec_transmit_msg);
+
+/*
+ * I don't like forward references but without this the low-level
+ * cec_received_msg() function would come after a bunch of high-level
+ * CEC protocol handling functions. That was very confusing.
+ */
+static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg,
+			      bool is_reply);
+
+/* Called by the CEC adapter if a message is received */
+void cec_received_msg(struct cec_adapter *adap, struct cec_msg *msg)
+{
+	struct cec_data *data;
+	u8 msg_init = cec_msg_initiator(msg);
+	u8 msg_dest = cec_msg_destination(msg);
+	bool is_reply = false;
+	bool valid_la = true;
+
+	if (WARN_ON(!msg->len || msg->len > CEC_MAX_MSG_SIZE))
+		return;
+
+	msg->rx_ts = ktime_get_ns();
+	msg->rx_status = CEC_RX_STATUS_OK;
+	msg->sequence = msg->reply = msg->timeout = 0;
+	msg->tx_status = 0;
+	msg->tx_ts = 0;
+	msg->flags = 0;
+	memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len);
+
+	mutex_lock(&adap->lock);
+	dprintk(2, "cec_received_msg: %*ph\n", msg->len, msg->msg);
+
+	/* Check if this message was for us (directed or broadcast). */
+	if (!cec_msg_is_broadcast(msg))
+		valid_la = cec_has_log_addr(adap, msg_dest);
+
+	/* It's a valid message and not a poll or CDC message */
+	if (valid_la && msg->len > 1 && msg->msg[1] != CEC_MSG_CDC_MESSAGE) {
+		u8 cmd = msg->msg[1];
+		bool abort = cmd == CEC_MSG_FEATURE_ABORT;
+
+		/* The aborted command is in msg[2] */
+		if (abort)
+			cmd = msg->msg[2];
+
+		/*
+		 * Walk over all transmitted messages that are waiting for a
+		 * reply.
+		 */
+		list_for_each_entry(data, &adap->wait_queue, list) {
+			struct cec_msg *dst = &data->msg;
+
+			/* Does the command match? */
+			if ((abort && cmd != dst->msg[1]) ||
+			    (!abort && cmd != dst->reply))
+				continue;
+
+			/* Does the addressing match? */
+			if (msg_init != cec_msg_destination(dst) &&
+			    !cec_msg_is_broadcast(dst))
+				continue;
+
+			/* We got a reply */
+			memcpy(dst->msg, msg->msg, msg->len);
+			dst->len = msg->len;
+			dst->rx_ts = msg->rx_ts;
+			dst->rx_status = msg->rx_status;
+			if (abort)
+				dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT;
+			/* Remove it from the wait_queue */
+			list_del_init(&data->list);
+
+			/* Cancel the pending timeout work */
+			if (!cancel_delayed_work(&data->work)) {
+				mutex_unlock(&adap->lock);
+				flush_scheduled_work();
+				mutex_lock(&adap->lock);
+			}
+			/*
+			 * Mark this as a reply, provided someone is still
+			 * waiting for the answer.
+			 */
+			if (data->fh)
+				is_reply = true;
+			cec_data_completed(data);
+			break;
+		}
+	}
+	mutex_unlock(&adap->lock);
+
+	/* Pass the message on to any monitoring filehandles */
+	cec_queue_msg_monitor(adap, msg, valid_la);
+
+	/* We're done if it is not for us or a poll message */
+	if (!valid_la || msg->len <= 1)
+		return;
+
+	/*
+	 * Process the message on the protocol level. If is_reply is true,
+	 * then cec_receive_notify() won't pass on the reply to the listener(s)
+	 * since that was already done by cec_data_completed() above.
+	 */
+	cec_receive_notify(adap, msg, is_reply);
+}
+EXPORT_SYMBOL_GPL(cec_received_msg);
+
+/* Logical Address Handling */
+
+/*
+ * Attempt to claim a specific logical address.
+ *
+ * This function is called with adap->lock held.
+ */
+static int cec_config_log_addr(struct cec_adapter *adap,
+			       unsigned int idx,
+			       unsigned int log_addr)
+{
+	struct cec_log_addrs *las = &adap->log_addrs;
+	struct cec_msg msg = { };
+	int err;
+
+	if (cec_has_log_addr(adap, log_addr))
+		return 0;
+
+	/* Send poll message */
+	msg.len = 1;
+	msg.msg[0] = 0xf0 | log_addr;
+	err = cec_transmit_msg_fh(adap, &msg, NULL, true);
+
+	/*
+	 * While trying to poll the physical address was reset
+	 * and the adapter was unconfigured, so bail out.
+	 */
+	if (!adap->is_configuring)
+		return -EINTR;
+
+	if (err)
+		return err;
+
+	if (msg.tx_status & CEC_TX_STATUS_OK)
+		return 0;
+
+	/*
+	 * Message not acknowledged, so this logical
+	 * address is free to use.
+	 */
+	err = adap->ops->adap_log_addr(adap, log_addr);
+	if (err)
+		return err;
+
+	las->log_addr[idx] = log_addr;
+	las->log_addr_mask |= 1 << log_addr;
+	adap->phys_addrs[log_addr] = adap->phys_addr;
+
+	dprintk(2, "claimed addr %d (%d)\n", log_addr,
+		las->primary_device_type[idx]);
+	return 1;
+}
+
+/*
+ * Unconfigure the adapter: clear all logical addresses and send
+ * the state changed event.
+ *
+ * This function is called with adap->lock held.
+ */
+static void cec_adap_unconfigure(struct cec_adapter *adap)
+{
+	WARN_ON(adap->ops->adap_log_addr(adap, CEC_LOG_ADDR_INVALID));
+	adap->log_addrs.log_addr_mask = 0;
+	adap->is_configuring = false;
+	adap->is_configured = false;
+	memset(adap->phys_addrs, 0xff, sizeof(adap->phys_addrs));
+	wake_up_interruptible(&adap->kthread_waitq);
+	cec_post_state_event(adap);
+}
+
+/*
+ * Attempt to claim the required logical addresses.
+ */
+static int cec_config_thread_func(void *arg)
+{
+	/* The various LAs for each type of device */
+	static const u8 tv_log_addrs[] = {
+		CEC_LOG_ADDR_TV, CEC_LOG_ADDR_SPECIFIC,
+		CEC_LOG_ADDR_INVALID
+	};
+	static const u8 record_log_addrs[] = {
+		CEC_LOG_ADDR_RECORD_1, CEC_LOG_ADDR_RECORD_2,
+		CEC_LOG_ADDR_RECORD_3,
+		CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2,
+		CEC_LOG_ADDR_INVALID
+	};
+	static const u8 tuner_log_addrs[] = {
+		CEC_LOG_ADDR_TUNER_1, CEC_LOG_ADDR_TUNER_2,
+		CEC_LOG_ADDR_TUNER_3, CEC_LOG_ADDR_TUNER_4,
+		CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2,
+		CEC_LOG_ADDR_INVALID
+	};
+	static const u8 playback_log_addrs[] = {
+		CEC_LOG_ADDR_PLAYBACK_1, CEC_LOG_ADDR_PLAYBACK_2,
+		CEC_LOG_ADDR_PLAYBACK_3,
+		CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2,
+		CEC_LOG_ADDR_INVALID
+	};
+	static const u8 audiosystem_log_addrs[] = {
+		CEC_LOG_ADDR_AUDIOSYSTEM,
+		CEC_LOG_ADDR_INVALID
+	};
+	static const u8 specific_use_log_addrs[] = {
+		CEC_LOG_ADDR_SPECIFIC,
+		CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2,
+		CEC_LOG_ADDR_INVALID
+	};
+	static const u8 *type2addrs[6] = {
+		[CEC_LOG_ADDR_TYPE_TV] = tv_log_addrs,
+		[CEC_LOG_ADDR_TYPE_RECORD] = record_log_addrs,
+		[CEC_LOG_ADDR_TYPE_TUNER] = tuner_log_addrs,
+		[CEC_LOG_ADDR_TYPE_PLAYBACK] = playback_log_addrs,
+		[CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = audiosystem_log_addrs,
+		[CEC_LOG_ADDR_TYPE_SPECIFIC] = specific_use_log_addrs,
+	};
+	static const u16 type2mask[] = {
+		[CEC_LOG_ADDR_TYPE_TV] = CEC_LOG_ADDR_MASK_TV,
+		[CEC_LOG_ADDR_TYPE_RECORD] = CEC_LOG_ADDR_MASK_RECORD,
+		[CEC_LOG_ADDR_TYPE_TUNER] = CEC_LOG_ADDR_MASK_TUNER,
+		[CEC_LOG_ADDR_TYPE_PLAYBACK] = CEC_LOG_ADDR_MASK_PLAYBACK,
+		[CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = CEC_LOG_ADDR_MASK_AUDIOSYSTEM,
+		[CEC_LOG_ADDR_TYPE_SPECIFIC] = CEC_LOG_ADDR_MASK_SPECIFIC,
+	};
+	struct cec_adapter *adap = arg;
+	struct cec_log_addrs *las = &adap->log_addrs;
+	int err;
+	int i, j;
+
+	mutex_lock(&adap->lock);
+	dprintk(1, "physical address: %x.%x.%x.%x, claim %d logical addresses\n",
+		cec_phys_addr_exp(adap->phys_addr), las->num_log_addrs);
+	las->log_addr_mask = 0;
+
+	if (las->log_addr_type[0] == CEC_LOG_ADDR_TYPE_UNREGISTERED)
+		goto configured;
+
+	for (i = 0; i < las->num_log_addrs; i++) {
+		unsigned int type = las->log_addr_type[i];
+		const u8 *la_list;
+		u8 last_la;
+
+		/*
+		 * The TV functionality can only map to physical address 0.
+		 * For any other address, try the Specific functionality
+		 * instead as per the spec.
+		 */
+		if (adap->phys_addr && type == CEC_LOG_ADDR_TYPE_TV)
+			type = CEC_LOG_ADDR_TYPE_SPECIFIC;
+
+		la_list = type2addrs[type];
+		last_la = las->log_addr[i];
+		las->log_addr[i] = CEC_LOG_ADDR_INVALID;
+		if (last_la == CEC_LOG_ADDR_INVALID ||
+		    last_la == CEC_LOG_ADDR_UNREGISTERED ||
+		    !(last_la & type2mask[type]))
+			last_la = la_list[0];
+
+		err = cec_config_log_addr(adap, i, last_la);
+		if (err > 0) /* Reused last LA */
+			continue;
+
+		if (err < 0)
+			goto unconfigure;
+
+		for (j = 0; la_list[j] != CEC_LOG_ADDR_INVALID; j++) {
+			/* Tried this one already, skip it */
+			if (la_list[j] == last_la)
+				continue;
+			/* The backup addresses are CEC 2.0 specific */
+			if ((la_list[j] == CEC_LOG_ADDR_BACKUP_1 ||
+			     la_list[j] == CEC_LOG_ADDR_BACKUP_2) &&
+			    las->cec_version < CEC_OP_CEC_VERSION_2_0)
+				continue;
+
+			err = cec_config_log_addr(adap, i, la_list[j]);
+			if (err == 0) /* LA is in use */
+				continue;
+			if (err < 0)
+				goto unconfigure;
+			/* Done, claimed an LA */
+			break;
+		}
+
+		if (la_list[j] == CEC_LOG_ADDR_INVALID)
+			dprintk(1, "could not claim LA %d\n", i);
+	}
+
+configured:
+	if (adap->log_addrs.log_addr_mask == 0) {
+		/* Fall back to unregistered */
+		las->log_addr[0] = CEC_LOG_ADDR_UNREGISTERED;
+		las->log_addr_mask = 1 << las->log_addr[0];
+	}
+	adap->is_configured = true;
+	adap->is_configuring = false;
+	cec_post_state_event(adap);
+	mutex_unlock(&adap->lock);
+
+	for (i = 0; i < las->num_log_addrs; i++) {
+		if (las->log_addr[i] == CEC_LOG_ADDR_INVALID)
+			continue;
+
+		/*
+		 * Report Features must come first according
+		 * to CEC 2.0
+		 */
+		if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED)
+			cec_report_features(adap, i);
+		cec_report_phys_addr(adap, i);
+	}
+	mutex_lock(&adap->lock);
+	adap->kthread_config = NULL;
+	mutex_unlock(&adap->lock);
+	complete(&adap->config_completion);
+	return 0;
+
+unconfigure:
+	for (i = 0; i < las->num_log_addrs; i++)
+		las->log_addr[i] = CEC_LOG_ADDR_INVALID;
+	cec_adap_unconfigure(adap);
+	adap->kthread_config = NULL;
+	mutex_unlock(&adap->lock);
+	complete(&adap->config_completion);
+	return 0;
+}
+
+/*
+ * Called from either __cec_s_phys_addr or __cec_s_log_addrs to claim the
+ * logical addresses.
+ *
+ * This function is called with adap->lock held.
+ */
+static void cec_claim_log_addrs(struct cec_adapter *adap, bool block)
+{
+	if (WARN_ON(adap->is_configuring || adap->is_configured))
+		return;
+
+	init_completion(&adap->config_completion);
+
+	/* Ready to kick off the thread */
+	adap->is_configuring = true;
+	adap->kthread_config = kthread_run(cec_config_thread_func, adap,
+					   "ceccfg-%s", adap->name);
+	if (IS_ERR(adap->kthread_config)) {
+		adap->kthread_config = NULL;
+	} else if (block) {
+		mutex_unlock(&adap->lock);
+		wait_for_completion(&adap->config_completion);
+		mutex_lock(&adap->lock);
+	}
+}
+
+/* Set a new physical address and send an event notifying userspace of this.
+ *
+ * This function is called with adap->lock held.
+ */
+void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block)
+{
+	if (phys_addr == adap->phys_addr || adap->devnode.unregistered)
+		return;
+
+	if (phys_addr == CEC_PHYS_ADDR_INVALID ||
+	    adap->phys_addr != CEC_PHYS_ADDR_INVALID) {
+		adap->phys_addr = CEC_PHYS_ADDR_INVALID;
+		cec_post_state_event(adap);
+		cec_adap_unconfigure(adap);
+		/* Disabling monitor all mode should always succeed */
+		if (adap->monitor_all_cnt)
+			WARN_ON(call_op(adap, adap_monitor_all_enable, false));
+		WARN_ON(adap->ops->adap_enable(adap, false));
+		if (phys_addr == CEC_PHYS_ADDR_INVALID)
+			return;
+	}
+
+	if (adap->ops->adap_enable(adap, true))
+		return;
+
+	if (adap->monitor_all_cnt &&
+	    call_op(adap, adap_monitor_all_enable, true)) {
+		WARN_ON(adap->ops->adap_enable(adap, false));
+		return;
+	}
+	adap->phys_addr = phys_addr;
+	cec_post_state_event(adap);
+	if (adap->log_addrs.num_log_addrs)
+		cec_claim_log_addrs(adap, block);
+}
+
+void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block)
+{
+	if (IS_ERR_OR_NULL(adap))
+		return;
+
+	if (WARN_ON(adap->capabilities & CEC_CAP_PHYS_ADDR))
+		return;
+	mutex_lock(&adap->lock);
+	__cec_s_phys_addr(adap, phys_addr, block);
+	mutex_unlock(&adap->lock);
+}
+EXPORT_SYMBOL_GPL(cec_s_phys_addr);
+
+/*
+ * Called from either the ioctl or a driver to set the logical addresses.
+ *
+ * This function is called with adap->lock held.
+ */
+int __cec_s_log_addrs(struct cec_adapter *adap,
+		      struct cec_log_addrs *log_addrs, bool block)
+{
+	u16 type_mask = 0;
+	int i;
+
+	if (adap->devnode.unregistered)
+		return -ENODEV;
+
+	if (!log_addrs || log_addrs->num_log_addrs == 0) {
+		adap->log_addrs.num_log_addrs = 0;
+		cec_adap_unconfigure(adap);
+		return 0;
+	}
+
+	/* Ensure the osd name is 0-terminated */
+	log_addrs->osd_name[sizeof(log_addrs->osd_name) - 1] = '\0';
+
+	/* Sanity checks */
+	if (log_addrs->num_log_addrs > adap->available_log_addrs) {
+		dprintk(1, "num_log_addrs > %d\n", adap->available_log_addrs);
+		return -EINVAL;
+	}
+
+	/*
+	 * Vendor ID is a 24 bit number, so check if the value is
+	 * within the correct range.
+	 */
+	if (log_addrs->vendor_id != CEC_VENDOR_ID_NONE &&
+	    (log_addrs->vendor_id & 0xff000000) != 0)
+		return -EINVAL;
+
+	if (log_addrs->cec_version != CEC_OP_CEC_VERSION_1_4 &&
+	    log_addrs->cec_version != CEC_OP_CEC_VERSION_2_0)
+		return -EINVAL;
+
+	if (log_addrs->num_log_addrs > 1)
+		for (i = 0; i < log_addrs->num_log_addrs; i++)
+			if (log_addrs->log_addr_type[i] ==
+					CEC_LOG_ADDR_TYPE_UNREGISTERED) {
+				dprintk(1, "num_log_addrs > 1 can't be combined with unregistered LA\n");
+				return -EINVAL;
+			}
+
+	for (i = 0; i < log_addrs->num_log_addrs; i++) {
+		const u8 feature_sz = ARRAY_SIZE(log_addrs->features[0]);
+		u8 *features = log_addrs->features[i];
+		bool op_is_dev_features = false;
+
+		log_addrs->log_addr[i] = CEC_LOG_ADDR_INVALID;
+		if (type_mask & (1 << log_addrs->log_addr_type[i])) {
+			dprintk(1, "duplicate logical address type\n");
+			return -EINVAL;
+		}
+		type_mask |= 1 << log_addrs->log_addr_type[i];
+		if ((type_mask & (1 << CEC_LOG_ADDR_TYPE_RECORD)) &&
+		    (type_mask & (1 << CEC_LOG_ADDR_TYPE_PLAYBACK))) {
+			/* Record already contains the playback functionality */
+			dprintk(1, "invalid record + playback combination\n");
+			return -EINVAL;
+		}
+		if (log_addrs->primary_device_type[i] >
+					CEC_OP_PRIM_DEVTYPE_PROCESSOR) {
+			dprintk(1, "unknown primary device type\n");
+			return -EINVAL;
+		}
+		if (log_addrs->primary_device_type[i] == 2) {
+			dprintk(1, "invalid primary device type\n");
+			return -EINVAL;
+		}
+		if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) {
+			dprintk(1, "unknown logical address type\n");
+			return -EINVAL;
+		}
+		for (i = 0; i < feature_sz; i++) {
+			if ((features[i] & 0x80) == 0) {
+				if (op_is_dev_features)
+					break;
+				op_is_dev_features = true;
+			}
+		}
+		if (!op_is_dev_features || i == feature_sz) {
+			dprintk(1, "malformed features\n");
+			return -EINVAL;
+		}
+		/* Zero unused part of the feature array */
+		memset(features + i, 0, feature_sz - i);
+	}
+
+	if (log_addrs->cec_version >= CEC_OP_CEC_VERSION_2_0) {
+		if (log_addrs->num_log_addrs > 2) {
+			dprintk(1, "CEC 2.0 allows no more than 2 logical addresses\n");
+			return -EINVAL;
+		}
+		if (log_addrs->num_log_addrs == 2) {
+			if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_AUDIOSYSTEM) |
+					   (1 << CEC_LOG_ADDR_TYPE_TV)))) {
+				dprintk(1, "Two LAs is only allowed for audiosystem and TV\n");
+				return -EINVAL;
+			}
+			if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_PLAYBACK) |
+					   (1 << CEC_LOG_ADDR_TYPE_RECORD)))) {
+				dprintk(1, "An audiosystem/TV can only be combined with record or playback\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	/* Zero unused LAs */
+	for (i = log_addrs->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) {
+		log_addrs->primary_device_type[i] = 0;
+		log_addrs->log_addr_type[i] = 0;
+		log_addrs->all_device_types[i] = 0;
+		memset(log_addrs->features[i], 0,
+		       sizeof(log_addrs->features[i]));
+	}
+
+	log_addrs->log_addr_mask = adap->log_addrs.log_addr_mask;
+	adap->log_addrs = *log_addrs;
+	if (adap->phys_addr != CEC_PHYS_ADDR_INVALID)
+		cec_claim_log_addrs(adap, block);
+	return 0;
+}
+
+int cec_s_log_addrs(struct cec_adapter *adap,
+		    struct cec_log_addrs *log_addrs, bool block)
+{
+	int err;
+
+	if (WARN_ON(adap->capabilities & CEC_CAP_LOG_ADDRS))
+		return -EINVAL;
+	mutex_lock(&adap->lock);
+	err = __cec_s_log_addrs(adap, log_addrs, block);
+	mutex_unlock(&adap->lock);
+	return err;
+}
+EXPORT_SYMBOL_GPL(cec_s_log_addrs);
+
+/* High-level core CEC message handling */
+
+/* Transmit the Report Features message */
+static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx)
+{
+	struct cec_msg msg = { };
+	const struct cec_log_addrs *las = &adap->log_addrs;
+	const u8 *features = las->features[la_idx];
+	bool op_is_dev_features = false;
+	unsigned int idx;
+
+	/* This is 2.0 and up only */
+	if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0)
+		return 0;
+
+	/* Report Features */
+	msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
+	msg.len = 4;
+	msg.msg[1] = CEC_MSG_REPORT_FEATURES;
+	msg.msg[2] = adap->log_addrs.cec_version;
+	msg.msg[3] = las->all_device_types[la_idx];
+
+	/* Write RC Profiles first, then Device Features */
+	for (idx = 0; idx < ARRAY_SIZE(las->features[0]); idx++) {
+		msg.msg[msg.len++] = features[idx];
+		if ((features[idx] & CEC_OP_FEAT_EXT) == 0) {
+			if (op_is_dev_features)
+				break;
+			op_is_dev_features = true;
+		}
+	}
+	return cec_transmit_msg(adap, &msg, false);
+}
+
+/* Transmit the Report Physical Address message */
+static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx)
+{
+	const struct cec_log_addrs *las = &adap->log_addrs;
+	struct cec_msg msg = { };
+
+	/* Report Physical Address */
+	msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
+	cec_msg_report_physical_addr(&msg, adap->phys_addr,
+				     las->primary_device_type[la_idx]);
+	dprintk(2, "config: la %d pa %x.%x.%x.%x\n",
+		las->log_addr[la_idx],
+			cec_phys_addr_exp(adap->phys_addr));
+	return cec_transmit_msg(adap, &msg, false);
+}
+
+/* Transmit the Feature Abort message */
+static int cec_feature_abort_reason(struct cec_adapter *adap,
+				    struct cec_msg *msg, u8 reason)
+{
+	struct cec_msg tx_msg = { };
+
+	/*
+	 * Don't reply with CEC_MSG_FEATURE_ABORT to a CEC_MSG_FEATURE_ABORT
+	 * message!
+	 */
+	if (msg->msg[1] == CEC_MSG_FEATURE_ABORT)
+		return 0;
+	cec_msg_set_reply_to(&tx_msg, msg);
+	cec_msg_feature_abort(&tx_msg, msg->msg[1], reason);
+	return cec_transmit_msg(adap, &tx_msg, false);
+}
+
+static int cec_feature_abort(struct cec_adapter *adap, struct cec_msg *msg)
+{
+	return cec_feature_abort_reason(adap, msg,
+					CEC_OP_ABORT_UNRECOGNIZED_OP);
+}
+
+static int cec_feature_refused(struct cec_adapter *adap, struct cec_msg *msg)
+{
+	return cec_feature_abort_reason(adap, msg,
+					CEC_OP_ABORT_REFUSED);
+}
+
+/*
+ * Called when a CEC message is received. This function will do any
+ * necessary core processing. The is_reply bool is true if this message
+ * is a reply to an earlier transmit.
+ *
+ * The message is either a broadcast message or a valid directed message.
+ */
+static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg,
+			      bool is_reply)
+{
+	bool is_broadcast = cec_msg_is_broadcast(msg);
+	u8 dest_laddr = cec_msg_destination(msg);
+	u8 init_laddr = cec_msg_initiator(msg);
+	u8 devtype = cec_log_addr2dev(adap, dest_laddr);
+	int la_idx = cec_log_addr2idx(adap, dest_laddr);
+	bool is_directed = la_idx >= 0;
+	bool from_unregistered = init_laddr == 0xf;
+	struct cec_msg tx_cec_msg = { };
+
+	dprintk(1, "cec_receive_notify: %*ph\n", msg->len, msg->msg);
+
+	if (adap->ops->received) {
+		/* Allow drivers to process the message first */
+		if (adap->ops->received(adap, msg) != -ENOMSG)
+			return 0;
+	}
+
+	/*
+	 * REPORT_PHYSICAL_ADDR, CEC_MSG_USER_CONTROL_PRESSED and
+	 * CEC_MSG_USER_CONTROL_RELEASED messages always have to be
+	 * handled by the CEC core, even if the passthrough mode is on.
+	 * The others are just ignored if passthrough mode is on.
+	 */
+	switch (msg->msg[1]) {
+	case CEC_MSG_GET_CEC_VERSION:
+	case CEC_MSG_GIVE_DEVICE_VENDOR_ID:
+	case CEC_MSG_ABORT:
+	case CEC_MSG_GIVE_DEVICE_POWER_STATUS:
+	case CEC_MSG_GIVE_PHYSICAL_ADDR:
+	case CEC_MSG_GIVE_OSD_NAME:
+	case CEC_MSG_GIVE_FEATURES:
+		/*
+		 * Skip processing these messages if the passthrough mode
+		 * is on.
+		 */
+		if (adap->passthrough)
+			goto skip_processing;
+		/* Ignore if addressing is wrong */
+		if (is_broadcast || from_unregistered)
+			return 0;
+		break;
+
+	case CEC_MSG_USER_CONTROL_PRESSED:
+	case CEC_MSG_USER_CONTROL_RELEASED:
+		/* Wrong addressing mode: don't process */
+		if (is_broadcast || from_unregistered)
+			goto skip_processing;
+		break;
+
+	case CEC_MSG_REPORT_PHYSICAL_ADDR:
+		/*
+		 * This message is always processed, regardless of the
+		 * passthrough setting.
+		 *
+		 * Exception: don't process if wrong addressing mode.
+		 */
+		if (!is_broadcast)
+			goto skip_processing;
+		break;
+
+	default:
+		break;
+	}
+
+	cec_msg_set_reply_to(&tx_cec_msg, msg);
+
+	switch (msg->msg[1]) {
+	/* The following messages are processed but still passed through */
+	case CEC_MSG_REPORT_PHYSICAL_ADDR: {
+		u16 pa = (msg->msg[2] << 8) | msg->msg[3];
+
+		if (!from_unregistered)
+			adap->phys_addrs[init_laddr] = pa;
+		dprintk(1, "Reported physical address %x.%x.%x.%x for logical address %d\n",
+			cec_phys_addr_exp(pa), init_laddr);
+		break;
+	}
+
+	case CEC_MSG_USER_CONTROL_PRESSED:
+		if (!(adap->capabilities & CEC_CAP_RC))
+			break;
+
+#if IS_REACHABLE(CONFIG_RC_CORE)
+		switch (msg->msg[2]) {
+		/*
+		 * Play function, this message can have variable length
+		 * depending on the specific play function that is used.
+		 */
+		case 0x60:
+			if (msg->len == 2)
+				rc_keydown(adap->rc, RC_TYPE_CEC,
+					   msg->msg[2], 0);
+			else
+				rc_keydown(adap->rc, RC_TYPE_CEC,
+					   msg->msg[2] << 8 | msg->msg[3], 0);
+			break;
+		/*
+		 * Other function messages that are not handled.
+		 * Currently the RC framework does not allow to supply an
+		 * additional parameter to a keypress. These "keys" contain
+		 * other information such as channel number, an input number
+		 * etc.
+		 * For the time being these messages are not processed by the
+		 * framework and are simply forwarded to the user space.
+		 */
+		case 0x56: case 0x57:
+		case 0x67: case 0x68: case 0x69: case 0x6a:
+			break;
+		default:
+			rc_keydown(adap->rc, RC_TYPE_CEC, msg->msg[2], 0);
+			break;
+		}
+#endif
+		break;
+
+	case CEC_MSG_USER_CONTROL_RELEASED:
+		if (!(adap->capabilities & CEC_CAP_RC))
+			break;
+#if IS_REACHABLE(CONFIG_RC_CORE)
+		rc_keyup(adap->rc);
+#endif
+		break;
+
+	/*
+	 * The remaining messages are only processed if the passthrough mode
+	 * is off.
+	 */
+	case CEC_MSG_GET_CEC_VERSION:
+		cec_msg_cec_version(&tx_cec_msg, adap->log_addrs.cec_version);
+		return cec_transmit_msg(adap, &tx_cec_msg, false);
+
+	case CEC_MSG_GIVE_PHYSICAL_ADDR:
+		/* Do nothing for CEC switches using addr 15 */
+		if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH && dest_laddr == 15)
+			return 0;
+		cec_msg_report_physical_addr(&tx_cec_msg, adap->phys_addr, devtype);
+		return cec_transmit_msg(adap, &tx_cec_msg, false);
+
+	case CEC_MSG_GIVE_DEVICE_VENDOR_ID:
+		if (adap->log_addrs.vendor_id == CEC_VENDOR_ID_NONE)
+			return cec_feature_abort(adap, msg);
+		cec_msg_device_vendor_id(&tx_cec_msg, adap->log_addrs.vendor_id);
+		return cec_transmit_msg(adap, &tx_cec_msg, false);
+
+	case CEC_MSG_ABORT:
+		/* Do nothing for CEC switches */
+		if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH)
+			return 0;
+		return cec_feature_refused(adap, msg);
+
+	case CEC_MSG_GIVE_OSD_NAME: {
+		if (adap->log_addrs.osd_name[0] == 0)
+			return cec_feature_abort(adap, msg);
+		cec_msg_set_osd_name(&tx_cec_msg, adap->log_addrs.osd_name);
+		return cec_transmit_msg(adap, &tx_cec_msg, false);
+	}
+
+	case CEC_MSG_GIVE_FEATURES:
+		if (adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0)
+			return cec_report_features(adap, la_idx);
+		return 0;
+
+	default:
+		/*
+		 * Unprocessed messages are aborted if userspace isn't doing
+		 * any processing either.
+		 */
+		if (is_directed && !is_reply && !adap->follower_cnt &&
+		    !adap->cec_follower && msg->msg[1] != CEC_MSG_FEATURE_ABORT)
+			return cec_feature_abort(adap, msg);
+		break;
+	}
+
+skip_processing:
+	/* If this was a reply, then we're done */
+	if (is_reply)
+		return 0;
+
+	/*
+	 * Send to the exclusive follower if there is one, otherwise send
+	 * to all followers.
+	 */
+	if (adap->cec_follower)
+		cec_queue_msg_fh(adap->cec_follower, msg);
+	else
+		cec_queue_msg_followers(adap, msg);
+	return 0;
+}
+
+/*
+ * Helper functions to keep track of the 'monitor all' use count.
+ *
+ * These functions are called with adap->lock held.
+ */
+int cec_monitor_all_cnt_inc(struct cec_adapter *adap)
+{
+	int ret = 0;
+
+	if (adap->monitor_all_cnt == 0)
+		ret = call_op(adap, adap_monitor_all_enable, 1);
+	if (ret == 0)
+		adap->monitor_all_cnt++;
+	return ret;
+}
+
+void cec_monitor_all_cnt_dec(struct cec_adapter *adap)
+{
+	adap->monitor_all_cnt--;
+	if (adap->monitor_all_cnt == 0)
+		WARN_ON(call_op(adap, adap_monitor_all_enable, 0));
+}
+
+#ifdef CONFIG_MEDIA_CEC_DEBUG
+/*
+ * Log the current state of the CEC adapter.
+ * Very useful for debugging.
+ */
+int cec_adap_status(struct seq_file *file, void *priv)
+{
+	struct cec_adapter *adap = dev_get_drvdata(file->private);
+	struct cec_data *data;
+
+	mutex_lock(&adap->lock);
+	seq_printf(file, "configured: %d\n", adap->is_configured);
+	seq_printf(file, "configuring: %d\n", adap->is_configuring);
+	seq_printf(file, "phys_addr: %x.%x.%x.%x\n",
+		   cec_phys_addr_exp(adap->phys_addr));
+	seq_printf(file, "number of LAs: %d\n", adap->log_addrs.num_log_addrs);
+	seq_printf(file, "LA mask: 0x%04x\n", adap->log_addrs.log_addr_mask);
+	if (adap->cec_follower)
+		seq_printf(file, "has CEC follower%s\n",
+			   adap->passthrough ? " (in passthrough mode)" : "");
+	if (adap->cec_initiator)
+		seq_puts(file, "has CEC initiator\n");
+	if (adap->monitor_all_cnt)
+		seq_printf(file, "file handles in Monitor All mode: %u\n",
+			   adap->monitor_all_cnt);
+	data = adap->transmitting;
+	if (data)
+		seq_printf(file, "transmitting message: %*ph (reply: %02x, timeout: %ums)\n",
+			   data->msg.len, data->msg.msg, data->msg.reply,
+			   data->msg.timeout);
+	seq_printf(file, "pending transmits: %u\n", adap->transmit_queue_sz);
+	list_for_each_entry(data, &adap->transmit_queue, list) {
+		seq_printf(file, "queued tx message: %*ph (reply: %02x, timeout: %ums)\n",
+			   data->msg.len, data->msg.msg, data->msg.reply,
+			   data->msg.timeout);
+	}
+	list_for_each_entry(data, &adap->wait_queue, list) {
+		seq_printf(file, "message waiting for reply: %*ph (reply: %02x, timeout: %ums)\n",
+			   data->msg.len, data->msg.msg, data->msg.reply,
+			   data->msg.timeout);
+	}
+
+	call_void_op(adap, adap_status, file);
+	mutex_unlock(&adap->lock);
+	return 0;
+}
+#endif
diff --git a/drivers/staging/media/cec/cec-api.c b/drivers/staging/media/cec/cec-api.c
new file mode 100644
index 000000000000..7be7615a0fdf
--- /dev/null
+++ b/drivers/staging/media/cec/cec-api.c
@@ -0,0 +1,579 @@
+/*
+ * cec-api.c - HDMI Consumer Electronics Control framework - API
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kmod.h>
+#include <linux/ktime.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/version.h>
+
+#include "cec-priv.h"
+
+static inline struct cec_devnode *cec_devnode_data(struct file *filp)
+{
+	struct cec_fh *fh = filp->private_data;
+
+	return &fh->adap->devnode;
+}
+
+/* CEC file operations */
+
+static unsigned int cec_poll(struct file *filp,
+			     struct poll_table_struct *poll)
+{
+	struct cec_devnode *devnode = cec_devnode_data(filp);
+	struct cec_fh *fh = filp->private_data;
+	struct cec_adapter *adap = fh->adap;
+	unsigned int res = 0;
+
+	if (!devnode->registered)
+		return POLLERR | POLLHUP;
+	mutex_lock(&adap->lock);
+	if (adap->is_configured &&
+	    adap->transmit_queue_sz < CEC_MAX_MSG_TX_QUEUE_SZ)
+		res |= POLLOUT | POLLWRNORM;
+	if (fh->queued_msgs)
+		res |= POLLIN | POLLRDNORM;
+	if (fh->pending_events)
+		res |= POLLPRI;
+	poll_wait(filp, &fh->wait, poll);
+	mutex_unlock(&adap->lock);
+	return res;
+}
+
+static bool cec_is_busy(const struct cec_adapter *adap,
+			const struct cec_fh *fh)
+{
+	bool valid_initiator = adap->cec_initiator && adap->cec_initiator == fh;
+	bool valid_follower = adap->cec_follower && adap->cec_follower == fh;
+
+	/*
+	 * Exclusive initiators and followers can always access the CEC adapter
+	 */
+	if (valid_initiator || valid_follower)
+		return false;
+	/*
+	 * All others can only access the CEC adapter if there is no
+	 * exclusive initiator and they are in INITIATOR mode.
+	 */
+	return adap->cec_initiator ||
+	       fh->mode_initiator == CEC_MODE_NO_INITIATOR;
+}
+
+static long cec_adap_g_caps(struct cec_adapter *adap,
+			    struct cec_caps __user *parg)
+{
+	struct cec_caps caps = {};
+
+	strlcpy(caps.driver, adap->devnode.parent->driver->name,
+		sizeof(caps.driver));
+	strlcpy(caps.name, adap->name, sizeof(caps.name));
+	caps.available_log_addrs = adap->available_log_addrs;
+	caps.capabilities = adap->capabilities;
+	caps.version = LINUX_VERSION_CODE;
+	if (copy_to_user(parg, &caps, sizeof(caps)))
+		return -EFAULT;
+	return 0;
+}
+
+static long cec_adap_g_phys_addr(struct cec_adapter *adap,
+				 __u16 __user *parg)
+{
+	u16 phys_addr;
+
+	mutex_lock(&adap->lock);
+	phys_addr = adap->phys_addr;
+	mutex_unlock(&adap->lock);
+	if (copy_to_user(parg, &phys_addr, sizeof(phys_addr)))
+		return -EFAULT;
+	return 0;
+}
+
+static long cec_adap_s_phys_addr(struct cec_adapter *adap, struct cec_fh *fh,
+				 bool block, __u16 __user *parg)
+{
+	u16 phys_addr;
+	long err;
+
+	if (!(adap->capabilities & CEC_CAP_PHYS_ADDR))
+		return -ENOTTY;
+	if (copy_from_user(&phys_addr, parg, sizeof(phys_addr)))
+		return -EFAULT;
+
+	err = cec_phys_addr_validate(phys_addr, NULL, NULL);
+	if (err)
+		return err;
+	mutex_lock(&adap->lock);
+	if (cec_is_busy(adap, fh))
+		err = -EBUSY;
+	else
+		__cec_s_phys_addr(adap, phys_addr, block);
+	mutex_unlock(&adap->lock);
+	return err;
+}
+
+static long cec_adap_g_log_addrs(struct cec_adapter *adap,
+				 struct cec_log_addrs __user *parg)
+{
+	struct cec_log_addrs log_addrs;
+
+	mutex_lock(&adap->lock);
+	log_addrs = adap->log_addrs;
+	if (!adap->is_configured)
+		memset(log_addrs.log_addr, CEC_LOG_ADDR_INVALID,
+		       sizeof(log_addrs.log_addr));
+	mutex_unlock(&adap->lock);
+
+	if (copy_to_user(parg, &log_addrs, sizeof(log_addrs)))
+		return -EFAULT;
+	return 0;
+}
+
+static long cec_adap_s_log_addrs(struct cec_adapter *adap, struct cec_fh *fh,
+				 bool block, struct cec_log_addrs __user *parg)
+{
+	struct cec_log_addrs log_addrs;
+	long err = -EBUSY;
+
+	if (!(adap->capabilities & CEC_CAP_LOG_ADDRS))
+		return -ENOTTY;
+	if (copy_from_user(&log_addrs, parg, sizeof(log_addrs)))
+		return -EFAULT;
+	log_addrs.flags = 0;
+	mutex_lock(&adap->lock);
+	if (!adap->is_configuring &&
+	    (!log_addrs.num_log_addrs || !adap->is_configured) &&
+	    !cec_is_busy(adap, fh)) {
+		err = __cec_s_log_addrs(adap, &log_addrs, block);
+		if (!err)
+			log_addrs = adap->log_addrs;
+	}
+	mutex_unlock(&adap->lock);
+	if (err)
+		return err;
+	if (copy_to_user(parg, &log_addrs, sizeof(log_addrs)))
+		return -EFAULT;
+	return 0;
+}
+
+static long cec_transmit(struct cec_adapter *adap, struct cec_fh *fh,
+			 bool block, struct cec_msg __user *parg)
+{
+	struct cec_msg msg = {};
+	long err = 0;
+
+	if (!(adap->capabilities & CEC_CAP_TRANSMIT))
+		return -ENOTTY;
+	if (copy_from_user(&msg, parg, sizeof(msg)))
+		return -EFAULT;
+	mutex_lock(&adap->lock);
+	if (!adap->is_configured)
+		err = -ENONET;
+	else if (cec_is_busy(adap, fh))
+		err = -EBUSY;
+	else
+		err = cec_transmit_msg_fh(adap, &msg, fh, block);
+	mutex_unlock(&adap->lock);
+	if (err)
+		return err;
+	if (copy_to_user(parg, &msg, sizeof(msg)))
+		return -EFAULT;
+	return 0;
+}
+
+/* Called by CEC_RECEIVE: wait for a message to arrive */
+static int cec_receive_msg(struct cec_fh *fh, struct cec_msg *msg, bool block)
+{
+	u32 timeout = msg->timeout;
+	int res;
+
+	do {
+		mutex_lock(&fh->lock);
+		/* Are there received messages queued up? */
+		if (fh->queued_msgs) {
+			/* Yes, return the first one */
+			struct cec_msg_entry *entry =
+				list_first_entry(&fh->msgs,
+						 struct cec_msg_entry, list);
+
+			list_del(&entry->list);
+			*msg = entry->msg;
+			kfree(entry);
+			fh->queued_msgs--;
+			mutex_unlock(&fh->lock);
+			/* restore original timeout value */
+			msg->timeout = timeout;
+			return 0;
+		}
+
+		/* No, return EAGAIN in non-blocking mode or wait */
+		mutex_unlock(&fh->lock);
+
+		/* Return when in non-blocking mode */
+		if (!block)
+			return -EAGAIN;
+
+		if (msg->timeout) {
+			/* The user specified a timeout */
+			res = wait_event_interruptible_timeout(fh->wait,
+							       fh->queued_msgs,
+				msecs_to_jiffies(msg->timeout));
+			if (res == 0)
+				res = -ETIMEDOUT;
+			else if (res > 0)
+				res = 0;
+		} else {
+			/* Wait indefinitely */
+			res = wait_event_interruptible(fh->wait,
+						       fh->queued_msgs);
+		}
+		/* Exit on error, otherwise loop to get the new message */
+	} while (!res);
+	return res;
+}
+
+static long cec_receive(struct cec_adapter *adap, struct cec_fh *fh,
+			bool block, struct cec_msg __user *parg)
+{
+	struct cec_msg msg = {};
+	long err = 0;
+
+	if (copy_from_user(&msg, parg, sizeof(msg)))
+		return -EFAULT;
+	mutex_lock(&adap->lock);
+	if (!adap->is_configured && fh->mode_follower < CEC_MODE_MONITOR)
+		err = -ENONET;
+	mutex_unlock(&adap->lock);
+	if (err)
+		return err;
+
+	err = cec_receive_msg(fh, &msg, block);
+	if (err)
+		return err;
+	if (copy_to_user(parg, &msg, sizeof(msg)))
+		return -EFAULT;
+	return 0;
+}
+
+static long cec_dqevent(struct cec_adapter *adap, struct cec_fh *fh,
+			bool block, struct cec_event __user *parg)
+{
+	struct cec_event *ev = NULL;
+	u64 ts = ~0ULL;
+	unsigned int i;
+	long err = 0;
+
+	mutex_lock(&fh->lock);
+	while (!fh->pending_events && block) {
+		mutex_unlock(&fh->lock);
+		err = wait_event_interruptible(fh->wait, fh->pending_events);
+		if (err)
+			return err;
+		mutex_lock(&fh->lock);
+	}
+
+	/* Find the oldest event */
+	for (i = 0; i < CEC_NUM_EVENTS; i++) {
+		if (fh->pending_events & (1 << (i + 1)) &&
+		    fh->events[i].ts <= ts) {
+			ev = &fh->events[i];
+			ts = ev->ts;
+		}
+	}
+	if (!ev) {
+		err = -EAGAIN;
+		goto unlock;
+	}
+
+	if (copy_to_user(parg, ev, sizeof(*ev))) {
+		err = -EFAULT;
+		goto unlock;
+	}
+
+	fh->pending_events &= ~(1 << ev->event);
+
+unlock:
+	mutex_unlock(&fh->lock);
+	return err;
+}
+
+static long cec_g_mode(struct cec_adapter *adap, struct cec_fh *fh,
+		       u32 __user *parg)
+{
+	u32 mode = fh->mode_initiator | fh->mode_follower;
+
+	if (copy_to_user(parg, &mode, sizeof(mode)))
+		return -EFAULT;
+	return 0;
+}
+
+static long cec_s_mode(struct cec_adapter *adap, struct cec_fh *fh,
+		       u32 __user *parg)
+{
+	u32 mode;
+	u8 mode_initiator;
+	u8 mode_follower;
+	long err = 0;
+
+	if (copy_from_user(&mode, parg, sizeof(mode)))
+		return -EFAULT;
+	if (mode & ~(CEC_MODE_INITIATOR_MSK | CEC_MODE_FOLLOWER_MSK))
+		return -EINVAL;
+
+	mode_initiator = mode & CEC_MODE_INITIATOR_MSK;
+	mode_follower = mode & CEC_MODE_FOLLOWER_MSK;
+
+	if (mode_initiator > CEC_MODE_EXCL_INITIATOR ||
+	    mode_follower > CEC_MODE_MONITOR_ALL)
+		return -EINVAL;
+
+	if (mode_follower == CEC_MODE_MONITOR_ALL &&
+	    !(adap->capabilities & CEC_CAP_MONITOR_ALL))
+		return -EINVAL;
+
+	/* Follower modes should always be able to send CEC messages */
+	if ((mode_initiator == CEC_MODE_NO_INITIATOR ||
+	     !(adap->capabilities & CEC_CAP_TRANSMIT)) &&
+	    mode_follower >= CEC_MODE_FOLLOWER &&
+	    mode_follower <= CEC_MODE_EXCL_FOLLOWER_PASSTHRU)
+		return -EINVAL;
+
+	/* Monitor modes require CEC_MODE_NO_INITIATOR */
+	if (mode_initiator && mode_follower >= CEC_MODE_MONITOR)
+		return -EINVAL;
+
+	/* Monitor modes require CAP_NET_ADMIN */
+	if (mode_follower >= CEC_MODE_MONITOR && !capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&adap->lock);
+	/*
+	 * You can't become exclusive follower if someone else already
+	 * has that job.
+	 */
+	if ((mode_follower == CEC_MODE_EXCL_FOLLOWER ||
+	     mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) &&
+	    adap->cec_follower && adap->cec_follower != fh)
+		err = -EBUSY;
+	/*
+	 * You can't become exclusive initiator if someone else already
+	 * has that job.
+	 */
+	if (mode_initiator == CEC_MODE_EXCL_INITIATOR &&
+	    adap->cec_initiator && adap->cec_initiator != fh)
+		err = -EBUSY;
+
+	if (!err) {
+		bool old_mon_all = fh->mode_follower == CEC_MODE_MONITOR_ALL;
+		bool new_mon_all = mode_follower == CEC_MODE_MONITOR_ALL;
+
+		if (old_mon_all != new_mon_all) {
+			if (new_mon_all)
+				err = cec_monitor_all_cnt_inc(adap);
+			else
+				cec_monitor_all_cnt_dec(adap);
+		}
+	}
+
+	if (err) {
+		mutex_unlock(&adap->lock);
+		return err;
+	}
+
+	if (fh->mode_follower == CEC_MODE_FOLLOWER)
+		adap->follower_cnt--;
+	if (mode_follower == CEC_MODE_FOLLOWER)
+		adap->follower_cnt++;
+	if (mode_follower == CEC_MODE_EXCL_FOLLOWER ||
+	    mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) {
+		adap->passthrough =
+			mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU;
+		adap->cec_follower = fh;
+	} else if (adap->cec_follower == fh) {
+		adap->passthrough = false;
+		adap->cec_follower = NULL;
+	}
+	if (mode_initiator == CEC_MODE_EXCL_INITIATOR)
+		adap->cec_initiator = fh;
+	else if (adap->cec_initiator == fh)
+		adap->cec_initiator = NULL;
+	fh->mode_initiator = mode_initiator;
+	fh->mode_follower = mode_follower;
+	mutex_unlock(&adap->lock);
+	return 0;
+}
+
+static long cec_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	struct cec_devnode *devnode = cec_devnode_data(filp);
+	struct cec_fh *fh = filp->private_data;
+	struct cec_adapter *adap = fh->adap;
+	bool block = !(filp->f_flags & O_NONBLOCK);
+	void __user *parg = (void __user *)arg;
+
+	if (!devnode->registered)
+		return -EIO;
+
+	switch (cmd) {
+	case CEC_ADAP_G_CAPS:
+		return cec_adap_g_caps(adap, parg);
+
+	case CEC_ADAP_G_PHYS_ADDR:
+		return cec_adap_g_phys_addr(adap, parg);
+
+	case CEC_ADAP_S_PHYS_ADDR:
+		return cec_adap_s_phys_addr(adap, fh, block, parg);
+
+	case CEC_ADAP_G_LOG_ADDRS:
+		return cec_adap_g_log_addrs(adap, parg);
+
+	case CEC_ADAP_S_LOG_ADDRS:
+		return cec_adap_s_log_addrs(adap, fh, block, parg);
+
+	case CEC_TRANSMIT:
+		return cec_transmit(adap, fh, block, parg);
+
+	case CEC_RECEIVE:
+		return cec_receive(adap, fh, block, parg);
+
+	case CEC_DQEVENT:
+		return cec_dqevent(adap, fh, block, parg);
+
+	case CEC_G_MODE:
+		return cec_g_mode(adap, fh, parg);
+
+	case CEC_S_MODE:
+		return cec_s_mode(adap, fh, parg);
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+static int cec_open(struct inode *inode, struct file *filp)
+{
+	struct cec_devnode *devnode =
+		container_of(inode->i_cdev, struct cec_devnode, cdev);
+	struct cec_adapter *adap = to_cec_adapter(devnode);
+	struct cec_fh *fh = kzalloc(sizeof(*fh), GFP_KERNEL);
+	/*
+	 * Initial events that are automatically sent when the cec device is
+	 * opened.
+	 */
+	struct cec_event ev_state = {
+		.event = CEC_EVENT_STATE_CHANGE,
+		.flags = CEC_EVENT_FL_INITIAL_STATE,
+	};
+	int err;
+
+	if (!fh)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&fh->msgs);
+	INIT_LIST_HEAD(&fh->xfer_list);
+	mutex_init(&fh->lock);
+	init_waitqueue_head(&fh->wait);
+
+	fh->mode_initiator = CEC_MODE_INITIATOR;
+	fh->adap = adap;
+
+	err = cec_get_device(devnode);
+	if (err) {
+		kfree(fh);
+		return err;
+	}
+
+	filp->private_data = fh;
+
+	mutex_lock(&devnode->fhs_lock);
+	/* Queue up initial state events */
+	ev_state.state_change.phys_addr = adap->phys_addr;
+	ev_state.state_change.log_addr_mask = adap->log_addrs.log_addr_mask;
+	cec_queue_event_fh(fh, &ev_state, 0);
+
+	list_add(&fh->list, &devnode->fhs);
+	mutex_unlock(&devnode->fhs_lock);
+
+	return 0;
+}
+
+/* Override for the release function */
+static int cec_release(struct inode *inode, struct file *filp)
+{
+	struct cec_devnode *devnode = cec_devnode_data(filp);
+	struct cec_adapter *adap = to_cec_adapter(devnode);
+	struct cec_fh *fh = filp->private_data;
+
+	mutex_lock(&adap->lock);
+	if (adap->cec_initiator == fh)
+		adap->cec_initiator = NULL;
+	if (adap->cec_follower == fh) {
+		adap->cec_follower = NULL;
+		adap->passthrough = false;
+	}
+	if (fh->mode_follower == CEC_MODE_FOLLOWER)
+		adap->follower_cnt--;
+	if (fh->mode_follower == CEC_MODE_MONITOR_ALL)
+		cec_monitor_all_cnt_dec(adap);
+	mutex_unlock(&adap->lock);
+
+	mutex_lock(&devnode->fhs_lock);
+	list_del(&fh->list);
+	mutex_unlock(&devnode->fhs_lock);
+
+	/* Unhook pending transmits from this filehandle. */
+	mutex_lock(&adap->lock);
+	while (!list_empty(&fh->xfer_list)) {
+		struct cec_data *data =
+			list_first_entry(&fh->xfer_list, struct cec_data, xfer_list);
+
+		data->blocking = false;
+		data->fh = NULL;
+		list_del(&data->xfer_list);
+	}
+	mutex_unlock(&adap->lock);
+	while (!list_empty(&fh->msgs)) {
+		struct cec_msg_entry *entry =
+			list_first_entry(&fh->msgs, struct cec_msg_entry, list);
+
+		list_del(&entry->list);
+		kfree(entry);
+	}
+	kfree(fh);
+
+	cec_put_device(devnode);
+	filp->private_data = NULL;
+	return 0;
+}
+
+const struct file_operations cec_devnode_fops = {
+	.owner = THIS_MODULE,
+	.open = cec_open,
+	.unlocked_ioctl = cec_ioctl,
+	.release = cec_release,
+	.poll = cec_poll,
+	.llseek = no_llseek,
+};
diff --git a/drivers/staging/media/cec/cec-core.c b/drivers/staging/media/cec/cec-core.c
new file mode 100644
index 000000000000..112a5fae12f5
--- /dev/null
+++ b/drivers/staging/media/cec/cec-core.c
@@ -0,0 +1,409 @@
+/*
+ * cec-core.c - HDMI Consumer Electronics Control framework - Core
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kmod.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "cec-priv.h"
+
+#define CEC_NUM_DEVICES	256
+#define CEC_NAME	"cec"
+
+int cec_debug;
+module_param_named(debug, cec_debug, int, 0644);
+MODULE_PARM_DESC(debug, "debug level (0-2)");
+
+static dev_t cec_dev_t;
+
+/* Active devices */
+static DEFINE_MUTEX(cec_devnode_lock);
+static DECLARE_BITMAP(cec_devnode_nums, CEC_NUM_DEVICES);
+
+static struct dentry *top_cec_dir;
+
+/* dev to cec_devnode */
+#define to_cec_devnode(cd) container_of(cd, struct cec_devnode, dev)
+
+int cec_get_device(struct cec_devnode *devnode)
+{
+	/*
+	 * Check if the cec device is available. This needs to be done with
+	 * the cec_devnode_lock held to prevent an open/unregister race:
+	 * without the lock, the device could be unregistered and freed between
+	 * the devnode->registered check and get_device() calls, leading to
+	 * a crash.
+	 */
+	mutex_lock(&cec_devnode_lock);
+	/*
+	 * return ENXIO if the cec device has been removed
+	 * already or if it is not registered anymore.
+	 */
+	if (!devnode->registered) {
+		mutex_unlock(&cec_devnode_lock);
+		return -ENXIO;
+	}
+	/* and increase the device refcount */
+	get_device(&devnode->dev);
+	mutex_unlock(&cec_devnode_lock);
+	return 0;
+}
+
+void cec_put_device(struct cec_devnode *devnode)
+{
+	mutex_lock(&cec_devnode_lock);
+	put_device(&devnode->dev);
+	mutex_unlock(&cec_devnode_lock);
+}
+
+/* Called when the last user of the cec device exits. */
+static void cec_devnode_release(struct device *cd)
+{
+	struct cec_devnode *devnode = to_cec_devnode(cd);
+
+	mutex_lock(&cec_devnode_lock);
+
+	/* Mark device node number as free */
+	clear_bit(devnode->minor, cec_devnode_nums);
+
+	mutex_unlock(&cec_devnode_lock);
+	cec_delete_adapter(to_cec_adapter(devnode));
+}
+
+static struct bus_type cec_bus_type = {
+	.name = CEC_NAME,
+};
+
+/*
+ * Register a cec device node
+ *
+ * The registration code assigns minor numbers and registers the new device node
+ * with the kernel. An error is returned if no free minor number can be found,
+ * or if the registration of the device node fails.
+ *
+ * Zero is returned on success.
+ *
+ * Note that if the cec_devnode_register call fails, the release() callback of
+ * the cec_devnode structure is *not* called, so the caller is responsible for
+ * freeing any data.
+ */
+static int __must_check cec_devnode_register(struct cec_devnode *devnode,
+					     struct module *owner)
+{
+	int minor;
+	int ret;
+
+	/* Initialization */
+	INIT_LIST_HEAD(&devnode->fhs);
+	mutex_init(&devnode->fhs_lock);
+
+	/* Part 1: Find a free minor number */
+	mutex_lock(&cec_devnode_lock);
+	minor = find_next_zero_bit(cec_devnode_nums, CEC_NUM_DEVICES, 0);
+	if (minor == CEC_NUM_DEVICES) {
+		mutex_unlock(&cec_devnode_lock);
+		pr_err("could not get a free minor\n");
+		return -ENFILE;
+	}
+
+	set_bit(minor, cec_devnode_nums);
+	mutex_unlock(&cec_devnode_lock);
+
+	devnode->minor = minor;
+	devnode->dev.bus = &cec_bus_type;
+	devnode->dev.devt = MKDEV(MAJOR(cec_dev_t), minor);
+	devnode->dev.release = cec_devnode_release;
+	devnode->dev.parent = devnode->parent;
+	dev_set_name(&devnode->dev, "cec%d", devnode->minor);
+	device_initialize(&devnode->dev);
+
+	/* Part 2: Initialize and register the character device */
+	cdev_init(&devnode->cdev, &cec_devnode_fops);
+	devnode->cdev.kobj.parent = &devnode->dev.kobj;
+	devnode->cdev.owner = owner;
+
+	ret = cdev_add(&devnode->cdev, devnode->dev.devt, 1);
+	if (ret < 0) {
+		pr_err("%s: cdev_add failed\n", __func__);
+		goto clr_bit;
+	}
+
+	ret = device_add(&devnode->dev);
+	if (ret)
+		goto cdev_del;
+
+	devnode->registered = true;
+	return 0;
+
+cdev_del:
+	cdev_del(&devnode->cdev);
+clr_bit:
+	clear_bit(devnode->minor, cec_devnode_nums);
+	return ret;
+}
+
+/*
+ * Unregister a cec device node
+ *
+ * This unregisters the passed device. Future open calls will be met with
+ * errors.
+ *
+ * This function can safely be called if the device node has never been
+ * registered or has already been unregistered.
+ */
+static void cec_devnode_unregister(struct cec_devnode *devnode)
+{
+	struct cec_fh *fh;
+
+	/* Check if devnode was never registered or already unregistered */
+	if (!devnode->registered || devnode->unregistered)
+		return;
+
+	mutex_lock(&devnode->fhs_lock);
+	list_for_each_entry(fh, &devnode->fhs, list)
+		wake_up_interruptible(&fh->wait);
+	mutex_unlock(&devnode->fhs_lock);
+
+	devnode->registered = false;
+	devnode->unregistered = true;
+	device_del(&devnode->dev);
+	cdev_del(&devnode->cdev);
+	put_device(&devnode->dev);
+}
+
+struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops,
+					 void *priv, const char *name, u32 caps,
+					 u8 available_las, struct device *parent)
+{
+	struct cec_adapter *adap;
+	int res;
+
+	if (WARN_ON(!parent))
+		return ERR_PTR(-EINVAL);
+	if (WARN_ON(!caps))
+		return ERR_PTR(-EINVAL);
+	if (WARN_ON(!ops))
+		return ERR_PTR(-EINVAL);
+	if (WARN_ON(!available_las || available_las > CEC_MAX_LOG_ADDRS))
+		return ERR_PTR(-EINVAL);
+	adap = kzalloc(sizeof(*adap), GFP_KERNEL);
+	if (!adap)
+		return ERR_PTR(-ENOMEM);
+	adap->owner = parent->driver->owner;
+	adap->devnode.parent = parent;
+	strlcpy(adap->name, name, sizeof(adap->name));
+	adap->phys_addr = CEC_PHYS_ADDR_INVALID;
+	adap->log_addrs.cec_version = CEC_OP_CEC_VERSION_2_0;
+	adap->log_addrs.vendor_id = CEC_VENDOR_ID_NONE;
+	adap->capabilities = caps;
+	adap->available_log_addrs = available_las;
+	adap->sequence = 0;
+	adap->ops = ops;
+	adap->priv = priv;
+	memset(adap->phys_addrs, 0xff, sizeof(adap->phys_addrs));
+	mutex_init(&adap->lock);
+	INIT_LIST_HEAD(&adap->transmit_queue);
+	INIT_LIST_HEAD(&adap->wait_queue);
+	init_waitqueue_head(&adap->kthread_waitq);
+
+	adap->kthread = kthread_run(cec_thread_func, adap, "cec-%s", name);
+	if (IS_ERR(adap->kthread)) {
+		pr_err("cec-%s: kernel_thread() failed\n", name);
+		res = PTR_ERR(adap->kthread);
+		kfree(adap);
+		return ERR_PTR(res);
+	}
+
+	if (!(caps & CEC_CAP_RC))
+		return adap;
+
+#if IS_REACHABLE(CONFIG_RC_CORE)
+	/* Prepare the RC input device */
+	adap->rc = rc_allocate_device();
+	if (!adap->rc) {
+		pr_err("cec-%s: failed to allocate memory for rc_dev\n",
+		       name);
+		kthread_stop(adap->kthread);
+		kfree(adap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	snprintf(adap->input_name, sizeof(adap->input_name),
+		 "RC for %s", name);
+	snprintf(adap->input_phys, sizeof(adap->input_phys),
+		 "%s/input0", name);
+
+	adap->rc->input_name = adap->input_name;
+	adap->rc->input_phys = adap->input_phys;
+	adap->rc->input_id.bustype = BUS_CEC;
+	adap->rc->input_id.vendor = 0;
+	adap->rc->input_id.product = 0;
+	adap->rc->input_id.version = 1;
+	adap->rc->dev.parent = parent;
+	adap->rc->driver_type = RC_DRIVER_SCANCODE;
+	adap->rc->driver_name = CEC_NAME;
+	adap->rc->allowed_protocols = RC_BIT_CEC;
+	adap->rc->priv = adap;
+	adap->rc->map_name = RC_MAP_CEC;
+	adap->rc->timeout = MS_TO_NS(100);
+#else
+	adap->capabilities &= ~CEC_CAP_RC;
+#endif
+	return adap;
+}
+EXPORT_SYMBOL_GPL(cec_allocate_adapter);
+
+int cec_register_adapter(struct cec_adapter *adap)
+{
+	int res;
+
+	if (IS_ERR_OR_NULL(adap))
+		return 0;
+
+#if IS_REACHABLE(CONFIG_RC_CORE)
+	if (adap->capabilities & CEC_CAP_RC) {
+		res = rc_register_device(adap->rc);
+
+		if (res) {
+			pr_err("cec-%s: failed to prepare input device\n",
+			       adap->name);
+			rc_free_device(adap->rc);
+			adap->rc = NULL;
+			return res;
+		}
+	}
+#endif
+
+	res = cec_devnode_register(&adap->devnode, adap->owner);
+	if (res) {
+#if IS_REACHABLE(CONFIG_RC_CORE)
+		/* Note: rc_unregister also calls rc_free */
+		rc_unregister_device(adap->rc);
+		adap->rc = NULL;
+#endif
+		return res;
+	}
+
+	dev_set_drvdata(&adap->devnode.dev, adap);
+#ifdef CONFIG_MEDIA_CEC_DEBUG
+	if (!top_cec_dir)
+		return 0;
+
+	adap->cec_dir = debugfs_create_dir(dev_name(&adap->devnode.dev), top_cec_dir);
+	if (IS_ERR_OR_NULL(adap->cec_dir)) {
+		pr_warn("cec-%s: Failed to create debugfs dir\n", adap->name);
+		return 0;
+	}
+	adap->status_file = debugfs_create_devm_seqfile(&adap->devnode.dev,
+		"status", adap->cec_dir, cec_adap_status);
+	if (IS_ERR_OR_NULL(adap->status_file)) {
+		pr_warn("cec-%s: Failed to create status file\n", adap->name);
+		debugfs_remove_recursive(adap->cec_dir);
+		adap->cec_dir = NULL;
+	}
+#endif
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cec_register_adapter);
+
+void cec_unregister_adapter(struct cec_adapter *adap)
+{
+	if (IS_ERR_OR_NULL(adap))
+		return;
+
+#if IS_REACHABLE(CONFIG_RC_CORE)
+	/* Note: rc_unregister also calls rc_free */
+	rc_unregister_device(adap->rc);
+	adap->rc = NULL;
+#endif
+	debugfs_remove_recursive(adap->cec_dir);
+	cec_devnode_unregister(&adap->devnode);
+}
+EXPORT_SYMBOL_GPL(cec_unregister_adapter);
+
+void cec_delete_adapter(struct cec_adapter *adap)
+{
+	if (IS_ERR_OR_NULL(adap))
+		return;
+	mutex_lock(&adap->lock);
+	__cec_s_phys_addr(adap, CEC_PHYS_ADDR_INVALID, false);
+	mutex_unlock(&adap->lock);
+	kthread_stop(adap->kthread);
+	if (adap->kthread_config)
+		kthread_stop(adap->kthread_config);
+#if IS_REACHABLE(CONFIG_RC_CORE)
+	if (adap->rc)
+		rc_free_device(adap->rc);
+#endif
+	kfree(adap);
+}
+EXPORT_SYMBOL_GPL(cec_delete_adapter);
+
+/*
+ *	Initialise cec for linux
+ */
+static int __init cec_devnode_init(void)
+{
+	int ret;
+
+	pr_info("Linux cec interface: v0.10\n");
+	ret = alloc_chrdev_region(&cec_dev_t, 0, CEC_NUM_DEVICES,
+				  CEC_NAME);
+	if (ret < 0) {
+		pr_warn("cec: unable to allocate major\n");
+		return ret;
+	}
+
+#ifdef CONFIG_MEDIA_CEC_DEBUG
+	top_cec_dir = debugfs_create_dir("cec", NULL);
+	if (IS_ERR_OR_NULL(top_cec_dir)) {
+		pr_warn("cec: Failed to create debugfs cec dir\n");
+		top_cec_dir = NULL;
+	}
+#endif
+
+	ret = bus_register(&cec_bus_type);
+	if (ret < 0) {
+		unregister_chrdev_region(cec_dev_t, CEC_NUM_DEVICES);
+		pr_warn("cec: bus_register failed\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void __exit cec_devnode_exit(void)
+{
+	debugfs_remove_recursive(top_cec_dir);
+	bus_unregister(&cec_bus_type);
+	unregister_chrdev_region(cec_dev_t, CEC_NUM_DEVICES);
+}
+
+subsys_initcall(cec_devnode_init);
+module_exit(cec_devnode_exit)
+
+MODULE_AUTHOR("Hans Verkuil <hans.verkuil@cisco.com>");
+MODULE_DESCRIPTION("Device node registration for cec drivers");
+MODULE_LICENSE("GPL");
diff --git a/drivers/staging/media/cec/cec-priv.h b/drivers/staging/media/cec/cec-priv.h
new file mode 100644
index 000000000000..70767a7900f2
--- /dev/null
+++ b/drivers/staging/media/cec/cec-priv.h
@@ -0,0 +1,56 @@
+/*
+ * cec-priv.h - HDMI Consumer Electronics Control internal header
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#ifndef _CEC_PRIV_H
+#define _CEC_PRIV_H
+
+#include <linux/cec-funcs.h>
+#include <media/cec.h>
+
+#define dprintk(lvl, fmt, arg...)					\
+	do {								\
+		if (lvl <= cec_debug)					\
+			pr_info("cec-%s: " fmt, adap->name, ## arg);	\
+	} while (0)
+
+/* devnode to cec_adapter */
+#define to_cec_adapter(node) container_of(node, struct cec_adapter, devnode)
+
+/* cec-core.c */
+extern int cec_debug;
+int cec_get_device(struct cec_devnode *devnode);
+void cec_put_device(struct cec_devnode *devnode);
+
+/* cec-adap.c */
+int cec_monitor_all_cnt_inc(struct cec_adapter *adap);
+void cec_monitor_all_cnt_dec(struct cec_adapter *adap);
+int cec_adap_status(struct seq_file *file, void *priv);
+int cec_thread_func(void *_adap);
+void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block);
+int __cec_s_log_addrs(struct cec_adapter *adap,
+		      struct cec_log_addrs *log_addrs, bool block);
+int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg,
+			struct cec_fh *fh, bool block);
+void cec_queue_event_fh(struct cec_fh *fh,
+			const struct cec_event *new_ev, u64 ts);
+
+/* cec-api.c */
+extern const struct file_operations cec_devnode_fops;
+
+#endif
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c
index ea3ddec75806..3319fb8f7d01 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c
@@ -542,7 +542,6 @@ static int vpfe_release(struct file *file)
 		video->io_usrs = 0;
 		/* Free buffers allocated */
 		vb2_queue_release(&video->buffer_queue);
-		vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 	}
 	/* Decrement device users counter */
 	video->usrs--;
@@ -1092,7 +1091,7 @@ vpfe_g_dv_timings(struct file *file, void *fh,
  * @nbuffers: ptr to number of buffers requested by application
  * @nplanes:: contains number of distinct video planes needed to hold a frame
  * @sizes[]: contains the size (in bytes) of each plane.
- * @alloc_ctxs: ptr to allocation context
+ * @alloc_devs: ptr to allocation context
  *
  * This callback function is called when reqbuf() is called to adjust
  * the buffer nbuffers and buffer size
@@ -1100,7 +1099,7 @@ vpfe_g_dv_timings(struct file *file, void *fh,
 static int
 vpfe_buffer_queue_setup(struct vb2_queue *vq,
 			unsigned int *nbuffers, unsigned int *nplanes,
-			unsigned int sizes[], void *alloc_ctxs[])
+			unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct vpfe_fh *fh = vb2_get_drv_priv(vq);
 	struct vpfe_video_device *video = fh->video;
@@ -1115,7 +1114,6 @@ vpfe_buffer_queue_setup(struct vb2_queue *vq,
 
 	*nplanes = 1;
 	sizes[0] = size;
-	alloc_ctxs[0] = video->alloc_ctx;
 	v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
 		 "nbuffers=%d, size=%lu\n", *nbuffers, size);
 	return 0;
@@ -1350,12 +1348,6 @@ static int vpfe_reqbufs(struct file *file, void *priv,
 	video->memory = req_buf->memory;
 
 	/* Initialize videobuf2 queue as per the buffer type */
-	video->alloc_ctx = vb2_dma_contig_init_ctx(vpfe_dev->pdev);
-	if (IS_ERR(video->alloc_ctx)) {
-		v4l2_err(&vpfe_dev->v4l2_dev, "Failed to get the context\n");
-		return PTR_ERR(video->alloc_ctx);
-	}
-
 	q = &video->buffer_queue;
 	q->type = req_buf->type;
 	q->io_modes = VB2_MMAP | VB2_USERPTR;
@@ -1365,11 +1357,11 @@ static int vpfe_reqbufs(struct file *file, void *priv,
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->buf_struct_size = sizeof(struct vpfe_cap_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->dev = vpfe_dev->pdev;
 
 	ret = vb2_queue_init(q);
 	if (ret) {
 		v4l2_err(&vpfe_dev->v4l2_dev, "vb2_queue_init() failed\n");
-		vb2_dma_contig_cleanup_ctx(vpfe_dev->pdev);
 		return ret;
 	}
 
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.h b/drivers/staging/media/davinci_vpfe/vpfe_video.h
index 653334d537d3..aaec4403df3b 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.h
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.h
@@ -123,8 +123,6 @@ struct vpfe_video_device {
 	/* Used to store pixel format */
 	struct v4l2_format			fmt;
 	struct vb2_queue			buffer_queue;
-	/* allocator-specific contexts for each plane */
-	struct vb2_alloc_ctx *alloc_ctx;
 	/* Queue of filled frames */
 	struct list_head			dma_queue;
 	spinlock_t				irqlock;
diff --git a/drivers/staging/media/lirc/lirc_parallel.c b/drivers/staging/media/lirc/lirc_parallel.c
index 68ede6c56e6d..3906ac6e686d 100644
--- a/drivers/staging/media/lirc/lirc_parallel.c
+++ b/drivers/staging/media/lirc/lirc_parallel.c
@@ -305,9 +305,9 @@ static void lirc_lirc_irq_handler(void *blah)
 
 	/* enable interrupt */
 	/*
-	  enable_irq(irq);
-	  out(LIRC_PORT_IRQ, in(LIRC_PORT_IRQ)|LP_PINTEN);
-	*/
+	 * enable_irq(irq);
+	 * out(LIRC_PORT_IRQ, in(LIRC_PORT_IRQ)|LP_PINTEN);
+	 */
 }
 
 /*** file operations ***/
@@ -620,7 +620,7 @@ static void kf(void *handle)
 	lirc_off();
 	/* this is a bit annoying when you actually print...*/
 	/*
-	printk(KERN_INFO "%s: reclaimed port\n", LIRC_DRIVER_NAME);
+	 * printk(KERN_INFO "%s: reclaimed port\n", LIRC_DRIVER_NAME);
 	*/
 }
 
diff --git a/drivers/staging/media/mn88472/Kconfig b/drivers/staging/media/mn88472/Kconfig
deleted file mode 100644
index a85c90a60bce..000000000000
--- a/drivers/staging/media/mn88472/Kconfig
+++ /dev/null
@@ -1,7 +0,0 @@
-config DVB_MN88472
-	tristate "Panasonic MN88472"
-	depends on DVB_CORE && I2C
-	select REGMAP_I2C
-	default m if !MEDIA_SUBDRV_AUTOSELECT
-	help
-	  Say Y when you want to support this frontend.
diff --git a/drivers/staging/media/mn88472/Makefile b/drivers/staging/media/mn88472/Makefile
deleted file mode 100644
index 5987b7e6d82a..000000000000
--- a/drivers/staging/media/mn88472/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-obj-$(CONFIG_DVB_MN88472) += mn88472.o
-
-ccflags-y += -Idrivers/media/dvb-core/
-ccflags-y += -Idrivers/media/dvb-frontends/
-ccflags-y += -Idrivers/media/tuners/
diff --git a/drivers/staging/media/mn88472/TODO b/drivers/staging/media/mn88472/TODO
deleted file mode 100644
index b90a14be3beb..000000000000
--- a/drivers/staging/media/mn88472/TODO
+++ /dev/null
@@ -1,21 +0,0 @@
-Driver general quality is not good enough for mainline. Also, other
-device drivers (USB-bridge, tuner) needed for Astrometa receiver in
-question could need some changes. However, if that driver is mainlined
-due to some other device than Astrometa, unrelated TODOs could be
-skipped. In that case rtl28xxu driver needs module parameter to prevent
-driver loading.
-
-Required TODOs:
-* missing lock flags
-* I2C errors
-* tuner sensitivity
-
-*Do not* send any patch fixing checkpatch.pl issues. Currently it passes
-checkpatch.pl tests. I don't want waste my time to review this kind of
-trivial stuff. *Do not* add missing register I/O error checks. Those are
-missing for the reason it is much easier to compare I2C data sniffs when
-there is less lines. Those error checks are about the last thing to be added.
-
-Patches should be submitted to:
-linux-media@vger.kernel.org and Antti Palosaari <crope@iki.fi>
-
diff --git a/drivers/staging/media/mx2/Kconfig b/drivers/staging/media/mx2/Kconfig
deleted file mode 100644
index beaa885cf104..000000000000
--- a/drivers/staging/media/mx2/Kconfig
+++ /dev/null
@@ -1,15 +0,0 @@
-config VIDEO_MX2
-	tristate "i.MX27 Camera Sensor Interface driver"
-	depends on VIDEO_DEV && SOC_CAMERA
-	depends on SOC_IMX27 || COMPILE_TEST
-	depends on HAS_DMA
-	select VIDEOBUF2_DMA_CONTIG
-	---help---
-	  This is a v4l2 driver for the i.MX27 Camera Sensor Interface
-
-	  This driver is deprecated: it should become a stand-alone driver
-	  instead of using the soc-camera framework.
-
-	  Unless someone is willing to take this on (unlikely with such
-	  ancient hardware) it is going to be removed from the kernel
-	  soon.
diff --git a/drivers/staging/media/mx2/Makefile b/drivers/staging/media/mx2/Makefile
deleted file mode 100644
index fc5b2826a558..000000000000
--- a/drivers/staging/media/mx2/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# Makefile for i.MX27 Camera Sensor driver
-
-obj-$(CONFIG_VIDEO_MX2) += mx2_camera.o
diff --git a/drivers/staging/media/mx2/TODO b/drivers/staging/media/mx2/TODO
deleted file mode 100644
index bc68fa443a3e..000000000000
--- a/drivers/staging/media/mx2/TODO
+++ /dev/null
@@ -1,10 +0,0 @@
-This driver is deprecated: it should become a stand-alone driver instead of
-using the soc-camera framework.
-
-Unless someone is willing to take this on (unlikely with such ancient
-hardware) it is going to be removed from the kernel soon.
-
-Note that trivial patches will not be accepted anymore, only a full conversion.
-
-If you want to convert this driver, please contact the linux-media mailinglist
-(see http://linuxtv.org/lists.php).
diff --git a/drivers/staging/media/mx2/mx2_camera.c b/drivers/staging/media/mx2/mx2_camera.c
deleted file mode 100644
index 48dd5b7851b5..000000000000
--- a/drivers/staging/media/mx2/mx2_camera.c
+++ /dev/null
@@ -1,1636 +0,0 @@
-/*
- * V4L2 Driver for i.MX27 camera host
- *
- * Copyright (C) 2008, Sascha Hauer, Pengutronix
- * Copyright (C) 2010, Baruch Siach, Orex Computed Radiography
- * Copyright (C) 2012, Javier Martin, Vista Silicon S.L.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/dma-mapping.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/gcd.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/math64.h>
-#include <linux/mm.h>
-#include <linux/moduleparam.h>
-#include <linux/time.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-
-#include <media/v4l2-common.h>
-#include <media/v4l2-dev.h>
-#include <media/videobuf2-v4l2.h>
-#include <media/videobuf2-dma-contig.h>
-#include <media/soc_camera.h>
-#include <media/drv-intf/soc_mediabus.h>
-
-#include <linux/videodev2.h>
-
-#include <linux/platform_data/media/camera-mx2.h>
-
-#include <asm/dma.h>
-
-#define MX2_CAM_DRV_NAME "mx2-camera"
-#define MX2_CAM_VERSION "0.0.6"
-#define MX2_CAM_DRIVER_DESCRIPTION "i.MX2x_Camera"
-
-/* reset values */
-#define CSICR1_RESET_VAL	0x40000800
-#define CSICR2_RESET_VAL	0x0
-#define CSICR3_RESET_VAL	0x0
-
-/* csi control reg 1 */
-#define CSICR1_SWAP16_EN	(1 << 31)
-#define CSICR1_EXT_VSYNC	(1 << 30)
-#define CSICR1_EOF_INTEN	(1 << 29)
-#define CSICR1_PRP_IF_EN	(1 << 28)
-#define CSICR1_CCIR_MODE	(1 << 27)
-#define CSICR1_COF_INTEN	(1 << 26)
-#define CSICR1_SF_OR_INTEN	(1 << 25)
-#define CSICR1_RF_OR_INTEN	(1 << 24)
-#define CSICR1_STATFF_LEVEL	(3 << 22)
-#define CSICR1_STATFF_INTEN	(1 << 21)
-#define CSICR1_RXFF_LEVEL(l)	(((l) & 3) << 19)
-#define CSICR1_RXFF_INTEN	(1 << 18)
-#define CSICR1_SOF_POL		(1 << 17)
-#define CSICR1_SOF_INTEN	(1 << 16)
-#define CSICR1_MCLKDIV(d)	(((d) & 0xF) << 12)
-#define CSICR1_HSYNC_POL	(1 << 11)
-#define CSICR1_CCIR_EN		(1 << 10)
-#define CSICR1_MCLKEN		(1 << 9)
-#define CSICR1_FCC		(1 << 8)
-#define CSICR1_PACK_DIR		(1 << 7)
-#define CSICR1_CLR_STATFIFO	(1 << 6)
-#define CSICR1_CLR_RXFIFO	(1 << 5)
-#define CSICR1_GCLK_MODE	(1 << 4)
-#define CSICR1_INV_DATA		(1 << 3)
-#define CSICR1_INV_PCLK		(1 << 2)
-#define CSICR1_REDGE		(1 << 1)
-#define CSICR1_FMT_MASK		(CSICR1_PACK_DIR | CSICR1_SWAP16_EN)
-
-#define SHIFT_STATFF_LEVEL	22
-#define SHIFT_RXFF_LEVEL	19
-#define SHIFT_MCLKDIV		12
-
-#define SHIFT_FRMCNT		16
-
-#define CSICR1			0x00
-#define CSICR2			0x04
-#define CSISR			0x08
-#define CSISTATFIFO		0x0c
-#define CSIRFIFO		0x10
-#define CSIRXCNT		0x14
-#define CSICR3			0x1c
-#define CSIDMASA_STATFIFO	0x20
-#define CSIDMATA_STATFIFO	0x24
-#define CSIDMASA_FB1		0x28
-#define CSIDMASA_FB2		0x2c
-#define CSIFBUF_PARA		0x30
-#define CSIIMAG_PARA		0x34
-
-/* EMMA PrP */
-#define PRP_CNTL			0x00
-#define PRP_INTR_CNTL			0x04
-#define PRP_INTRSTATUS			0x08
-#define PRP_SOURCE_Y_PTR		0x0c
-#define PRP_SOURCE_CB_PTR		0x10
-#define PRP_SOURCE_CR_PTR		0x14
-#define PRP_DEST_RGB1_PTR		0x18
-#define PRP_DEST_RGB2_PTR		0x1c
-#define PRP_DEST_Y_PTR			0x20
-#define PRP_DEST_CB_PTR			0x24
-#define PRP_DEST_CR_PTR			0x28
-#define PRP_SRC_FRAME_SIZE		0x2c
-#define PRP_DEST_CH1_LINE_STRIDE	0x30
-#define PRP_SRC_PIXEL_FORMAT_CNTL	0x34
-#define PRP_CH1_PIXEL_FORMAT_CNTL	0x38
-#define PRP_CH1_OUT_IMAGE_SIZE		0x3c
-#define PRP_CH2_OUT_IMAGE_SIZE		0x40
-#define PRP_SRC_LINE_STRIDE		0x44
-#define PRP_CSC_COEF_012		0x48
-#define PRP_CSC_COEF_345		0x4c
-#define PRP_CSC_COEF_678		0x50
-#define PRP_CH1_RZ_HORI_COEF1		0x54
-#define PRP_CH1_RZ_HORI_COEF2		0x58
-#define PRP_CH1_RZ_HORI_VALID		0x5c
-#define PRP_CH1_RZ_VERT_COEF1		0x60
-#define PRP_CH1_RZ_VERT_COEF2		0x64
-#define PRP_CH1_RZ_VERT_VALID		0x68
-#define PRP_CH2_RZ_HORI_COEF1		0x6c
-#define PRP_CH2_RZ_HORI_COEF2		0x70
-#define PRP_CH2_RZ_HORI_VALID		0x74
-#define PRP_CH2_RZ_VERT_COEF1		0x78
-#define PRP_CH2_RZ_VERT_COEF2		0x7c
-#define PRP_CH2_RZ_VERT_VALID		0x80
-
-#define PRP_CNTL_CH1EN		(1 << 0)
-#define PRP_CNTL_CH2EN		(1 << 1)
-#define PRP_CNTL_CSIEN		(1 << 2)
-#define PRP_CNTL_DATA_IN_YUV420	(0 << 3)
-#define PRP_CNTL_DATA_IN_YUV422	(1 << 3)
-#define PRP_CNTL_DATA_IN_RGB16	(2 << 3)
-#define PRP_CNTL_DATA_IN_RGB32	(3 << 3)
-#define PRP_CNTL_CH1_OUT_RGB8	(0 << 5)
-#define PRP_CNTL_CH1_OUT_RGB16	(1 << 5)
-#define PRP_CNTL_CH1_OUT_RGB32	(2 << 5)
-#define PRP_CNTL_CH1_OUT_YUV422	(3 << 5)
-#define PRP_CNTL_CH2_OUT_YUV420	(0 << 7)
-#define PRP_CNTL_CH2_OUT_YUV422 (1 << 7)
-#define PRP_CNTL_CH2_OUT_YUV444	(2 << 7)
-#define PRP_CNTL_CH1_LEN	(1 << 9)
-#define PRP_CNTL_CH2_LEN	(1 << 10)
-#define PRP_CNTL_SKIP_FRAME	(1 << 11)
-#define PRP_CNTL_SWRST		(1 << 12)
-#define PRP_CNTL_CLKEN		(1 << 13)
-#define PRP_CNTL_WEN		(1 << 14)
-#define PRP_CNTL_CH1BYP		(1 << 15)
-#define PRP_CNTL_IN_TSKIP(x)	((x) << 16)
-#define PRP_CNTL_CH1_TSKIP(x)	((x) << 19)
-#define PRP_CNTL_CH2_TSKIP(x)	((x) << 22)
-#define PRP_CNTL_INPUT_FIFO_LEVEL(x)	((x) << 25)
-#define PRP_CNTL_RZ_FIFO_LEVEL(x)	((x) << 27)
-#define PRP_CNTL_CH2B1EN	(1 << 29)
-#define PRP_CNTL_CH2B2EN	(1 << 30)
-#define PRP_CNTL_CH2FEN		(1 << 31)
-
-/* IRQ Enable and status register */
-#define PRP_INTR_RDERR		(1 << 0)
-#define PRP_INTR_CH1WERR	(1 << 1)
-#define PRP_INTR_CH2WERR	(1 << 2)
-#define PRP_INTR_CH1FC		(1 << 3)
-#define PRP_INTR_CH2FC		(1 << 5)
-#define PRP_INTR_LBOVF		(1 << 7)
-#define PRP_INTR_CH2OVF		(1 << 8)
-
-/* Resizing registers */
-#define PRP_RZ_VALID_TBL_LEN(x)	((x) << 24)
-#define PRP_RZ_VALID_BILINEAR	(1 << 31)
-
-#define MAX_VIDEO_MEM	16
-
-#define RESIZE_NUM_MIN	1
-#define RESIZE_NUM_MAX	20
-#define BC_COEF		3
-#define SZ_COEF		(1 << BC_COEF)
-
-#define RESIZE_DIR_H	0
-#define RESIZE_DIR_V	1
-
-#define RESIZE_ALGO_BILINEAR 0
-#define RESIZE_ALGO_AVERAGING 1
-
-struct mx2_prp_cfg {
-	int channel;
-	u32 in_fmt;
-	u32 out_fmt;
-	u32 src_pixel;
-	u32 ch1_pixel;
-	u32 irq_flags;
-	u32 csicr1;
-};
-
-/* prp resizing parameters */
-struct emma_prp_resize {
-	int		algo; /* type of algorithm used */
-	int		len; /* number of coefficients */
-	unsigned char	s[RESIZE_NUM_MAX]; /* table of coefficients */
-};
-
-/* prp configuration for a client-host fmt pair */
-struct mx2_fmt_cfg {
-	u32	in_fmt;
-	u32				out_fmt;
-	struct mx2_prp_cfg		cfg;
-};
-
-struct mx2_buf_internal {
-	struct list_head	queue;
-	int			bufnum;
-	bool			discard;
-};
-
-/* buffer for one video frame */
-struct mx2_buffer {
-	/* common v4l buffer stuff -- must be first */
-	struct vb2_v4l2_buffer vb;
-	struct mx2_buf_internal		internal;
-};
-
-enum mx2_camera_type {
-	IMX27_CAMERA,
-};
-
-struct mx2_camera_dev {
-	struct device		*dev;
-	struct soc_camera_host	soc_host;
-	struct clk		*clk_emma_ahb, *clk_emma_ipg;
-	struct clk		*clk_csi_ahb, *clk_csi_per;
-
-	void __iomem		*base_csi, *base_emma;
-
-	struct mx2_camera_platform_data *pdata;
-	unsigned long		platform_flags;
-
-	struct list_head	capture;
-	struct list_head	active_bufs;
-	struct list_head	discard;
-
-	spinlock_t		lock;
-
-	int			dma;
-	struct mx2_buffer	*active;
-	struct mx2_buffer	*fb1_active;
-	struct mx2_buffer	*fb2_active;
-
-	u32			csicr1;
-	enum mx2_camera_type	devtype;
-
-	struct mx2_buf_internal buf_discard[2];
-	void			*discard_buffer;
-	dma_addr_t		discard_buffer_dma;
-	size_t			discard_size;
-	struct mx2_fmt_cfg	*emma_prp;
-	struct emma_prp_resize	resizing[2];
-	unsigned int		s_width, s_height;
-	u32			frame_count;
-	struct vb2_alloc_ctx	*alloc_ctx;
-};
-
-static struct platform_device_id mx2_camera_devtype[] = {
-	{
-		.name = "imx27-camera",
-		.driver_data = IMX27_CAMERA,
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(platform, mx2_camera_devtype);
-
-static struct mx2_buffer *mx2_ibuf_to_buf(struct mx2_buf_internal *int_buf)
-{
-	return container_of(int_buf, struct mx2_buffer, internal);
-}
-
-static struct mx2_fmt_cfg mx27_emma_prp_table[] = {
-	/*
-	 * This is a generic configuration which is valid for most
-	 * prp input-output format combinations.
-	 * We set the incoming and outgoing pixelformat to a
-	 * 16 Bit wide format and adjust the bytesperline
-	 * accordingly. With this configuration the inputdata
-	 * will not be changed by the emma and could be any type
-	 * of 16 Bit Pixelformat.
-	 */
-	{
-		.in_fmt		= 0,
-		.out_fmt	= 0,
-		.cfg		= {
-			.channel	= 1,
-			.in_fmt		= PRP_CNTL_DATA_IN_RGB16,
-			.out_fmt	= PRP_CNTL_CH1_OUT_RGB16,
-			.src_pixel	= 0x2ca00565, /* RGB565 */
-			.ch1_pixel	= 0x2ca00565, /* RGB565 */
-			.irq_flags	= PRP_INTR_RDERR | PRP_INTR_CH1WERR |
-						PRP_INTR_CH1FC | PRP_INTR_LBOVF,
-			.csicr1		= 0,
-		}
-	},
-	{
-		.in_fmt		= MEDIA_BUS_FMT_UYVY8_2X8,
-		.out_fmt	= V4L2_PIX_FMT_YUYV,
-		.cfg		= {
-			.channel	= 1,
-			.in_fmt		= PRP_CNTL_DATA_IN_YUV422,
-			.out_fmt	= PRP_CNTL_CH1_OUT_YUV422,
-			.src_pixel	= 0x22000888, /* YUV422 (YUYV) */
-			.ch1_pixel	= 0x62000888, /* YUV422 (YUYV) */
-			.irq_flags	= PRP_INTR_RDERR | PRP_INTR_CH1WERR |
-						PRP_INTR_CH1FC | PRP_INTR_LBOVF,
-			.csicr1		= CSICR1_SWAP16_EN,
-		}
-	},
-	{
-		.in_fmt		= MEDIA_BUS_FMT_YUYV8_2X8,
-		.out_fmt	= V4L2_PIX_FMT_YUYV,
-		.cfg		= {
-			.channel	= 1,
-			.in_fmt		= PRP_CNTL_DATA_IN_YUV422,
-			.out_fmt	= PRP_CNTL_CH1_OUT_YUV422,
-			.src_pixel	= 0x22000888, /* YUV422 (YUYV) */
-			.ch1_pixel	= 0x62000888, /* YUV422 (YUYV) */
-			.irq_flags	= PRP_INTR_RDERR | PRP_INTR_CH1WERR |
-						PRP_INTR_CH1FC | PRP_INTR_LBOVF,
-			.csicr1		= CSICR1_PACK_DIR,
-		}
-	},
-	{
-		.in_fmt		= MEDIA_BUS_FMT_YUYV8_2X8,
-		.out_fmt	= V4L2_PIX_FMT_YUV420,
-		.cfg		= {
-			.channel	= 2,
-			.in_fmt		= PRP_CNTL_DATA_IN_YUV422,
-			.out_fmt	= PRP_CNTL_CH2_OUT_YUV420,
-			.src_pixel	= 0x22000888, /* YUV422 (YUYV) */
-			.irq_flags	= PRP_INTR_RDERR | PRP_INTR_CH2WERR |
-					PRP_INTR_CH2FC | PRP_INTR_LBOVF |
-					PRP_INTR_CH2OVF,
-			.csicr1		= CSICR1_PACK_DIR,
-		}
-	},
-	{
-		.in_fmt		= MEDIA_BUS_FMT_UYVY8_2X8,
-		.out_fmt	= V4L2_PIX_FMT_YUV420,
-		.cfg		= {
-			.channel	= 2,
-			.in_fmt		= PRP_CNTL_DATA_IN_YUV422,
-			.out_fmt	= PRP_CNTL_CH2_OUT_YUV420,
-			.src_pixel	= 0x22000888, /* YUV422 (YUYV) */
-			.irq_flags	= PRP_INTR_RDERR | PRP_INTR_CH2WERR |
-					PRP_INTR_CH2FC | PRP_INTR_LBOVF |
-					PRP_INTR_CH2OVF,
-			.csicr1		= CSICR1_SWAP16_EN,
-		}
-	},
-};
-
-static struct mx2_fmt_cfg *mx27_emma_prp_get_format(u32 in_fmt, u32 out_fmt)
-{
-	int i;
-
-	for (i = 1; i < ARRAY_SIZE(mx27_emma_prp_table); i++)
-		if ((mx27_emma_prp_table[i].in_fmt == in_fmt) &&
-				(mx27_emma_prp_table[i].out_fmt == out_fmt)) {
-			return &mx27_emma_prp_table[i];
-		}
-	/* If no match return the most generic configuration */
-	return &mx27_emma_prp_table[0];
-};
-
-static void mx27_update_emma_buf(struct mx2_camera_dev *pcdev,
-				 unsigned long phys, int bufnum)
-{
-	struct mx2_fmt_cfg *prp = pcdev->emma_prp;
-
-	if (prp->cfg.channel == 1) {
-		writel(phys, pcdev->base_emma +
-				PRP_DEST_RGB1_PTR + 4 * bufnum);
-	} else {
-		writel(phys, pcdev->base_emma +
-			PRP_DEST_Y_PTR - 0x14 * bufnum);
-		if (prp->out_fmt == V4L2_PIX_FMT_YUV420) {
-			u32 imgsize = pcdev->soc_host.icd->user_height *
-					pcdev->soc_host.icd->user_width;
-
-			writel(phys + imgsize, pcdev->base_emma +
-				PRP_DEST_CB_PTR - 0x14 * bufnum);
-			writel(phys + ((5 * imgsize) / 4), pcdev->base_emma +
-				PRP_DEST_CR_PTR - 0x14 * bufnum);
-		}
-	}
-}
-
-static void mx2_camera_deactivate(struct mx2_camera_dev *pcdev)
-{
-	clk_disable_unprepare(pcdev->clk_csi_ahb);
-	clk_disable_unprepare(pcdev->clk_csi_per);
-	writel(0, pcdev->base_csi + CSICR1);
-	writel(0, pcdev->base_emma + PRP_CNTL);
-}
-
-static int mx2_camera_add_device(struct soc_camera_device *icd)
-{
-	dev_info(icd->parent, "Camera driver attached to camera %d\n",
-		 icd->devnum);
-
-	return 0;
-}
-
-static void mx2_camera_remove_device(struct soc_camera_device *icd)
-{
-	dev_info(icd->parent, "Camera driver detached from camera %d\n",
-		 icd->devnum);
-}
-
-/*
- * The following two functions absolutely depend on the fact, that
- * there can be only one camera on mx2 camera sensor interface
- */
-static int mx2_camera_clock_start(struct soc_camera_host *ici)
-{
-	struct mx2_camera_dev *pcdev = ici->priv;
-	int ret;
-	u32 csicr1;
-
-	ret = clk_prepare_enable(pcdev->clk_csi_ahb);
-	if (ret < 0)
-		return ret;
-
-	ret = clk_prepare_enable(pcdev->clk_csi_per);
-	if (ret < 0)
-		goto exit_csi_ahb;
-
-	csicr1 = CSICR1_MCLKEN | CSICR1_PRP_IF_EN | CSICR1_FCC |
-		CSICR1_RXFF_LEVEL(0);
-
-	pcdev->csicr1 = csicr1;
-	writel(pcdev->csicr1, pcdev->base_csi + CSICR1);
-
-	pcdev->frame_count = 0;
-
-	return 0;
-
-exit_csi_ahb:
-	clk_disable_unprepare(pcdev->clk_csi_ahb);
-
-	return ret;
-}
-
-static void mx2_camera_clock_stop(struct soc_camera_host *ici)
-{
-	struct mx2_camera_dev *pcdev = ici->priv;
-
-	mx2_camera_deactivate(pcdev);
-}
-
-/*
- *  Videobuf operations
- */
-static int mx2_videobuf_setup(struct vb2_queue *vq,
-			unsigned int *count, unsigned int *num_planes,
-			unsigned int sizes[], void *alloc_ctxs[])
-{
-	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-
-	dev_dbg(icd->parent, "count=%d, size=%d\n", *count, sizes[0]);
-
-	alloc_ctxs[0] = pcdev->alloc_ctx;
-
-	sizes[0] = icd->sizeimage;
-
-	if (0 == *count)
-		*count = 32;
-	if (!*num_planes &&
-	    sizes[0] * *count > MAX_VIDEO_MEM * 1024 * 1024)
-		*count = (MAX_VIDEO_MEM * 1024 * 1024) / sizes[0];
-
-	*num_planes = 1;
-
-	return 0;
-}
-
-static int mx2_videobuf_prepare(struct vb2_buffer *vb)
-{
-	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
-	int ret = 0;
-
-	dev_dbg(icd->parent, "%s (vb=0x%p) 0x%p %lu\n", __func__,
-		vb, vb2_plane_vaddr(vb, 0), vb2_get_plane_payload(vb, 0));
-
-#ifdef DEBUG
-	/*
-	 * This can be useful if you want to see if we actually fill
-	 * the buffer with something
-	 */
-	memset((void *)vb2_plane_vaddr(vb, 0),
-	       0xaa, vb2_get_plane_payload(vb, 0));
-#endif
-
-	vb2_set_plane_payload(vb, 0, icd->sizeimage);
-	if (vb2_plane_vaddr(vb, 0) &&
-	    vb2_get_plane_payload(vb, 0) > vb2_plane_size(vb, 0)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	return 0;
-
-out:
-	return ret;
-}
-
-static void mx2_videobuf_queue(struct vb2_buffer *vb)
-{
-	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
-	struct soc_camera_host *ici =
-		to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-	struct mx2_buffer *buf = container_of(vbuf, struct mx2_buffer, vb);
-	unsigned long flags;
-
-	dev_dbg(icd->parent, "%s (vb=0x%p) 0x%p %lu\n", __func__,
-		vb, vb2_plane_vaddr(vb, 0), vb2_get_plane_payload(vb, 0));
-
-	spin_lock_irqsave(&pcdev->lock, flags);
-
-	list_add_tail(&buf->internal.queue, &pcdev->capture);
-
-	spin_unlock_irqrestore(&pcdev->lock, flags);
-}
-
-static void mx27_camera_emma_buf_init(struct soc_camera_device *icd,
-		int bytesperline)
-{
-	struct soc_camera_host *ici =
-		to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-	struct mx2_fmt_cfg *prp = pcdev->emma_prp;
-
-	writel((pcdev->s_width << 16) | pcdev->s_height,
-	       pcdev->base_emma + PRP_SRC_FRAME_SIZE);
-	writel(prp->cfg.src_pixel,
-	       pcdev->base_emma + PRP_SRC_PIXEL_FORMAT_CNTL);
-	if (prp->cfg.channel == 1) {
-		writel((icd->user_width << 16) | icd->user_height,
-			pcdev->base_emma + PRP_CH1_OUT_IMAGE_SIZE);
-		writel(bytesperline,
-			pcdev->base_emma + PRP_DEST_CH1_LINE_STRIDE);
-		writel(prp->cfg.ch1_pixel,
-			pcdev->base_emma + PRP_CH1_PIXEL_FORMAT_CNTL);
-	} else { /* channel 2 */
-		writel((icd->user_width << 16) | icd->user_height,
-			pcdev->base_emma + PRP_CH2_OUT_IMAGE_SIZE);
-	}
-
-	/* Enable interrupts */
-	writel(prp->cfg.irq_flags, pcdev->base_emma + PRP_INTR_CNTL);
-}
-
-static void mx2_prp_resize_commit(struct mx2_camera_dev *pcdev)
-{
-	int dir;
-
-	for (dir = RESIZE_DIR_H; dir <= RESIZE_DIR_V; dir++) {
-		unsigned char *s = pcdev->resizing[dir].s;
-		int len = pcdev->resizing[dir].len;
-		unsigned int coeff[2] = {0, 0};
-		unsigned int valid  = 0;
-		int i;
-
-		if (len == 0)
-			continue;
-
-		for (i = RESIZE_NUM_MAX - 1; i >= 0; i--) {
-			int j;
-
-			j = i > 9 ? 1 : 0;
-			coeff[j] = (coeff[j] << BC_COEF) |
-					(s[i] & (SZ_COEF - 1));
-
-			if (i == 5 || i == 15)
-				coeff[j] <<= 1;
-
-			valid = (valid << 1) | (s[i] >> BC_COEF);
-		}
-
-		valid |= PRP_RZ_VALID_TBL_LEN(len);
-
-		if (pcdev->resizing[dir].algo == RESIZE_ALGO_BILINEAR)
-			valid |= PRP_RZ_VALID_BILINEAR;
-
-		if (pcdev->emma_prp->cfg.channel == 1) {
-			if (dir == RESIZE_DIR_H) {
-				writel(coeff[0], pcdev->base_emma +
-							PRP_CH1_RZ_HORI_COEF1);
-				writel(coeff[1], pcdev->base_emma +
-							PRP_CH1_RZ_HORI_COEF2);
-				writel(valid, pcdev->base_emma +
-							PRP_CH1_RZ_HORI_VALID);
-			} else {
-				writel(coeff[0], pcdev->base_emma +
-							PRP_CH1_RZ_VERT_COEF1);
-				writel(coeff[1], pcdev->base_emma +
-							PRP_CH1_RZ_VERT_COEF2);
-				writel(valid, pcdev->base_emma +
-							PRP_CH1_RZ_VERT_VALID);
-			}
-		} else {
-			if (dir == RESIZE_DIR_H) {
-				writel(coeff[0], pcdev->base_emma +
-							PRP_CH2_RZ_HORI_COEF1);
-				writel(coeff[1], pcdev->base_emma +
-							PRP_CH2_RZ_HORI_COEF2);
-				writel(valid, pcdev->base_emma +
-							PRP_CH2_RZ_HORI_VALID);
-			} else {
-				writel(coeff[0], pcdev->base_emma +
-							PRP_CH2_RZ_VERT_COEF1);
-				writel(coeff[1], pcdev->base_emma +
-							PRP_CH2_RZ_VERT_COEF2);
-				writel(valid, pcdev->base_emma +
-							PRP_CH2_RZ_VERT_VALID);
-			}
-		}
-	}
-}
-
-static int mx2_start_streaming(struct vb2_queue *q, unsigned int count)
-{
-	struct soc_camera_device *icd = soc_camera_from_vb2q(q);
-	struct soc_camera_host *ici =
-		to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-	struct mx2_fmt_cfg *prp = pcdev->emma_prp;
-	struct vb2_buffer *vb;
-	struct mx2_buffer *buf;
-	unsigned long phys;
-	int bytesperline;
-	unsigned long flags;
-
-	if (count < 2)
-		return -ENOBUFS;
-
-	spin_lock_irqsave(&pcdev->lock, flags);
-
-	buf = list_first_entry(&pcdev->capture, struct mx2_buffer,
-			       internal.queue);
-	buf->internal.bufnum = 0;
-	vb = &buf->vb.vb2_buf;
-
-	phys = vb2_dma_contig_plane_dma_addr(vb, 0);
-	mx27_update_emma_buf(pcdev, phys, buf->internal.bufnum);
-	list_move_tail(pcdev->capture.next, &pcdev->active_bufs);
-
-	buf = list_first_entry(&pcdev->capture, struct mx2_buffer,
-			       internal.queue);
-	buf->internal.bufnum = 1;
-	vb = &buf->vb.vb2_buf;
-
-	phys = vb2_dma_contig_plane_dma_addr(vb, 0);
-	mx27_update_emma_buf(pcdev, phys, buf->internal.bufnum);
-	list_move_tail(pcdev->capture.next, &pcdev->active_bufs);
-
-	bytesperline = soc_mbus_bytes_per_line(icd->user_width,
-					       icd->current_fmt->host_fmt);
-	if (bytesperline < 0) {
-		spin_unlock_irqrestore(&pcdev->lock, flags);
-		return bytesperline;
-	}
-
-	/*
-	 * I didn't manage to properly enable/disable the prp
-	 * on a per frame basis during running transfers,
-	 * thus we allocate a buffer here and use it to
-	 * discard frames when no buffer is available.
-	 * Feel free to work on this ;)
-	 */
-	pcdev->discard_size = icd->user_height * bytesperline;
-	pcdev->discard_buffer = dma_alloc_coherent(ici->v4l2_dev.dev,
-					pcdev->discard_size,
-					&pcdev->discard_buffer_dma, GFP_ATOMIC);
-	if (!pcdev->discard_buffer) {
-		spin_unlock_irqrestore(&pcdev->lock, flags);
-		return -ENOMEM;
-	}
-
-	pcdev->buf_discard[0].discard = true;
-	list_add_tail(&pcdev->buf_discard[0].queue,
-		      &pcdev->discard);
-
-	pcdev->buf_discard[1].discard = true;
-	list_add_tail(&pcdev->buf_discard[1].queue,
-		      &pcdev->discard);
-
-	mx2_prp_resize_commit(pcdev);
-
-	mx27_camera_emma_buf_init(icd, bytesperline);
-
-	if (prp->cfg.channel == 1) {
-		writel(PRP_CNTL_CH1EN |
-		       PRP_CNTL_CSIEN |
-		       prp->cfg.in_fmt |
-		       prp->cfg.out_fmt |
-		       PRP_CNTL_CH1_LEN |
-		       PRP_CNTL_CH1BYP |
-		       PRP_CNTL_CH1_TSKIP(0) |
-		       PRP_CNTL_IN_TSKIP(0),
-		       pcdev->base_emma + PRP_CNTL);
-	} else {
-		writel(PRP_CNTL_CH2EN |
-		       PRP_CNTL_CSIEN |
-		       prp->cfg.in_fmt |
-		       prp->cfg.out_fmt |
-		       PRP_CNTL_CH2_LEN |
-		       PRP_CNTL_CH2_TSKIP(0) |
-		       PRP_CNTL_IN_TSKIP(0),
-		       pcdev->base_emma + PRP_CNTL);
-	}
-	spin_unlock_irqrestore(&pcdev->lock, flags);
-
-	return 0;
-}
-
-static void mx2_stop_streaming(struct vb2_queue *q)
-{
-	struct soc_camera_device *icd = soc_camera_from_vb2q(q);
-	struct soc_camera_host *ici =
-		to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-	struct mx2_fmt_cfg *prp = pcdev->emma_prp;
-	unsigned long flags;
-	void *b;
-	u32 cntl;
-
-	spin_lock_irqsave(&pcdev->lock, flags);
-
-	cntl = readl(pcdev->base_emma + PRP_CNTL);
-	if (prp->cfg.channel == 1) {
-		writel(cntl & ~PRP_CNTL_CH1EN,
-		       pcdev->base_emma + PRP_CNTL);
-	} else {
-		writel(cntl & ~PRP_CNTL_CH2EN,
-		       pcdev->base_emma + PRP_CNTL);
-	}
-	INIT_LIST_HEAD(&pcdev->capture);
-	INIT_LIST_HEAD(&pcdev->active_bufs);
-	INIT_LIST_HEAD(&pcdev->discard);
-
-	b = pcdev->discard_buffer;
-	pcdev->discard_buffer = NULL;
-
-	spin_unlock_irqrestore(&pcdev->lock, flags);
-
-	dma_free_coherent(ici->v4l2_dev.dev,
-			  pcdev->discard_size, b, pcdev->discard_buffer_dma);
-}
-
-static struct vb2_ops mx2_videobuf_ops = {
-	.queue_setup	 = mx2_videobuf_setup,
-	.buf_prepare	 = mx2_videobuf_prepare,
-	.buf_queue	 = mx2_videobuf_queue,
-	.start_streaming = mx2_start_streaming,
-	.stop_streaming	 = mx2_stop_streaming,
-};
-
-static int mx2_camera_init_videobuf(struct vb2_queue *q,
-			      struct soc_camera_device *icd)
-{
-	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	q->io_modes = VB2_MMAP | VB2_USERPTR;
-	q->drv_priv = icd;
-	q->ops = &mx2_videobuf_ops;
-	q->mem_ops = &vb2_dma_contig_memops;
-	q->buf_struct_size = sizeof(struct mx2_buffer);
-	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-
-	return vb2_queue_init(q);
-}
-
-#define MX2_BUS_FLAGS	(V4L2_MBUS_MASTER | \
-			V4L2_MBUS_VSYNC_ACTIVE_HIGH | \
-			V4L2_MBUS_VSYNC_ACTIVE_LOW | \
-			V4L2_MBUS_HSYNC_ACTIVE_HIGH | \
-			V4L2_MBUS_HSYNC_ACTIVE_LOW | \
-			V4L2_MBUS_PCLK_SAMPLE_RISING | \
-			V4L2_MBUS_PCLK_SAMPLE_FALLING | \
-			V4L2_MBUS_DATA_ACTIVE_HIGH | \
-			V4L2_MBUS_DATA_ACTIVE_LOW)
-
-static int mx27_camera_emma_prp_reset(struct mx2_camera_dev *pcdev)
-{
-	int count = 0;
-
-	readl(pcdev->base_emma + PRP_CNTL);
-	writel(PRP_CNTL_SWRST, pcdev->base_emma + PRP_CNTL);
-	while (count++ < 100) {
-		if (!(readl(pcdev->base_emma + PRP_CNTL) & PRP_CNTL_SWRST))
-			return 0;
-		barrier();
-		udelay(1);
-	}
-
-	return -ETIMEDOUT;
-}
-
-static int mx2_camera_set_bus_param(struct soc_camera_device *icd)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-	struct v4l2_mbus_config cfg = {.type = V4L2_MBUS_PARALLEL,};
-	unsigned long common_flags;
-	int ret;
-	int bytesperline;
-	u32 csicr1 = pcdev->csicr1;
-
-	ret = v4l2_subdev_call(sd, video, g_mbus_config, &cfg);
-	if (!ret) {
-		common_flags = soc_mbus_config_compatible(&cfg, MX2_BUS_FLAGS);
-		if (!common_flags) {
-			dev_warn(icd->parent,
-				 "Flags incompatible: camera 0x%x, host 0x%x\n",
-				 cfg.flags, MX2_BUS_FLAGS);
-			return -EINVAL;
-		}
-	} else if (ret != -ENOIOCTLCMD) {
-		return ret;
-	} else {
-		common_flags = MX2_BUS_FLAGS;
-	}
-
-	if ((common_flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH) &&
-	    (common_flags & V4L2_MBUS_HSYNC_ACTIVE_LOW)) {
-		if (pcdev->platform_flags & MX2_CAMERA_HSYNC_HIGH)
-			common_flags &= ~V4L2_MBUS_HSYNC_ACTIVE_LOW;
-		else
-			common_flags &= ~V4L2_MBUS_HSYNC_ACTIVE_HIGH;
-	}
-
-	if ((common_flags & V4L2_MBUS_PCLK_SAMPLE_RISING) &&
-	    (common_flags & V4L2_MBUS_PCLK_SAMPLE_FALLING)) {
-		if (pcdev->platform_flags & MX2_CAMERA_PCLK_SAMPLE_RISING)
-			common_flags &= ~V4L2_MBUS_PCLK_SAMPLE_FALLING;
-		else
-			common_flags &= ~V4L2_MBUS_PCLK_SAMPLE_RISING;
-	}
-
-	cfg.flags = common_flags;
-	ret = v4l2_subdev_call(sd, video, s_mbus_config, &cfg);
-	if (ret < 0 && ret != -ENOIOCTLCMD) {
-		dev_dbg(icd->parent, "camera s_mbus_config(0x%lx) returned %d\n",
-			common_flags, ret);
-		return ret;
-	}
-
-	csicr1 = (csicr1 & ~CSICR1_FMT_MASK) | pcdev->emma_prp->cfg.csicr1;
-
-	if (common_flags & V4L2_MBUS_PCLK_SAMPLE_RISING)
-		csicr1 |= CSICR1_REDGE;
-	if (common_flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH)
-		csicr1 |= CSICR1_SOF_POL;
-	if (common_flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH)
-		csicr1 |= CSICR1_HSYNC_POL;
-	if (pcdev->platform_flags & MX2_CAMERA_EXT_VSYNC)
-		csicr1 |= CSICR1_EXT_VSYNC;
-	if (pcdev->platform_flags & MX2_CAMERA_CCIR)
-		csicr1 |= CSICR1_CCIR_EN;
-	if (pcdev->platform_flags & MX2_CAMERA_CCIR_INTERLACE)
-		csicr1 |= CSICR1_CCIR_MODE;
-	if (pcdev->platform_flags & MX2_CAMERA_GATED_CLOCK)
-		csicr1 |= CSICR1_GCLK_MODE;
-	if (pcdev->platform_flags & MX2_CAMERA_INV_DATA)
-		csicr1 |= CSICR1_INV_DATA;
-
-	pcdev->csicr1 = csicr1;
-
-	bytesperline = soc_mbus_bytes_per_line(icd->user_width,
-			icd->current_fmt->host_fmt);
-	if (bytesperline < 0)
-		return bytesperline;
-
-	ret = mx27_camera_emma_prp_reset(pcdev);
-	if (ret)
-		return ret;
-
-	writel(pcdev->csicr1, pcdev->base_csi + CSICR1);
-
-	return 0;
-}
-
-static int mx2_camera_set_crop(struct soc_camera_device *icd,
-				const struct v4l2_crop *a)
-{
-	struct v4l2_crop a_writable = *a;
-	struct v4l2_rect *rect = &a_writable.c;
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct v4l2_subdev_format fmt = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-	};
-	struct v4l2_mbus_framefmt *mf = &fmt.format;
-	int ret;
-
-	soc_camera_limit_side(&rect->left, &rect->width, 0, 2, 4096);
-	soc_camera_limit_side(&rect->top, &rect->height, 0, 2, 4096);
-
-	ret = v4l2_subdev_call(sd, video, s_crop, a);
-	if (ret < 0)
-		return ret;
-
-	/* The capture device might have changed its output  */
-	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt);
-	if (ret < 0)
-		return ret;
-
-	dev_dbg(icd->parent, "Sensor cropped %dx%d\n",
-		mf->width, mf->height);
-
-	icd->user_width		= mf->width;
-	icd->user_height	= mf->height;
-
-	return ret;
-}
-
-static int mx2_camera_get_formats(struct soc_camera_device *icd,
-				  unsigned int idx,
-				  struct soc_camera_format_xlate *xlate)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	const struct soc_mbus_pixelfmt *fmt;
-	struct device *dev = icd->parent;
-	struct v4l2_subdev_mbus_code_enum code = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-		.index = idx,
-	};
-	int ret, formats = 0;
-
-	ret = v4l2_subdev_call(sd, pad, enum_mbus_code, NULL, &code);
-	if (ret < 0)
-		/* no more formats */
-		return 0;
-
-	fmt = soc_mbus_get_fmtdesc(code.code);
-	if (!fmt) {
-		dev_err(dev, "Invalid format code #%u: %d\n", idx, code.code);
-		return 0;
-	}
-
-	if (code.code == MEDIA_BUS_FMT_YUYV8_2X8 ||
-	    code.code == MEDIA_BUS_FMT_UYVY8_2X8) {
-		formats++;
-		if (xlate) {
-			/*
-			 * CH2 can output YUV420 which is a standard format in
-			 * soc_mediabus.c
-			 */
-			xlate->host_fmt =
-				soc_mbus_get_fmtdesc(MEDIA_BUS_FMT_YUYV8_1_5X8);
-			xlate->code	= code.code;
-			dev_dbg(dev, "Providing host format %s for sensor code %d\n",
-			       xlate->host_fmt->name, code.code);
-			xlate++;
-		}
-	}
-
-	if (code.code == MEDIA_BUS_FMT_UYVY8_2X8) {
-		formats++;
-		if (xlate) {
-			xlate->host_fmt =
-				soc_mbus_get_fmtdesc(MEDIA_BUS_FMT_YUYV8_2X8);
-			xlate->code	= code.code;
-			dev_dbg(dev, "Providing host format %s for sensor code %d\n",
-				xlate->host_fmt->name, code.code);
-			xlate++;
-		}
-	}
-
-	/* Generic pass-trough */
-	formats++;
-	if (xlate) {
-		xlate->host_fmt = fmt;
-		xlate->code	= code.code;
-		xlate++;
-	}
-	return formats;
-}
-
-static int mx2_emmaprp_resize(struct mx2_camera_dev *pcdev,
-			      struct v4l2_mbus_framefmt *mf_in,
-			      struct v4l2_pix_format *pix_out, bool apply)
-{
-	unsigned int num, den;
-	unsigned long m;
-	int i, dir;
-
-	for (dir = RESIZE_DIR_H; dir <= RESIZE_DIR_V; dir++) {
-		struct emma_prp_resize tmprsz;
-		unsigned char *s = tmprsz.s;
-		int len = 0;
-		int in, out;
-
-		if (dir == RESIZE_DIR_H) {
-			in = mf_in->width;
-			out = pix_out->width;
-		} else {
-			in = mf_in->height;
-			out = pix_out->height;
-		}
-
-		if (in < out)
-			return -EINVAL;
-		else if (in == out)
-			continue;
-
-		/* Calculate ratio */
-		m = gcd(in, out);
-		num = in / m;
-		den = out / m;
-		if (num > RESIZE_NUM_MAX)
-			return -EINVAL;
-
-		if ((num >= 2 * den) && (den == 1) &&
-		    (num < 9) && (!(num & 0x01))) {
-			int sum = 0;
-			int j;
-
-			/* Average scaling for >= 2:1 ratios */
-			/* Support can be added for num >=9 and odd values */
-
-			tmprsz.algo = RESIZE_ALGO_AVERAGING;
-			len = num;
-
-			for (i = 0; i < (len / 2); i++)
-				s[i] = 8;
-
-			do {
-				for (i = 0; i < (len / 2); i++) {
-					s[i] = s[i] >> 1;
-					sum = 0;
-					for (j = 0; j < (len / 2); j++)
-						sum += s[j];
-					if (sum == 4)
-						break;
-				}
-			} while (sum != 4);
-
-			for (i = (len / 2); i < len; i++)
-				s[i] = s[len - i - 1];
-
-			s[len - 1] |= SZ_COEF;
-		} else {
-			/* bilinear scaling for < 2:1 ratios */
-			int v; /* overflow counter */
-			int coeff, nxt; /* table output */
-			int in_pos_inc = 2 * den;
-			int out_pos = num;
-			int out_pos_inc = 2 * num;
-			int init_carry = num - den;
-			int carry = init_carry;
-
-			tmprsz.algo = RESIZE_ALGO_BILINEAR;
-			v = den + in_pos_inc;
-			do {
-				coeff = v - out_pos;
-				out_pos += out_pos_inc;
-				carry += out_pos_inc;
-				for (nxt = 0; v < out_pos; nxt++) {
-					v += in_pos_inc;
-					carry -= in_pos_inc;
-				}
-
-				if (len > RESIZE_NUM_MAX)
-					return -EINVAL;
-
-				coeff = ((coeff << BC_COEF) +
-					(in_pos_inc >> 1)) / in_pos_inc;
-
-				if (coeff >= (SZ_COEF - 1))
-					coeff--;
-
-				coeff |= SZ_COEF;
-				s[len] = (unsigned char)coeff;
-				len++;
-
-				for (i = 1; i < nxt; i++) {
-					if (len >= RESIZE_NUM_MAX)
-						return -EINVAL;
-					s[len] = 0;
-					len++;
-				}
-			} while (carry != init_carry);
-		}
-		tmprsz.len = len;
-		if (dir == RESIZE_DIR_H)
-			mf_in->width = pix_out->width;
-		else
-			mf_in->height = pix_out->height;
-
-		if (apply)
-			memcpy(&pcdev->resizing[dir], &tmprsz, sizeof(tmprsz));
-	}
-	return 0;
-}
-
-static int mx2_camera_set_fmt(struct soc_camera_device *icd,
-			       struct v4l2_format *f)
-{
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	const struct soc_camera_format_xlate *xlate;
-	struct v4l2_pix_format *pix = &f->fmt.pix;
-	struct v4l2_subdev_format format = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-	};
-	struct v4l2_mbus_framefmt *mf = &format.format;
-	int ret;
-
-	dev_dbg(icd->parent, "%s: requested params: width = %d, height = %d\n",
-		__func__, pix->width, pix->height);
-
-	xlate = soc_camera_xlate_by_fourcc(icd, pix->pixelformat);
-	if (!xlate) {
-		dev_warn(icd->parent, "Format %x not found\n",
-				pix->pixelformat);
-		return -EINVAL;
-	}
-
-	mf->width	= pix->width;
-	mf->height	= pix->height;
-	mf->field	= pix->field;
-	mf->colorspace	= pix->colorspace;
-	mf->code	= xlate->code;
-
-	ret = v4l2_subdev_call(sd, pad, set_fmt, NULL, &format);
-	if (ret < 0 && ret != -ENOIOCTLCMD)
-		return ret;
-
-	/* Store width and height returned by the sensor for resizing */
-	pcdev->s_width = mf->width;
-	pcdev->s_height = mf->height;
-	dev_dbg(icd->parent, "%s: sensor params: width = %d, height = %d\n",
-		__func__, pcdev->s_width, pcdev->s_height);
-
-	pcdev->emma_prp = mx27_emma_prp_get_format(xlate->code,
-						   xlate->host_fmt->fourcc);
-
-	memset(pcdev->resizing, 0, sizeof(pcdev->resizing));
-	if ((mf->width != pix->width || mf->height != pix->height) &&
-		pcdev->emma_prp->cfg.in_fmt == PRP_CNTL_DATA_IN_YUV422) {
-		if (mx2_emmaprp_resize(pcdev, mf, pix, true) < 0)
-			dev_dbg(icd->parent, "%s: can't resize\n", __func__);
-	}
-
-	if (mf->code != xlate->code)
-		return -EINVAL;
-
-	pix->width		= mf->width;
-	pix->height		= mf->height;
-	pix->field		= mf->field;
-	pix->colorspace		= mf->colorspace;
-	icd->current_fmt	= xlate;
-
-	dev_dbg(icd->parent, "%s: returned params: width = %d, height = %d\n",
-		__func__, pix->width, pix->height);
-
-	return 0;
-}
-
-static int mx2_camera_try_fmt(struct soc_camera_device *icd,
-				  struct v4l2_format *f)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	const struct soc_camera_format_xlate *xlate;
-	struct v4l2_pix_format *pix = &f->fmt.pix;
-	struct v4l2_subdev_pad_config pad_cfg;
-	struct v4l2_subdev_format format = {
-		.which = V4L2_SUBDEV_FORMAT_TRY,
-	};
-	struct v4l2_mbus_framefmt *mf = &format.format;
-	__u32 pixfmt = pix->pixelformat;
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx2_camera_dev *pcdev = ici->priv;
-	struct mx2_fmt_cfg *emma_prp;
-	int ret;
-
-	dev_dbg(icd->parent, "%s: requested params: width = %d, height = %d\n",
-		__func__, pix->width, pix->height);
-
-	xlate = soc_camera_xlate_by_fourcc(icd, pixfmt);
-	if (pixfmt && !xlate) {
-		dev_warn(icd->parent, "Format %x not found\n", pixfmt);
-		return -EINVAL;
-	}
-
-	/*
-	 * limit to MX27 hardware capabilities: width must be a multiple of 8 as
-	 * requested by the CSI. (Table 39-2 in the i.MX27 Reference Manual).
-	 */
-	pix->width &= ~0x7;
-
-	/* limit to sensor capabilities */
-	mf->width	= pix->width;
-	mf->height	= pix->height;
-	mf->field	= pix->field;
-	mf->colorspace	= pix->colorspace;
-	mf->code	= xlate->code;
-
-	ret = v4l2_subdev_call(sd, pad, set_fmt, &pad_cfg, &format);
-	if (ret < 0)
-		return ret;
-
-	dev_dbg(icd->parent, "%s: sensor params: width = %d, height = %d\n",
-		__func__, pcdev->s_width, pcdev->s_height);
-
-	/* If the sensor does not support image size try PrP resizing */
-	emma_prp = mx27_emma_prp_get_format(xlate->code,
-					    xlate->host_fmt->fourcc);
-
-	if ((mf->width != pix->width || mf->height != pix->height) &&
-		emma_prp->cfg.in_fmt == PRP_CNTL_DATA_IN_YUV422) {
-		if (mx2_emmaprp_resize(pcdev, mf, pix, false) < 0)
-			dev_dbg(icd->parent, "%s: can't resize\n", __func__);
-	}
-
-	if (mf->field == V4L2_FIELD_ANY)
-		mf->field = V4L2_FIELD_NONE;
-	/*
-	 * Driver supports interlaced images provided they have
-	 * both fields so that they can be processed as if they
-	 * were progressive.
-	 */
-	if (mf->field != V4L2_FIELD_NONE && !V4L2_FIELD_HAS_BOTH(mf->field)) {
-		dev_err(icd->parent, "Field type %d unsupported.\n",
-				mf->field);
-		return -EINVAL;
-	}
-
-	pix->width	= mf->width;
-	pix->height	= mf->height;
-	pix->field	= mf->field;
-	pix->colorspace	= mf->colorspace;
-
-	dev_dbg(icd->parent, "%s: returned params: width = %d, height = %d\n",
-		__func__, pix->width, pix->height);
-
-	return 0;
-}
-
-static int mx2_camera_querycap(struct soc_camera_host *ici,
-			       struct v4l2_capability *cap)
-{
-	/* cap->name is set by the friendly caller:-> */
-	strlcpy(cap->card, MX2_CAM_DRIVER_DESCRIPTION, sizeof(cap->card));
-	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING;
-	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
-
-	return 0;
-}
-
-static unsigned int mx2_camera_poll(struct file *file, poll_table *pt)
-{
-	struct soc_camera_device *icd = file->private_data;
-
-	return vb2_poll(&icd->vb2_vidq, file, pt);
-}
-
-static struct soc_camera_host_ops mx2_soc_camera_host_ops = {
-	.owner		= THIS_MODULE,
-	.add		= mx2_camera_add_device,
-	.remove		= mx2_camera_remove_device,
-	.clock_start	= mx2_camera_clock_start,
-	.clock_stop	= mx2_camera_clock_stop,
-	.set_fmt	= mx2_camera_set_fmt,
-	.set_crop	= mx2_camera_set_crop,
-	.get_formats	= mx2_camera_get_formats,
-	.try_fmt	= mx2_camera_try_fmt,
-	.init_videobuf2	= mx2_camera_init_videobuf,
-	.poll		= mx2_camera_poll,
-	.querycap	= mx2_camera_querycap,
-	.set_bus_param	= mx2_camera_set_bus_param,
-};
-
-static void mx27_camera_frame_done_emma(struct mx2_camera_dev *pcdev,
-		int bufnum, bool err)
-{
-#ifdef DEBUG
-	struct mx2_fmt_cfg *prp = pcdev->emma_prp;
-#endif
-	struct mx2_buf_internal *ibuf;
-	struct mx2_buffer *buf;
-	struct vb2_buffer *vb;
-	struct vb2_v4l2_buffer *vbuf;
-	unsigned long phys;
-
-	ibuf = list_first_entry(&pcdev->active_bufs, struct mx2_buf_internal,
-			       queue);
-
-	BUG_ON(ibuf->bufnum != bufnum);
-
-	if (ibuf->discard) {
-		/*
-		 * Discard buffer must not be returned to user space.
-		 * Just return it to the discard queue.
-		 */
-		list_move_tail(pcdev->active_bufs.next, &pcdev->discard);
-	} else {
-		buf = mx2_ibuf_to_buf(ibuf);
-
-		vb = &buf->vb.vb2_buf;
-		vbuf = to_vb2_v4l2_buffer(vb);
-#ifdef DEBUG
-		phys = vb2_dma_contig_plane_dma_addr(vb, 0);
-		if (prp->cfg.channel == 1) {
-			if (readl(pcdev->base_emma + PRP_DEST_RGB1_PTR +
-				4 * bufnum) != phys) {
-				dev_err(pcdev->dev, "%lx != %x\n", phys,
-					readl(pcdev->base_emma +
-					PRP_DEST_RGB1_PTR + 4 * bufnum));
-			}
-		} else {
-			if (readl(pcdev->base_emma + PRP_DEST_Y_PTR -
-				0x14 * bufnum) != phys) {
-				dev_err(pcdev->dev, "%lx != %x\n", phys,
-					readl(pcdev->base_emma +
-					PRP_DEST_Y_PTR - 0x14 * bufnum));
-			}
-		}
-#endif
-		dev_dbg(pcdev->dev, "%s (vb=0x%p) 0x%p %lu\n", __func__, vb,
-				vb2_plane_vaddr(vb, 0),
-				vb2_get_plane_payload(vb, 0));
-
-		list_del_init(&buf->internal.queue);
-		vb->timestamp = ktime_get_ns();
-		vbuf->sequence = pcdev->frame_count;
-		if (err)
-			vb2_buffer_done(vb, VB2_BUF_STATE_ERROR);
-		else
-			vb2_buffer_done(vb, VB2_BUF_STATE_DONE);
-	}
-
-	pcdev->frame_count++;
-
-	if (list_empty(&pcdev->capture)) {
-		if (list_empty(&pcdev->discard)) {
-			dev_warn(pcdev->dev, "%s: trying to access empty discard list\n",
-				 __func__);
-			return;
-		}
-
-		ibuf = list_first_entry(&pcdev->discard,
-					struct mx2_buf_internal, queue);
-		ibuf->bufnum = bufnum;
-
-		list_move_tail(pcdev->discard.next, &pcdev->active_bufs);
-		mx27_update_emma_buf(pcdev, pcdev->discard_buffer_dma, bufnum);
-		return;
-	}
-
-	buf = list_first_entry(&pcdev->capture, struct mx2_buffer,
-			       internal.queue);
-
-	buf->internal.bufnum = bufnum;
-
-	list_move_tail(pcdev->capture.next, &pcdev->active_bufs);
-
-	vb = &buf->vb.vb2_buf;
-
-	phys = vb2_dma_contig_plane_dma_addr(vb, 0);
-	mx27_update_emma_buf(pcdev, phys, bufnum);
-}
-
-static irqreturn_t mx27_camera_emma_irq(int irq_emma, void *data)
-{
-	struct mx2_camera_dev *pcdev = data;
-	unsigned int status = readl(pcdev->base_emma + PRP_INTRSTATUS);
-	struct mx2_buf_internal *ibuf;
-
-	spin_lock(&pcdev->lock);
-
-	if (list_empty(&pcdev->active_bufs)) {
-		dev_warn(pcdev->dev, "%s: called while active list is empty\n",
-			__func__);
-
-		if (!status) {
-			spin_unlock(&pcdev->lock);
-			return IRQ_NONE;
-		}
-	}
-
-	if (status & (1 << 7)) { /* overflow */
-		u32 cntl = readl(pcdev->base_emma + PRP_CNTL);
-		writel(cntl & ~(PRP_CNTL_CH1EN | PRP_CNTL_CH2EN),
-		       pcdev->base_emma + PRP_CNTL);
-		writel(cntl, pcdev->base_emma + PRP_CNTL);
-
-		ibuf = list_first_entry(&pcdev->active_bufs,
-					struct mx2_buf_internal, queue);
-		mx27_camera_frame_done_emma(pcdev,
-					ibuf->bufnum, true);
-
-		status &= ~(1 << 7);
-	} else if (((status & (3 << 5)) == (3 << 5)) ||
-		((status & (3 << 3)) == (3 << 3))) {
-		/*
-		 * Both buffers have triggered, process the one we're expecting
-		 * to first
-		 */
-		ibuf = list_first_entry(&pcdev->active_bufs,
-					struct mx2_buf_internal, queue);
-		mx27_camera_frame_done_emma(pcdev, ibuf->bufnum, false);
-		status &= ~(1 << (6 - ibuf->bufnum)); /* mark processed */
-	} else if ((status & (1 << 6)) || (status & (1 << 4))) {
-		mx27_camera_frame_done_emma(pcdev, 0, false);
-	} else if ((status & (1 << 5)) || (status & (1 << 3))) {
-		mx27_camera_frame_done_emma(pcdev, 1, false);
-	}
-
-	spin_unlock(&pcdev->lock);
-	writel(status, pcdev->base_emma + PRP_INTRSTATUS);
-
-	return IRQ_HANDLED;
-}
-
-static int mx27_camera_emma_init(struct platform_device *pdev)
-{
-	struct mx2_camera_dev *pcdev = platform_get_drvdata(pdev);
-	struct resource *res_emma;
-	int irq_emma;
-	int err = 0;
-
-	res_emma = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	irq_emma = platform_get_irq(pdev, 1);
-	if (!res_emma || !irq_emma) {
-		dev_err(pcdev->dev, "no EMMA resources\n");
-		err = -ENODEV;
-		goto out;
-	}
-
-	pcdev->base_emma = devm_ioremap_resource(pcdev->dev, res_emma);
-	if (IS_ERR(pcdev->base_emma)) {
-		err = PTR_ERR(pcdev->base_emma);
-		goto out;
-	}
-
-	err = devm_request_irq(pcdev->dev, irq_emma, mx27_camera_emma_irq, 0,
-			       MX2_CAM_DRV_NAME, pcdev);
-	if (err) {
-		dev_err(pcdev->dev, "Camera EMMA interrupt register failed\n");
-		goto out;
-	}
-
-	pcdev->clk_emma_ipg = devm_clk_get(pcdev->dev, "emma-ipg");
-	if (IS_ERR(pcdev->clk_emma_ipg)) {
-		err = PTR_ERR(pcdev->clk_emma_ipg);
-		goto out;
-	}
-
-	clk_prepare_enable(pcdev->clk_emma_ipg);
-
-	pcdev->clk_emma_ahb = devm_clk_get(pcdev->dev, "emma-ahb");
-	if (IS_ERR(pcdev->clk_emma_ahb)) {
-		err = PTR_ERR(pcdev->clk_emma_ahb);
-		goto exit_clk_emma_ipg;
-	}
-
-	clk_prepare_enable(pcdev->clk_emma_ahb);
-
-	err = mx27_camera_emma_prp_reset(pcdev);
-	if (err)
-		goto exit_clk_emma_ahb;
-
-	return err;
-
-exit_clk_emma_ahb:
-	clk_disable_unprepare(pcdev->clk_emma_ahb);
-exit_clk_emma_ipg:
-	clk_disable_unprepare(pcdev->clk_emma_ipg);
-out:
-	return err;
-}
-
-static int mx2_camera_probe(struct platform_device *pdev)
-{
-	struct mx2_camera_dev *pcdev;
-	struct resource *res_csi;
-	int irq_csi;
-	int err = 0;
-
-	dev_dbg(&pdev->dev, "initialising\n");
-
-	res_csi = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	irq_csi = platform_get_irq(pdev, 0);
-	if (res_csi == NULL || irq_csi < 0) {
-		dev_err(&pdev->dev, "Missing platform resources data\n");
-		err = -ENODEV;
-		goto exit;
-	}
-
-	pcdev = devm_kzalloc(&pdev->dev, sizeof(*pcdev), GFP_KERNEL);
-	if (!pcdev) {
-		dev_err(&pdev->dev, "Could not allocate pcdev\n");
-		err = -ENOMEM;
-		goto exit;
-	}
-
-	pcdev->clk_csi_ahb = devm_clk_get(&pdev->dev, "ahb");
-	if (IS_ERR(pcdev->clk_csi_ahb)) {
-		dev_err(&pdev->dev, "Could not get csi ahb clock\n");
-		err = PTR_ERR(pcdev->clk_csi_ahb);
-		goto exit;
-	}
-
-	pcdev->clk_csi_per = devm_clk_get(&pdev->dev, "per");
-	if (IS_ERR(pcdev->clk_csi_per)) {
-		dev_err(&pdev->dev, "Could not get csi per clock\n");
-		err = PTR_ERR(pcdev->clk_csi_per);
-		goto exit;
-	}
-
-	pcdev->pdata = pdev->dev.platform_data;
-	if (pcdev->pdata) {
-		long rate;
-
-		pcdev->platform_flags = pcdev->pdata->flags;
-
-		rate = clk_round_rate(pcdev->clk_csi_per,
-						pcdev->pdata->clk * 2);
-		if (rate <= 0) {
-			err = -ENODEV;
-			goto exit;
-		}
-		err = clk_set_rate(pcdev->clk_csi_per, rate);
-		if (err < 0)
-			goto exit;
-	}
-
-	INIT_LIST_HEAD(&pcdev->capture);
-	INIT_LIST_HEAD(&pcdev->active_bufs);
-	INIT_LIST_HEAD(&pcdev->discard);
-	spin_lock_init(&pcdev->lock);
-
-	pcdev->base_csi = devm_ioremap_resource(&pdev->dev, res_csi);
-	if (IS_ERR(pcdev->base_csi)) {
-		err = PTR_ERR(pcdev->base_csi);
-		goto exit;
-	}
-
-	pcdev->dev = &pdev->dev;
-	platform_set_drvdata(pdev, pcdev);
-
-	err = mx27_camera_emma_init(pdev);
-	if (err)
-		goto exit;
-
-	/*
-	 * We're done with drvdata here.  Clear the pointer so that
-	 * v4l2 core can start using drvdata on its purpose.
-	 */
-	platform_set_drvdata(pdev, NULL);
-
-	pcdev->soc_host.drv_name	= MX2_CAM_DRV_NAME,
-	pcdev->soc_host.ops		= &mx2_soc_camera_host_ops,
-	pcdev->soc_host.priv		= pcdev;
-	pcdev->soc_host.v4l2_dev.dev	= &pdev->dev;
-	pcdev->soc_host.nr		= pdev->id;
-
-	pcdev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(pcdev->alloc_ctx)) {
-		err = PTR_ERR(pcdev->alloc_ctx);
-		goto eallocctx;
-	}
-	err = soc_camera_host_register(&pcdev->soc_host);
-	if (err)
-		goto exit_free_emma;
-
-	dev_info(&pdev->dev, "MX2 Camera (CSI) driver probed, clock frequency: %ld\n",
-			clk_get_rate(pcdev->clk_csi_per));
-
-	return 0;
-
-exit_free_emma:
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
-eallocctx:
-	clk_disable_unprepare(pcdev->clk_emma_ipg);
-	clk_disable_unprepare(pcdev->clk_emma_ahb);
-exit:
-	return err;
-}
-
-static int mx2_camera_remove(struct platform_device *pdev)
-{
-	struct soc_camera_host *soc_host = to_soc_camera_host(&pdev->dev);
-	struct mx2_camera_dev *pcdev = container_of(soc_host,
-			struct mx2_camera_dev, soc_host);
-
-	soc_camera_host_unregister(&pcdev->soc_host);
-
-	vb2_dma_contig_cleanup_ctx(pcdev->alloc_ctx);
-
-	clk_disable_unprepare(pcdev->clk_emma_ipg);
-	clk_disable_unprepare(pcdev->clk_emma_ahb);
-
-	dev_info(&pdev->dev, "MX2 Camera driver unloaded\n");
-
-	return 0;
-}
-
-static struct platform_driver mx2_camera_driver = {
-	.driver		= {
-		.name	= MX2_CAM_DRV_NAME,
-	},
-	.id_table	= mx2_camera_devtype,
-	.remove		= mx2_camera_remove,
-};
-
-module_platform_driver_probe(mx2_camera_driver, mx2_camera_probe);
-
-MODULE_DESCRIPTION("i.MX27 SoC Camera Host driver");
-MODULE_AUTHOR("Sascha Hauer <sha@pengutronix.de>");
-MODULE_LICENSE("GPL");
-MODULE_VERSION(MX2_CAM_VERSION);
diff --git a/drivers/staging/media/mx3/Kconfig b/drivers/staging/media/mx3/Kconfig
deleted file mode 100644
index 595d5fe7cad1..000000000000
--- a/drivers/staging/media/mx3/Kconfig
+++ /dev/null
@@ -1,15 +0,0 @@
-config VIDEO_MX3
-	tristate "i.MX3x Camera Sensor Interface driver"
-	depends on VIDEO_DEV && MX3_IPU && SOC_CAMERA
-	depends on MX3_IPU || COMPILE_TEST
-	depends on HAS_DMA
-	select VIDEOBUF2_DMA_CONTIG
-	---help---
-	  This is a v4l2 driver for the i.MX3x Camera Sensor Interface
-
-	  This driver is deprecated: it should become a stand-alone driver
-	  instead of using the soc-camera framework.
-
-	  Unless someone is willing to take this on (unlikely with such
-	  ancient hardware) it is going to be removed from the kernel
-	  soon.
diff --git a/drivers/staging/media/mx3/Makefile b/drivers/staging/media/mx3/Makefile
deleted file mode 100644
index 6d91dcd80c1d..000000000000
--- a/drivers/staging/media/mx3/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# Makefile for i.MX3x Camera Sensor driver
-
-obj-$(CONFIG_VIDEO_MX3) += mx3_camera.o
diff --git a/drivers/staging/media/mx3/TODO b/drivers/staging/media/mx3/TODO
deleted file mode 100644
index bc68fa443a3e..000000000000
--- a/drivers/staging/media/mx3/TODO
+++ /dev/null
@@ -1,10 +0,0 @@
-This driver is deprecated: it should become a stand-alone driver instead of
-using the soc-camera framework.
-
-Unless someone is willing to take this on (unlikely with such ancient
-hardware) it is going to be removed from the kernel soon.
-
-Note that trivial patches will not be accepted anymore, only a full conversion.
-
-If you want to convert this driver, please contact the linux-media mailinglist
-(see http://linuxtv.org/lists.php).
diff --git a/drivers/staging/media/mx3/mx3_camera.c b/drivers/staging/media/mx3/mx3_camera.c
deleted file mode 100644
index aa39e9569b1a..000000000000
--- a/drivers/staging/media/mx3/mx3_camera.c
+++ /dev/null
@@ -1,1264 +0,0 @@
-/*
- * V4L2 Driver for i.MX3x camera host
- *
- * Copyright (C) 2008
- * Guennadi Liakhovetski, DENX Software Engineering, <lg@denx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/videodev2.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-#include <linux/vmalloc.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <linux/dma/ipu-dma.h>
-
-#include <media/v4l2-common.h>
-#include <media/v4l2-dev.h>
-#include <media/videobuf2-dma-contig.h>
-#include <media/soc_camera.h>
-#include <media/drv-intf/soc_mediabus.h>
-
-#include <linux/platform_data/media/camera-mx3.h>
-#include <linux/platform_data/dma-imx.h>
-
-#define MX3_CAM_DRV_NAME "mx3-camera"
-
-/* CMOS Sensor Interface Registers */
-#define CSI_REG_START		0x60
-
-#define CSI_SENS_CONF		(0x60 - CSI_REG_START)
-#define CSI_SENS_FRM_SIZE	(0x64 - CSI_REG_START)
-#define CSI_ACT_FRM_SIZE	(0x68 - CSI_REG_START)
-#define CSI_OUT_FRM_CTRL	(0x6C - CSI_REG_START)
-#define CSI_TST_CTRL		(0x70 - CSI_REG_START)
-#define CSI_CCIR_CODE_1		(0x74 - CSI_REG_START)
-#define CSI_CCIR_CODE_2		(0x78 - CSI_REG_START)
-#define CSI_CCIR_CODE_3		(0x7C - CSI_REG_START)
-#define CSI_FLASH_STROBE_1	(0x80 - CSI_REG_START)
-#define CSI_FLASH_STROBE_2	(0x84 - CSI_REG_START)
-
-#define CSI_SENS_CONF_VSYNC_POL_SHIFT		0
-#define CSI_SENS_CONF_HSYNC_POL_SHIFT		1
-#define CSI_SENS_CONF_DATA_POL_SHIFT		2
-#define CSI_SENS_CONF_PIX_CLK_POL_SHIFT		3
-#define CSI_SENS_CONF_SENS_PRTCL_SHIFT		4
-#define CSI_SENS_CONF_SENS_CLKSRC_SHIFT		7
-#define CSI_SENS_CONF_DATA_FMT_SHIFT		8
-#define CSI_SENS_CONF_DATA_WIDTH_SHIFT		10
-#define CSI_SENS_CONF_EXT_VSYNC_SHIFT		15
-#define CSI_SENS_CONF_DIVRATIO_SHIFT		16
-
-#define CSI_SENS_CONF_DATA_FMT_RGB_YUV444	(0UL << CSI_SENS_CONF_DATA_FMT_SHIFT)
-#define CSI_SENS_CONF_DATA_FMT_YUV422		(2UL << CSI_SENS_CONF_DATA_FMT_SHIFT)
-#define CSI_SENS_CONF_DATA_FMT_BAYER		(3UL << CSI_SENS_CONF_DATA_FMT_SHIFT)
-
-#define MAX_VIDEO_MEM 16
-
-struct mx3_camera_buffer {
-	/* common v4l buffer stuff -- must be first */
-	struct vb2_v4l2_buffer vb;
-	struct list_head			queue;
-
-	/* One descriptot per scatterlist (per frame) */
-	struct dma_async_tx_descriptor		*txd;
-
-	/* We have to "build" a scatterlist ourselves - one element per frame */
-	struct scatterlist			sg;
-};
-
-/**
- * struct mx3_camera_dev - i.MX3x camera (CSI) object
- * @dev:		camera device, to which the coherent buffer is attached
- * @icd:		currently attached camera sensor
- * @clk:		pointer to clock
- * @base:		remapped register base address
- * @pdata:		platform data
- * @platform_flags:	platform flags
- * @mclk:		master clock frequency in Hz
- * @capture:		list of capture videobuffers
- * @lock:		protects video buffer lists
- * @active:		active video buffer
- * @idmac_channel:	array of pointers to IPU DMAC DMA channels
- * @soc_host:		embedded soc_host object
- */
-struct mx3_camera_dev {
-	/*
-	 * i.MX3x is only supposed to handle one camera on its Camera Sensor
-	 * Interface. If anyone ever builds hardware to enable more than one
-	 * camera _simultaneously_, they will have to modify this driver too
-	 */
-	struct clk		*clk;
-
-	void __iomem		*base;
-
-	struct mx3_camera_pdata	*pdata;
-
-	unsigned long		platform_flags;
-	unsigned long		mclk;
-	u16			width_flags;	/* max 15 bits */
-
-	struct list_head	capture;
-	spinlock_t		lock;		/* Protects video buffer lists */
-	struct mx3_camera_buffer *active;
-	size_t			buf_total;
-	struct vb2_alloc_ctx	*alloc_ctx;
-	enum v4l2_field		field;
-	int			sequence;
-
-	/* IDMAC / dmaengine interface */
-	struct idmac_channel	*idmac_channel[1];	/* We need one channel */
-
-	struct soc_camera_host	soc_host;
-};
-
-struct dma_chan_request {
-	struct mx3_camera_dev	*mx3_cam;
-	enum ipu_channel	id;
-};
-
-static u32 csi_reg_read(struct mx3_camera_dev *mx3, off_t reg)
-{
-	return __raw_readl(mx3->base + reg);
-}
-
-static void csi_reg_write(struct mx3_camera_dev *mx3, u32 value, off_t reg)
-{
-	__raw_writel(value, mx3->base + reg);
-}
-
-static struct mx3_camera_buffer *to_mx3_vb(struct vb2_v4l2_buffer *vb)
-{
-	return container_of(vb, struct mx3_camera_buffer, vb);
-}
-
-/* Called from the IPU IDMAC ISR */
-static void mx3_cam_dma_done(void *arg)
-{
-	struct idmac_tx_desc *desc = to_tx_desc(arg);
-	struct dma_chan *chan = desc->txd.chan;
-	struct idmac_channel *ichannel = to_idmac_chan(chan);
-	struct mx3_camera_dev *mx3_cam = ichannel->client;
-
-	dev_dbg(chan->device->dev, "callback cookie %d, active DMA %pad\n",
-		desc->txd.cookie, mx3_cam->active ? &sg_dma_address(&mx3_cam->active->sg) : NULL);
-
-	spin_lock(&mx3_cam->lock);
-	if (mx3_cam->active) {
-		struct vb2_v4l2_buffer *vb = &mx3_cam->active->vb;
-		struct mx3_camera_buffer *buf = to_mx3_vb(vb);
-
-		list_del_init(&buf->queue);
-		vb->vb2_buf.timestamp = ktime_get_ns();
-		vb->field = mx3_cam->field;
-		vb->sequence = mx3_cam->sequence++;
-		vb2_buffer_done(&vb->vb2_buf, VB2_BUF_STATE_DONE);
-	}
-
-	if (list_empty(&mx3_cam->capture)) {
-		mx3_cam->active = NULL;
-		spin_unlock(&mx3_cam->lock);
-
-		/*
-		 * stop capture - without further buffers IPU_CHA_BUF0_RDY will
-		 * not get updated
-		 */
-		return;
-	}
-
-	mx3_cam->active = list_entry(mx3_cam->capture.next,
-				     struct mx3_camera_buffer, queue);
-	spin_unlock(&mx3_cam->lock);
-}
-
-/*
- * Videobuf operations
- */
-
-/*
- * Calculate the __buffer__ (not data) size and number of buffers.
- */
-static int mx3_videobuf_setup(struct vb2_queue *vq,
-			unsigned int *count, unsigned int *num_planes,
-			unsigned int sizes[], void *alloc_ctxs[])
-{
-	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-
-	if (!mx3_cam->idmac_channel[0])
-		return -EINVAL;
-
-	alloc_ctxs[0] = mx3_cam->alloc_ctx;
-
-	if (!vq->num_buffers)
-		mx3_cam->sequence = 0;
-
-	if (!*count)
-		*count = 2;
-
-	/* Called from VIDIOC_REQBUFS or in compatibility mode */
-	if (!*num_planes)
-		sizes[0] = icd->sizeimage;
-	else if (sizes[0] < icd->sizeimage)
-		return -EINVAL;
-
-	/* If *num_planes != 0, we have already verified *count. */
-	if (sizes[0] * *count + mx3_cam->buf_total > MAX_VIDEO_MEM * 1024 * 1024)
-		*count = (MAX_VIDEO_MEM * 1024 * 1024 - mx3_cam->buf_total) /
-			sizes[0];
-
-	*num_planes = 1;
-
-	return 0;
-}
-
-static enum pixel_fmt fourcc_to_ipu_pix(__u32 fourcc)
-{
-	/* Add more formats as need arises and test possibilities appear... */
-	switch (fourcc) {
-	case V4L2_PIX_FMT_RGB24:
-		return IPU_PIX_FMT_RGB24;
-	case V4L2_PIX_FMT_UYVY:
-	case V4L2_PIX_FMT_RGB565:
-	default:
-		return IPU_PIX_FMT_GENERIC;
-	}
-}
-
-static void mx3_videobuf_queue(struct vb2_buffer *vb)
-{
-	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct mx3_camera_buffer *buf = to_mx3_vb(vbuf);
-	struct scatterlist *sg = &buf->sg;
-	struct dma_async_tx_descriptor *txd;
-	struct idmac_channel *ichan = mx3_cam->idmac_channel[0];
-	struct idmac_video_param *video = &ichan->params.video;
-	const struct soc_mbus_pixelfmt *host_fmt = icd->current_fmt->host_fmt;
-	dma_cookie_t cookie;
-	size_t new_size;
-
-	new_size = icd->sizeimage;
-
-	if (vb2_plane_size(vb, 0) < new_size) {
-		dev_err(icd->parent, "Buffer #%d too small (%lu < %zu)\n",
-			vbuf->vb2_buf.index, vb2_plane_size(vb, 0), new_size);
-		goto error;
-	}
-
-	if (!buf->txd) {
-		sg_dma_address(sg)	= vb2_dma_contig_plane_dma_addr(vb, 0);
-		sg_dma_len(sg)		= new_size;
-
-		txd = dmaengine_prep_slave_sg(
-			&ichan->dma_chan, sg, 1, DMA_DEV_TO_MEM,
-			DMA_PREP_INTERRUPT);
-		if (!txd)
-			goto error;
-
-		txd->callback_param	= txd;
-		txd->callback		= mx3_cam_dma_done;
-
-		buf->txd		= txd;
-	} else {
-		txd = buf->txd;
-	}
-
-	vb2_set_plane_payload(vb, 0, new_size);
-
-	/* This is the configuration of one sg-element */
-	video->out_pixel_fmt = fourcc_to_ipu_pix(host_fmt->fourcc);
-
-	if (video->out_pixel_fmt == IPU_PIX_FMT_GENERIC) {
-		/*
-		 * If the IPU DMA channel is configured to transfer generic
-		 * 8-bit data, we have to set up the geometry parameters
-		 * correctly, according to the current pixel format. The DMA
-		 * horizontal parameters in this case are expressed in bytes,
-		 * not in pixels.
-		 */
-		video->out_width	= icd->bytesperline;
-		video->out_height	= icd->user_height;
-		video->out_stride	= icd->bytesperline;
-	} else {
-		/*
-		 * For IPU known formats the pixel unit will be managed
-		 * successfully by the IPU code
-		 */
-		video->out_width	= icd->user_width;
-		video->out_height	= icd->user_height;
-		video->out_stride	= icd->user_width;
-	}
-
-#ifdef DEBUG
-	/* helps to see what DMA actually has written */
-	if (vb2_plane_vaddr(vb, 0))
-		memset(vb2_plane_vaddr(vb, 0), 0xaa, vb2_get_plane_payload(vb, 0));
-#endif
-
-	spin_lock_irq(&mx3_cam->lock);
-	list_add_tail(&buf->queue, &mx3_cam->capture);
-
-	if (!mx3_cam->active)
-		mx3_cam->active = buf;
-
-	spin_unlock_irq(&mx3_cam->lock);
-
-	cookie = txd->tx_submit(txd);
-	dev_dbg(icd->parent, "Submitted cookie %d DMA %pad\n",
-		cookie, &sg_dma_address(&buf->sg));
-
-	if (cookie >= 0)
-		return;
-
-	spin_lock_irq(&mx3_cam->lock);
-
-	/* Submit error */
-	list_del_init(&buf->queue);
-
-	if (mx3_cam->active == buf)
-		mx3_cam->active = NULL;
-
-	spin_unlock_irq(&mx3_cam->lock);
-error:
-	vb2_buffer_done(vb, VB2_BUF_STATE_ERROR);
-}
-
-static void mx3_videobuf_release(struct vb2_buffer *vb)
-{
-	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct mx3_camera_buffer *buf = to_mx3_vb(vbuf);
-	struct dma_async_tx_descriptor *txd = buf->txd;
-	unsigned long flags;
-
-	dev_dbg(icd->parent,
-		"Release%s DMA %pad, queue %sempty\n",
-		mx3_cam->active == buf ? " active" : "", &sg_dma_address(&buf->sg),
-		list_empty(&buf->queue) ? "" : "not ");
-
-	spin_lock_irqsave(&mx3_cam->lock, flags);
-
-	if (mx3_cam->active == buf)
-		mx3_cam->active = NULL;
-
-	/* Doesn't hurt also if the list is empty */
-	list_del_init(&buf->queue);
-
-	if (txd) {
-		buf->txd = NULL;
-		if (mx3_cam->idmac_channel[0])
-			async_tx_ack(txd);
-	}
-
-	spin_unlock_irqrestore(&mx3_cam->lock, flags);
-
-	mx3_cam->buf_total -= vb2_plane_size(vb, 0);
-}
-
-static int mx3_videobuf_init(struct vb2_buffer *vb)
-{
-	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct mx3_camera_buffer *buf = to_mx3_vb(vbuf);
-
-	if (!buf->txd) {
-		/* This is for locking debugging only */
-		INIT_LIST_HEAD(&buf->queue);
-		sg_init_table(&buf->sg, 1);
-
-		mx3_cam->buf_total += vb2_plane_size(vb, 0);
-	}
-
-	return 0;
-}
-
-static void mx3_stop_streaming(struct vb2_queue *q)
-{
-	struct soc_camera_device *icd = soc_camera_from_vb2q(q);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct idmac_channel *ichan = mx3_cam->idmac_channel[0];
-	struct mx3_camera_buffer *buf, *tmp;
-	unsigned long flags;
-
-	if (ichan)
-		dmaengine_pause(&ichan->dma_chan);
-
-	spin_lock_irqsave(&mx3_cam->lock, flags);
-
-	mx3_cam->active = NULL;
-
-	list_for_each_entry_safe(buf, tmp, &mx3_cam->capture, queue) {
-		list_del_init(&buf->queue);
-		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
-	}
-
-	spin_unlock_irqrestore(&mx3_cam->lock, flags);
-}
-
-static struct vb2_ops mx3_videobuf_ops = {
-	.queue_setup	= mx3_videobuf_setup,
-	.buf_queue	= mx3_videobuf_queue,
-	.buf_cleanup	= mx3_videobuf_release,
-	.buf_init	= mx3_videobuf_init,
-	.wait_prepare	= vb2_ops_wait_prepare,
-	.wait_finish	= vb2_ops_wait_finish,
-	.stop_streaming	= mx3_stop_streaming,
-};
-
-static int mx3_camera_init_videobuf(struct vb2_queue *q,
-				     struct soc_camera_device *icd)
-{
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-
-	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	q->io_modes = VB2_MMAP | VB2_USERPTR;
-	q->drv_priv = icd;
-	q->ops = &mx3_videobuf_ops;
-	q->mem_ops = &vb2_dma_contig_memops;
-	q->buf_struct_size = sizeof(struct mx3_camera_buffer);
-	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->lock = &ici->host_lock;
-
-	return vb2_queue_init(q);
-}
-
-/* First part of ipu_csi_init_interface() */
-static void mx3_camera_activate(struct mx3_camera_dev *mx3_cam)
-{
-	u32 conf;
-	long rate;
-
-	/* Set default size: ipu_csi_set_window_size() */
-	csi_reg_write(mx3_cam, (640 - 1) | ((480 - 1) << 16), CSI_ACT_FRM_SIZE);
-	/* ...and position to 0:0: ipu_csi_set_window_pos() */
-	conf = csi_reg_read(mx3_cam, CSI_OUT_FRM_CTRL) & 0xffff0000;
-	csi_reg_write(mx3_cam, conf, CSI_OUT_FRM_CTRL);
-
-	/* We use only gated clock synchronisation mode so far */
-	conf = 0 << CSI_SENS_CONF_SENS_PRTCL_SHIFT;
-
-	/* Set generic data, platform-biggest bus-width */
-	conf |= CSI_SENS_CONF_DATA_FMT_BAYER;
-
-	if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_15)
-		conf |= 3 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-	else if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_10)
-		conf |= 2 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-	else if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_8)
-		conf |= 1 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-	else/* if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_4)*/
-		conf |= 0 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-
-	if (mx3_cam->platform_flags & MX3_CAMERA_CLK_SRC)
-		conf |= 1 << CSI_SENS_CONF_SENS_CLKSRC_SHIFT;
-	if (mx3_cam->platform_flags & MX3_CAMERA_EXT_VSYNC)
-		conf |= 1 << CSI_SENS_CONF_EXT_VSYNC_SHIFT;
-	if (mx3_cam->platform_flags & MX3_CAMERA_DP)
-		conf |= 1 << CSI_SENS_CONF_DATA_POL_SHIFT;
-	if (mx3_cam->platform_flags & MX3_CAMERA_PCP)
-		conf |= 1 << CSI_SENS_CONF_PIX_CLK_POL_SHIFT;
-	if (mx3_cam->platform_flags & MX3_CAMERA_HSP)
-		conf |= 1 << CSI_SENS_CONF_HSYNC_POL_SHIFT;
-	if (mx3_cam->platform_flags & MX3_CAMERA_VSP)
-		conf |= 1 << CSI_SENS_CONF_VSYNC_POL_SHIFT;
-
-	/* ipu_csi_init_interface() */
-	csi_reg_write(mx3_cam, conf, CSI_SENS_CONF);
-
-	clk_prepare_enable(mx3_cam->clk);
-	rate = clk_round_rate(mx3_cam->clk, mx3_cam->mclk);
-	dev_dbg(mx3_cam->soc_host.v4l2_dev.dev, "Set SENS_CONF to %x, rate %ld\n", conf, rate);
-	if (rate)
-		clk_set_rate(mx3_cam->clk, rate);
-}
-
-static int mx3_camera_add_device(struct soc_camera_device *icd)
-{
-	dev_info(icd->parent, "MX3 Camera driver attached to camera %d\n",
-		 icd->devnum);
-
-	return 0;
-}
-
-static void mx3_camera_remove_device(struct soc_camera_device *icd)
-{
-	dev_info(icd->parent, "MX3 Camera driver detached from camera %d\n",
-		 icd->devnum);
-}
-
-/* Called with .host_lock held */
-static int mx3_camera_clock_start(struct soc_camera_host *ici)
-{
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-
-	mx3_camera_activate(mx3_cam);
-
-	mx3_cam->buf_total = 0;
-
-	return 0;
-}
-
-/* Called with .host_lock held */
-static void mx3_camera_clock_stop(struct soc_camera_host *ici)
-{
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct idmac_channel **ichan = &mx3_cam->idmac_channel[0];
-
-	if (*ichan) {
-		dma_release_channel(&(*ichan)->dma_chan);
-		*ichan = NULL;
-	}
-
-	clk_disable_unprepare(mx3_cam->clk);
-}
-
-static int test_platform_param(struct mx3_camera_dev *mx3_cam,
-			       unsigned char buswidth, unsigned long *flags)
-{
-	/*
-	 * If requested data width is supported by the platform, use it or any
-	 * possible lower value - i.MX31 is smart enough to shift bits
-	 */
-	if (buswidth > fls(mx3_cam->width_flags))
-		return -EINVAL;
-
-	/*
-	 * Platform specified synchronization and pixel clock polarities are
-	 * only a recommendation and are only used during probing. MX3x
-	 * camera interface only works in master mode, i.e., uses HSYNC and
-	 * VSYNC signals from the sensor
-	 */
-	*flags = V4L2_MBUS_MASTER |
-		V4L2_MBUS_HSYNC_ACTIVE_HIGH |
-		V4L2_MBUS_HSYNC_ACTIVE_LOW |
-		V4L2_MBUS_VSYNC_ACTIVE_HIGH |
-		V4L2_MBUS_VSYNC_ACTIVE_LOW |
-		V4L2_MBUS_PCLK_SAMPLE_RISING |
-		V4L2_MBUS_PCLK_SAMPLE_FALLING |
-		V4L2_MBUS_DATA_ACTIVE_HIGH |
-		V4L2_MBUS_DATA_ACTIVE_LOW;
-
-	return 0;
-}
-
-static int mx3_camera_try_bus_param(struct soc_camera_device *icd,
-				    const unsigned int depth)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct v4l2_mbus_config cfg = {.type = V4L2_MBUS_PARALLEL,};
-	unsigned long bus_flags, common_flags;
-	int ret = test_platform_param(mx3_cam, depth, &bus_flags);
-
-	dev_dbg(icd->parent, "request bus width %d bit: %d\n", depth, ret);
-
-	if (ret < 0)
-		return ret;
-
-	ret = v4l2_subdev_call(sd, video, g_mbus_config, &cfg);
-	if (!ret) {
-		common_flags = soc_mbus_config_compatible(&cfg,
-							  bus_flags);
-		if (!common_flags) {
-			dev_warn(icd->parent,
-				 "Flags incompatible: camera 0x%x, host 0x%lx\n",
-				 cfg.flags, bus_flags);
-			return -EINVAL;
-		}
-	} else if (ret != -ENOIOCTLCMD) {
-		return ret;
-	}
-
-	return 0;
-}
-
-static bool chan_filter(struct dma_chan *chan, void *arg)
-{
-	struct dma_chan_request *rq = arg;
-	struct mx3_camera_pdata *pdata;
-
-	if (!imx_dma_is_ipu(chan))
-		return false;
-
-	if (!rq)
-		return false;
-
-	pdata = rq->mx3_cam->soc_host.v4l2_dev.dev->platform_data;
-
-	return rq->id == chan->chan_id &&
-		pdata->dma_dev == chan->device->dev;
-}
-
-static const struct soc_mbus_pixelfmt mx3_camera_formats[] = {
-	{
-		.fourcc			= V4L2_PIX_FMT_SBGGR8,
-		.name			= "Bayer BGGR (sRGB) 8 bit",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_NONE,
-		.order			= SOC_MBUS_ORDER_LE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	}, {
-		.fourcc			= V4L2_PIX_FMT_GREY,
-		.name			= "Monochrome 8 bit",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_NONE,
-		.order			= SOC_MBUS_ORDER_LE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-};
-
-/* This will be corrected as we get more formats */
-static bool mx3_camera_packing_supported(const struct soc_mbus_pixelfmt *fmt)
-{
-	return	fmt->packing == SOC_MBUS_PACKING_NONE ||
-		(fmt->bits_per_sample == 8 &&
-		 fmt->packing == SOC_MBUS_PACKING_2X8_PADHI) ||
-		(fmt->bits_per_sample > 8 &&
-		 fmt->packing == SOC_MBUS_PACKING_EXTEND16);
-}
-
-static int mx3_camera_get_formats(struct soc_camera_device *icd, unsigned int idx,
-				  struct soc_camera_format_xlate *xlate)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct device *dev = icd->parent;
-	int formats = 0, ret;
-	struct v4l2_subdev_mbus_code_enum code = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-		.index = idx,
-	};
-	const struct soc_mbus_pixelfmt *fmt;
-
-	ret = v4l2_subdev_call(sd, pad, enum_mbus_code, NULL, &code);
-	if (ret < 0)
-		/* No more formats */
-		return 0;
-
-	fmt = soc_mbus_get_fmtdesc(code.code);
-	if (!fmt) {
-		dev_warn(icd->parent,
-			 "Unsupported format code #%u: 0x%x\n", idx, code.code);
-		return 0;
-	}
-
-	/* This also checks support for the requested bits-per-sample */
-	ret = mx3_camera_try_bus_param(icd, fmt->bits_per_sample);
-	if (ret < 0)
-		return 0;
-
-	switch (code.code) {
-	case MEDIA_BUS_FMT_SBGGR10_1X10:
-		formats++;
-		if (xlate) {
-			xlate->host_fmt	= &mx3_camera_formats[0];
-			xlate->code	= code.code;
-			xlate++;
-			dev_dbg(dev, "Providing format %s using code 0x%x\n",
-				mx3_camera_formats[0].name, code.code);
-		}
-		break;
-	case MEDIA_BUS_FMT_Y10_1X10:
-		formats++;
-		if (xlate) {
-			xlate->host_fmt	= &mx3_camera_formats[1];
-			xlate->code	= code.code;
-			xlate++;
-			dev_dbg(dev, "Providing format %s using code 0x%x\n",
-				mx3_camera_formats[1].name, code.code);
-		}
-		break;
-	default:
-		if (!mx3_camera_packing_supported(fmt))
-			return 0;
-	}
-
-	/* Generic pass-through */
-	formats++;
-	if (xlate) {
-		xlate->host_fmt	= fmt;
-		xlate->code	= code.code;
-		dev_dbg(dev, "Providing format %c%c%c%c in pass-through mode\n",
-			(fmt->fourcc >> (0*8)) & 0xFF,
-			(fmt->fourcc >> (1*8)) & 0xFF,
-			(fmt->fourcc >> (2*8)) & 0xFF,
-			(fmt->fourcc >> (3*8)) & 0xFF);
-		xlate++;
-	}
-
-	return formats;
-}
-
-static void configure_geometry(struct mx3_camera_dev *mx3_cam,
-			       unsigned int width, unsigned int height,
-			       const struct soc_mbus_pixelfmt *fmt)
-{
-	u32 ctrl, width_field, height_field;
-
-	if (fourcc_to_ipu_pix(fmt->fourcc) == IPU_PIX_FMT_GENERIC) {
-		/*
-		 * As the CSI will be configured to output BAYER, here
-		 * the width parameter count the number of samples to
-		 * capture to complete the whole image width.
-		 */
-		unsigned int num, den;
-		int ret = soc_mbus_samples_per_pixel(fmt, &num, &den);
-		BUG_ON(ret < 0);
-		width = width * num / den;
-	}
-
-	/* Setup frame size - this cannot be changed on-the-fly... */
-	width_field = width - 1;
-	height_field = height - 1;
-	csi_reg_write(mx3_cam, width_field | (height_field << 16), CSI_SENS_FRM_SIZE);
-
-	csi_reg_write(mx3_cam, width_field << 16, CSI_FLASH_STROBE_1);
-	csi_reg_write(mx3_cam, (height_field << 16) | 0x22, CSI_FLASH_STROBE_2);
-
-	csi_reg_write(mx3_cam, width_field | (height_field << 16), CSI_ACT_FRM_SIZE);
-
-	/* ...and position */
-	ctrl = csi_reg_read(mx3_cam, CSI_OUT_FRM_CTRL) & 0xffff0000;
-	/* Sensor does the cropping */
-	csi_reg_write(mx3_cam, ctrl | 0 | (0 << 8), CSI_OUT_FRM_CTRL);
-}
-
-static int acquire_dma_channel(struct mx3_camera_dev *mx3_cam)
-{
-	dma_cap_mask_t mask;
-	struct dma_chan *chan;
-	struct idmac_channel **ichan = &mx3_cam->idmac_channel[0];
-	/* We have to use IDMAC_IC_7 for Bayer / generic data */
-	struct dma_chan_request rq = {.mx3_cam = mx3_cam,
-				      .id = IDMAC_IC_7};
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	dma_cap_set(DMA_PRIVATE, mask);
-	chan = dma_request_channel(mask, chan_filter, &rq);
-	if (!chan)
-		return -EBUSY;
-
-	*ichan = to_idmac_chan(chan);
-	(*ichan)->client = mx3_cam;
-
-	return 0;
-}
-
-/*
- * FIXME: learn to use stride != width, then we can keep stride properly aligned
- * and support arbitrary (even) widths.
- */
-static inline void stride_align(__u32 *width)
-{
-	if (ALIGN(*width, 8) < 4096)
-		*width = ALIGN(*width, 8);
-	else
-		*width = *width &  ~7;
-}
-
-/*
- * As long as we don't implement host-side cropping and scaling, we can use
- * default g_crop and cropcap from soc_camera.c
- */
-static int mx3_camera_set_crop(struct soc_camera_device *icd,
-			       const struct v4l2_crop *a)
-{
-	struct v4l2_crop a_writable = *a;
-	struct v4l2_rect *rect = &a_writable.c;
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct v4l2_subdev_format fmt = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-	};
-	struct v4l2_mbus_framefmt *mf = &fmt.format;
-	int ret;
-
-	soc_camera_limit_side(&rect->left, &rect->width, 0, 2, 4096);
-	soc_camera_limit_side(&rect->top, &rect->height, 0, 2, 4096);
-
-	ret = v4l2_subdev_call(sd, video, s_crop, a);
-	if (ret < 0)
-		return ret;
-
-	/* The capture device might have changed its output sizes */
-	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt);
-	if (ret < 0)
-		return ret;
-
-	if (mf->code != icd->current_fmt->code)
-		return -EINVAL;
-
-	if (mf->width & 7) {
-		/* Ouch! We can only handle 8-byte aligned width... */
-		stride_align(&mf->width);
-		ret = v4l2_subdev_call(sd, pad, set_fmt, NULL, &fmt);
-		if (ret < 0)
-			return ret;
-	}
-
-	if (mf->width != icd->user_width || mf->height != icd->user_height)
-		configure_geometry(mx3_cam, mf->width, mf->height,
-				   icd->current_fmt->host_fmt);
-
-	dev_dbg(icd->parent, "Sensor cropped %dx%d\n",
-		mf->width, mf->height);
-
-	icd->user_width		= mf->width;
-	icd->user_height	= mf->height;
-
-	return ret;
-}
-
-static int mx3_camera_set_fmt(struct soc_camera_device *icd,
-			      struct v4l2_format *f)
-{
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	const struct soc_camera_format_xlate *xlate;
-	struct v4l2_pix_format *pix = &f->fmt.pix;
-	struct v4l2_subdev_format format = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-	};
-	struct v4l2_mbus_framefmt *mf = &format.format;
-	int ret;
-
-	xlate = soc_camera_xlate_by_fourcc(icd, pix->pixelformat);
-	if (!xlate) {
-		dev_warn(icd->parent, "Format %x not found\n",
-			 pix->pixelformat);
-		return -EINVAL;
-	}
-
-	stride_align(&pix->width);
-	dev_dbg(icd->parent, "Set format %dx%d\n", pix->width, pix->height);
-
-	/*
-	 * Might have to perform a complete interface initialisation like in
-	 * ipu_csi_init_interface() in mxc_v4l2_s_param(). Also consider
-	 * mxc_v4l2_s_fmt()
-	 */
-
-	configure_geometry(mx3_cam, pix->width, pix->height, xlate->host_fmt);
-
-	mf->width	= pix->width;
-	mf->height	= pix->height;
-	mf->field	= pix->field;
-	mf->colorspace	= pix->colorspace;
-	mf->code	= xlate->code;
-
-	ret = v4l2_subdev_call(sd, pad, set_fmt, NULL, &format);
-	if (ret < 0)
-		return ret;
-
-	if (mf->code != xlate->code)
-		return -EINVAL;
-
-	if (!mx3_cam->idmac_channel[0]) {
-		ret = acquire_dma_channel(mx3_cam);
-		if (ret < 0)
-			return ret;
-	}
-
-	pix->width		= mf->width;
-	pix->height		= mf->height;
-	pix->field		= mf->field;
-	mx3_cam->field		= mf->field;
-	pix->colorspace		= mf->colorspace;
-	icd->current_fmt	= xlate;
-
-	dev_dbg(icd->parent, "Sensor set %dx%d\n", pix->width, pix->height);
-
-	return ret;
-}
-
-static int mx3_camera_try_fmt(struct soc_camera_device *icd,
-			      struct v4l2_format *f)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	const struct soc_camera_format_xlate *xlate;
-	struct v4l2_pix_format *pix = &f->fmt.pix;
-	struct v4l2_subdev_pad_config pad_cfg;
-	struct v4l2_subdev_format format = {
-		.which = V4L2_SUBDEV_FORMAT_TRY,
-	};
-	struct v4l2_mbus_framefmt *mf = &format.format;
-	__u32 pixfmt = pix->pixelformat;
-	int ret;
-
-	xlate = soc_camera_xlate_by_fourcc(icd, pixfmt);
-	if (pixfmt && !xlate) {
-		dev_warn(icd->parent, "Format %x not found\n", pixfmt);
-		return -EINVAL;
-	}
-
-	/* limit to MX3 hardware capabilities */
-	if (pix->height > 4096)
-		pix->height = 4096;
-	if (pix->width > 4096)
-		pix->width = 4096;
-
-	/* limit to sensor capabilities */
-	mf->width	= pix->width;
-	mf->height	= pix->height;
-	mf->field	= pix->field;
-	mf->colorspace	= pix->colorspace;
-	mf->code	= xlate->code;
-
-	ret = v4l2_subdev_call(sd, pad, set_fmt, &pad_cfg, &format);
-	if (ret < 0)
-		return ret;
-
-	pix->width	= mf->width;
-	pix->height	= mf->height;
-	pix->colorspace	= mf->colorspace;
-
-	switch (mf->field) {
-	case V4L2_FIELD_ANY:
-		pix->field = V4L2_FIELD_NONE;
-		break;
-	case V4L2_FIELD_NONE:
-		break;
-	default:
-		dev_err(icd->parent, "Field type %d unsupported.\n",
-			mf->field);
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
-
-static int mx3_camera_reqbufs(struct soc_camera_device *icd,
-			      struct v4l2_requestbuffers *p)
-{
-	return 0;
-}
-
-static unsigned int mx3_camera_poll(struct file *file, poll_table *pt)
-{
-	struct soc_camera_device *icd = file->private_data;
-
-	return vb2_poll(&icd->vb2_vidq, file, pt);
-}
-
-static int mx3_camera_querycap(struct soc_camera_host *ici,
-			       struct v4l2_capability *cap)
-{
-	/* cap->name is set by the firendly caller:-> */
-	strlcpy(cap->card, "i.MX3x Camera", sizeof(cap->card));
-	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING;
-	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
-
-	return 0;
-}
-
-static int mx3_camera_set_bus_param(struct soc_camera_device *icd)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct mx3_camera_dev *mx3_cam = ici->priv;
-	struct v4l2_mbus_config cfg = {.type = V4L2_MBUS_PARALLEL,};
-	u32 pixfmt = icd->current_fmt->host_fmt->fourcc;
-	unsigned long bus_flags, common_flags;
-	u32 dw, sens_conf;
-	const struct soc_mbus_pixelfmt *fmt;
-	int buswidth;
-	int ret;
-	const struct soc_camera_format_xlate *xlate;
-	struct device *dev = icd->parent;
-
-	fmt = soc_mbus_get_fmtdesc(icd->current_fmt->code);
-	if (!fmt)
-		return -EINVAL;
-
-	xlate = soc_camera_xlate_by_fourcc(icd, pixfmt);
-	if (!xlate) {
-		dev_warn(dev, "Format %x not found\n", pixfmt);
-		return -EINVAL;
-	}
-
-	buswidth = fmt->bits_per_sample;
-	ret = test_platform_param(mx3_cam, buswidth, &bus_flags);
-
-	dev_dbg(dev, "requested bus width %d bit: %d\n", buswidth, ret);
-
-	if (ret < 0)
-		return ret;
-
-	ret = v4l2_subdev_call(sd, video, g_mbus_config, &cfg);
-	if (!ret) {
-		common_flags = soc_mbus_config_compatible(&cfg,
-							  bus_flags);
-		if (!common_flags) {
-			dev_warn(icd->parent,
-				 "Flags incompatible: camera 0x%x, host 0x%lx\n",
-				 cfg.flags, bus_flags);
-			return -EINVAL;
-		}
-	} else if (ret != -ENOIOCTLCMD) {
-		return ret;
-	} else {
-		common_flags = bus_flags;
-	}
-
-	dev_dbg(dev, "Flags cam: 0x%x host: 0x%lx common: 0x%lx\n",
-		cfg.flags, bus_flags, common_flags);
-
-	/* Make choices, based on platform preferences */
-	if ((common_flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH) &&
-	    (common_flags & V4L2_MBUS_HSYNC_ACTIVE_LOW)) {
-		if (mx3_cam->platform_flags & MX3_CAMERA_HSP)
-			common_flags &= ~V4L2_MBUS_HSYNC_ACTIVE_HIGH;
-		else
-			common_flags &= ~V4L2_MBUS_HSYNC_ACTIVE_LOW;
-	}
-
-	if ((common_flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH) &&
-	    (common_flags & V4L2_MBUS_VSYNC_ACTIVE_LOW)) {
-		if (mx3_cam->platform_flags & MX3_CAMERA_VSP)
-			common_flags &= ~V4L2_MBUS_VSYNC_ACTIVE_HIGH;
-		else
-			common_flags &= ~V4L2_MBUS_VSYNC_ACTIVE_LOW;
-	}
-
-	if ((common_flags & V4L2_MBUS_DATA_ACTIVE_HIGH) &&
-	    (common_flags & V4L2_MBUS_DATA_ACTIVE_LOW)) {
-		if (mx3_cam->platform_flags & MX3_CAMERA_DP)
-			common_flags &= ~V4L2_MBUS_DATA_ACTIVE_HIGH;
-		else
-			common_flags &= ~V4L2_MBUS_DATA_ACTIVE_LOW;
-	}
-
-	if ((common_flags & V4L2_MBUS_PCLK_SAMPLE_RISING) &&
-	    (common_flags & V4L2_MBUS_PCLK_SAMPLE_FALLING)) {
-		if (mx3_cam->platform_flags & MX3_CAMERA_PCP)
-			common_flags &= ~V4L2_MBUS_PCLK_SAMPLE_RISING;
-		else
-			common_flags &= ~V4L2_MBUS_PCLK_SAMPLE_FALLING;
-	}
-
-	cfg.flags = common_flags;
-	ret = v4l2_subdev_call(sd, video, s_mbus_config, &cfg);
-	if (ret < 0 && ret != -ENOIOCTLCMD) {
-		dev_dbg(dev, "camera s_mbus_config(0x%lx) returned %d\n",
-			common_flags, ret);
-		return ret;
-	}
-
-	/*
-	 * So far only gated clock mode is supported. Add a line
-	 *	(3 << CSI_SENS_CONF_SENS_PRTCL_SHIFT) |
-	 * below and select the required mode when supporting other
-	 * synchronisation protocols.
-	 */
-	sens_conf = csi_reg_read(mx3_cam, CSI_SENS_CONF) &
-		~((1 << CSI_SENS_CONF_VSYNC_POL_SHIFT) |
-		  (1 << CSI_SENS_CONF_HSYNC_POL_SHIFT) |
-		  (1 << CSI_SENS_CONF_DATA_POL_SHIFT) |
-		  (1 << CSI_SENS_CONF_PIX_CLK_POL_SHIFT) |
-		  (3 << CSI_SENS_CONF_DATA_FMT_SHIFT) |
-		  (3 << CSI_SENS_CONF_DATA_WIDTH_SHIFT));
-
-	/* TODO: Support RGB and YUV formats */
-
-	/* This has been set in mx3_camera_activate(), but we clear it above */
-	sens_conf |= CSI_SENS_CONF_DATA_FMT_BAYER;
-
-	if (common_flags & V4L2_MBUS_PCLK_SAMPLE_FALLING)
-		sens_conf |= 1 << CSI_SENS_CONF_PIX_CLK_POL_SHIFT;
-	if (common_flags & V4L2_MBUS_HSYNC_ACTIVE_LOW)
-		sens_conf |= 1 << CSI_SENS_CONF_HSYNC_POL_SHIFT;
-	if (common_flags & V4L2_MBUS_VSYNC_ACTIVE_LOW)
-		sens_conf |= 1 << CSI_SENS_CONF_VSYNC_POL_SHIFT;
-	if (common_flags & V4L2_MBUS_DATA_ACTIVE_LOW)
-		sens_conf |= 1 << CSI_SENS_CONF_DATA_POL_SHIFT;
-
-	/* Just do what we're asked to do */
-	switch (xlate->host_fmt->bits_per_sample) {
-	case 4:
-		dw = 0 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-		break;
-	case 8:
-		dw = 1 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-		break;
-	case 10:
-		dw = 2 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-		break;
-	default:
-		/*
-		 * Actually it can only be 15 now, default is just to silence
-		 * compiler warnings
-		 */
-	case 15:
-		dw = 3 << CSI_SENS_CONF_DATA_WIDTH_SHIFT;
-	}
-
-	csi_reg_write(mx3_cam, sens_conf | dw, CSI_SENS_CONF);
-
-	dev_dbg(dev, "Set SENS_CONF to %x\n", sens_conf | dw);
-
-	return 0;
-}
-
-static struct soc_camera_host_ops mx3_soc_camera_host_ops = {
-	.owner		= THIS_MODULE,
-	.add		= mx3_camera_add_device,
-	.remove		= mx3_camera_remove_device,
-	.clock_start	= mx3_camera_clock_start,
-	.clock_stop	= mx3_camera_clock_stop,
-	.set_crop	= mx3_camera_set_crop,
-	.set_fmt	= mx3_camera_set_fmt,
-	.try_fmt	= mx3_camera_try_fmt,
-	.get_formats	= mx3_camera_get_formats,
-	.init_videobuf2	= mx3_camera_init_videobuf,
-	.reqbufs	= mx3_camera_reqbufs,
-	.poll		= mx3_camera_poll,
-	.querycap	= mx3_camera_querycap,
-	.set_bus_param	= mx3_camera_set_bus_param,
-};
-
-static int mx3_camera_probe(struct platform_device *pdev)
-{
-	struct mx3_camera_pdata	*pdata = pdev->dev.platform_data;
-	struct mx3_camera_dev *mx3_cam;
-	struct resource *res;
-	void __iomem *base;
-	int err = 0;
-	struct soc_camera_host *soc_host;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(base))
-		return PTR_ERR(base);
-
-	if (!pdata)
-		return -EINVAL;
-
-	mx3_cam = devm_kzalloc(&pdev->dev, sizeof(*mx3_cam), GFP_KERNEL);
-	if (!mx3_cam) {
-		dev_err(&pdev->dev, "Could not allocate mx3 camera object\n");
-		return -ENOMEM;
-	}
-
-	mx3_cam->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(mx3_cam->clk))
-		return PTR_ERR(mx3_cam->clk);
-
-	mx3_cam->pdata = pdata;
-	mx3_cam->platform_flags = pdata->flags;
-	if (!(mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_MASK)) {
-		/*
-		 * Platform hasn't set available data widths. This is bad.
-		 * Warn and use a default.
-		 */
-		dev_warn(&pdev->dev, "WARNING! Platform hasn't set available "
-			 "data widths, using default 8 bit\n");
-		mx3_cam->platform_flags |= MX3_CAMERA_DATAWIDTH_8;
-	}
-	if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_4)
-		mx3_cam->width_flags = 1 << 3;
-	if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_8)
-		mx3_cam->width_flags |= 1 << 7;
-	if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_10)
-		mx3_cam->width_flags |= 1 << 9;
-	if (mx3_cam->platform_flags & MX3_CAMERA_DATAWIDTH_15)
-		mx3_cam->width_flags |= 1 << 14;
-
-	mx3_cam->mclk = pdata->mclk_10khz * 10000;
-	if (!mx3_cam->mclk) {
-		dev_warn(&pdev->dev,
-			 "mclk_10khz == 0! Please, fix your platform data. "
-			 "Using default 20MHz\n");
-		mx3_cam->mclk = 20000000;
-	}
-
-	/* list of video-buffers */
-	INIT_LIST_HEAD(&mx3_cam->capture);
-	spin_lock_init(&mx3_cam->lock);
-
-	mx3_cam->base	= base;
-
-	soc_host		= &mx3_cam->soc_host;
-	soc_host->drv_name	= MX3_CAM_DRV_NAME;
-	soc_host->ops		= &mx3_soc_camera_host_ops;
-	soc_host->priv		= mx3_cam;
-	soc_host->v4l2_dev.dev	= &pdev->dev;
-	soc_host->nr		= pdev->id;
-
-	mx3_cam->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(mx3_cam->alloc_ctx))
-		return PTR_ERR(mx3_cam->alloc_ctx);
-
-	if (pdata->asd_sizes) {
-		soc_host->asd = pdata->asd;
-		soc_host->asd_sizes = pdata->asd_sizes;
-	}
-
-	err = soc_camera_host_register(soc_host);
-	if (err)
-		goto ecamhostreg;
-
-	/* IDMAC interface */
-	dmaengine_get();
-
-	return 0;
-
-ecamhostreg:
-	vb2_dma_contig_cleanup_ctx(mx3_cam->alloc_ctx);
-	return err;
-}
-
-static int mx3_camera_remove(struct platform_device *pdev)
-{
-	struct soc_camera_host *soc_host = to_soc_camera_host(&pdev->dev);
-	struct mx3_camera_dev *mx3_cam = container_of(soc_host,
-					struct mx3_camera_dev, soc_host);
-
-	soc_camera_host_unregister(soc_host);
-
-	/*
-	 * The channel has either not been allocated,
-	 * or should have been released
-	 */
-	if (WARN_ON(mx3_cam->idmac_channel[0]))
-		dma_release_channel(&mx3_cam->idmac_channel[0]->dma_chan);
-
-	vb2_dma_contig_cleanup_ctx(mx3_cam->alloc_ctx);
-
-	dmaengine_put();
-
-	return 0;
-}
-
-static struct platform_driver mx3_camera_driver = {
-	.driver		= {
-		.name	= MX3_CAM_DRV_NAME,
-	},
-	.probe		= mx3_camera_probe,
-	.remove		= mx3_camera_remove,
-};
-
-module_platform_driver(mx3_camera_driver);
-
-MODULE_DESCRIPTION("i.MX3x SoC Camera Host driver");
-MODULE_AUTHOR("Guennadi Liakhovetski <lg@denx.de>");
-MODULE_LICENSE("GPL v2");
-MODULE_VERSION("0.2.3");
-MODULE_ALIAS("platform:" MX3_CAM_DRV_NAME);
diff --git a/drivers/staging/media/omap1/Kconfig b/drivers/staging/media/omap1/Kconfig
deleted file mode 100644
index 6cfab3a04ae1..000000000000
--- a/drivers/staging/media/omap1/Kconfig
+++ /dev/null
@@ -1,13 +0,0 @@
-config VIDEO_OMAP1
-	tristate "OMAP1 Camera Interface driver"
-	depends on VIDEO_DEV && SOC_CAMERA
-	depends on ARCH_OMAP1
-	depends on HAS_DMA
-	select VIDEOBUF_DMA_CONTIG
-	select VIDEOBUF_DMA_SG
-	---help---
-	  This is a v4l2 driver for the TI OMAP1 camera interface
-
-	  This driver is deprecated and will be removed soon unless someone
-	  will start the work to convert this driver to the vb2 framework
-	  and remove the soc-camera dependency.
diff --git a/drivers/staging/media/omap1/Makefile b/drivers/staging/media/omap1/Makefile
deleted file mode 100644
index 2885622600f2..000000000000
--- a/drivers/staging/media/omap1/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# Makefile for OMAP1 driver
-
-obj-$(CONFIG_VIDEO_OMAP1) += omap1_camera.o
diff --git a/drivers/staging/media/omap1/TODO b/drivers/staging/media/omap1/TODO
deleted file mode 100644
index 1025f9f60ff0..000000000000
--- a/drivers/staging/media/omap1/TODO
+++ /dev/null
@@ -1,8 +0,0 @@
-This driver is deprecated and will be removed soon unless someone will start
-the work to convert this driver to the vb2 framework and remove the
-soc-camera dependency.
-
-Note that trivial patches will not be accepted anymore, only a full conversion.
-
-If you want to convert this driver, please contact the linux-media mailinglist
-(see http://linuxtv.org/lists.php).
diff --git a/drivers/staging/media/omap1/omap1_camera.c b/drivers/staging/media/omap1/omap1_camera.c
deleted file mode 100644
index 54b8dd2d2bba..000000000000
--- a/drivers/staging/media/omap1/omap1_camera.c
+++ /dev/null
@@ -1,1702 +0,0 @@
-/*
- * V4L2 SoC Camera driver for OMAP1 Camera Interface
- *
- * Copyright (C) 2010, Janusz Krzysztofik <jkrzyszt@tis.icnet.pl>
- *
- * Based on V4L2 Driver for i.MXL/i.MXL camera (CSI) host
- * Copyright (C) 2008, Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- * Copyright (C) 2009, Darius Augulis <augulis.darius@gmail.com>
- *
- * Based on PXA SoC camera driver
- * Copyright (C) 2006, Sascha Hauer, Pengutronix
- * Copyright (C) 2008, Guennadi Liakhovetski <kernel@pengutronix.de>
- *
- * Hardware specific bits initialy based on former work by Matt Callow
- * drivers/media/platform/omap/omap1510cam.c
- * Copyright (C) 2006 Matt Callow
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-
-#include <linux/clk.h>
-#include <linux/dma-mapping.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-#include <linux/platform_data/media/omap1_camera.h>
-#include <media/soc_camera.h>
-#include <media/drv-intf/soc_mediabus.h>
-#include <media/videobuf-dma-contig.h>
-#include <media/videobuf-dma-sg.h>
-
-#include <linux/omap-dma.h>
-
-
-#define DRIVER_NAME		"omap1-camera"
-#define DRIVER_VERSION		"0.0.2"
-
-#define OMAP_DMA_CAMERA_IF_RX		20
-
-/*
- * ---------------------------------------------------------------------------
- *  OMAP1 Camera Interface registers
- * ---------------------------------------------------------------------------
- */
-
-#define REG_CTRLCLOCK		0x00
-#define REG_IT_STATUS		0x04
-#define REG_MODE		0x08
-#define REG_STATUS		0x0C
-#define REG_CAMDATA		0x10
-#define REG_GPIO		0x14
-#define REG_PEAK_COUNTER	0x18
-
-/* CTRLCLOCK bit shifts */
-#define LCLK_EN			BIT(7)
-#define DPLL_EN			BIT(6)
-#define MCLK_EN			BIT(5)
-#define CAMEXCLK_EN		BIT(4)
-#define POLCLK			BIT(3)
-#define FOSCMOD_SHIFT		0
-#define FOSCMOD_MASK		(0x7 << FOSCMOD_SHIFT)
-#define FOSCMOD_12MHz		0x0
-#define FOSCMOD_6MHz		0x2
-#define FOSCMOD_9_6MHz		0x4
-#define FOSCMOD_24MHz		0x5
-#define FOSCMOD_8MHz		0x6
-
-/* IT_STATUS bit shifts */
-#define DATA_TRANSFER		BIT(5)
-#define FIFO_FULL		BIT(4)
-#define H_DOWN			BIT(3)
-#define H_UP			BIT(2)
-#define V_DOWN			BIT(1)
-#define V_UP			BIT(0)
-
-/* MODE bit shifts */
-#define RAZ_FIFO		BIT(18)
-#define EN_FIFO_FULL		BIT(17)
-#define EN_NIRQ			BIT(16)
-#define THRESHOLD_SHIFT		9
-#define THRESHOLD_MASK		(0x7f << THRESHOLD_SHIFT)
-#define DMA			BIT(8)
-#define EN_H_DOWN		BIT(7)
-#define EN_H_UP			BIT(6)
-#define EN_V_DOWN		BIT(5)
-#define EN_V_UP			BIT(4)
-#define ORDERCAMD		BIT(3)
-
-#define IRQ_MASK		(EN_V_UP | EN_V_DOWN | EN_H_UP | EN_H_DOWN | \
-				 EN_NIRQ | EN_FIFO_FULL)
-
-/* STATUS bit shifts */
-#define HSTATUS			BIT(1)
-#define VSTATUS			BIT(0)
-
-/* GPIO bit shifts */
-#define CAM_RST			BIT(0)
-
-/* end of OMAP1 Camera Interface registers */
-
-
-#define SOCAM_BUS_FLAGS	(V4L2_MBUS_MASTER | \
-			V4L2_MBUS_HSYNC_ACTIVE_HIGH | V4L2_MBUS_VSYNC_ACTIVE_HIGH | \
-			V4L2_MBUS_PCLK_SAMPLE_RISING | V4L2_MBUS_PCLK_SAMPLE_FALLING | \
-			V4L2_MBUS_DATA_ACTIVE_HIGH)
-
-
-#define FIFO_SIZE		((THRESHOLD_MASK >> THRESHOLD_SHIFT) + 1)
-#define FIFO_SHIFT		__fls(FIFO_SIZE)
-
-#define DMA_BURST_SHIFT		(1 + OMAP_DMA_DATA_BURST_4)
-#define DMA_BURST_SIZE		(1 << DMA_BURST_SHIFT)
-
-#define DMA_ELEMENT_SHIFT	OMAP_DMA_DATA_TYPE_S32
-#define DMA_ELEMENT_SIZE	(1 << DMA_ELEMENT_SHIFT)
-
-#define DMA_FRAME_SHIFT_CONTIG	(FIFO_SHIFT - 1)
-#define DMA_FRAME_SHIFT_SG	DMA_BURST_SHIFT
-
-#define DMA_FRAME_SHIFT(x)	((x) == OMAP1_CAM_DMA_CONTIG ? \
-						DMA_FRAME_SHIFT_CONTIG : \
-						DMA_FRAME_SHIFT_SG)
-#define DMA_FRAME_SIZE(x)	(1 << DMA_FRAME_SHIFT(x))
-#define DMA_SYNC		OMAP_DMA_SYNC_FRAME
-#define THRESHOLD_LEVEL		DMA_FRAME_SIZE
-
-
-#define MAX_VIDEO_MEM		4	/* arbitrary video memory limit in MB */
-
-
-/*
- * Structures
- */
-
-/* buffer for one video frame */
-struct omap1_cam_buf {
-	struct videobuf_buffer		vb;
-	u32	code;
-	int				inwork;
-	struct scatterlist		*sgbuf;
-	int				sgcount;
-	int				bytes_left;
-	enum videobuf_state		result;
-};
-
-struct omap1_cam_dev {
-	struct soc_camera_host		soc_host;
-	struct clk			*clk;
-
-	unsigned int			irq;
-	void __iomem			*base;
-
-	int				dma_ch;
-
-	struct omap1_cam_platform_data	*pdata;
-	struct resource			*res;
-	unsigned long			pflags;
-	unsigned long			camexclk;
-
-	struct list_head		capture;
-
-	/* lock used to protect videobuf */
-	spinlock_t			lock;
-
-	/* Pointers to DMA buffers */
-	struct omap1_cam_buf		*active;
-	struct omap1_cam_buf		*ready;
-
-	enum omap1_cam_vb_mode		vb_mode;
-	int				(*mmap_mapper)(struct videobuf_queue *q,
-						struct videobuf_buffer *buf,
-						struct vm_area_struct *vma);
-
-	u32				reg_cache[0];
-};
-
-
-static void cam_write(struct omap1_cam_dev *pcdev, u16 reg, u32 val)
-{
-	pcdev->reg_cache[reg / sizeof(u32)] = val;
-	__raw_writel(val, pcdev->base + reg);
-}
-
-static u32 cam_read(struct omap1_cam_dev *pcdev, u16 reg, bool from_cache)
-{
-	return !from_cache ? __raw_readl(pcdev->base + reg) :
-			pcdev->reg_cache[reg / sizeof(u32)];
-}
-
-#define CAM_READ(pcdev, reg) \
-		cam_read(pcdev, REG_##reg, false)
-#define CAM_WRITE(pcdev, reg, val) \
-		cam_write(pcdev, REG_##reg, val)
-#define CAM_READ_CACHE(pcdev, reg) \
-		cam_read(pcdev, REG_##reg, true)
-
-/*
- *  Videobuf operations
- */
-static int omap1_videobuf_setup(struct videobuf_queue *vq, unsigned int *count,
-		unsigned int *size)
-{
-	struct soc_camera_device *icd = vq->priv_data;
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct omap1_cam_dev *pcdev = ici->priv;
-
-	*size = icd->sizeimage;
-
-	if (!*count || *count < OMAP1_CAMERA_MIN_BUF_COUNT(pcdev->vb_mode))
-		*count = OMAP1_CAMERA_MIN_BUF_COUNT(pcdev->vb_mode);
-
-	if (*size * *count > MAX_VIDEO_MEM * 1024 * 1024)
-		*count = (MAX_VIDEO_MEM * 1024 * 1024) / *size;
-
-	dev_dbg(icd->parent,
-			"%s: count=%d, size=%d\n", __func__, *count, *size);
-
-	return 0;
-}
-
-static void free_buffer(struct videobuf_queue *vq, struct omap1_cam_buf *buf,
-		enum omap1_cam_vb_mode vb_mode)
-{
-	struct videobuf_buffer *vb = &buf->vb;
-
-	BUG_ON(in_interrupt());
-
-	videobuf_waiton(vq, vb, 0, 0);
-
-	if (vb_mode == OMAP1_CAM_DMA_CONTIG) {
-		videobuf_dma_contig_free(vq, vb);
-	} else {
-		struct soc_camera_device *icd = vq->priv_data;
-		struct device *dev = icd->parent;
-		struct videobuf_dmabuf *dma = videobuf_to_dma(vb);
-
-		videobuf_dma_unmap(dev, dma);
-		videobuf_dma_free(dma);
-	}
-
-	vb->state = VIDEOBUF_NEEDS_INIT;
-}
-
-static int omap1_videobuf_prepare(struct videobuf_queue *vq,
-		struct videobuf_buffer *vb, enum v4l2_field field)
-{
-	struct soc_camera_device *icd = vq->priv_data;
-	struct omap1_cam_buf *buf = container_of(vb, struct omap1_cam_buf, vb);
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct omap1_cam_dev *pcdev = ici->priv;
-	int ret;
-
-	WARN_ON(!list_empty(&vb->queue));
-
-	BUG_ON(NULL == icd->current_fmt);
-
-	buf->inwork = 1;
-
-	if (buf->code != icd->current_fmt->code || vb->field != field ||
-			vb->width  != icd->user_width ||
-			vb->height != icd->user_height) {
-		buf->code  = icd->current_fmt->code;
-		vb->width  = icd->user_width;
-		vb->height = icd->user_height;
-		vb->field  = field;
-		vb->state  = VIDEOBUF_NEEDS_INIT;
-	}
-
-	vb->size = icd->sizeimage;
-
-	if (vb->baddr && vb->bsize < vb->size) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (vb->state == VIDEOBUF_NEEDS_INIT) {
-		ret = videobuf_iolock(vq, vb, NULL);
-		if (ret)
-			goto fail;
-
-		vb->state = VIDEOBUF_PREPARED;
-	}
-	buf->inwork = 0;
-
-	return 0;
-fail:
-	free_buffer(vq, buf, pcdev->vb_mode);
-out:
-	buf->inwork = 0;
-	return ret;
-}
-
-static void set_dma_dest_params(int dma_ch, struct omap1_cam_buf *buf,
-		enum omap1_cam_vb_mode vb_mode)
-{
-	dma_addr_t dma_addr;
-	unsigned int block_size;
-
-	if (vb_mode == OMAP1_CAM_DMA_CONTIG) {
-		dma_addr = videobuf_to_dma_contig(&buf->vb);
-		block_size = buf->vb.size;
-	} else {
-		if (WARN_ON(!buf->sgbuf)) {
-			buf->result = VIDEOBUF_ERROR;
-			return;
-		}
-		dma_addr = sg_dma_address(buf->sgbuf);
-		if (WARN_ON(!dma_addr)) {
-			buf->sgbuf = NULL;
-			buf->result = VIDEOBUF_ERROR;
-			return;
-		}
-		block_size = sg_dma_len(buf->sgbuf);
-		if (WARN_ON(!block_size)) {
-			buf->sgbuf = NULL;
-			buf->result = VIDEOBUF_ERROR;
-			return;
-		}
-		if (unlikely(buf->bytes_left < block_size))
-			block_size = buf->bytes_left;
-		if (WARN_ON(dma_addr & (DMA_FRAME_SIZE(vb_mode) *
-				DMA_ELEMENT_SIZE - 1))) {
-			dma_addr = ALIGN(dma_addr, DMA_FRAME_SIZE(vb_mode) *
-					DMA_ELEMENT_SIZE);
-			block_size &= ~(DMA_FRAME_SIZE(vb_mode) *
-					DMA_ELEMENT_SIZE - 1);
-		}
-		buf->bytes_left -= block_size;
-		buf->sgcount++;
-	}
-
-	omap_set_dma_dest_params(dma_ch,
-		OMAP_DMA_PORT_EMIFF, OMAP_DMA_AMODE_POST_INC, dma_addr, 0, 0);
-	omap_set_dma_transfer_params(dma_ch,
-		OMAP_DMA_DATA_TYPE_S32, DMA_FRAME_SIZE(vb_mode),
-		block_size >> (DMA_FRAME_SHIFT(vb_mode) + DMA_ELEMENT_SHIFT),
-		DMA_SYNC, 0, 0);
-}
-
-static struct omap1_cam_buf *prepare_next_vb(struct omap1_cam_dev *pcdev)
-{
-	struct omap1_cam_buf *buf;
-
-	/*
-	 * If there is already a buffer pointed out by the pcdev->ready,
-	 * (re)use it, otherwise try to fetch and configure a new one.
-	 */
-	buf = pcdev->ready;
-	if (!buf) {
-		if (list_empty(&pcdev->capture))
-			return buf;
-		buf = list_entry(pcdev->capture.next,
-				struct omap1_cam_buf, vb.queue);
-		buf->vb.state = VIDEOBUF_ACTIVE;
-		pcdev->ready = buf;
-		list_del_init(&buf->vb.queue);
-	}
-
-	if (pcdev->vb_mode == OMAP1_CAM_DMA_CONTIG) {
-		/*
-		 * In CONTIG mode, we can safely enter next buffer parameters
-		 * into the DMA programming register set after the DMA
-		 * has already been activated on the previous buffer
-		 */
-		set_dma_dest_params(pcdev->dma_ch, buf, pcdev->vb_mode);
-	} else {
-		/*
-		 * In SG mode, the above is not safe since there are probably
-		 * a bunch of sgbufs from previous sglist still pending.
-		 * Instead, mark the sglist fresh for the upcoming
-		 * try_next_sgbuf().
-		 */
-		buf->sgbuf = NULL;
-	}
-
-	return buf;
-}
-
-static struct scatterlist *try_next_sgbuf(int dma_ch, struct omap1_cam_buf *buf)
-{
-	struct scatterlist *sgbuf;
-
-	if (likely(buf->sgbuf)) {
-		/* current sglist is active */
-		if (unlikely(!buf->bytes_left)) {
-			/* indicate sglist complete */
-			sgbuf = NULL;
-		} else {
-			/* process next sgbuf */
-			sgbuf = sg_next(buf->sgbuf);
-			if (WARN_ON(!sgbuf)) {
-				buf->result = VIDEOBUF_ERROR;
-			} else if (WARN_ON(!sg_dma_len(sgbuf))) {
-				sgbuf = NULL;
-				buf->result = VIDEOBUF_ERROR;
-			}
-		}
-		buf->sgbuf = sgbuf;
-	} else {
-		/* sglist is fresh, initialize it before using */
-		struct videobuf_dmabuf *dma = videobuf_to_dma(&buf->vb);
-
-		sgbuf = dma->sglist;
-		if (!(WARN_ON(!sgbuf))) {
-			buf->sgbuf = sgbuf;
-			buf->sgcount = 0;
-			buf->bytes_left = buf->vb.size;
-			buf->result = VIDEOBUF_DONE;
-		}
-	}
-	if (sgbuf)
-		/*
-		 * Put our next sgbuf parameters (address, size)
-		 * into the DMA programming register set.
-		 */
-		set_dma_dest_params(dma_ch, buf, OMAP1_CAM_DMA_SG);
-
-	return sgbuf;
-}
-
-static void start_capture(struct omap1_cam_dev *pcdev)
-{
-	struct omap1_cam_buf *buf = pcdev->active;
-	u32 ctrlclock = CAM_READ_CACHE(pcdev, CTRLCLOCK);
-	u32 mode = CAM_READ_CACHE(pcdev, MODE) & ~EN_V_DOWN;
-
-	if (WARN_ON(!buf))
-		return;
-
-	/*
-	 * Enable start of frame interrupt, which we will use for activating
-	 * our end of frame watchdog when capture actually starts.
-	 */
-	mode |= EN_V_UP;
-
-	if (unlikely(ctrlclock & LCLK_EN))
-		/* stop pixel clock before FIFO reset */
-		CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock & ~LCLK_EN);
-	/* reset FIFO */
-	CAM_WRITE(pcdev, MODE, mode | RAZ_FIFO);
-
-	omap_start_dma(pcdev->dma_ch);
-
-	if (pcdev->vb_mode == OMAP1_CAM_DMA_SG) {
-		/*
-		 * In SG mode, it's a good moment for fetching next sgbuf
-		 * from the current sglist and, if available, already putting
-		 * its parameters into the DMA programming register set.
-		 */
-		try_next_sgbuf(pcdev->dma_ch, buf);
-	}
-
-	/* (re)enable pixel clock */
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock | LCLK_EN);
-	/* release FIFO reset */
-	CAM_WRITE(pcdev, MODE, mode);
-}
-
-static void suspend_capture(struct omap1_cam_dev *pcdev)
-{
-	u32 ctrlclock = CAM_READ_CACHE(pcdev, CTRLCLOCK);
-
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock & ~LCLK_EN);
-	omap_stop_dma(pcdev->dma_ch);
-}
-
-static void disable_capture(struct omap1_cam_dev *pcdev)
-{
-	u32 mode = CAM_READ_CACHE(pcdev, MODE);
-
-	CAM_WRITE(pcdev, MODE, mode & ~(IRQ_MASK | DMA));
-}
-
-static void omap1_videobuf_queue(struct videobuf_queue *vq,
-						struct videobuf_buffer *vb)
-{
-	struct soc_camera_device *icd = vq->priv_data;
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct omap1_cam_dev *pcdev = ici->priv;
-	struct omap1_cam_buf *buf;
-	u32 mode;
-
-	list_add_tail(&vb->queue, &pcdev->capture);
-	vb->state = VIDEOBUF_QUEUED;
-
-	if (pcdev->active) {
-		/*
-		 * Capture in progress, so don't touch pcdev->ready even if
-		 * empty. Since the transfer of the DMA programming register set
-		 * content to the DMA working register set is done automatically
-		 * by the DMA hardware, this can pretty well happen while we
-		 * are keeping the lock here. Leave fetching it from the queue
-		 * to be done when a next DMA interrupt occures instead.
-		 */
-		return;
-	}
-
-	WARN_ON(pcdev->ready);
-
-	buf = prepare_next_vb(pcdev);
-	if (WARN_ON(!buf))
-		return;
-
-	pcdev->active = buf;
-	pcdev->ready = NULL;
-
-	dev_dbg(icd->parent,
-		"%s: capture not active, setup FIFO, start DMA\n", __func__);
-	mode = CAM_READ_CACHE(pcdev, MODE) & ~THRESHOLD_MASK;
-	mode |= THRESHOLD_LEVEL(pcdev->vb_mode) << THRESHOLD_SHIFT;
-	CAM_WRITE(pcdev, MODE, mode | EN_FIFO_FULL | DMA);
-
-	if (pcdev->vb_mode == OMAP1_CAM_DMA_SG) {
-		/*
-		 * In SG mode, the above prepare_next_vb() didn't actually
-		 * put anything into the DMA programming register set,
-		 * so we have to do it now, before activating DMA.
-		 */
-		try_next_sgbuf(pcdev->dma_ch, buf);
-	}
-
-	start_capture(pcdev);
-}
-
-static void omap1_videobuf_release(struct videobuf_queue *vq,
-				 struct videobuf_buffer *vb)
-{
-	struct omap1_cam_buf *buf =
-			container_of(vb, struct omap1_cam_buf, vb);
-	struct soc_camera_device *icd = vq->priv_data;
-	struct device *dev = icd->parent;
-	struct soc_camera_host *ici = to_soc_camera_host(dev);
-	struct omap1_cam_dev *pcdev = ici->priv;
-
-	switch (vb->state) {
-	case VIDEOBUF_DONE:
-		dev_dbg(dev, "%s (done)\n", __func__);
-		break;
-	case VIDEOBUF_ACTIVE:
-		dev_dbg(dev, "%s (active)\n", __func__);
-		break;
-	case VIDEOBUF_QUEUED:
-		dev_dbg(dev, "%s (queued)\n", __func__);
-		break;
-	case VIDEOBUF_PREPARED:
-		dev_dbg(dev, "%s (prepared)\n", __func__);
-		break;
-	default:
-		dev_dbg(dev, "%s (unknown %d)\n", __func__, vb->state);
-		break;
-	}
-
-	free_buffer(vq, buf, pcdev->vb_mode);
-}
-
-static void videobuf_done(struct omap1_cam_dev *pcdev,
-		enum videobuf_state result)
-{
-	struct omap1_cam_buf *buf = pcdev->active;
-	struct videobuf_buffer *vb;
-	struct device *dev = pcdev->soc_host.icd->parent;
-
-	if (WARN_ON(!buf)) {
-		suspend_capture(pcdev);
-		disable_capture(pcdev);
-		return;
-	}
-
-	if (result == VIDEOBUF_ERROR)
-		suspend_capture(pcdev);
-
-	vb = &buf->vb;
-	if (waitqueue_active(&vb->done)) {
-		if (!pcdev->ready && result != VIDEOBUF_ERROR) {
-			/*
-			 * No next buffer has been entered into the DMA
-			 * programming register set on time (could be done only
-			 * while the previous DMA interurpt was processed, not
-			 * later), so the last DMA block, be it a whole buffer
-			 * if in CONTIG or its last sgbuf if in SG mode, is
-			 * about to be reused by the just autoreinitialized DMA
-			 * engine, and overwritten with next frame data. Best we
-			 * can do is stopping the capture as soon as possible,
-			 * hopefully before the next frame start.
-			 */
-			suspend_capture(pcdev);
-		}
-		vb->state = result;
-		v4l2_get_timestamp(&vb->ts);
-		if (result != VIDEOBUF_ERROR)
-			vb->field_count++;
-		wake_up(&vb->done);
-
-		/* shift in next buffer */
-		buf = pcdev->ready;
-		pcdev->active = buf;
-		pcdev->ready = NULL;
-
-		if (!buf) {
-			/*
-			 * No next buffer was ready on time (see above), so
-			 * indicate error condition to force capture restart or
-			 * stop, depending on next buffer already queued or not.
-			 */
-			result = VIDEOBUF_ERROR;
-			prepare_next_vb(pcdev);
-
-			buf = pcdev->ready;
-			pcdev->active = buf;
-			pcdev->ready = NULL;
-		}
-	} else if (pcdev->ready) {
-		/*
-		 * In both CONTIG and SG mode, the DMA engine has possibly
-		 * been already autoreinitialized with the preprogrammed
-		 * pcdev->ready buffer.  We can either accept this fact
-		 * and just swap the buffers, or provoke an error condition
-		 * and restart capture.  The former seems less intrusive.
-		 */
-		dev_dbg(dev, "%s: nobody waiting on videobuf, swap with next\n",
-				__func__);
-		pcdev->active = pcdev->ready;
-
-		if (pcdev->vb_mode == OMAP1_CAM_DMA_SG) {
-			/*
-			 * In SG mode, we have to make sure that the buffer we
-			 * are putting back into the pcdev->ready is marked
-			 * fresh.
-			 */
-			buf->sgbuf = NULL;
-		}
-		pcdev->ready = buf;
-
-		buf = pcdev->active;
-	} else {
-		/*
-		 * No next buffer has been entered into
-		 * the DMA programming register set on time.
-		 */
-		if (pcdev->vb_mode == OMAP1_CAM_DMA_CONTIG) {
-			/*
-			 * In CONTIG mode, the DMA engine has already been
-			 * reinitialized with the current buffer. Best we can do
-			 * is not touching it.
-			 */
-			dev_dbg(dev,
-				"%s: nobody waiting on videobuf, reuse it\n",
-				__func__);
-		} else {
-			/*
-			 * In SG mode, the DMA engine has just been
-			 * autoreinitialized with the last sgbuf from the
-			 * current list. Restart capture in order to transfer
-			 * next frame start into the first sgbuf, not the last
-			 * one.
-			 */
-			if (result != VIDEOBUF_ERROR) {
-				suspend_capture(pcdev);
-				result = VIDEOBUF_ERROR;
-			}
-		}
-	}
-
-	if (!buf) {
-		dev_dbg(dev, "%s: no more videobufs, stop capture\n", __func__);
-		disable_capture(pcdev);
-		return;
-	}
-
-	if (pcdev->vb_mode == OMAP1_CAM_DMA_CONTIG) {
-		/*
-		 * In CONTIG mode, the current buffer parameters had already
-		 * been entered into the DMA programming register set while the
-		 * buffer was fetched with prepare_next_vb(), they may have also
-		 * been transferred into the runtime set and already active if
-		 * the DMA still running.
-		 */
-	} else {
-		/* In SG mode, extra steps are required */
-		if (result == VIDEOBUF_ERROR)
-			/* make sure we (re)use sglist from start on error */
-			buf->sgbuf = NULL;
-
-		/*
-		 * In any case, enter the next sgbuf parameters into the DMA
-		 * programming register set.  They will be used either during
-		 * nearest DMA autoreinitialization or, in case of an error,
-		 * on DMA startup below.
-		 */
-		try_next_sgbuf(pcdev->dma_ch, buf);
-	}
-
-	if (result == VIDEOBUF_ERROR) {
-		dev_dbg(dev, "%s: videobuf error; reset FIFO, restart DMA\n",
-				__func__);
-		start_capture(pcdev);
-		/*
-		 * In SG mode, the above also resulted in the next sgbuf
-		 * parameters being entered into the DMA programming register
-		 * set, making them ready for next DMA autoreinitialization.
-		 */
-	}
-
-	/*
-	 * Finally, try fetching next buffer.
-	 * In CONTIG mode, it will also enter it into the DMA programming
-	 * register set, making it ready for next DMA autoreinitialization.
-	 */
-	prepare_next_vb(pcdev);
-}
-
-static void dma_isr(int channel, unsigned short status, void *data)
-{
-	struct omap1_cam_dev *pcdev = data;
-	struct omap1_cam_buf *buf = pcdev->active;
-	unsigned long flags;
-
-	spin_lock_irqsave(&pcdev->lock, flags);
-
-	if (WARN_ON(!buf)) {
-		suspend_capture(pcdev);
-		disable_capture(pcdev);
-		goto out;
-	}
-
-	if (pcdev->vb_mode == OMAP1_CAM_DMA_CONTIG) {
-		/*
-		 * In CONTIG mode, assume we have just managed to collect the
-		 * whole frame, hopefully before our end of frame watchdog is
-		 * triggered. Then, all we have to do is disabling the watchdog
-		 * for this frame, and calling videobuf_done() with success
-		 * indicated.
-		 */
-		CAM_WRITE(pcdev, MODE,
-				CAM_READ_CACHE(pcdev, MODE) & ~EN_V_DOWN);
-		videobuf_done(pcdev, VIDEOBUF_DONE);
-	} else {
-		/*
-		 * In SG mode, we have to process every sgbuf from the current
-		 * sglist, one after another.
-		 */
-		if (buf->sgbuf) {
-			/*
-			 * Current sglist not completed yet, try fetching next
-			 * sgbuf, hopefully putting it into the DMA programming
-			 * register set, making it ready for next DMA
-			 * autoreinitialization.
-			 */
-			try_next_sgbuf(pcdev->dma_ch, buf);
-			if (buf->sgbuf)
-				goto out;
-
-			/*
-			 * No more sgbufs left in the current sglist. This
-			 * doesn't mean that the whole videobuffer is already
-			 * complete, but only that the last sgbuf from the
-			 * current sglist is about to be filled. It will be
-			 * ready on next DMA interrupt, signalled with the
-			 * buf->sgbuf set back to NULL.
-			 */
-			if (buf->result != VIDEOBUF_ERROR) {
-				/*
-				 * Video frame collected without errors so far,
-				 * we can prepare for collecting a next one
-				 * as soon as DMA gets autoreinitialized
-				 * after the current (last) sgbuf is completed.
-				 */
-				buf = prepare_next_vb(pcdev);
-				if (!buf)
-					goto out;
-
-				try_next_sgbuf(pcdev->dma_ch, buf);
-				goto out;
-			}
-		}
-		/* end of videobuf */
-		videobuf_done(pcdev, buf->result);
-	}
-
-out:
-	spin_unlock_irqrestore(&pcdev->lock, flags);
-}
-
-static irqreturn_t cam_isr(int irq, void *data)
-{
-	struct omap1_cam_dev *pcdev = data;
-	struct device *dev = pcdev->soc_host.icd->parent;
-	struct omap1_cam_buf *buf = pcdev->active;
-	u32 it_status;
-	unsigned long flags;
-
-	it_status = CAM_READ(pcdev, IT_STATUS);
-	if (!it_status)
-		return IRQ_NONE;
-
-	spin_lock_irqsave(&pcdev->lock, flags);
-
-	if (WARN_ON(!buf)) {
-		dev_warn(dev, "%s: unhandled camera interrupt, status == %#x\n",
-			 __func__, it_status);
-		suspend_capture(pcdev);
-		disable_capture(pcdev);
-		goto out;
-	}
-
-	if (unlikely(it_status & FIFO_FULL)) {
-		dev_warn(dev, "%s: FIFO overflow\n", __func__);
-
-	} else if (it_status & V_DOWN) {
-		/* end of video frame watchdog */
-		if (pcdev->vb_mode == OMAP1_CAM_DMA_CONTIG) {
-			/*
-			 * In CONTIG mode, the watchdog is disabled with
-			 * successful DMA end of block interrupt, and reenabled
-			 * on next frame start. If we get here, there is nothing
-			 * to check, we must be out of sync.
-			 */
-		} else {
-			if (buf->sgcount == 2) {
-				/*
-				 * If exactly 2 sgbufs from the next sglist have
-				 * been programmed into the DMA engine (the
-				 * first one already transferred into the DMA
-				 * runtime register set, the second one still
-				 * in the programming set), then we are in sync.
-				 */
-				goto out;
-			}
-		}
-		dev_notice(dev, "%s: unexpected end of video frame\n",
-				__func__);
-
-	} else if (it_status & V_UP) {
-		u32 mode;
-
-		if (pcdev->vb_mode == OMAP1_CAM_DMA_CONTIG) {
-			/*
-			 * In CONTIG mode, we need this interrupt every frame
-			 * in oredr to reenable our end of frame watchdog.
-			 */
-			mode = CAM_READ_CACHE(pcdev, MODE);
-		} else {
-			/*
-			 * In SG mode, the below enabled end of frame watchdog
-			 * is kept on permanently, so we can turn this one shot
-			 * setup off.
-			 */
-			mode = CAM_READ_CACHE(pcdev, MODE) & ~EN_V_UP;
-		}
-
-		if (!(mode & EN_V_DOWN)) {
-			/* (re)enable end of frame watchdog interrupt */
-			mode |= EN_V_DOWN;
-		}
-		CAM_WRITE(pcdev, MODE, mode);
-		goto out;
-
-	} else {
-		dev_warn(dev, "%s: unhandled camera interrupt, status == %#x\n",
-				__func__, it_status);
-		goto out;
-	}
-
-	videobuf_done(pcdev, VIDEOBUF_ERROR);
-out:
-	spin_unlock_irqrestore(&pcdev->lock, flags);
-	return IRQ_HANDLED;
-}
-
-static struct videobuf_queue_ops omap1_videobuf_ops = {
-	.buf_setup	= omap1_videobuf_setup,
-	.buf_prepare	= omap1_videobuf_prepare,
-	.buf_queue	= omap1_videobuf_queue,
-	.buf_release	= omap1_videobuf_release,
-};
-
-
-/*
- * SOC Camera host operations
- */
-
-static void sensor_reset(struct omap1_cam_dev *pcdev, bool reset)
-{
-	/* apply/release camera sensor reset if requested by platform data */
-	if (pcdev->pflags & OMAP1_CAMERA_RST_HIGH)
-		CAM_WRITE(pcdev, GPIO, reset);
-	else if (pcdev->pflags & OMAP1_CAMERA_RST_LOW)
-		CAM_WRITE(pcdev, GPIO, !reset);
-}
-
-static int omap1_cam_add_device(struct soc_camera_device *icd)
-{
-	dev_dbg(icd->parent, "OMAP1 Camera driver attached to camera %d\n",
-			icd->devnum);
-
-	return 0;
-}
-
-static void omap1_cam_remove_device(struct soc_camera_device *icd)
-{
-	dev_dbg(icd->parent,
-		"OMAP1 Camera driver detached from camera %d\n", icd->devnum);
-}
-
-/*
- * The following two functions absolutely depend on the fact, that
- * there can be only one camera on OMAP1 camera sensor interface
- */
-static int omap1_cam_clock_start(struct soc_camera_host *ici)
-{
-	struct omap1_cam_dev *pcdev = ici->priv;
-	u32 ctrlclock;
-
-	clk_enable(pcdev->clk);
-
-	/* setup sensor clock */
-	ctrlclock = CAM_READ(pcdev, CTRLCLOCK);
-	ctrlclock &= ~(CAMEXCLK_EN | MCLK_EN | DPLL_EN);
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock);
-
-	ctrlclock &= ~FOSCMOD_MASK;
-	switch (pcdev->camexclk) {
-	case 6000000:
-		ctrlclock |= CAMEXCLK_EN | FOSCMOD_6MHz;
-		break;
-	case 8000000:
-		ctrlclock |= CAMEXCLK_EN | FOSCMOD_8MHz | DPLL_EN;
-		break;
-	case 9600000:
-		ctrlclock |= CAMEXCLK_EN | FOSCMOD_9_6MHz | DPLL_EN;
-		break;
-	case 12000000:
-		ctrlclock |= CAMEXCLK_EN | FOSCMOD_12MHz;
-		break;
-	case 24000000:
-		ctrlclock |= CAMEXCLK_EN | FOSCMOD_24MHz | DPLL_EN;
-	default:
-		break;
-	}
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock & ~DPLL_EN);
-
-	/* enable internal clock */
-	ctrlclock |= MCLK_EN;
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock);
-
-	sensor_reset(pcdev, false);
-
-	return 0;
-}
-
-static void omap1_cam_clock_stop(struct soc_camera_host *ici)
-{
-	struct omap1_cam_dev *pcdev = ici->priv;
-	u32 ctrlclock;
-
-	suspend_capture(pcdev);
-	disable_capture(pcdev);
-
-	sensor_reset(pcdev, true);
-
-	/* disable and release system clocks */
-	ctrlclock = CAM_READ_CACHE(pcdev, CTRLCLOCK);
-	ctrlclock &= ~(MCLK_EN | DPLL_EN | CAMEXCLK_EN);
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock);
-
-	ctrlclock = (ctrlclock & ~FOSCMOD_MASK) | FOSCMOD_12MHz;
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock);
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock | MCLK_EN);
-
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock & ~MCLK_EN);
-
-	clk_disable(pcdev->clk);
-}
-
-/* Duplicate standard formats based on host capability of byte swapping */
-static const struct soc_mbus_lookup omap1_cam_formats[] = {
-{
-	.code = MEDIA_BUS_FMT_UYVY8_2X8,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_YUYV,
-		.name			= "YUYV",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-}, {
-	.code = MEDIA_BUS_FMT_VYUY8_2X8,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_YVYU,
-		.name			= "YVYU",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-}, {
-	.code = MEDIA_BUS_FMT_YUYV8_2X8,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_UYVY,
-		.name			= "UYVY",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-}, {
-	.code = MEDIA_BUS_FMT_YVYU8_2X8,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_VYUY,
-		.name			= "VYUY",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-}, {
-	.code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_RGB555,
-		.name			= "RGB555",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-}, {
-	.code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_RGB555X,
-		.name			= "RGB555X",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-}, {
-	.code = MEDIA_BUS_FMT_RGB565_2X8_BE,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_RGB565,
-		.name			= "RGB565",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-}, {
-	.code = MEDIA_BUS_FMT_RGB565_2X8_LE,
-	.fmt = {
-		.fourcc			= V4L2_PIX_FMT_RGB565X,
-		.name			= "RGB565X",
-		.bits_per_sample	= 8,
-		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
-		.order			= SOC_MBUS_ORDER_BE,
-		.layout			= SOC_MBUS_LAYOUT_PACKED,
-	},
-},
-};
-
-static int omap1_cam_get_formats(struct soc_camera_device *icd,
-		unsigned int idx, struct soc_camera_format_xlate *xlate)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct device *dev = icd->parent;
-	int formats = 0, ret;
-	struct v4l2_subdev_mbus_code_enum code = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-		.index = idx,
-	};
-	const struct soc_mbus_pixelfmt *fmt;
-
-	ret = v4l2_subdev_call(sd, pad, enum_mbus_code, NULL, &code);
-	if (ret < 0)
-		/* No more formats */
-		return 0;
-
-	fmt = soc_mbus_get_fmtdesc(code.code);
-	if (!fmt) {
-		dev_warn(dev, "%s: unsupported format code #%d: %d\n", __func__,
-				idx, code.code);
-		return 0;
-	}
-
-	/* Check support for the requested bits-per-sample */
-	if (fmt->bits_per_sample != 8)
-		return 0;
-
-	switch (code.code) {
-	case MEDIA_BUS_FMT_YUYV8_2X8:
-	case MEDIA_BUS_FMT_YVYU8_2X8:
-	case MEDIA_BUS_FMT_UYVY8_2X8:
-	case MEDIA_BUS_FMT_VYUY8_2X8:
-	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE:
-	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE:
-	case MEDIA_BUS_FMT_RGB565_2X8_BE:
-	case MEDIA_BUS_FMT_RGB565_2X8_LE:
-		formats++;
-		if (xlate) {
-			xlate->host_fmt	= soc_mbus_find_fmtdesc(code.code,
-						omap1_cam_formats,
-						ARRAY_SIZE(omap1_cam_formats));
-			xlate->code	= code.code;
-			xlate++;
-			dev_dbg(dev,
-				"%s: providing format %s as byte swapped code #%d\n",
-				__func__, xlate->host_fmt->name, code.code);
-		}
-	default:
-		if (xlate)
-			dev_dbg(dev,
-				"%s: providing format %s in pass-through mode\n",
-				__func__, fmt->name);
-	}
-	formats++;
-	if (xlate) {
-		xlate->host_fmt	= fmt;
-		xlate->code	= code.code;
-		xlate++;
-	}
-
-	return formats;
-}
-
-static bool is_dma_aligned(s32 bytes_per_line, unsigned int height,
-		enum omap1_cam_vb_mode vb_mode)
-{
-	int size = bytes_per_line * height;
-
-	return IS_ALIGNED(bytes_per_line, DMA_ELEMENT_SIZE) &&
-		IS_ALIGNED(size, DMA_FRAME_SIZE(vb_mode) * DMA_ELEMENT_SIZE);
-}
-
-static int dma_align(int *width, int *height,
-		const struct soc_mbus_pixelfmt *fmt,
-		enum omap1_cam_vb_mode vb_mode, bool enlarge)
-{
-	s32 bytes_per_line = soc_mbus_bytes_per_line(*width, fmt);
-
-	if (bytes_per_line < 0)
-		return bytes_per_line;
-
-	if (!is_dma_aligned(bytes_per_line, *height, vb_mode)) {
-		unsigned int pxalign = __fls(bytes_per_line / *width);
-		unsigned int salign  = DMA_FRAME_SHIFT(vb_mode) +
-				DMA_ELEMENT_SHIFT - pxalign;
-		unsigned int incr    = enlarge << salign;
-
-		v4l_bound_align_image(width, 1, *width + incr, 0,
-				height, 1, *height + incr, 0, salign);
-		return 0;
-	}
-	return 1;
-}
-
-#define subdev_call_with_sense(pcdev, dev, icd, sd, op, function, args...)		     \
-({										     \
-	struct soc_camera_sense sense = {					     \
-		.master_clock		= pcdev->camexclk,			     \
-		.pixel_clock_max	= 0,					     \
-	};									     \
-	int __ret;								     \
-										     \
-	if (pcdev->pdata)							     \
-		sense.pixel_clock_max = pcdev->pdata->lclk_khz_max * 1000;	     \
-	icd->sense = &sense;							     \
-	__ret = v4l2_subdev_call(sd, op, function, ##args);			     \
-	icd->sense = NULL;							     \
-										     \
-	if (sense.flags & SOCAM_SENSE_PCLK_CHANGED) {				     \
-		if (sense.pixel_clock > sense.pixel_clock_max) {		     \
-			dev_err(dev,						     \
-				"%s: pixel clock %lu set by the camera too high!\n", \
-				__func__, sense.pixel_clock);			     \
-			__ret = -EINVAL;					     \
-		}								     \
-	}									     \
-	__ret;									     \
-})
-
-static int set_format(struct omap1_cam_dev *pcdev, struct device *dev,
-		struct soc_camera_device *icd, struct v4l2_subdev *sd,
-		struct v4l2_subdev_format *format,
-		const struct soc_camera_format_xlate *xlate)
-{
-	s32 bytes_per_line;
-	struct v4l2_mbus_framefmt *mf = &format->format;
-	int ret = subdev_call_with_sense(pcdev, dev, icd, sd, pad, set_fmt, NULL, format);
-
-	if (ret < 0) {
-		dev_err(dev, "%s: set_fmt failed\n", __func__);
-		return ret;
-	}
-
-	if (mf->code != xlate->code) {
-		dev_err(dev, "%s: unexpected pixel code change\n", __func__);
-		return -EINVAL;
-	}
-
-	bytes_per_line = soc_mbus_bytes_per_line(mf->width, xlate->host_fmt);
-	if (bytes_per_line < 0) {
-		dev_err(dev, "%s: soc_mbus_bytes_per_line() failed\n",
-				__func__);
-		return bytes_per_line;
-	}
-
-	if (!is_dma_aligned(bytes_per_line, mf->height, pcdev->vb_mode)) {
-		dev_err(dev, "%s: resulting geometry %ux%u not DMA aligned\n",
-				__func__, mf->width, mf->height);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int omap1_cam_set_crop(struct soc_camera_device *icd,
-			       const struct v4l2_crop *crop)
-{
-	const struct v4l2_rect *rect = &crop->c;
-	const struct soc_camera_format_xlate *xlate = icd->current_fmt;
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct device *dev = icd->parent;
-	struct soc_camera_host *ici = to_soc_camera_host(dev);
-	struct omap1_cam_dev *pcdev = ici->priv;
-	struct v4l2_subdev_format fmt = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-	};
-	struct v4l2_mbus_framefmt *mf = &fmt.format;
-	int ret;
-
-	ret = subdev_call_with_sense(pcdev, dev, icd, sd, video, s_crop, crop);
-	if (ret < 0) {
-		dev_warn(dev, "%s: failed to crop to %ux%u@%u:%u\n", __func__,
-			 rect->width, rect->height, rect->left, rect->top);
-		return ret;
-	}
-
-	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt);
-	if (ret < 0) {
-		dev_warn(dev, "%s: failed to fetch current format\n", __func__);
-		return ret;
-	}
-
-	ret = dma_align(&mf->width, &mf->height, xlate->host_fmt, pcdev->vb_mode,
-			false);
-	if (ret < 0) {
-		dev_err(dev, "%s: failed to align %ux%u %s with DMA\n",
-				__func__, mf->width, mf->height,
-				xlate->host_fmt->name);
-		return ret;
-	}
-
-	if (!ret) {
-		/* sensor returned geometry not DMA aligned, trying to fix */
-		ret = set_format(pcdev, dev, icd, sd, &fmt, xlate);
-		if (ret < 0) {
-			dev_err(dev, "%s: failed to set format\n", __func__);
-			return ret;
-		}
-	}
-
-	icd->user_width	 = mf->width;
-	icd->user_height = mf->height;
-
-	return 0;
-}
-
-static int omap1_cam_set_fmt(struct soc_camera_device *icd,
-			      struct v4l2_format *f)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	const struct soc_camera_format_xlate *xlate;
-	struct device *dev = icd->parent;
-	struct soc_camera_host *ici = to_soc_camera_host(dev);
-	struct omap1_cam_dev *pcdev = ici->priv;
-	struct v4l2_pix_format *pix = &f->fmt.pix;
-	struct v4l2_subdev_format format = {
-		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-	};
-	struct v4l2_mbus_framefmt *mf = &format.format;
-	int ret;
-
-	xlate = soc_camera_xlate_by_fourcc(icd, pix->pixelformat);
-	if (!xlate) {
-		dev_warn(dev, "%s: format %#x not found\n", __func__,
-				pix->pixelformat);
-		return -EINVAL;
-	}
-
-	mf->width	= pix->width;
-	mf->height	= pix->height;
-	mf->field	= pix->field;
-	mf->colorspace	= pix->colorspace;
-	mf->code	= xlate->code;
-
-	ret = dma_align(&mf->width, &mf->height, xlate->host_fmt, pcdev->vb_mode,
-			true);
-	if (ret < 0) {
-		dev_err(dev, "%s: failed to align %ux%u %s with DMA\n",
-				__func__, pix->width, pix->height,
-				xlate->host_fmt->name);
-		return ret;
-	}
-
-	ret = set_format(pcdev, dev, icd, sd, &format, xlate);
-	if (ret < 0) {
-		dev_err(dev, "%s: failed to set format\n", __func__);
-		return ret;
-	}
-
-	pix->width	 = mf->width;
-	pix->height	 = mf->height;
-	pix->field	 = mf->field;
-	pix->colorspace  = mf->colorspace;
-	icd->current_fmt = xlate;
-
-	return 0;
-}
-
-static int omap1_cam_try_fmt(struct soc_camera_device *icd,
-			      struct v4l2_format *f)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	const struct soc_camera_format_xlate *xlate;
-	struct v4l2_pix_format *pix = &f->fmt.pix;
-	struct v4l2_subdev_pad_config pad_cfg;
-	struct v4l2_subdev_format format = {
-		.which = V4L2_SUBDEV_FORMAT_TRY,
-	};
-	struct v4l2_mbus_framefmt *mf = &format.format;
-	int ret;
-	/* TODO: limit to mx1 hardware capabilities */
-
-	xlate = soc_camera_xlate_by_fourcc(icd, pix->pixelformat);
-	if (!xlate) {
-		dev_warn(icd->parent, "Format %#x not found\n",
-			 pix->pixelformat);
-		return -EINVAL;
-	}
-
-	mf->width	= pix->width;
-	mf->height	= pix->height;
-	mf->field	= pix->field;
-	mf->colorspace	= pix->colorspace;
-	mf->code	= xlate->code;
-
-	/* limit to sensor capabilities */
-	ret = v4l2_subdev_call(sd, pad, set_fmt, &pad_cfg, &format);
-	if (ret < 0)
-		return ret;
-
-	pix->width	= mf->width;
-	pix->height	= mf->height;
-	pix->field	= mf->field;
-	pix->colorspace	= mf->colorspace;
-
-	return 0;
-}
-
-static bool sg_mode;
-
-/*
- * Local mmap_mapper wrapper,
- * used for detecting videobuf-dma-contig buffer allocation failures
- * and switching to videobuf-dma-sg automatically for future attempts.
- */
-static int omap1_cam_mmap_mapper(struct videobuf_queue *q,
-				  struct videobuf_buffer *buf,
-				  struct vm_area_struct *vma)
-{
-	struct soc_camera_device *icd = q->priv_data;
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct omap1_cam_dev *pcdev = ici->priv;
-	int ret;
-
-	ret = pcdev->mmap_mapper(q, buf, vma);
-
-	if (ret == -ENOMEM)
-		sg_mode = true;
-
-	return ret;
-}
-
-static void omap1_cam_init_videobuf(struct videobuf_queue *q,
-				     struct soc_camera_device *icd)
-{
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
-	struct omap1_cam_dev *pcdev = ici->priv;
-
-	if (!sg_mode)
-		videobuf_queue_dma_contig_init(q, &omap1_videobuf_ops,
-				icd->parent, &pcdev->lock,
-				V4L2_BUF_TYPE_VIDEO_CAPTURE, V4L2_FIELD_NONE,
-				sizeof(struct omap1_cam_buf), icd, &ici->host_lock);
-	else
-		videobuf_queue_sg_init(q, &omap1_videobuf_ops,
-				icd->parent, &pcdev->lock,
-				V4L2_BUF_TYPE_VIDEO_CAPTURE, V4L2_FIELD_NONE,
-				sizeof(struct omap1_cam_buf), icd, &ici->host_lock);
-
-	/* use videobuf mode (auto)selected with the module parameter */
-	pcdev->vb_mode = sg_mode ? OMAP1_CAM_DMA_SG : OMAP1_CAM_DMA_CONTIG;
-
-	/*
-	 * Ensure we substitute the videobuf-dma-contig version of the
-	 * mmap_mapper() callback with our own wrapper, used for switching
-	 * automatically to videobuf-dma-sg on buffer allocation failure.
-	 */
-	if (!sg_mode && q->int_ops->mmap_mapper != omap1_cam_mmap_mapper) {
-		pcdev->mmap_mapper = q->int_ops->mmap_mapper;
-		q->int_ops->mmap_mapper = omap1_cam_mmap_mapper;
-	}
-}
-
-static int omap1_cam_reqbufs(struct soc_camera_device *icd,
-			      struct v4l2_requestbuffers *p)
-{
-	int i;
-
-	/*
-	 * This is for locking debugging only. I removed spinlocks and now I
-	 * check whether .prepare is ever called on a linked buffer, or whether
-	 * a dma IRQ can occur for an in-work or unlinked buffer. Until now
-	 * it hadn't triggered
-	 */
-	for (i = 0; i < p->count; i++) {
-		struct omap1_cam_buf *buf = container_of(icd->vb_vidq.bufs[i],
-						      struct omap1_cam_buf, vb);
-		buf->inwork = 0;
-		INIT_LIST_HEAD(&buf->vb.queue);
-	}
-
-	return 0;
-}
-
-static int omap1_cam_querycap(struct soc_camera_host *ici,
-			       struct v4l2_capability *cap)
-{
-	/* cap->name is set by the friendly caller:-> */
-	strlcpy(cap->card, "OMAP1 Camera", sizeof(cap->card));
-	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING;
-	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
-
-	return 0;
-}
-
-static int omap1_cam_set_bus_param(struct soc_camera_device *icd)
-{
-	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	struct device *dev = icd->parent;
-	struct soc_camera_host *ici = to_soc_camera_host(dev);
-	struct omap1_cam_dev *pcdev = ici->priv;
-	u32 pixfmt = icd->current_fmt->host_fmt->fourcc;
-	const struct soc_camera_format_xlate *xlate;
-	const struct soc_mbus_pixelfmt *fmt;
-	struct v4l2_mbus_config cfg = {.type = V4L2_MBUS_PARALLEL,};
-	unsigned long common_flags;
-	u32 ctrlclock, mode;
-	int ret;
-
-	ret = v4l2_subdev_call(sd, video, g_mbus_config, &cfg);
-	if (!ret) {
-		common_flags = soc_mbus_config_compatible(&cfg, SOCAM_BUS_FLAGS);
-		if (!common_flags) {
-			dev_warn(dev,
-				 "Flags incompatible: camera 0x%x, host 0x%x\n",
-				 cfg.flags, SOCAM_BUS_FLAGS);
-			return -EINVAL;
-		}
-	} else if (ret != -ENOIOCTLCMD) {
-		return ret;
-	} else {
-		common_flags = SOCAM_BUS_FLAGS;
-	}
-
-	/* Make choices, possibly based on platform configuration */
-	if ((common_flags & V4L2_MBUS_PCLK_SAMPLE_RISING) &&
-			(common_flags & V4L2_MBUS_PCLK_SAMPLE_FALLING)) {
-		if (!pcdev->pdata ||
-				pcdev->pdata->flags & OMAP1_CAMERA_LCLK_RISING)
-			common_flags &= ~V4L2_MBUS_PCLK_SAMPLE_FALLING;
-		else
-			common_flags &= ~V4L2_MBUS_PCLK_SAMPLE_RISING;
-	}
-
-	cfg.flags = common_flags;
-	ret = v4l2_subdev_call(sd, video, s_mbus_config, &cfg);
-	if (ret < 0 && ret != -ENOIOCTLCMD) {
-		dev_dbg(dev, "camera s_mbus_config(0x%lx) returned %d\n",
-			common_flags, ret);
-		return ret;
-	}
-
-	ctrlclock = CAM_READ_CACHE(pcdev, CTRLCLOCK);
-	if (ctrlclock & LCLK_EN)
-		CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock & ~LCLK_EN);
-
-	if (common_flags & V4L2_MBUS_PCLK_SAMPLE_RISING) {
-		dev_dbg(dev, "CTRLCLOCK_REG |= POLCLK\n");
-		ctrlclock |= POLCLK;
-	} else {
-		dev_dbg(dev, "CTRLCLOCK_REG &= ~POLCLK\n");
-		ctrlclock &= ~POLCLK;
-	}
-	CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock & ~LCLK_EN);
-
-	if (ctrlclock & LCLK_EN)
-		CAM_WRITE(pcdev, CTRLCLOCK, ctrlclock);
-
-	/* select bus endianness */
-	xlate = soc_camera_xlate_by_fourcc(icd, pixfmt);
-	fmt = xlate->host_fmt;
-
-	mode = CAM_READ(pcdev, MODE) & ~(RAZ_FIFO | IRQ_MASK | DMA);
-	if (fmt->order == SOC_MBUS_ORDER_LE) {
-		dev_dbg(dev, "MODE_REG &= ~ORDERCAMD\n");
-		CAM_WRITE(pcdev, MODE, mode & ~ORDERCAMD);
-	} else {
-		dev_dbg(dev, "MODE_REG |= ORDERCAMD\n");
-		CAM_WRITE(pcdev, MODE, mode | ORDERCAMD);
-	}
-
-	return 0;
-}
-
-static unsigned int omap1_cam_poll(struct file *file, poll_table *pt)
-{
-	struct soc_camera_device *icd = file->private_data;
-	struct omap1_cam_buf *buf;
-
-	buf = list_entry(icd->vb_vidq.stream.next, struct omap1_cam_buf,
-			 vb.stream);
-
-	poll_wait(file, &buf->vb.done, pt);
-
-	if (buf->vb.state == VIDEOBUF_DONE ||
-	    buf->vb.state == VIDEOBUF_ERROR)
-		return POLLIN | POLLRDNORM;
-
-	return 0;
-}
-
-static struct soc_camera_host_ops omap1_host_ops = {
-	.owner		= THIS_MODULE,
-	.add		= omap1_cam_add_device,
-	.remove		= omap1_cam_remove_device,
-	.clock_start	= omap1_cam_clock_start,
-	.clock_stop	= omap1_cam_clock_stop,
-	.get_formats	= omap1_cam_get_formats,
-	.set_crop	= omap1_cam_set_crop,
-	.set_fmt	= omap1_cam_set_fmt,
-	.try_fmt	= omap1_cam_try_fmt,
-	.init_videobuf	= omap1_cam_init_videobuf,
-	.reqbufs	= omap1_cam_reqbufs,
-	.querycap	= omap1_cam_querycap,
-	.set_bus_param	= omap1_cam_set_bus_param,
-	.poll		= omap1_cam_poll,
-};
-
-static int omap1_cam_probe(struct platform_device *pdev)
-{
-	struct omap1_cam_dev *pcdev;
-	struct resource *res;
-	struct clk *clk;
-	void __iomem *base;
-	unsigned int irq;
-	int err = 0;
-
-	irq = platform_get_irq(pdev, 0);
-	if ((int)irq <= 0) {
-		err = -ENODEV;
-		goto exit;
-	}
-
-	clk = devm_clk_get(&pdev->dev, "armper_ck");
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
-
-	pcdev = devm_kzalloc(&pdev->dev, sizeof(*pcdev) + resource_size(res),
-			     GFP_KERNEL);
-	if (!pcdev)
-		return -ENOMEM;
-
-	pcdev->clk = clk;
-
-	pcdev->pdata = pdev->dev.platform_data;
-	if (pcdev->pdata) {
-		pcdev->pflags = pcdev->pdata->flags;
-		pcdev->camexclk = pcdev->pdata->camexclk_khz * 1000;
-	}
-
-	switch (pcdev->camexclk) {
-	case 6000000:
-	case 8000000:
-	case 9600000:
-	case 12000000:
-	case 24000000:
-		break;
-	default:
-		/* pcdev->camexclk != 0 => pcdev->pdata != NULL */
-		dev_warn(&pdev->dev,
-				"Incorrect sensor clock frequency %ld kHz, "
-				"should be one of 0, 6, 8, 9.6, 12 or 24 MHz, "
-				"please correct your platform data\n",
-				pcdev->pdata->camexclk_khz);
-		pcdev->camexclk = 0;
-	case 0:
-		dev_info(&pdev->dev, "Not providing sensor clock\n");
-	}
-
-	INIT_LIST_HEAD(&pcdev->capture);
-	spin_lock_init(&pcdev->lock);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(base))
-		return PTR_ERR(base);
-
-	pcdev->irq = irq;
-	pcdev->base = base;
-
-	sensor_reset(pcdev, true);
-
-	err = omap_request_dma(OMAP_DMA_CAMERA_IF_RX, DRIVER_NAME,
-			dma_isr, (void *)pcdev, &pcdev->dma_ch);
-	if (err < 0) {
-		dev_err(&pdev->dev, "Can't request DMA for OMAP1 Camera\n");
-		return -EBUSY;
-	}
-	dev_dbg(&pdev->dev, "got DMA channel %d\n", pcdev->dma_ch);
-
-	/* preconfigure DMA */
-	omap_set_dma_src_params(pcdev->dma_ch, OMAP_DMA_PORT_TIPB,
-			OMAP_DMA_AMODE_CONSTANT, res->start + REG_CAMDATA,
-			0, 0);
-	omap_set_dma_dest_burst_mode(pcdev->dma_ch, OMAP_DMA_DATA_BURST_4);
-	/* setup DMA autoinitialization */
-	omap_dma_link_lch(pcdev->dma_ch, pcdev->dma_ch);
-
-	err = devm_request_irq(&pdev->dev, pcdev->irq, cam_isr, 0, DRIVER_NAME,
-			       pcdev);
-	if (err) {
-		dev_err(&pdev->dev, "Camera interrupt register failed\n");
-		goto exit_free_dma;
-	}
-
-	pcdev->soc_host.drv_name	= DRIVER_NAME;
-	pcdev->soc_host.ops		= &omap1_host_ops;
-	pcdev->soc_host.priv		= pcdev;
-	pcdev->soc_host.v4l2_dev.dev	= &pdev->dev;
-	pcdev->soc_host.nr		= pdev->id;
-
-	err = soc_camera_host_register(&pcdev->soc_host);
-	if (err)
-		return err;
-
-	dev_info(&pdev->dev, "OMAP1 Camera Interface driver loaded\n");
-
-	return 0;
-
-exit_free_dma:
-	omap_free_dma(pcdev->dma_ch);
-exit:
-	return err;
-}
-
-static int omap1_cam_remove(struct platform_device *pdev)
-{
-	struct soc_camera_host *soc_host = to_soc_camera_host(&pdev->dev);
-	struct omap1_cam_dev *pcdev = container_of(soc_host,
-					struct omap1_cam_dev, soc_host);
-
-	omap_free_dma(pcdev->dma_ch);
-
-	soc_camera_host_unregister(soc_host);
-
-	dev_info(&pdev->dev, "OMAP1 Camera Interface driver unloaded\n");
-
-	return 0;
-}
-
-static struct platform_driver omap1_cam_driver = {
-	.driver		= {
-		.name	= DRIVER_NAME,
-	},
-	.probe		= omap1_cam_probe,
-	.remove		= omap1_cam_remove,
-};
-
-module_platform_driver(omap1_cam_driver);
-
-module_param(sg_mode, bool, 0644);
-MODULE_PARM_DESC(sg_mode, "videobuf mode, 0: dma-contig (default), 1: dma-sg");
-
-MODULE_DESCRIPTION("OMAP1 Camera Interface driver");
-MODULE_AUTHOR("Janusz Krzysztofik <jkrzyszt@tis.icnet.pl>");
-MODULE_LICENSE("GPL v2");
-MODULE_VERSION(DRIVER_VERSION);
-MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index cf8da23558bb..90b7ff56722d 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -298,7 +298,7 @@ iss_video_check_format(struct iss_video *video, struct iss_video_fh *vfh)
 
 static int iss_video_queue_setup(struct vb2_queue *vq,
 				 unsigned int *count, unsigned int *num_planes,
-				 unsigned int sizes[], void *alloc_ctxs[])
+				 unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct iss_video_fh *vfh = vb2_get_drv_priv(vq);
 	struct iss_video *video = vfh->video;
@@ -310,8 +310,6 @@ static int iss_video_queue_setup(struct vb2_queue *vq,
 	if (sizes[0] == 0)
 		return -EINVAL;
 
-	alloc_ctxs[0] = video->alloc_ctx;
-
 	*count = min(*count, video->capture_mem / PAGE_ALIGN(sizes[0]));
 
 	return 0;
@@ -1017,13 +1015,6 @@ static int iss_video_open(struct file *file)
 		goto done;
 	}
 
-	video->alloc_ctx = vb2_dma_contig_init_ctx(video->iss->dev);
-	if (IS_ERR(video->alloc_ctx)) {
-		ret = PTR_ERR(video->alloc_ctx);
-		omap4iss_put(video->iss);
-		goto done;
-	}
-
 	q = &handle->queue;
 
 	q->type = video->type;
@@ -1033,6 +1024,7 @@ static int iss_video_open(struct file *file)
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->buf_struct_size = sizeof(struct iss_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->dev = video->iss->dev;
 
 	ret = vb2_queue_init(q);
 	if (ret) {
diff --git a/drivers/staging/media/omap4iss/iss_video.h b/drivers/staging/media/omap4iss/iss_video.h
index c8bd2958a3f8..d7e05d04512c 100644
--- a/drivers/staging/media/omap4iss/iss_video.h
+++ b/drivers/staging/media/omap4iss/iss_video.h
@@ -170,7 +170,6 @@ struct iss_video {
 	spinlock_t qlock;		/* protects dmaqueue and error */
 	struct list_head dmaqueue;
 	enum iss_video_dmaqueue_flags dmaqueue_flags;
-	struct vb2_alloc_ctx *alloc_ctx;
 
 	const struct iss_video_operations *ops;
 };
diff --git a/drivers/staging/media/pulse8-cec/Kconfig b/drivers/staging/media/pulse8-cec/Kconfig
new file mode 100644
index 000000000000..c6aa2d1c9df0
--- /dev/null
+++ b/drivers/staging/media/pulse8-cec/Kconfig
@@ -0,0 +1,10 @@
+config USB_PULSE8_CEC
+	tristate "Pulse Eight HDMI CEC"
+	depends on USB_ACM && MEDIA_CEC
+	select SERIO
+	select SERIO_SERPORT
+	---help---
+	  This is a cec driver for the Pulse Eight HDMI CEC device.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pulse8-cec.
diff --git a/drivers/staging/media/pulse8-cec/Makefile b/drivers/staging/media/pulse8-cec/Makefile
new file mode 100644
index 000000000000..9800690bc25a
--- /dev/null
+++ b/drivers/staging/media/pulse8-cec/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_USB_PULSE8_CEC) += pulse8-cec.o
diff --git a/drivers/staging/media/pulse8-cec/TODO b/drivers/staging/media/pulse8-cec/TODO
new file mode 100644
index 000000000000..fa6660245e5f
--- /dev/null
+++ b/drivers/staging/media/pulse8-cec/TODO
@@ -0,0 +1,52 @@
+This driver needs to mature a bit more and another round of
+code cleanups.
+
+Otherwise it looks to be in good shape. And of course the fact
+that the CEC framework is in staging at the moment also prevents
+this driver from being mainlined.
+
+Some notes:
+
+1) Regarding the "autonomous" mode of the Pulse-Eight: currently this
+is disabled, but the idea is that this allows basic functionality
+when the PC is off, and it can wake-up the PC through USB.
+
+To prevent the device to go into autonomous mode the driver would
+have to send MSGCODE_SET_CONTROLLED 1 and then send a ping every
+30 seconds (in practice once every 15 seconds would be good). When
+powering off or going to standby send MSGCODE_SET_CONTROLLED 0 to
+turn the autonomous mode back on.
+
+This needs to be implemented in the driver. Autonomous mode was
+added in firmware v2.
+
+2) Writing to the EEPROM can only be done once every 10 seconds.
+
+3) To use this driver you also need to patch the inputattach utility,
+this patch will be submitted once this driver is moved out of staging.
+
+diff -urN linuxconsoletools-1.4.9/utils/inputattach.c linuxconsoletools-1.4.9.new/utils/inputattach.c
+--- linuxconsoletools-1.4.9/utils/inputattach.c	2016-01-09 16:27:02.000000000 +0100
++++ linuxconsoletools-1.4.9.new/utils/inputattach.c	2016-03-20 11:35:31.707788967 +0100
+@@ -861,6 +861,9 @@
+ { "--wacom_iv",		"-wacom_iv",	"Wacom protocol IV tablet",
+ 	B9600, CS8 | CRTSCTS,
+ 	SERIO_WACOM_IV,		0x00,	0x00,	0,	wacom_iv_init },
++{ "--pulse8-cec",		"-pulse8-cec",	"Pulse Eight HDMI CEC dongle",
++	B9600, CS8,
++	SERIO_PULSE8_CEC,		0x00,	0x00,	0,	NULL },
+ { NULL, NULL, NULL, 0, 0, 0, 0, 0, 0, NULL }
+ };
+ 
+diff -urN linuxconsoletools-1.4.9/utils/serio-ids.h linuxconsoletools-1.4.9.new/utils/serio-ids.h
+--- linuxconsoletools-1.4.9/utils/serio-ids.h	2015-04-26 18:29:42.000000000 +0200
++++ linuxconsoletools-1.4.9.new/utils/serio-ids.h	2016-03-20 11:41:00.153558539 +0100
+@@ -131,5 +131,8 @@
+ #ifndef SERIO_EASYPEN
+ # define SERIO_EASYPEN		0x3f
+ #endif
++#ifndef SERIO_PULSE8_CEC
++# define SERIO_PULSE8_CEC	0x40
++#endif
+ 
+ #endif
diff --git a/drivers/staging/media/pulse8-cec/pulse8-cec.c b/drivers/staging/media/pulse8-cec/pulse8-cec.c
new file mode 100644
index 000000000000..94f8590492dc
--- /dev/null
+++ b/drivers/staging/media/pulse8-cec/pulse8-cec.c
@@ -0,0 +1,505 @@
+/*
+ * Pulse Eight HDMI CEC driver
+ *
+ * Copyright 2016 Hans Verkuil <hverkuil@xs4all.nl
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version of 2 of the License, or (at your
+ * option) any later version. See the file COPYING in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/completion.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/serio.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/delay.h>
+
+#include <media/cec.h>
+
+MODULE_AUTHOR("Hans Verkuil <hverkuil@xs4all.nl>");
+MODULE_DESCRIPTION("Pulse Eight HDMI CEC driver");
+MODULE_LICENSE("GPL");
+
+static int debug;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "debug level (0-1)");
+
+enum pulse8_msgcodes {
+	MSGCODE_NOTHING = 0,
+	MSGCODE_PING,
+	MSGCODE_TIMEOUT_ERROR,
+	MSGCODE_HIGH_ERROR,
+	MSGCODE_LOW_ERROR,
+	MSGCODE_FRAME_START,
+	MSGCODE_FRAME_DATA,
+	MSGCODE_RECEIVE_FAILED,
+	MSGCODE_COMMAND_ACCEPTED,	/* 0x08 */
+	MSGCODE_COMMAND_REJECTED,
+	MSGCODE_SET_ACK_MASK,
+	MSGCODE_TRANSMIT,
+	MSGCODE_TRANSMIT_EOM,
+	MSGCODE_TRANSMIT_IDLETIME,
+	MSGCODE_TRANSMIT_ACK_POLARITY,
+	MSGCODE_TRANSMIT_LINE_TIMEOUT,
+	MSGCODE_TRANSMIT_SUCCEEDED,	/* 0x10 */
+	MSGCODE_TRANSMIT_FAILED_LINE,
+	MSGCODE_TRANSMIT_FAILED_ACK,
+	MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA,
+	MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE,
+	MSGCODE_FIRMWARE_VERSION,
+	MSGCODE_START_BOOTLOADER,
+	MSGCODE_GET_BUILDDATE,
+	MSGCODE_SET_CONTROLLED,		/* 0x18 */
+	MSGCODE_GET_AUTO_ENABLED,
+	MSGCODE_SET_AUTO_ENABLED,
+	MSGCODE_GET_DEFAULT_LOGICAL_ADDRESS,
+	MSGCODE_SET_DEFAULT_LOGICAL_ADDRESS,
+	MSGCODE_GET_LOGICAL_ADDRESS_MASK,
+	MSGCODE_SET_LOGICAL_ADDRESS_MASK,
+	MSGCODE_GET_PHYSICAL_ADDRESS,
+	MSGCODE_SET_PHYSICAL_ADDRESS,	/* 0x20 */
+	MSGCODE_GET_DEVICE_TYPE,
+	MSGCODE_SET_DEVICE_TYPE,
+	MSGCODE_GET_HDMI_VERSION,
+	MSGCODE_SET_HDMI_VERSION,
+	MSGCODE_GET_OSD_NAME,
+	MSGCODE_SET_OSD_NAME,
+	MSGCODE_WRITE_EEPROM,
+	MSGCODE_GET_ADAPTER_TYPE,	/* 0x28 */
+	MSGCODE_SET_ACTIVE_SOURCE,
+
+	MSGCODE_FRAME_EOM = 0x80,
+	MSGCODE_FRAME_ACK = 0x40,
+};
+
+#define MSGSTART	0xff
+#define MSGEND		0xfe
+#define MSGESC		0xfd
+#define MSGOFFSET	3
+
+#define DATA_SIZE 256
+
+struct pulse8 {
+	struct device *dev;
+	struct serio *serio;
+	struct cec_adapter *adap;
+	struct completion cmd_done;
+	struct work_struct work;
+	struct cec_msg rx_msg;
+	u8 data[DATA_SIZE];
+	unsigned int len;
+	u8 buf[DATA_SIZE];
+	unsigned int idx;
+	bool escape;
+	bool started;
+};
+
+static void pulse8_irq_work_handler(struct work_struct *work)
+{
+	struct pulse8 *pulse8 =
+		container_of(work, struct pulse8, work);
+
+	switch (pulse8->data[0] & 0x3f) {
+	case MSGCODE_FRAME_DATA:
+		cec_received_msg(pulse8->adap, &pulse8->rx_msg);
+		break;
+	case MSGCODE_TRANSMIT_SUCCEEDED:
+		cec_transmit_done(pulse8->adap, CEC_TX_STATUS_OK,
+				  0, 0, 0, 0);
+		break;
+	case MSGCODE_TRANSMIT_FAILED_LINE:
+		cec_transmit_done(pulse8->adap, CEC_TX_STATUS_ARB_LOST,
+				  1, 0, 0, 0);
+		break;
+	case MSGCODE_TRANSMIT_FAILED_ACK:
+		cec_transmit_done(pulse8->adap, CEC_TX_STATUS_NACK,
+				  0, 1, 0, 0);
+		break;
+	case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA:
+	case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
+		cec_transmit_done(pulse8->adap, CEC_TX_STATUS_ERROR,
+				  0, 0, 0, 1);
+		break;
+	}
+}
+
+static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
+				    unsigned int flags)
+{
+	struct pulse8 *pulse8 = serio_get_drvdata(serio);
+
+	if (!pulse8->started && data != MSGSTART)
+		return IRQ_HANDLED;
+	if (data == MSGESC) {
+		pulse8->escape = true;
+		return IRQ_HANDLED;
+	}
+	if (pulse8->escape) {
+		data += MSGOFFSET;
+		pulse8->escape = false;
+	} else if (data == MSGEND) {
+		struct cec_msg *msg = &pulse8->rx_msg;
+
+		if (debug)
+			dev_info(pulse8->dev, "received: %*ph\n",
+				 pulse8->idx, pulse8->buf);
+		pulse8->data[0] = pulse8->buf[0];
+		switch (pulse8->buf[0] & 0x3f) {
+		case MSGCODE_FRAME_START:
+			msg->len = 1;
+			msg->msg[0] = pulse8->buf[1];
+			break;
+		case MSGCODE_FRAME_DATA:
+			if (msg->len == CEC_MAX_MSG_SIZE)
+				break;
+			msg->msg[msg->len++] = pulse8->buf[1];
+			if (pulse8->buf[0] & MSGCODE_FRAME_EOM)
+				schedule_work(&pulse8->work);
+			break;
+		case MSGCODE_TRANSMIT_SUCCEEDED:
+		case MSGCODE_TRANSMIT_FAILED_LINE:
+		case MSGCODE_TRANSMIT_FAILED_ACK:
+		case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA:
+		case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
+			schedule_work(&pulse8->work);
+			break;
+		case MSGCODE_TIMEOUT_ERROR:
+			break;
+		case MSGCODE_COMMAND_ACCEPTED:
+		case MSGCODE_COMMAND_REJECTED:
+		default:
+			if (pulse8->idx == 0)
+				break;
+			memcpy(pulse8->data, pulse8->buf, pulse8->idx);
+			pulse8->len = pulse8->idx;
+			complete(&pulse8->cmd_done);
+			break;
+		}
+		pulse8->idx = 0;
+		pulse8->started = false;
+		return IRQ_HANDLED;
+	} else if (data == MSGSTART) {
+		pulse8->idx = 0;
+		pulse8->started = true;
+		return IRQ_HANDLED;
+	}
+
+	if (pulse8->idx >= DATA_SIZE) {
+		dev_dbg(pulse8->dev,
+			"throwing away %d bytes of garbage\n", pulse8->idx);
+		pulse8->idx = 0;
+	}
+	pulse8->buf[pulse8->idx++] = data;
+	return IRQ_HANDLED;
+}
+
+static void pulse8_disconnect(struct serio *serio)
+{
+	struct pulse8 *pulse8 = serio_get_drvdata(serio);
+
+	cec_unregister_adapter(pulse8->adap);
+	dev_info(&serio->dev, "disconnected\n");
+	serio_close(serio);
+	serio_set_drvdata(serio, NULL);
+	kfree(pulse8);
+}
+
+static int pulse8_send(struct serio *serio, const u8 *command, u8 cmd_len)
+{
+	int err = 0;
+
+	err = serio_write(serio, MSGSTART);
+	if (err)
+		return err;
+	for (; !err && cmd_len; command++, cmd_len--) {
+		if (*command >= MSGESC) {
+			err = serio_write(serio, MSGESC);
+			if (!err)
+				err = serio_write(serio, *command - MSGOFFSET);
+		} else {
+			err = serio_write(serio, *command);
+		}
+	}
+	if (!err)
+		err = serio_write(serio, 0xfe);
+
+	return err;
+}
+
+static int pulse8_send_and_wait(struct pulse8 *pulse8,
+				const u8 *cmd, u8 cmd_len, u8 response, u8 size)
+{
+	int err;
+
+	/*dev_info(pulse8->dev, "transmit: %*ph\n", cmd_len, cmd);*/
+	init_completion(&pulse8->cmd_done);
+
+	err = pulse8_send(pulse8->serio, cmd, cmd_len);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&pulse8->cmd_done, HZ))
+		return -ETIMEDOUT;
+	if ((pulse8->data[0] & 0x3f) == MSGCODE_COMMAND_REJECTED &&
+	    cmd[0] != MSGCODE_SET_CONTROLLED &&
+	    cmd[0] != MSGCODE_SET_AUTO_ENABLED &&
+	    cmd[0] != MSGCODE_GET_BUILDDATE) {
+		u8 cmd_sc[2];
+
+		cmd_sc[0] = MSGCODE_SET_CONTROLLED;
+		cmd_sc[1] = 1;
+		err = pulse8_send_and_wait(pulse8, cmd_sc, 2,
+					   MSGCODE_COMMAND_ACCEPTED, 1);
+		if (err)
+			return err;
+		init_completion(&pulse8->cmd_done);
+
+		err = pulse8_send(pulse8->serio, cmd, cmd_len);
+		if (err)
+			return err;
+
+		if (!wait_for_completion_timeout(&pulse8->cmd_done, HZ))
+			return -ETIMEDOUT;
+	}
+	if (response &&
+	    ((pulse8->data[0] & 0x3f) != response || pulse8->len < size + 1)) {
+		dev_info(pulse8->dev, "transmit: failed %02x\n",
+			 pulse8->data[0] & 0x3f);
+		return -EIO;
+	}
+	return 0;
+}
+
+static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio)
+{
+	u8 *data = pulse8->data + 1;
+	unsigned int count = 0;
+	unsigned int vers = 0;
+	u8 cmd[2];
+	int err;
+
+	cmd[0] = MSGCODE_PING;
+	err = pulse8_send_and_wait(pulse8, cmd, 1,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
+	cmd[0] = MSGCODE_FIRMWARE_VERSION;
+	if (!err)
+		err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 2);
+	if (err)
+		return err;
+
+	vers = (data[0] << 8) | data[1];
+
+	dev_info(pulse8->dev, "Firmware version %04x\n", vers);
+	if (vers < 2)
+		return 0;
+
+	cmd[0] = MSGCODE_GET_BUILDDATE;
+	if (!err)
+		err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 4);
+	if (!err) {
+		time_t date = (data[0] << 24) | (data[1] << 16) |
+			(data[2] << 8) | data[3];
+		struct tm tm;
+
+		time_to_tm(date, 0, &tm);
+
+		dev_info(pulse8->dev, "Firmware build date %04ld.%02d.%02d %02d:%02d:%02d\n",
+			 tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+			 tm.tm_hour, tm.tm_min, tm.tm_sec);
+	}
+
+	do {
+		if (count)
+			msleep(500);
+		cmd[0] = MSGCODE_SET_AUTO_ENABLED;
+		cmd[1] = 0;
+		err = pulse8_send_and_wait(pulse8, cmd, 2,
+					   MSGCODE_COMMAND_ACCEPTED, 1);
+		if (err && count == 0) {
+			dev_info(pulse8->dev, "No Auto Enabled supported\n");
+			return 0;
+		}
+
+		cmd[0] = MSGCODE_GET_AUTO_ENABLED;
+		if (!err)
+			err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1);
+		if (!err && !data[0]) {
+			cmd[0] = MSGCODE_WRITE_EEPROM;
+			err = pulse8_send_and_wait(pulse8, cmd, 1,
+						   MSGCODE_COMMAND_ACCEPTED, 1);
+			cmd[0] = MSGCODE_GET_AUTO_ENABLED;
+			if (!err)
+				err = pulse8_send_and_wait(pulse8, cmd, 1,
+							   cmd[0], 1);
+		}
+	} while (!err && data[0] && count++ < 5);
+
+	if (!err && data[0])
+		err = -EIO;
+
+	return err;
+}
+
+static int pulse8_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct pulse8 *pulse8 = adap->priv;
+	u8 cmd[16];
+	int err;
+
+	cmd[0] = MSGCODE_SET_CONTROLLED;
+	cmd[1] = enable;
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 1);
+	return enable ? err : 0;
+}
+
+static int pulse8_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
+{
+	struct pulse8 *pulse8 = adap->priv;
+	u16 mask = 0;
+	u8 cmd[3];
+	int err;
+
+	if (log_addr != CEC_LOG_ADDR_INVALID)
+		mask = 1 << log_addr;
+	cmd[0] = MSGCODE_SET_ACK_MASK;
+	cmd[1] = mask >> 8;
+	cmd[2] = mask & 0xff;
+	err = pulse8_send_and_wait(pulse8, cmd, 3,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
+	if (mask == 0)
+		return 0;
+	return err;
+}
+
+static int pulse8_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				    u32 signal_free_time, struct cec_msg *msg)
+{
+	struct pulse8 *pulse8 = adap->priv;
+	u8 cmd[2];
+	unsigned int i;
+	int err;
+
+	cmd[0] = MSGCODE_TRANSMIT_IDLETIME;
+	cmd[1] = 3;
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 1);
+	cmd[0] = MSGCODE_TRANSMIT_ACK_POLARITY;
+	cmd[1] = cec_msg_is_broadcast(msg);
+	if (!err)
+		err = pulse8_send_and_wait(pulse8, cmd, 2,
+					   MSGCODE_COMMAND_ACCEPTED, 1);
+	cmd[0] = msg->len == 1 ? MSGCODE_TRANSMIT_EOM : MSGCODE_TRANSMIT;
+	cmd[1] = msg->msg[0];
+	if (!err)
+		err = pulse8_send_and_wait(pulse8, cmd, 2,
+					   MSGCODE_COMMAND_ACCEPTED, 1);
+	if (!err && msg->len > 1) {
+		cmd[0] = msg->len == 2 ? MSGCODE_TRANSMIT_EOM :
+					 MSGCODE_TRANSMIT;
+		cmd[1] = msg->msg[1];
+		err = pulse8_send_and_wait(pulse8, cmd, 2,
+					   MSGCODE_COMMAND_ACCEPTED, 1);
+		for (i = 0; !err && i + 2 < msg->len; i++) {
+			cmd[0] = (i + 2 == msg->len - 1) ?
+				MSGCODE_TRANSMIT_EOM : MSGCODE_TRANSMIT;
+			cmd[1] = msg->msg[i + 2];
+			err = pulse8_send_and_wait(pulse8, cmd, 2,
+						   MSGCODE_COMMAND_ACCEPTED, 1);
+		}
+	}
+
+	return err;
+}
+
+static int pulse8_received(struct cec_adapter *adap, struct cec_msg *msg)
+{
+	return -ENOMSG;
+}
+
+static const struct cec_adap_ops pulse8_cec_adap_ops = {
+	.adap_enable = pulse8_cec_adap_enable,
+	.adap_log_addr = pulse8_cec_adap_log_addr,
+	.adap_transmit = pulse8_cec_adap_transmit,
+	.received = pulse8_received,
+};
+
+static int pulse8_connect(struct serio *serio, struct serio_driver *drv)
+{
+	u32 caps = CEC_CAP_TRANSMIT | CEC_CAP_LOG_ADDRS | CEC_CAP_PHYS_ADDR |
+		CEC_CAP_PASSTHROUGH | CEC_CAP_RC | CEC_CAP_MONITOR_ALL;
+	struct pulse8 *pulse8;
+	int err = -ENOMEM;
+
+	pulse8 = kzalloc(sizeof(*pulse8), GFP_KERNEL);
+
+	if (!pulse8)
+		return -ENOMEM;
+
+	pulse8->serio = serio;
+	pulse8->adap = cec_allocate_adapter(&pulse8_cec_adap_ops, pulse8,
+		"HDMI CEC", caps, 1, &serio->dev);
+	err = PTR_ERR_OR_ZERO(pulse8->adap);
+	if (err < 0)
+		goto free_device;
+
+	pulse8->dev = &serio->dev;
+	serio_set_drvdata(serio, pulse8);
+	INIT_WORK(&pulse8->work, pulse8_irq_work_handler);
+
+	err = serio_open(serio, drv);
+	if (err)
+		goto delete_adap;
+
+	err = pulse8_setup(pulse8, serio);
+	if (err)
+		goto close_serio;
+
+	err = cec_register_adapter(pulse8->adap);
+	if (err < 0)
+		goto close_serio;
+
+	pulse8->dev = &pulse8->adap->devnode.dev;
+	return 0;
+
+close_serio:
+	serio_close(serio);
+delete_adap:
+	cec_delete_adapter(pulse8->adap);
+	serio_set_drvdata(serio, NULL);
+free_device:
+	kfree(pulse8);
+	return err;
+}
+
+static struct serio_device_id pulse8_serio_ids[] = {
+	{
+		.type	= SERIO_RS232,
+		.proto	= SERIO_PULSE8_CEC,
+		.id	= SERIO_ANY,
+		.extra	= SERIO_ANY,
+	},
+	{ 0 }
+};
+
+MODULE_DEVICE_TABLE(serio, pulse8_serio_ids);
+
+static struct serio_driver pulse8_drv = {
+	.driver		= {
+		.name	= "pulse8-cec",
+	},
+	.description	= "Pulse Eight HDMI CEC driver",
+	.id_table	= pulse8_serio_ids,
+	.interrupt	= pulse8_interrupt,
+	.connect	= pulse8_connect,
+	.disconnect	= pulse8_disconnect,
+};
+
+module_serio_driver(pulse8_drv);
diff --git a/drivers/staging/media/s5p-cec/Kconfig b/drivers/staging/media/s5p-cec/Kconfig
new file mode 100644
index 000000000000..0315fd7ad0f1
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/Kconfig
@@ -0,0 +1,9 @@
+config VIDEO_SAMSUNG_S5P_CEC
+       tristate "Samsung S5P CEC driver"
+       depends on VIDEO_DEV && MEDIA_CEC && (PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST)
+       ---help---
+         This is a driver for Samsung S5P HDMI CEC interface. It uses the
+         generic CEC framework interface.
+         CEC bus is present in the HDMI connector and enables communication
+         between compatible devices.
+
diff --git a/drivers/staging/media/s5p-cec/Makefile b/drivers/staging/media/s5p-cec/Makefile
new file mode 100644
index 000000000000..0e2cf457825a
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_VIDEO_SAMSUNG_S5P_CEC)	+= s5p-cec.o
+s5p-cec-y += s5p_cec.o exynos_hdmi_cecctrl.o
diff --git a/drivers/staging/media/s5p-cec/TODO b/drivers/staging/media/s5p-cec/TODO
new file mode 100644
index 000000000000..f51d5268ac40
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/TODO
@@ -0,0 +1,7 @@
+This driver depends on the CEC framework, which is currently in
+staging, so therefor this driver is in staging as well.
+
+In addition, this driver requires that userspace sets the physical
+address. However, this should be passed on from the corresponding
+samsung HDMI driver. It is very annoying if userspace has to do this,
+and other than USB CEC adapters this must be handled automatically.
diff --git a/drivers/staging/media/s5p-cec/exynos_hdmi_cec.h b/drivers/staging/media/s5p-cec/exynos_hdmi_cec.h
new file mode 100644
index 000000000000..3e4fc7b05e83
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/exynos_hdmi_cec.h
@@ -0,0 +1,38 @@
+/* drivers/media/platform/s5p-cec/exynos_hdmi_cec.h
+ *
+ * Copyright (c) 2010, 2014 Samsung Electronics
+ *		http://www.samsung.com/
+ *
+ * Header file for interface of Samsung Exynos hdmi cec hardware
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _EXYNOS_HDMI_CEC_H_
+#define _EXYNOS_HDMI_CEC_H_ __FILE__
+
+#include <linux/regmap.h>
+#include <linux/miscdevice.h>
+#include "s5p_cec.h"
+
+void s5p_cec_set_divider(struct s5p_cec_dev *cec);
+void s5p_cec_enable_rx(struct s5p_cec_dev *cec);
+void s5p_cec_mask_rx_interrupts(struct s5p_cec_dev *cec);
+void s5p_cec_unmask_rx_interrupts(struct s5p_cec_dev *cec);
+void s5p_cec_mask_tx_interrupts(struct s5p_cec_dev *cec);
+void s5p_cec_unmask_tx_interrupts(struct s5p_cec_dev *cec);
+void s5p_cec_reset(struct s5p_cec_dev *cec);
+void s5p_cec_tx_reset(struct s5p_cec_dev *cec);
+void s5p_cec_rx_reset(struct s5p_cec_dev *cec);
+void s5p_cec_threshold(struct s5p_cec_dev *cec);
+void s5p_cec_copy_packet(struct s5p_cec_dev *cec, char *data,
+			 size_t count, u8 retries);
+void s5p_cec_set_addr(struct s5p_cec_dev *cec, u32 addr);
+u32 s5p_cec_get_status(struct s5p_cec_dev *cec);
+void s5p_clr_pending_tx(struct s5p_cec_dev *cec);
+void s5p_clr_pending_rx(struct s5p_cec_dev *cec);
+void s5p_cec_get_rx_buf(struct s5p_cec_dev *cec, u32 size, u8 *buffer);
+
+#endif /* _EXYNOS_HDMI_CEC_H_ */
diff --git a/drivers/staging/media/s5p-cec/exynos_hdmi_cecctrl.c b/drivers/staging/media/s5p-cec/exynos_hdmi_cecctrl.c
new file mode 100644
index 000000000000..ce95e0fcd882
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/exynos_hdmi_cecctrl.c
@@ -0,0 +1,209 @@
+/* drivers/media/platform/s5p-cec/exynos_hdmi_cecctrl.c
+ *
+ * Copyright (c) 2009, 2014 Samsung Electronics
+ *		http://www.samsung.com/
+ *
+ * cec ftn file for Samsung TVOUT driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/io.h>
+#include <linux/device.h>
+
+#include "exynos_hdmi_cec.h"
+#include "regs-cec.h"
+
+#define S5P_HDMI_FIN			24000000
+#define CEC_DIV_RATIO			320000
+
+#define CEC_MESSAGE_BROADCAST_MASK	0x0F
+#define CEC_MESSAGE_BROADCAST		0x0F
+#define CEC_FILTER_THRESHOLD		0x15
+
+void s5p_cec_set_divider(struct s5p_cec_dev *cec)
+{
+	u32 div_ratio, div_val;
+	unsigned int reg;
+
+	div_ratio  = S5P_HDMI_FIN / CEC_DIV_RATIO - 1;
+
+	if (regmap_read(cec->pmu, EXYNOS_HDMI_PHY_CONTROL, &reg)) {
+		dev_err(cec->dev, "failed to read phy control\n");
+		return;
+	}
+
+	reg = (reg & ~(0x3FF << 16)) | (div_ratio << 16);
+
+	if (regmap_write(cec->pmu, EXYNOS_HDMI_PHY_CONTROL, reg)) {
+		dev_err(cec->dev, "failed to write phy control\n");
+		return;
+	}
+
+	div_val = CEC_DIV_RATIO * 0.00005 - 1;
+
+	writeb(0x0, cec->reg + S5P_CEC_DIVISOR_3);
+	writeb(0x0, cec->reg + S5P_CEC_DIVISOR_2);
+	writeb(0x0, cec->reg + S5P_CEC_DIVISOR_1);
+	writeb(div_val, cec->reg + S5P_CEC_DIVISOR_0);
+}
+
+void s5p_cec_enable_rx(struct s5p_cec_dev *cec)
+{
+	u8 reg;
+
+	reg = readb(cec->reg + S5P_CEC_RX_CTRL);
+	reg |= S5P_CEC_RX_CTRL_ENABLE;
+	writeb(reg, cec->reg + S5P_CEC_RX_CTRL);
+}
+
+void s5p_cec_mask_rx_interrupts(struct s5p_cec_dev *cec)
+{
+	u8 reg;
+
+	reg = readb(cec->reg + S5P_CEC_IRQ_MASK);
+	reg |= S5P_CEC_IRQ_RX_DONE;
+	reg |= S5P_CEC_IRQ_RX_ERROR;
+	writeb(reg, cec->reg + S5P_CEC_IRQ_MASK);
+}
+
+void s5p_cec_unmask_rx_interrupts(struct s5p_cec_dev *cec)
+{
+	u8 reg;
+
+	reg = readb(cec->reg + S5P_CEC_IRQ_MASK);
+	reg &= ~S5P_CEC_IRQ_RX_DONE;
+	reg &= ~S5P_CEC_IRQ_RX_ERROR;
+	writeb(reg, cec->reg + S5P_CEC_IRQ_MASK);
+}
+
+void s5p_cec_mask_tx_interrupts(struct s5p_cec_dev *cec)
+{
+	u8 reg;
+
+	reg = readb(cec->reg + S5P_CEC_IRQ_MASK);
+	reg |= S5P_CEC_IRQ_TX_DONE;
+	reg |= S5P_CEC_IRQ_TX_ERROR;
+	writeb(reg, cec->reg + S5P_CEC_IRQ_MASK);
+
+}
+
+void s5p_cec_unmask_tx_interrupts(struct s5p_cec_dev *cec)
+{
+	u8 reg;
+
+	reg = readb(cec->reg + S5P_CEC_IRQ_MASK);
+	reg &= ~S5P_CEC_IRQ_TX_DONE;
+	reg &= ~S5P_CEC_IRQ_TX_ERROR;
+	writeb(reg, cec->reg + S5P_CEC_IRQ_MASK);
+}
+
+void s5p_cec_reset(struct s5p_cec_dev *cec)
+{
+	u8 reg;
+
+	writeb(S5P_CEC_RX_CTRL_RESET, cec->reg + S5P_CEC_RX_CTRL);
+	writeb(S5P_CEC_TX_CTRL_RESET, cec->reg + S5P_CEC_TX_CTRL);
+
+	reg = readb(cec->reg + 0xc4);
+	reg &= ~0x1;
+	writeb(reg, cec->reg + 0xc4);
+}
+
+void s5p_cec_tx_reset(struct s5p_cec_dev *cec)
+{
+	writeb(S5P_CEC_TX_CTRL_RESET, cec->reg + S5P_CEC_TX_CTRL);
+}
+
+void s5p_cec_rx_reset(struct s5p_cec_dev *cec)
+{
+	u8 reg;
+
+	writeb(S5P_CEC_RX_CTRL_RESET, cec->reg + S5P_CEC_RX_CTRL);
+
+	reg = readb(cec->reg + 0xc4);
+	reg &= ~0x1;
+	writeb(reg, cec->reg + 0xc4);
+}
+
+void s5p_cec_threshold(struct s5p_cec_dev *cec)
+{
+	writeb(CEC_FILTER_THRESHOLD, cec->reg + S5P_CEC_RX_FILTER_TH);
+	writeb(0, cec->reg + S5P_CEC_RX_FILTER_CTRL);
+}
+
+void s5p_cec_copy_packet(struct s5p_cec_dev *cec, char *data,
+			 size_t count, u8 retries)
+{
+	int i = 0;
+	u8 reg;
+
+	while (i < count) {
+		writeb(data[i], cec->reg + (S5P_CEC_TX_BUFF0 + (i * 4)));
+		i++;
+	}
+
+	writeb(count, cec->reg + S5P_CEC_TX_BYTES);
+	reg = readb(cec->reg + S5P_CEC_TX_CTRL);
+	reg |= S5P_CEC_TX_CTRL_START;
+	reg &= ~0x70;
+	reg |= retries << 4;
+
+	if ((data[0] & CEC_MESSAGE_BROADCAST_MASK) == CEC_MESSAGE_BROADCAST) {
+		dev_dbg(cec->dev, "Broadcast");
+		reg |= S5P_CEC_TX_CTRL_BCAST;
+	} else {
+		dev_dbg(cec->dev, "No Broadcast");
+		reg &= ~S5P_CEC_TX_CTRL_BCAST;
+	}
+
+	writeb(reg, cec->reg + S5P_CEC_TX_CTRL);
+	dev_dbg(cec->dev, "cec-tx: cec count (%zu): %*ph", count,
+		(int)count, data);
+}
+
+void s5p_cec_set_addr(struct s5p_cec_dev *cec, u32 addr)
+{
+	writeb(addr & 0x0F, cec->reg + S5P_CEC_LOGIC_ADDR);
+}
+
+u32 s5p_cec_get_status(struct s5p_cec_dev *cec)
+{
+	u32 status = 0;
+
+	status = readb(cec->reg + S5P_CEC_STATUS_0);
+	status |= readb(cec->reg + S5P_CEC_STATUS_1) << 8;
+	status |= readb(cec->reg + S5P_CEC_STATUS_2) << 16;
+	status |= readb(cec->reg + S5P_CEC_STATUS_3) << 24;
+
+	dev_dbg(cec->dev, "status = 0x%x!\n", status);
+
+	return status;
+}
+
+void s5p_clr_pending_tx(struct s5p_cec_dev *cec)
+{
+	writeb(S5P_CEC_IRQ_TX_DONE | S5P_CEC_IRQ_TX_ERROR,
+					cec->reg + S5P_CEC_IRQ_CLEAR);
+}
+
+void s5p_clr_pending_rx(struct s5p_cec_dev *cec)
+{
+	writeb(S5P_CEC_IRQ_RX_DONE | S5P_CEC_IRQ_RX_ERROR,
+					cec->reg + S5P_CEC_IRQ_CLEAR);
+}
+
+void s5p_cec_get_rx_buf(struct s5p_cec_dev *cec, u32 size, u8 *buffer)
+{
+	u32 i = 0;
+	char debug[40];
+
+	while (i < size) {
+		buffer[i] = readb(cec->reg + S5P_CEC_RX_BUFF0 + (i * 4));
+		sprintf(debug + i * 2, "%02x ", buffer[i]);
+		i++;
+	}
+	dev_dbg(cec->dev, "cec-rx: cec size(%d): %s", size, debug);
+}
diff --git a/drivers/staging/media/s5p-cec/regs-cec.h b/drivers/staging/media/s5p-cec/regs-cec.h
new file mode 100644
index 000000000000..b2e7e129920e
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/regs-cec.h
@@ -0,0 +1,96 @@
+/* drivers/media/platform/s5p-cec/regs-cec.h
+ *
+ * Copyright (c) 2010 Samsung Electronics
+ *		http://www.samsung.com/
+ *
+ *  register header file for Samsung TVOUT driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __EXYNOS_REGS__H
+#define __EXYNOS_REGS__H
+
+/*
+ * Register part
+ */
+#define S5P_CEC_STATUS_0			(0x0000)
+#define S5P_CEC_STATUS_1			(0x0004)
+#define S5P_CEC_STATUS_2			(0x0008)
+#define S5P_CEC_STATUS_3			(0x000C)
+#define S5P_CEC_IRQ_MASK			(0x0010)
+#define S5P_CEC_IRQ_CLEAR			(0x0014)
+#define S5P_CEC_LOGIC_ADDR			(0x0020)
+#define S5P_CEC_DIVISOR_0			(0x0030)
+#define S5P_CEC_DIVISOR_1			(0x0034)
+#define S5P_CEC_DIVISOR_2			(0x0038)
+#define S5P_CEC_DIVISOR_3			(0x003C)
+
+#define S5P_CEC_TX_CTRL				(0x0040)
+#define S5P_CEC_TX_BYTES			(0x0044)
+#define S5P_CEC_TX_STAT0			(0x0060)
+#define S5P_CEC_TX_STAT1			(0x0064)
+#define S5P_CEC_TX_BUFF0			(0x0080)
+#define S5P_CEC_TX_BUFF1			(0x0084)
+#define S5P_CEC_TX_BUFF2			(0x0088)
+#define S5P_CEC_TX_BUFF3			(0x008C)
+#define S5P_CEC_TX_BUFF4			(0x0090)
+#define S5P_CEC_TX_BUFF5			(0x0094)
+#define S5P_CEC_TX_BUFF6			(0x0098)
+#define S5P_CEC_TX_BUFF7			(0x009C)
+#define S5P_CEC_TX_BUFF8			(0x00A0)
+#define S5P_CEC_TX_BUFF9			(0x00A4)
+#define S5P_CEC_TX_BUFF10			(0x00A8)
+#define S5P_CEC_TX_BUFF11			(0x00AC)
+#define S5P_CEC_TX_BUFF12			(0x00B0)
+#define S5P_CEC_TX_BUFF13			(0x00B4)
+#define S5P_CEC_TX_BUFF14			(0x00B8)
+#define S5P_CEC_TX_BUFF15			(0x00BC)
+
+#define S5P_CEC_RX_CTRL				(0x00C0)
+#define S5P_CEC_RX_STAT0			(0x00E0)
+#define S5P_CEC_RX_STAT1			(0x00E4)
+#define S5P_CEC_RX_BUFF0			(0x0100)
+#define S5P_CEC_RX_BUFF1			(0x0104)
+#define S5P_CEC_RX_BUFF2			(0x0108)
+#define S5P_CEC_RX_BUFF3			(0x010C)
+#define S5P_CEC_RX_BUFF4			(0x0110)
+#define S5P_CEC_RX_BUFF5			(0x0114)
+#define S5P_CEC_RX_BUFF6			(0x0118)
+#define S5P_CEC_RX_BUFF7			(0x011C)
+#define S5P_CEC_RX_BUFF8			(0x0120)
+#define S5P_CEC_RX_BUFF9			(0x0124)
+#define S5P_CEC_RX_BUFF10			(0x0128)
+#define S5P_CEC_RX_BUFF11			(0x012C)
+#define S5P_CEC_RX_BUFF12			(0x0130)
+#define S5P_CEC_RX_BUFF13			(0x0134)
+#define S5P_CEC_RX_BUFF14			(0x0138)
+#define S5P_CEC_RX_BUFF15			(0x013C)
+
+#define S5P_CEC_RX_FILTER_CTRL			(0x0180)
+#define S5P_CEC_RX_FILTER_TH			(0x0184)
+
+/*
+ * Bit definition part
+ */
+#define S5P_CEC_IRQ_TX_DONE			(1<<0)
+#define S5P_CEC_IRQ_TX_ERROR			(1<<1)
+#define S5P_CEC_IRQ_RX_DONE			(1<<4)
+#define S5P_CEC_IRQ_RX_ERROR			(1<<5)
+
+#define S5P_CEC_TX_CTRL_START			(1<<0)
+#define S5P_CEC_TX_CTRL_BCAST			(1<<1)
+#define S5P_CEC_TX_CTRL_RETRY			(0x04<<4)
+#define S5P_CEC_TX_CTRL_RESET			(1<<7)
+
+#define S5P_CEC_RX_CTRL_ENABLE			(1<<0)
+#define S5P_CEC_RX_CTRL_RESET			(1<<7)
+
+#define S5P_CEC_LOGIC_ADDR_MASK			(0xF)
+
+/* PMU Registers for PHY */
+#define EXYNOS_HDMI_PHY_CONTROL			0x700
+
+#endif	/* __EXYNOS_REGS__H	*/
diff --git a/drivers/staging/media/s5p-cec/s5p_cec.c b/drivers/staging/media/s5p-cec/s5p_cec.c
new file mode 100644
index 000000000000..78333273c4e5
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/s5p_cec.c
@@ -0,0 +1,294 @@
+/* drivers/media/platform/s5p-cec/s5p_cec.c
+ *
+ * Samsung S5P CEC driver
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This driver is based on the "cec interface driver for exynos soc" by
+ * SangPil Moon.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/timer.h>
+#include <linux/version.h>
+#include <linux/workqueue.h>
+#include <media/cec.h>
+
+#include "exynos_hdmi_cec.h"
+#include "regs-cec.h"
+#include "s5p_cec.h"
+
+#define CEC_NAME	"s5p-cec"
+
+static int debug;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "debug level (0-2)");
+
+static int s5p_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct s5p_cec_dev *cec = adap->priv;
+
+	if (enable) {
+		pm_runtime_get_sync(cec->dev);
+
+		s5p_cec_reset(cec);
+
+		s5p_cec_set_divider(cec);
+		s5p_cec_threshold(cec);
+
+		s5p_cec_unmask_tx_interrupts(cec);
+		s5p_cec_unmask_rx_interrupts(cec);
+		s5p_cec_enable_rx(cec);
+	} else {
+		s5p_cec_mask_tx_interrupts(cec);
+		s5p_cec_mask_rx_interrupts(cec);
+		pm_runtime_disable(cec->dev);
+	}
+
+	return 0;
+}
+
+static int s5p_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct s5p_cec_dev *cec = adap->priv;
+
+	s5p_cec_set_addr(cec, addr);
+	return 0;
+}
+
+static int s5p_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				 u32 signal_free_time, struct cec_msg *msg)
+{
+	struct s5p_cec_dev *cec = adap->priv;
+
+	/*
+	 * Unclear if 0 retries are allowed by the hardware, so have 1 as
+	 * the minimum.
+	 */
+	s5p_cec_copy_packet(cec, msg->msg, msg->len, max(1, attempts - 1));
+	return 0;
+}
+
+static irqreturn_t s5p_cec_irq_handler(int irq, void *priv)
+{
+	struct s5p_cec_dev *cec = priv;
+	u32 status = 0;
+
+	status = s5p_cec_get_status(cec);
+
+	dev_dbg(cec->dev, "irq received\n");
+
+	if (status & CEC_STATUS_TX_DONE) {
+		if (status & CEC_STATUS_TX_ERROR) {
+			dev_dbg(cec->dev, "CEC_STATUS_TX_ERROR set\n");
+			cec->tx = STATE_ERROR;
+		} else {
+			dev_dbg(cec->dev, "CEC_STATUS_TX_DONE\n");
+			cec->tx = STATE_DONE;
+		}
+		s5p_clr_pending_tx(cec);
+	}
+
+	if (status & CEC_STATUS_RX_DONE) {
+		if (status & CEC_STATUS_RX_ERROR) {
+			dev_dbg(cec->dev, "CEC_STATUS_RX_ERROR set\n");
+			s5p_cec_rx_reset(cec);
+			s5p_cec_enable_rx(cec);
+		} else {
+			dev_dbg(cec->dev, "CEC_STATUS_RX_DONE set\n");
+			if (cec->rx != STATE_IDLE)
+				dev_dbg(cec->dev, "Buffer overrun (worker did not process previous message)\n");
+			cec->rx = STATE_BUSY;
+			cec->msg.len = status >> 24;
+			cec->msg.rx_status = CEC_RX_STATUS_OK;
+			s5p_cec_get_rx_buf(cec, cec->msg.len,
+					cec->msg.msg);
+			cec->rx = STATE_DONE;
+			s5p_cec_enable_rx(cec);
+		}
+		/* Clear interrupt pending bit */
+		s5p_clr_pending_rx(cec);
+	}
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t s5p_cec_irq_handler_thread(int irq, void *priv)
+{
+	struct s5p_cec_dev *cec = priv;
+
+	dev_dbg(cec->dev, "irq processing thread\n");
+	switch (cec->tx) {
+	case STATE_DONE:
+		cec_transmit_done(cec->adap, CEC_TX_STATUS_OK, 0, 0, 0, 0);
+		cec->tx = STATE_IDLE;
+		break;
+	case STATE_ERROR:
+		cec_transmit_done(cec->adap,
+			CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_ERROR,
+			0, 0, 0, 1);
+		cec->tx = STATE_IDLE;
+		break;
+	case STATE_BUSY:
+		dev_err(cec->dev, "state set to busy, this should not occur here\n");
+		break;
+	default:
+		break;
+	}
+
+	switch (cec->rx) {
+	case STATE_DONE:
+		cec_received_msg(cec->adap, &cec->msg);
+		cec->rx = STATE_IDLE;
+		break;
+	default:
+		break;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static const struct cec_adap_ops s5p_cec_adap_ops = {
+	.adap_enable = s5p_cec_adap_enable,
+	.adap_log_addr = s5p_cec_adap_log_addr,
+	.adap_transmit = s5p_cec_adap_transmit,
+};
+
+static int s5p_cec_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct s5p_cec_dev *cec;
+	int ret;
+
+	cec = devm_kzalloc(&pdev->dev, sizeof(*cec), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	cec->dev = dev;
+
+	cec->irq = platform_get_irq(pdev, 0);
+	if (cec->irq < 0)
+		return cec->irq;
+
+	ret = devm_request_threaded_irq(dev, cec->irq, s5p_cec_irq_handler,
+		s5p_cec_irq_handler_thread, 0, pdev->name, cec);
+	if (ret)
+		return ret;
+
+	cec->clk = devm_clk_get(dev, "hdmicec");
+	if (IS_ERR(cec->clk))
+		return PTR_ERR(cec->clk);
+
+	cec->pmu = syscon_regmap_lookup_by_phandle(dev->of_node,
+						 "samsung,syscon-phandle");
+	if (IS_ERR(cec->pmu))
+		return -EPROBE_DEFER;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cec->reg = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cec->reg))
+		return PTR_ERR(cec->reg);
+
+	cec->adap = cec_allocate_adapter(&s5p_cec_adap_ops, cec,
+		CEC_NAME,
+		CEC_CAP_PHYS_ADDR | CEC_CAP_LOG_ADDRS | CEC_CAP_TRANSMIT |
+		CEC_CAP_PASSTHROUGH | CEC_CAP_RC,
+		1, &pdev->dev);
+	ret = PTR_ERR_OR_ZERO(cec->adap);
+	if (ret)
+		return ret;
+	ret = cec_register_adapter(cec->adap);
+	if (ret) {
+		cec_delete_adapter(cec->adap);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, cec);
+	pm_runtime_enable(dev);
+
+	dev_dbg(dev, "successfuly probed\n");
+	return 0;
+}
+
+static int s5p_cec_remove(struct platform_device *pdev)
+{
+	struct s5p_cec_dev *cec = platform_get_drvdata(pdev);
+
+	cec_unregister_adapter(cec->adap);
+	pm_runtime_disable(&pdev->dev);
+	return 0;
+}
+
+static int s5p_cec_runtime_suspend(struct device *dev)
+{
+	struct s5p_cec_dev *cec = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(cec->clk);
+	return 0;
+}
+
+static int s5p_cec_runtime_resume(struct device *dev)
+{
+	struct s5p_cec_dev *cec = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(cec->clk);
+	if (ret < 0)
+		return ret;
+	return 0;
+}
+
+static int __maybe_unused s5p_cec_suspend(struct device *dev)
+{
+	if (pm_runtime_suspended(dev))
+		return 0;
+	return s5p_cec_runtime_suspend(dev);
+}
+
+static int __maybe_unused s5p_cec_resume(struct device *dev)
+{
+	if (pm_runtime_suspended(dev))
+		return 0;
+	return s5p_cec_runtime_resume(dev);
+}
+
+static const struct dev_pm_ops s5p_cec_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(s5p_cec_suspend, s5p_cec_resume)
+	SET_RUNTIME_PM_OPS(s5p_cec_runtime_suspend, s5p_cec_runtime_resume,
+			   NULL)
+};
+
+static const struct of_device_id s5p_cec_match[] = {
+	{
+		.compatible	= "samsung,s5p-cec",
+	},
+	{},
+};
+
+static struct platform_driver s5p_cec_pdrv = {
+	.probe	= s5p_cec_probe,
+	.remove	= s5p_cec_remove,
+	.driver	= {
+		.name		= CEC_NAME,
+		.of_match_table	= s5p_cec_match,
+		.pm		= &s5p_cec_pm_ops,
+	},
+};
+
+module_platform_driver(s5p_cec_pdrv);
+
+MODULE_AUTHOR("Kamil Debski <kamil@wypas.org>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Samsung S5P CEC driver");
diff --git a/drivers/staging/media/s5p-cec/s5p_cec.h b/drivers/staging/media/s5p-cec/s5p_cec.h
new file mode 100644
index 000000000000..03732c13d19f
--- /dev/null
+++ b/drivers/staging/media/s5p-cec/s5p_cec.h
@@ -0,0 +1,76 @@
+/* drivers/media/platform/s5p-cec/s5p_cec.h
+ *
+ * Samsung S5P HDMI CEC driver
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _S5P_CEC_H_
+#define _S5P_CEC_H_ __FILE__
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/timer.h>
+#include <linux/version.h>
+#include <linux/workqueue.h>
+#include <media/cec.h>
+
+#include "exynos_hdmi_cec.h"
+#include "regs-cec.h"
+#include "s5p_cec.h"
+
+#define CEC_NAME	"s5p-cec"
+
+#define CEC_STATUS_TX_RUNNING		(1 << 0)
+#define CEC_STATUS_TX_TRANSFERRING	(1 << 1)
+#define CEC_STATUS_TX_DONE		(1 << 2)
+#define CEC_STATUS_TX_ERROR		(1 << 3)
+#define CEC_STATUS_TX_BYTES		(0xFF << 8)
+#define CEC_STATUS_RX_RUNNING		(1 << 16)
+#define CEC_STATUS_RX_RECEIVING		(1 << 17)
+#define CEC_STATUS_RX_DONE		(1 << 18)
+#define CEC_STATUS_RX_ERROR		(1 << 19)
+#define CEC_STATUS_RX_BCAST		(1 << 20)
+#define CEC_STATUS_RX_BYTES		(0xFF << 24)
+
+#define CEC_WORKER_TX_DONE		(1 << 0)
+#define CEC_WORKER_RX_MSG		(1 << 1)
+
+/* CEC Rx buffer size */
+#define CEC_RX_BUFF_SIZE		16
+/* CEC Tx buffer size */
+#define CEC_TX_BUFF_SIZE		16
+
+enum cec_state {
+	STATE_IDLE,
+	STATE_BUSY,
+	STATE_DONE,
+	STATE_ERROR
+};
+
+struct s5p_cec_dev {
+	struct cec_adapter	*adap;
+	struct clk		*clk;
+	struct device		*dev;
+	struct mutex		lock;
+	struct regmap           *pmu;
+	int			irq;
+	void __iomem		*reg;
+
+	enum cec_state		rx;
+	enum cec_state		tx;
+	struct cec_msg		msg;
+};
+
+#endif /* _S5P_CEC_H_ */
diff --git a/drivers/staging/media/timb/Kconfig b/drivers/staging/media/timb/Kconfig
deleted file mode 100644
index e413fecc1e67..000000000000
--- a/drivers/staging/media/timb/Kconfig
+++ /dev/null
@@ -1,11 +0,0 @@
-config VIDEO_TIMBERDALE
-	tristate "Support for timberdale Video In/LogiWIN"
-	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && HAS_DMA
-	depends on (MFD_TIMBERDALE && TIMB_DMA) || COMPILE_TEST
-	select VIDEO_ADV7180
-	select VIDEOBUF_DMA_CONTIG
-	---help---
-	  Add support for the Video In peripherial of the timberdale FPGA.
-
-	  This driver is deprecated and will be removed soon unless someone
-	  will start the work to convert this driver to the vb2 framework.
diff --git a/drivers/staging/media/timb/Makefile b/drivers/staging/media/timb/Makefile
deleted file mode 100644
index 4c989c23a0e0..000000000000
--- a/drivers/staging/media/timb/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-$(CONFIG_VIDEO_TIMBERDALE)	+= timblogiw.o
diff --git a/drivers/staging/media/timb/timblogiw.c b/drivers/staging/media/timb/timblogiw.c
deleted file mode 100644
index 113c9f3c0b3e..000000000000
--- a/drivers/staging/media/timb/timblogiw.c
+++ /dev/null
@@ -1,870 +0,0 @@
-/*
- * timblogiw.c timberdale FPGA LogiWin Video In driver
- * Copyright (c) 2009-2010 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-/* Supports:
- * Timberdale FPGA LogiWin Video In
- */
-
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/dmaengine.h>
-#include <linux/scatterlist.h>
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/i2c.h>
-#include <linux/module.h>
-#include <media/v4l2-ioctl.h>
-#include <media/v4l2-device.h>
-#include <media/videobuf-dma-contig.h>
-#include <linux/platform_data/media/timb_video.h>
-
-#define DRIVER_NAME			"timb-video"
-
-#define TIMBLOGIWIN_NAME		"Timberdale Video-In"
-#define TIMBLOGIW_VERSION_CODE		0x04
-
-#define TIMBLOGIW_LINES_PER_DESC	44
-#define TIMBLOGIW_MAX_VIDEO_MEM		16
-
-#define TIMBLOGIW_HAS_DECODER(lw)	(lw->pdata.encoder.module_name)
-
-
-struct timblogiw {
-	struct video_device		video_dev;
-	struct v4l2_device		v4l2_dev; /* mutual exclusion */
-	struct mutex			lock;
-	struct device			*dev;
-	struct timb_video_platform_data pdata;
-	struct v4l2_subdev		*sd_enc;	/* encoder */
-	bool				opened;
-};
-
-struct timblogiw_tvnorm {
-	v4l2_std_id std;
-	u16     width;
-	u16     height;
-	u8	fps;
-};
-
-struct timblogiw_fh {
-	struct videobuf_queue		vb_vidq;
-	struct timblogiw_tvnorm const	*cur_norm;
-	struct list_head		capture;
-	struct dma_chan			*chan;
-	spinlock_t			queue_lock; /* mutual exclusion */
-	unsigned int			frame_count;
-};
-
-struct timblogiw_buffer {
-	/* common v4l buffer stuff -- must be first */
-	struct videobuf_buffer	vb;
-	struct scatterlist	sg[16];
-	dma_cookie_t		cookie;
-	struct timblogiw_fh	*fh;
-};
-
-static const struct timblogiw_tvnorm timblogiw_tvnorms[] = {
-	{
-		.std			= V4L2_STD_PAL,
-		.width			= 720,
-		.height			= 576,
-		.fps			= 25
-	},
-	{
-		.std			= V4L2_STD_NTSC,
-		.width			= 720,
-		.height			= 480,
-		.fps			= 30
-	}
-};
-
-static int timblogiw_bytes_per_line(const struct timblogiw_tvnorm *norm)
-{
-	return norm->width * 2;
-}
-
-
-static int timblogiw_frame_size(const struct timblogiw_tvnorm *norm)
-{
-	return norm->height * timblogiw_bytes_per_line(norm);
-}
-
-static const struct timblogiw_tvnorm *timblogiw_get_norm(const v4l2_std_id std)
-{
-	int i;
-	for (i = 0; i < ARRAY_SIZE(timblogiw_tvnorms); i++)
-		if (timblogiw_tvnorms[i].std & std)
-			return timblogiw_tvnorms + i;
-
-	/* default to first element */
-	return timblogiw_tvnorms;
-}
-
-static void timblogiw_dma_cb(void *data)
-{
-	struct timblogiw_buffer *buf = data;
-	struct timblogiw_fh *fh = buf->fh;
-	struct videobuf_buffer *vb = &buf->vb;
-
-	spin_lock(&fh->queue_lock);
-
-	/* mark the transfer done */
-	buf->cookie = -1;
-
-	fh->frame_count++;
-
-	if (vb->state != VIDEOBUF_ERROR) {
-		list_del(&vb->queue);
-		v4l2_get_timestamp(&vb->ts);
-		vb->field_count = fh->frame_count * 2;
-		vb->state = VIDEOBUF_DONE;
-
-		wake_up(&vb->done);
-	}
-
-	if (!list_empty(&fh->capture)) {
-		vb = list_entry(fh->capture.next, struct videobuf_buffer,
-			queue);
-		vb->state = VIDEOBUF_ACTIVE;
-	}
-
-	spin_unlock(&fh->queue_lock);
-}
-
-static bool timblogiw_dma_filter_fn(struct dma_chan *chan, void *filter_param)
-{
-	return chan->chan_id == (uintptr_t)filter_param;
-}
-
-/* IOCTL functions */
-
-static int timblogiw_g_fmt(struct file *file, void  *priv,
-	struct v4l2_format *format)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw *lw = video_get_drvdata(vdev);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s entry\n", __func__);
-
-	if (format->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		return -EINVAL;
-
-	mutex_lock(&lw->lock);
-
-	format->fmt.pix.width = fh->cur_norm->width;
-	format->fmt.pix.height = fh->cur_norm->height;
-	format->fmt.pix.pixelformat = V4L2_PIX_FMT_UYVY;
-	format->fmt.pix.bytesperline = timblogiw_bytes_per_line(fh->cur_norm);
-	format->fmt.pix.sizeimage = timblogiw_frame_size(fh->cur_norm);
-	format->fmt.pix.field = V4L2_FIELD_NONE;
-
-	mutex_unlock(&lw->lock);
-
-	return 0;
-}
-
-static int timblogiw_try_fmt(struct file *file, void  *priv,
-	struct v4l2_format *format)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct v4l2_pix_format *pix = &format->fmt.pix;
-
-	dev_dbg(&vdev->dev,
-		"%s - width=%d, height=%d, pixelformat=%d, field=%d\n"
-		"bytes per line %d, size image: %d, colorspace: %d\n",
-		__func__,
-		pix->width, pix->height, pix->pixelformat, pix->field,
-		pix->bytesperline, pix->sizeimage, pix->colorspace);
-
-	if (format->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		return -EINVAL;
-
-	if (pix->field != V4L2_FIELD_NONE)
-		return -EINVAL;
-
-	if (pix->pixelformat != V4L2_PIX_FMT_UYVY)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int timblogiw_s_fmt(struct file *file, void  *priv,
-	struct v4l2_format *format)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw *lw = video_get_drvdata(vdev);
-	struct timblogiw_fh *fh = priv;
-	struct v4l2_pix_format *pix = &format->fmt.pix;
-	int err;
-
-	mutex_lock(&lw->lock);
-
-	err = timblogiw_try_fmt(file, priv, format);
-	if (err)
-		goto out;
-
-	if (videobuf_queue_is_busy(&fh->vb_vidq)) {
-		dev_err(&vdev->dev, "%s queue busy\n", __func__);
-		err = -EBUSY;
-		goto out;
-	}
-
-	pix->width = fh->cur_norm->width;
-	pix->height = fh->cur_norm->height;
-
-out:
-	mutex_unlock(&lw->lock);
-	return err;
-}
-
-static int timblogiw_querycap(struct file *file, void  *priv,
-	struct v4l2_capability *cap)
-{
-	struct video_device *vdev = video_devdata(file);
-
-	dev_dbg(&vdev->dev, "%s: Entry\n",  __func__);
-	strncpy(cap->card, TIMBLOGIWIN_NAME, sizeof(cap->card)-1);
-	strncpy(cap->driver, DRIVER_NAME, sizeof(cap->driver) - 1);
-	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", vdev->name);
-	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING |
-		V4L2_CAP_READWRITE;
-	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
-
-	return 0;
-}
-
-static int timblogiw_enum_fmt(struct file *file, void  *priv,
-	struct v4l2_fmtdesc *fmt)
-{
-	struct video_device *vdev = video_devdata(file);
-
-	dev_dbg(&vdev->dev, "%s, index: %d\n",  __func__, fmt->index);
-
-	if (fmt->index != 0)
-		return -EINVAL;
-	memset(fmt, 0, sizeof(*fmt));
-	fmt->index = 0;
-	fmt->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	strncpy(fmt->description, "4:2:2, packed, YUYV",
-		sizeof(fmt->description)-1);
-	fmt->pixelformat = V4L2_PIX_FMT_UYVY;
-
-	return 0;
-}
-
-static int timblogiw_g_parm(struct file *file, void *priv,
-	struct v4l2_streamparm *sp)
-{
-	struct timblogiw_fh *fh = priv;
-	struct v4l2_captureparm *cp = &sp->parm.capture;
-
-	cp->capability = V4L2_CAP_TIMEPERFRAME;
-	cp->timeperframe.numerator = 1;
-	cp->timeperframe.denominator = fh->cur_norm->fps;
-
-	return 0;
-}
-
-static int timblogiw_reqbufs(struct file *file, void  *priv,
-	struct v4l2_requestbuffers *rb)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	return videobuf_reqbufs(&fh->vb_vidq, rb);
-}
-
-static int timblogiw_querybuf(struct file *file, void  *priv,
-	struct v4l2_buffer *b)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	return videobuf_querybuf(&fh->vb_vidq, b);
-}
-
-static int timblogiw_qbuf(struct file *file, void  *priv, struct v4l2_buffer *b)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	return videobuf_qbuf(&fh->vb_vidq, b);
-}
-
-static int timblogiw_dqbuf(struct file *file, void  *priv,
-	struct v4l2_buffer *b)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	return videobuf_dqbuf(&fh->vb_vidq, b, file->f_flags & O_NONBLOCK);
-}
-
-static int timblogiw_g_std(struct file *file, void  *priv, v4l2_std_id *std)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	*std = fh->cur_norm->std;
-	return 0;
-}
-
-static int timblogiw_s_std(struct file *file, void  *priv, v4l2_std_id std)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw *lw = video_get_drvdata(vdev);
-	struct timblogiw_fh *fh = priv;
-	int err = 0;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	mutex_lock(&lw->lock);
-
-	if (TIMBLOGIW_HAS_DECODER(lw))
-		err = v4l2_subdev_call(lw->sd_enc, video, s_std, std);
-
-	if (!err)
-		fh->cur_norm = timblogiw_get_norm(std);
-
-	mutex_unlock(&lw->lock);
-
-	return err;
-}
-
-static int timblogiw_enuminput(struct file *file, void  *priv,
-	struct v4l2_input *inp)
-{
-	struct video_device *vdev = video_devdata(file);
-	int i;
-
-	dev_dbg(&vdev->dev, "%s: Entry\n",  __func__);
-
-	if (inp->index != 0)
-		return -EINVAL;
-
-	inp->index = 0;
-
-	strncpy(inp->name, "Timb input 1", sizeof(inp->name) - 1);
-	inp->type = V4L2_INPUT_TYPE_CAMERA;
-
-	inp->std = 0;
-	for (i = 0; i < ARRAY_SIZE(timblogiw_tvnorms); i++)
-		inp->std |= timblogiw_tvnorms[i].std;
-
-	return 0;
-}
-
-static int timblogiw_g_input(struct file *file, void  *priv,
-	unsigned int *input)
-{
-	struct video_device *vdev = video_devdata(file);
-
-	dev_dbg(&vdev->dev, "%s: Entry\n",  __func__);
-
-	*input = 0;
-
-	return 0;
-}
-
-static int timblogiw_s_input(struct file *file, void  *priv, unsigned int input)
-{
-	struct video_device *vdev = video_devdata(file);
-
-	dev_dbg(&vdev->dev, "%s: Entry\n",  __func__);
-
-	if (input != 0)
-		return -EINVAL;
-	return 0;
-}
-
-static int timblogiw_streamon(struct file *file, void  *priv, enum v4l2_buf_type type)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE) {
-		dev_dbg(&vdev->dev, "%s - No capture device\n", __func__);
-		return -EINVAL;
-	}
-
-	fh->frame_count = 0;
-	return videobuf_streamon(&fh->vb_vidq);
-}
-
-static int timblogiw_streamoff(struct file *file, void  *priv,
-	enum v4l2_buf_type type)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s entry\n",  __func__);
-
-	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		return -EINVAL;
-
-	return videobuf_streamoff(&fh->vb_vidq);
-}
-
-static int timblogiw_querystd(struct file *file, void  *priv, v4l2_std_id *std)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw *lw = video_get_drvdata(vdev);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s entry\n",  __func__);
-
-	if (TIMBLOGIW_HAS_DECODER(lw))
-		return v4l2_subdev_call(lw->sd_enc, video, querystd, std);
-	else {
-		*std = fh->cur_norm->std;
-		return 0;
-	}
-}
-
-static int timblogiw_enum_framesizes(struct file *file, void  *priv,
-	struct v4l2_frmsizeenum *fsize)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = priv;
-
-	dev_dbg(&vdev->dev, "%s - index: %d, format: %d\n",  __func__,
-		fsize->index, fsize->pixel_format);
-
-	if ((fsize->index != 0) ||
-		(fsize->pixel_format != V4L2_PIX_FMT_UYVY))
-		return -EINVAL;
-
-	fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE;
-	fsize->discrete.width = fh->cur_norm->width;
-	fsize->discrete.height = fh->cur_norm->height;
-
-	return 0;
-}
-
-/* Video buffer functions */
-
-static int buffer_setup(struct videobuf_queue *vq, unsigned int *count,
-	unsigned int *size)
-{
-	struct timblogiw_fh *fh = vq->priv_data;
-
-	*size = timblogiw_frame_size(fh->cur_norm);
-
-	if (!*count)
-		*count = 32;
-
-	while (*size * *count > TIMBLOGIW_MAX_VIDEO_MEM * 1024 * 1024)
-		(*count)--;
-
-	return 0;
-}
-
-static int buffer_prepare(struct videobuf_queue *vq, struct videobuf_buffer *vb,
-	enum v4l2_field field)
-{
-	struct timblogiw_fh *fh = vq->priv_data;
-	struct timblogiw_buffer *buf = container_of(vb, struct timblogiw_buffer,
-		vb);
-	unsigned int data_size = timblogiw_frame_size(fh->cur_norm);
-	int err = 0;
-
-	if (vb->baddr && vb->bsize < data_size)
-		/* User provided buffer, but it is too small */
-		return -ENOMEM;
-
-	vb->size = data_size;
-	vb->width = fh->cur_norm->width;
-	vb->height = fh->cur_norm->height;
-	vb->field = field;
-
-	if (vb->state == VIDEOBUF_NEEDS_INIT) {
-		int i;
-		unsigned int size;
-		unsigned int bytes_per_desc = TIMBLOGIW_LINES_PER_DESC *
-			timblogiw_bytes_per_line(fh->cur_norm);
-		dma_addr_t addr;
-
-		sg_init_table(buf->sg, ARRAY_SIZE(buf->sg));
-
-		err = videobuf_iolock(vq, vb, NULL);
-		if (err)
-			goto err;
-
-		addr = videobuf_to_dma_contig(vb);
-		for (i = 0, size = 0; size < data_size; i++) {
-			sg_dma_address(buf->sg + i) = addr + size;
-			size += bytes_per_desc;
-			sg_dma_len(buf->sg + i) = (size > data_size) ?
-				(bytes_per_desc - (size - data_size)) :
-				bytes_per_desc;
-		}
-
-		vb->state = VIDEOBUF_PREPARED;
-		buf->cookie = -1;
-		buf->fh = fh;
-	}
-
-	return 0;
-
-err:
-	videobuf_dma_contig_free(vq, vb);
-	vb->state = VIDEOBUF_NEEDS_INIT;
-	return err;
-}
-
-static void buffer_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
-{
-	struct timblogiw_fh *fh = vq->priv_data;
-	struct timblogiw_buffer *buf = container_of(vb, struct timblogiw_buffer,
-		vb);
-	struct dma_async_tx_descriptor *desc;
-	int sg_elems;
-	int bytes_per_desc = TIMBLOGIW_LINES_PER_DESC *
-		timblogiw_bytes_per_line(fh->cur_norm);
-
-	sg_elems = timblogiw_frame_size(fh->cur_norm) / bytes_per_desc;
-	sg_elems +=
-		(timblogiw_frame_size(fh->cur_norm) % bytes_per_desc) ? 1 : 0;
-
-	if (list_empty(&fh->capture))
-		vb->state = VIDEOBUF_ACTIVE;
-	else
-		vb->state = VIDEOBUF_QUEUED;
-
-	list_add_tail(&vb->queue, &fh->capture);
-
-	spin_unlock_irq(&fh->queue_lock);
-
-	desc = dmaengine_prep_slave_sg(fh->chan,
-		buf->sg, sg_elems, DMA_DEV_TO_MEM,
-		DMA_PREP_INTERRUPT);
-	if (!desc) {
-		spin_lock_irq(&fh->queue_lock);
-		list_del_init(&vb->queue);
-		vb->state = VIDEOBUF_PREPARED;
-		return;
-	}
-
-	desc->callback_param = buf;
-	desc->callback = timblogiw_dma_cb;
-
-	buf->cookie = desc->tx_submit(desc);
-
-	spin_lock_irq(&fh->queue_lock);
-}
-
-static void buffer_release(struct videobuf_queue *vq,
-	struct videobuf_buffer *vb)
-{
-	struct timblogiw_fh *fh = vq->priv_data;
-	struct timblogiw_buffer *buf = container_of(vb, struct timblogiw_buffer,
-		vb);
-
-	videobuf_waiton(vq, vb, 0, 0);
-	if (buf->cookie >= 0)
-		dma_sync_wait(fh->chan, buf->cookie);
-
-	videobuf_dma_contig_free(vq, vb);
-	vb->state = VIDEOBUF_NEEDS_INIT;
-}
-
-static struct videobuf_queue_ops timblogiw_video_qops = {
-	.buf_setup      = buffer_setup,
-	.buf_prepare    = buffer_prepare,
-	.buf_queue      = buffer_queue,
-	.buf_release    = buffer_release,
-};
-
-/* Device Operations functions */
-
-static int timblogiw_open(struct file *file)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw *lw = video_get_drvdata(vdev);
-	struct timblogiw_fh *fh;
-	v4l2_std_id std;
-	dma_cap_mask_t mask;
-	int err = 0;
-
-	dev_dbg(&vdev->dev, "%s: entry\n", __func__);
-
-	mutex_lock(&lw->lock);
-	if (lw->opened) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	if (TIMBLOGIW_HAS_DECODER(lw) && !lw->sd_enc) {
-		struct i2c_adapter *adapt;
-
-		/* find the video decoder */
-		adapt = i2c_get_adapter(lw->pdata.i2c_adapter);
-		if (!adapt) {
-			dev_err(&vdev->dev, "No I2C bus #%d\n",
-				lw->pdata.i2c_adapter);
-			err = -ENODEV;
-			goto out;
-		}
-
-		/* now find the encoder */
-		lw->sd_enc = v4l2_i2c_new_subdev_board(&lw->v4l2_dev, adapt,
-			lw->pdata.encoder.info, NULL);
-
-		i2c_put_adapter(adapt);
-
-		if (!lw->sd_enc) {
-			dev_err(&vdev->dev, "Failed to get encoder: %s\n",
-				lw->pdata.encoder.module_name);
-			err = -ENODEV;
-			goto out;
-		}
-	}
-
-	fh = kzalloc(sizeof(*fh), GFP_KERNEL);
-	if (!fh) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	fh->cur_norm = timblogiw_tvnorms;
-	timblogiw_querystd(file, fh, &std);
-	fh->cur_norm = timblogiw_get_norm(std);
-
-	INIT_LIST_HEAD(&fh->capture);
-	spin_lock_init(&fh->queue_lock);
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	dma_cap_set(DMA_PRIVATE, mask);
-
-	/* find the DMA channel */
-	fh->chan = dma_request_channel(mask, timblogiw_dma_filter_fn,
-			(void *)(uintptr_t)lw->pdata.dma_channel);
-	if (!fh->chan) {
-		dev_err(&vdev->dev, "Failed to get DMA channel\n");
-		kfree(fh);
-		err = -ENODEV;
-		goto out;
-	}
-
-	file->private_data = fh;
-	videobuf_queue_dma_contig_init(&fh->vb_vidq,
-		&timblogiw_video_qops, lw->dev, &fh->queue_lock,
-		V4L2_BUF_TYPE_VIDEO_CAPTURE, V4L2_FIELD_NONE,
-		sizeof(struct timblogiw_buffer), fh, NULL);
-
-	lw->opened = true;
-out:
-	mutex_unlock(&lw->lock);
-
-	return err;
-}
-
-static int timblogiw_close(struct file *file)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw *lw = video_get_drvdata(vdev);
-	struct timblogiw_fh *fh = file->private_data;
-
-	dev_dbg(&vdev->dev, "%s: Entry\n",  __func__);
-
-	videobuf_stop(&fh->vb_vidq);
-	videobuf_mmap_free(&fh->vb_vidq);
-
-	dma_release_channel(fh->chan);
-
-	kfree(fh);
-
-	mutex_lock(&lw->lock);
-	lw->opened = false;
-	mutex_unlock(&lw->lock);
-	return 0;
-}
-
-static ssize_t timblogiw_read(struct file *file, char __user *data,
-	size_t count, loff_t *ppos)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = file->private_data;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	return videobuf_read_stream(&fh->vb_vidq, data, count, ppos, 0,
-		file->f_flags & O_NONBLOCK);
-}
-
-static unsigned int timblogiw_poll(struct file *file,
-	struct poll_table_struct *wait)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = file->private_data;
-
-	dev_dbg(&vdev->dev, "%s: entry\n",  __func__);
-
-	return videobuf_poll_stream(file, &fh->vb_vidq, wait);
-}
-
-static int timblogiw_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct timblogiw_fh *fh = file->private_data;
-
-	dev_dbg(&vdev->dev, "%s: entry\n", __func__);
-
-	return videobuf_mmap_mapper(&fh->vb_vidq, vma);
-}
-
-/* Platform device functions */
-
-static struct v4l2_ioctl_ops timblogiw_ioctl_ops = {
-	.vidioc_querycap		= timblogiw_querycap,
-	.vidioc_enum_fmt_vid_cap	= timblogiw_enum_fmt,
-	.vidioc_g_fmt_vid_cap		= timblogiw_g_fmt,
-	.vidioc_try_fmt_vid_cap		= timblogiw_try_fmt,
-	.vidioc_s_fmt_vid_cap		= timblogiw_s_fmt,
-	.vidioc_g_parm			= timblogiw_g_parm,
-	.vidioc_reqbufs			= timblogiw_reqbufs,
-	.vidioc_querybuf		= timblogiw_querybuf,
-	.vidioc_qbuf			= timblogiw_qbuf,
-	.vidioc_dqbuf			= timblogiw_dqbuf,
-	.vidioc_g_std			= timblogiw_g_std,
-	.vidioc_s_std			= timblogiw_s_std,
-	.vidioc_enum_input		= timblogiw_enuminput,
-	.vidioc_g_input			= timblogiw_g_input,
-	.vidioc_s_input			= timblogiw_s_input,
-	.vidioc_streamon		= timblogiw_streamon,
-	.vidioc_streamoff		= timblogiw_streamoff,
-	.vidioc_querystd		= timblogiw_querystd,
-	.vidioc_enum_framesizes		= timblogiw_enum_framesizes,
-};
-
-static struct v4l2_file_operations timblogiw_fops = {
-	.owner		= THIS_MODULE,
-	.open		= timblogiw_open,
-	.release	= timblogiw_close,
-	.unlocked_ioctl		= video_ioctl2, /* V4L2 ioctl handler */
-	.mmap		= timblogiw_mmap,
-	.read		= timblogiw_read,
-	.poll		= timblogiw_poll,
-};
-
-static struct video_device timblogiw_template = {
-	.name		= TIMBLOGIWIN_NAME,
-	.fops		= &timblogiw_fops,
-	.ioctl_ops	= &timblogiw_ioctl_ops,
-	.release	= video_device_release_empty,
-	.minor		= -1,
-	.tvnorms	= V4L2_STD_PAL | V4L2_STD_NTSC
-};
-
-static int timblogiw_probe(struct platform_device *pdev)
-{
-	int err;
-	struct timblogiw *lw = NULL;
-	struct timb_video_platform_data *pdata = pdev->dev.platform_data;
-
-	if (!pdata) {
-		dev_err(&pdev->dev, "No platform data\n");
-		err = -EINVAL;
-		goto err;
-	}
-
-	if (!pdata->encoder.module_name)
-		dev_info(&pdev->dev, "Running without decoder\n");
-
-	lw = devm_kzalloc(&pdev->dev, sizeof(*lw), GFP_KERNEL);
-	if (!lw) {
-		err = -ENOMEM;
-		goto err;
-	}
-
-	if (pdev->dev.parent)
-		lw->dev = pdev->dev.parent;
-	else
-		lw->dev = &pdev->dev;
-
-	memcpy(&lw->pdata, pdata, sizeof(lw->pdata));
-
-	mutex_init(&lw->lock);
-
-	lw->video_dev = timblogiw_template;
-
-	strlcpy(lw->v4l2_dev.name, DRIVER_NAME, sizeof(lw->v4l2_dev.name));
-	err = v4l2_device_register(NULL, &lw->v4l2_dev);
-	if (err)
-		goto err;
-
-	lw->video_dev.v4l2_dev = &lw->v4l2_dev;
-
-	platform_set_drvdata(pdev, lw);
-	video_set_drvdata(&lw->video_dev, lw);
-
-	err = video_register_device(&lw->video_dev, VFL_TYPE_GRABBER, 0);
-	if (err) {
-		dev_err(&pdev->dev, "Error reg video: %d\n", err);
-		goto err_request;
-	}
-
-	return 0;
-
-err_request:
-	v4l2_device_unregister(&lw->v4l2_dev);
-err:
-	dev_err(&pdev->dev, "Failed to register: %d\n", err);
-
-	return err;
-}
-
-static int timblogiw_remove(struct platform_device *pdev)
-{
-	struct timblogiw *lw = platform_get_drvdata(pdev);
-
-	video_unregister_device(&lw->video_dev);
-
-	v4l2_device_unregister(&lw->v4l2_dev);
-
-	return 0;
-}
-
-static struct platform_driver timblogiw_platform_driver = {
-	.driver = {
-		.name	= DRIVER_NAME,
-	},
-	.probe		= timblogiw_probe,
-	.remove		= timblogiw_remove,
-};
-
-module_platform_driver(timblogiw_platform_driver);
-
-MODULE_DESCRIPTION(TIMBLOGIWIN_NAME);
-MODULE_AUTHOR("Pelagicore AB <info@pelagicore.com>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:"DRIVER_NAME);
diff --git a/drivers/staging/media/tw686x-kh/tw686x-kh-video.c b/drivers/staging/media/tw686x-kh/tw686x-kh-video.c
index 6ecb504a79f9..9bf32aec2fc6 100644
--- a/drivers/staging/media/tw686x-kh/tw686x-kh-video.c
+++ b/drivers/staging/media/tw686x-kh/tw686x-kh-video.c
@@ -130,12 +130,11 @@ static void tw686x_get_format(struct tw686x_video_channel *vc,
 
 static int tw686x_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
 			      unsigned int *nplanes, unsigned int sizes[],
-			      void *alloc_ctxs[])
+			      struct device *alloc_devs[])
 {
 	struct tw686x_video_channel *vc = vb2_get_drv_priv(vq);
 	unsigned int size = vc->width * vc->height * vc->format->depth / 8;
 
-	alloc_ctxs[0] = vc->alloc_ctx;
 	if (*nbuffers < 2)
 		*nbuffers = 2;
 
@@ -645,7 +644,6 @@ void tw686x_kh_video_free(struct tw686x_dev *dev)
 		v4l2_ctrl_handler_free(&vc->ctrl_handler);
 		if (vc->device)
 			video_unregister_device(vc->device);
-		vb2_dma_sg_cleanup_ctx(vc->alloc_ctx);
 		for (n = 0; n < 2; n++) {
 			struct dma_desc *descs = &vc->sg_tables[n];
 
@@ -750,13 +748,6 @@ int tw686x_kh_video_init(struct tw686x_dev *dev)
 			goto error;
 		}
 
-		vc->alloc_ctx = vb2_dma_sg_init_ctx(&dev->pci_dev->dev);
-		if (IS_ERR(vc->alloc_ctx)) {
-			pr_warn("Unable to initialize DMA scatter-gather context\n");
-			err = PTR_ERR(vc->alloc_ctx);
-			goto error;
-		}
-
 		vc->vidq.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 		vc->vidq.io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
 		vc->vidq.drv_priv = vc;
@@ -766,6 +757,7 @@ int tw686x_kh_video_init(struct tw686x_dev *dev)
 		vc->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 		vc->vidq.min_buffers_needed = 2;
 		vc->vidq.lock = &vc->vb_mutex;
+		vc->vidq.dev = &dev->pci_dev->dev;
 		vc->vidq.gfp_flags = GFP_DMA32;
 
 		err = vb2_queue_init(&vc->vidq);
diff --git a/drivers/staging/media/tw686x-kh/tw686x-kh.h b/drivers/staging/media/tw686x-kh/tw686x-kh.h
index dc257967dbc7..6284a90d6fe3 100644
--- a/drivers/staging/media/tw686x-kh/tw686x-kh.h
+++ b/drivers/staging/media/tw686x-kh/tw686x-kh.h
@@ -56,7 +56,6 @@ struct tw686x_video_channel {
 	struct video_device *device;
 	struct dma_desc sg_tables[2];
 	struct tw686x_vb2_buf *curr_bufs[2];
-	void *alloc_ctx;
 	struct vdma_desc *sg_descs[2];
 
 	struct v4l2_ctrl_handler ctrl_handler;
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 7c4efb4417b0..22af12f8b8eb 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -312,7 +312,8 @@ static void iblock_bio_done(struct bio *bio)
 }
 
 static struct bio *
-iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num)
+iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num, int op,
+	       int op_flags)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(cmd->se_dev);
 	struct bio *bio;
@@ -334,18 +335,19 @@ iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num)
 	bio->bi_private = cmd;
 	bio->bi_end_io = &iblock_bio_done;
 	bio->bi_iter.bi_sector = lba;
+	bio_set_op_attrs(bio, op, op_flags);
 
 	return bio;
 }
 
-static void iblock_submit_bios(struct bio_list *list, int rw)
+static void iblock_submit_bios(struct bio_list *list)
 {
 	struct blk_plug plug;
 	struct bio *bio;
 
 	blk_start_plug(&plug);
 	while ((bio = bio_list_pop(list)))
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	blk_finish_plug(&plug);
 }
 
@@ -387,9 +389,10 @@ iblock_execute_sync_cache(struct se_cmd *cmd)
 	bio = bio_alloc(GFP_KERNEL, 0);
 	bio->bi_end_io = iblock_end_io_flush;
 	bio->bi_bdev = ib_dev->ibd_bd;
+	bio->bi_rw = WRITE_FLUSH;
 	if (!immed)
 		bio->bi_private = cmd;
-	submit_bio(WRITE_FLUSH, bio);
+	submit_bio(bio);
 	return 0;
 }
 
@@ -478,7 +481,7 @@ iblock_execute_write_same(struct se_cmd *cmd)
 		goto fail;
 	cmd->priv = ibr;
 
-	bio = iblock_get_bio(cmd, block_lba, 1);
+	bio = iblock_get_bio(cmd, block_lba, 1, REQ_OP_WRITE, 0);
 	if (!bio)
 		goto fail_free_ibr;
 
@@ -491,7 +494,8 @@ iblock_execute_write_same(struct se_cmd *cmd)
 		while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset)
 				!= sg->length) {
 
-			bio = iblock_get_bio(cmd, block_lba, 1);
+			bio = iblock_get_bio(cmd, block_lba, 1, REQ_OP_WRITE,
+					     0);
 			if (!bio)
 				goto fail_put_bios;
 
@@ -504,7 +508,7 @@ iblock_execute_write_same(struct se_cmd *cmd)
 		sectors -= 1;
 	}
 
-	iblock_submit_bios(&list, WRITE);
+	iblock_submit_bios(&list);
 	return 0;
 
 fail_put_bios:
@@ -677,8 +681,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	struct scatterlist *sg;
 	u32 sg_num = sgl_nents;
 	unsigned bio_cnt;
-	int rw = 0;
-	int i;
+	int i, op, op_flags = 0;
 
 	if (data_direction == DMA_TO_DEVICE) {
 		struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
@@ -687,18 +690,15 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		 * Force writethrough using WRITE_FUA if a volatile write cache
 		 * is not enabled, or if initiator set the Force Unit Access bit.
 		 */
+		op = REQ_OP_WRITE;
 		if (test_bit(QUEUE_FLAG_FUA, &q->queue_flags)) {
 			if (cmd->se_cmd_flags & SCF_FUA)
-				rw = WRITE_FUA;
+				op_flags = WRITE_FUA;
 			else if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
-				rw = WRITE_FUA;
-			else
-				rw = WRITE;
-		} else {
-			rw = WRITE;
+				op_flags = WRITE_FUA;
 		}
 	} else {
-		rw = READ;
+		op = REQ_OP_READ;
 	}
 
 	ibr = kzalloc(sizeof(struct iblock_req), GFP_KERNEL);
@@ -712,7 +712,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		return 0;
 	}
 
-	bio = iblock_get_bio(cmd, block_lba, sgl_nents);
+	bio = iblock_get_bio(cmd, block_lba, sgl_nents, op, op_flags);
 	if (!bio)
 		goto fail_free_ibr;
 
@@ -732,11 +732,12 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset)
 				!= sg->length) {
 			if (bio_cnt >= IBLOCK_MAX_BIO_PER_TASK) {
-				iblock_submit_bios(&list, rw);
+				iblock_submit_bios(&list);
 				bio_cnt = 0;
 			}
 
-			bio = iblock_get_bio(cmd, block_lba, sg_num);
+			bio = iblock_get_bio(cmd, block_lba, sg_num, op,
+					     op_flags);
 			if (!bio)
 				goto fail_put_bios;
 
@@ -756,7 +757,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 			goto fail_put_bios;
 	}
 
-	iblock_submit_bios(&list, rw);
+	iblock_submit_bios(&list);
 	iblock_complete_cmd(cmd);
 	return 0;
 
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index de18790eb21c..9125d9358dea 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -876,19 +876,19 @@ static inline struct bio *pscsi_get_bio(int nr_vecs)
 
 static sense_reason_t
 pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
-		enum dma_data_direction data_direction, struct bio **hbio)
+		struct request *req)
 {
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev);
-	struct bio *bio = NULL, *tbio = NULL;
+	struct bio *bio = NULL;
 	struct page *page;
 	struct scatterlist *sg;
 	u32 data_len = cmd->data_length, i, len, bytes, off;
 	int nr_pages = (cmd->data_length + sgl[0].offset +
 			PAGE_SIZE - 1) >> PAGE_SHIFT;
 	int nr_vecs = 0, rc;
-	int rw = (data_direction == DMA_TO_DEVICE);
+	int rw = (cmd->data_direction == DMA_TO_DEVICE);
 
-	*hbio = NULL;
+	BUG_ON(!cmd->data_length);
 
 	pr_debug("PSCSI: nr_pages: %d\n", nr_pages);
 
@@ -922,21 +922,11 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 					goto fail;
 
 				if (rw)
-					bio->bi_rw |= REQ_WRITE;
+					bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 				pr_debug("PSCSI: Allocated bio: %p,"
 					" dir: %s nr_vecs: %d\n", bio,
 					(rw) ? "rw" : "r", nr_vecs);
-				/*
-				 * Set *hbio pointer to handle the case:
-				 * nr_pages > BIO_MAX_PAGES, where additional
-				 * bios need to be added to complete a given
-				 * command.
-				 */
-				if (!*hbio)
-					*hbio = tbio = bio;
-				else
-					tbio = tbio->bi_next = bio;
 			}
 
 			pr_debug("PSCSI: Calling bio_add_pc_page() i: %d"
@@ -955,11 +945,16 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 				pr_debug("PSCSI: Reached bio->bi_vcnt max:"
 					" %d i: %d bio: %p, allocating another"
 					" bio\n", bio->bi_vcnt, i, bio);
+
+				rc = blk_rq_append_bio(req, bio);
+				if (rc) {
+					pr_err("pSCSI: failed to append bio\n");
+					goto fail;
+				}
+
 				/*
 				 * Clear the pointer so that another bio will
-				 * be allocated with pscsi_get_bio() above, the
-				 * current bio has already been set *tbio and
-				 * bio->bi_next.
+				 * be allocated with pscsi_get_bio() above.
 				 */
 				bio = NULL;
 			}
@@ -968,13 +963,16 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		}
 	}
 
+	if (bio) {
+		rc = blk_rq_append_bio(req, bio);
+		if (rc) {
+			pr_err("pSCSI: failed to append bio\n");
+			goto fail;
+		}
+	}
+
 	return 0;
 fail:
-	while (*hbio) {
-		bio = *hbio;
-		*hbio = (*hbio)->bi_next;
-		bio_endio(bio);
-	}
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 
@@ -992,11 +990,9 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 {
 	struct scatterlist *sgl = cmd->t_data_sg;
 	u32 sgl_nents = cmd->t_data_nents;
-	enum dma_data_direction data_direction = cmd->data_direction;
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev);
 	struct pscsi_plugin_task *pt;
 	struct request *req;
-	struct bio *hbio;
 	sense_reason_t ret;
 
 	/*
@@ -1012,31 +1008,21 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 	memcpy(pt->pscsi_cdb, cmd->t_task_cdb,
 		scsi_command_size(cmd->t_task_cdb));
 
-	if (!sgl) {
-		req = blk_get_request(pdv->pdv_sd->request_queue,
-				(data_direction == DMA_TO_DEVICE),
-				GFP_KERNEL);
-		if (IS_ERR(req)) {
-			pr_err("PSCSI: blk_get_request() failed\n");
-			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-			goto fail;
-		}
+	req = blk_get_request(pdv->pdv_sd->request_queue,
+			(cmd->data_direction == DMA_TO_DEVICE),
+			GFP_KERNEL);
+	if (IS_ERR(req)) {
+		pr_err("PSCSI: blk_get_request() failed\n");
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		goto fail;
+	}
 
-		blk_rq_set_block_pc(req);
-	} else {
-		BUG_ON(!cmd->data_length);
+	blk_rq_set_block_pc(req);
 
-		ret = pscsi_map_sg(cmd, sgl, sgl_nents, data_direction, &hbio);
+	if (sgl) {
+		ret = pscsi_map_sg(cmd, sgl, sgl_nents, req);
 		if (ret)
-			goto fail;
-
-		req = blk_make_request(pdv->pdv_sd->request_queue, hbio,
-				       GFP_KERNEL);
-		if (IS_ERR(req)) {
-			pr_err("pSCSI: blk_make_request() failed\n");
-			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-			goto fail_free_bio;
-		}
+			goto fail_put_request;
 	}
 
 	req->end_io = pscsi_req_done;
@@ -1057,13 +1043,8 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 
 	return 0;
 
-fail_free_bio:
-	while (hbio) {
-		struct bio *bio = hbio;
-		hbio = hbio->bi_next;
-		bio_endio(bio);
-	}
-	ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+fail_put_request:
+	blk_put_request(req);
 fail:
 	kfree(pt);
 	return ret;
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 5b4b47ed948b..3788ed74c9ab 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -787,22 +787,34 @@ __cpufreq_cooling_register(struct device_node *np,
 			const struct cpumask *clip_cpus, u32 capacitance,
 			get_static_t plat_static_func)
 {
+	struct cpufreq_policy *policy;
 	struct thermal_cooling_device *cool_dev;
 	struct cpufreq_cooling_device *cpufreq_dev;
 	char dev_name[THERMAL_NAME_LENGTH];
 	struct cpufreq_frequency_table *pos, *table;
+	struct cpumask temp_mask;
 	unsigned int freq, i, num_cpus;
 	int ret;
 
-	table = cpufreq_frequency_get_table(cpumask_first(clip_cpus));
+	cpumask_and(&temp_mask, clip_cpus, cpu_online_mask);
+	policy = cpufreq_cpu_get(cpumask_first(&temp_mask));
+	if (!policy) {
+		pr_debug("%s: CPUFreq policy not found\n", __func__);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	table = policy->freq_table;
 	if (!table) {
 		pr_debug("%s: CPUFreq table not found\n", __func__);
-		return ERR_PTR(-EPROBE_DEFER);
+		cool_dev = ERR_PTR(-ENODEV);
+		goto put_policy;
 	}
 
 	cpufreq_dev = kzalloc(sizeof(*cpufreq_dev), GFP_KERNEL);
-	if (!cpufreq_dev)
-		return ERR_PTR(-ENOMEM);
+	if (!cpufreq_dev) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto put_policy;
+	}
 
 	num_cpus = cpumask_weight(clip_cpus);
 	cpufreq_dev->time_in_idle = kcalloc(num_cpus,
@@ -892,7 +904,7 @@ __cpufreq_cooling_register(struct device_node *np,
 					  CPUFREQ_POLICY_NOTIFIER);
 	mutex_unlock(&cooling_cpufreq_lock);
 
-	return cool_dev;
+	goto put_policy;
 
 remove_idr:
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
@@ -906,6 +918,8 @@ free_time_in_idle:
 	kfree(cpufreq_dev->time_in_idle);
 free_cdev:
 	kfree(cpufreq_dev);
+put_policy:
+	cpufreq_cpu_put(policy);
 
 	return cool_dev;
 }
diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c
index 912694f3d54e..6377e9fee6e5 100644
--- a/drivers/usb/gadget/function/uvc_queue.c
+++ b/drivers/usb/gadget/function/uvc_queue.c
@@ -43,7 +43,7 @@
 
 static int uvc_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
-			   unsigned int sizes[], void *alloc_ctxs[])
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct uvc_video_queue *queue = vb2_get_drv_priv(vq);
 	struct uvc_video *video = container_of(queue, struct uvc_video, queue);
diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig
index e9e5ae521fa6..6e705971d637 100644
--- a/drivers/usb/misc/Kconfig
+++ b/drivers/usb/misc/Kconfig
@@ -260,11 +260,12 @@ config USB_CHAOSKEY
 	tristate "ChaosKey random number generator driver support"
 	depends on HW_RANDOM
 	help
-	  Say Y here if you want to connect an AltusMetrum ChaosKey to
-	  your computer's USB port. The ChaosKey is a hardware random
-	  number generator which hooks into the kernel entropy pool to
-	  ensure a large supply of entropy for /dev/random and
-	  /dev/urandom and also provides direct access via /dev/chaoskeyX
+	  Say Y here if you want to connect an AltusMetrum ChaosKey or
+	  Araneus Alea I to your computer's USB port. These devices
+	  are hardware random number generators which hook into the
+	  kernel entropy pool to ensure a large supply of entropy for
+	  /dev/random and /dev/urandom and also provides direct access
+	  via /dev/chaoskeyX
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called chaoskey.
diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c
index 76350e4ee807..6ddd08a32777 100644
--- a/drivers/usb/misc/chaoskey.c
+++ b/drivers/usb/misc/chaoskey.c
@@ -55,9 +55,13 @@ MODULE_LICENSE("GPL");
 #define CHAOSKEY_VENDOR_ID	0x1d50	/* OpenMoko */
 #define CHAOSKEY_PRODUCT_ID	0x60c6	/* ChaosKey */
 
+#define ALEA_VENDOR_ID		0x12d8	/* Araneus */
+#define ALEA_PRODUCT_ID		0x0001	/* Alea I */
+
 #define CHAOSKEY_BUF_LEN	64	/* max size of USB full speed packet */
 
-#define NAK_TIMEOUT (HZ)		/* stall/wait timeout for device */
+#define NAK_TIMEOUT (HZ)		/* normal stall/wait timeout */
+#define ALEA_FIRST_TIMEOUT (HZ*3)	/* first stall/wait timeout for Alea */
 
 #ifdef CONFIG_USB_DYNAMIC_MINORS
 #define USB_CHAOSKEY_MINOR_BASE 0
@@ -69,6 +73,7 @@ MODULE_LICENSE("GPL");
 
 static const struct usb_device_id chaoskey_table[] = {
 	{ USB_DEVICE(CHAOSKEY_VENDOR_ID, CHAOSKEY_PRODUCT_ID) },
+	{ USB_DEVICE(ALEA_VENDOR_ID, ALEA_PRODUCT_ID) },
 	{ },
 };
 MODULE_DEVICE_TABLE(usb, chaoskey_table);
@@ -84,6 +89,7 @@ struct chaoskey {
 	int open;			/* open count */
 	bool present;			/* device not disconnected */
 	bool reading;			/* ongoing IO */
+	bool reads_started;		/* track first read for Alea */
 	int size;			/* size of buf */
 	int valid;			/* bytes of buf read */
 	int used;			/* bytes of buf consumed */
@@ -188,6 +194,9 @@ static int chaoskey_probe(struct usb_interface *interface,
 
 	dev->in_ep = in_ep;
 
+	if (udev->descriptor.idVendor != ALEA_VENDOR_ID)
+		dev->reads_started = 1;
+
 	dev->size = size;
 	dev->present = 1;
 
@@ -357,6 +366,7 @@ static int _chaoskey_fill(struct chaoskey *dev)
 {
 	DEFINE_WAIT(wait);
 	int result;
+	bool started;
 
 	usb_dbg(dev->interface, "fill");
 
@@ -389,10 +399,17 @@ static int _chaoskey_fill(struct chaoskey *dev)
 		goto out;
 	}
 
+	/* The first read on the Alea takes a little under 2 seconds.
+	 * Reads after the first read take only a few microseconds
+	 * though.  Presumably the entropy-generating circuit needs
+	 * time to ramp up.  So, we wait longer on the first read.
+	 */
+	started = dev->reads_started;
+	dev->reads_started = true;
 	result = wait_event_interruptible_timeout(
 		dev->wait_q,
 		!dev->reading,
-		NAK_TIMEOUT);
+		(started ? NAK_TIMEOUT : ALEA_FIRST_TIMEOUT) );
 
 	if (result < 0)
 		goto out;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 71ccab1d22c6..d012be4ab977 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -493,7 +493,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
 
 	if (size < 0)
 		return size;
-	if (!ops->direct_access)
+	if (!blk_queue_dax(bdev_get_queue(bdev)) || !ops->direct_access)
 		return -EOPNOTSUPP;
 	if ((sector + DIV_ROUND_UP(size, 512)) >
 					part_nr_sects_read(bdev->bd_part))
@@ -1287,7 +1287,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) &&
+		    blk_queue_dax(disk->queue))
 			bdev->bd_inode->i_flags = S_DAX;
 		else
 			bdev->bd_inode->i_flags = 0;
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 7706c8dc5fa6..5d5cae05818d 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1673,6 +1673,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		}
 		bio->bi_bdev = block_ctx->dev->bdev;
 		bio->bi_iter.bi_sector = dev_bytenr >> 9;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
@@ -1685,7 +1686,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 			       "btrfsic: error, failed to add a single page!\n");
 			return -1;
 		}
-		if (submit_bio_wait(READ, bio)) {
+		if (submit_bio_wait(bio)) {
 			printk(KERN_INFO
 			       "btrfsic: read error at logical %llu dev %s!\n",
 			       block_ctx->start, block_ctx->dev->name);
@@ -2206,7 +2207,7 @@ static void btrfsic_bio_end_io(struct bio *bp)
 			       block->dev_bytenr, block->mirror_num);
 		next_block = block->next_in_same_bio;
 		block->iodone_w_error = iodone_w_error;
-		if (block->submit_bio_bh_rw & REQ_FLUSH) {
+		if (block->submit_bio_bh_rw & REQ_PREFLUSH) {
 			dev_state->last_flush_gen++;
 			if ((dev_state->state->print_mask &
 			     BTRFSIC_PRINT_MASK_END_IO_BIO_BH))
@@ -2242,7 +2243,7 @@ static void btrfsic_bh_end_io(struct buffer_head *bh, int uptodate)
 		       block->dev_bytenr, block->mirror_num);
 
 	block->iodone_w_error = iodone_w_error;
-	if (block->submit_bio_bh_rw & REQ_FLUSH) {
+	if (block->submit_bio_bh_rw & REQ_PREFLUSH) {
 		dev_state->last_flush_gen++;
 		if ((dev_state->state->print_mask &
 		     BTRFSIC_PRINT_MASK_END_IO_BIO_BH))
@@ -2855,12 +2856,12 @@ static struct btrfsic_dev_state *btrfsic_dev_state_lookup(
 	return ds;
 }
 
-int btrfsic_submit_bh(int rw, struct buffer_head *bh)
+int btrfsic_submit_bh(int op, int op_flags, struct buffer_head *bh)
 {
 	struct btrfsic_dev_state *dev_state;
 
 	if (!btrfsic_is_initialized)
-		return submit_bh(rw, bh);
+		return submit_bh(op, op_flags, bh);
 
 	mutex_lock(&btrfsic_mutex);
 	/* since btrfsic_submit_bh() might also be called before
@@ -2869,26 +2870,26 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh)
 
 	/* Only called to write the superblock (incl. FLUSH/FUA) */
 	if (NULL != dev_state &&
-	    (rw & WRITE) && bh->b_size > 0) {
+	    (op == REQ_OP_WRITE) && bh->b_size > 0) {
 		u64 dev_bytenr;
 
 		dev_bytenr = 4096 * bh->b_blocknr;
 		if (dev_state->state->print_mask &
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
 			printk(KERN_INFO
-			       "submit_bh(rw=0x%x, blocknr=%llu (bytenr %llu),"
-			       " size=%zu, data=%p, bdev=%p)\n",
-			       rw, (unsigned long long)bh->b_blocknr,
+			       "submit_bh(op=0x%x,0x%x, blocknr=%llu "
+			       "(bytenr %llu), size=%zu, data=%p, bdev=%p)\n",
+			       op, op_flags, (unsigned long long)bh->b_blocknr,
 			       dev_bytenr, bh->b_size, bh->b_data, bh->b_bdev);
 		btrfsic_process_written_block(dev_state, dev_bytenr,
 					      &bh->b_data, 1, NULL,
-					      NULL, bh, rw);
-	} else if (NULL != dev_state && (rw & REQ_FLUSH)) {
+					      NULL, bh, op_flags);
+	} else if (NULL != dev_state && (op_flags & REQ_PREFLUSH)) {
 		if (dev_state->state->print_mask &
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
 			printk(KERN_INFO
-			       "submit_bh(rw=0x%x FLUSH, bdev=%p)\n",
-			       rw, bh->b_bdev);
+			       "submit_bh(op=0x%x,0x%x FLUSH, bdev=%p)\n",
+			       op, op_flags, bh->b_bdev);
 		if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) {
 			if ((dev_state->state->print_mask &
 			     (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
@@ -2906,7 +2907,7 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh)
 			block->never_written = 0;
 			block->iodone_w_error = 0;
 			block->flush_gen = dev_state->last_flush_gen + 1;
-			block->submit_bio_bh_rw = rw;
+			block->submit_bio_bh_rw = op_flags;
 			block->orig_bio_bh_private = bh->b_private;
 			block->orig_bio_bh_end_io.bh = bh->b_end_io;
 			block->next_in_same_bio = NULL;
@@ -2915,10 +2916,10 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh)
 		}
 	}
 	mutex_unlock(&btrfsic_mutex);
-	return submit_bh(rw, bh);
+	return submit_bh(op, op_flags, bh);
 }
 
-static void __btrfsic_submit_bio(int rw, struct bio *bio)
+static void __btrfsic_submit_bio(struct bio *bio)
 {
 	struct btrfsic_dev_state *dev_state;
 
@@ -2930,7 +2931,7 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 	 * btrfsic_mount(), this might return NULL */
 	dev_state = btrfsic_dev_state_lookup(bio->bi_bdev);
 	if (NULL != dev_state &&
-	    (rw & WRITE) && NULL != bio->bi_io_vec) {
+	    (bio_op(bio) == REQ_OP_WRITE) && NULL != bio->bi_io_vec) {
 		unsigned int i;
 		u64 dev_bytenr;
 		u64 cur_bytenr;
@@ -2942,9 +2943,9 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 		if (dev_state->state->print_mask &
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
 			printk(KERN_INFO
-			       "submit_bio(rw=0x%x, bi_vcnt=%u,"
+			       "submit_bio(rw=%d,0x%x, bi_vcnt=%u,"
 			       " bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
-			       rw, bio->bi_vcnt,
+			       bio_op(bio), bio->bi_rw, bio->bi_vcnt,
 			       (unsigned long long)bio->bi_iter.bi_sector,
 			       dev_bytenr, bio->bi_bdev);
 
@@ -2975,18 +2976,18 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 		btrfsic_process_written_block(dev_state, dev_bytenr,
 					      mapped_datav, bio->bi_vcnt,
 					      bio, &bio_is_patched,
-					      NULL, rw);
+					      NULL, bio->bi_rw);
 		while (i > 0) {
 			i--;
 			kunmap(bio->bi_io_vec[i].bv_page);
 		}
 		kfree(mapped_datav);
-	} else if (NULL != dev_state && (rw & REQ_FLUSH)) {
+	} else if (NULL != dev_state && (bio->bi_rw & REQ_PREFLUSH)) {
 		if (dev_state->state->print_mask &
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
 			printk(KERN_INFO
-			       "submit_bio(rw=0x%x FLUSH, bdev=%p)\n",
-			       rw, bio->bi_bdev);
+			       "submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n",
+			       bio_op(bio), bio->bi_rw, bio->bi_bdev);
 		if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) {
 			if ((dev_state->state->print_mask &
 			     (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
@@ -3004,7 +3005,7 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 			block->never_written = 0;
 			block->iodone_w_error = 0;
 			block->flush_gen = dev_state->last_flush_gen + 1;
-			block->submit_bio_bh_rw = rw;
+			block->submit_bio_bh_rw = bio->bi_rw;
 			block->orig_bio_bh_private = bio->bi_private;
 			block->orig_bio_bh_end_io.bio = bio->bi_end_io;
 			block->next_in_same_bio = NULL;
@@ -3016,16 +3017,16 @@ leave:
 	mutex_unlock(&btrfsic_mutex);
 }
 
-void btrfsic_submit_bio(int rw, struct bio *bio)
+void btrfsic_submit_bio(struct bio *bio)
 {
-	__btrfsic_submit_bio(rw, bio);
-	submit_bio(rw, bio);
+	__btrfsic_submit_bio(bio);
+	submit_bio(bio);
 }
 
-int btrfsic_submit_bio_wait(int rw, struct bio *bio)
+int btrfsic_submit_bio_wait(struct bio *bio)
 {
-	__btrfsic_submit_bio(rw, bio);
-	return submit_bio_wait(rw, bio);
+	__btrfsic_submit_bio(bio);
+	return submit_bio_wait(bio);
 }
 
 int btrfsic_mount(struct btrfs_root *root,
diff --git a/fs/btrfs/check-integrity.h b/fs/btrfs/check-integrity.h
index 13b8566c97ab..f78dff1c7e86 100644
--- a/fs/btrfs/check-integrity.h
+++ b/fs/btrfs/check-integrity.h
@@ -20,9 +20,9 @@
 #define __BTRFS_CHECK_INTEGRITY__
 
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-int btrfsic_submit_bh(int rw, struct buffer_head *bh);
-void btrfsic_submit_bio(int rw, struct bio *bio);
-int btrfsic_submit_bio_wait(int rw, struct bio *bio);
+int btrfsic_submit_bh(int op, int op_flags, struct buffer_head *bh);
+void btrfsic_submit_bio(struct bio *bio);
+int btrfsic_submit_bio_wait(struct bio *bio);
 #else
 #define btrfsic_submit_bh submit_bh
 #define btrfsic_submit_bio submit_bio
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 658c39b70fba..cefedabf0a92 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -363,6 +363,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		kfree(cb);
 		return -ENOMEM;
 	}
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	bio->bi_private = cb;
 	bio->bi_end_io = end_compressed_bio_write;
 	atomic_inc(&cb->pending_bios);
@@ -373,7 +374,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		page = compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		if (bio->bi_iter.bi_size)
-			ret = io_tree->ops->merge_bio_hook(WRITE, page, 0,
+			ret = io_tree->ops->merge_bio_hook(page, 0,
 							   PAGE_SIZE,
 							   bio, 0);
 		else
@@ -401,13 +402,14 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				BUG_ON(ret); /* -ENOMEM */
 			}
 
-			ret = btrfs_map_bio(root, WRITE, bio, 0, 1);
+			ret = btrfs_map_bio(root, bio, 0, 1);
 			BUG_ON(ret); /* -ENOMEM */
 
 			bio_put(bio);
 
 			bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
 			BUG_ON(!bio);
+			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			bio->bi_private = cb;
 			bio->bi_end_io = end_compressed_bio_write;
 			bio_add_page(bio, page, PAGE_SIZE, 0);
@@ -431,7 +433,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
-	ret = btrfs_map_bio(root, WRITE, bio, 0, 1);
+	ret = btrfs_map_bio(root, bio, 0, 1);
 	BUG_ON(ret); /* -ENOMEM */
 
 	bio_put(bio);
@@ -646,6 +648,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
 	if (!comp_bio)
 		goto fail2;
+	bio_set_op_attrs (comp_bio, REQ_OP_READ, 0);
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
 	atomic_inc(&cb->pending_bios);
@@ -656,7 +659,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		page->index = em_start >> PAGE_SHIFT;
 
 		if (comp_bio->bi_iter.bi_size)
-			ret = tree->ops->merge_bio_hook(READ, page, 0,
+			ret = tree->ops->merge_bio_hook(page, 0,
 							PAGE_SIZE,
 							comp_bio, 0);
 		else
@@ -687,8 +690,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			sums += DIV_ROUND_UP(comp_bio->bi_iter.bi_size,
 					     root->sectorsize);
 
-			ret = btrfs_map_bio(root, READ, comp_bio,
-					    mirror_num, 0);
+			ret = btrfs_map_bio(root, comp_bio, mirror_num, 0);
 			if (ret) {
 				bio->bi_error = ret;
 				bio_endio(comp_bio);
@@ -699,6 +701,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			comp_bio = compressed_bio_alloc(bdev, cur_disk_byte,
 							GFP_NOFS);
 			BUG_ON(!comp_bio);
+			bio_set_op_attrs(comp_bio, REQ_OP_READ, 0);
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
 
@@ -717,7 +720,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
-	ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0);
+	ret = btrfs_map_bio(root, comp_bio, mirror_num, 0);
 	if (ret) {
 		bio->bi_error = ret;
 		bio_endio(comp_bio);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4274a7bfdaed..b2620d1f883f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3091,7 +3091,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *new_root,
 			     struct btrfs_root *parent_root,
 			     u64 new_dirid);
-int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
+int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio,
 			 unsigned long bio_flags);
 int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 60ce1190307b..9a726ded2c6d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -124,7 +124,6 @@ struct async_submit_bio {
 	struct list_head list;
 	extent_submit_bio_hook_t *submit_bio_start;
 	extent_submit_bio_hook_t *submit_bio_done;
-	int rw;
 	int mirror_num;
 	unsigned long bio_flags;
 	/*
@@ -727,7 +726,7 @@ static void end_workqueue_bio(struct bio *bio)
 	fs_info = end_io_wq->info;
 	end_io_wq->error = bio->bi_error;
 
-	if (bio->bi_rw & REQ_WRITE) {
+	if (bio_op(bio) == REQ_OP_WRITE) {
 		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
 			wq = fs_info->endio_meta_write_workers;
 			func = btrfs_endio_meta_write_helper;
@@ -797,7 +796,7 @@ static void run_one_async_start(struct btrfs_work *work)
 	int ret;
 
 	async = container_of(work, struct  async_submit_bio, work);
-	ret = async->submit_bio_start(async->inode, async->rw, async->bio,
+	ret = async->submit_bio_start(async->inode, async->bio,
 				      async->mirror_num, async->bio_flags,
 				      async->bio_offset);
 	if (ret)
@@ -830,9 +829,8 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
-	async->submit_bio_done(async->inode, async->rw, async->bio,
-			       async->mirror_num, async->bio_flags,
-			       async->bio_offset);
+	async->submit_bio_done(async->inode, async->bio, async->mirror_num,
+			       async->bio_flags, async->bio_offset);
 }
 
 static void run_one_async_free(struct btrfs_work *work)
@@ -844,7 +842,7 @@ static void run_one_async_free(struct btrfs_work *work)
 }
 
 int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
-			int rw, struct bio *bio, int mirror_num,
+			struct bio *bio, int mirror_num,
 			unsigned long bio_flags,
 			u64 bio_offset,
 			extent_submit_bio_hook_t *submit_bio_start,
@@ -857,7 +855,6 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 		return -ENOMEM;
 
 	async->inode = inode;
-	async->rw = rw;
 	async->bio = bio;
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
@@ -873,7 +870,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 
 	atomic_inc(&fs_info->nr_async_submits);
 
-	if (rw & REQ_SYNC)
+	if (bio->bi_rw & REQ_SYNC)
 		btrfs_set_work_high_priority(&async->work);
 
 	btrfs_queue_work(fs_info->workers, &async->work);
@@ -903,9 +900,8 @@ static int btree_csum_one_bio(struct bio *bio)
 	return ret;
 }
 
-static int __btree_submit_bio_start(struct inode *inode, int rw,
-				    struct bio *bio, int mirror_num,
-				    unsigned long bio_flags,
+static int __btree_submit_bio_start(struct inode *inode, struct bio *bio,
+				    int mirror_num, unsigned long bio_flags,
 				    u64 bio_offset)
 {
 	/*
@@ -915,7 +911,7 @@ static int __btree_submit_bio_start(struct inode *inode, int rw,
 	return btree_csum_one_bio(bio);
 }
 
-static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
+static int __btree_submit_bio_done(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags,
 				 u64 bio_offset)
 {
@@ -925,7 +921,7 @@ static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
 	 * when we're called for a write, we're already in the async
 	 * submission context.  Just jump into btrfs_map_bio
 	 */
-	ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
+	ret = btrfs_map_bio(BTRFS_I(inode)->root, bio, mirror_num, 1);
 	if (ret) {
 		bio->bi_error = ret;
 		bio_endio(bio);
@@ -944,14 +940,14 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
 	return 1;
 }
 
-static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
+static int btree_submit_bio_hook(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags,
 				 u64 bio_offset)
 {
 	int async = check_async_write(inode, bio_flags);
 	int ret;
 
-	if (!(rw & REQ_WRITE)) {
+	if (bio_op(bio) != REQ_OP_WRITE) {
 		/*
 		 * called for a read, do the setup so that checksum validation
 		 * can happen in the async kernel threads
@@ -960,21 +956,19 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 					  bio, BTRFS_WQ_ENDIO_METADATA);
 		if (ret)
 			goto out_w_error;
-		ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
-				    mirror_num, 0);
+		ret = btrfs_map_bio(BTRFS_I(inode)->root, bio, mirror_num, 0);
 	} else if (!async) {
 		ret = btree_csum_one_bio(bio);
 		if (ret)
 			goto out_w_error;
-		ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
-				    mirror_num, 0);
+		ret = btrfs_map_bio(BTRFS_I(inode)->root, bio, mirror_num, 0);
 	} else {
 		/*
 		 * kthread helpers are used to submit writes so that
 		 * checksumming can happen in parallel across all CPUs
 		 */
 		ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
-					  inode, rw, bio, mirror_num, 0,
+					  inode, bio, mirror_num, 0,
 					  bio_offset,
 					  __btree_submit_bio_start,
 					  __btree_submit_bio_done);
@@ -3418,9 +3412,9 @@ static int write_dev_supers(struct btrfs_device *device,
 		 * to go down lazy.
 		 */
 		if (i == 0)
-			ret = btrfsic_submit_bh(WRITE_FUA, bh);
+			ret = btrfsic_submit_bh(REQ_OP_WRITE, WRITE_FUA, bh);
 		else
-			ret = btrfsic_submit_bh(WRITE_SYNC, bh);
+			ret = btrfsic_submit_bh(REQ_OP_WRITE, WRITE_SYNC, bh);
 		if (ret)
 			errors++;
 	}
@@ -3484,12 +3478,13 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 
 	bio->bi_end_io = btrfs_end_empty_barrier;
 	bio->bi_bdev = device->bdev;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
 	device->flush_bio = bio;
 
 	bio_get(bio);
-	btrfsic_submit_bio(WRITE_FLUSH, bio);
+	btrfsic_submit_bio(bio);
 
 	return 0;
 }
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index acba821499a9..dbf3e1aab69e 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -122,7 +122,7 @@ void btrfs_csum_final(u32 crc, char *result);
 int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 			enum btrfs_wq_endio_type metadata);
 int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
-			int rw, struct bio *bio, int mirror_num,
+			struct bio *bio, int mirror_num,
 			unsigned long bio_flags, u64 bio_offset,
 			extent_submit_bio_hook_t *submit_bio_start,
 			extent_submit_bio_hook_t *submit_bio_done);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 82b912a293ab..b480fd555774 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2048,7 +2048,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 	 */
 	btrfs_bio_counter_inc_blocked(root->fs_info);
 	/* Tell the block device(s) that the sectors can be discarded */
-	ret = btrfs_map_block(root->fs_info, REQ_DISCARD,
+	ret = btrfs_map_block(root->fs_info, REQ_OP_DISCARD,
 			      bytenr, &num_bytes, &bbio, 0);
 	/* Error condition is -ENOMEM */
 	if (!ret) {
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e91d55837dd2..cee4cb99b8ce 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2049,9 +2049,10 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 		return -EIO;
 	}
 	bio->bi_bdev = dev->bdev;
+	bio->bi_rw = WRITE_SYNC;
 	bio_add_page(bio, page, length, pg_offset);
 
-	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
+	if (btrfsic_submit_bio_wait(bio)) {
 		/* try to remap that extent elsewhere? */
 		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
@@ -2386,7 +2387,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	int read_mode;
 	int ret;
 
-	BUG_ON(failed_bio->bi_rw & REQ_WRITE);
+	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
 
 	ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
 	if (ret)
@@ -2412,12 +2413,12 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		free_io_failure(inode, failrec);
 		return -EIO;
 	}
+	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
 	pr_debug("Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d\n",
 		 read_mode, failrec->this_mirror, failrec->in_validation);
 
-	ret = tree->ops->submit_bio_hook(inode, read_mode, bio,
-					 failrec->this_mirror,
+	ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror,
 					 failrec->bio_flags, 0);
 	if (ret) {
 		free_io_failure(inode, failrec);
@@ -2723,8 +2724,8 @@ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 }
 
 
-static int __must_check submit_one_bio(int rw, struct bio *bio,
-				       int mirror_num, unsigned long bio_flags)
+static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
+				       unsigned long bio_flags)
 {
 	int ret = 0;
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
@@ -2735,33 +2736,32 @@ static int __must_check submit_one_bio(int rw, struct bio *bio,
 	start = page_offset(page) + bvec->bv_offset;
 
 	bio->bi_private = NULL;
-
 	bio_get(bio);
 
 	if (tree->ops && tree->ops->submit_bio_hook)
-		ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
+		ret = tree->ops->submit_bio_hook(page->mapping->host, bio,
 					   mirror_num, bio_flags, start);
 	else
-		btrfsic_submit_bio(rw, bio);
+		btrfsic_submit_bio(bio);
 
 	bio_put(bio);
 	return ret;
 }
 
-static int merge_bio(int rw, struct extent_io_tree *tree, struct page *page,
+static int merge_bio(struct extent_io_tree *tree, struct page *page,
 		     unsigned long offset, size_t size, struct bio *bio,
 		     unsigned long bio_flags)
 {
 	int ret = 0;
 	if (tree->ops && tree->ops->merge_bio_hook)
-		ret = tree->ops->merge_bio_hook(rw, page, offset, size, bio,
+		ret = tree->ops->merge_bio_hook(page, offset, size, bio,
 						bio_flags);
 	BUG_ON(ret < 0);
 	return ret;
 
 }
 
-static int submit_extent_page(int rw, struct extent_io_tree *tree,
+static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree,
 			      struct writeback_control *wbc,
 			      struct page *page, sector_t sector,
 			      size_t size, unsigned long offset,
@@ -2789,10 +2789,9 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 
 		if (prev_bio_flags != bio_flags || !contig ||
 		    force_bio_submit ||
-		    merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
+		    merge_bio(tree, page, offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, offset) < page_size) {
-			ret = submit_one_bio(rw, bio, mirror_num,
-					     prev_bio_flags);
+			ret = submit_one_bio(bio, mirror_num, prev_bio_flags);
 			if (ret < 0) {
 				*bio_ret = NULL;
 				return ret;
@@ -2813,6 +2812,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 	bio_add_page(bio, page, page_size, offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
+	bio_set_op_attrs(bio, op, op_flags);
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
 		wbc_account_io(wbc, page, page_size);
@@ -2821,7 +2821,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 	if (bio_ret)
 		*bio_ret = bio;
 	else
-		ret = submit_one_bio(rw, bio, mirror_num, bio_flags);
+		ret = submit_one_bio(bio, mirror_num, bio_flags);
 
 	return ret;
 }
@@ -2885,7 +2885,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 			 get_extent_t *get_extent,
 			 struct extent_map **em_cached,
 			 struct bio **bio, int mirror_num,
-			 unsigned long *bio_flags, int rw,
+			 unsigned long *bio_flags, int read_flags,
 			 u64 *prev_em_start)
 {
 	struct inode *inode = page->mapping->host;
@@ -3068,8 +3068,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 		}
 
 		pnr -= page->index;
-		ret = submit_extent_page(rw, tree, NULL, page,
-					 sector, disk_io_size, pg_offset,
+		ret = submit_extent_page(REQ_OP_READ, read_flags, tree, NULL,
+					 page, sector, disk_io_size, pg_offset,
 					 bdev, bio, pnr,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
@@ -3100,7 +3100,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 					     get_extent_t *get_extent,
 					     struct extent_map **em_cached,
 					     struct bio **bio, int mirror_num,
-					     unsigned long *bio_flags, int rw,
+					     unsigned long *bio_flags,
 					     u64 *prev_em_start)
 {
 	struct inode *inode;
@@ -3121,7 +3121,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 
 	for (index = 0; index < nr_pages; index++) {
 		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
-			      mirror_num, bio_flags, rw, prev_em_start);
+			      mirror_num, bio_flags, 0, prev_em_start);
 		put_page(pages[index]);
 	}
 }
@@ -3131,7 +3131,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 			       int nr_pages, get_extent_t *get_extent,
 			       struct extent_map **em_cached,
 			       struct bio **bio, int mirror_num,
-			       unsigned long *bio_flags, int rw,
+			       unsigned long *bio_flags,
 			       u64 *prev_em_start)
 {
 	u64 start = 0;
@@ -3153,7 +3153,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 						  index - first_index, start,
 						  end, get_extent, em_cached,
 						  bio, mirror_num, bio_flags,
-						  rw, prev_em_start);
+						  prev_em_start);
 			start = page_start;
 			end = start + PAGE_SIZE - 1;
 			first_index = index;
@@ -3164,7 +3164,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 		__do_contiguous_readpages(tree, &pages[first_index],
 					  index - first_index, start,
 					  end, get_extent, em_cached, bio,
-					  mirror_num, bio_flags, rw,
+					  mirror_num, bio_flags,
 					  prev_em_start);
 }
 
@@ -3172,7 +3172,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 				   struct page *page,
 				   get_extent_t *get_extent,
 				   struct bio **bio, int mirror_num,
-				   unsigned long *bio_flags, int rw)
+				   unsigned long *bio_flags, int read_flags)
 {
 	struct inode *inode = page->mapping->host;
 	struct btrfs_ordered_extent *ordered;
@@ -3192,7 +3192,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	}
 
 	ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
-			    bio_flags, rw, NULL);
+			    bio_flags, read_flags, NULL);
 	return ret;
 }
 
@@ -3204,9 +3204,9 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	int ret;
 
 	ret = __extent_read_full_page(tree, page, get_extent, &bio, mirror_num,
-				      &bio_flags, READ);
+				      &bio_flags, 0);
 	if (bio)
-		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
+		ret = submit_one_bio(bio, mirror_num, bio_flags);
 	return ret;
 }
 
@@ -3440,8 +3440,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			       page->index, cur, end);
 		}
 
-		ret = submit_extent_page(write_flags, tree, wbc, page,
-					 sector, iosize, pg_offset,
+		ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
+					 page, sector, iosize, pg_offset,
 					 bdev, &epd->bio, max_nr,
 					 end_bio_extent_writepage,
 					 0, 0, 0, false);
@@ -3480,13 +3480,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	size_t pg_offset = 0;
 	loff_t i_size = i_size_read(inode);
 	unsigned long end_index = i_size >> PAGE_SHIFT;
-	int write_flags;
+	int write_flags = 0;
 	unsigned long nr_written = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		write_flags = WRITE_SYNC;
-	else
-		write_flags = WRITE;
 
 	trace___extent_writepage(page, inode, wbc);
 
@@ -3730,7 +3728,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	u64 offset = eb->start;
 	unsigned long i, num_pages;
 	unsigned long bio_flags = 0;
-	int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
+	int write_flags = (epd->sync_io ? WRITE_SYNC : 0) | REQ_META;
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
@@ -3744,9 +3742,10 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 
 		clear_page_dirty_for_io(p);
 		set_page_writeback(p);
-		ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
-					 PAGE_SIZE, 0, bdev, &epd->bio,
-					 -1, end_bio_extent_buffer_writepage,
+		ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
+					 p, offset >> 9, PAGE_SIZE, 0, bdev,
+					 &epd->bio, -1,
+					 end_bio_extent_buffer_writepage,
 					 0, epd->bio_flags, bio_flags, false);
 		epd->bio_flags = bio_flags;
 		if (ret) {
@@ -4056,13 +4055,12 @@ retry:
 static void flush_epd_write_bio(struct extent_page_data *epd)
 {
 	if (epd->bio) {
-		int rw = WRITE;
 		int ret;
 
-		if (epd->sync_io)
-			rw = WRITE_SYNC;
+		bio_set_op_attrs(epd->bio, REQ_OP_WRITE,
+				 epd->sync_io ? WRITE_SYNC : 0);
 
-		ret = submit_one_bio(rw, epd->bio, 0, epd->bio_flags);
+		ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
 		BUG_ON(ret < 0); /* -ENOMEM */
 		epd->bio = NULL;
 	}
@@ -4190,19 +4188,19 @@ int extent_readpages(struct extent_io_tree *tree,
 		if (nr < ARRAY_SIZE(pagepool))
 			continue;
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ, &prev_em_start);
+				   &bio, 0, &bio_flags, &prev_em_start);
 		nr = 0;
 	}
 	if (nr)
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ, &prev_em_start);
+				   &bio, 0, &bio_flags, &prev_em_start);
 
 	if (em_cached)
 		free_extent_map(em_cached);
 
 	BUG_ON(!list_empty(pages));
 	if (bio)
-		return submit_one_bio(READ, bio, 0, bio_flags);
+		return submit_one_bio(bio, 0, bio_flags);
 	return 0;
 }
 
@@ -5237,7 +5235,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			err = __extent_read_full_page(tree, page,
 						      get_extent, &bio,
 						      mirror_num, &bio_flags,
-						      READ | REQ_META);
+						      REQ_META);
 			if (err)
 				ret = err;
 		} else {
@@ -5246,8 +5244,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	}
 
 	if (bio) {
-		err = submit_one_bio(READ | REQ_META, bio, mirror_num,
-				     bio_flags);
+		err = submit_one_bio(bio, mirror_num, bio_flags);
 		if (err)
 			return err;
 	}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index c0c1c4fef6ce..bc2729a7612d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -63,16 +63,16 @@ struct btrfs_root;
 struct btrfs_io_bio;
 struct io_failure_record;
 
-typedef	int (extent_submit_bio_hook_t)(struct inode *inode, int rw,
-				       struct bio *bio, int mirror_num,
-				       unsigned long bio_flags, u64 bio_offset);
+typedef	int (extent_submit_bio_hook_t)(struct inode *inode, struct bio *bio,
+				       int mirror_num, unsigned long bio_flags,
+				       u64 bio_offset);
 struct extent_io_ops {
 	int (*fill_delalloc)(struct inode *inode, struct page *locked_page,
 			     u64 start, u64 end, int *page_started,
 			     unsigned long *nr_written);
 	int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
 	extent_submit_bio_hook_t *submit_bio_hook;
-	int (*merge_bio_hook)(int rw, struct page *page, unsigned long offset,
+	int (*merge_bio_hook)(struct page *page, unsigned long offset,
 			      size_t size, struct bio *bio,
 			      unsigned long bio_flags);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4421954720b8..df731c0ebec7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1823,7 +1823,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
  * extent_io.c merge_bio_hook, this must check the chunk tree to make sure
  * we don't create bios that span stripes or chunks
  */
-int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
+int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio,
 			 unsigned long bio_flags)
 {
@@ -1838,7 +1838,7 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
 
 	length = bio->bi_iter.bi_size;
 	map_length = length;
-	ret = btrfs_map_block(root->fs_info, rw, logical,
+	ret = btrfs_map_block(root->fs_info, bio_op(bio), logical,
 			      &map_length, NULL, 0);
 	/* Will always return 0 with map_multi == NULL */
 	BUG_ON(ret < 0);
@@ -1855,9 +1855,8 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_start(struct inode *inode, int rw,
-				    struct bio *bio, int mirror_num,
-				    unsigned long bio_flags,
+static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
+				    int mirror_num, unsigned long bio_flags,
 				    u64 bio_offset)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -1876,14 +1875,14 @@ static int __btrfs_submit_bio_start(struct inode *inode, int rw,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
+static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
 			  int mirror_num, unsigned long bio_flags,
 			  u64 bio_offset)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
-	ret = btrfs_map_bio(root, rw, bio, mirror_num, 1);
+	ret = btrfs_map_bio(root, bio, mirror_num, 1);
 	if (ret) {
 		bio->bi_error = ret;
 		bio_endio(bio);
@@ -1895,7 +1894,7 @@ static int __btrfs_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
  * extent_io.c submission hook. This does the right thing for csum calculation
  * on write, or reading the csums from the tree before a read
  */
-static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
+static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 			  int mirror_num, unsigned long bio_flags,
 			  u64 bio_offset)
 {
@@ -1910,7 +1909,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 	if (btrfs_is_free_space_inode(inode))
 		metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
 
-	if (!(rw & REQ_WRITE)) {
+	if (bio_op(bio) != REQ_OP_WRITE) {
 		ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata);
 		if (ret)
 			goto out;
@@ -1932,7 +1931,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 			goto mapit;
 		/* we're doing a write, do the async checksumming */
 		ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
-				   inode, rw, bio, mirror_num,
+				   inode, bio, mirror_num,
 				   bio_flags, bio_offset,
 				   __btrfs_submit_bio_start,
 				   __btrfs_submit_bio_done);
@@ -1944,7 +1943,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 	}
 
 mapit:
-	ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
+	ret = btrfs_map_bio(root, bio, mirror_num, 0);
 
 out:
 	if (ret < 0) {
@@ -7790,12 +7789,12 @@ err:
 }
 
 static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
-					int rw, int mirror_num)
+					int mirror_num)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
-	BUG_ON(rw & REQ_WRITE);
+	BUG_ON(bio_op(bio) == REQ_OP_WRITE);
 
 	bio_get(bio);
 
@@ -7804,7 +7803,7 @@ static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
 	if (ret)
 		goto err;
 
-	ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
+	ret = btrfs_map_bio(root, bio, mirror_num, 0);
 err:
 	bio_put(bio);
 	return ret;
@@ -7855,7 +7854,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	int read_mode;
 	int ret;
 
-	BUG_ON(failed_bio->bi_rw & REQ_WRITE);
+	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
 
 	ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
 	if (ret)
@@ -7883,13 +7882,13 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 		free_io_failure(inode, failrec);
 		return -EIO;
 	}
+	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
 	btrfs_debug(BTRFS_I(inode)->root->fs_info,
 		    "Repair DIO Read Error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d\n",
 		    read_mode, failrec->this_mirror, failrec->in_validation);
 
-	ret = submit_dio_repair_bio(inode, bio, read_mode,
-				    failrec->this_mirror);
+	ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
 	if (ret) {
 		free_io_failure(inode, failrec);
 		bio_put(bio);
@@ -8179,7 +8178,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
 	bio_put(bio);
 }
 
-static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw,
+static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
 				    struct bio *bio, int mirror_num,
 				    unsigned long bio_flags, u64 offset)
 {
@@ -8197,8 +8196,8 @@ static void btrfs_end_dio_bio(struct bio *bio)
 
 	if (err)
 		btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
-			   "direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
-			   btrfs_ino(dip->inode), bio->bi_rw,
+			   "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d",
+			   btrfs_ino(dip->inode), bio_op(bio), bio->bi_rw,
 			   (unsigned long long)bio->bi_iter.bi_sector,
 			   bio->bi_iter.bi_size, err);
 
@@ -8272,11 +8271,11 @@ static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,
 }
 
 static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
-					 int rw, u64 file_offset, int skip_sum,
+					 u64 file_offset, int skip_sum,
 					 int async_submit)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
-	int write = rw & REQ_WRITE;
+	bool write = bio_op(bio) == REQ_OP_WRITE;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
@@ -8297,8 +8296,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 
 	if (write && async_submit) {
 		ret = btrfs_wq_submit_bio(root->fs_info,
-				   inode, rw, bio, 0, 0,
-				   file_offset,
+				   inode, bio, 0, 0, file_offset,
 				   __btrfs_submit_bio_start_direct_io,
 				   __btrfs_submit_bio_done);
 		goto err;
@@ -8317,13 +8315,13 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 			goto err;
 	}
 map:
-	ret = btrfs_map_bio(root, rw, bio, 0, async_submit);
+	ret = btrfs_map_bio(root, bio, 0, async_submit);
 err:
 	bio_put(bio);
 	return ret;
 }
 
-static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
+static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 				    int skip_sum)
 {
 	struct inode *inode = dip->inode;
@@ -8342,8 +8340,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	int i;
 
 	map_length = orig_bio->bi_iter.bi_size;
-	ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
-			      &map_length, NULL, 0);
+	ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
+			      start_sector << 9, &map_length, NULL, 0);
 	if (ret)
 		return -EIO;
 
@@ -8363,6 +8361,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	if (!bio)
 		return -ENOMEM;
 
+	bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw);
 	bio->bi_private = dip;
 	bio->bi_end_io = btrfs_end_dio_bio;
 	btrfs_io_bio(bio)->logical = file_offset;
@@ -8382,7 +8381,7 @@ next_block:
 			 * before we're done setting it up
 			 */
 			atomic_inc(&dip->pending_bios);
-			ret = __btrfs_submit_dio_bio(bio, inode, rw,
+			ret = __btrfs_submit_dio_bio(bio, inode,
 						     file_offset, skip_sum,
 						     async_submit);
 			if (ret) {
@@ -8400,12 +8399,13 @@ next_block:
 						  start_sector, GFP_NOFS);
 			if (!bio)
 				goto out_err;
+			bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw);
 			bio->bi_private = dip;
 			bio->bi_end_io = btrfs_end_dio_bio;
 			btrfs_io_bio(bio)->logical = file_offset;
 
 			map_length = orig_bio->bi_iter.bi_size;
-			ret = btrfs_map_block(root->fs_info, rw,
+			ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
 					      start_sector << 9,
 					      &map_length, NULL, 0);
 			if (ret) {
@@ -8425,7 +8425,7 @@ next_block:
 	}
 
 submit:
-	ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum,
+	ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
 				     async_submit);
 	if (!ret)
 		return 0;
@@ -8445,14 +8445,14 @@ out_err:
 	return 0;
 }
 
-static void btrfs_submit_direct(int rw, struct bio *dio_bio,
-				struct inode *inode, loff_t file_offset)
+static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+				loff_t file_offset)
 {
 	struct btrfs_dio_private *dip = NULL;
 	struct bio *io_bio = NULL;
 	struct btrfs_io_bio *btrfs_bio;
 	int skip_sum;
-	int write = rw & REQ_WRITE;
+	bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
 	int ret = 0;
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
@@ -8503,7 +8503,7 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 			dio_data->unsubmitted_oe_range_end;
 	}
 
-	ret = btrfs_submit_direct_hook(rw, dip, skip_sum);
+	ret = btrfs_submit_direct_hook(dip, skip_sum);
 	if (!ret)
 		return;
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index f8b6d411a034..cd8d302a1f61 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1320,7 +1320,9 @@ write_data:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		submit_bio(WRITE, bio);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+		submit_bio(bio);
 	}
 	return;
 
@@ -1573,11 +1575,12 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_rmw_end_io;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio,
 				    BTRFS_WQ_ENDIO_RAID56);
 
-		submit_bio(READ, bio);
+		submit_bio(bio);
 	}
 	/* the actual write will happen once the reads are done */
 	return 0;
@@ -2097,11 +2100,12 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_recover_end_io;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio,
 				    BTRFS_WQ_ENDIO_RAID56);
 
-		submit_bio(READ, bio);
+		submit_bio(bio);
 	}
 out:
 	return 0;
@@ -2433,7 +2437,9 @@ submit_write:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		submit_bio(WRITE, bio);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+		submit_bio(bio);
 	}
 	return;
 
@@ -2610,11 +2616,12 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid56_parity_scrub_end_io;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio,
 				    BTRFS_WQ_ENDIO_RAID56);
 
-		submit_bio(READ, bio);
+		submit_bio(bio);
 	}
 	/* the actual write will happen once the reads are done */
 	return;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 70427ef66b04..e08b6bc676e3 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1504,8 +1504,9 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 				sblock->no_io_error_seen = 0;
 		} else {
 			bio->bi_iter.bi_sector = page->physical >> 9;
+			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 
-			if (btrfsic_submit_bio_wait(READ, bio))
+			if (btrfsic_submit_bio_wait(bio))
 				sblock->no_io_error_seen = 0;
 		}
 
@@ -1583,6 +1584,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 			return -EIO;
 		bio->bi_bdev = page_bad->dev->bdev;
 		bio->bi_iter.bi_sector = page_bad->physical >> 9;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 		ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
 		if (PAGE_SIZE != ret) {
@@ -1590,7 +1592,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 			return -EIO;
 		}
 
-		if (btrfsic_submit_bio_wait(WRITE, bio)) {
+		if (btrfsic_submit_bio_wait(bio)) {
 			btrfs_dev_stat_inc_and_print(page_bad->dev,
 				BTRFS_DEV_STAT_WRITE_ERRS);
 			btrfs_dev_replace_stats_inc(
@@ -1684,6 +1686,7 @@ again:
 		bio->bi_end_io = scrub_wr_bio_end_io;
 		bio->bi_bdev = sbio->dev->bdev;
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 		sbio->err = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical_for_dev_replace ||
@@ -1731,7 +1734,7 @@ static void scrub_wr_submit(struct scrub_ctx *sctx)
 	 * orders the requests before sending them to the driver which
 	 * doubled the write performance on spinning disks when measured
 	 * with Linux 3.5 */
-	btrfsic_submit_bio(WRITE, sbio->bio);
+	btrfsic_submit_bio(sbio->bio);
 }
 
 static void scrub_wr_bio_end_io(struct bio *bio)
@@ -2041,7 +2044,7 @@ static void scrub_submit(struct scrub_ctx *sctx)
 	sbio = sctx->bios[sctx->curr];
 	sctx->curr = -1;
 	scrub_pending_bio_inc(sctx);
-	btrfsic_submit_bio(READ, sbio->bio);
+	btrfsic_submit_bio(sbio->bio);
 }
 
 static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx,
@@ -2088,6 +2091,7 @@ again:
 		bio->bi_end_io = scrub_bio_end_io;
 		bio->bi_bdev = sbio->dev->bdev;
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
+		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		sbio->err = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical ||
@@ -4436,6 +4440,7 @@ static int write_page_nocow(struct scrub_ctx *sctx,
 	bio->bi_iter.bi_size = 0;
 	bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
 	bio->bi_bdev = dev->bdev;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_SYNC);
 	ret = bio_add_page(bio, page, PAGE_SIZE, 0);
 	if (ret != PAGE_SIZE) {
 leave_with_eio:
@@ -4444,7 +4449,7 @@ leave_with_eio:
 		return -EIO;
 	}
 
-	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio))
+	if (btrfsic_submit_bio_wait(bio))
 		goto leave_with_eio;
 
 	bio_put(bio);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 589f128173b1..0fb4a959012e 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -462,7 +462,7 @@ loop_lock:
 			sync_pending = 0;
 		}
 
-		btrfsic_submit_bio(cur->bi_rw, cur);
+		btrfsic_submit_bio(cur);
 		num_run++;
 		batch_run++;
 
@@ -5260,7 +5260,7 @@ void btrfs_put_bbio(struct btrfs_bio *bbio)
 		kfree(bbio);
 }
 
-static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
+static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 			     u64 logical, u64 *length,
 			     struct btrfs_bio **bbio_ret,
 			     int mirror_num, int need_raid_map)
@@ -5346,7 +5346,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		raid56_full_stripe_start *= full_stripe_len;
 	}
 
-	if (rw & REQ_DISCARD) {
+	if (op == REQ_OP_DISCARD) {
 		/* we don't discard raid56 yet */
 		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 			ret = -EOPNOTSUPP;
@@ -5359,7 +5359,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		   For other RAID types and for RAID[56] reads, just allow a single
 		   stripe (on a single disk). */
 		if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
-		    (rw & REQ_WRITE)) {
+		    (op == REQ_OP_WRITE)) {
 			max_len = stripe_len * nr_data_stripes(map) -
 				(offset - raid56_full_stripe_start);
 		} else {
@@ -5384,8 +5384,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		btrfs_dev_replace_set_lock_blocking(dev_replace);
 
 	if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
-	    !(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)) &&
-	    dev_replace->tgtdev != NULL) {
+	    op != REQ_OP_WRITE && op != REQ_OP_DISCARD &&
+	    op != REQ_GET_READ_MIRRORS && dev_replace->tgtdev != NULL) {
 		/*
 		 * in dev-replace case, for repair case (that's the only
 		 * case where the mirror is selected explicitly when
@@ -5472,15 +5472,17 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			    (offset + *length);
 
 	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
-		if (rw & REQ_DISCARD)
+		if (op == REQ_OP_DISCARD)
 			num_stripes = min_t(u64, map->num_stripes,
 					    stripe_nr_end - stripe_nr_orig);
 		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
 				&stripe_index);
-		if (!(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)))
+		if (op != REQ_OP_WRITE && op != REQ_OP_DISCARD &&
+		    op != REQ_GET_READ_MIRRORS)
 			mirror_num = 1;
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
-		if (rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS))
+		if (op == REQ_OP_WRITE || op == REQ_OP_DISCARD ||
+		    op == REQ_GET_READ_MIRRORS)
 			num_stripes = map->num_stripes;
 		else if (mirror_num)
 			stripe_index = mirror_num - 1;
@@ -5493,7 +5495,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		}
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
-		if (rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)) {
+		if (op == REQ_OP_WRITE || op == REQ_OP_DISCARD ||
+		    op == REQ_GET_READ_MIRRORS) {
 			num_stripes = map->num_stripes;
 		} else if (mirror_num) {
 			stripe_index = mirror_num - 1;
@@ -5507,9 +5510,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
 		stripe_index *= map->sub_stripes;
 
-		if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
+		if (op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS)
 			num_stripes = map->sub_stripes;
-		else if (rw & REQ_DISCARD)
+		else if (op == REQ_OP_DISCARD)
 			num_stripes = min_t(u64, map->sub_stripes *
 					    (stripe_nr_end - stripe_nr_orig),
 					    map->num_stripes);
@@ -5527,7 +5530,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		if (need_raid_map &&
-		    ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) ||
+		    (op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS ||
 		     mirror_num > 1)) {
 			/* push stripe_nr back to the start of the full stripe */
 			stripe_nr = div_u64(raid56_full_stripe_start,
@@ -5555,8 +5558,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			/* We distribute the parity blocks across stripes */
 			div_u64_rem(stripe_nr + stripe_index, map->num_stripes,
 					&stripe_index);
-			if (!(rw & (REQ_WRITE | REQ_DISCARD |
-				    REQ_GET_READ_MIRRORS)) && mirror_num <= 1)
+			if ((op != REQ_OP_WRITE && op != REQ_OP_DISCARD &&
+			    op != REQ_GET_READ_MIRRORS) && mirror_num <= 1)
 				mirror_num = 1;
 		}
 	} else {
@@ -5579,9 +5582,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 
 	num_alloc_stripes = num_stripes;
 	if (dev_replace_is_ongoing) {
-		if (rw & (REQ_WRITE | REQ_DISCARD))
+		if (op == REQ_OP_WRITE || op == REQ_OP_DISCARD)
 			num_alloc_stripes <<= 1;
-		if (rw & REQ_GET_READ_MIRRORS)
+		if (op == REQ_GET_READ_MIRRORS)
 			num_alloc_stripes++;
 		tgtdev_indexes = num_stripes;
 	}
@@ -5596,7 +5599,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 
 	/* build raid_map */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK &&
-	    need_raid_map && ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) ||
+	    need_raid_map &&
+	    ((op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS) ||
 	    mirror_num > 1)) {
 		u64 tmp;
 		unsigned rot;
@@ -5621,7 +5625,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 				RAID6_Q_STRIPE;
 	}
 
-	if (rw & REQ_DISCARD) {
+	if (op == REQ_OP_DISCARD) {
 		u32 factor = 0;
 		u32 sub_stripes = 0;
 		u64 stripes_per_dev = 0;
@@ -5701,14 +5705,15 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		}
 	}
 
-	if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
+	if (op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS)
 		max_errors = btrfs_chunk_max_errors(map);
 
 	if (bbio->raid_map)
 		sort_parity_stripes(bbio, num_stripes);
 
 	tgtdev_indexes = 0;
-	if (dev_replace_is_ongoing && (rw & (REQ_WRITE | REQ_DISCARD)) &&
+	if (dev_replace_is_ongoing &&
+	   (op == REQ_OP_WRITE || op == REQ_OP_DISCARD) &&
 	    dev_replace->tgtdev != NULL) {
 		int index_where_to_add;
 		u64 srcdev_devid = dev_replace->srcdev->devid;
@@ -5743,7 +5748,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			}
 		}
 		num_stripes = index_where_to_add;
-	} else if (dev_replace_is_ongoing && (rw & REQ_GET_READ_MIRRORS) &&
+	} else if (dev_replace_is_ongoing && (op == REQ_GET_READ_MIRRORS) &&
 		   dev_replace->tgtdev != NULL) {
 		u64 srcdev_devid = dev_replace->srcdev->devid;
 		int index_srcdev = 0;
@@ -5815,21 +5820,21 @@ out:
 	return ret;
 }
 
-int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
+int btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		      u64 logical, u64 *length,
 		      struct btrfs_bio **bbio_ret, int mirror_num)
 {
-	return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret,
+	return __btrfs_map_block(fs_info, op, logical, length, bbio_ret,
 				 mirror_num, 0);
 }
 
 /* For Scrub/replace */
-int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw,
+int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int op,
 		     u64 logical, u64 *length,
 		     struct btrfs_bio **bbio_ret, int mirror_num,
 		     int need_raid_map)
 {
-	return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret,
+	return __btrfs_map_block(fs_info, op, logical, length, bbio_ret,
 				 mirror_num, need_raid_map);
 }
 
@@ -5943,7 +5948,7 @@ static void btrfs_end_bio(struct bio *bio)
 			BUG_ON(stripe_index >= bbio->num_stripes);
 			dev = bbio->stripes[stripe_index].dev;
 			if (dev->bdev) {
-				if (bio->bi_rw & WRITE)
+				if (bio_op(bio) == REQ_OP_WRITE)
 					btrfs_dev_stat_inc(dev,
 						BTRFS_DEV_STAT_WRITE_ERRS);
 				else
@@ -5997,7 +6002,7 @@ static void btrfs_end_bio(struct bio *bio)
  */
 static noinline void btrfs_schedule_bio(struct btrfs_root *root,
 					struct btrfs_device *device,
-					int rw, struct bio *bio)
+					struct bio *bio)
 {
 	int should_queue = 1;
 	struct btrfs_pending_bios *pending_bios;
@@ -6008,9 +6013,9 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root,
 	}
 
 	/* don't bother with additional async steps for reads, right now */
-	if (!(rw & REQ_WRITE)) {
+	if (bio_op(bio) == REQ_OP_READ) {
 		bio_get(bio);
-		btrfsic_submit_bio(rw, bio);
+		btrfsic_submit_bio(bio);
 		bio_put(bio);
 		return;
 	}
@@ -6024,7 +6029,6 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root,
 	atomic_inc(&root->fs_info->nr_async_bios);
 	WARN_ON(bio->bi_next);
 	bio->bi_next = NULL;
-	bio->bi_rw |= rw;
 
 	spin_lock(&device->io_lock);
 	if (bio->bi_rw & REQ_SYNC)
@@ -6050,7 +6054,7 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root,
 
 static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
 			      struct bio *bio, u64 physical, int dev_nr,
-			      int rw, int async)
+			      int async)
 {
 	struct btrfs_device *dev = bbio->stripes[dev_nr].dev;
 
@@ -6064,8 +6068,8 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
 
 		rcu_read_lock();
 		name = rcu_dereference(dev->name);
-		pr_debug("btrfs_map_bio: rw %d, sector=%llu, dev=%lu "
-			 "(%s id %llu), size=%u\n", rw,
+		pr_debug("btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu "
+			 "(%s id %llu), size=%u\n", bio_op(bio), bio->bi_rw,
 			 (u64)bio->bi_iter.bi_sector, (u_long)dev->bdev->bd_dev,
 			 name->str, dev->devid, bio->bi_iter.bi_size);
 		rcu_read_unlock();
@@ -6076,9 +6080,9 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
 	btrfs_bio_counter_inc_noblocked(root->fs_info);
 
 	if (async)
-		btrfs_schedule_bio(root, dev, rw, bio);
+		btrfs_schedule_bio(root, dev, bio);
 	else
-		btrfsic_submit_bio(rw, bio);
+		btrfsic_submit_bio(bio);
 }
 
 static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
@@ -6095,7 +6099,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 	}
 }
 
-int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
+int btrfs_map_bio(struct btrfs_root *root, struct bio *bio,
 		  int mirror_num, int async_submit)
 {
 	struct btrfs_device *dev;
@@ -6112,8 +6116,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 	map_length = length;
 
 	btrfs_bio_counter_inc_blocked(root->fs_info);
-	ret = __btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
-			      mirror_num, 1);
+	ret = __btrfs_map_block(root->fs_info, bio_op(bio), logical,
+				&map_length, &bbio, mirror_num, 1);
 	if (ret) {
 		btrfs_bio_counter_dec(root->fs_info);
 		return ret;
@@ -6127,10 +6131,10 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 	atomic_set(&bbio->stripes_pending, bbio->num_stripes);
 
 	if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
-	    ((rw & WRITE) || (mirror_num > 1))) {
+	    ((bio_op(bio) == REQ_OP_WRITE) || (mirror_num > 1))) {
 		/* In this case, map_length has been set to the length of
 		   a single stripe; not the whole write */
-		if (rw & WRITE) {
+		if (bio_op(bio) == REQ_OP_WRITE) {
 			ret = raid56_parity_write(root, bio, bbio, map_length);
 		} else {
 			ret = raid56_parity_recover(root, bio, bbio, map_length,
@@ -6149,7 +6153,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 
 	for (dev_nr = 0; dev_nr < total_devs; dev_nr++) {
 		dev = bbio->stripes[dev_nr].dev;
-		if (!dev || !dev->bdev || (rw & WRITE && !dev->writeable)) {
+		if (!dev || !dev->bdev ||
+		    (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) {
 			bbio_error(bbio, first_bio, logical);
 			continue;
 		}
@@ -6161,7 +6166,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 			bio = first_bio;
 
 		submit_stripe_bio(root, bbio, bio,
-				  bbio->stripes[dev_nr].physical, dev_nr, rw,
+				  bbio->stripes[dev_nr].physical, dev_nr,
 				  async_submit);
 	}
 	btrfs_bio_counter_dec(root->fs_info);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 0ac90f8d85bd..6613e6335ca2 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -375,10 +375,10 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 				   u64 end, u64 *length);
 void btrfs_get_bbio(struct btrfs_bio *bbio);
 void btrfs_put_bbio(struct btrfs_bio *bbio);
-int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
+int btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		    u64 logical, u64 *length,
 		    struct btrfs_bio **bbio_ret, int mirror_num);
-int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw,
+int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int op,
 		     u64 logical, u64 *length,
 		     struct btrfs_bio **bbio_ret, int mirror_num,
 		     int need_raid_map);
@@ -391,7 +391,7 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *extent_root, u64 type);
 void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
 void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
-int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
+int btrfs_map_bio(struct btrfs_root *root, struct bio *bio,
 		  int mirror_num, int async_submit);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
diff --git a/fs/buffer.c b/fs/buffer.c
index 6c15012a75d9..b9fa1be75e69 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -45,7 +45,7 @@
 #include <trace/events/block.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
-static int submit_bh_wbc(int rw, struct buffer_head *bh,
+static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 			 unsigned long bio_flags,
 			 struct writeback_control *wbc);
 
@@ -153,7 +153,7 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		/* This happens, due to failed READA attempts. */
+		/* This happens, due to failed read-ahead attempts. */
 		clear_buffer_uptodate(bh);
 	}
 	unlock_buffer(bh);
@@ -588,7 +588,7 @@ void write_boundary_block(struct block_device *bdev,
 	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
 	if (bh) {
 		if (buffer_dirty(bh))
-			ll_rw_block(WRITE, 1, &bh);
+			ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
 		put_bh(bh);
 	}
 }
@@ -1225,7 +1225,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh)
 	} else {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ, bh);
+		submit_bh(REQ_OP_READ, 0, bh);
 		wait_on_buffer(bh);
 		if (buffer_uptodate(bh))
 			return bh;
@@ -1395,7 +1395,7 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 {
 	struct buffer_head *bh = __getblk(bdev, block, size);
 	if (likely(bh)) {
-		ll_rw_block(READA, 1, &bh);
+		ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
 		brelse(bh);
 	}
 }
@@ -1697,7 +1697,7 @@ int __block_write_full_page(struct inode *inode, struct page *page,
 	struct buffer_head *bh, *head;
 	unsigned int blocksize, bbits;
 	int nr_underway = 0;
-	int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+	int write_flags = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : 0);
 
 	head = create_page_buffers(page, inode,
 					(1 << BH_Dirty)|(1 << BH_Uptodate));
@@ -1786,7 +1786,7 @@ int __block_write_full_page(struct inode *inode, struct page *page,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh_wbc(write_op, bh, 0, wbc);
+			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, 0, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -1840,7 +1840,7 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh_wbc(write_op, bh, 0, wbc);
+			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, 0, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -1956,7 +1956,7 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
 		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
 		    !buffer_unwritten(bh) &&
 		     (block_start < from || block_end > to)) {
-			ll_rw_block(READ, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 			*wait_bh++=bh;
 		}
 	}
@@ -2249,7 +2249,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
 		if (buffer_uptodate(bh))
 			end_buffer_async_read(bh, 1);
 		else
-			submit_bh(READ, bh);
+			submit_bh(REQ_OP_READ, 0, bh);
 	}
 	return 0;
 }
@@ -2583,7 +2583,7 @@ int nobh_write_begin(struct address_space *mapping,
 		if (block_start < from || block_end > to) {
 			lock_buffer(bh);
 			bh->b_end_io = end_buffer_read_nobh;
-			submit_bh(READ, bh);
+			submit_bh(REQ_OP_READ, 0, bh);
 			nr_reads++;
 		}
 	}
@@ -2853,7 +2853,7 @@ int block_truncate_page(struct address_space *mapping,
 
 	if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
 		err = -EIO;
-		ll_rw_block(READ, 1, &bh);
+		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 		wait_on_buffer(bh);
 		/* Uhhuh. Read error. Complain and punt. */
 		if (!buffer_uptodate(bh))
@@ -2950,7 +2950,7 @@ static void end_bio_bh_io_sync(struct bio *bio)
  * errors, this only handles the "we need to be able to
  * do IO at the final sector" case.
  */
-void guard_bio_eod(int rw, struct bio *bio)
+void guard_bio_eod(int op, struct bio *bio)
 {
 	sector_t maxsector;
 	struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
@@ -2980,13 +2980,13 @@ void guard_bio_eod(int rw, struct bio *bio)
 	bvec->bv_len -= truncated_bytes;
 
 	/* ..and clear the end of the buffer for reads */
-	if ((rw & RW_MASK) == READ) {
+	if (op == REQ_OP_READ) {
 		zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
 				truncated_bytes);
 	}
 }
 
-static int submit_bh_wbc(int rw, struct buffer_head *bh,
+static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 			 unsigned long bio_flags, struct writeback_control *wbc)
 {
 	struct bio *bio;
@@ -3000,7 +3000,7 @@ static int submit_bh_wbc(int rw, struct buffer_head *bh,
 	/*
 	 * Only clear out a write error when rewriting
 	 */
-	if (test_set_buffer_req(bh) && (rw & WRITE))
+	if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
 		clear_buffer_write_io_error(bh);
 
 	/*
@@ -3025,39 +3025,42 @@ static int submit_bh_wbc(int rw, struct buffer_head *bh,
 	bio->bi_flags |= bio_flags;
 
 	/* Take care of bh's that straddle the end of the device */
-	guard_bio_eod(rw, bio);
+	guard_bio_eod(op, bio);
 
 	if (buffer_meta(bh))
-		rw |= REQ_META;
+		op_flags |= REQ_META;
 	if (buffer_prio(bh))
-		rw |= REQ_PRIO;
+		op_flags |= REQ_PRIO;
+	bio_set_op_attrs(bio, op, op_flags);
 
-	submit_bio(rw, bio);
+	submit_bio(bio);
 	return 0;
 }
 
-int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
+int _submit_bh(int op, int op_flags, struct buffer_head *bh,
+	       unsigned long bio_flags)
 {
-	return submit_bh_wbc(rw, bh, bio_flags, NULL);
+	return submit_bh_wbc(op, op_flags, bh, bio_flags, NULL);
 }
 EXPORT_SYMBOL_GPL(_submit_bh);
 
-int submit_bh(int rw, struct buffer_head *bh)
+int submit_bh(int op, int op_flags,  struct buffer_head *bh)
 {
-	return submit_bh_wbc(rw, bh, 0, NULL);
+	return submit_bh_wbc(op, op_flags, bh, 0, NULL);
 }
 EXPORT_SYMBOL(submit_bh);
 
 /**
  * ll_rw_block: low-level access to block devices (DEPRECATED)
- * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
+ * @op: whether to %READ or %WRITE
+ * @op_flags: rq_flag_bits
  * @nr: number of &struct buffer_heads in the array
  * @bhs: array of pointers to &struct buffer_head
  *
  * ll_rw_block() takes an array of pointers to &struct buffer_heads, and
- * requests an I/O operation on them, either a %READ or a %WRITE.  The third
- * %READA option is described in the documentation for generic_make_request()
- * which ll_rw_block() calls.
+ * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE.
+ * @op_flags contains flags modifying the detailed I/O behavior, most notably
+ * %REQ_RAHEAD.
  *
  * This function drops any buffer that it cannot get a lock on (with the
  * BH_Lock state bit), any buffer that appears to be clean when doing a write
@@ -3073,7 +3076,7 @@ EXPORT_SYMBOL(submit_bh);
  * All of the buffers must be for the same device, and must also be a
  * multiple of the current approved size for the device.
  */
-void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
+void ll_rw_block(int op, int op_flags,  int nr, struct buffer_head *bhs[])
 {
 	int i;
 
@@ -3082,18 +3085,18 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 
 		if (!trylock_buffer(bh))
 			continue;
-		if (rw == WRITE) {
+		if (op == WRITE) {
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
 				get_bh(bh);
-				submit_bh(WRITE, bh);
+				submit_bh(op, op_flags, bh);
 				continue;
 			}
 		} else {
 			if (!buffer_uptodate(bh)) {
 				bh->b_end_io = end_buffer_read_sync;
 				get_bh(bh);
-				submit_bh(rw, bh);
+				submit_bh(op, op_flags, bh);
 				continue;
 			}
 		}
@@ -3102,7 +3105,7 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 }
 EXPORT_SYMBOL(ll_rw_block);
 
-void write_dirty_buffer(struct buffer_head *bh, int rw)
+void write_dirty_buffer(struct buffer_head *bh, int op_flags)
 {
 	lock_buffer(bh);
 	if (!test_clear_buffer_dirty(bh)) {
@@ -3111,7 +3114,7 @@ void write_dirty_buffer(struct buffer_head *bh, int rw)
 	}
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
-	submit_bh(rw, bh);
+	submit_bh(REQ_OP_WRITE, op_flags, bh);
 }
 EXPORT_SYMBOL(write_dirty_buffer);
 
@@ -3120,7 +3123,7 @@ EXPORT_SYMBOL(write_dirty_buffer);
  * and then start new I/O and then wait upon it.  The caller must have a ref on
  * the buffer_head.
  */
-int __sync_dirty_buffer(struct buffer_head *bh, int rw)
+int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
 {
 	int ret = 0;
 
@@ -3129,7 +3132,7 @@ int __sync_dirty_buffer(struct buffer_head *bh, int rw)
 	if (test_clear_buffer_dirty(bh)) {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
-		ret = submit_bh(rw, bh);
+		ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
 		wait_on_buffer(bh);
 		if (!ret && !buffer_uptodate(bh))
 			ret = -EIO;
@@ -3392,7 +3395,7 @@ int bh_submit_read(struct buffer_head *bh)
 
 	get_bh(bh);
 	bh->b_end_io = end_buffer_read_sync;
-	submit_bh(READ, bh);
+	submit_bh(REQ_OP_READ, 0, bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return 0;
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index bd01b92aad98..c1e9f29c924c 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -57,6 +57,7 @@
 #include <linux/i2c-dev.h>
 #include <linux/atalk.h>
 #include <linux/gfp.h>
+#include <linux/cec.h>
 
 #include "internal.h"
 
@@ -1377,6 +1378,17 @@ COMPATIBLE_IOCTL(VIDEO_GET_NAVI)
 COMPATIBLE_IOCTL(VIDEO_SET_ATTRIBUTES)
 COMPATIBLE_IOCTL(VIDEO_GET_SIZE)
 COMPATIBLE_IOCTL(VIDEO_GET_FRAME_RATE)
+/* cec */
+COMPATIBLE_IOCTL(CEC_ADAP_G_CAPS)
+COMPATIBLE_IOCTL(CEC_ADAP_G_LOG_ADDRS)
+COMPATIBLE_IOCTL(CEC_ADAP_S_LOG_ADDRS)
+COMPATIBLE_IOCTL(CEC_ADAP_G_PHYS_ADDR)
+COMPATIBLE_IOCTL(CEC_ADAP_S_PHYS_ADDR)
+COMPATIBLE_IOCTL(CEC_G_MODE)
+COMPATIBLE_IOCTL(CEC_S_MODE)
+COMPATIBLE_IOCTL(CEC_TRANSMIT)
+COMPATIBLE_IOCTL(CEC_RECEIVE)
+COMPATIBLE_IOCTL(CEC_DQEVENT)
 
 /* joystick */
 COMPATIBLE_IOCTL(JSIOCGVERSION)
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 2fc8c43ce531..c502c116924c 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -318,6 +318,7 @@ int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
 		bio->bi_bdev = inode->i_sb->s_bdev;
 		bio->bi_iter.bi_sector =
 			pblk << (inode->i_sb->s_blocksize_bits - 9);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 		ret = bio_add_page(bio, ciphertext_page,
 					inode->i_sb->s_blocksize, 0);
 		if (ret != inode->i_sb->s_blocksize) {
@@ -327,7 +328,7 @@ int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
 			err = -EIO;
 			goto errout;
 		}
-		err = submit_bio_wait(WRITE, bio);
+		err = submit_bio_wait(bio);
 		if ((err == 0) && bio->bi_error)
 			err = -EIO;
 		bio_put(bio);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index f3b4408be590..7c3ce73cb617 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -108,7 +108,8 @@ struct dio_submit {
 /* dio_state communicated between submission path and end_io */
 struct dio {
 	int flags;			/* doesn't change */
-	int rw;
+	int op;
+	int op_flags;
 	blk_qc_t bio_cookie;
 	struct block_device *bio_bdev;
 	struct inode *inode;
@@ -163,7 +164,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 	ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
 				&sdio->from);
 
-	if (ret < 0 && sdio->blocks_available && (dio->rw & WRITE)) {
+	if (ret < 0 && sdio->blocks_available && (dio->op == REQ_OP_WRITE)) {
 		struct page *page = ZERO_PAGE(0);
 		/*
 		 * A memory fault, but the filesystem has some outstanding
@@ -242,7 +243,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
 		transferred = dio->result;
 
 		/* Check for short read case */
-		if ((dio->rw == READ) && ((offset + transferred) > dio->i_size))
+		if ((dio->op == REQ_OP_READ) &&
+		    ((offset + transferred) > dio->i_size))
 			transferred = dio->i_size - offset;
 	}
 
@@ -273,7 +275,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
 		 */
 		dio->iocb->ki_pos += transferred;
 
-		if (dio->rw & WRITE)
+		if (dio->op == REQ_OP_WRITE)
 			ret = generic_write_sync(dio->iocb,  transferred);
 		dio->iocb->ki_complete(dio->iocb, ret, 0);
 	}
@@ -375,6 +377,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 
 	bio->bi_bdev = bdev;
 	bio->bi_iter.bi_sector = first_sector;
+	bio_set_op_attrs(bio, dio->op, dio->op_flags);
 	if (dio->is_async)
 		bio->bi_end_io = dio_bio_end_aio;
 	else
@@ -402,17 +405,16 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 	dio->refcount++;
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
-	if (dio->is_async && dio->rw == READ && dio->should_dirty)
+	if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty)
 		bio_set_pages_dirty(bio);
 
 	dio->bio_bdev = bio->bi_bdev;
 
 	if (sdio->submit_io) {
-		sdio->submit_io(dio->rw, bio, dio->inode,
-			       sdio->logical_offset_in_bio);
+		sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio);
 		dio->bio_cookie = BLK_QC_T_NONE;
 	} else
-		dio->bio_cookie = submit_bio(dio->rw, bio);
+		dio->bio_cookie = submit_bio(bio);
 
 	sdio->bio = NULL;
 	sdio->boundary = 0;
@@ -478,14 +480,14 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 	if (bio->bi_error)
 		dio->io_error = -EIO;
 
-	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
+	if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) {
 		err = bio->bi_error;
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
 
-			if (dio->rw == READ && !PageCompound(page) &&
+			if (dio->op == REQ_OP_READ && !PageCompound(page) &&
 					dio->should_dirty)
 				set_page_dirty_lock(page);
 			put_page(page);
@@ -638,7 +640,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
 		 * which may decide to handle it or also return an unmapped
 		 * buffer head.
 		 */
-		create = dio->rw & WRITE;
+		create = dio->op == REQ_OP_WRITE;
 		if (dio->flags & DIO_SKIP_HOLES) {
 			if (fs_startblk <= ((i_size_read(dio->inode) - 1) >>
 							i_blkbits))
@@ -788,7 +790,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 {
 	int ret = 0;
 
-	if (dio->rw & WRITE) {
+	if (dio->op == REQ_OP_WRITE) {
 		/*
 		 * Read accounting is performed in submit_bio()
 		 */
@@ -988,7 +990,7 @@ do_holes:
 				loff_t i_size_aligned;
 
 				/* AKPM: eargh, -ENOTBLK is a hack */
-				if (dio->rw & WRITE) {
+				if (dio->op == REQ_OP_WRITE) {
 					put_page(page);
 					return -ENOTBLK;
 				}
@@ -1202,7 +1204,12 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 		dio->is_async = true;
 
 	dio->inode = inode;
-	dio->rw = iov_iter_rw(iter) == WRITE ? WRITE_ODIRECT : READ;
+	if (iov_iter_rw(iter) == WRITE) {
+		dio->op = REQ_OP_WRITE;
+		dio->op_flags = WRITE_ODIRECT;
+	} else {
+		dio->op = REQ_OP_READ;
+	}
 
 	/*
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 7bd8ac8dfb28..8bb72807e70d 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -878,7 +878,7 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
 			} else {
 				bio = master_dev->bio;
 				/* FIXME: bio_set_dir() */
-				bio->bi_rw |= REQ_WRITE;
+				bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			}
 
 			osd_req_write(or, _ios_obj(ios, cur_comp),
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 9f9992b37924..4c40c0786e16 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -1194,6 +1194,27 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
 }
 
 /*
+ * Returns 1 if the passed-in block region is valid; 0 if some part overlaps
+ * with filesystem metadata blocksi.
+ */
+int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk,
+			  unsigned int count)
+{
+	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count < start_blk) ||
+	    (start_blk > le32_to_cpu(sbi->s_es->s_blocks_count)))
+		return 0;
+
+	/* Ensure we do not step over superblock */
+	if ((start_blk <= sbi->s_sb_block) &&
+	    (start_blk + count >= sbi->s_sb_block))
+		return 0;
+
+
+	return 1;
+}
+
+/*
  * ext2_new_blocks() -- core block(s) allocation function
  * @inode:		file inode
  * @goal:		given target block(filesystem wide)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 170939f379d7..3fb93681bf7f 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -367,6 +367,7 @@ struct ext2_inode {
  */
 #define	EXT2_VALID_FS			0x0001	/* Unmounted cleanly */
 #define	EXT2_ERROR_FS			0x0002	/* Errors detected */
+#define	EFSCORRUPTED			EUCLEAN	/* Filesystem is corrupted */
 
 /*
  * Mount flags
@@ -739,6 +740,8 @@ extern unsigned long ext2_bg_num_gdb(struct super_block *sb, int group);
 extern ext2_fsblk_t ext2_new_block(struct inode *, unsigned long, int *);
 extern ext2_fsblk_t ext2_new_blocks(struct inode *, unsigned long,
 				unsigned long *, int *);
+extern int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk,
+				 unsigned int count);
 extern void ext2_free_blocks (struct inode *, unsigned long,
 			      unsigned long);
 extern unsigned long ext2_count_free_blocks (struct super_block *);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index fcbe58641e40..d5c7d09919f3 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1389,6 +1389,16 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 	ei->i_frag_size = raw_inode->i_fsize;
 	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
 	ei->i_dir_acl = 0;
+
+	if (ei->i_file_acl &&
+	    !ext2_data_block_valid(EXT2_SB(sb), ei->i_file_acl, 1)) {
+		ext2_error(sb, "ext2_iget", "bad extended attribute block %u",
+			   ei->i_file_acl);
+		brelse(bh);
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
+
 	if (S_ISREG(inode->i_mode))
 		inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
 	else
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 1a5e3bff0b63..b7f896f3f7a7 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -759,10 +759,19 @@ void
 ext2_xattr_delete_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
+	struct ext2_sb_info *sbi = EXT2_SB(inode->i_sb);
 
 	down_write(&EXT2_I(inode)->xattr_sem);
 	if (!EXT2_I(inode)->i_file_acl)
 		goto cleanup;
+
+	if (!ext2_data_block_valid(sbi, EXT2_I(inode)->i_file_acl, 0)) {
+		ext2_error(inode->i_sb, "ext2_xattr_delete_inode",
+			"inode %ld: xattr block %d is out of data blocks range",
+			inode->i_ino, EXT2_I(inode)->i_file_acl);
+		goto cleanup;
+	}
+
 	bh = sb_bread(inode->i_sb, EXT2_I(inode)->i_file_acl);
 	if (!bh) {
 		ext2_error(inode->i_sb, "ext2_xattr_delete_inode",
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index b46e9fc64196..e38039fd96ff 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -99,17 +99,9 @@ config EXT4_FS_SECURITY
 	  extended attributes for file security labels, say N.
 
 config EXT4_ENCRYPTION
-	tristate "Ext4 Encryption"
+	bool "Ext4 Encryption"
 	depends on EXT4_FS
-	select CRYPTO_AES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
-	select CRYPTO_XTS
-	select CRYPTO_CTS
-	select CRYPTO_CTR
-	select CRYPTO_SHA256
-	select KEYS
-	select ENCRYPTED_KEYS
+	select FS_ENCRYPTION
 	help
 	  Enable encryption of ext4 files and directories.  This
 	  feature is similar to ecryptfs, but it is more memory
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index f52cf54f0cbc..354103f3490c 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -12,5 +12,3 @@ ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
-ext4-$(CONFIG_EXT4_FS_ENCRYPTION)	+= crypto_policy.o crypto.o \
-		crypto_key.o crypto_fname.o
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 3020fd70c392..e04ec868e37e 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -208,6 +208,9 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	memset(bh->b_data, 0, sb->s_blocksize);
 
 	bit_max = ext4_num_base_meta_clusters(sb, block_group);
+	if ((bit_max >> 3) >= bh->b_size)
+		return -EFSCORRUPTED;
+
 	for (bit = 0; bit < bit_max; bit++)
 		ext4_set_bit(bit, bh->b_data);
 
@@ -470,7 +473,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	trace_ext4_read_block_bitmap_load(sb, block_group);
 	bh->b_end_io = ext4_end_bitmap_read;
 	get_bh(bh);
-	submit_bh(READ | REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
 	return bh;
 verify:
 	err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
@@ -610,7 +613,9 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 
 	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
 
-	jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+	smp_mb();
+	if (EXT4_SB(sb)->s_mb_free_pending)
+		jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
 	return 1;
 }
 
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
deleted file mode 100644
index 6a6c27373b54..000000000000
--- a/fs/ext4/crypto.c
+++ /dev/null
@@ -1,536 +0,0 @@
-/*
- * linux/fs/ext4/crypto.c
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption functions for ext4
- *
- * Written by Michael Halcrow, 2014.
- *
- * Filename encryption additions
- *	Uday Savagaonkar, 2014
- * Encryption policy handling additions
- *	Ildar Muslukhov, 2014
- *
- * This has not yet undergone a rigorous security audit.
- *
- * The usage of AES-XTS should conform to recommendations in NIST
- * Special Publication 800-38E and IEEE P1619/D16.
- */
-
-#include <crypto/skcipher.h>
-#include <keys/user-type.h>
-#include <keys/encrypted-type.h>
-#include <linux/ecryptfs.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-#include <linux/namei.h>
-
-#include "ext4_extents.h"
-#include "xattr.h"
-
-/* Encryption added and removed here! (L: */
-
-static unsigned int num_prealloc_crypto_pages = 32;
-static unsigned int num_prealloc_crypto_ctxs = 128;
-
-module_param(num_prealloc_crypto_pages, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_pages,
-		 "Number of crypto pages to preallocate");
-module_param(num_prealloc_crypto_ctxs, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
-		 "Number of crypto contexts to preallocate");
-
-static mempool_t *ext4_bounce_page_pool;
-
-static LIST_HEAD(ext4_free_crypto_ctxs);
-static DEFINE_SPINLOCK(ext4_crypto_ctx_lock);
-
-static struct kmem_cache *ext4_crypto_ctx_cachep;
-struct kmem_cache *ext4_crypt_info_cachep;
-
-/**
- * ext4_release_crypto_ctx() - Releases an encryption context
- * @ctx: The encryption context to release.
- *
- * If the encryption context was allocated from the pre-allocated pool, returns
- * it to that pool. Else, frees it.
- *
- * If there's a bounce page in the context, this frees that.
- */
-void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx)
-{
-	unsigned long flags;
-
-	if (ctx->flags & EXT4_WRITE_PATH_FL && ctx->w.bounce_page)
-		mempool_free(ctx->w.bounce_page, ext4_bounce_page_pool);
-	ctx->w.bounce_page = NULL;
-	ctx->w.control_page = NULL;
-	if (ctx->flags & EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL) {
-		kmem_cache_free(ext4_crypto_ctx_cachep, ctx);
-	} else {
-		spin_lock_irqsave(&ext4_crypto_ctx_lock, flags);
-		list_add(&ctx->free_list, &ext4_free_crypto_ctxs);
-		spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
-	}
-}
-
-/**
- * ext4_get_crypto_ctx() - Gets an encryption context
- * @inode:       The inode for which we are doing the crypto
- *
- * Allocates and initializes an encryption context.
- *
- * Return: An allocated and initialized encryption context on success; error
- * value or NULL otherwise.
- */
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
-					    gfp_t gfp_flags)
-{
-	struct ext4_crypto_ctx *ctx = NULL;
-	int res = 0;
-	unsigned long flags;
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-
-	if (ci == NULL)
-		return ERR_PTR(-ENOKEY);
-
-	/*
-	 * We first try getting the ctx from a free list because in
-	 * the common case the ctx will have an allocated and
-	 * initialized crypto tfm, so it's probably a worthwhile
-	 * optimization. For the bounce page, we first try getting it
-	 * from the kernel allocator because that's just about as fast
-	 * as getting it from a list and because a cache of free pages
-	 * should generally be a "last resort" option for a filesystem
-	 * to be able to do its job.
-	 */
-	spin_lock_irqsave(&ext4_crypto_ctx_lock, flags);
-	ctx = list_first_entry_or_null(&ext4_free_crypto_ctxs,
-				       struct ext4_crypto_ctx, free_list);
-	if (ctx)
-		list_del(&ctx->free_list);
-	spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
-	if (!ctx) {
-		ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, gfp_flags);
-		if (!ctx) {
-			res = -ENOMEM;
-			goto out;
-		}
-		ctx->flags |= EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	} else {
-		ctx->flags &= ~EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	}
-	ctx->flags &= ~EXT4_WRITE_PATH_FL;
-
-out:
-	if (res) {
-		if (!IS_ERR_OR_NULL(ctx))
-			ext4_release_crypto_ctx(ctx);
-		ctx = ERR_PTR(res);
-	}
-	return ctx;
-}
-
-struct workqueue_struct *ext4_read_workqueue;
-static DEFINE_MUTEX(crypto_init);
-
-/**
- * ext4_exit_crypto() - Shutdown the ext4 encryption system
- */
-void ext4_exit_crypto(void)
-{
-	struct ext4_crypto_ctx *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &ext4_free_crypto_ctxs, free_list)
-		kmem_cache_free(ext4_crypto_ctx_cachep, pos);
-	INIT_LIST_HEAD(&ext4_free_crypto_ctxs);
-	if (ext4_bounce_page_pool)
-		mempool_destroy(ext4_bounce_page_pool);
-	ext4_bounce_page_pool = NULL;
-	if (ext4_read_workqueue)
-		destroy_workqueue(ext4_read_workqueue);
-	ext4_read_workqueue = NULL;
-	if (ext4_crypto_ctx_cachep)
-		kmem_cache_destroy(ext4_crypto_ctx_cachep);
-	ext4_crypto_ctx_cachep = NULL;
-	if (ext4_crypt_info_cachep)
-		kmem_cache_destroy(ext4_crypt_info_cachep);
-	ext4_crypt_info_cachep = NULL;
-}
-
-/**
- * ext4_init_crypto() - Set up for ext4 encryption.
- *
- * We only call this when we start accessing encrypted files, since it
- * results in memory getting allocated that wouldn't otherwise be used.
- *
- * Return: Zero on success, non-zero otherwise.
- */
-int ext4_init_crypto(void)
-{
-	int i, res = -ENOMEM;
-
-	mutex_lock(&crypto_init);
-	if (ext4_read_workqueue)
-		goto already_initialized;
-	ext4_read_workqueue = alloc_workqueue("ext4_crypto", WQ_HIGHPRI, 0);
-	if (!ext4_read_workqueue)
-		goto fail;
-
-	ext4_crypto_ctx_cachep = KMEM_CACHE(ext4_crypto_ctx,
-					    SLAB_RECLAIM_ACCOUNT);
-	if (!ext4_crypto_ctx_cachep)
-		goto fail;
-
-	ext4_crypt_info_cachep = KMEM_CACHE(ext4_crypt_info,
-					    SLAB_RECLAIM_ACCOUNT);
-	if (!ext4_crypt_info_cachep)
-		goto fail;
-
-	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
-		struct ext4_crypto_ctx *ctx;
-
-		ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS);
-		if (!ctx) {
-			res = -ENOMEM;
-			goto fail;
-		}
-		list_add(&ctx->free_list, &ext4_free_crypto_ctxs);
-	}
-
-	ext4_bounce_page_pool =
-		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
-	if (!ext4_bounce_page_pool) {
-		res = -ENOMEM;
-		goto fail;
-	}
-already_initialized:
-	mutex_unlock(&crypto_init);
-	return 0;
-fail:
-	ext4_exit_crypto();
-	mutex_unlock(&crypto_init);
-	return res;
-}
-
-void ext4_restore_control_page(struct page *data_page)
-{
-	struct ext4_crypto_ctx *ctx =
-		(struct ext4_crypto_ctx *)page_private(data_page);
-
-	set_page_private(data_page, (unsigned long)NULL);
-	ClearPagePrivate(data_page);
-	unlock_page(data_page);
-	ext4_release_crypto_ctx(ctx);
-}
-
-/**
- * ext4_crypt_complete() - The completion callback for page encryption
- * @req: The asynchronous encryption request context
- * @res: The result of the encryption operation
- */
-static void ext4_crypt_complete(struct crypto_async_request *req, int res)
-{
-	struct ext4_completion_result *ecr = req->data;
-
-	if (res == -EINPROGRESS)
-		return;
-	ecr->res = res;
-	complete(&ecr->completion);
-}
-
-typedef enum {
-	EXT4_DECRYPT = 0,
-	EXT4_ENCRYPT,
-} ext4_direction_t;
-
-static int ext4_page_crypto(struct inode *inode,
-			    ext4_direction_t rw,
-			    pgoff_t index,
-			    struct page *src_page,
-			    struct page *dest_page,
-			    gfp_t gfp_flags)
-
-{
-	u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
-	struct skcipher_request *req = NULL;
-	DECLARE_EXT4_COMPLETION_RESULT(ecr);
-	struct scatterlist dst, src;
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
-	int res = 0;
-
-	req = skcipher_request_alloc(tfm, gfp_flags);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-				   "%s: crypto_request_alloc() failed\n",
-				   __func__);
-		return -ENOMEM;
-	}
-	skcipher_request_set_callback(
-		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		ext4_crypt_complete, &ecr);
-
-	BUILD_BUG_ON(EXT4_XTS_TWEAK_SIZE < sizeof(index));
-	memcpy(xts_tweak, &index, sizeof(index));
-	memset(&xts_tweak[sizeof(index)], 0,
-	       EXT4_XTS_TWEAK_SIZE - sizeof(index));
-
-	sg_init_table(&dst, 1);
-	sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
-	sg_init_table(&src, 1);
-	sg_set_page(&src, src_page, PAGE_SIZE, 0);
-	skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE,
-				   xts_tweak);
-	if (rw == EXT4_DECRYPT)
-		res = crypto_skcipher_decrypt(req);
-	else
-		res = crypto_skcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-	skcipher_request_free(req);
-	if (res) {
-		printk_ratelimited(
-			KERN_ERR
-			"%s: crypto_skcipher_encrypt() returned %d\n",
-			__func__, res);
-		return res;
-	}
-	return 0;
-}
-
-static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx,
-				      gfp_t gfp_flags)
-{
-	ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, gfp_flags);
-	if (ctx->w.bounce_page == NULL)
-		return ERR_PTR(-ENOMEM);
-	ctx->flags |= EXT4_WRITE_PATH_FL;
-	return ctx->w.bounce_page;
-}
-
-/**
- * ext4_encrypt() - Encrypts a page
- * @inode:          The inode for which the encryption should take place
- * @plaintext_page: The page to encrypt. Must be locked.
- *
- * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
- * encryption context.
- *
- * Called on the page write path.  The caller must call
- * ext4_restore_control_page() on the returned ciphertext page to
- * release the bounce buffer and the encryption context.
- *
- * Return: An allocated page with the encrypted content on success. Else, an
- * error value or NULL.
- */
-struct page *ext4_encrypt(struct inode *inode,
-			  struct page *plaintext_page,
-			  gfp_t gfp_flags)
-{
-	struct ext4_crypto_ctx *ctx;
-	struct page *ciphertext_page = NULL;
-	int err;
-
-	BUG_ON(!PageLocked(plaintext_page));
-
-	ctx = ext4_get_crypto_ctx(inode, gfp_flags);
-	if (IS_ERR(ctx))
-		return (struct page *) ctx;
-
-	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
-	if (IS_ERR(ciphertext_page))
-		goto errout;
-	ctx->w.control_page = plaintext_page;
-	err = ext4_page_crypto(inode, EXT4_ENCRYPT, plaintext_page->index,
-			       plaintext_page, ciphertext_page, gfp_flags);
-	if (err) {
-		ciphertext_page = ERR_PTR(err);
-	errout:
-		ext4_release_crypto_ctx(ctx);
-		return ciphertext_page;
-	}
-	SetPagePrivate(ciphertext_page);
-	set_page_private(ciphertext_page, (unsigned long)ctx);
-	lock_page(ciphertext_page);
-	return ciphertext_page;
-}
-
-/**
- * ext4_decrypt() - Decrypts a page in-place
- * @ctx:  The encryption context.
- * @page: The page to decrypt. Must be locked.
- *
- * Decrypts page in-place using the ctx encryption context.
- *
- * Called from the read completion callback.
- *
- * Return: Zero on success, non-zero otherwise.
- */
-int ext4_decrypt(struct page *page)
-{
-	BUG_ON(!PageLocked(page));
-
-	return ext4_page_crypto(page->mapping->host, EXT4_DECRYPT,
-				page->index, page, page, GFP_NOFS);
-}
-
-int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
-			   ext4_fsblk_t pblk, ext4_lblk_t len)
-{
-	struct ext4_crypto_ctx	*ctx;
-	struct page		*ciphertext_page = NULL;
-	struct bio		*bio;
-	int			ret, err = 0;
-
-#if 0
-	ext4_msg(inode->i_sb, KERN_CRIT,
-		 "ext4_encrypted_zeroout ino %lu lblk %u len %u",
-		 (unsigned long) inode->i_ino, lblk, len);
-#endif
-
-	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
-
-	ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
-	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
-	if (IS_ERR(ciphertext_page)) {
-		err = PTR_ERR(ciphertext_page);
-		goto errout;
-	}
-
-	while (len--) {
-		err = ext4_page_crypto(inode, EXT4_ENCRYPT, lblk,
-				       ZERO_PAGE(0), ciphertext_page,
-				       GFP_NOFS);
-		if (err)
-			goto errout;
-
-		bio = bio_alloc(GFP_NOWAIT, 1);
-		if (!bio) {
-			err = -ENOMEM;
-			goto errout;
-		}
-		bio->bi_bdev = inode->i_sb->s_bdev;
-		bio->bi_iter.bi_sector =
-			pblk << (inode->i_sb->s_blocksize_bits - 9);
-		ret = bio_add_page(bio, ciphertext_page,
-				   inode->i_sb->s_blocksize, 0);
-		if (ret != inode->i_sb->s_blocksize) {
-			/* should never happen! */
-			ext4_msg(inode->i_sb, KERN_ERR,
-				 "bio_add_page failed: %d", ret);
-			WARN_ON(1);
-			bio_put(bio);
-			err = -EIO;
-			goto errout;
-		}
-		err = submit_bio_wait(WRITE, bio);
-		if ((err == 0) && bio->bi_error)
-			err = -EIO;
-		bio_put(bio);
-		if (err)
-			goto errout;
-		lblk++; pblk++;
-	}
-	err = 0;
-errout:
-	ext4_release_crypto_ctx(ctx);
-	return err;
-}
-
-bool ext4_valid_contents_enc_mode(uint32_t mode)
-{
-	return (mode == EXT4_ENCRYPTION_MODE_AES_256_XTS);
-}
-
-/**
- * ext4_validate_encryption_key_size() - Validate the encryption key size
- * @mode: The key mode.
- * @size: The key size to validate.
- *
- * Return: The validated key size for @mode. Zero if invalid.
- */
-uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
-{
-	if (size == ext4_encryption_key_size(mode))
-		return size;
-	return 0;
-}
-
-/*
- * Validate dentries for encrypted directories to make sure we aren't
- * potentially caching stale data after a key has been added or
- * removed.
- */
-static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	struct dentry *dir;
-	struct ext4_crypt_info *ci;
-	int dir_has_key, cached_with_key;
-
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	dir = dget_parent(dentry);
-	if (!ext4_encrypted_inode(d_inode(dir))) {
-		dput(dir);
-		return 0;
-	}
-	ci = EXT4_I(d_inode(dir))->i_crypt_info;
-	if (ci && ci->ci_keyring_key &&
-	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					  (1 << KEY_FLAG_REVOKED) |
-					  (1 << KEY_FLAG_DEAD))))
-		ci = NULL;
-
-	/* this should eventually be an flag in d_flags */
-	cached_with_key = dentry->d_fsdata != NULL;
-	dir_has_key = (ci != NULL);
-	dput(dir);
-
-	/*
-	 * If the dentry was cached without the key, and it is a
-	 * negative dentry, it might be a valid name.  We can't check
-	 * if the key has since been made available due to locking
-	 * reasons, so we fail the validation so ext4_lookup() can do
-	 * this check.
-	 *
-	 * We also fail the validation if the dentry was created with
-	 * the key present, but we no longer have the key, or vice versa.
-	 */
-	if ((!cached_with_key && d_is_negative(dentry)) ||
-	    (!cached_with_key && dir_has_key) ||
-	    (cached_with_key && !dir_has_key)) {
-#if 0				/* Revalidation debug */
-		char buf[80];
-		char *cp = simple_dname(dentry, buf, sizeof(buf));
-
-		if (IS_ERR(cp))
-			cp = (char *) "???";
-		pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
-		       cached_with_key, d_is_negative(dentry),
-		       dir_has_key);
-#endif
-		return 0;
-	}
-	return 1;
-}
-
-const struct dentry_operations ext4_encrypted_d_ops = {
-	.d_revalidate = ext4_d_revalidate,
-};
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
deleted file mode 100644
index 1a2f360405db..000000000000
--- a/fs/ext4/crypto_fname.c
+++ /dev/null
@@ -1,468 +0,0 @@
-/*
- * linux/fs/ext4/crypto_fname.c
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains functions for filename crypto management in ext4
- *
- * Written by Uday Savagaonkar, 2014.
- *
- * This has not yet undergone a rigorous security audit.
- *
- */
-
-#include <crypto/skcipher.h>
-#include <keys/encrypted-type.h>
-#include <keys/user-type.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-
-#include "ext4.h"
-#include "ext4_crypto.h"
-#include "xattr.h"
-
-/**
- * ext4_dir_crypt_complete() -
- */
-static void ext4_dir_crypt_complete(struct crypto_async_request *req, int res)
-{
-	struct ext4_completion_result *ecr = req->data;
-
-	if (res == -EINPROGRESS)
-		return;
-	ecr->res = res;
-	complete(&ecr->completion);
-}
-
-bool ext4_valid_filenames_enc_mode(uint32_t mode)
-{
-	return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS);
-}
-
-static unsigned max_name_len(struct inode *inode)
-{
-	return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
-		EXT4_NAME_LEN;
-}
-
-/**
- * ext4_fname_encrypt() -
- *
- * This function encrypts the input filename, and returns the length of the
- * ciphertext. Errors are returned as negative numbers.  We trust the caller to
- * allocate sufficient memory to oname string.
- */
-static int ext4_fname_encrypt(struct inode *inode,
-			      const struct qstr *iname,
-			      struct ext4_str *oname)
-{
-	u32 ciphertext_len;
-	struct skcipher_request *req = NULL;
-	DECLARE_EXT4_COMPLETION_RESULT(ecr);
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
-	int res = 0;
-	char iv[EXT4_CRYPTO_BLOCK_SIZE];
-	struct scatterlist src_sg, dst_sg;
-	int padding = 4 << (ci->ci_flags & EXT4_POLICY_FLAGS_PAD_MASK);
-	char *workbuf, buf[32], *alloc_buf = NULL;
-	unsigned lim = max_name_len(inode);
-
-	if (iname->len <= 0 || iname->len > lim)
-		return -EIO;
-
-	ciphertext_len = (iname->len < EXT4_CRYPTO_BLOCK_SIZE) ?
-		EXT4_CRYPTO_BLOCK_SIZE : iname->len;
-	ciphertext_len = ext4_fname_crypto_round_up(ciphertext_len, padding);
-	ciphertext_len = (ciphertext_len > lim)
-			? lim : ciphertext_len;
-
-	if (ciphertext_len <= sizeof(buf)) {
-		workbuf = buf;
-	} else {
-		alloc_buf = kmalloc(ciphertext_len, GFP_NOFS);
-		if (!alloc_buf)
-			return -ENOMEM;
-		workbuf = alloc_buf;
-	}
-
-	/* Allocate request */
-	req = skcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(
-		    KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
-		kfree(alloc_buf);
-		return -ENOMEM;
-	}
-	skcipher_request_set_callback(req,
-		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		ext4_dir_crypt_complete, &ecr);
-
-	/* Copy the input */
-	memcpy(workbuf, iname->name, iname->len);
-	if (iname->len < ciphertext_len)
-		memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
-
-	/* Initialize IV */
-	memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE);
-
-	/* Create encryption request */
-	sg_init_one(&src_sg, workbuf, ciphertext_len);
-	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_skcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-	kfree(alloc_buf);
-	skcipher_request_free(req);
-	if (res < 0) {
-		printk_ratelimited(
-		    KERN_ERR "%s: Error (error code %d)\n", __func__, res);
-	}
-	oname->len = ciphertext_len;
-	return res;
-}
-
-/*
- * ext4_fname_decrypt()
- *	This function decrypts the input filename, and returns
- *	the length of the plaintext.
- *	Errors are returned as negative numbers.
- *	We trust the caller to allocate sufficient memory to oname string.
- */
-static int ext4_fname_decrypt(struct inode *inode,
-			      const struct ext4_str *iname,
-			      struct ext4_str *oname)
-{
-	struct ext4_str tmp_in[2], tmp_out[1];
-	struct skcipher_request *req = NULL;
-	DECLARE_EXT4_COMPLETION_RESULT(ecr);
-	struct scatterlist src_sg, dst_sg;
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
-	int res = 0;
-	char iv[EXT4_CRYPTO_BLOCK_SIZE];
-	unsigned lim = max_name_len(inode);
-
-	if (iname->len <= 0 || iname->len > lim)
-		return -EIO;
-
-	tmp_in[0].name = iname->name;
-	tmp_in[0].len = iname->len;
-	tmp_out[0].name = oname->name;
-
-	/* Allocate request */
-	req = skcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(
-		    KERN_ERR "%s: crypto_request_alloc() failed\n",  __func__);
-		return -ENOMEM;
-	}
-	skcipher_request_set_callback(req,
-		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		ext4_dir_crypt_complete, &ecr);
-
-	/* Initialize IV */
-	memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE);
-
-	/* Create encryption request */
-	sg_init_one(&src_sg, iname->name, iname->len);
-	sg_init_one(&dst_sg, oname->name, oname->len);
-	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_skcipher_decrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-	skcipher_request_free(req);
-	if (res < 0) {
-		printk_ratelimited(
-		    KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n",
-		    __func__, res);
-		return res;
-	}
-
-	oname->len = strnlen(oname->name, iname->len);
-	return oname->len;
-}
-
-static const char *lookup_table =
-	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
-
-/**
- * ext4_fname_encode_digest() -
- *
- * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
- * The encoded string is roughly 4/3 times the size of the input string.
- */
-static int digest_encode(const char *src, int len, char *dst)
-{
-	int i = 0, bits = 0, ac = 0;
-	char *cp = dst;
-
-	while (i < len) {
-		ac += (((unsigned char) src[i]) << bits);
-		bits += 8;
-		do {
-			*cp++ = lookup_table[ac & 0x3f];
-			ac >>= 6;
-			bits -= 6;
-		} while (bits >= 6);
-		i++;
-	}
-	if (bits)
-		*cp++ = lookup_table[ac & 0x3f];
-	return cp - dst;
-}
-
-static int digest_decode(const char *src, int len, char *dst)
-{
-	int i = 0, bits = 0, ac = 0;
-	const char *p;
-	char *cp = dst;
-
-	while (i < len) {
-		p = strchr(lookup_table, src[i]);
-		if (p == NULL || src[i] == 0)
-			return -2;
-		ac += (p - lookup_table) << bits;
-		bits += 6;
-		if (bits >= 8) {
-			*cp++ = ac & 0xff;
-			ac >>= 8;
-			bits -= 8;
-		}
-		i++;
-	}
-	if (ac)
-		return -1;
-	return cp - dst;
-}
-
-/**
- * ext4_fname_crypto_round_up() -
- *
- * Return: The next multiple of block size
- */
-u32 ext4_fname_crypto_round_up(u32 size, u32 blksize)
-{
-	return ((size+blksize-1)/blksize)*blksize;
-}
-
-unsigned ext4_fname_encrypted_size(struct inode *inode, u32 ilen)
-{
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	int padding = 32;
-
-	if (ci)
-		padding = 4 << (ci->ci_flags & EXT4_POLICY_FLAGS_PAD_MASK);
-	if (ilen < EXT4_CRYPTO_BLOCK_SIZE)
-		ilen = EXT4_CRYPTO_BLOCK_SIZE;
-	return ext4_fname_crypto_round_up(ilen, padding);
-}
-
-/*
- * ext4_fname_crypto_alloc_buffer() -
- *
- * Allocates an output buffer that is sufficient for the crypto operation
- * specified by the context and the direction.
- */
-int ext4_fname_crypto_alloc_buffer(struct inode *inode,
-				   u32 ilen, struct ext4_str *crypto_str)
-{
-	unsigned int olen = ext4_fname_encrypted_size(inode, ilen);
-
-	crypto_str->len = olen;
-	if (olen < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2)
-		olen = EXT4_FNAME_CRYPTO_DIGEST_SIZE*2;
-	/* Allocated buffer can hold one more character to null-terminate the
-	 * string */
-	crypto_str->name = kmalloc(olen+1, GFP_NOFS);
-	if (!(crypto_str->name))
-		return -ENOMEM;
-	return 0;
-}
-
-/**
- * ext4_fname_crypto_free_buffer() -
- *
- * Frees the buffer allocated for crypto operation.
- */
-void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str)
-{
-	if (!crypto_str)
-		return;
-	kfree(crypto_str->name);
-	crypto_str->name = NULL;
-}
-
-/**
- * ext4_fname_disk_to_usr() - converts a filename from disk space to user space
- */
-int _ext4_fname_disk_to_usr(struct inode *inode,
-			    struct dx_hash_info *hinfo,
-			    const struct ext4_str *iname,
-			    struct ext4_str *oname)
-{
-	char buf[24];
-	int ret;
-
-	if (iname->len < 3) {
-		/*Check for . and .. */
-		if (iname->name[0] == '.' && iname->name[iname->len-1] == '.') {
-			oname->name[0] = '.';
-			oname->name[iname->len-1] = '.';
-			oname->len = iname->len;
-			return oname->len;
-		}
-	}
-	if (iname->len < EXT4_CRYPTO_BLOCK_SIZE) {
-		EXT4_ERROR_INODE(inode, "encrypted inode too small");
-		return -EUCLEAN;
-	}
-	if (EXT4_I(inode)->i_crypt_info)
-		return ext4_fname_decrypt(inode, iname, oname);
-
-	if (iname->len <= EXT4_FNAME_CRYPTO_DIGEST_SIZE) {
-		ret = digest_encode(iname->name, iname->len, oname->name);
-		oname->len = ret;
-		return ret;
-	}
-	if (hinfo) {
-		memcpy(buf, &hinfo->hash, 4);
-		memcpy(buf+4, &hinfo->minor_hash, 4);
-	} else
-		memset(buf, 0, 8);
-	memcpy(buf + 8, iname->name + iname->len - 16, 16);
-	oname->name[0] = '_';
-	ret = digest_encode(buf, 24, oname->name+1);
-	oname->len = ret + 1;
-	return ret + 1;
-}
-
-int ext4_fname_disk_to_usr(struct inode *inode,
-			   struct dx_hash_info *hinfo,
-			   const struct ext4_dir_entry_2 *de,
-			   struct ext4_str *oname)
-{
-	struct ext4_str iname = {.name = (unsigned char *) de->name,
-				 .len = de->name_len };
-
-	return _ext4_fname_disk_to_usr(inode, hinfo, &iname, oname);
-}
-
-
-/**
- * ext4_fname_usr_to_disk() - converts a filename from user space to disk space
- */
-int ext4_fname_usr_to_disk(struct inode *inode,
-			   const struct qstr *iname,
-			   struct ext4_str *oname)
-{
-	int res;
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-
-	if (iname->len < 3) {
-		/*Check for . and .. */
-		if (iname->name[0] == '.' &&
-				iname->name[iname->len-1] == '.') {
-			oname->name[0] = '.';
-			oname->name[iname->len-1] = '.';
-			oname->len = iname->len;
-			return oname->len;
-		}
-	}
-	if (ci) {
-		res = ext4_fname_encrypt(inode, iname, oname);
-		return res;
-	}
-	/* Without a proper key, a user is not allowed to modify the filenames
-	 * in a directory. Consequently, a user space name cannot be mapped to
-	 * a disk-space name */
-	return -EACCES;
-}
-
-int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
-			      int lookup, struct ext4_filename *fname)
-{
-	struct ext4_crypt_info *ci;
-	int ret = 0, bigname = 0;
-
-	memset(fname, 0, sizeof(struct ext4_filename));
-	fname->usr_fname = iname;
-
-	if (!ext4_encrypted_inode(dir) ||
-	    ((iname->name[0] == '.') &&
-	     ((iname->len == 1) ||
-	      ((iname->name[1] == '.') && (iname->len == 2))))) {
-		fname->disk_name.name = (unsigned char *) iname->name;
-		fname->disk_name.len = iname->len;
-		return 0;
-	}
-	ret = ext4_get_encryption_info(dir);
-	if (ret)
-		return ret;
-	ci = EXT4_I(dir)->i_crypt_info;
-	if (ci) {
-		ret = ext4_fname_crypto_alloc_buffer(dir, iname->len,
-						     &fname->crypto_buf);
-		if (ret < 0)
-			return ret;
-		ret = ext4_fname_encrypt(dir, iname, &fname->crypto_buf);
-		if (ret < 0)
-			goto errout;
-		fname->disk_name.name = fname->crypto_buf.name;
-		fname->disk_name.len = fname->crypto_buf.len;
-		return 0;
-	}
-	if (!lookup)
-		return -EACCES;
-
-	/* We don't have the key and we are doing a lookup; decode the
-	 * user-supplied name
-	 */
-	if (iname->name[0] == '_')
-		bigname = 1;
-	if ((bigname && (iname->len != 33)) ||
-	    (!bigname && (iname->len > 43)))
-		return -ENOENT;
-
-	fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
-	if (fname->crypto_buf.name == NULL)
-		return -ENOMEM;
-	ret = digest_decode(iname->name + bigname, iname->len - bigname,
-			    fname->crypto_buf.name);
-	if (ret < 0) {
-		ret = -ENOENT;
-		goto errout;
-	}
-	fname->crypto_buf.len = ret;
-	if (bigname) {
-		memcpy(&fname->hinfo.hash, fname->crypto_buf.name, 4);
-		memcpy(&fname->hinfo.minor_hash, fname->crypto_buf.name + 4, 4);
-	} else {
-		fname->disk_name.name = fname->crypto_buf.name;
-		fname->disk_name.len = fname->crypto_buf.len;
-	}
-	return 0;
-errout:
-	kfree(fname->crypto_buf.name);
-	fname->crypto_buf.name = NULL;
-	return ret;
-}
-
-void ext4_fname_free_filename(struct ext4_filename *fname)
-{
-	kfree(fname->crypto_buf.name);
-	fname->crypto_buf.name = NULL;
-	fname->usr_fname = NULL;
-	fname->disk_name.name = NULL;
-}
diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c
deleted file mode 100644
index 0129d688d1f7..000000000000
--- a/fs/ext4/crypto_key.c
+++ /dev/null
@@ -1,274 +0,0 @@
-/*
- * linux/fs/ext4/crypto_key.c
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption key functions for ext4
- *
- * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
- */
-
-#include <crypto/skcipher.h>
-#include <keys/encrypted-type.h>
-#include <keys/user-type.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <uapi/linux/keyctl.h>
-
-#include "ext4.h"
-#include "xattr.h"
-
-static void derive_crypt_complete(struct crypto_async_request *req, int rc)
-{
-	struct ext4_completion_result *ecr = req->data;
-
-	if (rc == -EINPROGRESS)
-		return;
-
-	ecr->res = rc;
-	complete(&ecr->completion);
-}
-
-/**
- * ext4_derive_key_aes() - Derive a key using AES-128-ECB
- * @deriving_key: Encryption key used for derivation.
- * @source_key:   Source key to which to apply derivation.
- * @derived_key:  Derived key.
- *
- * Return: Zero on success; non-zero otherwise.
- */
-static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE],
-			       char source_key[EXT4_AES_256_XTS_KEY_SIZE],
-			       char derived_key[EXT4_AES_256_XTS_KEY_SIZE])
-{
-	int res = 0;
-	struct skcipher_request *req = NULL;
-	DECLARE_EXT4_COMPLETION_RESULT(ecr);
-	struct scatterlist src_sg, dst_sg;
-	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
-
-	if (IS_ERR(tfm)) {
-		res = PTR_ERR(tfm);
-		tfm = NULL;
-		goto out;
-	}
-	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = skcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		res = -ENOMEM;
-		goto out;
-	}
-	skcipher_request_set_callback(req,
-			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-			derive_crypt_complete, &ecr);
-	res = crypto_skcipher_setkey(tfm, deriving_key,
-				     EXT4_AES_128_ECB_KEY_SIZE);
-	if (res < 0)
-		goto out;
-	sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE);
-	sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE);
-	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
-				   EXT4_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_skcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-
-out:
-	skcipher_request_free(req);
-	crypto_free_skcipher(tfm);
-	return res;
-}
-
-void ext4_free_crypt_info(struct ext4_crypt_info *ci)
-{
-	if (!ci)
-		return;
-
-	if (ci->ci_keyring_key)
-		key_put(ci->ci_keyring_key);
-	crypto_free_skcipher(ci->ci_ctfm);
-	kmem_cache_free(ext4_crypt_info_cachep, ci);
-}
-
-void ext4_free_encryption_info(struct inode *inode,
-			       struct ext4_crypt_info *ci)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_crypt_info *prev;
-
-	if (ci == NULL)
-		ci = ACCESS_ONCE(ei->i_crypt_info);
-	if (ci == NULL)
-		return;
-	prev = cmpxchg(&ei->i_crypt_info, ci, NULL);
-	if (prev != ci)
-		return;
-
-	ext4_free_crypt_info(ci);
-}
-
-int _ext4_get_encryption_info(struct inode *inode)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_crypt_info *crypt_info;
-	char full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
-				 (EXT4_KEY_DESCRIPTOR_SIZE * 2) + 1];
-	struct key *keyring_key = NULL;
-	struct ext4_encryption_key *master_key;
-	struct ext4_encryption_context ctx;
-	const struct user_key_payload *ukp;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct crypto_skcipher *ctfm;
-	const char *cipher_str;
-	char raw_key[EXT4_MAX_KEY_SIZE];
-	char mode;
-	int res;
-
-	if (!ext4_read_workqueue) {
-		res = ext4_init_crypto();
-		if (res)
-			return res;
-	}
-
-retry:
-	crypt_info = ACCESS_ONCE(ei->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-		    key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		ext4_free_encryption_info(inode, crypt_info);
-		goto retry;
-	}
-
-	res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
-				 &ctx, sizeof(ctx));
-	if (res < 0) {
-		if (!DUMMY_ENCRYPTION_ENABLED(sbi))
-			return res;
-		ctx.contents_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS;
-		ctx.filenames_encryption_mode =
-			EXT4_ENCRYPTION_MODE_AES_256_CTS;
-		ctx.flags = 0;
-	} else if (res != sizeof(ctx))
-		return -EINVAL;
-	res = 0;
-
-	crypt_info = kmem_cache_alloc(ext4_crypt_info_cachep, GFP_KERNEL);
-	if (!crypt_info)
-		return -ENOMEM;
-
-	crypt_info->ci_flags = ctx.flags;
-	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
-	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
-	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
-	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
-	       sizeof(crypt_info->ci_master_key));
-	if (S_ISREG(inode->i_mode))
-		mode = crypt_info->ci_data_mode;
-	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		mode = crypt_info->ci_filename_mode;
-	else
-		BUG();
-	switch (mode) {
-	case EXT4_ENCRYPTION_MODE_AES_256_XTS:
-		cipher_str = "xts(aes)";
-		break;
-	case EXT4_ENCRYPTION_MODE_AES_256_CTS:
-		cipher_str = "cts(cbc(aes))";
-		break;
-	default:
-		printk_once(KERN_WARNING
-			    "ext4: unsupported key mode %d (ino %u)\n",
-			    mode, (unsigned) inode->i_ino);
-		res = -ENOKEY;
-		goto out;
-	}
-	if (DUMMY_ENCRYPTION_ENABLED(sbi)) {
-		memset(raw_key, 0x42, EXT4_AES_256_XTS_KEY_SIZE);
-		goto got_key;
-	}
-	memcpy(full_key_descriptor, EXT4_KEY_DESC_PREFIX,
-	       EXT4_KEY_DESC_PREFIX_SIZE);
-	sprintf(full_key_descriptor + EXT4_KEY_DESC_PREFIX_SIZE,
-		"%*phN", EXT4_KEY_DESCRIPTOR_SIZE,
-		ctx.master_key_descriptor);
-	full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
-			    (2 * EXT4_KEY_DESCRIPTOR_SIZE)] = '\0';
-	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
-	if (IS_ERR(keyring_key)) {
-		res = PTR_ERR(keyring_key);
-		keyring_key = NULL;
-		goto out;
-	}
-	crypt_info->ci_keyring_key = keyring_key;
-	if (keyring_key->type != &key_type_logon) {
-		printk_once(KERN_WARNING
-			    "ext4: key type must be logon\n");
-		res = -ENOKEY;
-		goto out;
-	}
-	down_read(&keyring_key->sem);
-	ukp = user_key_payload(keyring_key);
-	if (ukp->datalen != sizeof(struct ext4_encryption_key)) {
-		res = -EINVAL;
-		up_read(&keyring_key->sem);
-		goto out;
-	}
-	master_key = (struct ext4_encryption_key *)ukp->data;
-	BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE !=
-		     EXT4_KEY_DERIVATION_NONCE_SIZE);
-	if (master_key->size != EXT4_AES_256_XTS_KEY_SIZE) {
-		printk_once(KERN_WARNING
-			    "ext4: key size incorrect: %d\n",
-			    master_key->size);
-		res = -ENOKEY;
-		up_read(&keyring_key->sem);
-		goto out;
-	}
-	res = ext4_derive_key_aes(ctx.nonce, master_key->raw,
-				  raw_key);
-	up_read(&keyring_key->sem);
-	if (res)
-		goto out;
-got_key:
-	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
-	if (!ctfm || IS_ERR(ctfm)) {
-		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
-		printk(KERN_DEBUG
-		       "%s: error %d (inode %u) allocating crypto tfm\n",
-		       __func__, res, (unsigned) inode->i_ino);
-		goto out;
-	}
-	crypt_info->ci_ctfm = ctfm;
-	crypto_skcipher_clear_flags(ctfm, ~0);
-	crypto_tfm_set_flags(crypto_skcipher_tfm(ctfm),
-			     CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_skcipher_setkey(ctfm, raw_key,
-				     ext4_encryption_key_size(mode));
-	if (res)
-		goto out;
-	memzero_explicit(raw_key, sizeof(raw_key));
-	if (cmpxchg(&ei->i_crypt_info, NULL, crypt_info) != NULL) {
-		ext4_free_crypt_info(crypt_info);
-		goto retry;
-	}
-	return 0;
-
-out:
-	if (res == -ENOKEY)
-		res = 0;
-	ext4_free_crypt_info(crypt_info);
-	memzero_explicit(raw_key, sizeof(raw_key));
-	return res;
-}
-
-int ext4_has_encryption_key(struct inode *inode)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-
-	return (ei->i_crypt_info != NULL);
-}
diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c
deleted file mode 100644
index ad050698143f..000000000000
--- a/fs/ext4/crypto_policy.c
+++ /dev/null
@@ -1,229 +0,0 @@
-/*
- * linux/fs/ext4/crypto_policy.c
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption policy functions for ext4
- *
- * Written by Michael Halcrow, 2015.
- */
-
-#include <linux/random.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include "ext4_jbd2.h"
-#include "ext4.h"
-#include "xattr.h"
-
-static int ext4_inode_has_encryption_context(struct inode *inode)
-{
-	int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0);
-	return (res > 0);
-}
-
-/*
- * check whether the policy is consistent with the encryption context
- * for the inode
- */
-static int ext4_is_encryption_context_consistent_with_policy(
-	struct inode *inode, const struct ext4_encryption_policy *policy)
-{
-	struct ext4_encryption_context ctx;
-	int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-				 sizeof(ctx));
-	if (res != sizeof(ctx))
-		return 0;
-	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
-			EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(ctx.flags ==
-		 policy->flags) &&
-		(ctx.contents_encryption_mode ==
-		 policy->contents_encryption_mode) &&
-		(ctx.filenames_encryption_mode ==
-		 policy->filenames_encryption_mode));
-}
-
-static int ext4_create_encryption_context_from_policy(
-	struct inode *inode, const struct ext4_encryption_policy *policy)
-{
-	struct ext4_encryption_context ctx;
-	handle_t *handle;
-	int res, res2;
-
-	res = ext4_convert_inline_data(inode);
-	if (res)
-		return res;
-
-	ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
-	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
-	       EXT4_KEY_DESCRIPTOR_SIZE);
-	if (!ext4_valid_contents_enc_mode(policy->contents_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid contents encryption mode %d\n", __func__,
-			policy->contents_encryption_mode);
-		return -EINVAL;
-	}
-	if (!ext4_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid filenames encryption mode %d\n", __func__,
-			policy->filenames_encryption_mode);
-		return -EINVAL;
-	}
-	if (policy->flags & ~EXT4_POLICY_FLAGS_VALID)
-		return -EINVAL;
-	ctx.contents_encryption_mode = policy->contents_encryption_mode;
-	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
-	ctx.flags = policy->flags;
-	BUILD_BUG_ON(sizeof(ctx.nonce) != EXT4_KEY_DERIVATION_NONCE_SIZE);
-	get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
-
-	handle = ext4_journal_start(inode, EXT4_HT_MISC,
-				    ext4_jbd2_credits_xattr(inode));
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
-	res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-			     sizeof(ctx), 0);
-	if (!res) {
-		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
-		res = ext4_mark_inode_dirty(handle, inode);
-		if (res)
-			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
-	}
-	res2 = ext4_journal_stop(handle);
-	if (!res)
-		res = res2;
-	return res;
-}
-
-int ext4_process_policy(const struct ext4_encryption_policy *policy,
-			struct inode *inode)
-{
-	if (policy->version != 0)
-		return -EINVAL;
-
-	if (!ext4_inode_has_encryption_context(inode)) {
-		if (!S_ISDIR(inode->i_mode))
-			return -EINVAL;
-		if (!ext4_empty_dir(inode))
-			return -ENOTEMPTY;
-		return ext4_create_encryption_context_from_policy(inode,
-								  policy);
-	}
-
-	if (ext4_is_encryption_context_consistent_with_policy(inode, policy))
-		return 0;
-
-	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
-	       __func__);
-	return -EINVAL;
-}
-
-int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy)
-{
-	struct ext4_encryption_context ctx;
-
-	int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
-				 &ctx, sizeof(ctx));
-	if (res != sizeof(ctx))
-		return -ENOENT;
-	if (ctx.format != EXT4_ENCRYPTION_CONTEXT_FORMAT_V1)
-		return -EINVAL;
-	policy->version = 0;
-	policy->contents_encryption_mode = ctx.contents_encryption_mode;
-	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
-	policy->flags = ctx.flags;
-	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
-	       EXT4_KEY_DESCRIPTOR_SIZE);
-	return 0;
-}
-
-int ext4_is_child_context_consistent_with_parent(struct inode *parent,
-						 struct inode *child)
-{
-	struct ext4_crypt_info *parent_ci, *child_ci;
-	int res;
-
-	if ((parent == NULL) || (child == NULL)) {
-		pr_err("parent %p child %p\n", parent, child);
-		WARN_ON(1);	/* Should never happen */
-		return 0;
-	}
-	/* no restrictions if the parent directory is not encrypted */
-	if (!ext4_encrypted_inode(parent))
-		return 1;
-	/* if the child directory is not encrypted, this is always a problem */
-	if (!ext4_encrypted_inode(child))
-		return 0;
-	res = ext4_get_encryption_info(parent);
-	if (res)
-		return 0;
-	res = ext4_get_encryption_info(child);
-	if (res)
-		return 0;
-	parent_ci = EXT4_I(parent)->i_crypt_info;
-	child_ci = EXT4_I(child)->i_crypt_info;
-	if (!parent_ci && !child_ci)
-		return 1;
-	if (!parent_ci || !child_ci)
-		return 0;
-
-	return (memcmp(parent_ci->ci_master_key,
-		       child_ci->ci_master_key,
-		       EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
-		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
-		(parent_ci->ci_flags == child_ci->ci_flags));
-}
-
-/**
- * ext4_inherit_context() - Sets a child context from its parent
- * @parent: Parent inode from which the context is inherited.
- * @child:  Child inode that inherits the context from @parent.
- *
- * Return: Zero on success, non-zero otherwise
- */
-int ext4_inherit_context(struct inode *parent, struct inode *child)
-{
-	struct ext4_encryption_context ctx;
-	struct ext4_crypt_info *ci;
-	int res;
-
-	res = ext4_get_encryption_info(parent);
-	if (res < 0)
-		return res;
-	ci = EXT4_I(parent)->i_crypt_info;
-	if (ci == NULL)
-		return -ENOKEY;
-
-	ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
-	if (DUMMY_ENCRYPTION_ENABLED(EXT4_SB(parent->i_sb))) {
-		ctx.contents_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS;
-		ctx.filenames_encryption_mode =
-			EXT4_ENCRYPTION_MODE_AES_256_CTS;
-		ctx.flags = 0;
-		memset(ctx.master_key_descriptor, 0x42,
-		       EXT4_KEY_DESCRIPTOR_SIZE);
-		res = 0;
-	} else {
-		ctx.contents_encryption_mode = ci->ci_data_mode;
-		ctx.filenames_encryption_mode = ci->ci_filename_mode;
-		ctx.flags = ci->ci_flags;
-		memcpy(ctx.master_key_descriptor, ci->ci_master_key,
-		       EXT4_KEY_DESCRIPTOR_SIZE);
-	}
-	get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
-	res = ext4_xattr_set(child, EXT4_XATTR_INDEX_ENCRYPTION,
-			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-			     sizeof(ctx), 0);
-	if (!res) {
-		ext4_set_inode_flag(child, EXT4_INODE_ENCRYPT);
-		ext4_clear_inode_state(child, EXT4_STATE_MAY_INLINE_DATA);
-		res = ext4_get_encryption_info(child);
-	}
-	return res;
-}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 68323e3da3fa..67415e0e6af0 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -109,10 +109,10 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *bh = NULL;
 	int dir_has_error = 0;
-	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
+	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
 
 	if (ext4_encrypted_inode(inode)) {
-		err = ext4_get_encryption_info(inode);
+		err = fscrypt_get_encryption_info(inode);
 		if (err && err != -ENOKEY)
 			return err;
 	}
@@ -139,8 +139,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	if (ext4_encrypted_inode(inode)) {
-		err = ext4_fname_crypto_alloc_buffer(inode, EXT4_NAME_LEN,
-						     &fname_crypto_str);
+		err = fscrypt_fname_alloc_buffer(inode, EXT4_NAME_LEN, &fstr);
 		if (err < 0)
 			return err;
 	}
@@ -253,16 +252,19 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					    get_dtype(sb, de->file_type)))
 						goto done;
 				} else {
-					int save_len = fname_crypto_str.len;
+					int save_len = fstr.len;
+					struct fscrypt_str de_name =
+							FSTR_INIT(de->name,
+								de->name_len);
 
 					/* Directory is encrypted */
-					err = ext4_fname_disk_to_usr(inode,
-						NULL, de, &fname_crypto_str);
-					fname_crypto_str.len = save_len;
+					err = fscrypt_fname_disk_to_usr(inode,
+						0, 0, &de_name, &fstr);
+					fstr.len = save_len;
 					if (err < 0)
 						goto errout;
 					if (!dir_emit(ctx,
-					    fname_crypto_str.name, err,
+					    fstr.name, err,
 					    le32_to_cpu(de->inode),
 					    get_dtype(sb, de->file_type)))
 						goto done;
@@ -281,7 +283,7 @@ done:
 	err = 0;
 errout:
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-	ext4_fname_crypto_free_buffer(&fname_crypto_str);
+	fscrypt_fname_free_buffer(&fstr);
 #endif
 	brelse(bh);
 	return err;
@@ -432,7 +434,7 @@ void ext4_htree_free_dir_info(struct dir_private_info *p)
 int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 			     __u32 minor_hash,
 			    struct ext4_dir_entry_2 *dirent,
-			    struct ext4_str *ent_name)
+			    struct fscrypt_str *ent_name)
 {
 	struct rb_node **p, *parent = NULL;
 	struct fname *fname, *new_fn;
@@ -609,7 +611,7 @@ finished:
 static int ext4_dir_open(struct inode * inode, struct file * filp)
 {
 	if (ext4_encrypted_inode(inode))
-		return ext4_get_encryption_info(inode) ? -EACCES : 0;
+		return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
 	return 0;
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b84aa1ca480a..ea31931386ec 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -32,6 +32,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/ratelimit.h>
 #include <crypto/hash.h>
+#include <linux/fscrypto.h>
 #include <linux/falloc.h>
 #include <linux/percpu-rwsem.h>
 #ifdef __KERNEL__
@@ -608,15 +609,6 @@ enum {
 #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
 
-/* Encryption algorithms */
-#define EXT4_ENCRYPTION_MODE_INVALID		0
-#define EXT4_ENCRYPTION_MODE_AES_256_XTS	1
-#define EXT4_ENCRYPTION_MODE_AES_256_GCM	2
-#define EXT4_ENCRYPTION_MODE_AES_256_CBC	3
-#define EXT4_ENCRYPTION_MODE_AES_256_CTS	4
-
-#include "ext4_crypto.h"
-
 /*
  * ioctl commands
  */
@@ -638,9 +630,9 @@ enum {
 #define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
 #define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
 #define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
-#define EXT4_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct ext4_encryption_policy)
-#define EXT4_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
-#define EXT4_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct ext4_encryption_policy)
+#define EXT4_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
+#define EXT4_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
+#define EXT4_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
 
 #ifndef FS_IOC_FSGETXATTR
 /* Until the uapi changes get merged for project quota... */
@@ -1082,10 +1074,6 @@ struct ext4_inode_info {
 	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
 	__u32 i_csum_seed;
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	/* Encryption params */
-	struct ext4_crypt_info *i_crypt_info;
-#endif
 	kprojid_t i_projid;
 };
 
@@ -1344,6 +1332,11 @@ struct ext4_super_block {
 /* Number of quota types we support */
 #define EXT4_MAXQUOTAS 3
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#define EXT4_KEY_DESC_PREFIX "ext4:"
+#define EXT4_KEY_DESC_PREFIX_SIZE 5
+#endif
+
 /*
  * fourth extended-fs super-block data in memory
  */
@@ -1430,6 +1423,7 @@ struct ext4_sb_info {
 	unsigned short *s_mb_offsets;
 	unsigned int *s_mb_maxs;
 	unsigned int s_group_info_size;
+	unsigned int s_mb_free_pending;
 
 	/* tunables */
 	unsigned long s_stripe;
@@ -1512,6 +1506,12 @@ struct ext4_sb_info {
 
 	/* Barrier between changing inodes' journal flags and writepages ops. */
 	struct percpu_rw_semaphore s_journal_flag_rwsem;
+
+	/* Encryption support */
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	u8 key_prefix[EXT4_KEY_DESC_PREFIX_SIZE];
+	u8 key_prefix_size;
+#endif
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1610,15 +1610,6 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 /*
  * Returns true if the inode is inode is encrypted
  */
-static inline int ext4_encrypted_inode(struct inode *inode)
-{
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT);
-#else
-	return 0;
-#endif
-}
-
 #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
 
 /*
@@ -2082,10 +2073,10 @@ struct dx_hash_info
 
 struct ext4_filename {
 	const struct qstr *usr_fname;
-	struct ext4_str disk_name;
+	struct fscrypt_str disk_name;
 	struct dx_hash_info hinfo;
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-	struct ext4_str crypto_buf;
+	struct fscrypt_str crypto_buf;
 #endif
 };
 
@@ -2296,132 +2287,82 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
 					      struct ext4_group_desc *gdp);
 ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
 
-/* crypto_policy.c */
-int ext4_is_child_context_consistent_with_parent(struct inode *parent,
-						 struct inode *child);
-int ext4_inherit_context(struct inode *parent, struct inode *child);
-void ext4_to_hex(char *dst, char *src, size_t src_size);
-int ext4_process_policy(const struct ext4_encryption_policy *policy,
-			struct inode *inode);
-int ext4_get_policy(struct inode *inode,
-		    struct ext4_encryption_policy *policy);
-
-/* crypto.c */
-extern struct kmem_cache *ext4_crypt_info_cachep;
-bool ext4_valid_contents_enc_mode(uint32_t mode);
-uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size);
-extern struct workqueue_struct *ext4_read_workqueue;
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
-					    gfp_t gfp_flags);
-void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx);
-void ext4_restore_control_page(struct page *data_page);
-struct page *ext4_encrypt(struct inode *inode,
-			  struct page *plaintext_page,
-			  gfp_t gfp_flags);
-int ext4_decrypt(struct page *page);
-int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
-			   ext4_fsblk_t pblk, ext4_lblk_t len);
-extern const struct dentry_operations ext4_encrypted_d_ops;
-
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-int ext4_init_crypto(void);
-void ext4_exit_crypto(void);
 static inline int ext4_sb_has_crypto(struct super_block *sb)
 {
 	return ext4_has_feature_encrypt(sb);
 }
-#else
-static inline int ext4_init_crypto(void) { return 0; }
-static inline void ext4_exit_crypto(void) { }
-static inline int ext4_sb_has_crypto(struct super_block *sb)
+
+static inline bool ext4_encrypted_inode(struct inode *inode)
 {
-	return 0;
+	return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT);
 }
-#endif
 
-/* crypto_fname.c */
-bool ext4_valid_filenames_enc_mode(uint32_t mode);
-u32 ext4_fname_crypto_round_up(u32 size, u32 blksize);
-unsigned ext4_fname_encrypted_size(struct inode *inode, u32 ilen);
-int ext4_fname_crypto_alloc_buffer(struct inode *inode,
-				   u32 ilen, struct ext4_str *crypto_str);
-int _ext4_fname_disk_to_usr(struct inode *inode,
-			    struct dx_hash_info *hinfo,
-			    const struct ext4_str *iname,
-			    struct ext4_str *oname);
-int ext4_fname_disk_to_usr(struct inode *inode,
-			   struct dx_hash_info *hinfo,
-			   const struct ext4_dir_entry_2 *de,
-			   struct ext4_str *oname);
-int ext4_fname_usr_to_disk(struct inode *inode,
-			   const struct qstr *iname,
-			   struct ext4_str *oname);
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str);
-int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
-			      int lookup, struct ext4_filename *fname);
-void ext4_fname_free_filename(struct ext4_filename *fname);
-#else
-static inline
-int ext4_setup_fname_crypto(struct inode *inode)
-{
-	return 0;
-}
-static inline void ext4_fname_crypto_free_buffer(struct ext4_str *p) { }
 static inline int ext4_fname_setup_filename(struct inode *dir,
-				     const struct qstr *iname,
-				     int lookup, struct ext4_filename *fname)
+			const struct qstr *iname,
+			int lookup, struct ext4_filename *fname)
 {
-	fname->usr_fname = iname;
-	fname->disk_name.name = (unsigned char *) iname->name;
-	fname->disk_name.len = iname->len;
-	return 0;
-}
-static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
-#endif
-
+	struct fscrypt_name name;
+	int err;
 
-/* crypto_key.c */
-void ext4_free_crypt_info(struct ext4_crypt_info *ci);
-void ext4_free_encryption_info(struct inode *inode, struct ext4_crypt_info *ci);
-int _ext4_get_encryption_info(struct inode *inode);
+	memset(fname, 0, sizeof(struct ext4_filename));
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-int ext4_has_encryption_key(struct inode *inode);
+	err = fscrypt_setup_filename(dir, iname, lookup, &name);
 
-static inline int ext4_get_encryption_info(struct inode *inode)
-{
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-
-	if (!ci ||
-	    (ci->ci_keyring_key &&
-	     (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					   (1 << KEY_FLAG_REVOKED) |
-					   (1 << KEY_FLAG_DEAD)))))
-		return _ext4_get_encryption_info(inode);
-	return 0;
+	fname->usr_fname = name.usr_fname;
+	fname->disk_name = name.disk_name;
+	fname->hinfo.hash = name.hash;
+	fname->hinfo.minor_hash = name.minor_hash;
+	fname->crypto_buf = name.crypto_buf;
+	return err;
 }
 
-static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode)
+static inline void ext4_fname_free_filename(struct ext4_filename *fname)
 {
-	return EXT4_I(inode)->i_crypt_info;
-}
+	struct fscrypt_name name;
 
-#else
-static inline int ext4_has_encryption_key(struct inode *inode)
-{
-	return 0;
+	name.crypto_buf = fname->crypto_buf;
+	fscrypt_free_filename(&name);
+
+	fname->crypto_buf.name = NULL;
+	fname->usr_fname = NULL;
+	fname->disk_name.name = NULL;
 }
-static inline int ext4_get_encryption_info(struct inode *inode)
+#else
+static inline int ext4_fname_setup_filename(struct inode *dir,
+		const struct qstr *iname,
+		int lookup, struct ext4_filename *fname)
 {
+	fname->usr_fname = iname;
+	fname->disk_name.name = (unsigned char *) iname->name;
+	fname->disk_name.len = iname->len;
 	return 0;
 }
-static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode)
-{
-	return NULL;
-}
-#endif
+static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
 
+#define fscrypt_set_d_op(i)
+#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
+#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
+#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
+#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
+#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
+#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
+#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
+#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
+#define fscrypt_process_policy		fscrypt_notsupp_process_policy
+#define fscrypt_get_policy		fscrypt_notsupp_get_policy
+#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
+#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
+#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
+#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
+#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
+#define fscrypt_free_filename		fscrypt_notsupp_free_filename
+#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
+#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
+#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
+#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
+#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
+#endif
 
 /* dir.c */
 extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
@@ -2435,7 +2376,7 @@ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
 extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 				__u32 minor_hash,
 				struct ext4_dir_entry_2 *dirent,
-				struct ext4_str *ent_name);
+				struct fscrypt_str *ent_name);
 extern void ext4_htree_free_dir_info(struct dir_private_info *p);
 extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
 			     struct buffer_head *bh,
@@ -2623,7 +2564,7 @@ extern int ext4_generic_delete_entry(handle_t *handle,
 				     void *entry_buf,
 				     int buf_size,
 				     int csum_size);
-extern int ext4_empty_dir(struct inode *inode);
+extern bool ext4_empty_dir(struct inode *inode);
 
 /* resize.c */
 extern int ext4_group_add(struct super_block *sb,
@@ -3105,7 +3046,7 @@ extern int ext4_delete_inline_entry(handle_t *handle,
 				    struct ext4_dir_entry_2 *de_del,
 				    struct buffer_head *bh,
 				    int *has_inline_data);
-extern int empty_inline_dir(struct inode *dir, int *has_inline_data);
+extern bool empty_inline_dir(struct inode *dir, int *has_inline_data);
 extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
 					struct ext4_dir_entry_2 **parent_de,
 					int *retval);
diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h
deleted file mode 100644
index 1f73c29717e1..000000000000
--- a/fs/ext4/ext4_crypto.h
+++ /dev/null
@@ -1,159 +0,0 @@
-/*
- * linux/fs/ext4/ext4_crypto.h
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption header content for ext4
- *
- * Written by Michael Halcrow, 2015.
- */
-
-#ifndef _EXT4_CRYPTO_H
-#define _EXT4_CRYPTO_H
-
-#include <linux/fs.h>
-
-#define EXT4_KEY_DESCRIPTOR_SIZE 8
-
-/* Policy provided via an ioctl on the topmost directory */
-struct ext4_encryption_policy {
-	char version;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
-} __attribute__((__packed__));
-
-#define EXT4_ENCRYPTION_CONTEXT_FORMAT_V1 1
-#define EXT4_KEY_DERIVATION_NONCE_SIZE 16
-
-#define EXT4_POLICY_FLAGS_PAD_4		0x00
-#define EXT4_POLICY_FLAGS_PAD_8		0x01
-#define EXT4_POLICY_FLAGS_PAD_16	0x02
-#define EXT4_POLICY_FLAGS_PAD_32	0x03
-#define EXT4_POLICY_FLAGS_PAD_MASK	0x03
-#define EXT4_POLICY_FLAGS_VALID		0x03
-
-/**
- * Encryption context for inode
- *
- * Protector format:
- *  1 byte: Protector format (1 = this version)
- *  1 byte: File contents encryption mode
- *  1 byte: File names encryption mode
- *  1 byte: Reserved
- *  8 bytes: Master Key descriptor
- *  16 bytes: Encryption Key derivation nonce
- */
-struct ext4_encryption_context {
-	char format;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
-	char nonce[EXT4_KEY_DERIVATION_NONCE_SIZE];
-} __attribute__((__packed__));
-
-/* Encryption parameters */
-#define EXT4_XTS_TWEAK_SIZE 16
-#define EXT4_AES_128_ECB_KEY_SIZE 16
-#define EXT4_AES_256_GCM_KEY_SIZE 32
-#define EXT4_AES_256_CBC_KEY_SIZE 32
-#define EXT4_AES_256_CTS_KEY_SIZE 32
-#define EXT4_AES_256_XTS_KEY_SIZE 64
-#define EXT4_MAX_KEY_SIZE 64
-
-#define EXT4_KEY_DESC_PREFIX "ext4:"
-#define EXT4_KEY_DESC_PREFIX_SIZE 5
-
-/* This is passed in from userspace into the kernel keyring */
-struct ext4_encryption_key {
-        __u32 mode;
-        char raw[EXT4_MAX_KEY_SIZE];
-        __u32 size;
-} __attribute__((__packed__));
-
-struct ext4_crypt_info {
-	char		ci_data_mode;
-	char		ci_filename_mode;
-	char		ci_flags;
-	struct crypto_skcipher *ci_ctfm;
-	struct key	*ci_keyring_key;
-	char		ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE];
-};
-
-#define EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL             0x00000001
-#define EXT4_WRITE_PATH_FL			      0x00000002
-
-struct ext4_crypto_ctx {
-	union {
-		struct {
-			struct page *bounce_page;       /* Ciphertext page */
-			struct page *control_page;      /* Original page  */
-		} w;
-		struct {
-			struct bio *bio;
-			struct work_struct work;
-		} r;
-		struct list_head free_list;     /* Free list */
-	};
-	char flags;                      /* Flags */
-	char mode;                       /* Encryption mode for tfm */
-};
-
-struct ext4_completion_result {
-	struct completion completion;
-	int res;
-};
-
-#define DECLARE_EXT4_COMPLETION_RESULT(ecr) \
-	struct ext4_completion_result ecr = { \
-		COMPLETION_INITIALIZER((ecr).completion), 0 }
-
-static inline int ext4_encryption_key_size(int mode)
-{
-	switch (mode) {
-	case EXT4_ENCRYPTION_MODE_AES_256_XTS:
-		return EXT4_AES_256_XTS_KEY_SIZE;
-	case EXT4_ENCRYPTION_MODE_AES_256_GCM:
-		return EXT4_AES_256_GCM_KEY_SIZE;
-	case EXT4_ENCRYPTION_MODE_AES_256_CBC:
-		return EXT4_AES_256_CBC_KEY_SIZE;
-	case EXT4_ENCRYPTION_MODE_AES_256_CTS:
-		return EXT4_AES_256_CTS_KEY_SIZE;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-#define EXT4_FNAME_NUM_SCATTER_ENTRIES	4
-#define EXT4_CRYPTO_BLOCK_SIZE		16
-#define EXT4_FNAME_CRYPTO_DIGEST_SIZE	32
-
-struct ext4_str {
-	unsigned char *name;
-	u32 len;
-};
-
-/**
- * For encrypted symlinks, the ciphertext length is stored at the beginning
- * of the string in little-endian format.
- */
-struct ext4_encrypted_symlink_data {
-	__le16 len;
-	char encrypted_path[1];
-} __attribute__((__packed__));
-
-/**
- * This function is used to calculate the disk space required to
- * store a filename of length l in encrypted symlink format.
- */
-static inline u32 encrypted_symlink_data_len(u32 l)
-{
-	if (l < EXT4_CRYPTO_BLOCK_SIZE)
-		l = EXT4_CRYPTO_BLOCK_SIZE;
-	return (l + sizeof(struct ext4_encrypted_symlink_data) - 1);
-}
-
-#endif	/* _EXT4_CRYPTO_H */
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 09c1ef38cbe6..b1d52c14098e 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -175,6 +175,13 @@ struct ext4_journal_cb_entry {
  * There is no guaranteed calling order of multiple registered callbacks on
  * the same transaction.
  */
+static inline void _ext4_journal_callback_add(handle_t *handle,
+			struct ext4_journal_cb_entry *jce)
+{
+	/* Add the jce to transaction's private list */
+	list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
+}
+
 static inline void ext4_journal_callback_add(handle_t *handle,
 			void (*func)(struct super_block *sb,
 				     struct ext4_journal_cb_entry *jce,
@@ -187,10 +194,11 @@ static inline void ext4_journal_callback_add(handle_t *handle,
 	/* Add the jce to transaction's private list */
 	jce->jce_func = func;
 	spin_lock(&sbi->s_md_lock);
-	list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
+	_ext4_journal_callback_add(handle, jce);
 	spin_unlock(&sbi->s_md_lock);
 }
 
+
 /**
  * ext4_journal_callback_del: delete a registered callback
  * @handle: active journal transaction handle on which callback was registered
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 2a2eef9c14e4..d7ccb7f51dfc 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -381,9 +381,13 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 	ext4_fsblk_t block = ext4_ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
 	ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
-	ext4_lblk_t last = lblock + len - 1;
 
-	if (len == 0 || lblock > last)
+	/*
+	 * We allow neither:
+	 *  - zero length
+	 *  - overflow/wrap-around
+	 */
+	if (lblock + len <= lblock)
 		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
@@ -474,6 +478,10 @@ static int __ext4_ext_check(const char *function, unsigned int line,
 		error_msg = "invalid extent entries";
 		goto corrupted;
 	}
+	if (unlikely(depth > 32)) {
+		error_msg = "too large eh_depth";
+		goto corrupted;
+	}
 	/* Verify checksum on non-root extent tree nodes */
 	if (ext_depth(inode) != depth &&
 	    !ext4_extent_block_csum_verify(inode, eh)) {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6664f9c82005..261ac3734c58 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -303,10 +303,10 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	struct inode *inode = file->f_mapping->host;
 
 	if (ext4_encrypted_inode(inode)) {
-		int err = ext4_get_encryption_info(inode);
+		int err = fscrypt_get_encryption_info(inode);
 		if (err)
 			return 0;
-		if (ext4_encryption_info(inode) == NULL)
+		if (!fscrypt_has_encryption_key(inode))
 			return -ENOKEY;
 	}
 	file_accessed(file);
@@ -362,16 +362,16 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		}
 	}
 	if (ext4_encrypted_inode(inode)) {
-		ret = ext4_get_encryption_info(inode);
+		ret = fscrypt_get_encryption_info(inode);
 		if (ret)
 			return -EACCES;
-		if (ext4_encryption_info(inode) == NULL)
+		if (!fscrypt_has_encryption_key(inode))
 			return -ENOKEY;
 	}
 
 	dir = dget_parent(file_dentry(filp));
 	if (ext4_encrypted_inode(d_inode(dir)) &&
-	    !ext4_is_child_context_consistent_with_parent(d_inode(dir), inode)) {
+			!fscrypt_has_permitted_context(d_inode(dir), inode)) {
 		ext4_warning(inode->i_sb,
 			     "Inconsistent encryption contexts: %lu/%lu",
 			     (unsigned long) d_inode(dir)->i_ino,
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 8850254136ae..5c4372512ef7 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -106,9 +106,11 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 
 	if (!journal) {
-		ret = generic_file_fsync(file, start, end, datasync);
+		ret = __generic_file_fsync(file, start, end, datasync);
 		if (!ret && !hlist_empty(&inode->i_dentry))
 			ret = ext4_sync_parent(inode);
+		if (test_opt(inode->i_sb, BARRIER))
+			goto issue_flush;
 		goto out;
 	}
 
@@ -140,6 +142,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		needs_barrier = true;
 	ret = jbd2_complete_transaction(journal, commit_tid);
 	if (needs_barrier) {
+	issue_flush:
 		err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 		if (!ret)
 			ret = err;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 3da4cf8d18b6..9e66cd1d7b78 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -214,7 +214,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	trace_ext4_load_inode_bitmap(sb, block_group);
 	bh->b_end_io = ext4_end_bitmap_read;
 	get_bh(bh);
-	submit_bh(READ | REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 	if (!buffer_uptodate(bh)) {
 		put_bh(bh);
@@ -767,10 +767,10 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	if ((ext4_encrypted_inode(dir) ||
 	     DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
 	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
-		err = ext4_get_encryption_info(dir);
+		err = fscrypt_get_encryption_info(dir);
 		if (err)
 			return ERR_PTR(err);
-		if (ext4_encryption_info(dir) == NULL)
+		if (!fscrypt_has_encryption_key(dir))
 			return ERR_PTR(-EPERM);
 		if (!handle)
 			nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb);
@@ -1115,7 +1115,8 @@ got:
 	}
 
 	if (encrypt) {
-		err = ext4_inherit_context(dir, inode);
+		/* give pointer to avoid set_context with journal ops. */
+		err = fscrypt_inherit_context(dir, inode, &encrypt, true);
 		if (err)
 			goto fail_free_drop;
 	}
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index ff7538c26992..f74d5ee2cdec 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1326,7 +1326,7 @@ int htree_inlinedir_to_tree(struct file *dir_file,
 	struct ext4_iloc iloc;
 	void *dir_buf = NULL;
 	struct ext4_dir_entry_2 fake;
-	struct ext4_str tmp_str;
+	struct fscrypt_str tmp_str;
 
 	ret = ext4_get_inode_loc(inode, &iloc);
 	if (ret)
@@ -1739,20 +1739,20 @@ ext4_get_inline_entry(struct inode *inode,
 	return (struct ext4_dir_entry_2 *)(inline_pos + offset);
 }
 
-int empty_inline_dir(struct inode *dir, int *has_inline_data)
+bool empty_inline_dir(struct inode *dir, int *has_inline_data)
 {
 	int err, inline_size;
 	struct ext4_iloc iloc;
 	void *inline_pos;
 	unsigned int offset;
 	struct ext4_dir_entry_2 *de;
-	int ret = 1;
+	bool ret = true;
 
 	err = ext4_get_inode_loc(dir, &iloc);
 	if (err) {
 		EXT4_ERROR_INODE(dir, "error %d getting inode %lu block",
 				 err, dir->i_ino);
-		return 1;
+		return true;
 	}
 
 	down_read(&EXT4_I(dir)->xattr_sem);
@@ -1766,7 +1766,7 @@ int empty_inline_dir(struct inode *dir, int *has_inline_data)
 		ext4_warning(dir->i_sb,
 			     "bad inline directory (dir #%lu) - no `..'",
 			     dir->i_ino);
-		ret = 1;
+		ret = true;
 		goto out;
 	}
 
@@ -1784,11 +1784,11 @@ int empty_inline_dir(struct inode *dir, int *has_inline_data)
 				     dir->i_ino, le32_to_cpu(de->inode),
 				     le16_to_cpu(de->rec_len), de->name_len,
 				     inline_size);
-			ret = 1;
+			ret = true;
 			goto out;
 		}
 		if (le32_to_cpu(de->inode)) {
-			ret = 0;
+			ret = false;
 			goto out;
 		}
 		offset += ext4_rec_len_from_disk(de->rec_len, inline_size);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f7140ca66e3b..3131747199e1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -51,25 +51,31 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	__u16 csum_lo;
-	__u16 csum_hi = 0;
 	__u32 csum;
+	__u16 dummy_csum = 0;
+	int offset = offsetof(struct ext4_inode, i_checksum_lo);
+	unsigned int csum_size = sizeof(dummy_csum);
 
-	csum_lo = le16_to_cpu(raw->i_checksum_lo);
-	raw->i_checksum_lo = 0;
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
-		csum_hi = le16_to_cpu(raw->i_checksum_hi);
-		raw->i_checksum_hi = 0;
-	}
-
-	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
-			   EXT4_INODE_SIZE(inode->i_sb));
+	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
+	offset += csum_size;
+	csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+			   EXT4_GOOD_OLD_INODE_SIZE - offset);
 
-	raw->i_checksum_lo = cpu_to_le16(csum_lo);
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
-		raw->i_checksum_hi = cpu_to_le16(csum_hi);
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		offset = offsetof(struct ext4_inode, i_checksum_hi);
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw +
+				   EXT4_GOOD_OLD_INODE_SIZE,
+				   offset - EXT4_GOOD_OLD_INODE_SIZE);
+		if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
+			csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
+					   csum_size);
+			offset += csum_size;
+			csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+					   EXT4_INODE_SIZE(inode->i_sb) -
+					   offset);
+		}
+	}
 
 	return csum;
 }
@@ -205,9 +211,9 @@ void ext4_evict_inode(struct inode *inode)
 		 * Note that directories do not have this problem because they
 		 * don't use page cache.
 		 */
-		if (ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
-		    inode->i_ino != EXT4_JOURNAL_INO) {
+		if (inode->i_ino != EXT4_JOURNAL_INO &&
+		    ext4_should_journal_data(inode) &&
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -386,7 +392,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
 	int ret;
 
 	if (ext4_encrypted_inode(inode))
-		return ext4_encrypted_zeroout(inode, lblk, pblk, len);
+		return fscrypt_zeroout_range(inode, lblk, pblk, len);
 
 	ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
 	if (ret > 0)
@@ -981,7 +987,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 		return bh;
 	if (!bh || buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
+	ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
@@ -1135,7 +1141,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
 		    !buffer_unwritten(bh) &&
 		    (block_start < from || block_end > to)) {
-			ll_rw_block(READ, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 			*wait_bh++ = bh;
 			decrypt = ext4_encrypted_inode(inode) &&
 				S_ISREG(inode->i_mode);
@@ -1152,7 +1158,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 	if (unlikely(err))
 		page_zero_new_buffers(page, from, to);
 	else if (decrypt)
-		err = ext4_decrypt(page);
+		err = fscrypt_decrypt_page(page);
 	return err;
 }
 #endif
@@ -2748,13 +2754,36 @@ retry:
 				done = true;
 			}
 		}
-		ext4_journal_stop(handle);
+		/*
+		 * Caution: If the handle is synchronous,
+		 * ext4_journal_stop() can wait for transaction commit
+		 * to finish which may depend on writeback of pages to
+		 * complete or on page lock to be released.  In that
+		 * case, we have to wait until after after we have
+		 * submitted all the IO, released page locks we hold,
+		 * and dropped io_end reference (for extent conversion
+		 * to be able to complete) before stopping the handle.
+		 */
+		if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+			ext4_journal_stop(handle);
+			handle = NULL;
+		}
 		/* Submit prepared bio */
 		ext4_io_submit(&mpd.io_submit);
 		/* Unlock pages we didn't use */
 		mpage_release_unused_pages(&mpd, give_up_on_write);
-		/* Drop our io_end reference we got from init */
-		ext4_put_io_end(mpd.io_submit.io_end);
+		/*
+		 * Drop our io_end reference we got from init. We have
+		 * to be careful and use deferred io_end finishing if
+		 * we are still holding the transaction as we can
+		 * release the last reference to io_end which may end
+		 * up doing unwritten extent conversion.
+		 */
+		if (handle) {
+			ext4_put_io_end_defer(mpd.io_submit.io_end);
+			ext4_journal_stop(handle);
+		} else
+			ext4_put_io_end(mpd.io_submit.io_end);
 
 		if (ret == -ENOSPC && sbi->s_journal) {
 			/*
@@ -3698,7 +3727,7 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 
 	if (!buffer_uptodate(bh)) {
 		err = -EIO;
-		ll_rw_block(READ, 1, &bh);
+		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 		wait_on_buffer(bh);
 		/* Uhhuh. Read error. Complain and punt. */
 		if (!buffer_uptodate(bh))
@@ -3706,9 +3735,9 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		if (S_ISREG(inode->i_mode) &&
 		    ext4_encrypted_inode(inode)) {
 			/* We expect the key to be set. */
-			BUG_ON(!ext4_has_encryption_key(inode));
+			BUG_ON(!fscrypt_has_encryption_key(inode));
 			BUG_ON(blocksize != PAGE_SIZE);
-			WARN_ON_ONCE(ext4_decrypt(page));
+			WARN_ON_ONCE(fscrypt_decrypt_page(page));
 		}
 	}
 	if (ext4_should_journal_data(inode)) {
@@ -4281,7 +4310,7 @@ make_io:
 		trace_ext4_load_inode(inode);
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ | REQ_META | REQ_PRIO, bh);
+		submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			EXT4_ERROR_INODE_BLOCK(inode, block,
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 28cc412852af..10686fd67fb4 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -308,6 +308,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
 	kprojid_t kprojid;
 	struct ext4_iloc iloc;
 	struct ext4_inode *raw_inode;
+	struct dquot *transfer_to[MAXQUOTAS] = { };
 
 	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
 			EXT4_FEATURE_RO_COMPAT_PROJECT)) {
@@ -361,17 +362,14 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
 	if (err)
 		goto out_stop;
 
-	if (sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
-		struct dquot *transfer_to[MAXQUOTAS] = { };
-
-		transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
-		if (!IS_ERR(transfer_to[PRJQUOTA])) {
-			err = __dquot_transfer(inode, transfer_to);
-			dqput(transfer_to[PRJQUOTA]);
-			if (err)
-				goto out_dirty;
-		}
+	transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
+	if (!IS_ERR(transfer_to[PRJQUOTA])) {
+		err = __dquot_transfer(inode, transfer_to);
+		dqput(transfer_to[PRJQUOTA]);
+		if (err)
+			goto out_dirty;
 	}
+
 	EXT4_I(inode)->i_projid = kprojid;
 	inode->i_ctime = ext4_current_time(inode);
 out_dirty:
@@ -772,19 +770,13 @@ resizefs_out:
 		return ext4_ext_precache(inode);
 	case EXT4_IOC_SET_ENCRYPTION_POLICY: {
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-		struct ext4_encryption_policy policy;
-		int err = 0;
+		struct fscrypt_policy policy;
 
 		if (copy_from_user(&policy,
-				   (struct ext4_encryption_policy __user *)arg,
-				   sizeof(policy))) {
-			err = -EFAULT;
-			goto encryption_policy_out;
-		}
-
-		err = ext4_process_policy(&policy, inode);
-encryption_policy_out:
-		return err;
+				   (struct fscrypt_policy __user *)arg,
+				   sizeof(policy)))
+			return -EFAULT;
+		return fscrypt_process_policy(inode, &policy);
 #else
 		return -EOPNOTSUPP;
 #endif
@@ -827,12 +819,12 @@ encryption_policy_out:
 	}
 	case EXT4_IOC_GET_ENCRYPTION_POLICY: {
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-		struct ext4_encryption_policy policy;
+		struct fscrypt_policy policy;
 		int err = 0;
 
 		if (!ext4_encrypted_inode(inode))
 			return -ENOENT;
-		err = ext4_get_policy(inode, &policy);
+		err = fscrypt_get_policy(inode, &policy);
 		if (err)
 			return err;
 		if (copy_to_user((void __user *)arg, &policy, sizeof(policy)))
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c1ab3ec30423..11562161e24a 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2627,6 +2627,7 @@ int ext4_mb_init(struct super_block *sb)
 
 	spin_lock_init(&sbi->s_md_lock);
 	spin_lock_init(&sbi->s_bal_lock);
+	sbi->s_mb_free_pending = 0;
 
 	sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN;
 	sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN;
@@ -2814,6 +2815,9 @@ static void ext4_free_data_callback(struct super_block *sb,
 	/* we expect to find existing buddy because it's pinned */
 	BUG_ON(err != 0);
 
+	spin_lock(&EXT4_SB(sb)->s_md_lock);
+	EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count;
+	spin_unlock(&EXT4_SB(sb)->s_md_lock);
 
 	db = e4b.bd_info;
 	/* there are blocks to put in buddy to make them really free */
@@ -2939,7 +2943,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
 			   "fs metadata", block, block+len);
 		/* File system mounted not to panic on error
-		 * Fix the bitmap and repeat the block allocation
+		 * Fix the bitmap and return EFSCORRUPTED
 		 * We leak some of the blocks here.
 		 */
 		ext4_lock_group(sb, ac->ac_b_ex.fe_group);
@@ -2948,7 +2952,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
 		if (!err)
-			err = -EAGAIN;
+			err = -EFSCORRUPTED;
 		goto out_err;
 	}
 
@@ -4513,18 +4517,7 @@ repeat:
 	}
 	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
 		*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
-		if (*errp == -EAGAIN) {
-			/*
-			 * drop the reference that we took
-			 * in ext4_mb_use_best_found
-			 */
-			ext4_mb_release_context(ac);
-			ac->ac_b_ex.fe_group = 0;
-			ac->ac_b_ex.fe_start = 0;
-			ac->ac_b_ex.fe_len = 0;
-			ac->ac_status = AC_STATUS_CONTINUE;
-			goto repeat;
-		} else if (*errp) {
+		if (*errp) {
 			ext4_discard_allocated_blocks(ac);
 			goto errout;
 		} else {
@@ -4583,6 +4576,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 {
 	ext4_group_t group = e4b->bd_group;
 	ext4_grpblk_t cluster;
+	ext4_grpblk_t clusters = new_entry->efd_count;
 	struct ext4_free_data *entry;
 	struct ext4_group_info *db = e4b->bd_info;
 	struct super_block *sb = e4b->bd_sb;
@@ -4649,8 +4643,11 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 		}
 	}
 	/* Add the extent to transaction's private list */
-	ext4_journal_callback_add(handle, ext4_free_data_callback,
-				  &new_entry->efd_jce);
+	new_entry->efd_jce.jce_func = ext4_free_data_callback;
+	spin_lock(&sbi->s_md_lock);
+	_ext4_journal_callback_add(handle, &new_entry->efd_jce);
+	sbi->s_mb_free_pending += clusters;
+	spin_unlock(&sbi->s_md_lock);
 	return 0;
 }
 
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 23d436d6f8b8..d89754ef1aab 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -52,7 +52,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
 	lock_buffer(bh);
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
-	submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_WRITE, WRITE_SYNC | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 	sb_end_write(sb);
 	if (unlikely(!buffer_uptodate(bh)))
@@ -88,7 +88,7 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
 	get_bh(*bh);
 	lock_buffer(*bh);
 	(*bh)->b_end_io = end_buffer_read_sync;
-	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh);
+	submit_bh(REQ_OP_READ, READ_SYNC | REQ_META | REQ_PRIO, *bh);
 	wait_on_buffer(*bh);
 	if (!buffer_uptodate(*bh)) {
 		ret = -EIO;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index ec4c39952e84..34c0142caf6a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -420,15 +420,14 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	__u32 csum;
-	__le32 save_csum;
 	int size;
+	__u32 dummy_csum = 0;
+	int offset = offsetof(struct dx_tail, dt_checksum);
 
 	size = count_offset + (count * sizeof(struct dx_entry));
-	save_csum = t->dt_checksum;
-	t->dt_checksum = 0;
 	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
-	csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail));
-	t->dt_checksum = save_csum;
+	csum = ext4_chksum(sbi, csum, (__u8 *)t, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
 
 	return cpu_to_le32(csum);
 }
@@ -446,14 +445,14 @@ static int ext4_dx_csum_verify(struct inode *inode,
 	c = get_dx_countlimit(inode, dirent, &count_offset);
 	if (!c) {
 		EXT4_ERROR_INODE(inode, "dir seems corrupt?  Run e2fsck -D.");
-		return 1;
+		return 0;
 	}
 	limit = le16_to_cpu(c->limit);
 	count = le16_to_cpu(c->count);
 	if (count_offset + (limit * sizeof(struct dx_entry)) >
 	    EXT4_BLOCK_SIZE(inode->i_sb) - sizeof(struct dx_tail)) {
 		warn_no_space_for_csum(inode);
-		return 1;
+		return 0;
 	}
 	t = (struct dx_tail *)(((struct dx_entry *)c) + limit);
 
@@ -612,19 +611,19 @@ static struct stats dx_show_leaf(struct inode *dir,
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 				int len;
 				char *name;
-				struct ext4_str fname_crypto_str
-					= {.name = NULL, .len = 0};
+				struct fscrypt_str fname_crypto_str =
+					FSTR_INIT(NULL, 0);
 				int res = 0;
 
 				name  = de->name;
 				len = de->name_len;
-				if (ext4_encrypted_inode(inode))
-					res = ext4_get_encryption_info(dir);
+				if (ext4_encrypted_inode(dir))
+					res = fscrypt_get_encryption_info(dir);
 				if (res) {
 					printk(KERN_WARNING "Error setting up"
 					       " fname crypto: %d\n", res);
 				}
-				if (ctx == NULL) {
+				if (!fscrypt_has_encryption_key(dir)) {
 					/* Directory is not encrypted */
 					ext4fs_dirhash(de->name,
 						de->name_len, &h);
@@ -633,19 +632,21 @@ static struct stats dx_show_leaf(struct inode *dir,
 					       (unsigned) ((char *) de
 							   - base));
 				} else {
+					struct fscrypt_str de_name =
+						FSTR_INIT(name, len);
+
 					/* Directory is encrypted */
-					res = ext4_fname_crypto_alloc_buffer(
-						ctx, de->name_len,
+					res = fscrypt_fname_alloc_buffer(
+						dir, len,
 						&fname_crypto_str);
-					if (res < 0) {
+					if (res < 0)
 						printk(KERN_WARNING "Error "
 							"allocating crypto "
 							"buffer--skipping "
 							"crypto\n");
-						ctx = NULL;
-					}
-					res = ext4_fname_disk_to_usr(ctx, NULL, de,
-							&fname_crypto_str);
+					res = fscrypt_fname_disk_to_usr(dir,
+						0, 0, &de_name,
+						&fname_crypto_str);
 					if (res < 0) {
 						printk(KERN_WARNING "Error "
 							"converting filename "
@@ -662,8 +663,8 @@ static struct stats dx_show_leaf(struct inode *dir,
 					printk("%*.s:(E)%x.%u ", len, name,
 					       h.hash, (unsigned) ((char *) de
 								   - base));
-					ext4_fname_crypto_free_buffer(
-						&fname_crypto_str);
+					fscrypt_fname_free_buffer(
+							&fname_crypto_str);
 				}
 #else
 				int len = de->name_len;
@@ -952,7 +953,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de, *top;
 	int err = 0, count = 0;
-	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}, tmp_str;
+	struct fscrypt_str fname_crypto_str = FSTR_INIT(NULL, 0), tmp_str;
 
 	dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
 							(unsigned long)block));
@@ -967,12 +968,12 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 	/* Check if the directory is encrypted */
 	if (ext4_encrypted_inode(dir)) {
-		err = ext4_get_encryption_info(dir);
+		err = fscrypt_get_encryption_info(dir);
 		if (err < 0) {
 			brelse(bh);
 			return err;
 		}
-		err = ext4_fname_crypto_alloc_buffer(dir, EXT4_NAME_LEN,
+		err = fscrypt_fname_alloc_buffer(dir, EXT4_NAME_LEN,
 						     &fname_crypto_str);
 		if (err < 0) {
 			brelse(bh);
@@ -1003,10 +1004,13 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 				   &tmp_str);
 		} else {
 			int save_len = fname_crypto_str.len;
+			struct fscrypt_str de_name = FSTR_INIT(de->name,
+								de->name_len);
 
 			/* Directory is encrypted */
-			err = ext4_fname_disk_to_usr(dir, hinfo, de,
-						     &fname_crypto_str);
+			err = fscrypt_fname_disk_to_usr(dir, hinfo->hash,
+					hinfo->minor_hash, &de_name,
+					&fname_crypto_str);
 			if (err < 0) {
 				count = err;
 				goto errout;
@@ -1025,7 +1029,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 errout:
 	brelse(bh);
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-	ext4_fname_crypto_free_buffer(&fname_crypto_str);
+	fscrypt_fname_free_buffer(&fname_crypto_str);
 #endif
 	return count;
 }
@@ -1050,7 +1054,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	int count = 0;
 	int ret, err;
 	__u32 hashval;
-	struct ext4_str tmp_str;
+	struct fscrypt_str tmp_str;
 
 	dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
 		       start_hash, start_minor_hash));
@@ -1443,7 +1447,8 @@ restart:
 				}
 				bh_use[ra_max] = bh;
 				if (bh)
-					ll_rw_block(READ | REQ_META | REQ_PRIO,
+					ll_rw_block(REQ_OP_READ,
+						    REQ_META | REQ_PRIO,
 						    1, &bh);
 			}
 		}
@@ -1563,26 +1568,23 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 	struct ext4_dir_entry_2 *de;
 	struct buffer_head *bh;
 
-       if (ext4_encrypted_inode(dir)) {
-               int res = ext4_get_encryption_info(dir);
+	if (ext4_encrypted_inode(dir)) {
+		int res = fscrypt_get_encryption_info(dir);
 
 		/*
-		 * This should be a properly defined flag for
-		 * dentry->d_flags when we uplift this to the VFS.
-		 * d_fsdata is set to (void *) 1 if if the dentry is
+		 * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
 		 * created while the directory was encrypted and we
-		 * don't have access to the key.
+		 * have access to the key.
 		 */
-	       dentry->d_fsdata = NULL;
-	       if (ext4_encryption_info(dir))
-		       dentry->d_fsdata = (void *) 1;
-	       d_set_d_op(dentry, &ext4_encrypted_d_ops);
-	       if (res && res != -ENOKEY)
-		       return ERR_PTR(res);
-       }
+		if (fscrypt_has_encryption_key(dir))
+			fscrypt_set_encrypted_dentry(dentry);
+		fscrypt_set_d_op(dentry);
+		if (res && res != -ENOKEY)
+			return ERR_PTR(res);
+	}
 
-	if (dentry->d_name.len > EXT4_NAME_LEN)
-		return ERR_PTR(-ENAMETOOLONG);
+       if (dentry->d_name.len > EXT4_NAME_LEN)
+	       return ERR_PTR(-ENAMETOOLONG);
 
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
 	if (IS_ERR(bh))
@@ -1609,11 +1611,9 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 		}
 		if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
 		    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
-		    !ext4_is_child_context_consistent_with_parent(dir,
-								  inode)) {
+		    !fscrypt_has_permitted_context(dir, inode)) {
 			int nokey = ext4_encrypted_inode(inode) &&
-				!ext4_encryption_info(inode);
-
+				!fscrypt_has_encryption_key(inode);
 			iput(inode);
 			if (nokey)
 				return ERR_PTR(-ENOKEY);
@@ -2690,30 +2690,30 @@ out_stop:
 /*
  * routine to check that the specified directory is empty (for rmdir)
  */
-int ext4_empty_dir(struct inode *inode)
+bool ext4_empty_dir(struct inode *inode)
 {
 	unsigned int offset;
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de, *de1;
 	struct super_block *sb;
-	int err = 0;
 
 	if (ext4_has_inline_data(inode)) {
 		int has_inline_data = 1;
+		int ret;
 
-		err = empty_inline_dir(inode, &has_inline_data);
+		ret = empty_inline_dir(inode, &has_inline_data);
 		if (has_inline_data)
-			return err;
+			return ret;
 	}
 
 	sb = inode->i_sb;
 	if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2)) {
 		EXT4_ERROR_INODE(inode, "invalid size");
-		return 1;
+		return true;
 	}
 	bh = ext4_read_dirblock(inode, 0, EITHER);
 	if (IS_ERR(bh))
-		return 1;
+		return true;
 
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
 	de1 = ext4_next_entry(de, sb->s_blocksize);
@@ -2722,7 +2722,7 @@ int ext4_empty_dir(struct inode *inode)
 			strcmp(".", de->name) || strcmp("..", de1->name)) {
 		ext4_warning_inode(inode, "directory missing '.' and/or '..'");
 		brelse(bh);
-		return 1;
+		return true;
 	}
 	offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) +
 		 ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
@@ -2730,12 +2730,11 @@ int ext4_empty_dir(struct inode *inode)
 	while (offset < inode->i_size) {
 		if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
 			unsigned int lblock;
-			err = 0;
 			brelse(bh);
 			lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb);
 			bh = ext4_read_dirblock(inode, lblock, EITHER);
 			if (IS_ERR(bh))
-				return 1;
+				return true;
 			de = (struct ext4_dir_entry_2 *) bh->b_data;
 		}
 		if (ext4_check_dir_entry(inode, NULL, de, bh,
@@ -2747,13 +2746,13 @@ int ext4_empty_dir(struct inode *inode)
 		}
 		if (le32_to_cpu(de->inode)) {
 			brelse(bh);
-			return 0;
+			return false;
 		}
 		offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
 		de = ext4_next_entry(de, sb->s_blocksize);
 	}
 	brelse(bh);
-	return 1;
+	return true;
 }
 
 /*
@@ -3076,8 +3075,8 @@ static int ext4_symlink(struct inode *dir,
 	int err, len = strlen(symname);
 	int credits;
 	bool encryption_required;
-	struct ext4_str disk_link;
-	struct ext4_encrypted_symlink_data *sd = NULL;
+	struct fscrypt_str disk_link;
+	struct fscrypt_symlink_data *sd = NULL;
 
 	disk_link.len = len + 1;
 	disk_link.name = (char *) symname;
@@ -3085,13 +3084,13 @@ static int ext4_symlink(struct inode *dir,
 	encryption_required = (ext4_encrypted_inode(dir) ||
 			       DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb)));
 	if (encryption_required) {
-		err = ext4_get_encryption_info(dir);
+		err = fscrypt_get_encryption_info(dir);
 		if (err)
 			return err;
-		if (ext4_encryption_info(dir) == NULL)
+		if (!fscrypt_has_encryption_key(dir))
 			return -EPERM;
-		disk_link.len = (ext4_fname_encrypted_size(dir, len) +
-				 sizeof(struct ext4_encrypted_symlink_data));
+		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
+				 sizeof(struct fscrypt_symlink_data));
 		sd = kzalloc(disk_link.len, GFP_KERNEL);
 		if (!sd)
 			return -ENOMEM;
@@ -3139,13 +3138,12 @@ static int ext4_symlink(struct inode *dir,
 
 	if (encryption_required) {
 		struct qstr istr;
-		struct ext4_str ostr;
+		struct fscrypt_str ostr =
+			FSTR_INIT(sd->encrypted_path, disk_link.len);
 
 		istr.name = (const unsigned char *) symname;
 		istr.len = len;
-		ostr.name = sd->encrypted_path;
-		ostr.len = disk_link.len;
-		err = ext4_fname_usr_to_disk(inode, &istr, &ostr);
+		err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
 		if (err < 0)
 			goto err_drop_inode;
 		sd->len = cpu_to_le16(ostr.len);
@@ -3234,7 +3232,7 @@ static int ext4_link(struct dentry *old_dentry,
 	if (inode->i_nlink >= EXT4_LINK_MAX)
 		return -EMLINK;
 	if (ext4_encrypted_inode(dir) &&
-	    !ext4_is_child_context_consistent_with_parent(dir, inode))
+			!fscrypt_has_permitted_context(dir, inode))
 		return -EPERM;
 
        if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
@@ -3557,8 +3555,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if ((old.dir != new.dir) &&
 	    ext4_encrypted_inode(new.dir) &&
-	    !ext4_is_child_context_consistent_with_parent(new.dir,
-							  old.inode)) {
+	    !fscrypt_has_permitted_context(new.dir, old.inode)) {
 		retval = -EPERM;
 		goto end_rename;
 	}
@@ -3730,10 +3727,8 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if ((ext4_encrypted_inode(old_dir) ||
 	     ext4_encrypted_inode(new_dir)) &&
 	    (old_dir != new_dir) &&
-	    (!ext4_is_child_context_consistent_with_parent(new_dir,
-							   old.inode) ||
-	     !ext4_is_child_context_consistent_with_parent(old_dir,
-							   new.inode)))
+	    (!fscrypt_has_permitted_context(new_dir, old.inode) ||
+	     !fscrypt_has_permitted_context(old_dir, new.inode)))
 		return -EPERM;
 
 	if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) &&
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 2a01df9cc1c3..a6132a730967 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/backing-dev.h>
+#include <linux/fscrypto.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -67,7 +68,6 @@ static void ext4_finish_bio(struct bio *bio)
 		struct page *page = bvec->bv_page;
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 		struct page *data_page = NULL;
-		struct ext4_crypto_ctx *ctx = NULL;
 #endif
 		struct buffer_head *bh, *head;
 		unsigned bio_start = bvec->bv_offset;
@@ -82,8 +82,7 @@ static void ext4_finish_bio(struct bio *bio)
 		if (!page->mapping) {
 			/* The bounce data pages are unmapped. */
 			data_page = page;
-			ctx = (struct ext4_crypto_ctx *)page_private(data_page);
-			page = ctx->w.control_page;
+			fscrypt_pullback_bio_page(&page, false);
 		}
 #endif
 
@@ -113,8 +112,8 @@ static void ext4_finish_bio(struct bio *bio)
 		local_irq_restore(flags);
 		if (!under_io) {
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-			if (ctx)
-				ext4_restore_control_page(data_page);
+			if (data_page)
+				fscrypt_restore_control_page(data_page);
 #endif
 			end_page_writeback(page);
 		}
@@ -340,9 +339,10 @@ void ext4_io_submit(struct ext4_io_submit *io)
 	struct bio *bio = io->io_bio;
 
 	if (bio) {
-		int io_op = io->io_wbc->sync_mode == WB_SYNC_ALL ?
-			    WRITE_SYNC : WRITE;
-		submit_bio(io_op, io->io_bio);
+		int io_op_flags = io->io_wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : 0;
+		bio_set_op_attrs(io->io_bio, REQ_OP_WRITE, io_op_flags);
+		submit_bio(io->io_bio);
 	}
 	io->io_bio = NULL;
 }
@@ -472,7 +472,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 		gfp_t gfp_flags = GFP_NOFS;
 
 	retry_encrypt:
-		data_page = ext4_encrypt(inode, page, gfp_flags);
+		data_page = fscrypt_encrypt_page(inode, page, gfp_flags);
 		if (IS_ERR(data_page)) {
 			ret = PTR_ERR(data_page);
 			if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
@@ -510,7 +510,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	if (ret) {
 	out:
 		if (data_page)
-			ext4_restore_control_page(data_page);
+			fscrypt_restore_control_page(data_page);
 		printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
 		redirty_page_for_writepage(wbc, page);
 		do {
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index c75b66a64982..a81b829d56de 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -46,37 +46,6 @@
 
 #include "ext4.h"
 
-/*
- * Call ext4_decrypt on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
-{
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	struct ext4_crypto_ctx *ctx =
-		container_of(work, struct ext4_crypto_ctx, r.work);
-	struct bio	*bio	= ctx->r.bio;
-	struct bio_vec	*bv;
-	int		i;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		struct page *page = bv->bv_page;
-
-		int ret = ext4_decrypt(page);
-		if (ret) {
-			WARN_ON_ONCE(1);
-			SetPageError(page);
-		} else
-			SetPageUptodate(page);
-		unlock_page(page);
-	}
-	ext4_release_crypto_ctx(ctx);
-	bio_put(bio);
-#else
-	BUG();
-#endif
-}
-
 static inline bool ext4_bio_encrypted(struct bio *bio)
 {
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
@@ -104,14 +73,10 @@ static void mpage_end_io(struct bio *bio)
 	int i;
 
 	if (ext4_bio_encrypted(bio)) {
-		struct ext4_crypto_ctx *ctx = bio->bi_private;
-
 		if (bio->bi_error) {
-			ext4_release_crypto_ctx(ctx);
+			fscrypt_release_ctx(bio->bi_private);
 		} else {
-			INIT_WORK(&ctx->r.work, completion_pages);
-			ctx->r.bio = bio;
-			queue_work(ext4_read_workqueue, &ctx->r.work);
+			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
 			return;
 		}
 	}
@@ -135,7 +100,6 @@ int ext4_mpage_readpages(struct address_space *mapping,
 			 unsigned nr_pages)
 {
 	struct bio *bio = NULL;
-	unsigned page_idx;
 	sector_t last_block_in_bio = 0;
 
 	struct inode *inode = mapping->host;
@@ -157,7 +121,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 	map.m_len = 0;
 	map.m_flags = 0;
 
-	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
+	for (; nr_pages; nr_pages--) {
 		int fully_mapped = 1;
 		unsigned first_hole = blocks_per_page;
 
@@ -271,15 +235,15 @@ int ext4_mpage_readpages(struct address_space *mapping,
 		 */
 		if (bio && (last_block_in_bio != blocks[0] - 1)) {
 		submit_and_realloc:
-			submit_bio(READ, bio);
+			submit_bio(bio);
 			bio = NULL;
 		}
 		if (bio == NULL) {
-			struct ext4_crypto_ctx *ctx = NULL;
+			struct fscrypt_ctx *ctx = NULL;
 
 			if (ext4_encrypted_inode(inode) &&
 			    S_ISREG(inode->i_mode)) {
-				ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
+				ctx = fscrypt_get_ctx(inode, GFP_NOFS);
 				if (IS_ERR(ctx))
 					goto set_error_page;
 			}
@@ -287,13 +251,14 @@ int ext4_mpage_readpages(struct address_space *mapping,
 				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
-					ext4_release_crypto_ctx(ctx);
+					fscrypt_release_ctx(ctx);
 				goto set_error_page;
 			}
 			bio->bi_bdev = bdev;
 			bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
 			bio->bi_end_io = mpage_end_io;
 			bio->bi_private = ctx;
+			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		}
 
 		length = first_hole << blkbits;
@@ -303,14 +268,14 @@ int ext4_mpage_readpages(struct address_space *mapping,
 		if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
 		     (relative_block == map.m_len)) ||
 		    (first_hole != blocks_per_page)) {
-			submit_bio(READ, bio);
+			submit_bio(bio);
 			bio = NULL;
 		} else
 			last_block_in_bio = blocks[blocks_per_page - 1];
 		goto next_page;
 	confused:
 		if (bio) {
-			submit_bio(READ, bio);
+			submit_bio(bio);
 			bio = NULL;
 		}
 		if (!PageUptodate(page))
@@ -323,6 +288,6 @@ int ext4_mpage_readpages(struct address_space *mapping,
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
-		submit_bio(READ, bio);
+		submit_bio(bio);
 	return 0;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3822a5aedc61..1c593aa0218e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -945,9 +945,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	ei->i_crypt_info = NULL;
-#endif
 	return &ei->vfs_inode;
 }
 
@@ -1026,8 +1023,7 @@ void ext4_clear_inode(struct inode *inode)
 		EXT4_I(inode)->jinode = NULL;
 	}
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-	if (EXT4_I(inode)->i_crypt_info)
-		ext4_free_encryption_info(inode, EXT4_I(inode)->i_crypt_info);
+	fscrypt_put_encryption_info(inode, NULL);
 #endif
 }
 
@@ -1094,6 +1090,90 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
 	return try_to_free_buffers(page);
 }
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
+}
+
+static int ext4_key_prefix(struct inode *inode, u8 **key)
+{
+	*key = EXT4_SB(inode->i_sb)->key_prefix;
+	return EXT4_SB(inode->i_sb)->key_prefix_size;
+}
+
+static int ext4_prepare_context(struct inode *inode)
+{
+	return ext4_convert_inline_data(inode);
+}
+
+static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
+							void *fs_data)
+{
+	handle_t *handle;
+	int res, res2;
+
+	/* fs_data is null when internally used. */
+	if (fs_data) {
+		res  = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
+				len, 0);
+		if (!res) {
+			ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+			ext4_clear_inode_state(inode,
+					EXT4_STATE_MAY_INLINE_DATA);
+		}
+		return res;
+	}
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC,
+			ext4_jbd2_credits_xattr(inode));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+			EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
+			len, 0);
+	if (!res) {
+		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+		res = ext4_mark_inode_dirty(handle, inode);
+		if (res)
+			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
+	}
+	res2 = ext4_journal_stop(handle);
+	if (!res)
+		res = res2;
+	return res;
+}
+
+static int ext4_dummy_context(struct inode *inode)
+{
+	return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
+}
+
+static unsigned ext4_max_namelen(struct inode *inode)
+{
+	return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
+		EXT4_NAME_LEN;
+}
+
+static struct fscrypt_operations ext4_cryptops = {
+	.get_context		= ext4_get_context,
+	.key_prefix		= ext4_key_prefix,
+	.prepare_context	= ext4_prepare_context,
+	.set_context		= ext4_set_context,
+	.dummy_context		= ext4_dummy_context,
+	.is_encrypted		= ext4_encrypted_inode,
+	.empty_dir		= ext4_empty_dir,
+	.max_namelen		= ext4_max_namelen,
+};
+#else
+static struct fscrypt_operations ext4_cryptops = {
+	.is_encrypted		= ext4_encrypted_inode,
+};
+#endif
+
 #ifdef CONFIG_QUOTA
 static char *quotatypes[] = INITQFNAMES;
 #define QTYPE2NAME(t) (quotatypes[t])
@@ -2068,23 +2148,25 @@ failed:
 static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 				   struct ext4_group_desc *gdp)
 {
-	int offset;
+	int offset = offsetof(struct ext4_group_desc, bg_checksum);
 	__u16 crc = 0;
 	__le32 le_group = cpu_to_le32(block_group);
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (ext4_has_metadata_csum(sbi->s_sb)) {
 		/* Use new metadata_csum algorithm */
-		__le16 save_csum;
 		__u32 csum32;
+		__u16 dummy_csum = 0;
 
-		save_csum = gdp->bg_checksum;
-		gdp->bg_checksum = 0;
 		csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
 				     sizeof(le_group));
-		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
-				     sbi->s_desc_size);
-		gdp->bg_checksum = save_csum;
+		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset);
+		csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum,
+				     sizeof(dummy_csum));
+		offset += sizeof(dummy_csum);
+		if (offset < sbi->s_desc_size)
+			csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset,
+					     sbi->s_desc_size - offset);
 
 		crc = csum32 & 0xFFFF;
 		goto out;
@@ -2094,8 +2176,6 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 	if (!ext4_has_feature_gdt_csum(sb))
 		return 0;
 
-	offset = offsetof(struct ext4_group_desc, bg_checksum);
-
 	crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
 	crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
 	crc = crc16(crc, (__u8 *)gdp, offset);
@@ -2278,6 +2358,16 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 	while (es->s_last_orphan) {
 		struct inode *inode;
 
+		/*
+		 * We may have encountered an error during cleanup; if
+		 * so, skip the rest.
+		 */
+		if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+			jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
+			es->s_last_orphan = 0;
+			break;
+		}
+
 		inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
 		if (IS_ERR(inode)) {
 			es->s_last_orphan = 0;
@@ -3416,6 +3506,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Number of reserved GDT blocks insanely large: %d",
+			 le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
+		goto failed_mount;
+	}
+
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
 		err = bdev_dax_supported(sb, blocksize);
 		if (err)
@@ -3686,6 +3783,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_op = &ext4_sops;
 	sb->s_export_op = &ext4_export_ops;
 	sb->s_xattr = ext4_xattr_handlers;
+	sb->s_cop = &ext4_cryptops;
 #ifdef CONFIG_QUOTA
 	sb->dq_op = &ext4_quota_operations;
 	if (ext4_has_feature_quota(sb))
@@ -3996,6 +4094,11 @@ no_journal:
 	ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
 
 	kfree(orig_data);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	memcpy(sbi->key_prefix, EXT4_KEY_DESC_PREFIX,
+				EXT4_KEY_DESC_PREFIX_SIZE);
+	sbi->key_prefix_size = EXT4_KEY_DESC_PREFIX_SIZE;
+#endif
 	return 0;
 
 cantfind_ext4:
@@ -4204,7 +4307,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 		goto out_bdev;
 	}
 	journal->j_private = sb;
-	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &journal->j_sb_buffer);
+	ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &journal->j_sb_buffer);
 	wait_on_buffer(journal->j_sb_buffer);
 	if (!buffer_uptodate(journal->j_sb_buffer)) {
 		ext4_msg(sb, KERN_ERR, "I/O error on journal device");
@@ -4327,20 +4430,6 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 
 	if (!sbh || block_device_ejected(sb))
 		return error;
-	if (buffer_write_io_error(sbh)) {
-		/*
-		 * Oh, dear.  A previous attempt to write the
-		 * superblock failed.  This could happen because the
-		 * USB device was yanked out.  Or it could happen to
-		 * be a transient write error and maybe the block will
-		 * be remapped.  Nothing we can do but to retry the
-		 * write and hope for the best.
-		 */
-		ext4_msg(sb, KERN_ERR, "previous I/O error to "
-		       "superblock detected");
-		clear_buffer_write_io_error(sbh);
-		set_buffer_uptodate(sbh);
-	}
 	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
@@ -4371,7 +4460,23 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 				&EXT4_SB(sb)->s_freeinodes_counter));
 	BUFFER_TRACE(sbh, "marking dirty");
 	ext4_superblock_csum_set(sb);
+	lock_buffer(sbh);
+	if (buffer_write_io_error(sbh)) {
+		/*
+		 * Oh, dear.  A previous attempt to write the
+		 * superblock failed.  This could happen because the
+		 * USB device was yanked out.  Or it could happen to
+		 * be a transient write error and maybe the block will
+		 * be remapped.  Nothing we can do but to retry the
+		 * write and hope for the best.
+		 */
+		ext4_msg(sb, KERN_ERR, "previous I/O error to "
+		       "superblock detected");
+		clear_buffer_write_io_error(sbh);
+		set_buffer_uptodate(sbh);
+	}
 	mark_buffer_dirty(sbh);
+	unlock_buffer(sbh);
 	if (sync) {
 		error = __sync_dirty_buffer(sbh,
 			test_opt(sb, BARRIER) ? WRITE_FUA : WRITE_SYNC);
@@ -5422,7 +5527,6 @@ out5:
 
 static void __exit ext4_exit_fs(void)
 {
-	ext4_exit_crypto();
 	ext4_destroy_lazyinit_thread();
 	unregister_as_ext2();
 	unregister_as_ext3();
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 75ed5c2f0c16..4d83d9e05f2e 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -22,23 +22,22 @@
 #include "ext4.h"
 #include "xattr.h"
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
 static const char *ext4_encrypted_get_link(struct dentry *dentry,
 					   struct inode *inode,
 					   struct delayed_call *done)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
-	struct ext4_str cstr, pstr;
-	struct ext4_encrypted_symlink_data *sd;
+	struct fscrypt_str cstr, pstr;
+	struct fscrypt_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
 	int res;
-	u32 plen, max_size = inode->i_sb->s_blocksize;
+	u32 max_size = inode->i_sb->s_blocksize;
 
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
 
-	res = ext4_get_encryption_info(inode);
+	res = fscrypt_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
 
@@ -54,30 +53,27 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
 	}
 
 	/* Symlink is encrypted */
-	sd = (struct ext4_encrypted_symlink_data *)caddr;
+	sd = (struct fscrypt_symlink_data *)caddr;
 	cstr.name = sd->encrypted_path;
 	cstr.len  = le16_to_cpu(sd->len);
-	if ((cstr.len +
-	     sizeof(struct ext4_encrypted_symlink_data) - 1) >
-	    max_size) {
+	if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
 		/* Symlink data on the disk is corrupted */
 		res = -EFSCORRUPTED;
 		goto errout;
 	}
-	plen = (cstr.len < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) ?
-		EXT4_FNAME_CRYPTO_DIGEST_SIZE*2 : cstr.len;
-	paddr = kmalloc(plen + 1, GFP_NOFS);
-	if (!paddr) {
-		res = -ENOMEM;
+
+	res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
+	if (res)
 		goto errout;
-	}
-	pstr.name = paddr;
-	pstr.len = plen;
-	res = _ext4_fname_disk_to_usr(inode, NULL, &cstr, &pstr);
+
+	res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
 	if (res < 0)
 		goto errout;
+
+	paddr = pstr.name;
+
 	/* Null-terminate the name */
-	if (res <= plen)
+	if (res <= pstr.len)
 		paddr[res] = '\0';
 	if (cpage)
 		put_page(cpage);
@@ -99,7 +95,6 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 	.listxattr	= ext4_listxattr,
 	.removexattr	= generic_removexattr,
 };
-#endif
 
 const struct inode_operations ext4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index e79bd32b9b79..39e9cfb1b371 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -121,17 +121,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	__u32 csum;
-	__le32 save_csum;
 	__le64 dsk_block_nr = cpu_to_le64(block_nr);
+	__u32 dummy_csum = 0;
+	int offset = offsetof(struct ext4_xattr_header, h_checksum);
 
-	save_csum = hdr->h_checksum;
-	hdr->h_checksum = 0;
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
 			   sizeof(dsk_block_nr));
-	csum = ext4_chksum(sbi, csum, (__u8 *)hdr,
-			   EXT4_BLOCK_SIZE(inode->i_sb));
+	csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
+	offset += sizeof(dummy_csum);
+	csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
+			   EXT4_BLOCK_SIZE(inode->i_sb) - offset);
 
-	hdr->h_checksum = save_csum;
 	return cpu_to_le32(csum);
 }
 
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 389160049993..124b4a3017b5 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -63,14 +63,15 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = META,
-		.rw = READ_SYNC | REQ_META | REQ_PRIO,
+		.op = REQ_OP_READ,
+		.op_flags = READ_SYNC | REQ_META | REQ_PRIO,
 		.old_blkaddr = index,
 		.new_blkaddr = index,
 		.encrypted_page = NULL,
 	};
 
 	if (unlikely(!is_meta))
-		fio.rw &= ~REQ_META;
+		fio.op_flags &= ~REQ_META;
 repeat:
 	page = f2fs_grab_cache_page(mapping, index, false);
 	if (!page) {
@@ -157,13 +158,14 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = META,
-		.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
+		.op = REQ_OP_READ,
+		.op_flags = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : REQ_RAHEAD,
 		.encrypted_page = NULL,
 	};
 	struct blk_plug plug;
 
 	if (unlikely(type == META_POR))
-		fio.rw &= ~REQ_META;
+		fio.op_flags &= ~REQ_META;
 
 	blk_start_plug(&plug);
 	for (; nrpages-- > 0; blkno++) {
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index c80dda4bdff8..ded224518978 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -97,12 +97,11 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 	return bio;
 }
 
-static inline void __submit_bio(struct f2fs_sb_info *sbi, int rw,
-						struct bio *bio)
+static inline void __submit_bio(struct f2fs_sb_info *sbi, struct bio *bio)
 {
-	if (!is_read_io(rw))
+	if (!is_read_io(bio_op(bio)))
 		atomic_inc(&sbi->nr_wb_bios);
-	submit_bio(rw, bio);
+	submit_bio(bio);
 }
 
 static void __submit_merged_bio(struct f2fs_bio_info *io)
@@ -112,12 +111,14 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	if (!io->bio)
 		return;
 
-	if (is_read_io(fio->rw))
+	if (is_read_io(fio->op))
 		trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
 	else
 		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
 
-	__submit_bio(io->sbi, fio->rw, io->bio);
+	bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
+
+	__submit_bio(io->sbi, io->bio);
 	io->bio = NULL;
 }
 
@@ -183,10 +184,12 @@ static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
+		io->fio.op = REQ_OP_WRITE;
 		if (test_opt(sbi, NOBARRIER))
-			io->fio.rw = WRITE_FLUSH | REQ_META | REQ_PRIO;
+			io->fio.op_flags = WRITE_FLUSH | REQ_META | REQ_PRIO;
 		else
-			io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
+			io->fio.op_flags = WRITE_FLUSH_FUA | REQ_META |
+								REQ_PRIO;
 	}
 	__submit_merged_bio(io);
 out:
@@ -228,14 +231,16 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	f2fs_trace_ios(fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->rw));
+	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op));
 
 	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		bio_put(bio);
 		return -EFAULT;
 	}
+	bio->bi_rw = fio->op_flags;
+	bio_set_op_attrs(bio, fio->op, fio->op_flags);
 
-	__submit_bio(fio->sbi, fio->rw, bio);
+	__submit_bio(fio->sbi, bio);
 	return 0;
 }
 
@@ -244,7 +249,7 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 	struct f2fs_sb_info *sbi = fio->sbi;
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
 	struct f2fs_bio_info *io;
-	bool is_read = is_read_io(fio->rw);
+	bool is_read = is_read_io(fio->op);
 	struct page *bio_page;
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
@@ -256,7 +261,7 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 	down_write(&io->io_rwsem);
 
 	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
-						io->fio.rw != fio->rw))
+	    (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags)))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
@@ -390,7 +395,7 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
 }
 
 struct page *get_read_data_page(struct inode *inode, pgoff_t index,
-						int rw, bool for_write)
+						int op_flags, bool for_write)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;
@@ -400,7 +405,8 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
-		.rw = rw,
+		.op = REQ_OP_READ,
+		.op_flags = op_flags,
 		.encrypted_page = NULL,
 	};
 
@@ -1052,7 +1058,7 @@ got_it:
 		 */
 		if (bio && (last_block_in_bio != block_nr - 1)) {
 submit_and_realloc:
-			__submit_bio(F2FS_I_SB(inode), READ, bio);
+			__submit_bio(F2FS_I_SB(inode), bio);
 			bio = NULL;
 		}
 		if (bio == NULL) {
@@ -1081,6 +1087,7 @@ submit_and_realloc:
 			bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
 			bio->bi_end_io = f2fs_read_end_io;
 			bio->bi_private = ctx;
+			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		}
 
 		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
@@ -1095,7 +1102,7 @@ set_error_page:
 		goto next_page;
 confused:
 		if (bio) {
-			__submit_bio(F2FS_I_SB(inode), READ, bio);
+			__submit_bio(F2FS_I_SB(inode), bio);
 			bio = NULL;
 		}
 		unlock_page(page);
@@ -1105,7 +1112,7 @@ next_page:
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
-		__submit_bio(F2FS_I_SB(inode), READ, bio);
+		__submit_bio(F2FS_I_SB(inode), bio);
 	return 0;
 }
 
@@ -1222,7 +1229,8 @@ static int f2fs_write_data_page(struct page *page,
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = DATA,
-		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+		.op = REQ_OP_WRITE,
+		.op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0,
 		.page = page,
 		.encrypted_page = NULL,
 	};
@@ -1663,7 +1671,8 @@ repeat:
 		struct f2fs_io_info fio = {
 			.sbi = sbi,
 			.type = DATA,
-			.rw = READ_SYNC,
+			.op = REQ_OP_READ,
+			.op_flags = READ_SYNC,
 			.old_blkaddr = blkaddr,
 			.new_blkaddr = blkaddr,
 			.page = page,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 916e7c238e3d..23ae6a81ccd6 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -686,14 +686,15 @@ enum page_type {
 struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
-	int rw;			/* contains R/RS/W/WS with REQ_META/REQ_PRIO */
+	int op;			/* contains REQ_OP_ */
+	int op_flags;		/* rq_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
 };
 
-#define is_read_io(rw)	(((rw) & 1) == READ)
+#define is_read_io(rw) (rw == READ)
 struct f2fs_bio_info {
 	struct f2fs_sb_info *sbi;	/* f2fs superblock */
 	struct bio *bio;		/* bios to merge */
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 38d56f678912..f06ed73adf99 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -538,7 +538,8 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
-		.rw = READ_SYNC,
+		.op = REQ_OP_READ,
+		.op_flags = READ_SYNC,
 		.encrypted_page = NULL,
 	};
 	struct dnode_of_data dn;
@@ -612,7 +613,8 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	/* allocate block address */
 	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
 
-	fio.rw = WRITE_SYNC;
+	fio.op = REQ_OP_WRITE;
+	fio.op_flags = WRITE_SYNC;
 	fio.new_blkaddr = newaddr;
 	f2fs_submit_page_mbio(&fio);
 
@@ -649,7 +651,8 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 		struct f2fs_io_info fio = {
 			.sbi = F2FS_I_SB(inode),
 			.type = DATA,
-			.rw = WRITE_SYNC,
+			.op = REQ_OP_WRITE,
+			.op_flags = WRITE_SYNC,
 			.page = page,
 			.encrypted_page = NULL,
 		};
@@ -730,7 +733,8 @@ next_step:
 
 			start_bidx = start_bidx_of_node(nofs, inode);
 			data_page = get_read_data_page(inode,
-					start_bidx + ofs_in_node, READA, true);
+					start_bidx + ofs_in_node, REQ_RAHEAD,
+					true);
 			if (IS_ERR(data_page)) {
 				iput(inode);
 				continue;
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index a4bb155dd00a..c15e53c1d794 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -108,7 +108,8 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(dn->inode),
 		.type = DATA,
-		.rw = WRITE_SYNC | REQ_PRIO,
+		.op = REQ_OP_WRITE,
+		.op_flags = WRITE_SYNC | REQ_PRIO,
 		.page = page,
 		.encrypted_page = NULL,
 	};
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 1f21aae80c40..d1867698e601 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1070,14 +1070,15 @@ fail:
  * 0: f2fs_put_page(page, 0)
  * LOCKED_PAGE or error: f2fs_put_page(page, 1)
  */
-static int read_node_page(struct page *page, int rw)
+static int read_node_page(struct page *page, int op_flags)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	struct node_info ni;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = NODE,
-		.rw = rw,
+		.op = REQ_OP_READ,
+		.op_flags = op_flags,
 		.page = page,
 		.encrypted_page = NULL,
 	};
@@ -1118,7 +1119,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 	if (!apage)
 		return;
 
-	err = read_node_page(apage, READA);
+	err = read_node_page(apage, REQ_RAHEAD);
 	f2fs_put_page(apage, err ? 1 : 0);
 }
 
@@ -1568,7 +1569,8 @@ static int f2fs_write_node_page(struct page *page,
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = NODE,
-		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+		.op = REQ_OP_WRITE,
+		.op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0,
 		.page = page,
 		.encrypted_page = NULL,
 	};
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 2e6f537a0e7d..4c2d1fa1e0e2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -257,7 +257,8 @@ static int __commit_inmem_pages(struct inode *inode,
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = DATA,
-		.rw = WRITE_SYNC | REQ_PRIO,
+		.op = REQ_OP_WRITE,
+		.op_flags = WRITE_SYNC | REQ_PRIO,
 		.encrypted_page = NULL,
 	};
 	bool submit_bio = false;
@@ -406,7 +407,8 @@ repeat:
 		fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
 
 		bio->bi_bdev = sbi->sb->s_bdev;
-		ret = submit_bio_wait(WRITE_FLUSH, bio);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+		ret = submit_bio_wait(bio);
 
 		llist_for_each_entry_safe(cmd, next,
 					  fcc->dispatch_list, llnode) {
@@ -438,7 +440,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 		int ret;
 
 		bio->bi_bdev = sbi->sb->s_bdev;
-		ret = submit_bio_wait(WRITE_FLUSH, bio);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+		ret = submit_bio_wait(bio);
 		bio_put(bio);
 		return ret;
 	}
@@ -1401,7 +1404,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = META,
-		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
+		.op = REQ_OP_WRITE,
+		.op_flags = WRITE_SYNC | REQ_META | REQ_PRIO,
 		.old_blkaddr = page->index,
 		.new_blkaddr = page->index,
 		.page = page,
@@ -1409,7 +1413,7 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 	};
 
 	if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
-		fio.rw &= ~REQ_META;
+		fio.op_flags &= ~REQ_META;
 
 	set_page_writeback(page);
 	f2fs_submit_page_mbio(&fio);
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index 562ce0821559..73b4e1d1912a 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -25,11 +25,11 @@ static inline void __print_last_io(void)
 	if (!last_io.len)
 		return;
 
-	trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n",
+	trace_printk("%3x:%3x %4x %-16s %2x %5x %5x %12x %4x\n",
 			last_io.major, last_io.minor,
 			last_io.pid, "----------------",
 			last_io.type,
-			last_io.fio.rw,
+			last_io.fio.op, last_io.fio.op_flags,
 			last_io.fio.new_blkaddr,
 			last_io.len);
 	memset(&last_io, 0, sizeof(last_io));
@@ -101,7 +101,8 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
 	if (last_io.major == major && last_io.minor == minor &&
 			last_io.pid == pid &&
 			last_io.type == __file_type(inode, pid) &&
-			last_io.fio.rw == fio->rw &&
+			last_io.fio.op == fio->op &&
+			last_io.fio.op_flags == fio->op_flags &&
 			last_io.fio.new_blkaddr + last_io.len ==
 							fio->new_blkaddr) {
 		last_io.len++;
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index c4589e981760..8a8698119ff7 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -267,7 +267,7 @@ int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs)
 	int i, err = 0;
 
 	for (i = 0; i < nr_bhs; i++)
-		write_dirty_buffer(bhs[i], WRITE);
+		write_dirty_buffer(bhs[i], 0);
 
 	for (i = 0; i < nr_bhs; i++) {
 		wait_on_buffer(bhs[i]);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 24ce1cdd434a..6e2bec1cd289 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -285,7 +285,8 @@ static void gfs2_metapath_ra(struct gfs2_glock *gl,
 		if (trylock_buffer(rabh)) {
 			if (!buffer_uptodate(rabh)) {
 				rabh->b_end_io = end_buffer_read_sync;
-				submit_bh(READA | REQ_META, rabh);
+				submit_bh(REQ_OP_READ, REQ_RAHEAD | REQ_META,
+						rabh);
 				continue;
 			}
 			unlock_buffer(rabh);
@@ -974,7 +975,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 
 	if (!buffer_uptodate(bh)) {
 		err = -EIO;
-		ll_rw_block(READ, 1, &bh);
+		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 		wait_on_buffer(bh);
 		/* Uhhuh. Read error. Complain and punt. */
 		if (!buffer_uptodate(bh))
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index e30cc9fb2bef..fcb59b23f1e3 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1513,7 +1513,7 @@ static void gfs2_dir_readahead(struct inode *inode, unsigned hsize, u32 index,
 				continue;
 			}
 			bh->b_end_io = end_buffer_read_sync;
-			submit_bh(READA | REQ_META, bh);
+			submit_bh(REQ_OP_READ, REQ_RAHEAD | REQ_META, bh);
 			continue;
 		}
 		brelse(bh);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 0ff028c15199..e58ccef09c91 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -657,7 +657,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 	struct gfs2_log_header *lh;
 	unsigned int tail;
 	u32 hash;
-	int rw = WRITE_FLUSH_FUA | REQ_META;
+	int op_flags = WRITE_FLUSH_FUA | REQ_META;
 	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
 	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
 	lh = page_address(page);
@@ -682,12 +682,12 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
 		gfs2_ordered_wait(sdp);
 		log_flush_wait(sdp);
-		rw = WRITE_SYNC | REQ_META | REQ_PRIO;
+		op_flags = WRITE_SYNC | REQ_META | REQ_PRIO;
 	}
 
 	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
 	gfs2_log_write_page(sdp, page);
-	gfs2_log_flush_bio(sdp, rw);
+	gfs2_log_flush_bio(sdp, REQ_OP_WRITE, op_flags);
 	log_flush_wait(sdp);
 
 	if (sdp->sd_log_tail != tail)
@@ -738,7 +738,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 
 	gfs2_ordered_write(sdp);
 	lops_before_commit(sdp, tr);
-	gfs2_log_flush_bio(sdp, WRITE);
+	gfs2_log_flush_bio(sdp, REQ_OP_WRITE, 0);
 
 	if (sdp->sd_log_head != sdp->sd_log_flush_head) {
 		log_flush_wait(sdp);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 8e3ba20d5e9d..49d5a1b61b06 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -230,17 +230,19 @@ static void gfs2_end_log_write(struct bio *bio)
 /**
  * gfs2_log_flush_bio - Submit any pending log bio
  * @sdp: The superblock
- * @rw: The rw flags
+ * @op: REQ_OP
+ * @op_flags: rq_flag_bits
  *
  * Submit any pending part-built or full bio to the block device. If
  * there is no pending bio, then this is a no-op.
  */
 
-void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw)
+void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int op, int op_flags)
 {
 	if (sdp->sd_log_bio) {
 		atomic_inc(&sdp->sd_log_in_flight);
-		submit_bio(rw, sdp->sd_log_bio);
+		bio_set_op_attrs(sdp->sd_log_bio, op, op_flags);
+		submit_bio(sdp->sd_log_bio);
 		sdp->sd_log_bio = NULL;
 	}
 }
@@ -299,7 +301,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno)
 		nblk >>= sdp->sd_fsb2bb_shift;
 		if (blkno == nblk)
 			return bio;
-		gfs2_log_flush_bio(sdp, WRITE);
+		gfs2_log_flush_bio(sdp, REQ_OP_WRITE, 0);
 	}
 
 	return gfs2_log_alloc_bio(sdp, blkno);
@@ -328,7 +330,7 @@ static void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page,
 	bio = gfs2_log_get_bio(sdp, blkno);
 	ret = bio_add_page(bio, page, size, offset);
 	if (ret == 0) {
-		gfs2_log_flush_bio(sdp, WRITE);
+		gfs2_log_flush_bio(sdp, REQ_OP_WRITE, 0);
 		bio = gfs2_log_alloc_bio(sdp, blkno);
 		ret = bio_add_page(bio, page, size, offset);
 		WARN_ON(ret == 0);
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index a65a7ba32ffd..e529f536c117 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -27,7 +27,7 @@ extern const struct gfs2_log_operations gfs2_databuf_lops;
 
 extern const struct gfs2_log_operations *gfs2_log_ops[];
 extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page);
-extern void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw);
+extern void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int op, int op_flags);
 extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
 
 static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 8eaadabbc771..950b8be68e41 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -37,8 +37,8 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
 {
 	struct buffer_head *bh, *head;
 	int nr_underway = 0;
-	int write_op = REQ_META | REQ_PRIO |
-		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+	int write_flags = REQ_META | REQ_PRIO |
+		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : 0);
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!page_has_buffers(page));
@@ -79,7 +79,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(write_op, bh);
+			submit_bh(REQ_OP_WRITE, write_flags, bh);
 			nr_underway++;
 		}
 		bh = next;
@@ -213,7 +213,8 @@ static void gfs2_meta_read_endio(struct bio *bio)
  * Submit several consecutive buffer head I/O requests as a single bio I/O
  * request.  (See submit_bh_wbc.)
  */
-static void gfs2_submit_bhs(int rw, struct buffer_head *bhs[], int num)
+static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[],
+			    int num)
 {
 	struct buffer_head *bh = bhs[0];
 	struct bio *bio;
@@ -230,7 +231,8 @@ static void gfs2_submit_bhs(int rw, struct buffer_head *bhs[], int num)
 		bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
 	}
 	bio->bi_end_io = gfs2_meta_read_endio;
-	submit_bio(rw, bio);
+	bio_set_op_attrs(bio, op, op_flags);
+	submit_bio(bio);
 }
 
 /**
@@ -280,7 +282,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 		}
 	}
 
-	gfs2_submit_bhs(READ_SYNC | REQ_META | REQ_PRIO, bhs, num);
+	gfs2_submit_bhs(REQ_OP_READ, READ_SYNC | REQ_META | REQ_PRIO, bhs, num);
 	if (!(flags & DIO_WAIT))
 		return 0;
 
@@ -448,7 +450,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 	if (buffer_uptodate(first_bh))
 		goto out;
 	if (!buffer_locked(first_bh))
-		ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh);
+		ll_rw_block(REQ_OP_READ, READ_SYNC | REQ_META, 1, &first_bh);
 
 	dblock++;
 	extlen--;
@@ -457,7 +459,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 		bh = gfs2_getbuf(gl, dblock, CREATE);
 
 		if (!buffer_uptodate(bh) && !buffer_locked(bh))
-			ll_rw_block(READA | REQ_META, 1, &bh);
+			ll_rw_block(REQ_OP_READ, REQ_RAHEAD | REQ_META, 1, &bh);
 		brelse(bh);
 		dblock++;
 		extlen--;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b8f6fc9513ef..ef1e1822977f 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -246,7 +246,8 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
 
 	bio->bi_end_io = end_bio_io_page;
 	bio->bi_private = page;
-	submit_bio(READ_SYNC | REQ_META, bio);
+	bio_set_op_attrs(bio, REQ_OP_READ, READ_SYNC | REQ_META);
+	submit_bio(bio);
 	wait_on_page_locked(page);
 	bio_put(bio);
 	if (!PageUptodate(page)) {
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 6c657b202501..77930ca25303 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -730,7 +730,7 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
 		if (PageUptodate(page))
 			set_buffer_uptodate(bh);
 		if (!buffer_uptodate(bh)) {
-			ll_rw_block(READ | REQ_META, 1, &bh);
+			ll_rw_block(REQ_OP_READ, REQ_META, 1, &bh);
 			wait_on_buffer(bh);
 			if (!buffer_uptodate(bh))
 				goto unlock_out;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index fdc3446d934a..047245bd2cd6 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -526,7 +526,7 @@ int hfsplus_compare_dentry(const struct dentry *parent,
 
 /* wrapper.c */
 int hfsplus_submit_bio(struct super_block *sb, sector_t sector, void *buf,
-		       void **data, int rw);
+		       void **data, int op, int op_flags);
 int hfsplus_read_wrapper(struct super_block *sb);
 
 /* time macros */
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index eb355d81e279..63164ebc52fa 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -112,7 +112,8 @@ static int hfs_parse_new_pmap(struct super_block *sb, void *buf,
 		if ((u8 *)pm - (u8 *)buf >= buf_size) {
 			res = hfsplus_submit_bio(sb,
 						 *part_start + HFS_PMAP_BLK + i,
-						 buf, (void **)&pm, READ);
+						 buf, (void **)&pm, REQ_OP_READ,
+						 0);
 			if (res)
 				return res;
 		}
@@ -136,7 +137,7 @@ int hfs_part_find(struct super_block *sb,
 		return -ENOMEM;
 
 	res = hfsplus_submit_bio(sb, *part_start + HFS_PMAP_BLK,
-				 buf, &data, READ);
+				 buf, &data, REQ_OP_READ, 0);
 	if (res)
 		goto out;
 
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 755bf30ba1ce..11854dd84572 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -220,7 +220,8 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait)
 
 	error2 = hfsplus_submit_bio(sb,
 				   sbi->part_start + HFSPLUS_VOLHEAD_SECTOR,
-				   sbi->s_vhdr_buf, NULL, WRITE_SYNC);
+				   sbi->s_vhdr_buf, NULL, REQ_OP_WRITE,
+				   WRITE_SYNC);
 	if (!error)
 		error = error2;
 	if (!write_backup)
@@ -228,7 +229,8 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait)
 
 	error2 = hfsplus_submit_bio(sb,
 				  sbi->part_start + sbi->sect_count - 2,
-				  sbi->s_backup_vhdr_buf, NULL, WRITE_SYNC);
+				  sbi->s_backup_vhdr_buf, NULL, REQ_OP_WRITE,
+				  WRITE_SYNC);
 	if (!error)
 		error2 = error;
 out:
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index cc6235671437..ebb85e5f6549 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -30,7 +30,8 @@ struct hfsplus_wd {
  * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes
  * @buf: buffer for I/O
  * @data: output pointer for location of requested data
- * @rw: direction of I/O
+ * @op: direction of I/O
+ * @op_flags: request op flags
  *
  * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than
  * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads
@@ -44,7 +45,7 @@ struct hfsplus_wd {
  * will work correctly.
  */
 int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
-		void *buf, void **data, int rw)
+		       void *buf, void **data, int op, int op_flags)
 {
 	struct bio *bio;
 	int ret = 0;
@@ -65,8 +66,9 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
 	bio = bio_alloc(GFP_NOIO, 1);
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_bdev = sb->s_bdev;
+	bio_set_op_attrs(bio, op, op_flags);
 
-	if (!(rw & WRITE) && data)
+	if (op != WRITE && data)
 		*data = (u8 *)buf + offset;
 
 	while (io_size > 0) {
@@ -83,7 +85,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
 		buf = (u8 *)buf + len;
 	}
 
-	ret = submit_bio_wait(rw, bio);
+	ret = submit_bio_wait(bio);
 out:
 	bio_put(bio);
 	return ret < 0 ? ret : 0;
@@ -181,7 +183,7 @@ int hfsplus_read_wrapper(struct super_block *sb)
 reread:
 	error = hfsplus_submit_bio(sb, part_start + HFSPLUS_VOLHEAD_SECTOR,
 				   sbi->s_vhdr_buf, (void **)&sbi->s_vhdr,
-				   READ);
+				   REQ_OP_READ, 0);
 	if (error)
 		goto out_free_backup_vhdr;
 
@@ -213,7 +215,8 @@ reread:
 
 	error = hfsplus_submit_bio(sb, part_start + part_size - 2,
 				   sbi->s_backup_vhdr_buf,
-				   (void **)&sbi->s_backup_vhdr, READ);
+				   (void **)&sbi->s_backup_vhdr, REQ_OP_READ,
+				   0);
 	if (error)
 		goto out_free_backup_vhdr;
 
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index 2e4e834d1a98..2ce5b75ee9a5 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -81,7 +81,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 	blocknum = block_start >> bufshift;
 	memset(bhs, 0, (needblocks + 1) * sizeof(struct buffer_head *));
 	haveblocks = isofs_get_blocks(inode, blocknum, bhs, needblocks);
-	ll_rw_block(READ, haveblocks, bhs);
+	ll_rw_block(REQ_OP_READ, 0, haveblocks, bhs);
 
 	curbh = 0;
 	curpage = 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 70078096117d..5bb565f9989c 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -124,7 +124,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	int ret;
-	struct timespec now = current_kernel_time();
+	struct timespec64 now = current_kernel_time64();
 
 	*cbh = NULL;
 
@@ -155,9 +155,9 @@ static int journal_submit_commit_record(journal_t *journal,
 
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !jbd2_has_feature_async_commit(journal))
-		ret = submit_bh(WRITE_SYNC | WRITE_FLUSH_FUA, bh);
+		ret = submit_bh(REQ_OP_WRITE, WRITE_SYNC | WRITE_FLUSH_FUA, bh);
 	else
-		ret = submit_bh(WRITE_SYNC, bh);
+		ret = submit_bh(REQ_OP_WRITE, WRITE_SYNC, bh);
 
 	*cbh = bh;
 	return ret;
@@ -718,7 +718,7 @@ start_journal_io:
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
 				bh->b_end_io = journal_end_buffer_io_sync;
-				submit_bh(WRITE_SYNC, bh);
+				submit_bh(REQ_OP_WRITE, WRITE_SYNC, bh);
 			}
 			cond_resched();
 			stats.run.rs_blocks_logged += bufs;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index e3ca4b4cac84..46261a6f902d 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -691,6 +691,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 {
 	int err = 0;
 
+	jbd2_might_wait_for_commit(journal);
 	read_lock(&journal->j_state_lock);
 #ifdef CONFIG_JBD2_DEBUG
 	if (!tid_geq(journal->j_commit_request, tid)) {
@@ -1091,6 +1092,7 @@ static void jbd2_stats_proc_exit(journal_t *journal)
 
 static journal_t * journal_init_common (void)
 {
+	static struct lock_class_key jbd2_trans_commit_key;
 	journal_t *journal;
 	int err;
 
@@ -1126,6 +1128,9 @@ static journal_t * journal_init_common (void)
 
 	spin_lock_init(&journal->j_history_lock);
 
+	lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle",
+			 &jbd2_trans_commit_key, 0);
+
 	return journal;
 }
 
@@ -1346,15 +1351,15 @@ static int journal_reset(journal_t *journal)
 	return jbd2_journal_start_thread(journal);
 }
 
-static int jbd2_write_superblock(journal_t *journal, int write_op)
+static int jbd2_write_superblock(journal_t *journal, int write_flags)
 {
 	struct buffer_head *bh = journal->j_sb_buffer;
 	journal_superblock_t *sb = journal->j_superblock;
 	int ret;
 
-	trace_jbd2_write_superblock(journal, write_op);
+	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
-		write_op &= ~(REQ_FUA | REQ_FLUSH);
+		write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
 	lock_buffer(bh);
 	if (buffer_write_io_error(bh)) {
 		/*
@@ -1374,7 +1379,7 @@ static int jbd2_write_superblock(journal_t *journal, int write_op)
 	jbd2_superblock_csum_set(journal, sb);
 	get_bh(bh);
 	bh->b_end_io = end_buffer_write_sync;
-	ret = submit_bh(write_op, bh);
+	ret = submit_bh(REQ_OP_WRITE, write_flags, bh);
 	wait_on_buffer(bh);
 	if (buffer_write_io_error(bh)) {
 		clear_buffer_write_io_error(bh);
@@ -1498,7 +1503,7 @@ static int journal_get_superblock(journal_t *journal)
 
 	J_ASSERT(bh != NULL);
 	if (!buffer_uptodate(bh)) {
-		ll_rw_block(READ, 1, &bh);
+		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			printk(KERN_ERR
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 805bc6bcd8ab..02dd3360cb20 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -104,7 +104,7 @@ static int do_readahead(journal_t *journal, unsigned int start)
 		if (!buffer_uptodate(bh) && !buffer_locked(bh)) {
 			bufs[nbufs++] = bh;
 			if (nbufs == MAXBUF) {
-				ll_rw_block(READ, nbufs, bufs);
+				ll_rw_block(REQ_OP_READ, 0, nbufs, bufs);
 				journal_brelse_array(bufs, nbufs);
 				nbufs = 0;
 			}
@@ -113,7 +113,7 @@ static int do_readahead(journal_t *journal, unsigned int start)
 	}
 
 	if (nbufs)
-		ll_rw_block(READ, nbufs, bufs);
+		ll_rw_block(REQ_OP_READ, 0, nbufs, bufs);
 	err = 0;
 
 failed:
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 1749519b362f..b5bc3e249163 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -182,6 +182,8 @@ static int add_transaction_credits(journal_t *journal, int blocks,
 	int needed;
 	int total = blocks + rsv_blocks;
 
+	jbd2_might_wait_for_commit(journal);
+
 	/*
 	 * If the current transaction is locked down for commit, wait
 	 * for the lock to be released.
@@ -382,13 +384,11 @@ repeat:
 	read_unlock(&journal->j_state_lock);
 	current->journal_info = handle;
 
-	lock_map_acquire(&handle->h_lockdep_map);
+	rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_);
 	jbd2_journal_free_transaction(new_transaction);
 	return 0;
 }
 
-static struct lock_class_key jbd2_handle_key;
-
 /* Allocate a new handle.  This should probably be in a slab... */
 static handle_t *new_handle(int nblocks)
 {
@@ -398,9 +398,6 @@ static handle_t *new_handle(int nblocks)
 	handle->h_buffer_credits = nblocks;
 	handle->h_ref = 1;
 
-	lockdep_init_map(&handle->h_lockdep_map, "jbd2_handle",
-						&jbd2_handle_key, 0);
-
 	return handle;
 }
 
@@ -672,7 +669,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
 	if (need_to_start)
 		jbd2_log_start_commit(journal, tid);
 
-	lock_map_release(&handle->h_lockdep_map);
+	rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
 	handle->h_buffer_credits = nblocks;
 	ret = start_this_handle(journal, handle, gfp_mask);
 	return ret;
@@ -700,6 +697,8 @@ void jbd2_journal_lock_updates(journal_t *journal)
 {
 	DEFINE_WAIT(wait);
 
+	jbd2_might_wait_for_commit(journal);
+
 	write_lock(&journal->j_state_lock);
 	++journal->j_barrier_count;
 
@@ -1750,11 +1749,11 @@ int jbd2_journal_stop(handle_t *handle)
 			wake_up(&journal->j_wait_transaction_locked);
 	}
 
+	rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
+
 	if (wait_for_commit)
 		err = jbd2_log_wait_commit(journal, tid);
 
-	lock_map_release(&handle->h_lockdep_map);
-
 	if (handle->h_rsv_handle)
 		jbd2_journal_free_reserved(handle->h_rsv_handle);
 free_and_exit:
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 63759d723920..a74752146ec9 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -2002,12 +2002,13 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
 
 	bio->bi_end_io = lbmIODone;
 	bio->bi_private = bp;
+	bio_set_op_attrs(bio, REQ_OP_READ, READ_SYNC);
 	/*check if journaling to disk has been disabled*/
 	if (log->no_integrity) {
 		bio->bi_iter.bi_size = 0;
 		lbmIODone(bio);
 	} else {
-		submit_bio(READ_SYNC, bio);
+		submit_bio(bio);
 	}
 
 	wait_event(bp->l_ioevent, (bp->l_flag != lbmREAD));
@@ -2145,13 +2146,14 @@ static void lbmStartIO(struct lbuf * bp)
 
 	bio->bi_end_io = lbmIODone;
 	bio->bi_private = bp;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_SYNC);
 
 	/* check if journaling to disk has been disabled */
 	if (log->no_integrity) {
 		bio->bi_iter.bi_size = 0;
 		lbmIODone(bio);
 	} else {
-		submit_bio(WRITE_SYNC, bio);
+		submit_bio(bio);
 		INCREMENT(lmStat.submitted);
 	}
 }
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index b60e015cc757..e7fa9e513040 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -411,7 +411,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
 			inc_io(page);
 			if (!bio->bi_iter.bi_size)
 				goto dump_bio;
-			submit_bio(WRITE, bio);
+			submit_bio(bio);
 			nr_underway++;
 			bio = NULL;
 		} else
@@ -434,6 +434,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
 		bio->bi_iter.bi_sector = pblock << (inode->i_blkbits - 9);
 		bio->bi_end_io = metapage_write_end_io;
 		bio->bi_private = page;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 		/* Don't call bio_add_page yet, we may add to this vec */
 		bio_offset = offset;
@@ -448,7 +449,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
 		if (!bio->bi_iter.bi_size)
 			goto dump_bio;
 
-		submit_bio(WRITE, bio);
+		submit_bio(bio);
 		nr_underway++;
 	}
 	if (redirty)
@@ -506,7 +507,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 				insert_metapage(page, NULL);
 			inc_io(page);
 			if (bio)
-				submit_bio(READ, bio);
+				submit_bio(bio);
 
 			bio = bio_alloc(GFP_NOFS, 1);
 			bio->bi_bdev = inode->i_sb->s_bdev;
@@ -514,6 +515,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 				pblock << (inode->i_blkbits - 9);
 			bio->bi_end_io = metapage_read_end_io;
 			bio->bi_private = page;
+			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 			len = xlen << inode->i_blkbits;
 			offset = block_offset << inode->i_blkbits;
 			if (bio_add_page(bio, page, len, offset) < len)
@@ -523,7 +525,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 			block_offset++;
 	}
 	if (bio)
-		submit_bio(READ, bio);
+		submit_bio(bio);
 	else
 		unlock_page(page);
 
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index cc26f8f215f5..a8329cc47dec 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -14,7 +14,7 @@
 
 #define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))
 
-static int sync_request(struct page *page, struct block_device *bdev, int rw)
+static int sync_request(struct page *page, struct block_device *bdev, int op)
 {
 	struct bio bio;
 	struct bio_vec bio_vec;
@@ -29,8 +29,9 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw)
 	bio.bi_bdev = bdev;
 	bio.bi_iter.bi_sector = page->index * (PAGE_SIZE >> 9);
 	bio.bi_iter.bi_size = PAGE_SIZE;
+	bio_set_op_attrs(&bio, op, 0);
 
-	return submit_bio_wait(rw, &bio);
+	return submit_bio_wait(&bio);
 }
 
 static int bdev_readpage(void *_sb, struct page *page)
@@ -95,8 +96,9 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
 			bio->bi_iter.bi_sector = ofs >> 9;
 			bio->bi_private = sb;
 			bio->bi_end_io = writeseg_end_io;
+			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			atomic_inc(&super->s_pending_writes);
-			submit_bio(WRITE, bio);
+			submit_bio(bio);
 
 			ofs += i * PAGE_SIZE;
 			index += i;
@@ -122,8 +124,9 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
 	bio->bi_iter.bi_sector = ofs >> 9;
 	bio->bi_private = sb;
 	bio->bi_end_io = writeseg_end_io;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	atomic_inc(&super->s_pending_writes);
-	submit_bio(WRITE, bio);
+	submit_bio(bio);
 	return 0;
 }
 
@@ -185,8 +188,9 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
 			bio->bi_iter.bi_sector = ofs >> 9;
 			bio->bi_private = sb;
 			bio->bi_end_io = erase_end_io;
+			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			atomic_inc(&super->s_pending_writes);
-			submit_bio(WRITE, bio);
+			submit_bio(bio);
 
 			ofs += i * PAGE_SIZE;
 			index += i;
@@ -206,8 +210,9 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
 	bio->bi_iter.bi_sector = ofs >> 9;
 	bio->bi_private = sb;
 	bio->bi_end_io = erase_end_io;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	atomic_inc(&super->s_pending_writes);
-	submit_bio(WRITE, bio);
+	submit_bio(bio);
 	return 0;
 }
 
diff --git a/fs/mpage.c b/fs/mpage.c
index c8a05901a37b..2ca1f39c8cba 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -56,11 +56,12 @@ static void mpage_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
-static struct bio *mpage_bio_submit(int rw, struct bio *bio)
+static struct bio *mpage_bio_submit(int op, int op_flags, struct bio *bio)
 {
 	bio->bi_end_io = mpage_end_io;
-	guard_bio_eod(rw, bio);
-	submit_bio(rw, bio);
+	bio_set_op_attrs(bio, op, op_flags);
+	guard_bio_eod(op, bio);
+	submit_bio(bio);
 	return NULL;
 }
 
@@ -271,7 +272,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && (*last_block_in_bio != blocks[0] - 1))
-		bio = mpage_bio_submit(READ, bio);
+		bio = mpage_bio_submit(REQ_OP_READ, 0, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -288,7 +289,7 @@ alloc_new:
 
 	length = first_hole << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(READ, bio);
+		bio = mpage_bio_submit(REQ_OP_READ, 0, bio);
 		goto alloc_new;
 	}
 
@@ -296,7 +297,7 @@ alloc_new:
 	nblocks = map_bh->b_size >> blkbits;
 	if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
 	    (first_hole != blocks_per_page))
-		bio = mpage_bio_submit(READ, bio);
+		bio = mpage_bio_submit(REQ_OP_READ, 0, bio);
 	else
 		*last_block_in_bio = blocks[blocks_per_page - 1];
 out:
@@ -304,7 +305,7 @@ out:
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(READ, bio);
+		bio = mpage_bio_submit(REQ_OP_READ, 0, bio);
 	if (!PageUptodate(page))
 	        block_read_full_page(page, get_block);
 	else
@@ -386,7 +387,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	}
 	BUG_ON(!list_empty(pages));
 	if (bio)
-		mpage_bio_submit(READ, bio);
+		mpage_bio_submit(REQ_OP_READ, 0, bio);
 	return 0;
 }
 EXPORT_SYMBOL(mpage_readpages);
@@ -407,7 +408,7 @@ int mpage_readpage(struct page *page, get_block_t get_block)
 	bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
 			&map_bh, &first_logical_block, get_block, gfp);
 	if (bio)
-		mpage_bio_submit(READ, bio);
+		mpage_bio_submit(REQ_OP_READ, 0, bio);
 	return 0;
 }
 EXPORT_SYMBOL(mpage_readpage);
@@ -488,7 +489,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct buffer_head map_bh;
 	loff_t i_size = i_size_read(inode);
 	int ret = 0;
-	int wr = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
+	int op_flags = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : 0);
 
 	if (page_has_buffers(page)) {
 		struct buffer_head *head = page_buffers(page);
@@ -597,7 +598,7 @@ page_is_mapped:
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
-		bio = mpage_bio_submit(wr, bio);
+		bio = mpage_bio_submit(REQ_OP_WRITE, op_flags, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -624,7 +625,7 @@ alloc_new:
 	wbc_account_io(wbc, page, PAGE_SIZE);
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(wr, bio);
+		bio = mpage_bio_submit(REQ_OP_WRITE, op_flags, bio);
 		goto alloc_new;
 	}
 
@@ -634,7 +635,7 @@ alloc_new:
 	set_page_writeback(page);
 	unlock_page(page);
 	if (boundary || (first_unmapped != blocks_per_page)) {
-		bio = mpage_bio_submit(wr, bio);
+		bio = mpage_bio_submit(REQ_OP_WRITE, op_flags, bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
@@ -646,7 +647,7 @@ alloc_new:
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(wr, bio);
+		bio = mpage_bio_submit(REQ_OP_WRITE, op_flags, bio);
 
 	if (mpd->use_writepage) {
 		ret = mapping->a_ops->writepage(page, wbc);
@@ -703,9 +704,9 @@ mpage_writepages(struct address_space *mapping,
 
 		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
 		if (mpd.bio) {
-			int wr = (wbc->sync_mode == WB_SYNC_ALL ?
-				  WRITE_SYNC : WRITE);
-			mpage_bio_submit(wr, mpd.bio);
+			int op_flags = (wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : 0);
+			mpage_bio_submit(REQ_OP_WRITE, op_flags, mpd.bio);
 		}
 	}
 	blk_finish_plug(&plug);
@@ -724,9 +725,9 @@ int mpage_writepage(struct page *page, get_block_t get_block,
 	};
 	int ret = __mpage_writepage(page, wbc, &mpd);
 	if (mpd.bio) {
-		int wr = (wbc->sync_mode == WB_SYNC_ALL ?
-			  WRITE_SYNC : WRITE);
-		mpage_bio_submit(wr, mpd.bio);
+		int op_flags = (wbc->sync_mode == WB_SYNC_ALL ?
+			  WRITE_SYNC : 0);
+		mpage_bio_submit(REQ_OP_WRITE, op_flags, mpd.bio);
 	}
 	return ret;
 }
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 17a42e4eb872..f55a4e756047 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -102,14 +102,15 @@ static inline void put_parallel(struct parallel_io *p)
 }
 
 static struct bio *
-bl_submit_bio(int rw, struct bio *bio)
+bl_submit_bio(struct bio *bio)
 {
 	if (bio) {
 		get_parallel(bio->bi_private);
 		dprintk("%s submitting %s bio %u@%llu\n", __func__,
-			rw == READ ? "read" : "write", bio->bi_iter.bi_size,
+			bio_op(bio) == READ ? "read" : "write",
+			bio->bi_iter.bi_size,
 			(unsigned long long)bio->bi_iter.bi_sector);
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	}
 	return NULL;
 }
@@ -158,7 +159,7 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
 	if (disk_addr < map->start || disk_addr >= map->start + map->len) {
 		if (!dev->map(dev, disk_addr, map))
 			return ERR_PTR(-EIO);
-		bio = bl_submit_bio(rw, bio);
+		bio = bl_submit_bio(bio);
 	}
 	disk_addr += map->disk_offset;
 	disk_addr -= map->start;
@@ -174,9 +175,10 @@ retry:
 				disk_addr >> SECTOR_SHIFT, end_io, par);
 		if (!bio)
 			return ERR_PTR(-ENOMEM);
+		bio_set_op_attrs(bio, rw, 0);
 	}
 	if (bio_add_page(bio, page, *len, offset) < *len) {
-		bio = bl_submit_bio(rw, bio);
+		bio = bl_submit_bio(bio);
 		goto retry;
 	}
 	return bio;
@@ -252,7 +254,7 @@ bl_read_pagelist(struct nfs_pgio_header *header)
 	for (i = pg_index; i < header->page_array.npages; i++) {
 		if (extent_length <= 0) {
 			/* We've used up the previous extent */
-			bio = bl_submit_bio(READ, bio);
+			bio = bl_submit_bio(bio);
 
 			/* Get the next one */
 			if (!ext_tree_lookup(bl, isect, &be, false)) {
@@ -273,7 +275,7 @@ bl_read_pagelist(struct nfs_pgio_header *header)
 		}
 
 		if (is_hole(&be)) {
-			bio = bl_submit_bio(READ, bio);
+			bio = bl_submit_bio(bio);
 			/* Fill hole w/ zeroes w/o accessing device */
 			dprintk("%s Zeroing page for hole\n", __func__);
 			zero_user_segment(pages[i], pg_offset, pg_len);
@@ -306,7 +308,7 @@ bl_read_pagelist(struct nfs_pgio_header *header)
 		header->res.count = (isect << SECTOR_SHIFT) - header->args.offset;
 	}
 out:
-	bl_submit_bio(READ, bio);
+	bl_submit_bio(bio);
 	blk_finish_plug(&plug);
 	put_parallel(par);
 	return PNFS_ATTEMPTED;
@@ -398,7 +400,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 	for (i = pg_index; i < header->page_array.npages; i++) {
 		if (extent_length <= 0) {
 			/* We've used up the previous extent */
-			bio = bl_submit_bio(WRITE, bio);
+			bio = bl_submit_bio(bio);
 			/* Get the next one */
 			if (!ext_tree_lookup(bl, isect, &be, true)) {
 				header->pnfs_error = -EINVAL;
@@ -427,7 +429,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 
 	header->res.count = header->args.count;
 out:
-	bl_submit_bio(WRITE, bio);
+	bl_submit_bio(bio);
 	blk_finish_plug(&plug);
 	put_parallel(par);
 	return PNFS_ATTEMPTED;
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 0576033699bc..4cca998ec7a0 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -62,7 +62,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 }
 
 int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
-			      sector_t pblocknr, int mode,
+			      sector_t pblocknr, int mode, int mode_flags,
 			      struct buffer_head **pbh, sector_t *submit_ptr)
 {
 	struct buffer_head *bh;
@@ -95,7 +95,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
 		}
 	}
 
-	if (mode == READA) {
+	if (mode_flags & REQ_RAHEAD) {
 		if (pblocknr != *submit_ptr + 1 || !trylock_buffer(bh)) {
 			err = -EBUSY; /* internal code */
 			brelse(bh);
@@ -114,7 +114,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
 	bh->b_blocknr = pblocknr; /* set block address for read */
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(mode, bh);
+	submit_bh(mode, mode_flags, bh);
 	bh->b_blocknr = blocknr; /* set back to the given block address */
 	*submit_ptr = pblocknr;
 	err = 0;
diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h
index 2cc1b80e18f7..4e8aaa1aeb65 100644
--- a/fs/nilfs2/btnode.h
+++ b/fs/nilfs2/btnode.h
@@ -43,7 +43,7 @@ void nilfs_btnode_cache_clear(struct address_space *);
 struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc,
 					      __u64 blocknr);
 int nilfs_btnode_submit_block(struct address_space *, __u64, sector_t, int,
-			      struct buffer_head **, sector_t *);
+			      int, struct buffer_head **, sector_t *);
 void nilfs_btnode_delete(struct buffer_head *);
 int nilfs_btnode_prepare_change_key(struct address_space *,
 				    struct nilfs_btnode_chkey_ctxt *);
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index eccb1c89ccbb..982d1e3df3a5 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -476,7 +476,8 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
 	sector_t submit_ptr = 0;
 	int ret;
 
-	ret = nilfs_btnode_submit_block(btnc, ptr, 0, READ, &bh, &submit_ptr);
+	ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, 0, &bh,
+					&submit_ptr);
 	if (ret) {
 		if (ret != -EEXIST)
 			return ret;
@@ -492,7 +493,8 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
 		     n > 0 && i < ra->ncmax; n--, i++) {
 			ptr2 = nilfs_btree_node_get_ptr(ra->node, i, ra->ncmax);
 
-			ret = nilfs_btnode_submit_block(btnc, ptr2, 0, READA,
+			ret = nilfs_btnode_submit_block(btnc, ptr2, 0,
+							REQ_OP_READ, REQ_RAHEAD,
 							&ra_bh, &submit_ptr);
 			if (likely(!ret || ret == -EEXIST))
 				brelse(ra_bh);
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 693aded72498..e9148f94d696 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -101,7 +101,7 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
 	bh->b_blocknr = pbn;
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(READ, bh);
+	submit_bh(REQ_OP_READ, 0, bh);
 	if (vbn)
 		bh->b_blocknr = vbn;
  out:
@@ -138,7 +138,8 @@ int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn,
 	int ret;
 
 	ret = nilfs_btnode_submit_block(&NILFS_I(inode)->i_btnode_cache,
-					vbn ? : pbn, pbn, READ, out_bh, &pbn);
+					vbn ? : pbn, pbn, REQ_OP_READ, 0,
+					out_bh, &pbn);
 	if (ret == -EEXIST) /* internal code (cache hit) */
 		ret = 0;
 	return ret;
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 3417d859a03c..0d7b71fbeff8 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -121,7 +121,7 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
 
 static int
 nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
-		       int mode, struct buffer_head **out_bh)
+		       int mode, int mode_flags, struct buffer_head **out_bh)
 {
 	struct buffer_head *bh;
 	__u64 blknum = 0;
@@ -135,7 +135,7 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
 	if (buffer_uptodate(bh))
 		goto out;
 
-	if (mode == READA) {
+	if (mode_flags & REQ_RAHEAD) {
 		if (!trylock_buffer(bh)) {
 			ret = -EBUSY;
 			goto failed_bh;
@@ -157,7 +157,7 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
 
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(mode, bh);
+	submit_bh(mode, mode_flags, bh);
 	ret = 0;
 
 	trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff, mode);
@@ -181,7 +181,7 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
 	int i, nr_ra_blocks = NILFS_MDT_MAX_RA_BLOCKS;
 	int err;
 
-	err = nilfs_mdt_submit_block(inode, block, READ, &first_bh);
+	err = nilfs_mdt_submit_block(inode, block, REQ_OP_READ, 0, &first_bh);
 	if (err == -EEXIST) /* internal code */
 		goto out;
 
@@ -191,7 +191,8 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
 	if (readahead) {
 		blkoff = block + 1;
 		for (i = 0; i < nr_ra_blocks; i++, blkoff++) {
-			err = nilfs_mdt_submit_block(inode, blkoff, READA, &bh);
+			err = nilfs_mdt_submit_block(inode, blkoff, REQ_OP_READ,
+						     REQ_RAHEAD, &bh);
 			if (likely(!err || err == -EEXIST))
 				brelse(bh);
 			else if (err != -EBUSY)
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index bf36df10540b..a962d7d83447 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -346,7 +346,8 @@ static void nilfs_end_bio_write(struct bio *bio)
 }
 
 static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
-				   struct nilfs_write_info *wi, int mode)
+				   struct nilfs_write_info *wi, int mode,
+				   int mode_flags)
 {
 	struct bio *bio = wi->bio;
 	int err;
@@ -364,7 +365,8 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
 
 	bio->bi_end_io = nilfs_end_bio_write;
 	bio->bi_private = segbuf;
-	submit_bio(mode, bio);
+	bio_set_op_attrs(bio, mode, mode_flags);
+	submit_bio(bio);
 	segbuf->sb_nbio++;
 
 	wi->bio = NULL;
@@ -437,7 +439,7 @@ static int nilfs_segbuf_submit_bh(struct nilfs_segment_buffer *segbuf,
 		return 0;
 	}
 	/* bio is FULL */
-	err = nilfs_segbuf_submit_bio(segbuf, wi, mode);
+	err = nilfs_segbuf_submit_bio(segbuf, wi, mode, 0);
 	/* never submit current bh */
 	if (likely(!err))
 		goto repeat;
@@ -461,19 +463,19 @@ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf,
 {
 	struct nilfs_write_info wi;
 	struct buffer_head *bh;
-	int res = 0, rw = WRITE;
+	int res = 0;
 
 	wi.nilfs = nilfs;
 	nilfs_segbuf_prepare_write(segbuf, &wi);
 
 	list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) {
-		res = nilfs_segbuf_submit_bh(segbuf, &wi, bh, rw);
+		res = nilfs_segbuf_submit_bh(segbuf, &wi, bh, REQ_OP_WRITE);
 		if (unlikely(res))
 			goto failed_bio;
 	}
 
 	list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) {
-		res = nilfs_segbuf_submit_bh(segbuf, &wi, bh, rw);
+		res = nilfs_segbuf_submit_bh(segbuf, &wi, bh, REQ_OP_WRITE);
 		if (unlikely(res))
 			goto failed_bio;
 	}
@@ -483,8 +485,8 @@ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf,
 		 * Last BIO is always sent through the following
 		 * submission.
 		 */
-		rw |= REQ_SYNC;
-		res = nilfs_segbuf_submit_bio(segbuf, &wi, rw);
+		res = nilfs_segbuf_submit_bio(segbuf, &wi, REQ_OP_WRITE,
+					      REQ_SYNC);
 	}
 
  failed_bio:
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 97768a1379f2..fe251f187ff8 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -362,7 +362,7 @@ handle_zblock:
 		for (i = 0; i < nr; i++) {
 			tbh = arr[i];
 			if (likely(!buffer_uptodate(tbh)))
-				submit_bh(READ, tbh);
+				submit_bh(REQ_OP_READ, 0, tbh);
 			else
 				ntfs_end_buffer_async_read(tbh, 1);
 		}
@@ -877,7 +877,7 @@ lock_retry_remap:
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(WRITE, bh);
+			submit_bh(REQ_OP_WRITE, 0, bh);
 			need_end_writeback = false;
 		}
 		bh = next;
@@ -1202,7 +1202,7 @@ lock_retry_remap:
 		BUG_ON(!buffer_mapped(tbh));
 		get_bh(tbh);
 		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(WRITE, tbh);
+		submit_bh(REQ_OP_WRITE, 0, tbh);
 	}
 	/* Synchronize the mft mirror now if not @sync. */
 	if (is_mft && !sync)
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index f2b5e746f49b..f8eb04387ca4 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -670,7 +670,7 @@ lock_retry_remap:
 		}
 		get_bh(tbh);
 		tbh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ, tbh);
+		submit_bh(REQ_OP_READ, 0, tbh);
 	}
 
 	/* Wait for io completion on all buffer heads. */
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 5622ed5a201e..f548629dfaac 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -553,7 +553,7 @@ static inline int ntfs_submit_bh_for_read(struct buffer_head *bh)
 	lock_buffer(bh);
 	get_bh(bh);
 	bh->b_end_io = end_buffer_read_sync;
-	return submit_bh(READ, bh);
+	return submit_bh(REQ_OP_READ, 0, bh);
 }
 
 /**
diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
index 9d71213ca81e..761f12f7f3ef 100644
--- a/fs/ntfs/logfile.c
+++ b/fs/ntfs/logfile.c
@@ -821,7 +821,7 @@ map_vcn:
 			 * completed ignore errors afterwards as we can assume
 			 * that if one buffer worked all of them will work.
 			 */
-			submit_bh(WRITE, bh);
+			submit_bh(REQ_OP_WRITE, 0, bh);
 			if (should_wait) {
 				should_wait = false;
 				wait_on_buffer(bh);
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 37b2501caaa4..d15d492ce47b 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -592,7 +592,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
 			clear_buffer_dirty(tbh);
 			get_bh(tbh);
 			tbh->b_end_io = end_buffer_write_sync;
-			submit_bh(WRITE, tbh);
+			submit_bh(REQ_OP_WRITE, 0, tbh);
 		}
 		/* Wait on i/o completion of buffers. */
 		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
@@ -785,7 +785,7 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
 		clear_buffer_dirty(tbh);
 		get_bh(tbh);
 		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(WRITE, tbh);
+		submit_bh(REQ_OP_WRITE, 0, tbh);
 	}
 	/* Synchronize the mft mirror now if not @sync. */
 	if (!sync && ni->mft_no < vol->mftmirr_size)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index c034edf3ef38..e97a37179614 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -640,7 +640,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
 			   !buffer_new(bh) &&
 			   ocfs2_should_read_blk(inode, page, block_start) &&
 			   (block_start < from || block_end > to)) {
-			ll_rw_block(READ, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 			*wait_bh++=bh;
 		}
 
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 498641eed2db..8f040f88ade4 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -79,7 +79,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 
 	get_bh(bh); /* for end_buffer_write_sync() */
 	bh->b_end_io = end_buffer_write_sync;
-	submit_bh(WRITE, bh);
+	submit_bh(REQ_OP_WRITE, 0, bh);
 
 	wait_on_buffer(bh);
 
@@ -154,7 +154,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 		clear_buffer_uptodate(bh);
 		get_bh(bh); /* for end_buffer_read_sync() */
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ, bh);
+		submit_bh(REQ_OP_READ, 0, bh);
 	}
 
 	for (i = nr; i > 0; i--) {
@@ -310,7 +310,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 			if (validate)
 				set_buffer_needs_validate(bh);
 			bh->b_end_io = end_buffer_read_sync;
-			submit_bh(READ, bh);
+			submit_bh(REQ_OP_READ, 0, bh);
 			continue;
 		}
 	}
@@ -424,7 +424,7 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 	get_bh(bh); /* for end_buffer_write_sync() */
 	bh->b_end_io = end_buffer_write_sync;
 	ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &di->i_check);
-	submit_bh(WRITE, bh);
+	submit_bh(REQ_OP_WRITE, 0, bh);
 
 	wait_on_buffer(bh);
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 6aaf3e351391..636abcbd4650 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -530,7 +530,8 @@ static void o2hb_bio_end_io(struct bio *bio)
 static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 				      struct o2hb_bio_wait_ctxt *wc,
 				      unsigned int *current_slot,
-				      unsigned int max_slots)
+				      unsigned int max_slots, int op,
+				      int op_flags)
 {
 	int len, current_page;
 	unsigned int vec_len, vec_start;
@@ -556,6 +557,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 	bio->bi_bdev = reg->hr_bdev;
 	bio->bi_private = wc;
 	bio->bi_end_io = o2hb_bio_end_io;
+	bio_set_op_attrs(bio, op, op_flags);
 
 	vec_start = (cs << bits) % PAGE_SIZE;
 	while(cs < max_slots) {
@@ -591,7 +593,8 @@ static int o2hb_read_slots(struct o2hb_region *reg,
 	o2hb_bio_wait_init(&wc);
 
 	while(current_slot < max_slots) {
-		bio = o2hb_setup_one_bio(reg, &wc, &current_slot, max_slots);
+		bio = o2hb_setup_one_bio(reg, &wc, &current_slot, max_slots,
+					 REQ_OP_READ, 0);
 		if (IS_ERR(bio)) {
 			status = PTR_ERR(bio);
 			mlog_errno(status);
@@ -599,7 +602,7 @@ static int o2hb_read_slots(struct o2hb_region *reg,
 		}
 
 		atomic_inc(&wc.wc_num_reqs);
-		submit_bio(READ, bio);
+		submit_bio(bio);
 	}
 
 	status = 0;
@@ -623,7 +626,8 @@ static int o2hb_issue_node_write(struct o2hb_region *reg,
 
 	slot = o2nm_this_node();
 
-	bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1);
+	bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1, REQ_OP_WRITE,
+				 WRITE_SYNC);
 	if (IS_ERR(bio)) {
 		status = PTR_ERR(bio);
 		mlog_errno(status);
@@ -631,7 +635,7 @@ static int o2hb_issue_node_write(struct o2hb_region *reg,
 	}
 
 	atomic_inc(&write_wc->wc_num_reqs);
-	submit_bio(WRITE_SYNC, bio);
+	submit_bio(bio);
 
 	status = 0;
 bail:
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index d97de212c4db..603b28d6f008 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1819,7 +1819,7 @@ static int ocfs2_get_sector(struct super_block *sb,
 	if (!buffer_dirty(*bh))
 		clear_buffer_uptodate(*bh);
 	unlock_buffer(*bh);
-	ll_rw_block(READ, 1, bh);
+	ll_rw_block(REQ_OP_READ, 0, 1, bh);
 	wait_on_buffer(*bh);
 	if (!buffer_uptodate(*bh)) {
 		mlog_errno(-EIO);
diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c
index 03f89dbb2512..28f2195cd798 100644
--- a/fs/orangefs/acl.c
+++ b/fs/orangefs/acl.c
@@ -18,10 +18,10 @@ struct posix_acl *orangefs_get_acl(struct inode *inode, int type)
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		key = ORANGEFS_XATTR_NAME_ACL_ACCESS;
+		key = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		key = ORANGEFS_XATTR_NAME_ACL_DEFAULT;
+		key = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		gossip_err("orangefs_get_acl: bogus value of type %d\n", type);
@@ -43,11 +43,8 @@ struct posix_acl *orangefs_get_acl(struct inode *inode, int type)
 		     get_khandle_from_ino(inode),
 		     key,
 		     type);
-	ret = orangefs_inode_getxattr(inode,
-				   "",
-				   key,
-				   value,
-				   ORANGEFS_MAX_XATTR_VALUELEN);
+	ret = orangefs_inode_getxattr(inode, key, value,
+				      ORANGEFS_MAX_XATTR_VALUELEN);
 	/* if the key exists, convert it to an in-memory rep */
 	if (ret > 0) {
 		acl = posix_acl_from_xattr(&init_user_ns, value, ret);
@@ -74,7 +71,7 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = ORANGEFS_XATTR_NAME_ACL_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			umode_t mode = inode->i_mode;
 			/*
@@ -98,7 +95,7 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = ORANGEFS_XATTR_NAME_ACL_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		gossip_err("%s: invalid type %d!\n", __func__, type);
@@ -131,7 +128,7 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	 * will xlate to a removexattr. However, we don't want removexattr
 	 * complain if attributes does not exist.
 	 */
-	error = orangefs_inode_setxattr(inode, "", name, value, size, 0);
+	error = orangefs_inode_setxattr(inode, name, value, size, 0);
 
 out:
 	kfree(value);
diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c
index db170beba797..a287a66d94e3 100644
--- a/fs/orangefs/devorangefs-req.c
+++ b/fs/orangefs/devorangefs-req.c
@@ -116,6 +116,13 @@ static int orangefs_devreq_open(struct inode *inode, struct file *file)
 {
 	int ret = -EINVAL;
 
+	/* in order to ensure that the filesystem driver sees correct UIDs */
+	if (file->f_cred->user_ns != &init_user_ns) {
+		gossip_err("%s: device cannot be opened outside init_user_ns\n",
+			   __func__);
+		goto out;
+	}
+
 	if (!(file->f_flags & O_NONBLOCK)) {
 		gossip_err("%s: device cannot be opened in blocking mode\n",
 			   __func__);
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index 491e82c6f705..526040e09f78 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -516,7 +516,6 @@ static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	if (cmd == FS_IOC_GETFLAGS) {
 		val = 0;
 		ret = orangefs_inode_getxattr(file_inode(file),
-					      ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
 					      "user.pvfs2.meta_hint",
 					      &val, sizeof(val));
 		if (ret < 0 && ret != -ENODATA)
@@ -549,7 +548,6 @@ static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 			     "orangefs_ioctl: FS_IOC_SETFLAGS: %llu\n",
 			     (unsigned long long)val);
 		ret = orangefs_inode_setxattr(file_inode(file),
-					      ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
 					      "user.pvfs2.meta_hint",
 					      &val, sizeof(val), 0);
 	}
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 06a8da75651d..8f2fa94cc4f6 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -124,19 +124,16 @@ static int orangefs_releasepage(struct page *page, gfp_t foo)
  * will need to be able to use O_DIRECT on open in order to support
  * AIO. Modeled after NFS, they do this too.
  */
-/*
- * static ssize_t orangefs_direct_IO(int rw,
- *			struct kiocb *iocb,
- *			struct iov_iter *iter,
- *			loff_t offset)
- *{
- *	gossip_debug(GOSSIP_INODE_DEBUG,
- *		     "orangefs_direct_IO: %s\n",
- *		     iocb->ki_filp->f_path.dentry->d_name.name);
- *
- *	return -EINVAL;
- *}
- */
+
+static ssize_t orangefs_direct_IO(struct kiocb *iocb,
+				  struct iov_iter *iter)
+{
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_direct_IO: %s\n",
+		     iocb->ki_filp->f_path.dentry->d_name.name);
+
+	return -EINVAL;
+}
 
 struct backing_dev_info orangefs_backing_dev_info = {
 	.name = "orangefs",
@@ -150,7 +147,7 @@ const struct address_space_operations orangefs_address_operations = {
 	.readpages = orangefs_readpages,
 	.invalidatepage = orangefs_invalidatepage,
 	.releasepage = orangefs_releasepage,
-/*	.direct_IO = orangefs_direct_IO */
+	.direct_IO = orangefs_direct_IO,
 };
 
 static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
diff --git a/fs/orangefs/orangefs-cache.c b/fs/orangefs/orangefs-cache.c
index 900a2e38e11b..b6edbe9fb309 100644
--- a/fs/orangefs/orangefs-cache.c
+++ b/fs/orangefs/orangefs-cache.c
@@ -136,10 +136,10 @@ struct orangefs_kernel_op_s *op_alloc(__s32 type)
 			     llu(new_op->tag),
 			     get_opname_string(new_op));
 
-		new_op->upcall.uid = from_kuid(current_user_ns(),
+		new_op->upcall.uid = from_kuid(&init_user_ns,
 					       current_fsuid());
 
-		new_op->upcall.gid = from_kgid(current_user_ns(),
+		new_op->upcall.gid = from_kgid(&init_user_ns,
 					       current_fsgid());
 	} else {
 		gossip_err("op_alloc: kmem_cache_zalloc failed!\n");
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 2281882f718e..c1181e5529af 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -119,17 +119,6 @@ struct client_debug_mask {
 #define ORANGEFS_CACHE_CREATE_FLAGS 0
 #endif /* ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB)) */
 
-/* orangefs xattr and acl related defines */
-#define ORANGEFS_XATTR_INDEX_POSIX_ACL_ACCESS  1
-#define ORANGEFS_XATTR_INDEX_POSIX_ACL_DEFAULT 2
-#define ORANGEFS_XATTR_INDEX_TRUSTED           3
-#define ORANGEFS_XATTR_INDEX_DEFAULT           4
-
-#define ORANGEFS_XATTR_NAME_ACL_ACCESS XATTR_NAME_POSIX_ACL_ACCESS
-#define ORANGEFS_XATTR_NAME_ACL_DEFAULT XATTR_NAME_POSIX_ACL_DEFAULT
-#define ORANGEFS_XATTR_NAME_TRUSTED_PREFIX "trusted."
-#define ORANGEFS_XATTR_NAME_DEFAULT_PREFIX ""
-
 /* these functions are defined in orangefs-utils.c */
 int orangefs_prepare_cdm_array(char *debug_array_string);
 int orangefs_prepare_debugfs_help_string(int);
@@ -528,13 +517,11 @@ __s32 fsid_of_op(struct orangefs_kernel_op_s *op);
 int orangefs_flush_inode(struct inode *inode);
 
 ssize_t orangefs_inode_getxattr(struct inode *inode,
-			     const char *prefix,
 			     const char *name,
 			     void *buffer,
 			     size_t size);
 
 int orangefs_inode_setxattr(struct inode *inode,
-			 const char *prefix,
 			 const char *name,
 			 const void *value,
 			 size_t size,
@@ -600,8 +587,8 @@ int service_operation(struct orangefs_kernel_op_s *op,
 
 #define fill_default_sys_attrs(sys_attr, type, mode)			\
 do {									\
-	sys_attr.owner = from_kuid(current_user_ns(), current_fsuid()); \
-	sys_attr.group = from_kgid(current_user_ns(), current_fsgid()); \
+	sys_attr.owner = from_kuid(&init_user_ns, current_fsuid()); \
+	sys_attr.group = from_kgid(&init_user_ns, current_fsgid()); \
 	sys_attr.perms = ORANGEFS_util_translate_mode(mode);		\
 	sys_attr.mtime = 0;						\
 	sys_attr.atime = 0;						\
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
index 2d129b5886ee..c5fbc62357c6 100644
--- a/fs/orangefs/orangefs-utils.c
+++ b/fs/orangefs/orangefs-utils.c
@@ -153,12 +153,12 @@ static inline int copy_attributes_from_inode(struct inode *inode,
 	 */
 	attrs->mask = 0;
 	if (iattr->ia_valid & ATTR_UID) {
-		attrs->owner = from_kuid(current_user_ns(), iattr->ia_uid);
+		attrs->owner = from_kuid(&init_user_ns, iattr->ia_uid);
 		attrs->mask |= ORANGEFS_ATTR_SYS_UID;
 		gossip_debug(GOSSIP_UTILS_DEBUG, "(UID) %d\n", attrs->owner);
 	}
 	if (iattr->ia_valid & ATTR_GID) {
-		attrs->group = from_kgid(current_user_ns(), iattr->ia_gid);
+		attrs->group = from_kgid(&init_user_ns, iattr->ia_gid);
 		attrs->mask |= ORANGEFS_ATTR_SYS_GID;
 		gossip_debug(GOSSIP_UTILS_DEBUG, "(GID) %d\n", attrs->group);
 	}
diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c
index 5893ddde0e4b..2a9f07f06d10 100644
--- a/fs/orangefs/xattr.c
+++ b/fs/orangefs/xattr.c
@@ -59,8 +59,8 @@ static inline int convert_to_internal_xattr_flags(int setxattr_flags)
  * unless the key does not exist for the file and/or if
  * there were errors in fetching the attribute value.
  */
-ssize_t orangefs_inode_getxattr(struct inode *inode, const char *prefix,
-		const char *name, void *buffer, size_t size)
+ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name,
+				void *buffer, size_t size)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	struct orangefs_kernel_op_s *new_op = NULL;
@@ -70,17 +70,17 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *prefix,
 	int fsgid;
 
 	gossip_debug(GOSSIP_XATTR_DEBUG,
-		     "%s: prefix %s name %s, buffer_size %zd\n",
-		     __func__, prefix, name, size);
+		     "%s: name %s, buffer_size %zd\n",
+		     __func__, name, size);
 
-	if ((strlen(name) + strlen(prefix)) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+	if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) {
 		gossip_err("Invalid key length (%d)\n",
-			   (int)(strlen(name) + strlen(prefix)));
+			   (int)strlen(name));
 		return -EINVAL;
 	}
 
-	fsuid = from_kuid(current_user_ns(), current_fsuid());
-	fsgid = from_kgid(current_user_ns(), current_fsgid());
+	fsuid = from_kuid(&init_user_ns, current_fsuid());
+	fsgid = from_kgid(&init_user_ns, current_fsgid());
 
 	gossip_debug(GOSSIP_XATTR_DEBUG,
 		     "getxattr on inode %pU, name %s "
@@ -97,15 +97,14 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *prefix,
 		goto out_unlock;
 
 	new_op->upcall.req.getxattr.refn = orangefs_inode->refn;
-	ret = snprintf((char *)new_op->upcall.req.getxattr.key,
-		       ORANGEFS_MAX_XATTR_NAMELEN, "%s%s", prefix, name);
+	strcpy(new_op->upcall.req.getxattr.key, name);
 
 	/*
 	 * NOTE: Although keys are meant to be NULL terminated textual
 	 * strings, I am going to explicitly pass the length just in case
 	 * we change this later on...
 	 */
-	new_op->upcall.req.getxattr.key_sz = ret + 1;
+	new_op->upcall.req.getxattr.key_sz = strlen(name) + 1;
 
 	ret = service_operation(new_op, "orangefs_inode_getxattr",
 				get_interruptible_flag(inode));
@@ -163,10 +162,8 @@ out_unlock:
 	return ret;
 }
 
-static int orangefs_inode_removexattr(struct inode *inode,
-			    const char *prefix,
-			    const char *name,
-			    int flags)
+static int orangefs_inode_removexattr(struct inode *inode, const char *name,
+				      int flags)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	struct orangefs_kernel_op_s *new_op = NULL;
@@ -183,12 +180,8 @@ static int orangefs_inode_removexattr(struct inode *inode,
 	 * textual strings, I am going to explicitly pass the
 	 * length just in case we change this later on...
 	 */
-	ret = snprintf((char *)new_op->upcall.req.removexattr.key,
-		       ORANGEFS_MAX_XATTR_NAMELEN,
-		       "%s%s",
-		       (prefix ? prefix : ""),
-		       name);
-	new_op->upcall.req.removexattr.key_sz = ret + 1;
+	strcpy(new_op->upcall.req.removexattr.key, name);
+	new_op->upcall.req.removexattr.key_sz = strlen(name) + 1;
 
 	gossip_debug(GOSSIP_XATTR_DEBUG,
 		     "orangefs_inode_removexattr: key %s, key_sz %d\n",
@@ -223,8 +216,8 @@ out_unlock:
  * Returns a -ve number on error and 0 on success.  Key is text, but value
  * can be binary!
  */
-int orangefs_inode_setxattr(struct inode *inode, const char *prefix,
-		const char *name, const void *value, size_t size, int flags)
+int orangefs_inode_setxattr(struct inode *inode, const char *name,
+			    const void *value, size_t size, int flags)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	struct orangefs_kernel_op_s *new_op;
@@ -232,8 +225,8 @@ int orangefs_inode_setxattr(struct inode *inode, const char *prefix,
 	int ret = -ENOMEM;
 
 	gossip_debug(GOSSIP_XATTR_DEBUG,
-		     "%s: prefix %s, name %s, buffer_size %zd\n",
-		     __func__, prefix, name, size);
+		     "%s: name %s, buffer_size %zd\n",
+		     __func__, name, size);
 
 	if (size >= ORANGEFS_MAX_XATTR_VALUELEN ||
 	    flags < 0) {
@@ -245,29 +238,19 @@ int orangefs_inode_setxattr(struct inode *inode, const char *prefix,
 
 	internal_flag = convert_to_internal_xattr_flags(flags);
 
-	if (prefix) {
-		if (strlen(name) + strlen(prefix) >= ORANGEFS_MAX_XATTR_NAMELEN) {
-			gossip_err
-			    ("orangefs_inode_setxattr: bogus key size (%d)\n",
-			     (int)(strlen(name) + strlen(prefix)));
-			return -EINVAL;
-		}
-	} else {
-		if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) {
-			gossip_err
-			    ("orangefs_inode_setxattr: bogus key size (%d)\n",
-			     (int)(strlen(name)));
-			return -EINVAL;
-		}
+	if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+		gossip_err
+		    ("orangefs_inode_setxattr: bogus key size (%d)\n",
+		     (int)(strlen(name)));
+		return -EINVAL;
 	}
 
 	/* This is equivalent to a removexattr */
 	if (size == 0 && value == NULL) {
 		gossip_debug(GOSSIP_XATTR_DEBUG,
-			     "removing xattr (%s%s)\n",
-			     prefix,
+			     "removing xattr (%s)\n",
 			     name);
-		return orangefs_inode_removexattr(inode, prefix, name, flags);
+		return orangefs_inode_removexattr(inode, name, flags);
 	}
 
 	gossip_debug(GOSSIP_XATTR_DEBUG,
@@ -288,11 +271,8 @@ int orangefs_inode_setxattr(struct inode *inode, const char *prefix,
 	 * strings, I am going to explicitly pass the length just in
 	 * case we change this later on...
 	 */
-	ret = snprintf((char *)new_op->upcall.req.setxattr.keyval.key,
-		       ORANGEFS_MAX_XATTR_NAMELEN,
-		       "%s%s",
-		       prefix, name);
-	new_op->upcall.req.setxattr.keyval.key_sz = ret + 1;
+	strcpy(new_op->upcall.req.setxattr.keyval.key, name);
+	new_op->upcall.req.setxattr.keyval.key_sz = strlen(name) + 1;
 	memcpy(new_op->upcall.req.setxattr.keyval.val, value, size);
 	new_op->upcall.req.setxattr.keyval.val_sz = size;
 
@@ -455,12 +435,7 @@ static int orangefs_xattr_set_default(const struct xattr_handler *handler,
 				      size_t size,
 				      int flags)
 {
-	return orangefs_inode_setxattr(inode,
-				    ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
-				    name,
-				    buffer,
-				    size,
-				    flags);
+	return orangefs_inode_setxattr(inode, name, buffer, size, flags);
 }
 
 static int orangefs_xattr_get_default(const struct xattr_handler *handler,
@@ -470,57 +445,12 @@ static int orangefs_xattr_get_default(const struct xattr_handler *handler,
 				      void *buffer,
 				      size_t size)
 {
-	return orangefs_inode_getxattr(inode,
-				    ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
-				    name,
-				    buffer,
-				    size);
-
-}
+	return orangefs_inode_getxattr(inode, name, buffer, size);
 
-static int orangefs_xattr_set_trusted(const struct xattr_handler *handler,
-				     struct dentry *unused,
-				     struct inode *inode,
-				     const char *name,
-				     const void *buffer,
-				     size_t size,
-				     int flags)
-{
-	return orangefs_inode_setxattr(inode,
-				    ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
-				    name,
-				    buffer,
-				    size,
-				    flags);
 }
 
-static int orangefs_xattr_get_trusted(const struct xattr_handler *handler,
-				      struct dentry *unused,
-				      struct inode *inode,
-				      const char *name,
-				      void *buffer,
-				      size_t size)
-{
-	return orangefs_inode_getxattr(inode,
-				    ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
-				    name,
-				    buffer,
-				    size);
-}
-
-static struct xattr_handler orangefs_xattr_trusted_handler = {
-	.prefix = ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
-	.get = orangefs_xattr_get_trusted,
-	.set = orangefs_xattr_set_trusted,
-};
-
 static struct xattr_handler orangefs_xattr_default_handler = {
-	/*
-	 * NOTE: this is set to be the empty string.
-	 * so that all un-prefixed xattrs keys get caught
-	 * here!
-	 */
-	.prefix = ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+	.prefix = "",  /* match any name => handlers called with full name */
 	.get = orangefs_xattr_get_default,
 	.set = orangefs_xattr_set_default,
 };
@@ -528,7 +458,6 @@ static struct xattr_handler orangefs_xattr_default_handler = {
 const struct xattr_handler *orangefs_xattr_handlers[] = {
 	&posix_acl_access_xattr_handler,
 	&posix_acl_default_xattr_handler,
-	&orangefs_xattr_trusted_handler,
 	&orangefs_xattr_default_handler,
 	NULL
 };
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 360ae43f590c..be40813eff52 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -1,8 +1,6 @@
 config PSTORE
 	tristate "Persistent store support"
 	default n
-	select ZLIB_DEFLATE
-	select ZLIB_INFLATE
 	help
 	   This option enables generic access to platform level
 	   persistent storage via "pstore" filesystem that can
@@ -14,6 +12,35 @@ config PSTORE
 	   If you don't have a platform persistent store driver,
 	   say N.
 
+choice
+        prompt "Choose compression algorithm"
+        depends on PSTORE
+        default PSTORE_ZLIB_COMPRESS
+        help
+          This option chooses compression algorithm.
+
+config PSTORE_ZLIB_COMPRESS
+        bool "ZLIB"
+        select ZLIB_DEFLATE
+        select ZLIB_INFLATE
+        help
+          This option enables ZLIB compression algorithm support.
+
+config PSTORE_LZO_COMPRESS
+        bool "LZO"
+        select LZO_COMPRESS
+        select LZO_DECOMPRESS
+        help
+          This option enables LZO compression algorithm support.
+
+config PSTORE_LZ4_COMPRESS
+        bool "LZ4"
+        select LZ4_COMPRESS
+        select LZ4_DECOMPRESS
+        help
+          This option enables LZ4 compression algorithm support.
+endchoice
+
 config PSTORE_CONSOLE
 	bool "Log kernel console messages"
 	depends on PSTORE
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 45d6110744cb..ec9ddef5ae75 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -178,7 +178,6 @@ static loff_t pstore_file_llseek(struct file *file, loff_t off, int whence)
 }
 
 static const struct file_operations pstore_file_operations = {
-	.owner		= THIS_MODULE,
 	.open		= pstore_file_open,
 	.read		= pstore_file_read,
 	.llseek		= pstore_file_llseek,
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 588461bb2dd4..16ecca5b72d8 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -28,7 +28,15 @@
 #include <linux/console.h>
 #include <linux/module.h>
 #include <linux/pstore.h>
+#ifdef CONFIG_PSTORE_ZLIB_COMPRESS
 #include <linux/zlib.h>
+#endif
+#ifdef CONFIG_PSTORE_LZO_COMPRESS
+#include <linux/lzo.h>
+#endif
+#ifdef CONFIG_PSTORE_LZ4_COMPRESS
+#include <linux/lz4.h>
+#endif
 #include <linux/string.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
@@ -69,10 +77,23 @@ struct pstore_info *psinfo;
 static char *backend;
 
 /* Compression parameters */
+#ifdef CONFIG_PSTORE_ZLIB_COMPRESS
 #define COMPR_LEVEL 6
 #define WINDOW_BITS 12
 #define MEM_LEVEL 4
 static struct z_stream_s stream;
+#else
+static unsigned char *workspace;
+#endif
+
+struct pstore_zbackend {
+	int (*compress)(const void *in, void *out, size_t inlen, size_t outlen);
+	int (*decompress)(void *in, void *out, size_t inlen, size_t outlen);
+	void (*allocate)(void);
+	void (*free)(void);
+
+	const char *name;
+};
 
 static char *big_oops_buf;
 static size_t big_oops_buf_sz;
@@ -129,9 +150,9 @@ bool pstore_cannot_block_path(enum kmsg_dump_reason reason)
 }
 EXPORT_SYMBOL_GPL(pstore_cannot_block_path);
 
+#ifdef CONFIG_PSTORE_ZLIB_COMPRESS
 /* Derived from logfs_compress() */
-static int pstore_compress(const void *in, void *out, size_t inlen,
-							size_t outlen)
+static int compress_zlib(const void *in, void *out, size_t inlen, size_t outlen)
 {
 	int err, ret;
 
@@ -165,7 +186,7 @@ error:
 }
 
 /* Derived from logfs_uncompress */
-static int pstore_decompress(void *in, void *out, size_t inlen, size_t outlen)
+static int decompress_zlib(void *in, void *out, size_t inlen, size_t outlen)
 {
 	int err, ret;
 
@@ -194,7 +215,7 @@ error:
 	return ret;
 }
 
-static void allocate_buf_for_compression(void)
+static void allocate_zlib(void)
 {
 	size_t size;
 	size_t cmpr;
@@ -237,12 +258,190 @@ static void allocate_buf_for_compression(void)
 
 }
 
-static void free_buf_for_compression(void)
+static void free_zlib(void)
 {
 	kfree(stream.workspace);
 	stream.workspace = NULL;
 	kfree(big_oops_buf);
 	big_oops_buf = NULL;
+	big_oops_buf_sz = 0;
+}
+
+static struct pstore_zbackend backend_zlib = {
+	.compress	= compress_zlib,
+	.decompress	= decompress_zlib,
+	.allocate	= allocate_zlib,
+	.free		= free_zlib,
+	.name		= "zlib",
+};
+#endif
+
+#ifdef CONFIG_PSTORE_LZO_COMPRESS
+static int compress_lzo(const void *in, void *out, size_t inlen, size_t outlen)
+{
+	int ret;
+
+	ret = lzo1x_1_compress(in, inlen, out, &outlen, workspace);
+	if (ret != LZO_E_OK) {
+		pr_err("lzo_compress error, ret = %d!\n", ret);
+		return -EIO;
+	}
+
+	return outlen;
+}
+
+static int decompress_lzo(void *in, void *out, size_t inlen, size_t outlen)
+{
+	int ret;
+
+	ret = lzo1x_decompress_safe(in, inlen, out, &outlen);
+	if (ret != LZO_E_OK) {
+		pr_err("lzo_decompress error, ret = %d!\n", ret);
+		return -EIO;
+	}
+
+	return outlen;
+}
+
+static void allocate_lzo(void)
+{
+	big_oops_buf_sz = lzo1x_worst_compress(psinfo->bufsize);
+	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+	if (big_oops_buf) {
+		workspace = kmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+		if (!workspace) {
+			pr_err("No memory for compression workspace; skipping compression\n");
+			kfree(big_oops_buf);
+			big_oops_buf = NULL;
+		}
+	} else {
+		pr_err("No memory for uncompressed data; skipping compression\n");
+		workspace = NULL;
+	}
+}
+
+static void free_lzo(void)
+{
+	kfree(workspace);
+	kfree(big_oops_buf);
+	big_oops_buf = NULL;
+	big_oops_buf_sz = 0;
+}
+
+static struct pstore_zbackend backend_lzo = {
+	.compress	= compress_lzo,
+	.decompress	= decompress_lzo,
+	.allocate	= allocate_lzo,
+	.free		= free_lzo,
+	.name		= "lzo",
+};
+#endif
+
+#ifdef CONFIG_PSTORE_LZ4_COMPRESS
+static int compress_lz4(const void *in, void *out, size_t inlen, size_t outlen)
+{
+	int ret;
+
+	ret = lz4_compress(in, inlen, out, &outlen, workspace);
+	if (ret) {
+		pr_err("lz4_compress error, ret = %d!\n", ret);
+		return -EIO;
+	}
+
+	return outlen;
+}
+
+static int decompress_lz4(void *in, void *out, size_t inlen, size_t outlen)
+{
+	int ret;
+
+	ret = lz4_decompress_unknownoutputsize(in, inlen, out, &outlen);
+	if (ret) {
+		pr_err("lz4_decompress error, ret = %d!\n", ret);
+		return -EIO;
+	}
+
+	return outlen;
+}
+
+static void allocate_lz4(void)
+{
+	big_oops_buf_sz = lz4_compressbound(psinfo->bufsize);
+	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+	if (big_oops_buf) {
+		workspace = kmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
+		if (!workspace) {
+			pr_err("No memory for compression workspace; skipping compression\n");
+			kfree(big_oops_buf);
+			big_oops_buf = NULL;
+		}
+	} else {
+		pr_err("No memory for uncompressed data; skipping compression\n");
+		workspace = NULL;
+	}
+}
+
+static void free_lz4(void)
+{
+	kfree(workspace);
+	kfree(big_oops_buf);
+	big_oops_buf = NULL;
+	big_oops_buf_sz = 0;
+}
+
+static struct pstore_zbackend backend_lz4 = {
+	.compress	= compress_lz4,
+	.decompress	= decompress_lz4,
+	.allocate	= allocate_lz4,
+	.free		= free_lz4,
+	.name		= "lz4",
+};
+#endif
+
+static struct pstore_zbackend *zbackend =
+#if defined(CONFIG_PSTORE_ZLIB_COMPRESS)
+	&backend_zlib;
+#elif defined(CONFIG_PSTORE_LZO_COMPRESS)
+	&backend_lzo;
+#elif defined(CONFIG_PSTORE_LZ4_COMPRESS)
+	&backend_lz4;
+#else
+	NULL;
+#endif
+
+static int pstore_compress(const void *in, void *out,
+			   size_t inlen, size_t outlen)
+{
+	if (zbackend)
+		return zbackend->compress(in, out, inlen, outlen);
+	else
+		return -EIO;
+}
+
+static int pstore_decompress(void *in, void *out, size_t inlen, size_t outlen)
+{
+	if (zbackend)
+		return zbackend->decompress(in, out, inlen, outlen);
+	else
+		return -EIO;
+}
+
+static void allocate_buf_for_compression(void)
+{
+	if (zbackend) {
+		pr_info("using %s compression\n", zbackend->name);
+		zbackend->allocate();
+	} else {
+		pr_err("allocate compression buffer error!\n");
+	}
+}
+
+static void free_buf_for_compression(void)
+{
+	if (zbackend)
+		zbackend->free();
+	else
+		pr_err("free compression buffer error!\n");
 }
 
 /*
@@ -284,7 +483,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 	u64		id;
 	unsigned int	part = 1;
 	unsigned long	flags = 0;
-	int		is_locked = 0;
+	int		is_locked;
 	int		ret;
 
 	why = get_reason_str(reason);
@@ -295,8 +494,10 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 			pr_err("pstore dump routine blocked in %s path, may corrupt error record\n"
 				       , in_nmi() ? "NMI" : why);
 		}
-	} else
+	} else {
 		spin_lock_irqsave(&psinfo->buf_lock, flags);
+		is_locked = 1;
+	}
 	oopscount++;
 	while (total < kmsg_bytes) {
 		char *dst;
@@ -304,19 +505,25 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 		int hsize;
 		int zipped_len = -1;
 		size_t len;
-		bool compressed;
+		bool compressed = false;
 		size_t total_len;
 
 		if (big_oops_buf && is_locked) {
 			dst = big_oops_buf;
-			hsize = sprintf(dst, "%s#%d Part%u\n", why,
-							oopscount, part);
-			size = big_oops_buf_sz - hsize;
+			size = big_oops_buf_sz;
+		} else {
+			dst = psinfo->buf;
+			size = psinfo->bufsize;
+		}
 
-			if (!kmsg_dump_get_buffer(dumper, true, dst + hsize,
-								size, &len))
-				break;
+		hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount, part);
+		size -= hsize;
+
+		if (!kmsg_dump_get_buffer(dumper, true, dst + hsize,
+					  size, &len))
+			break;
 
+		if (big_oops_buf && is_locked) {
 			zipped_len = pstore_compress(dst, psinfo->buf,
 						hsize + len, psinfo->bufsize);
 
@@ -324,21 +531,9 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 				compressed = true;
 				total_len = zipped_len;
 			} else {
-				compressed = false;
 				total_len = copy_kmsg_to_buffer(hsize, len);
 			}
 		} else {
-			dst = psinfo->buf;
-			hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount,
-									part);
-			size = psinfo->bufsize - hsize;
-			dst += hsize;
-
-			if (!kmsg_dump_get_buffer(dumper, true, dst,
-								size, &len))
-				break;
-
-			compressed = false;
 			total_len = hsize + len;
 		}
 
@@ -350,10 +545,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 		total += total_len;
 		part++;
 	}
-	if (pstore_cannot_block_path(reason)) {
-		if (is_locked)
-			spin_unlock_irqrestore(&psinfo->buf_lock, flags);
-	} else
+	if (is_locked)
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 }
 
@@ -497,9 +689,11 @@ EXPORT_SYMBOL_GPL(pstore_register);
 
 void pstore_unregister(struct pstore_info *psi)
 {
-	pstore_unregister_pmsg();
-	pstore_unregister_ftrace();
-	pstore_unregister_console();
+	if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
+		pstore_unregister_pmsg();
+		pstore_unregister_ftrace();
+		pstore_unregister_console();
+	}
 	pstore_unregister_kmsg();
 
 	free_buf_for_compression();
@@ -527,6 +721,7 @@ void pstore_get_records(int quiet)
 	int			failed = 0, rc;
 	bool			compressed;
 	int			unzipped_len = -1;
+	ssize_t			ecc_notice_size = 0;
 
 	if (!psi)
 		return;
@@ -536,7 +731,7 @@ void pstore_get_records(int quiet)
 		goto out;
 
 	while ((size = psi->read(&id, &type, &count, &time, &buf, &compressed,
-				psi)) > 0) {
+				 &ecc_notice_size, psi)) > 0) {
 		if (compressed && (type == PSTORE_TYPE_DMESG)) {
 			if (big_oops_buf)
 				unzipped_len = pstore_decompress(buf,
@@ -544,6 +739,9 @@ void pstore_get_records(int quiet)
 							big_oops_buf_sz);
 
 			if (unzipped_len > 0) {
+				if (ecc_notice_size)
+					memcpy(big_oops_buf + unzipped_len,
+					       buf + size, ecc_notice_size);
 				kfree(buf);
 				buf = big_oops_buf;
 				size = unzipped_len;
@@ -555,7 +753,8 @@ void pstore_get_records(int quiet)
 			}
 		}
 		rc = pstore_mkfile(type, psi->name, id, count, buf,
-				  compressed, (size_t)size, time, psi);
+				   compressed, size + ecc_notice_size,
+				   time, psi);
 		if (unzipped_len < 0) {
 			/* Free buffer other than big oops */
 			kfree(buf);
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index bd9812e83461..47516a794011 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -34,6 +34,8 @@
 #include <linux/slab.h>
 #include <linux/compiler.h>
 #include <linux/pstore_ram.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #define RAMOOPS_KERNMSG_HDR "===="
 #define MIN_MEM_SIZE 4096UL
@@ -181,10 +183,10 @@ static bool prz_ok(struct persistent_ram_zone *prz)
 static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 				   int *count, struct timespec *time,
 				   char **buf, bool *compressed,
+				   ssize_t *ecc_notice_size,
 				   struct pstore_info *psi)
 {
 	ssize_t size;
-	ssize_t ecc_notice_size;
 	struct ramoops_context *cxt = psi->data;
 	struct persistent_ram_zone *prz = NULL;
 	int header_length = 0;
@@ -229,16 +231,16 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 	size = persistent_ram_old_size(prz) - header_length;
 
 	/* ECC correction notice */
-	ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0);
+	*ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0);
 
-	*buf = kmalloc(size + ecc_notice_size + 1, GFP_KERNEL);
+	*buf = kmalloc(size + *ecc_notice_size + 1, GFP_KERNEL);
 	if (*buf == NULL)
 		return -ENOMEM;
 
 	memcpy(*buf, (char *)persistent_ram_old(prz) + header_length, size);
-	persistent_ram_ecc_string(prz, *buf + size, ecc_notice_size + 1);
+	persistent_ram_ecc_string(prz, *buf + size, *ecc_notice_size + 1);
 
-	return size + ecc_notice_size;
+	return size;
 }
 
 static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz,
@@ -458,15 +460,98 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
 	return 0;
 }
 
+static int ramoops_parse_dt_size(struct platform_device *pdev,
+				 const char *propname, u32 *value)
+{
+	u32 val32 = 0;
+	int ret;
+
+	ret = of_property_read_u32(pdev->dev.of_node, propname, &val32);
+	if (ret < 0 && ret != -EINVAL) {
+		dev_err(&pdev->dev, "failed to parse property %s: %d\n",
+			propname, ret);
+		return ret;
+	}
+
+	if (val32 > INT_MAX) {
+		dev_err(&pdev->dev, "%s %u > INT_MAX\n", propname, val32);
+		return -EOVERFLOW;
+	}
+
+	*value = val32;
+	return 0;
+}
+
+static int ramoops_parse_dt(struct platform_device *pdev,
+			    struct ramoops_platform_data *pdata)
+{
+	struct device_node *of_node = pdev->dev.of_node;
+	struct device_node *mem_region;
+	struct resource res;
+	u32 value;
+	int ret;
+
+	dev_dbg(&pdev->dev, "using Device Tree\n");
+
+	mem_region = of_parse_phandle(of_node, "memory-region", 0);
+	if (!mem_region) {
+		dev_err(&pdev->dev, "no memory-region phandle\n");
+		return -ENODEV;
+	}
+
+	ret = of_address_to_resource(mem_region, 0, &res);
+	of_node_put(mem_region);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"failed to translate memory-region to resource: %d\n",
+			ret);
+		return ret;
+	}
+
+	pdata->mem_size = resource_size(&res);
+	pdata->mem_address = res.start;
+	pdata->mem_type = of_property_read_bool(of_node, "unbuffered");
+	pdata->dump_oops = !of_property_read_bool(of_node, "no-dump-oops");
+
+#define parse_size(name, field) {					\
+		ret = ramoops_parse_dt_size(pdev, name, &value);	\
+		if (ret < 0)						\
+			return ret;					\
+		field = value;						\
+	}
+
+	parse_size("record-size", pdata->record_size);
+	parse_size("console-size", pdata->console_size);
+	parse_size("ftrace-size", pdata->ftrace_size);
+	parse_size("pmsg-size", pdata->pmsg_size);
+	parse_size("ecc-size", pdata->ecc_info.ecc_size);
+
+#undef parse_size
+
+	return 0;
+}
+
 static int ramoops_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct ramoops_platform_data *pdata = pdev->dev.platform_data;
+	struct ramoops_platform_data *pdata = dev->platform_data;
 	struct ramoops_context *cxt = &oops_cxt;
 	size_t dump_mem_sz;
 	phys_addr_t paddr;
 	int err = -EINVAL;
 
+	if (dev_of_node(dev) && !pdata) {
+		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata) {
+			err = -ENOMEM;
+			goto fail_out;
+		}
+
+		err = ramoops_parse_dt(pdev, pdata);
+		if (err < 0)
+			goto fail_out;
+	}
+
 	/* Only a single ramoops area allowed at a time, so fail extra
 	 * probes.
 	 */
@@ -596,11 +681,17 @@ static int ramoops_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id dt_match[] = {
+	{ .compatible = "ramoops" },
+	{}
+};
+
 static struct platform_driver ramoops_driver = {
 	.probe		= ramoops_probe,
 	.remove		= ramoops_remove,
 	.driver		= {
-		.name	= "ramoops",
+		.name		= "ramoops",
+		.of_match_table	= dt_match,
 	},
 };
 
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 825455d3e4ba..c2c59f9ff04b 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2668,7 +2668,7 @@ static int reiserfs_write_full_page(struct page *page,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(WRITE, bh);
+			submit_bh(REQ_OP_WRITE, 0, bh);
 			nr++;
 		}
 		put_bh(bh);
@@ -2728,7 +2728,7 @@ fail:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh(WRITE, bh);
+			submit_bh(REQ_OP_WRITE, 0, bh);
 			nr++;
 		}
 		put_bh(bh);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 2ace90e981f0..bc2dde2423c2 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -652,7 +652,7 @@ static void submit_logged_buffer(struct buffer_head *bh)
 		BUG();
 	if (!buffer_uptodate(bh))
 		BUG();
-	submit_bh(WRITE, bh);
+	submit_bh(REQ_OP_WRITE, 0, bh);
 }
 
 static void submit_ordered_buffer(struct buffer_head *bh)
@@ -662,7 +662,7 @@ static void submit_ordered_buffer(struct buffer_head *bh)
 	clear_buffer_dirty(bh);
 	if (!buffer_uptodate(bh))
 		BUG();
-	submit_bh(WRITE, bh);
+	submit_bh(REQ_OP_WRITE, 0, bh);
 }
 
 #define CHUNK_SIZE 32
@@ -870,7 +870,7 @@ loop_next:
 		 */
 		if (buffer_dirty(bh) && unlikely(bh->b_page->mapping == NULL)) {
 			spin_unlock(lock);
-			ll_rw_block(WRITE, 1, &bh);
+			ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
 			spin_lock(lock);
 		}
 		put_bh(bh);
@@ -1057,7 +1057,7 @@ static int flush_commit_list(struct super_block *s,
 		if (tbh) {
 			if (buffer_dirty(tbh)) {
 		            depth = reiserfs_write_unlock_nested(s);
-			    ll_rw_block(WRITE, 1, &tbh);
+			    ll_rw_block(REQ_OP_WRITE, 0, 1, &tbh);
 			    reiserfs_write_lock_nested(s, depth);
 			}
 			put_bh(tbh) ;
@@ -2244,7 +2244,7 @@ abort_replay:
 		}
 	}
 	/* read in the log blocks, memcpy to the corresponding real block */
-	ll_rw_block(READ, get_desc_trans_len(desc), log_blocks);
+	ll_rw_block(REQ_OP_READ, 0, get_desc_trans_len(desc), log_blocks);
 	for (i = 0; i < get_desc_trans_len(desc); i++) {
 
 		wait_on_buffer(log_blocks[i]);
@@ -2269,7 +2269,7 @@ abort_replay:
 	/* flush out the real blocks */
 	for (i = 0; i < get_desc_trans_len(desc); i++) {
 		set_buffer_dirty(real_blocks[i]);
-		write_dirty_buffer(real_blocks[i], WRITE);
+		write_dirty_buffer(real_blocks[i], 0);
 	}
 	for (i = 0; i < get_desc_trans_len(desc); i++) {
 		wait_on_buffer(real_blocks[i]);
@@ -2346,7 +2346,7 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev,
 		} else
 			bhlist[j++] = bh;
 	}
-	ll_rw_block(READ, j, bhlist);
+	ll_rw_block(REQ_OP_READ, 0, j, bhlist);
 	for (i = 1; i < j; i++)
 		brelse(bhlist[i]);
 	bh = bhlist[0];
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 5feacd689241..4032d1e87c8f 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -551,7 +551,7 @@ static int search_by_key_reada(struct super_block *s,
 		if (!buffer_uptodate(bh[j])) {
 			if (depth == -1)
 				depth = reiserfs_write_unlock_nested(s);
-			ll_rw_block(READA, 1, bh + j);
+			ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, bh + j);
 		}
 		brelse(bh[j]);
 	}
@@ -660,7 +660,7 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,
 			if (!buffer_uptodate(bh) && depth == -1)
 				depth = reiserfs_write_unlock_nested(sb);
 
-			ll_rw_block(READ, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 			wait_on_buffer(bh);
 
 			if (depth != -1)
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index c72c16c5a60f..7a4a85a6821e 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1666,7 +1666,7 @@ static int read_super_block(struct super_block *s, int offset)
 /* after journal replay, reread all bitmap and super blocks */
 static int reread_meta_blocks(struct super_block *s)
 {
-	ll_rw_block(READ, 1, &SB_BUFFER_WITH_SB(s));
+	ll_rw_block(REQ_OP_READ, 0, 1, &SB_BUFFER_WITH_SB(s));
 	wait_on_buffer(SB_BUFFER_WITH_SB(s));
 	if (!buffer_uptodate(SB_BUFFER_WITH_SB(s))) {
 		reiserfs_warning(s, "reiserfs-2504", "error reading the super");
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 2c2618410d51..ce62a380314f 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -124,7 +124,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 				goto block_release;
 			bytes += msblk->devblksize;
 		}
-		ll_rw_block(READ, b, bh);
+		ll_rw_block(REQ_OP_READ, 0, b, bh);
 	} else {
 		/*
 		 * Metadata block.
@@ -156,7 +156,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 				goto block_release;
 			bytes += msblk->devblksize;
 		}
-		ll_rw_block(READ, b - 1, bh + 1);
+		ll_rw_block(REQ_OP_READ, 0, b - 1, bh + 1);
 	}
 
 	for (i = 0; i < b; i++) {
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 4c5593abc553..aaec13c95253 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -113,7 +113,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 					brelse(tmp);
 			}
 			if (num) {
-				ll_rw_block(READA, num, bha);
+				ll_rw_block(REQ_OP_READ, REQ_RAHEAD, num, bha);
 				for (i = 0; i < num; i++)
 					brelse(bha[i]);
 			}
diff --git a/fs/udf/directory.c b/fs/udf/directory.c
index c763fda257bf..988d5352bdb8 100644
--- a/fs/udf/directory.c
+++ b/fs/udf/directory.c
@@ -87,7 +87,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos,
 					brelse(tmp);
 			}
 			if (num) {
-				ll_rw_block(READA, num, bha);
+				ll_rw_block(REQ_OP_READ, REQ_RAHEAD, num, bha);
 				for (i = 0; i < num; i++)
 					brelse(bha[i]);
 			}
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index f323aff740ef..55aa587bbc38 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1199,7 +1199,7 @@ struct buffer_head *udf_bread(struct inode *inode, int block,
 	if (buffer_uptodate(bh))
 		return bh;
 
-	ll_rw_block(READ, 1, &bh);
+	ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 0447b949c7f5..67e085d591d8 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -292,7 +292,7 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg,
 			if (!buffer_mapped(bh))
 					map_bh(bh, inode->i_sb, oldb + pos);
 			if (!buffer_uptodate(bh)) {
-				ll_rw_block(READ, 1, &bh);
+				ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 				wait_on_buffer(bh);
 				if (!buffer_uptodate(bh)) {
 					ufs_error(inode->i_sb, __func__,
diff --git a/fs/ufs/util.c b/fs/ufs/util.c
index a409e3e7827a..f41ad0a6106f 100644
--- a/fs/ufs/util.c
+++ b/fs/ufs/util.c
@@ -118,7 +118,7 @@ void ubh_sync_block(struct ufs_buffer_head *ubh)
 		unsigned i;
 
 		for (i = 0; i < ubh->count; i++)
-			write_dirty_buffer(ubh->bh[i], WRITE);
+			write_dirty_buffer(ubh->bh[i], 0);
 
 		for (i = 0; i < ubh->count; i++)
 			wait_on_buffer(ubh->bh[i]);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4c463b99fe57..87d2b215cbbd 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -438,7 +438,8 @@ xfs_submit_ioend(
 
 	ioend->io_bio->bi_private = ioend;
 	ioend->io_bio->bi_end_io = xfs_end_bio;
-
+	bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE,
+			 (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0);
 	/*
 	 * If we are failing the IO now, just mark the ioend with an
 	 * error and finish it. This will run IO completion immediately
@@ -451,8 +452,7 @@ xfs_submit_ioend(
 		return status;
 	}
 
-	submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
-		   ioend->io_bio);
+	submit_bio(ioend->io_bio);
 	return 0;
 }
 
@@ -510,8 +510,9 @@ xfs_chain_bio(
 
 	bio_chain(ioend->io_bio, new);
 	bio_get(ioend->io_bio);		/* for xfs_destroy_ioend */
-	submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
-		   ioend->io_bio);
+	bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE,
+			  (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0);
+	submit_bio(ioend->io_bio);
 	ioend->io_bio = new;
 }
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e71cfbd5acb3..a87a0d5477bd 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1127,7 +1127,8 @@ xfs_buf_ioapply_map(
 	int		map,
 	int		*buf_offset,
 	int		*count,
-	int		rw)
+	int		op,
+	int		op_flags)
 {
 	int		page_index;
 	int		total_nr_pages = bp->b_page_count;
@@ -1157,16 +1158,14 @@ xfs_buf_ioapply_map(
 
 next_chunk:
 	atomic_inc(&bp->b_io_remaining);
-	nr_pages = BIO_MAX_SECTORS >> (PAGE_SHIFT - BBSHIFT);
-	if (nr_pages > total_nr_pages)
-		nr_pages = total_nr_pages;
+	nr_pages = min(total_nr_pages, BIO_MAX_PAGES);
 
 	bio = bio_alloc(GFP_NOIO, nr_pages);
 	bio->bi_bdev = bp->b_target->bt_bdev;
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_end_io = xfs_buf_bio_end_io;
 	bio->bi_private = bp;
-
+	bio_set_op_attrs(bio, op, op_flags);
 
 	for (; size && nr_pages; nr_pages--, page_index++) {
 		int	rbytes, nbytes = PAGE_SIZE - offset;
@@ -1190,7 +1189,7 @@ next_chunk:
 			flush_kernel_vmap_range(bp->b_addr,
 						xfs_buf_vmap_len(bp));
 		}
-		submit_bio(rw, bio);
+		submit_bio(bio);
 		if (size)
 			goto next_chunk;
 	} else {
@@ -1210,7 +1209,8 @@ _xfs_buf_ioapply(
 	struct xfs_buf	*bp)
 {
 	struct blk_plug	plug;
-	int		rw;
+	int		op;
+	int		op_flags = 0;
 	int		offset;
 	int		size;
 	int		i;
@@ -1229,14 +1229,13 @@ _xfs_buf_ioapply(
 		bp->b_ioend_wq = bp->b_target->bt_mount->m_buf_workqueue;
 
 	if (bp->b_flags & XBF_WRITE) {
+		op = REQ_OP_WRITE;
 		if (bp->b_flags & XBF_SYNCIO)
-			rw = WRITE_SYNC;
-		else
-			rw = WRITE;
+			op_flags = WRITE_SYNC;
 		if (bp->b_flags & XBF_FUA)
-			rw |= REQ_FUA;
+			op_flags |= REQ_FUA;
 		if (bp->b_flags & XBF_FLUSH)
-			rw |= REQ_FLUSH;
+			op_flags |= REQ_PREFLUSH;
 
 		/*
 		 * Run the write verifier callback function if it exists. If
@@ -1266,13 +1265,14 @@ _xfs_buf_ioapply(
 			}
 		}
 	} else if (bp->b_flags & XBF_READ_AHEAD) {
-		rw = READA;
+		op = REQ_OP_READ;
+		op_flags = REQ_RAHEAD;
 	} else {
-		rw = READ;
+		op = REQ_OP_READ;
 	}
 
 	/* we only use the buffer cache for meta-data */
-	rw |= REQ_META;
+	op_flags |= REQ_META;
 
 	/*
 	 * Walk all the vectors issuing IO on them. Set up the initial offset
@@ -1284,7 +1284,7 @@ _xfs_buf_ioapply(
 	size = BBTOB(bp->b_io_length);
 	blk_start_plug(&plug);
 	for (i = 0; i < bp->b_map_count; i++) {
-		xfs_buf_ioapply_map(bp, i, &offset, &size, rw);
+		xfs_buf_ioapply_map(bp, i, &offset, &size, op, op_flags);
 		if (bp->b_error)
 			break;
 		if (size <= 0)
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index 94a37cd7fbda..d4b72944ccda 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -15,6 +15,10 @@ extern int pxm_to_node(int);
 extern int node_to_pxm(int);
 extern int acpi_map_pxm_to_node(int);
 extern unsigned char acpi_srat_revision;
+extern int acpi_numa __initdata;
+
+extern void bad_srat(void);
+extern int srat_disabled(void);
 
 #endif				/* CONFIG_ACPI_NUMA */
 #endif				/* __ACP_NUMA_H */
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index dad8af3ebeb5..284965cbc9af 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -15,10 +15,9 @@
 #define _CPPC_ACPI_H
 
 #include <linux/acpi.h>
-#include <linux/mailbox_controller.h>
-#include <linux/mailbox_client.h>
 #include <linux/types.h>
 
+#include <acpi/pcc.h>
 #include <acpi/processor.h>
 
 /* Only support CPPCv2 for now. */
@@ -130,8 +129,4 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
 extern int acpi_get_psd_map(struct cpudata **);
 
-/* Methods to interact with the PCC mailbox controller. */
-extern struct mbox_chan *
-	pcc_mbox_request_channel(struct mbox_client *, unsigned int);
-
 #endif /* _CPPC_ACPI_H*/
diff --git a/include/acpi/pcc.h b/include/acpi/pcc.h
new file mode 100644
index 000000000000..17a940a14477
--- /dev/null
+++ b/include/acpi/pcc.h
@@ -0,0 +1,29 @@
+/*
+ * PCC (Platform Communications Channel) methods
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#ifndef _PCC_H
+#define _PCC_H
+
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox_client.h>
+
+#ifdef CONFIG_PCC
+extern struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
+						  int subspace_id);
+extern void pcc_mbox_free_channel(struct mbox_chan *chan);
+#else
+static inline struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
+							 int subspace_id)
+{
+	return NULL;
+}
+static inline void pcc_mbox_free_channel(struct mbox_chan *chan) { }
+#endif
+
+#endif /* _PCC_H */
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 45c2d6528829..93b61b1f2beb 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -73,6 +73,10 @@
 #define ACPI_DEBUGGER
 #endif
 
+#ifdef CONFIG_ACPI_DEBUG
+#define ACPI_MUTEX_DEBUG
+#endif
+
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 6f1805dd5d3c..bfe6b2e10f3a 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -39,6 +39,7 @@
 #define ACPI_CSTATE_SYSTEMIO	0
 #define ACPI_CSTATE_FFH		1
 #define ACPI_CSTATE_HALT	2
+#define ACPI_CSTATE_INTEGER	3
 
 #define ACPI_CX_DESC_LEN	32
 
@@ -67,9 +68,25 @@ struct acpi_processor_cx {
 	char desc[ACPI_CX_DESC_LEN];
 };
 
+struct acpi_lpi_state {
+	u32 min_residency;
+	u32 wake_latency; /* worst case */
+	u32 flags;
+	u32 arch_flags;
+	u32 res_cnt_freq;
+	u32 enable_parent_state;
+	u64 address;
+	u8 index;
+	u8 entry_method;
+	char desc[ACPI_CX_DESC_LEN];
+};
+
 struct acpi_processor_power {
 	int count;
-	struct acpi_processor_cx states[ACPI_PROCESSOR_MAX_POWER];
+	union {
+		struct acpi_processor_cx states[ACPI_PROCESSOR_MAX_POWER];
+		struct acpi_lpi_state lpi_states[ACPI_PROCESSOR_MAX_POWER];
+	};
 	int timer_broadcast_on_state;
 };
 
@@ -189,6 +206,7 @@ struct acpi_processor_flags {
 	u8 bm_control:1;
 	u8 bm_check:1;
 	u8 has_cst:1;
+	u8 has_lpi:1;
 	u8 power_setup_done:1;
 	u8 bm_rld_set:1;
 	u8 need_hotplug_init:1;
@@ -242,7 +260,7 @@ extern int acpi_processor_get_performance_info(struct acpi_processor *pr);
 DECLARE_PER_CPU(struct acpi_processor *, processors);
 extern struct acpi_processor_errata errata;
 
-#ifdef ARCH_HAS_POWER_INIT
+#if defined(ARCH_HAS_POWER_INIT) && defined(CONFIG_ACPI_PROCESSOR_CSTATE)
 void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 					unsigned int cpu);
 int acpi_processor_ffh_cstate_probe(unsigned int cpu,
@@ -309,6 +327,7 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 
 /* in processor_core.c */
 phys_cpuid_t acpi_get_phys_id(acpi_handle, int type, u32 acpi_id);
+phys_cpuid_t acpi_map_madt_entry(u32 acpi_id);
 int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id);
 int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
 
@@ -371,7 +390,7 @@ extern struct cpuidle_driver acpi_idle_driver;
 #ifdef CONFIG_ACPI_PROCESSOR_IDLE
 int acpi_processor_power_init(struct acpi_processor *pr);
 int acpi_processor_power_exit(struct acpi_processor *pr);
-int acpi_processor_cst_has_changed(struct acpi_processor *pr);
+int acpi_processor_power_state_has_changed(struct acpi_processor *pr);
 int acpi_processor_hotplug(struct acpi_processor *pr);
 #else
 static inline int acpi_processor_power_init(struct acpi_processor *pr)
@@ -384,7 +403,7 @@ static inline int acpi_processor_power_exit(struct acpi_processor *pr)
 	return -ENODEV;
 }
 
-static inline int acpi_processor_cst_has_changed(struct acpi_processor *pr)
+static inline int acpi_processor_power_state_has_changed(struct acpi_processor *pr)
 {
 	return -ENODEV;
 }
diff --git a/include/acpi/video.h b/include/acpi/video.h
index 5731ccb42585..4536bd345ab4 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -54,7 +54,7 @@ extern int acpi_video_get_levels(struct acpi_device *device,
 				 struct acpi_video_device_brightness **dev_br,
 				 int *pmax_level);
 #else
-static inline int acpi_video_register(void) { return 0; }
+static inline int acpi_video_register(void) { return -ENODEV; }
 static inline void acpi_video_unregister(void) { return; }
 static inline int acpi_video_get_edid(struct acpi_device *device, int type,
 				      int device_id, void **edid)
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 002b81f6f2bc..7ef015eb3403 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -585,6 +585,16 @@ static inline u32 ioread32(const volatile void __iomem *addr)
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef ioread64
+#define ioread64 ioread64
+static inline u64 ioread64(const volatile void __iomem *addr)
+{
+	return readq(addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef iowrite8
 #define iowrite8 iowrite8
 static inline void iowrite8(u8 value, volatile void __iomem *addr)
@@ -609,11 +619,21 @@ static inline void iowrite32(u32 value, volatile void __iomem *addr)
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef iowrite64
+#define iowrite64 iowrite64
+static inline void iowrite64(u64 value, volatile void __iomem *addr)
+{
+	writeq(value, addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef ioread16be
 #define ioread16be ioread16be
 static inline u16 ioread16be(const volatile void __iomem *addr)
 {
-	return __be16_to_cpu(__raw_readw(addr));
+	return swab16(readw(addr));
 }
 #endif
 
@@ -621,15 +641,25 @@ static inline u16 ioread16be(const volatile void __iomem *addr)
 #define ioread32be ioread32be
 static inline u32 ioread32be(const volatile void __iomem *addr)
 {
-	return __be32_to_cpu(__raw_readl(addr));
+	return swab32(readl(addr));
+}
+#endif
+
+#ifdef CONFIG_64BIT
+#ifndef ioread64be
+#define ioread64be ioread64be
+static inline u64 ioread64be(const volatile void __iomem *addr)
+{
+	return swab64(readq(addr));
 }
 #endif
+#endif /* CONFIG_64BIT */
 
 #ifndef iowrite16be
 #define iowrite16be iowrite16be
 static inline void iowrite16be(u16 value, void volatile __iomem *addr)
 {
-	__raw_writew(__cpu_to_be16(value), addr);
+	writew(swab16(value), addr);
 }
 #endif
 
@@ -637,10 +667,20 @@ static inline void iowrite16be(u16 value, void volatile __iomem *addr)
 #define iowrite32be iowrite32be
 static inline void iowrite32be(u32 value, volatile void __iomem *addr)
 {
-	__raw_writel(__cpu_to_be32(value), addr);
+	writel(swab32(value), addr);
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef iowrite64be
+#define iowrite64be iowrite64be
+static inline void iowrite64be(u64 value, volatile void __iomem *addr)
+{
+	writeq(swab64(value), addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef ioread8_rep
 #define ioread8_rep ioread8_rep
 static inline void ioread8_rep(const volatile void __iomem *addr, void *buffer,
@@ -668,6 +708,17 @@ static inline void ioread32_rep(const volatile void __iomem *addr,
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef ioread64_rep
+#define ioread64_rep ioread64_rep
+static inline void ioread64_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsq(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef iowrite8_rep
 #define iowrite8_rep iowrite8_rep
 static inline void iowrite8_rep(volatile void __iomem *addr,
@@ -697,6 +748,18 @@ static inline void iowrite32_rep(volatile void __iomem *addr,
 	writesl(addr, buffer, count);
 }
 #endif
+
+#ifdef CONFIG_64BIT
+#ifndef iowrite64_rep
+#define iowrite64_rep iowrite64_rep
+static inline void iowrite64_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesq(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_64BIT */
 #endif /* CONFIG_GENERIC_IOMAP */
 
 #ifdef __KERNEL__
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index d8f8622fa044..650fede33c25 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -30,12 +30,20 @@ extern unsigned int ioread16(void __iomem *);
 extern unsigned int ioread16be(void __iomem *);
 extern unsigned int ioread32(void __iomem *);
 extern unsigned int ioread32be(void __iomem *);
+#ifdef CONFIG_64BIT
+extern u64 ioread64(void __iomem *);
+extern u64 ioread64be(void __iomem *);
+#endif
 
 extern void iowrite8(u8, void __iomem *);
 extern void iowrite16(u16, void __iomem *);
 extern void iowrite16be(u16, void __iomem *);
 extern void iowrite32(u32, void __iomem *);
 extern void iowrite32be(u32, void __iomem *);
+#ifdef CONFIG_64BIT
+extern void iowrite64(u64, void __iomem *);
+extern void iowrite64be(u64, void __iomem *);
+#endif
 
 /*
  * "string" versions of the above. Note that they
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 081d0f258d4c..54643d1f5af4 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -250,6 +250,14 @@
 	VMLINUX_SYMBOL(__end_init_task) = .;
 
 /*
+ * Allow architectures to handle ro_after_init data on their
+ * own by defining an empty RO_AFTER_INIT_DATA.
+ */
+#ifndef RO_AFTER_INIT_DATA
+#define RO_AFTER_INIT_DATA *(.data..ro_after_init)
+#endif
+
+/*
  * Read only Data
  */
 #define RO_DATA_SECTION(align)						\
@@ -257,7 +265,7 @@
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start_rodata) = .;			\
 		*(.rodata) *(.rodata.*)					\
-		*(.data..ro_after_init)	/* Read only after init */	\
+		RO_AFTER_INIT_DATA	/* Read only after init */	\
 		*(__vermagic)		/* Kernel version magic */	\
 		. = ALIGN(8);						\
 		VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .;		\
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 75174f80a106..12f84327ca36 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -112,11 +112,12 @@ struct aead_request {
  *		 supplied during the decryption operation. This function is also
  *		 responsible for checking the authentication tag size for
  *		 validity.
- * @setkey: see struct ablkcipher_alg
- * @encrypt: see struct ablkcipher_alg
- * @decrypt: see struct ablkcipher_alg
- * @geniv: see struct ablkcipher_alg
- * @ivsize: see struct ablkcipher_alg
+ * @setkey: see struct skcipher_alg
+ * @encrypt: see struct skcipher_alg
+ * @decrypt: see struct skcipher_alg
+ * @geniv: see struct skcipher_alg
+ * @ivsize: see struct skcipher_alg
+ * @chunksize: see struct skcipher_alg
  * @init: Initialize the cryptographic transformation object. This function
  *	  is used to initialize the cryptographic transformation object.
  *	  This function is called only once at the instantiation time, right
@@ -145,6 +146,7 @@ struct aead_alg {
 
 	unsigned int ivsize;
 	unsigned int maxauthsize;
+	unsigned int chunksize;
 
 	struct crypto_alg base;
 };
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index eeafd21afb44..8637cdfe382a 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -244,6 +244,8 @@ static inline struct crypto_alg *crypto_attr_alg(struct rtattr *rta,
 }
 
 int crypto_attr_u32(struct rtattr *rta, u32 *num);
+int crypto_inst_setname(struct crypto_instance *inst, const char *name,
+			struct crypto_alg *alg);
 void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg,
 			     unsigned int head);
 struct crypto_instance *crypto_alloc_instance(const char *name,
@@ -440,8 +442,10 @@ static inline int crypto_memneq(const void *a, const void *b, size_t size)
 
 static inline void crypto_yield(u32 flags)
 {
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PREEMPT_VOLUNTARY)
 	if (flags & CRYPTO_TFM_REQ_MAY_SLEEP)
 		cond_resched();
+#endif
 }
 
 #endif	/* _CRYPTO_ALGAPI_H */
diff --git a/include/crypto/cryptd.h b/include/crypto/cryptd.h
index 1547f540c920..bc792d5a9e88 100644
--- a/include/crypto/cryptd.h
+++ b/include/crypto/cryptd.h
@@ -31,6 +31,7 @@ static inline struct cryptd_ablkcipher *__cryptd_ablkcipher_cast(
 struct cryptd_ablkcipher *cryptd_alloc_ablkcipher(const char *alg_name,
 						  u32 type, u32 mask);
 struct crypto_blkcipher *cryptd_ablkcipher_child(struct cryptd_ablkcipher *tfm);
+bool cryptd_ablkcipher_queued(struct cryptd_ablkcipher *tfm);
 void cryptd_free_ablkcipher(struct cryptd_ablkcipher *tfm);
 
 struct cryptd_ahash {
@@ -48,6 +49,8 @@ struct cryptd_ahash *cryptd_alloc_ahash(const char *alg_name,
 					u32 type, u32 mask);
 struct crypto_shash *cryptd_ahash_child(struct cryptd_ahash *tfm);
 struct shash_desc *cryptd_shash_desc(struct ahash_request *req);
+/* Must be called without moving CPUs. */
+bool cryptd_ahash_queued(struct cryptd_ahash *tfm);
 void cryptd_free_ahash(struct cryptd_ahash *tfm);
 
 struct cryptd_aead {
@@ -64,6 +67,8 @@ struct cryptd_aead *cryptd_alloc_aead(const char *alg_name,
 					  u32 type, u32 mask);
 
 struct crypto_aead *cryptd_aead_child(struct cryptd_aead *tfm);
+/* Must be called without moving CPUs. */
+bool cryptd_aead_queued(struct cryptd_aead *tfm);
 
 void cryptd_free_aead(struct cryptd_aead *tfm);
 
diff --git a/include/crypto/dh.h b/include/crypto/dh.h
new file mode 100644
index 000000000000..5102a8f282e6
--- /dev/null
+++ b/include/crypto/dh.h
@@ -0,0 +1,29 @@
+/*
+ * Diffie-Hellman secret to be used with kpp API along with helper functions
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_DH_
+#define _CRYPTO_DH_
+
+struct dh {
+	void *key;
+	void *p;
+	void *g;
+	unsigned int key_size;
+	unsigned int p_size;
+	unsigned int g_size;
+};
+
+int crypto_dh_key_len(const struct dh *params);
+int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params);
+int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params);
+
+#endif
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index d961b2b16f55..61580b19f9f6 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -43,6 +43,7 @@
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 #include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
 #include <linux/slab.h>
@@ -107,14 +108,25 @@ struct drbg_test_data {
 struct drbg_state {
 	struct mutex drbg_mutex;	/* lock around DRBG */
 	unsigned char *V;	/* internal state 10.1.1.1 1a) */
+	unsigned char *Vbuf;
 	/* hash: static value 10.1.1.1 1b) hmac / ctr: key */
 	unsigned char *C;
+	unsigned char *Cbuf;
 	/* Number of RNG requests since last reseed -- 10.1.1.1 1c) */
 	size_t reseed_ctr;
 	size_t reseed_threshold;
 	 /* some memory the DRBG can use for its operation */
 	unsigned char *scratchpad;
+	unsigned char *scratchpadbuf;
 	void *priv_data;	/* Cipher handle */
+
+	struct crypto_skcipher *ctr_handle;	/* CTR mode cipher handle */
+	struct skcipher_request *ctr_req;	/* CTR mode request handle */
+	__u8 *ctr_null_value_buf;		/* CTR mode unaligned buffer */
+	__u8 *ctr_null_value;			/* CTR mode aligned zero buf */
+	struct completion ctr_completion;	/* CTR mode async handler */
+	int ctr_async_err;			/* CTR mode async error */
+
 	bool seeded;		/* DRBG fully seeded? */
 	bool pr;		/* Prediction resistance enabled? */
 	struct work_struct seed_work;	/* asynchronous seeding support */
diff --git a/include/crypto/ecdh.h b/include/crypto/ecdh.h
new file mode 100644
index 000000000000..84bad548d194
--- /dev/null
+++ b/include/crypto/ecdh.h
@@ -0,0 +1,30 @@
+/*
+ * ECDH params to be used with kpp API
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_ECDH_
+#define _CRYPTO_ECDH_
+
+/* Curves IDs */
+#define ECC_CURVE_NIST_P192	0x0001
+#define ECC_CURVE_NIST_P256	0x0002
+
+struct ecdh {
+	unsigned short curve_id;
+	char *key;
+	unsigned short key_size;
+};
+
+int crypto_ecdh_key_len(const struct ecdh *params);
+int crypto_ecdh_encode_key(char *buf, unsigned int len, const struct ecdh *p);
+int crypto_ecdh_decode_key(const char *buf, unsigned int len, struct ecdh *p);
+
+#endif
diff --git a/include/crypto/internal/aead.h b/include/crypto/internal/aead.h
index da3864991d4c..6ad8e31d3868 100644
--- a/include/crypto/internal/aead.h
+++ b/include/crypto/internal/aead.h
@@ -159,6 +159,27 @@ static inline struct aead_request *aead_get_backlog(struct aead_queue *queue)
 	return req ? container_of(req, struct aead_request, base) : NULL;
 }
 
+static inline unsigned int crypto_aead_alg_chunksize(struct aead_alg *alg)
+{
+	return alg->chunksize;
+}
+
+/**
+ * crypto_aead_chunksize() - obtain chunk size
+ * @tfm: cipher handle
+ *
+ * The block size is set to one for ciphers such as CCM.  However,
+ * you still need to provide incremental updates in multiples of
+ * the underlying block size as the IV does not have sub-block
+ * granularity.  This is known in this API as the chunk size.
+ *
+ * Return: chunk size in bytes
+ */
+static inline unsigned int crypto_aead_chunksize(struct crypto_aead *tfm)
+{
+	return crypto_aead_alg_chunksize(crypto_aead_alg(tfm));
+}
+
 int crypto_register_aead(struct aead_alg *alg);
 void crypto_unregister_aead(struct aead_alg *alg);
 int crypto_register_aeads(struct aead_alg *algs, int count);
diff --git a/include/crypto/internal/geniv.h b/include/crypto/internal/geniv.h
index 59333635e712..2bcfb931bc5b 100644
--- a/include/crypto/internal/geniv.h
+++ b/include/crypto/internal/geniv.h
@@ -20,7 +20,7 @@
 struct aead_geniv_ctx {
 	spinlock_t lock;
 	struct crypto_aead *child;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *sknull;
 	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
 };
 
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 49dae16f8929..1d4f365d8f03 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -114,14 +114,10 @@ int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc);
 
-int shash_ahash_mcryptd_update(struct ahash_request *req,
-			       struct shash_desc *desc);
-int shash_ahash_mcryptd_final(struct ahash_request *req,
-			      struct shash_desc *desc);
-int shash_ahash_mcryptd_finup(struct ahash_request *req,
-			      struct shash_desc *desc);
-int shash_ahash_mcryptd_digest(struct ahash_request *req,
-			       struct shash_desc *desc);
+int ahash_mcryptd_update(struct ahash_request *desc);
+int ahash_mcryptd_final(struct ahash_request *desc);
+int ahash_mcryptd_finup(struct ahash_request *desc);
+int ahash_mcryptd_digest(struct ahash_request *desc);
 
 int crypto_init_shash_ops_async(struct crypto_tfm *tfm);
 
diff --git a/include/crypto/internal/kpp.h b/include/crypto/internal/kpp.h
new file mode 100644
index 000000000000..ad3acf3649be
--- /dev/null
+++ b/include/crypto/internal/kpp.h
@@ -0,0 +1,64 @@
+/*
+ * Key-agreement Protocol Primitives (KPP)
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_KPP_INT_H
+#define _CRYPTO_KPP_INT_H
+#include <crypto/kpp.h>
+#include <crypto/algapi.h>
+
+/*
+ * Transform internal helpers.
+ */
+static inline void *kpp_request_ctx(struct kpp_request *req)
+{
+	return req->__ctx;
+}
+
+static inline void *kpp_tfm_ctx(struct crypto_kpp *tfm)
+{
+	return tfm->base.__crt_ctx;
+}
+
+static inline void kpp_request_complete(struct kpp_request *req, int err)
+{
+	req->base.complete(&req->base, err);
+}
+
+static inline const char *kpp_alg_name(struct crypto_kpp *tfm)
+{
+	return crypto_kpp_tfm(tfm)->__crt_alg->cra_name;
+}
+
+/**
+ * crypto_register_kpp() -- Register key-agreement protocol primitives algorithm
+ *
+ * Function registers an implementation of a key-agreement protocol primitive
+ * algorithm
+ *
+ * @alg:	algorithm definition
+ *
+ * Return: zero on success; error code in case of error
+ */
+int crypto_register_kpp(struct kpp_alg *alg);
+
+/**
+ * crypto_unregister_kpp() -- Unregister key-agreement protocol primitive
+ * algorithm
+ *
+ * Function unregisters an implementation of a key-agreement protocol primitive
+ * algorithm
+ *
+ * @alg:	algorithm definition
+ */
+void crypto_unregister_kpp(struct kpp_alg *alg);
+
+#endif
diff --git a/include/crypto/internal/rsa.h b/include/crypto/internal/rsa.h
index c7585bdecbc2..9e8f1590de98 100644
--- a/include/crypto/internal/rsa.h
+++ b/include/crypto/internal/rsa.h
@@ -12,12 +12,44 @@
  */
 #ifndef _RSA_HELPER_
 #define _RSA_HELPER_
-#include <linux/mpi.h>
+#include <linux/types.h>
 
+/**
+ * rsa_key - RSA key structure
+ * @n           : RSA modulus raw byte stream
+ * @e           : RSA public exponent raw byte stream
+ * @d           : RSA private exponent raw byte stream
+ * @p           : RSA prime factor p of n raw byte stream
+ * @q           : RSA prime factor q of n raw byte stream
+ * @dp          : RSA exponent d mod (p - 1) raw byte stream
+ * @dq          : RSA exponent d mod (q - 1) raw byte stream
+ * @qinv        : RSA CRT coefficient q^(-1) mod p raw byte stream
+ * @n_sz        : length in bytes of RSA modulus n
+ * @e_sz        : length in bytes of RSA public exponent
+ * @d_sz        : length in bytes of RSA private exponent
+ * @p_sz        : length in bytes of p field
+ * @q_sz        : length in bytes of q field
+ * @dp_sz       : length in bytes of dp field
+ * @dq_sz       : length in bytes of dq field
+ * @qinv_sz     : length in bytes of qinv field
+ */
 struct rsa_key {
-	MPI n;
-	MPI e;
-	MPI d;
+	const u8 *n;
+	const u8 *e;
+	const u8 *d;
+	const u8 *p;
+	const u8 *q;
+	const u8 *dp;
+	const u8 *dq;
+	const u8 *qinv;
+	size_t n_sz;
+	size_t e_sz;
+	size_t d_sz;
+	size_t p_sz;
+	size_t q_sz;
+	size_t dp_sz;
+	size_t dq_sz;
+	size_t qinv_sz;
 };
 
 int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key,
@@ -26,7 +58,5 @@ int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key,
 int rsa_parse_priv_key(struct rsa_key *rsa_key, const void *key,
 		       unsigned int key_len);
 
-void rsa_free_key(struct rsa_key *rsa_key);
-
 extern struct crypto_template rsa_pkcs1pad_tmpl;
 #endif
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index 2cf7a61ece59..a21a95e1a375 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -19,12 +19,46 @@
 
 struct rtattr;
 
+struct skcipher_instance {
+	void (*free)(struct skcipher_instance *inst);
+	union {
+		struct {
+			char head[offsetof(struct skcipher_alg, base)];
+			struct crypto_instance base;
+		} s;
+		struct skcipher_alg alg;
+	};
+};
+
 struct crypto_skcipher_spawn {
 	struct crypto_spawn base;
 };
 
 extern const struct crypto_type crypto_givcipher_type;
 
+static inline struct crypto_instance *skcipher_crypto_instance(
+	struct skcipher_instance *inst)
+{
+	return &inst->s.base;
+}
+
+static inline struct skcipher_instance *skcipher_alg_instance(
+	struct crypto_skcipher *skcipher)
+{
+	return container_of(crypto_skcipher_alg(skcipher),
+			    struct skcipher_instance, alg);
+}
+
+static inline void *skcipher_instance_ctx(struct skcipher_instance *inst)
+{
+	return crypto_instance_ctx(skcipher_crypto_instance(inst));
+}
+
+static inline void skcipher_request_complete(struct skcipher_request *req, int err)
+{
+	req->base.complete(&req->base, err);
+}
+
 static inline void crypto_set_skcipher_spawn(
 	struct crypto_skcipher_spawn *spawn, struct crypto_instance *inst)
 {
@@ -34,6 +68,12 @@ static inline void crypto_set_skcipher_spawn(
 int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name,
 			 u32 type, u32 mask);
 
+static inline int crypto_grab_skcipher2(struct crypto_skcipher_spawn *spawn,
+					const char *name, u32 type, u32 mask)
+{
+	return crypto_grab_skcipher(spawn, name, type, mask);
+}
+
 struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask);
 
 static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn)
@@ -41,54 +81,42 @@ static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn)
 	crypto_drop_spawn(&spawn->base);
 }
 
-static inline struct crypto_alg *crypto_skcipher_spawn_alg(
+static inline struct skcipher_alg *crypto_skcipher_spawn_alg(
 	struct crypto_skcipher_spawn *spawn)
 {
-	return spawn->base.alg;
+	return container_of(spawn->base.alg, struct skcipher_alg, base);
 }
 
-static inline struct crypto_ablkcipher *crypto_spawn_skcipher(
+static inline struct skcipher_alg *crypto_spawn_skcipher_alg(
 	struct crypto_skcipher_spawn *spawn)
 {
-	return __crypto_ablkcipher_cast(
-		crypto_spawn_tfm(&spawn->base, crypto_skcipher_type(0),
-				 crypto_skcipher_mask(0)));
+	return crypto_skcipher_spawn_alg(spawn);
 }
 
-int skcipher_null_givencrypt(struct skcipher_givcrypt_request *req);
-int skcipher_null_givdecrypt(struct skcipher_givcrypt_request *req);
-const char *crypto_default_geniv(const struct crypto_alg *alg);
-
-struct crypto_instance *skcipher_geniv_alloc(struct crypto_template *tmpl,
-					     struct rtattr **tb, u32 type,
-					     u32 mask);
-void skcipher_geniv_free(struct crypto_instance *inst);
-int skcipher_geniv_init(struct crypto_tfm *tfm);
-void skcipher_geniv_exit(struct crypto_tfm *tfm);
-
-static inline struct crypto_ablkcipher *skcipher_geniv_cipher(
-	struct crypto_ablkcipher *geniv)
+static inline struct crypto_skcipher *crypto_spawn_skcipher(
+	struct crypto_skcipher_spawn *spawn)
 {
-	return crypto_ablkcipher_crt(geniv)->base;
+	return crypto_spawn_tfm2(&spawn->base);
 }
 
-static inline int skcipher_enqueue_givcrypt(
-	struct crypto_queue *queue, struct skcipher_givcrypt_request *request)
+static inline struct crypto_skcipher *crypto_spawn_skcipher2(
+	struct crypto_skcipher_spawn *spawn)
 {
-	return ablkcipher_enqueue_request(queue, &request->creq);
+	return crypto_spawn_skcipher(spawn);
 }
 
-static inline struct skcipher_givcrypt_request *skcipher_dequeue_givcrypt(
-	struct crypto_queue *queue)
+static inline void crypto_skcipher_set_reqsize(
+	struct crypto_skcipher *skcipher, unsigned int reqsize)
 {
-	return skcipher_givcrypt_cast(crypto_dequeue_request(queue));
+	skcipher->reqsize = reqsize;
 }
 
-static inline void *skcipher_givcrypt_reqctx(
-	struct skcipher_givcrypt_request *req)
-{
-	return ablkcipher_request_ctx(&req->creq);
-}
+int crypto_register_skcipher(struct skcipher_alg *alg);
+void crypto_unregister_skcipher(struct skcipher_alg *alg);
+int crypto_register_skciphers(struct skcipher_alg *algs, int count);
+void crypto_unregister_skciphers(struct skcipher_alg *algs, int count);
+int skcipher_register_instance(struct crypto_template *tmpl,
+			       struct skcipher_instance *inst);
 
 static inline void ablkcipher_request_complete(struct ablkcipher_request *req,
 					       int err)
@@ -96,12 +124,6 @@ static inline void ablkcipher_request_complete(struct ablkcipher_request *req,
 	req->base.complete(&req->base, err);
 }
 
-static inline void skcipher_givcrypt_complete(
-	struct skcipher_givcrypt_request *req, int err)
-{
-	ablkcipher_request_complete(&req->creq, err);
-}
-
 static inline u32 ablkcipher_request_flags(struct ablkcipher_request *req)
 {
 	return req->base.flags;
@@ -122,5 +144,31 @@ static inline u32 skcipher_request_flags(struct skcipher_request *req)
 	return req->base.flags;
 }
 
+static inline unsigned int crypto_skcipher_alg_min_keysize(
+	struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blkcipher.min_keysize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_ablkcipher.min_keysize;
+
+	return alg->min_keysize;
+}
+
+static inline unsigned int crypto_skcipher_alg_max_keysize(
+	struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blkcipher.max_keysize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_ablkcipher.max_keysize;
+
+	return alg->max_keysize;
+}
+
 #endif	/* _CRYPTO_INTERNAL_SKCIPHER_H */
 
diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h
new file mode 100644
index 000000000000..30791f75c180
--- /dev/null
+++ b/include/crypto/kpp.h
@@ -0,0 +1,330 @@
+/*
+ * Key-agreement Protocol Primitives (KPP)
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _CRYPTO_KPP_
+#define _CRYPTO_KPP_
+#include <linux/crypto.h>
+
+/**
+ * struct kpp_request
+ *
+ * @base:	Common attributes for async crypto requests
+ * @src:	Source data
+ * @dst:	Destination data
+ * @src_len:	Size of the input buffer
+ * @dst_len:	Size of the output buffer. It needs to be at least
+ *		as big as the expected result depending	on the operation
+ *		After operation it will be updated with the actual size of the
+ *		result. In case of error where the dst sgl size was insufficient,
+ *		it will be updated to the size required for the operation.
+ * @__ctx:	Start of private context data
+ */
+struct kpp_request {
+	struct crypto_async_request base;
+	struct scatterlist *src;
+	struct scatterlist *dst;
+	unsigned int src_len;
+	unsigned int dst_len;
+	void *__ctx[] CRYPTO_MINALIGN_ATTR;
+};
+
+/**
+ * struct crypto_kpp - user-instantiated object which encapsulate
+ * algorithms and core processing logic
+ *
+ * @base:	Common crypto API algorithm data structure
+ */
+struct crypto_kpp {
+	struct crypto_tfm base;
+};
+
+/**
+ * struct kpp_alg - generic key-agreement protocol primitives
+ *
+ * @set_secret:		Function invokes the protocol specific function to
+ *			store the secret private key along with parameters.
+ *			The implementation knows how to decode thie buffer
+ * @generate_public_key: Function generate the public key to be sent to the
+ *			counterpart. In case of error, where output is not big
+ *			enough req->dst_len will be updated to the size
+ *			required
+ * @compute_shared_secret: Function compute the shared secret as defined by
+ *			the algorithm. The result is given back to the user.
+ *			In case of error, where output is not big enough,
+ *			req->dst_len will be updated to the size required
+ * @max_size:		Function returns the size of the output buffer
+ * @init:		Initialize the object. This is called only once at
+ *			instantiation time. In case the cryptographic hardware
+ *			needs to be initialized. Software fallback should be
+ *			put in place here.
+ * @exit:		Undo everything @init did.
+ *
+ * @reqsize:		Request context size required by algorithm
+ *			implementation
+ * @base		Common crypto API algorithm data structure
+ */
+struct kpp_alg {
+	int (*set_secret)(struct crypto_kpp *tfm, void *buffer,
+			  unsigned int len);
+	int (*generate_public_key)(struct kpp_request *req);
+	int (*compute_shared_secret)(struct kpp_request *req);
+
+	int (*max_size)(struct crypto_kpp *tfm);
+
+	int (*init)(struct crypto_kpp *tfm);
+	void (*exit)(struct crypto_kpp *tfm);
+
+	unsigned int reqsize;
+	struct crypto_alg base;
+};
+
+/**
+ * DOC: Generic Key-agreement Protocol Primitevs API
+ *
+ * The KPP API is used with the algorithm type
+ * CRYPTO_ALG_TYPE_KPP (listed as type "kpp" in /proc/crypto)
+ */
+
+/**
+ * crypto_alloc_kpp() - allocate KPP tfm handle
+ * @alg_name: is the name of the kpp algorithm (e.g. "dh", "ecdh")
+ * @type: specifies the type of the algorithm
+ * @mask: specifies the mask for the algorithm
+ *
+ * Allocate a handle for kpp algorithm. The returned struct crypto_kpp
+ * is requeried for any following API invocation
+ *
+ * Return: allocated handle in case of success; IS_ERR() is true in case of
+ *	   an error, PTR_ERR() returns the error code.
+ */
+struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask);
+
+static inline struct crypto_tfm *crypto_kpp_tfm(struct crypto_kpp *tfm)
+{
+	return &tfm->base;
+}
+
+static inline struct kpp_alg *__crypto_kpp_alg(struct crypto_alg *alg)
+{
+	return container_of(alg, struct kpp_alg, base);
+}
+
+static inline struct crypto_kpp *__crypto_kpp_tfm(struct crypto_tfm *tfm)
+{
+	return container_of(tfm, struct crypto_kpp, base);
+}
+
+static inline struct kpp_alg *crypto_kpp_alg(struct crypto_kpp *tfm)
+{
+	return __crypto_kpp_alg(crypto_kpp_tfm(tfm)->__crt_alg);
+}
+
+static inline unsigned int crypto_kpp_reqsize(struct crypto_kpp *tfm)
+{
+	return crypto_kpp_alg(tfm)->reqsize;
+}
+
+static inline void kpp_request_set_tfm(struct kpp_request *req,
+				       struct crypto_kpp *tfm)
+{
+	req->base.tfm = crypto_kpp_tfm(tfm);
+}
+
+static inline struct crypto_kpp *crypto_kpp_reqtfm(struct kpp_request *req)
+{
+	return __crypto_kpp_tfm(req->base.tfm);
+}
+
+/**
+ * crypto_free_kpp() - free KPP tfm handle
+ *
+ * @tfm: KPP tfm handle allocated with crypto_alloc_kpp()
+ */
+static inline void crypto_free_kpp(struct crypto_kpp *tfm)
+{
+	crypto_destroy_tfm(tfm, crypto_kpp_tfm(tfm));
+}
+
+/**
+ * kpp_request_alloc() - allocates kpp request
+ *
+ * @tfm:	KPP tfm handle allocated with crypto_alloc_kpp()
+ * @gfp:	allocation flags
+ *
+ * Return: allocated handle in case of success or NULL in case of an error.
+ */
+static inline struct kpp_request *kpp_request_alloc(struct crypto_kpp *tfm,
+						    gfp_t gfp)
+{
+	struct kpp_request *req;
+
+	req = kmalloc(sizeof(*req) + crypto_kpp_reqsize(tfm), gfp);
+	if (likely(req))
+		kpp_request_set_tfm(req, tfm);
+
+	return req;
+}
+
+/**
+ * kpp_request_free() - zeroize and free kpp request
+ *
+ * @req:	request to free
+ */
+static inline void kpp_request_free(struct kpp_request *req)
+{
+	kzfree(req);
+}
+
+/**
+ * kpp_request_set_callback() - Sets an asynchronous callback.
+ *
+ * Callback will be called when an asynchronous operation on a given
+ * request is finished.
+ *
+ * @req:	request that the callback will be set for
+ * @flgs:	specify for instance if the operation may backlog
+ * @cmpl:	callback which will be called
+ * @data:	private data used by the caller
+ */
+static inline void kpp_request_set_callback(struct kpp_request *req,
+					    u32 flgs,
+					    crypto_completion_t cmpl,
+					    void *data)
+{
+	req->base.complete = cmpl;
+	req->base.data = data;
+	req->base.flags = flgs;
+}
+
+/**
+ * kpp_request_set_input() - Sets input buffer
+ *
+ * Sets parameters required by generate_public_key
+ *
+ * @req:	kpp request
+ * @input:	ptr to input scatter list
+ * @input_len:	size of the input scatter list
+ */
+static inline void kpp_request_set_input(struct kpp_request *req,
+					 struct scatterlist *input,
+					 unsigned int input_len)
+{
+	req->src = input;
+	req->src_len = input_len;
+}
+
+/**
+ * kpp_request_set_output() - Sets output buffer
+ *
+ * Sets parameters required by kpp operation
+ *
+ * @req:	kpp request
+ * @output:	ptr to output scatter list
+ * @output_len:	size of the output scatter list
+ */
+static inline void kpp_request_set_output(struct kpp_request *req,
+					  struct scatterlist *output,
+					  unsigned int output_len)
+{
+	req->dst = output;
+	req->dst_len = output_len;
+}
+
+enum {
+	CRYPTO_KPP_SECRET_TYPE_UNKNOWN,
+	CRYPTO_KPP_SECRET_TYPE_DH,
+	CRYPTO_KPP_SECRET_TYPE_ECDH,
+};
+
+/**
+ * struct kpp_secret - small header for packing secret buffer
+ *
+ * @type:	define type of secret. Each kpp type will define its own
+ * @len:	specify the len of the secret, include the header, that
+ *		follows the struct
+ */
+struct kpp_secret {
+	unsigned short type;
+	unsigned short len;
+};
+
+/**
+ * crypto_kpp_set_secret() - Invoke kpp operation
+ *
+ * Function invokes the specific kpp operation for a given alg.
+ *
+ * @tfm:	tfm handle
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, void *buffer,
+					unsigned int len)
+{
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->set_secret(tfm, buffer, len);
+}
+
+/**
+ * crypto_kpp_generate_public_key() - Invoke kpp operation
+ *
+ * Function invokes the specific kpp operation for generating the public part
+ * for a given kpp algorithm
+ *
+ * @req:	kpp key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_kpp_generate_public_key(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->generate_public_key(req);
+}
+
+/**
+ * crypto_kpp_compute_shared_secret() - Invoke kpp operation
+ *
+ * Function invokes the specific kpp operation for computing the shared secret
+ * for a given kpp algorithm.
+ *
+ * @req:	kpp key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->compute_shared_secret(req);
+}
+
+/**
+ * crypto_kpp_maxsize() - Get len for output buffer
+ *
+ * Function returns the output buffer size required
+ *
+ * @tfm:	KPP tfm handle allocated with crypto_alloc_kpp()
+ *
+ * Return: minimum len for output buffer or error code if key hasn't been set
+ */
+static inline int crypto_kpp_maxsize(struct crypto_kpp *tfm)
+{
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->max_size(tfm);
+}
+
+#endif
diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h
index c23ee1f7ee80..4a53c0d38cd2 100644
--- a/include/crypto/mcryptd.h
+++ b/include/crypto/mcryptd.h
@@ -39,7 +39,7 @@ struct mcryptd_instance_ctx {
 };
 
 struct mcryptd_hash_ctx {
-	struct crypto_shash *child;
+	struct crypto_ahash *child;
 	struct mcryptd_alg_state *alg_state;
 };
 
@@ -59,13 +59,13 @@ struct mcryptd_hash_request_ctx {
 	struct crypto_hash_walk walk;
 	u8 *out;
 	int flag;
-	struct shash_desc desc;
+	struct ahash_request areq;
 };
 
 struct mcryptd_ahash *mcryptd_alloc_ahash(const char *alg_name,
 					u32 type, u32 mask);
-struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm);
-struct shash_desc *mcryptd_shash_desc(struct ahash_request *req);
+struct crypto_ahash *mcryptd_ahash_child(struct mcryptd_ahash *tfm);
+struct ahash_request *mcryptd_ahash_desc(struct ahash_request *req);
 void mcryptd_free_ahash(struct mcryptd_ahash *tfm);
 void mcryptd_flusher(struct work_struct *work);
 
diff --git a/include/crypto/null.h b/include/crypto/null.h
index 06dc30d9f56e..3f0c59fb0a61 100644
--- a/include/crypto/null.h
+++ b/include/crypto/null.h
@@ -8,7 +8,17 @@
 #define NULL_DIGEST_SIZE	0
 #define NULL_IV_SIZE		0
 
-struct crypto_blkcipher *crypto_get_default_null_skcipher(void);
+struct crypto_skcipher *crypto_get_default_null_skcipher(void);
 void crypto_put_default_null_skcipher(void);
 
+static inline struct crypto_skcipher *crypto_get_default_null_skcipher2(void)
+{
+	return crypto_get_default_null_skcipher();
+}
+
+static inline void crypto_put_default_null_skcipher2(void)
+{
+	crypto_put_default_null_skcipher();
+}
+
 #endif
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 35f99b68d037..880e6be9e95e 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -16,14 +16,10 @@
 #ifndef _CRYPTO_SCATTERWALK_H
 #define _CRYPTO_SCATTERWALK_H
 
-#include <asm/kmap_types.h>
 #include <crypto/algapi.h>
-#include <linux/hardirq.h>
 #include <linux/highmem.h>
 #include <linux/kernel.h>
-#include <linux/mm.h>
 #include <linux/scatterlist.h>
-#include <linux/sched.h>
 
 static inline void scatterwalk_crypto_chain(struct scatterlist *head,
 					    struct scatterlist *sg,
@@ -83,17 +79,53 @@ static inline void scatterwalk_unmap(void *vaddr)
 	kunmap_atomic(vaddr);
 }
 
-void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg);
+static inline void scatterwalk_start(struct scatter_walk *walk,
+				     struct scatterlist *sg)
+{
+	walk->sg = sg;
+	walk->offset = sg->offset;
+}
+
+static inline void *scatterwalk_map(struct scatter_walk *walk)
+{
+	return kmap_atomic(scatterwalk_page(walk)) +
+	       offset_in_page(walk->offset);
+}
+
+static inline void scatterwalk_pagedone(struct scatter_walk *walk, int out,
+					unsigned int more)
+{
+	if (out) {
+		struct page *page;
+
+		page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT);
+		/* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as
+		 * PageSlab cannot be optimised away per se due to
+		 * use of volatile pointer.
+		 */
+		if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page))
+			flush_dcache_page(page);
+	}
+
+	if (more && walk->offset >= walk->sg->offset + walk->sg->length)
+		scatterwalk_start(walk, sg_next(walk->sg));
+}
+
+static inline void scatterwalk_done(struct scatter_walk *walk, int out,
+				    int more)
+{
+	if (!more || walk->offset >= walk->sg->offset + walk->sg->length ||
+	    !(walk->offset & (PAGE_SIZE - 1)))
+		scatterwalk_pagedone(walk, out, more);
+}
+
 void scatterwalk_copychunks(void *buf, struct scatter_walk *walk,
 			    size_t nbytes, int out);
 void *scatterwalk_map(struct scatter_walk *walk);
-void scatterwalk_done(struct scatter_walk *walk, int out, int more);
 
 void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 			      unsigned int start, unsigned int nbytes, int out);
 
-int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes);
-
 struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
 				     struct scatterlist *src,
 				     unsigned int len);
diff --git a/include/crypto/sha3.h b/include/crypto/sha3.h
new file mode 100644
index 000000000000..f4c9f68f5ffe
--- /dev/null
+++ b/include/crypto/sha3.h
@@ -0,0 +1,29 @@
+/*
+ * Common values for SHA-3 algorithms
+ */
+#ifndef __CRYPTO_SHA3_H__
+#define __CRYPTO_SHA3_H__
+
+#define SHA3_224_DIGEST_SIZE	(224 / 8)
+#define SHA3_224_BLOCK_SIZE	(200 - 2 * SHA3_224_DIGEST_SIZE)
+
+#define SHA3_256_DIGEST_SIZE	(256 / 8)
+#define SHA3_256_BLOCK_SIZE	(200 - 2 * SHA3_256_DIGEST_SIZE)
+
+#define SHA3_384_DIGEST_SIZE	(384 / 8)
+#define SHA3_384_BLOCK_SIZE	(200 - 2 * SHA3_384_DIGEST_SIZE)
+
+#define SHA3_512_DIGEST_SIZE	(512 / 8)
+#define SHA3_512_BLOCK_SIZE	(200 - 2 * SHA3_512_DIGEST_SIZE)
+
+struct sha3_state {
+	u64		st[25];
+	unsigned int	md_len;
+	unsigned int	rsiz;
+	unsigned int	rsizw;
+
+	unsigned int	partial;
+	u8		buf[SHA3_224_BLOCK_SIZE];
+};
+
+#endif
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index 0f987f50bb52..cc4d98a7892e 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -65,86 +65,80 @@ struct crypto_skcipher {
 	struct crypto_tfm base;
 };
 
-#define SKCIPHER_REQUEST_ON_STACK(name, tfm) \
-	char __##name##_desc[sizeof(struct skcipher_request) + \
-		crypto_skcipher_reqsize(tfm)] CRYPTO_MINALIGN_ATTR; \
-	struct skcipher_request *name = (void *)__##name##_desc
-
-static inline struct crypto_ablkcipher *skcipher_givcrypt_reqtfm(
-	struct skcipher_givcrypt_request *req)
-{
-	return crypto_ablkcipher_reqtfm(&req->creq);
-}
+/**
+ * struct skcipher_alg - symmetric key cipher definition
+ * @min_keysize: Minimum key size supported by the transformation. This is the
+ *		 smallest key length supported by this transformation algorithm.
+ *		 This must be set to one of the pre-defined values as this is
+ *		 not hardware specific. Possible values for this field can be
+ *		 found via git grep "_MIN_KEY_SIZE" include/crypto/
+ * @max_keysize: Maximum key size supported by the transformation. This is the
+ *		 largest key length supported by this transformation algorithm.
+ *		 This must be set to one of the pre-defined values as this is
+ *		 not hardware specific. Possible values for this field can be
+ *		 found via git grep "_MAX_KEY_SIZE" include/crypto/
+ * @setkey: Set key for the transformation. This function is used to either
+ *	    program a supplied key into the hardware or store the key in the
+ *	    transformation context for programming it later. Note that this
+ *	    function does modify the transformation context. This function can
+ *	    be called multiple times during the existence of the transformation
+ *	    object, so one must make sure the key is properly reprogrammed into
+ *	    the hardware. This function is also responsible for checking the key
+ *	    length for validity. In case a software fallback was put in place in
+ *	    the @cra_init call, this function might need to use the fallback if
+ *	    the algorithm doesn't support all of the key sizes.
+ * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt
+ *	     the supplied scatterlist containing the blocks of data. The crypto
+ *	     API consumer is responsible for aligning the entries of the
+ *	     scatterlist properly and making sure the chunks are correctly
+ *	     sized. In case a software fallback was put in place in the
+ *	     @cra_init call, this function might need to use the fallback if
+ *	     the algorithm doesn't support all of the key sizes. In case the
+ *	     key was stored in transformation context, the key might need to be
+ *	     re-programmed into the hardware in this function. This function
+ *	     shall not modify the transformation context, as this function may
+ *	     be called in parallel with the same transformation object.
+ * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt
+ *	     and the conditions are exactly the same.
+ * @init: Initialize the cryptographic transformation object. This function
+ *	  is used to initialize the cryptographic transformation object.
+ *	  This function is called only once at the instantiation time, right
+ *	  after the transformation context was allocated. In case the
+ *	  cryptographic hardware has some special requirements which need to
+ *	  be handled by software, this function shall check for the precise
+ *	  requirement of the transformation and put any software fallbacks
+ *	  in place.
+ * @exit: Deinitialize the cryptographic transformation object. This is a
+ *	  counterpart to @init, used to remove various changes set in
+ *	  @init.
+ * @ivsize: IV size applicable for transformation. The consumer must provide an
+ *	    IV of exactly that size to perform the encrypt or decrypt operation.
+ * @chunksize: Equal to the block size except for stream ciphers such as
+ *	       CTR where it is set to the underlying block size.
+ * @base: Definition of a generic crypto algorithm.
+ *
+ * All fields except @ivsize are mandatory and must be filled.
+ */
+struct skcipher_alg {
+	int (*setkey)(struct crypto_skcipher *tfm, const u8 *key,
+	              unsigned int keylen);
+	int (*encrypt)(struct skcipher_request *req);
+	int (*decrypt)(struct skcipher_request *req);
+	int (*init)(struct crypto_skcipher *tfm);
+	void (*exit)(struct crypto_skcipher *tfm);
 
-static inline int crypto_skcipher_givencrypt(
-	struct skcipher_givcrypt_request *req)
-{
-	struct ablkcipher_tfm *crt =
-		crypto_ablkcipher_crt(skcipher_givcrypt_reqtfm(req));
-	return crt->givencrypt(req);
-};
+	unsigned int min_keysize;
+	unsigned int max_keysize;
+	unsigned int ivsize;
+	unsigned int chunksize;
 
-static inline int crypto_skcipher_givdecrypt(
-	struct skcipher_givcrypt_request *req)
-{
-	struct ablkcipher_tfm *crt =
-		crypto_ablkcipher_crt(skcipher_givcrypt_reqtfm(req));
-	return crt->givdecrypt(req);
+	struct crypto_alg base;
 };
 
-static inline void skcipher_givcrypt_set_tfm(
-	struct skcipher_givcrypt_request *req, struct crypto_ablkcipher *tfm)
-{
-	req->creq.base.tfm = crypto_ablkcipher_tfm(tfm);
-}
-
-static inline struct skcipher_givcrypt_request *skcipher_givcrypt_cast(
-	struct crypto_async_request *req)
-{
-	return container_of(ablkcipher_request_cast(req),
-			    struct skcipher_givcrypt_request, creq);
-}
-
-static inline struct skcipher_givcrypt_request *skcipher_givcrypt_alloc(
-	struct crypto_ablkcipher *tfm, gfp_t gfp)
-{
-	struct skcipher_givcrypt_request *req;
-
-	req = kmalloc(sizeof(struct skcipher_givcrypt_request) +
-		      crypto_ablkcipher_reqsize(tfm), gfp);
-
-	if (likely(req))
-		skcipher_givcrypt_set_tfm(req, tfm);
-
-	return req;
-}
-
-static inline void skcipher_givcrypt_free(struct skcipher_givcrypt_request *req)
-{
-	kfree(req);
-}
-
-static inline void skcipher_givcrypt_set_callback(
-	struct skcipher_givcrypt_request *req, u32 flags,
-	crypto_completion_t compl, void *data)
-{
-	ablkcipher_request_set_callback(&req->creq, flags, compl, data);
-}
-
-static inline void skcipher_givcrypt_set_crypt(
-	struct skcipher_givcrypt_request *req,
-	struct scatterlist *src, struct scatterlist *dst,
-	unsigned int nbytes, void *iv)
-{
-	ablkcipher_request_set_crypt(&req->creq, src, dst, nbytes, iv);
-}
-
-static inline void skcipher_givcrypt_set_giv(
-	struct skcipher_givcrypt_request *req, u8 *giv, u64 seq)
-{
-	req->giv = giv;
-	req->seq = seq;
-}
+#define SKCIPHER_REQUEST_ON_STACK(name, tfm) \
+	char __##name##_desc[sizeof(struct skcipher_request) + \
+		crypto_skcipher_reqsize(tfm)] CRYPTO_MINALIGN_ATTR; \
+	struct skcipher_request *name = (void *)__##name##_desc
 
 /**
  * DOC: Symmetric Key Cipher API
@@ -231,12 +225,43 @@ static inline int crypto_has_skcipher(const char *alg_name, u32 type,
 			      crypto_skcipher_mask(mask));
 }
 
+/**
+ * crypto_has_skcipher2() - Search for the availability of an skcipher.
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      skcipher
+ * @type: specifies the type of the skcipher
+ * @mask: specifies the mask for the skcipher
+ *
+ * Return: true when the skcipher is known to the kernel crypto API; false
+ *	   otherwise
+ */
+int crypto_has_skcipher2(const char *alg_name, u32 type, u32 mask);
+
 static inline const char *crypto_skcipher_driver_name(
 	struct crypto_skcipher *tfm)
 {
 	return crypto_tfm_alg_driver_name(crypto_skcipher_tfm(tfm));
 }
 
+static inline struct skcipher_alg *crypto_skcipher_alg(
+	struct crypto_skcipher *tfm)
+{
+	return container_of(crypto_skcipher_tfm(tfm)->__crt_alg,
+			    struct skcipher_alg, base);
+}
+
+static inline unsigned int crypto_skcipher_alg_ivsize(struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blkcipher.ivsize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_ablkcipher.ivsize;
+
+	return alg->ivsize;
+}
+
 /**
  * crypto_skcipher_ivsize() - obtain IV size
  * @tfm: cipher handle
@@ -251,6 +276,36 @@ static inline unsigned int crypto_skcipher_ivsize(struct crypto_skcipher *tfm)
 	return tfm->ivsize;
 }
 
+static inline unsigned int crypto_skcipher_alg_chunksize(
+	struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blocksize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_blocksize;
+
+	return alg->chunksize;
+}
+
+/**
+ * crypto_skcipher_chunksize() - obtain chunk size
+ * @tfm: cipher handle
+ *
+ * The block size is set to one for ciphers such as CTR.  However,
+ * you still need to provide incremental updates in multiples of
+ * the underlying block size as the IV does not have sub-block
+ * granularity.  This is known in this API as the chunk size.
+ *
+ * Return: chunk size in bytes
+ */
+static inline unsigned int crypto_skcipher_chunksize(
+	struct crypto_skcipher *tfm)
+{
+	return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm));
+}
+
 /**
  * crypto_skcipher_blocksize() - obtain block size of cipher
  * @tfm: cipher handle
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 288fac5294f5..cc63aef07249 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -208,7 +208,6 @@ void acpi_boot_table_init (void);
 int acpi_mps_check (void);
 int acpi_numa_init (void);
 
-void early_acpi_table_init(void *data, size_t size);
 int acpi_table_init (void);
 int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
 int __init acpi_parse_entries(char *id, unsigned long table_size,
@@ -232,12 +231,26 @@ int acpi_table_parse_madt(enum acpi_madt_type id,
 int acpi_parse_mcfg (struct acpi_table_header *header);
 void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
 
-/* the following four functions are architecture-dependent */
+/* the following numa functions are architecture-dependent */
 void acpi_numa_slit_init (struct acpi_table_slit *slit);
+
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
 void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa);
+#else
+static inline void
+acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { }
+#endif
+
 void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa);
+
+#ifdef CONFIG_ARM64
+void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa);
+#else
+static inline void
+acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
+#endif
+
 int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
-void acpi_numa_arch_fixup(void);
 
 #ifndef PHYS_CPUID_INVALID
 typedef u32 phys_cpuid_t;
@@ -444,8 +457,12 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 #define OSC_SB_HOTPLUG_OST_SUPPORT		0x00000008
 #define OSC_SB_APEI_SUPPORT			0x00000010
 #define OSC_SB_CPC_SUPPORT			0x00000020
+#define OSC_SB_CPCV2_SUPPORT			0x00000040
+#define OSC_SB_PCLPI_SUPPORT			0x00000080
+#define OSC_SB_OSLPI_SUPPORT			0x00000100
 
 extern bool osc_sb_apei_support_acked;
+extern bool osc_pc_lpi_support_confirmed;
 
 /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */
 #define OSC_PCI_EXT_CONFIG_SUPPORT		0x00000001
@@ -532,6 +549,24 @@ void acpi_walk_dep_device_list(acpi_handle handle);
 struct platform_device *acpi_create_platform_device(struct acpi_device *);
 #define ACPI_PTR(_ptr)	(_ptr)
 
+static inline void acpi_device_set_enumerated(struct acpi_device *adev)
+{
+	adev->flags.visited = true;
+}
+
+static inline void acpi_device_clear_enumerated(struct acpi_device *adev)
+{
+	adev->flags.visited = false;
+}
+
+enum acpi_reconfig_event  {
+	ACPI_RECONFIG_DEVICE_ADD = 0,
+	ACPI_RECONFIG_DEVICE_REMOVE,
+};
+
+int acpi_reconfig_notifier_register(struct notifier_block *nb);
+int acpi_reconfig_notifier_unregister(struct notifier_block *nb);
+
 #else	/* !CONFIG_ACPI */
 
 #define acpi_disabled 1
@@ -588,7 +623,6 @@ static inline const char *acpi_dev_name(struct acpi_device *adev)
 	return NULL;
 }
 
-static inline void early_acpi_table_init(void *data, size_t size) { }
 static inline void acpi_early_init(void) { }
 static inline void acpi_subsystem_init(void) { }
 
@@ -678,6 +712,24 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev)
 
 #define ACPI_PTR(_ptr)	(NULL)
 
+static inline void acpi_device_set_enumerated(struct acpi_device *adev)
+{
+}
+
+static inline void acpi_device_clear_enumerated(struct acpi_device *adev)
+{
+}
+
+static inline int acpi_reconfig_notifier_register(struct notifier_block *nb)
+{
+	return -EINVAL;
+}
+
+static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb)
+{
+	return -EINVAL;
+}
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI
@@ -997,4 +1049,10 @@ static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
 #define acpi_probe_device_table(t)	({ int __r = 0; __r;})
 #endif
 
+#ifdef CONFIG_ACPI_TABLE_UPGRADE
+void acpi_table_upgrade(void);
+#else
+static inline void acpi_table_upgrade(void) { }
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 99346be5a7ca..adbc812c009b 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -46,8 +46,9 @@ enum {
 	ATA_MAX_SECTORS_128	= 128,
 	ATA_MAX_SECTORS		= 256,
 	ATA_MAX_SECTORS_1024    = 1024,
-	ATA_MAX_SECTORS_LBA48	= 65535,/* TODO: 65536? */
+	ATA_MAX_SECTORS_LBA48	= 65535,/* avoid count to be 0000h */
 	ATA_MAX_SECTORS_TAPE	= 65535,
+	ATA_MAX_TRIM_RNUM	= 64,	/* 512-byte payload / (6-byte LBA + 2-byte range per entry) */
 
 	ATA_ID_WORDS		= 256,
 	ATA_ID_CONFIG		= 0,
@@ -409,6 +410,9 @@ enum {
 	SETFEATURES_WC_ON	= 0x02, /* Enable write cache */
 	SETFEATURES_WC_OFF	= 0x82, /* Disable write cache */
 
+	SETFEATURES_RA_ON	= 0xaa, /* Enable read look-ahead */
+	SETFEATURES_RA_OFF	= 0x55, /* Disable read look-ahead */
+
 	/* Enable/Disable Automatic Acoustic Management */
 	SETFEATURES_AAM_ON	= 0x42,
 	SETFEATURES_AAM_OFF	= 0xC2,
@@ -519,16 +523,23 @@ enum {
 	SERR_DEV_XCHG		= (1 << 26), /* device exchanged */
 };
 
-enum ata_tf_protocols {
-	/* ATA taskfile protocols */
-	ATA_PROT_UNKNOWN,	/* unknown/invalid */
-	ATA_PROT_NODATA,	/* no data */
-	ATA_PROT_PIO,		/* PIO data xfer */
-	ATA_PROT_DMA,		/* DMA */
-	ATA_PROT_NCQ,		/* NCQ */
-	ATAPI_PROT_NODATA,	/* packet command, no data */
-	ATAPI_PROT_PIO,		/* packet command, PIO data xfer*/
-	ATAPI_PROT_DMA,		/* packet command with special DMA sauce */
+enum ata_prot_flags {
+	/* protocol flags */
+	ATA_PROT_FLAG_PIO	= (1 << 0), /* is PIO */
+	ATA_PROT_FLAG_DMA	= (1 << 1), /* is DMA */
+	ATA_PROT_FLAG_NCQ	= (1 << 2), /* is NCQ */
+	ATA_PROT_FLAG_ATAPI	= (1 << 3), /* is ATAPI */
+
+	/* taskfile protocols */
+	ATA_PROT_UNKNOWN	= (u8)-1,
+	ATA_PROT_NODATA		= 0,
+	ATA_PROT_PIO		= ATA_PROT_FLAG_PIO,
+	ATA_PROT_DMA		= ATA_PROT_FLAG_DMA,
+	ATA_PROT_NCQ_NODATA	= ATA_PROT_FLAG_NCQ,
+	ATA_PROT_NCQ		= ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ,
+	ATAPI_PROT_NODATA	= ATA_PROT_FLAG_ATAPI,
+	ATAPI_PROT_PIO		= ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO,
+	ATAPI_PROT_DMA		= ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA,
 };
 
 enum ata_ioctls {
@@ -1066,12 +1077,12 @@ static inline void ata_id_to_hd_driveid(u16 *id)
  * TO NV CACHE PINNED SET.
  */
 static inline unsigned ata_set_lba_range_entries(void *_buffer,
-		unsigned buf_size, u64 sector, unsigned long count)
+		unsigned num, u64 sector, unsigned long count)
 {
 	__le64 *buffer = _buffer;
 	unsigned i = 0, used_bytes;
 
-	while (i < buf_size / 8 ) { /* 6-byte LBA + 2-byte range per entry */
+	while (i < num) {
 		u64 entry = sector |
 			((u64)(count > 0xffff ? 0xffff : count) << 48);
 		buffer[i++] = __cpu_to_le64(entry);
@@ -1095,13 +1106,13 @@ static inline bool ata_ok(u8 status)
 static inline bool lba_28_ok(u64 block, u32 n_block)
 {
 	/* check the ending block number: must be LESS THAN 0x0fffffff */
-	return ((block + n_block) < ((1 << 28) - 1)) && (n_block <= 256);
+	return ((block + n_block) < ((1 << 28) - 1)) && (n_block <= ATA_MAX_SECTORS);
 }
 
 static inline bool lba_48_ok(u64 block, u32 n_block)
 {
 	/* check the ending block number */
-	return ((block + n_block - 1) < ((u64)1 << 48)) && (n_block <= 65536);
+	return ((block + n_block - 1) < ((u64)1 << 48)) && (n_block <= ATA_MAX_SECTORS_LBA48);
 }
 
 #define sata_pmp_gscr_vendor(gscr)	((gscr)[SATA_PMP_GSCR_PROD_ID] & 0xffff)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 9faebf7f9a33..583c10810e32 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -41,44 +41,9 @@
 #endif
 
 #define BIO_MAX_PAGES		256
-#define BIO_MAX_SIZE		(BIO_MAX_PAGES << PAGE_SHIFT)
-#define BIO_MAX_SECTORS		(BIO_MAX_SIZE >> 9)
 
-/*
- * upper 16 bits of bi_rw define the io priority of this bio
- */
-#define BIO_PRIO_SHIFT	(8 * sizeof(unsigned long) - IOPRIO_BITS)
-#define bio_prio(bio)	((bio)->bi_rw >> BIO_PRIO_SHIFT)
-#define bio_prio_valid(bio)	ioprio_valid(bio_prio(bio))
-
-#define bio_set_prio(bio, prio)		do {			\
-	WARN_ON(prio >= (1 << IOPRIO_BITS));			\
-	(bio)->bi_rw &= ((1UL << BIO_PRIO_SHIFT) - 1);		\
-	(bio)->bi_rw |= ((unsigned long) (prio) << BIO_PRIO_SHIFT);	\
-} while (0)
-
-/*
- * various member access, note that bio_data should of course not be used
- * on highmem page vectors
- */
-#define __bvec_iter_bvec(bvec, iter)	(&(bvec)[(iter).bi_idx])
-
-#define bvec_iter_page(bvec, iter)				\
-	(__bvec_iter_bvec((bvec), (iter))->bv_page)
-
-#define bvec_iter_len(bvec, iter)				\
-	min((iter).bi_size,					\
-	    __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done)
-
-#define bvec_iter_offset(bvec, iter)				\
-	(__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done)
-
-#define bvec_iter_bvec(bvec, iter)				\
-((struct bio_vec) {						\
-	.bv_page	= bvec_iter_page((bvec), (iter)),	\
-	.bv_len		= bvec_iter_len((bvec), (iter)),	\
-	.bv_offset	= bvec_iter_offset((bvec), (iter)),	\
-})
+#define bio_prio(bio)			(bio)->bi_ioprio
+#define bio_set_prio(bio, prio)		((bio)->bi_ioprio = prio)
 
 #define bio_iter_iovec(bio, iter)				\
 	bvec_iter_bvec((bio)->bi_io_vec, (iter))
@@ -106,18 +71,23 @@ static inline bool bio_has_data(struct bio *bio)
 {
 	if (bio &&
 	    bio->bi_iter.bi_size &&
-	    !(bio->bi_rw & REQ_DISCARD))
+	    bio_op(bio) != REQ_OP_DISCARD)
 		return true;
 
 	return false;
 }
 
+static inline bool bio_no_advance_iter(struct bio *bio)
+{
+	return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME;
+}
+
 static inline bool bio_is_rw(struct bio *bio)
 {
 	if (!bio_has_data(bio))
 		return false;
 
-	if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
+	if (bio_no_advance_iter(bio))
 		return false;
 
 	return true;
@@ -193,39 +163,12 @@ static inline void *bio_data(struct bio *bio)
 #define bio_for_each_segment_all(bvl, bio, i)				\
 	for (i = 0, bvl = (bio)->bi_io_vec; i < (bio)->bi_vcnt; i++, bvl++)
 
-static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter,
-				     unsigned bytes)
-{
-	WARN_ONCE(bytes > iter->bi_size,
-		  "Attempted to advance past end of bvec iter\n");
-
-	while (bytes) {
-		unsigned len = min(bytes, bvec_iter_len(bv, *iter));
-
-		bytes -= len;
-		iter->bi_size -= len;
-		iter->bi_bvec_done += len;
-
-		if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) {
-			iter->bi_bvec_done = 0;
-			iter->bi_idx++;
-		}
-	}
-}
-
-#define for_each_bvec(bvl, bio_vec, iter, start)			\
-	for (iter = (start);						\
-	     (iter).bi_size &&						\
-		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
-	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
-
-
 static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
 				    unsigned bytes)
 {
 	iter->bi_sector += bytes >> 9;
 
-	if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
+	if (bio_no_advance_iter(bio))
 		iter->bi_size -= bytes;
 	else
 		bvec_iter_advance(bio->bi_io_vec, iter, bytes);
@@ -253,10 +196,10 @@ static inline unsigned bio_segments(struct bio *bio)
 	 * differently:
 	 */
 
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		return 1;
 
-	if (bio->bi_rw & REQ_WRITE_SAME)
+	if (bio_op(bio) == REQ_OP_WRITE_SAME)
 		return 1;
 
 	bio_for_each_segment(bv, bio, iter)
@@ -473,7 +416,7 @@ static inline void bio_io_error(struct bio *bio)
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
 
-extern int submit_bio_wait(int rw, struct bio *bio);
+extern int submit_bio_wait(struct bio *bio);
 extern void bio_advance(struct bio *, unsigned);
 
 extern void bio_init(struct bio *);
@@ -720,8 +663,6 @@ static inline void bio_inc_remaining(struct bio *bio)
  * and the bvec_slabs[].
  */
 #define BIO_POOL_SIZE 2
-#define BIOVEC_NR_POOLS 6
-#define BIOVEC_MAX_IDX	(BIOVEC_NR_POOLS - 1)
 
 struct bio_set {
 	struct kmem_cache *bio_slab;
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index e9b0b9ab07e5..27bfc0b631a9 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -267,6 +267,10 @@ static inline int bitmap_equal(const unsigned long *src1,
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
+#ifdef CONFIG_S390
+	else if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0)
+		return !memcmp(src1, src2, nbits / 8);
+#endif
 	else
 		return __bitmap_equal(src1, src2, nbits);
 }
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index c02e669945e9..f77150a4a96a 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -590,25 +590,26 @@ static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
 /**
  * blkg_rwstat_add - add a value to a blkg_rwstat
  * @rwstat: target blkg_rwstat
- * @rw: mask of REQ_{WRITE|SYNC}
+ * @op: REQ_OP
+ * @op_flags: rq_flag_bits
  * @val: value to add
  *
  * Add @val to @rwstat.  The counters are chosen according to @rw.  The
  * caller is responsible for synchronizing calls to this function.
  */
 static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
-				   int rw, uint64_t val)
+				   int op, int op_flags, uint64_t val)
 {
 	struct percpu_counter *cnt;
 
-	if (rw & REQ_WRITE)
+	if (op_is_write(op))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
 
 	__percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH);
 
-	if (rw & REQ_SYNC)
+	if (op_flags & REQ_SYNC)
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
@@ -713,9 +714,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 	if (!throtl) {
 		blkg = blkg ?: q->root_blkg;
-		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_rw,
+		blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_rw,
 				bio->bi_iter.bi_size);
-		blkg_rwstat_add(&blkg->stat_ios, bio->bi_rw, 1);
+		blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_rw, 1);
 	}
 
 	rcu_read_unlock();
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2498fdf3a503..e43bbffb5b7a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -96,6 +96,7 @@ typedef int (init_request_fn)(void *, struct request *, unsigned int,
 		unsigned int, unsigned int);
 typedef void (exit_request_fn)(void *, struct request *, unsigned int,
 		unsigned int);
+typedef int (reinit_request_fn)(void *, struct request *);
 
 typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 		bool);
@@ -145,6 +146,7 @@ struct blk_mq_ops {
 	 */
 	init_request_fn		*init_request;
 	exit_request_fn		*exit_request;
+	reinit_request_fn	*reinit_request;
 };
 
 enum {
@@ -196,6 +198,8 @@ enum {
 
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		unsigned int flags);
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op,
+		unsigned int flags, unsigned int hctx_idx);
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
 struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags);
 
@@ -243,6 +247,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);
+int blk_mq_reinit_tagset(struct blk_mq_tag_set *set);
 
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 77e5d81f07aa..f254eb264924 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -6,6 +6,7 @@
 #define __LINUX_BLK_TYPES_H
 
 #include <linux/types.h>
+#include <linux/bvec.h>
 
 struct bio_set;
 struct bio;
@@ -17,28 +18,7 @@ struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 typedef void (bio_destructor_t) (struct bio *);
 
-/*
- * was unsigned short, but we might as well be ready for > 64kB I/O pages
- */
-struct bio_vec {
-	struct page	*bv_page;
-	unsigned int	bv_len;
-	unsigned int	bv_offset;
-};
-
 #ifdef CONFIG_BLOCK
-
-struct bvec_iter {
-	sector_t		bi_sector;	/* device address in 512 byte
-						   sectors */
-	unsigned int		bi_size;	/* residual I/O count */
-
-	unsigned int		bi_idx;		/* current index into bvl_vec */
-
-	unsigned int            bi_bvec_done;	/* number of bytes completed in
-						   current bvec */
-};
-
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
  * stacking drivers)
@@ -46,11 +26,12 @@ struct bvec_iter {
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
-	unsigned int		bi_flags;	/* status, command, etc */
 	int			bi_error;
-	unsigned long		bi_rw;		/* bottom bits READ/WRITE,
-						 * top bits priority
+	unsigned int		bi_rw;		/* bottom bits req flags,
+						 * top bits REQ_OP
 						 */
+	unsigned short		bi_flags;	/* status, command, etc */
+	unsigned short		bi_ioprio;
 
 	struct bvec_iter	bi_iter;
 
@@ -107,6 +88,16 @@ struct bio {
 	struct bio_vec		bi_inline_vecs[0];
 };
 
+#define BIO_OP_SHIFT	(8 * sizeof(unsigned int) - REQ_OP_BITS)
+#define bio_op(bio)	((bio)->bi_rw >> BIO_OP_SHIFT)
+
+#define bio_set_op_attrs(bio, op, op_flags) do {		\
+	WARN_ON(op >= (1 << REQ_OP_BITS));			\
+	(bio)->bi_rw &= ((1 << BIO_OP_SHIFT) - 1);		\
+	(bio)->bi_rw |= ((unsigned int) (op) << BIO_OP_SHIFT);	\
+	(bio)->bi_rw |= op_flags;				\
+} while (0)
+
 #define BIO_RESET_BYTES		offsetof(struct bio, bi_max_vecs)
 
 /*
@@ -123,19 +114,25 @@ struct bio {
 
 /*
  * Flags starting here get preserved by bio_reset() - this includes
- * BIO_POOL_IDX()
+ * BVEC_POOL_IDX()
+ */
+#define BIO_RESET_BITS	10
+
+/*
+ * We support 6 different bvec pools, the last one is magic in that it
+ * is backed by a mempool.
  */
-#define BIO_RESET_BITS	13
-#define BIO_OWNS_VEC	13	/* bio_free() should free bvec */
+#define BVEC_POOL_NR		6
+#define BVEC_POOL_MAX		(BVEC_POOL_NR - 1)
 
 /*
- * top 4 bits of bio flags indicate the pool this bio came from
+ * Top 4 bits of bio flags indicate the pool the bvecs came from.  We add
+ * 1 to the actual index so that 0 indicates that there are no bvecs to be
+ * freed.
  */
-#define BIO_POOL_BITS		(4)
-#define BIO_POOL_NONE		((1UL << BIO_POOL_BITS) - 1)
-#define BIO_POOL_OFFSET		(32 - BIO_POOL_BITS)
-#define BIO_POOL_MASK		(1UL << BIO_POOL_OFFSET)
-#define BIO_POOL_IDX(bio)	((bio)->bi_flags >> BIO_POOL_OFFSET)
+#define BVEC_POOL_BITS		(4)
+#define BVEC_POOL_OFFSET	(16 - BVEC_POOL_BITS)
+#define BVEC_POOL_IDX(bio)	((bio)->bi_flags >> BVEC_POOL_OFFSET)
 
 #endif /* CONFIG_BLOCK */
 
@@ -145,7 +142,6 @@ struct bio {
  */
 enum rq_flag_bits {
 	/* common flags */
-	__REQ_WRITE,		/* not set, read. set, write */
 	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
 	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
 	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
@@ -153,14 +149,11 @@ enum rq_flag_bits {
 	__REQ_SYNC,		/* request is sync (sync write or read) */
 	__REQ_META,		/* metadata io request */
 	__REQ_PRIO,		/* boost priority in cfq */
-	__REQ_DISCARD,		/* request to discard sectors */
-	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
-	__REQ_WRITE_SAME,	/* write same block many times */
 
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
 	__REQ_INTEGRITY,	/* I/O includes block integrity payload */
 	__REQ_FUA,		/* forced unit access */
-	__REQ_FLUSH,		/* request for cache flush */
+	__REQ_PREFLUSH,		/* request for cache flush */
 
 	/* bio only flags */
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
@@ -191,31 +184,25 @@ enum rq_flag_bits {
 	__REQ_NR_BITS,		/* stops here */
 };
 
-#define REQ_WRITE		(1ULL << __REQ_WRITE)
 #define REQ_FAILFAST_DEV	(1ULL << __REQ_FAILFAST_DEV)
 #define REQ_FAILFAST_TRANSPORT	(1ULL << __REQ_FAILFAST_TRANSPORT)
 #define REQ_FAILFAST_DRIVER	(1ULL << __REQ_FAILFAST_DRIVER)
 #define REQ_SYNC		(1ULL << __REQ_SYNC)
 #define REQ_META		(1ULL << __REQ_META)
 #define REQ_PRIO		(1ULL << __REQ_PRIO)
-#define REQ_DISCARD		(1ULL << __REQ_DISCARD)
-#define REQ_WRITE_SAME		(1ULL << __REQ_WRITE_SAME)
 #define REQ_NOIDLE		(1ULL << __REQ_NOIDLE)
 #define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
-	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
-	 REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
-	 REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE)
+	(REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \
+	 REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
-#define BIO_NO_ADVANCE_ITER_MASK	(REQ_DISCARD|REQ_WRITE_SAME)
-
 /* This mask is used for both bio and request merge checking */
 #define REQ_NOMERGE_FLAGS \
-	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_FLUSH_SEQ)
+	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_PREFLUSH | REQ_FUA | REQ_FLUSH_SEQ)
 
 #define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
 #define REQ_THROTTLED		(1ULL << __REQ_THROTTLED)
@@ -233,15 +220,25 @@ enum rq_flag_bits {
 #define REQ_PREEMPT		(1ULL << __REQ_PREEMPT)
 #define REQ_ALLOCED		(1ULL << __REQ_ALLOCED)
 #define REQ_COPY_USER		(1ULL << __REQ_COPY_USER)
-#define REQ_FLUSH		(1ULL << __REQ_FLUSH)
+#define REQ_PREFLUSH		(1ULL << __REQ_PREFLUSH)
 #define REQ_FLUSH_SEQ		(1ULL << __REQ_FLUSH_SEQ)
 #define REQ_IO_STAT		(1ULL << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1ULL << __REQ_MIXED_MERGE)
-#define REQ_SECURE		(1ULL << __REQ_SECURE)
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
 
+enum req_op {
+	REQ_OP_READ,
+	REQ_OP_WRITE,
+	REQ_OP_DISCARD,		/* request to discard sectors */
+	REQ_OP_SECURE_ERASE,	/* request to securely erase sectors */
+	REQ_OP_WRITE_SAME,	/* write same block many times */
+	REQ_OP_FLUSH,		/* request for cache flush */
+};
+
+#define REQ_OP_BITS 3
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE	-1U
 #define BLK_QC_T_SHIFT	16
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3d9cf326574f..c96db9c22d10 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -90,18 +90,17 @@ struct request {
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
-		unsigned long fifo_time;
+		u64 fifo_time;
 	};
 
 	struct request_queue *q;
 	struct blk_mq_ctx *mq_ctx;
 
-	u64 cmd_flags;
+	int cpu;
 	unsigned cmd_type;
+	u64 cmd_flags;
 	unsigned long atomic_flags;
 
-	int cpu;
-
 	/* the following two fields are internal, NEVER access directly */
 	unsigned int __data_len;	/* total data len */
 	sector_t __sector;		/* sector cursor */
@@ -200,6 +199,20 @@ struct request {
 	struct request *next_rq;
 };
 
+#define REQ_OP_SHIFT (8 * sizeof(u64) - REQ_OP_BITS)
+#define req_op(req)  ((req)->cmd_flags >> REQ_OP_SHIFT)
+
+#define req_set_op(req, op) do {				\
+	WARN_ON(op >= (1 << REQ_OP_BITS));			\
+	(req)->cmd_flags &= ((1ULL << REQ_OP_SHIFT) - 1);	\
+	(req)->cmd_flags |= ((u64) (op) << REQ_OP_SHIFT);	\
+} while (0)
+
+#define req_set_op_attrs(req, op, flags) do {	\
+	req_set_op(req, op);			\
+	(req)->cmd_flags |= flags;		\
+} while (0)
+
 static inline unsigned short req_get_ioprio(struct request *req)
 {
 	return req->ioprio;
@@ -483,7 +496,7 @@ struct request_queue {
 #define QUEUE_FLAG_DISCARD     14	/* supports DISCARD */
 #define QUEUE_FLAG_NOXMERGES   15	/* No extended merges */
 #define QUEUE_FLAG_ADD_RANDOM  16	/* Contributes to random pool */
-#define QUEUE_FLAG_SECDISCARD  17	/* supports SECDISCARD */
+#define QUEUE_FLAG_SECERASE    17	/* supports secure erase */
 #define QUEUE_FLAG_SAME_FORCE  18	/* force complete on same CPU */
 #define QUEUE_FLAG_DEAD        19	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE   20	/* queue is initialized */
@@ -492,6 +505,7 @@ struct request_queue {
 #define QUEUE_FLAG_WC	       23	/* Write back caching */
 #define QUEUE_FLAG_FUA	       24	/* device supports FUA writes */
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
+#define QUEUE_FLAG_DAX         26	/* device supports DAX */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -579,8 +593,9 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
-#define blk_queue_secdiscard(q)	(blk_queue_discard(q) && \
-	test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags))
+#define blk_queue_secure_erase(q) \
+	(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
+#define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
 
 #define blk_noretry_request(rq) \
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
@@ -597,7 +612,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
-#define rq_data_dir(rq)		((int)((rq)->cmd_flags & 1))
+#define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
 
 /*
  * Driver can handle struct request, if it either has an old style
@@ -616,14 +631,14 @@ static inline unsigned int blk_queue_cluster(struct request_queue *q)
 /*
  * We regard a request as sync, if either a read or a sync write
  */
-static inline bool rw_is_sync(unsigned int rw_flags)
+static inline bool rw_is_sync(int op, unsigned int rw_flags)
 {
-	return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC);
+	return op == REQ_OP_READ || (rw_flags & REQ_SYNC);
 }
 
 static inline bool rq_is_sync(struct request *rq)
 {
-	return rw_is_sync(rq->cmd_flags);
+	return rw_is_sync(req_op(rq), rq->cmd_flags);
 }
 
 static inline bool blk_rl_full(struct request_list *rl, bool sync)
@@ -652,22 +667,10 @@ static inline bool rq_mergeable(struct request *rq)
 	if (rq->cmd_type != REQ_TYPE_FS)
 		return false;
 
-	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
+	if (req_op(rq) == REQ_OP_FLUSH)
 		return false;
 
-	return true;
-}
-
-static inline bool blk_check_merge_flags(unsigned int flags1,
-					 unsigned int flags2)
-{
-	if ((flags1 & REQ_DISCARD) != (flags2 & REQ_DISCARD))
-		return false;
-
-	if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE))
-		return false;
-
-	if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME))
+	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
 		return false;
 
 	return true;
@@ -786,8 +789,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
-extern struct request *blk_make_request(struct request_queue *, struct bio *,
-					gfp_t);
 extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
@@ -800,6 +801,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
+extern int blk_rq_append_bio(struct request *rq, struct bio *bio);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
 extern void blk_queue_split(struct request_queue *, struct bio **,
 			    struct bio_set *);
@@ -879,12 +881,12 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 }
 
 static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
-						     unsigned int cmd_flags)
+						     int op)
 {
-	if (unlikely(cmd_flags & REQ_DISCARD))
+	if (unlikely(op == REQ_OP_DISCARD))
 		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
 
-	if (unlikely(cmd_flags & REQ_WRITE_SAME))
+	if (unlikely(op == REQ_OP_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
 
 	return q->limits.max_sectors;
@@ -904,18 +906,19 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
 			(offset & (q->limits.chunk_sectors - 1));
 }
 
-static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
+static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
+						  sector_t offset)
 {
 	struct request_queue *q = rq->q;
 
 	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
 		return q->limits.max_hw_sectors;
 
-	if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
-		return blk_queue_get_max_sectors(q, rq->cmd_flags);
+	if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD))
+		return blk_queue_get_max_sectors(q, req_op(rq));
 
-	return min(blk_max_size_offset(q, blk_rq_pos(rq)),
-			blk_queue_get_max_sectors(q, rq->cmd_flags));
+	return min(blk_max_size_offset(q, offset),
+			blk_queue_get_max_sectors(q, req_op(rq)));
 }
 
 static inline unsigned int blk_rq_count_bios(struct request *rq)
@@ -1135,13 +1138,16 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 	return bqt->tag_index[tag];
 }
 
-#define BLKDEV_DISCARD_SECURE  0x01    /* secure discard */
+
+#define BLKDEV_DISCARD_SECURE	(1 << 0)	/* issue a secure erase */
+#define BLKDEV_DISCARD_ZERO	(1 << 1)	/* must reliably zero data */
 
 extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop);
+		sector_t nr_sects, gfp_t gfp_mask, int flags,
+		struct bio **biop);
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 0f3172b8b225..cceb72f9e29f 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -118,7 +118,7 @@ static inline int blk_cmd_buf_len(struct request *rq)
 }
 
 extern void blk_dump_cmd(char *buf, struct request *rq);
-extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
+extern void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes);
 
 #endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 7e14e545c4b6..ebbacd14d450 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -187,12 +187,13 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
 void __lock_buffer(struct buffer_head *bh);
-void ll_rw_block(int, int, struct buffer_head * bh[]);
+void ll_rw_block(int, int, int, struct buffer_head * bh[]);
 int sync_dirty_buffer(struct buffer_head *bh);
-int __sync_dirty_buffer(struct buffer_head *bh, int rw);
-void write_dirty_buffer(struct buffer_head *bh, int rw);
-int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags);
-int submit_bh(int, struct buffer_head *);
+int __sync_dirty_buffer(struct buffer_head *bh, int op_flags);
+void write_dirty_buffer(struct buffer_head *bh, int op_flags);
+int _submit_bh(int op, int op_flags, struct buffer_head *bh,
+	       unsigned long bio_flags);
+int submit_bh(int, int, struct buffer_head *);
 void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize);
 int bh_uptodate_or_lock(struct buffer_head *bh);
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
new file mode 100644
index 000000000000..701b64a3b7c5
--- /dev/null
+++ b/include/linux/bvec.h
@@ -0,0 +1,96 @@
+/*
+ * bvec iterator
+ *
+ * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ */
+#ifndef __LINUX_BVEC_ITER_H
+#define __LINUX_BVEC_ITER_H
+
+#include <linux/kernel.h>
+#include <linux/bug.h>
+
+/*
+ * was unsigned short, but we might as well be ready for > 64kB I/O pages
+ */
+struct bio_vec {
+	struct page	*bv_page;
+	unsigned int	bv_len;
+	unsigned int	bv_offset;
+};
+
+struct bvec_iter {
+	sector_t		bi_sector;	/* device address in 512 byte
+						   sectors */
+	unsigned int		bi_size;	/* residual I/O count */
+
+	unsigned int		bi_idx;		/* current index into bvl_vec */
+
+	unsigned int            bi_bvec_done;	/* number of bytes completed in
+						   current bvec */
+};
+
+/*
+ * various member access, note that bio_data should of course not be used
+ * on highmem page vectors
+ */
+#define __bvec_iter_bvec(bvec, iter)	(&(bvec)[(iter).bi_idx])
+
+#define bvec_iter_page(bvec, iter)				\
+	(__bvec_iter_bvec((bvec), (iter))->bv_page)
+
+#define bvec_iter_len(bvec, iter)				\
+	min((iter).bi_size,					\
+	    __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done)
+
+#define bvec_iter_offset(bvec, iter)				\
+	(__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done)
+
+#define bvec_iter_bvec(bvec, iter)				\
+((struct bio_vec) {						\
+	.bv_page	= bvec_iter_page((bvec), (iter)),	\
+	.bv_len		= bvec_iter_len((bvec), (iter)),	\
+	.bv_offset	= bvec_iter_offset((bvec), (iter)),	\
+})
+
+static inline void bvec_iter_advance(const struct bio_vec *bv,
+				     struct bvec_iter *iter,
+				     unsigned bytes)
+{
+	WARN_ONCE(bytes > iter->bi_size,
+		  "Attempted to advance past end of bvec iter\n");
+
+	while (bytes) {
+		unsigned len = min(bytes, bvec_iter_len(bv, *iter));
+
+		bytes -= len;
+		iter->bi_size -= len;
+		iter->bi_bvec_done += len;
+
+		if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) {
+			iter->bi_bvec_done = 0;
+			iter->bi_idx++;
+		}
+	}
+}
+
+#define for_each_bvec(bvl, bio_vec, iter, start)			\
+	for (iter = (start);						\
+	     (iter).bi_size &&						\
+		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
+	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
+
+#endif /* __LINUX_BVEC_ITER_H */
diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h
new file mode 100644
index 000000000000..82c3d3b7269d
--- /dev/null
+++ b/include/linux/cec-funcs.h
@@ -0,0 +1,1899 @@
+/*
+ * cec - HDMI Consumer Electronics Control message functions
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * Alternatively you can redistribute this file under the terms of the
+ * BSD license as stated below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ * 3. The names of its contributors may not be used to endorse or promote
+ *    products derived from this software without specific prior written
+ *    permission.
+ *
+ * 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.
+ */
+
+/*
+ * Note: this framework is still in staging and it is likely the API
+ * will change before it goes out of staging.
+ *
+ * Once it is moved out of staging this header will move to uapi.
+ */
+#ifndef _CEC_UAPI_FUNCS_H
+#define _CEC_UAPI_FUNCS_H
+
+#include <linux/cec.h>
+
+/* One Touch Play Feature */
+static inline void cec_msg_active_source(struct cec_msg *msg, __u16 phys_addr)
+{
+	msg->len = 4;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_ACTIVE_SOURCE;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+}
+
+static inline void cec_ops_active_source(const struct cec_msg *msg,
+					 __u16 *phys_addr)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+static inline void cec_msg_image_view_on(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_IMAGE_VIEW_ON;
+}
+
+static inline void cec_msg_text_view_on(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_TEXT_VIEW_ON;
+}
+
+
+/* Routing Control Feature */
+static inline void cec_msg_inactive_source(struct cec_msg *msg,
+					   __u16 phys_addr)
+{
+	msg->len = 4;
+	msg->msg[1] = CEC_MSG_INACTIVE_SOURCE;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+}
+
+static inline void cec_ops_inactive_source(const struct cec_msg *msg,
+					   __u16 *phys_addr)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+static inline void cec_msg_request_active_source(struct cec_msg *msg,
+						 bool reply)
+{
+	msg->len = 2;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_REQUEST_ACTIVE_SOURCE;
+	msg->reply = reply ? CEC_MSG_ACTIVE_SOURCE : 0;
+}
+
+static inline void cec_msg_routing_information(struct cec_msg *msg,
+					       __u16 phys_addr)
+{
+	msg->len = 4;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_ROUTING_INFORMATION;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+}
+
+static inline void cec_ops_routing_information(const struct cec_msg *msg,
+					       __u16 *phys_addr)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+static inline void cec_msg_routing_change(struct cec_msg *msg,
+					  bool reply,
+					  __u16 orig_phys_addr,
+					  __u16 new_phys_addr)
+{
+	msg->len = 6;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_ROUTING_CHANGE;
+	msg->msg[2] = orig_phys_addr >> 8;
+	msg->msg[3] = orig_phys_addr & 0xff;
+	msg->msg[4] = new_phys_addr >> 8;
+	msg->msg[5] = new_phys_addr & 0xff;
+	msg->reply = reply ? CEC_MSG_ROUTING_INFORMATION : 0;
+}
+
+static inline void cec_ops_routing_change(const struct cec_msg *msg,
+					  __u16 *orig_phys_addr,
+					  __u16 *new_phys_addr)
+{
+	*orig_phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*new_phys_addr = (msg->msg[4] << 8) | msg->msg[5];
+}
+
+static inline void cec_msg_set_stream_path(struct cec_msg *msg, __u16 phys_addr)
+{
+	msg->len = 4;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_SET_STREAM_PATH;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+}
+
+static inline void cec_ops_set_stream_path(const struct cec_msg *msg,
+					   __u16 *phys_addr)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+
+/* Standby Feature */
+static inline void cec_msg_standby(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_STANDBY;
+}
+
+
+/* One Touch Record Feature */
+static inline void cec_msg_record_off(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_RECORD_OFF;
+}
+
+struct cec_op_arib_data {
+	__u16 transport_id;
+	__u16 service_id;
+	__u16 orig_network_id;
+};
+
+struct cec_op_atsc_data {
+	__u16 transport_id;
+	__u16 program_number;
+};
+
+struct cec_op_dvb_data {
+	__u16 transport_id;
+	__u16 service_id;
+	__u16 orig_network_id;
+};
+
+struct cec_op_channel_data {
+	__u8 channel_number_fmt;
+	__u16 major;
+	__u16 minor;
+};
+
+struct cec_op_digital_service_id {
+	__u8 service_id_method;
+	__u8 dig_bcast_system;
+	union {
+		struct cec_op_arib_data arib;
+		struct cec_op_atsc_data atsc;
+		struct cec_op_dvb_data dvb;
+		struct cec_op_channel_data channel;
+	};
+};
+
+struct cec_op_record_src {
+	__u8 type;
+	union {
+		struct cec_op_digital_service_id digital;
+		struct {
+			__u8 ana_bcast_type;
+			__u16 ana_freq;
+			__u8 bcast_system;
+		} analog;
+		struct {
+			__u8 plug;
+		} ext_plug;
+		struct {
+			__u16 phys_addr;
+		} ext_phys_addr;
+	};
+};
+
+static inline void cec_set_digital_service_id(__u8 *msg,
+	      const struct cec_op_digital_service_id *digital)
+{
+	*msg++ = (digital->service_id_method << 7) | digital->dig_bcast_system;
+	if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) {
+		*msg++ = (digital->channel.channel_number_fmt << 2) |
+			 (digital->channel.major >> 8);
+		*msg++ = digital->channel.major && 0xff;
+		*msg++ = digital->channel.minor >> 8;
+		*msg++ = digital->channel.minor & 0xff;
+		*msg++ = 0;
+		*msg++ = 0;
+		return;
+	}
+	switch (digital->dig_bcast_system) {
+	case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN:
+	case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE:
+	case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT:
+	case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T:
+		*msg++ = digital->atsc.transport_id >> 8;
+		*msg++ = digital->atsc.transport_id & 0xff;
+		*msg++ = digital->atsc.program_number >> 8;
+		*msg++ = digital->atsc.program_number & 0xff;
+		*msg++ = 0;
+		*msg++ = 0;
+		break;
+	default:
+		*msg++ = digital->dvb.transport_id >> 8;
+		*msg++ = digital->dvb.transport_id & 0xff;
+		*msg++ = digital->dvb.service_id >> 8;
+		*msg++ = digital->dvb.service_id & 0xff;
+		*msg++ = digital->dvb.orig_network_id >> 8;
+		*msg++ = digital->dvb.orig_network_id & 0xff;
+		break;
+	}
+}
+
+static inline void cec_get_digital_service_id(const __u8 *msg,
+	      struct cec_op_digital_service_id *digital)
+{
+	digital->service_id_method = msg[0] >> 7;
+	digital->dig_bcast_system = msg[0] & 0x7f;
+	if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) {
+		digital->channel.channel_number_fmt = msg[1] >> 2;
+		digital->channel.major = ((msg[1] & 3) << 6) | msg[2];
+		digital->channel.minor = (msg[3] << 8) | msg[4];
+		return;
+	}
+	digital->dvb.transport_id = (msg[1] << 8) | msg[2];
+	digital->dvb.service_id = (msg[3] << 8) | msg[4];
+	digital->dvb.orig_network_id = (msg[5] << 8) | msg[6];
+}
+
+static inline void cec_msg_record_on_own(struct cec_msg *msg)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_RECORD_ON;
+	msg->msg[2] = CEC_OP_RECORD_SRC_OWN;
+}
+
+static inline void cec_msg_record_on_digital(struct cec_msg *msg,
+			     const struct cec_op_digital_service_id *digital)
+{
+	msg->len = 10;
+	msg->msg[1] = CEC_MSG_RECORD_ON;
+	msg->msg[2] = CEC_OP_RECORD_SRC_DIGITAL;
+	cec_set_digital_service_id(msg->msg + 3, digital);
+}
+
+static inline void cec_msg_record_on_analog(struct cec_msg *msg,
+					    __u8 ana_bcast_type,
+					    __u16 ana_freq,
+					    __u8 bcast_system)
+{
+	msg->len = 7;
+	msg->msg[1] = CEC_MSG_RECORD_ON;
+	msg->msg[2] = CEC_OP_RECORD_SRC_ANALOG;
+	msg->msg[3] = ana_bcast_type;
+	msg->msg[4] = ana_freq >> 8;
+	msg->msg[5] = ana_freq & 0xff;
+	msg->msg[6] = bcast_system;
+}
+
+static inline void cec_msg_record_on_plug(struct cec_msg *msg,
+					  __u8 plug)
+{
+	msg->len = 4;
+	msg->msg[1] = CEC_MSG_RECORD_ON;
+	msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PLUG;
+	msg->msg[3] = plug;
+}
+
+static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg,
+					       __u16 phys_addr)
+{
+	msg->len = 5;
+	msg->msg[1] = CEC_MSG_RECORD_ON;
+	msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PHYS_ADDR;
+	msg->msg[3] = phys_addr >> 8;
+	msg->msg[4] = phys_addr & 0xff;
+}
+
+static inline void cec_msg_record_on(struct cec_msg *msg,
+				     const struct cec_op_record_src *rec_src)
+{
+	switch (rec_src->type) {
+	case CEC_OP_RECORD_SRC_OWN:
+		cec_msg_record_on_own(msg);
+		break;
+	case CEC_OP_RECORD_SRC_DIGITAL:
+		cec_msg_record_on_digital(msg, &rec_src->digital);
+		break;
+	case CEC_OP_RECORD_SRC_ANALOG:
+		cec_msg_record_on_analog(msg,
+					 rec_src->analog.ana_bcast_type,
+					 rec_src->analog.ana_freq,
+					 rec_src->analog.bcast_system);
+		break;
+	case CEC_OP_RECORD_SRC_EXT_PLUG:
+		cec_msg_record_on_plug(msg, rec_src->ext_plug.plug);
+		break;
+	case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR:
+		cec_msg_record_on_phys_addr(msg,
+					    rec_src->ext_phys_addr.phys_addr);
+		break;
+	}
+}
+
+static inline void cec_ops_record_on(const struct cec_msg *msg,
+				     struct cec_op_record_src *rec_src)
+{
+	rec_src->type = msg->msg[2];
+	switch (rec_src->type) {
+	case CEC_OP_RECORD_SRC_OWN:
+		break;
+	case CEC_OP_RECORD_SRC_DIGITAL:
+		cec_get_digital_service_id(msg->msg + 3, &rec_src->digital);
+		break;
+	case CEC_OP_RECORD_SRC_ANALOG:
+		rec_src->analog.ana_bcast_type = msg->msg[3];
+		rec_src->analog.ana_freq =
+			(msg->msg[4] << 8) | msg->msg[5];
+		rec_src->analog.bcast_system = msg->msg[6];
+		break;
+	case CEC_OP_RECORD_SRC_EXT_PLUG:
+		rec_src->ext_plug.plug = msg->msg[3];
+		break;
+	case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR:
+		rec_src->ext_phys_addr.phys_addr =
+			(msg->msg[3] << 8) | msg->msg[4];
+		break;
+	}
+}
+
+static inline void cec_msg_record_status(struct cec_msg *msg, __u8 rec_status)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_RECORD_STATUS;
+	msg->msg[2] = rec_status;
+}
+
+static inline void cec_ops_record_status(const struct cec_msg *msg,
+					 __u8 *rec_status)
+{
+	*rec_status = msg->msg[2];
+}
+
+static inline void cec_msg_record_tv_screen(struct cec_msg *msg,
+					    bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_RECORD_TV_SCREEN;
+	msg->reply = reply ? CEC_MSG_RECORD_ON : 0;
+}
+
+
+/* Timer Programming Feature */
+static inline void cec_msg_timer_status(struct cec_msg *msg,
+					__u8 timer_overlap_warning,
+					__u8 media_info,
+					__u8 prog_info,
+					__u8 prog_error,
+					__u8 duration_hr,
+					__u8 duration_min)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_TIMER_STATUS;
+	msg->msg[2] = (timer_overlap_warning << 7) |
+		(media_info << 5) |
+		(prog_info ? 0x10 : 0) |
+		(prog_info ? prog_info : prog_error);
+	if (prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE ||
+	    prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE ||
+	    prog_error == CEC_OP_PROG_ERROR_DUPLICATE) {
+		msg->len += 2;
+		msg->msg[3] = ((duration_hr / 10) << 4) | (duration_hr % 10);
+		msg->msg[4] = ((duration_min / 10) << 4) | (duration_min % 10);
+	}
+}
+
+static inline void cec_ops_timer_status(const struct cec_msg *msg,
+					__u8 *timer_overlap_warning,
+					__u8 *media_info,
+					__u8 *prog_info,
+					__u8 *prog_error,
+					__u8 *duration_hr,
+					__u8 *duration_min)
+{
+	*timer_overlap_warning = msg->msg[2] >> 7;
+	*media_info = (msg->msg[2] >> 5) & 3;
+	if (msg->msg[2] & 0x10) {
+		*prog_info = msg->msg[2] & 0xf;
+		*prog_error = 0;
+	} else {
+		*prog_info = 0;
+		*prog_error = msg->msg[2] & 0xf;
+	}
+	if (*prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE ||
+	    *prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE ||
+	    *prog_error == CEC_OP_PROG_ERROR_DUPLICATE) {
+		*duration_hr = (msg->msg[3] >> 4) * 10 + (msg->msg[3] & 0xf);
+		*duration_min = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf);
+	} else {
+		*duration_hr = *duration_min = 0;
+	}
+}
+
+static inline void cec_msg_timer_cleared_status(struct cec_msg *msg,
+						__u8 timer_cleared_status)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_TIMER_CLEARED_STATUS;
+	msg->msg[2] = timer_cleared_status;
+}
+
+static inline void cec_ops_timer_cleared_status(const struct cec_msg *msg,
+						__u8 *timer_cleared_status)
+{
+	*timer_cleared_status = msg->msg[2];
+}
+
+static inline void cec_msg_clear_analogue_timer(struct cec_msg *msg,
+						bool reply,
+						__u8 day,
+						__u8 month,
+						__u8 start_hr,
+						__u8 start_min,
+						__u8 duration_hr,
+						__u8 duration_min,
+						__u8 recording_seq,
+						__u8 ana_bcast_type,
+						__u16 ana_freq,
+						__u8 bcast_system)
+{
+	msg->len = 13;
+	msg->msg[1] = CEC_MSG_CLEAR_ANALOGUE_TIMER;
+	msg->msg[2] = day;
+	msg->msg[3] = month;
+	/* Hours and minutes are in BCD format */
+	msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10);
+	msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10);
+	msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10);
+	msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10);
+	msg->msg[8] = recording_seq;
+	msg->msg[9] = ana_bcast_type;
+	msg->msg[10] = ana_freq >> 8;
+	msg->msg[11] = ana_freq & 0xff;
+	msg->msg[12] = bcast_system;
+	msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0;
+}
+
+static inline void cec_ops_clear_analogue_timer(const struct cec_msg *msg,
+						__u8 *day,
+						__u8 *month,
+						__u8 *start_hr,
+						__u8 *start_min,
+						__u8 *duration_hr,
+						__u8 *duration_min,
+						__u8 *recording_seq,
+						__u8 *ana_bcast_type,
+						__u16 *ana_freq,
+						__u8 *bcast_system)
+{
+	*day = msg->msg[2];
+	*month = msg->msg[3];
+	/* Hours and minutes are in BCD format */
+	*start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf);
+	*start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf);
+	*duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf);
+	*duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf);
+	*recording_seq = msg->msg[8];
+	*ana_bcast_type = msg->msg[9];
+	*ana_freq = (msg->msg[10] << 8) | msg->msg[11];
+	*bcast_system = msg->msg[12];
+}
+
+static inline void cec_msg_clear_digital_timer(struct cec_msg *msg,
+				bool reply,
+				__u8 day,
+				__u8 month,
+				__u8 start_hr,
+				__u8 start_min,
+				__u8 duration_hr,
+				__u8 duration_min,
+				__u8 recording_seq,
+				const struct cec_op_digital_service_id *digital)
+{
+	msg->len = 16;
+	msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0;
+	msg->msg[1] = CEC_MSG_CLEAR_DIGITAL_TIMER;
+	msg->msg[2] = day;
+	msg->msg[3] = month;
+	/* Hours and minutes are in BCD format */
+	msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10);
+	msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10);
+	msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10);
+	msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10);
+	msg->msg[8] = recording_seq;
+	cec_set_digital_service_id(msg->msg + 9, digital);
+}
+
+static inline void cec_ops_clear_digital_timer(const struct cec_msg *msg,
+				__u8 *day,
+				__u8 *month,
+				__u8 *start_hr,
+				__u8 *start_min,
+				__u8 *duration_hr,
+				__u8 *duration_min,
+				__u8 *recording_seq,
+				struct cec_op_digital_service_id *digital)
+{
+	*day = msg->msg[2];
+	*month = msg->msg[3];
+	/* Hours and minutes are in BCD format */
+	*start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf);
+	*start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf);
+	*duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf);
+	*duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf);
+	*recording_seq = msg->msg[8];
+	cec_get_digital_service_id(msg->msg + 9, digital);
+}
+
+static inline void cec_msg_clear_ext_timer(struct cec_msg *msg,
+					   bool reply,
+					   __u8 day,
+					   __u8 month,
+					   __u8 start_hr,
+					   __u8 start_min,
+					   __u8 duration_hr,
+					   __u8 duration_min,
+					   __u8 recording_seq,
+					   __u8 ext_src_spec,
+					   __u8 plug,
+					   __u16 phys_addr)
+{
+	msg->len = 13;
+	msg->msg[1] = CEC_MSG_CLEAR_EXT_TIMER;
+	msg->msg[2] = day;
+	msg->msg[3] = month;
+	/* Hours and minutes are in BCD format */
+	msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10);
+	msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10);
+	msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10);
+	msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10);
+	msg->msg[8] = recording_seq;
+	msg->msg[9] = ext_src_spec;
+	msg->msg[10] = plug;
+	msg->msg[11] = phys_addr >> 8;
+	msg->msg[12] = phys_addr & 0xff;
+	msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0;
+}
+
+static inline void cec_ops_clear_ext_timer(const struct cec_msg *msg,
+					   __u8 *day,
+					   __u8 *month,
+					   __u8 *start_hr,
+					   __u8 *start_min,
+					   __u8 *duration_hr,
+					   __u8 *duration_min,
+					   __u8 *recording_seq,
+					   __u8 *ext_src_spec,
+					   __u8 *plug,
+					   __u16 *phys_addr)
+{
+	*day = msg->msg[2];
+	*month = msg->msg[3];
+	/* Hours and minutes are in BCD format */
+	*start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf);
+	*start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf);
+	*duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf);
+	*duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf);
+	*recording_seq = msg->msg[8];
+	*ext_src_spec = msg->msg[9];
+	*plug = msg->msg[10];
+	*phys_addr = (msg->msg[11] << 8) | msg->msg[12];
+}
+
+static inline void cec_msg_set_analogue_timer(struct cec_msg *msg,
+					      bool reply,
+					      __u8 day,
+					      __u8 month,
+					      __u8 start_hr,
+					      __u8 start_min,
+					      __u8 duration_hr,
+					      __u8 duration_min,
+					      __u8 recording_seq,
+					      __u8 ana_bcast_type,
+					      __u16 ana_freq,
+					      __u8 bcast_system)
+{
+	msg->len = 13;
+	msg->msg[1] = CEC_MSG_SET_ANALOGUE_TIMER;
+	msg->msg[2] = day;
+	msg->msg[3] = month;
+	/* Hours and minutes are in BCD format */
+	msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10);
+	msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10);
+	msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10);
+	msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10);
+	msg->msg[8] = recording_seq;
+	msg->msg[9] = ana_bcast_type;
+	msg->msg[10] = ana_freq >> 8;
+	msg->msg[11] = ana_freq & 0xff;
+	msg->msg[12] = bcast_system;
+	msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0;
+}
+
+static inline void cec_ops_set_analogue_timer(const struct cec_msg *msg,
+					      __u8 *day,
+					      __u8 *month,
+					      __u8 *start_hr,
+					      __u8 *start_min,
+					      __u8 *duration_hr,
+					      __u8 *duration_min,
+					      __u8 *recording_seq,
+					      __u8 *ana_bcast_type,
+					      __u16 *ana_freq,
+					      __u8 *bcast_system)
+{
+	*day = msg->msg[2];
+	*month = msg->msg[3];
+	/* Hours and minutes are in BCD format */
+	*start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf);
+	*start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf);
+	*duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf);
+	*duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf);
+	*recording_seq = msg->msg[8];
+	*ana_bcast_type = msg->msg[9];
+	*ana_freq = (msg->msg[10] << 8) | msg->msg[11];
+	*bcast_system = msg->msg[12];
+}
+
+static inline void cec_msg_set_digital_timer(struct cec_msg *msg,
+			bool reply,
+			__u8 day,
+			__u8 month,
+			__u8 start_hr,
+			__u8 start_min,
+			__u8 duration_hr,
+			__u8 duration_min,
+			__u8 recording_seq,
+			const struct cec_op_digital_service_id *digital)
+{
+	msg->len = 16;
+	msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0;
+	msg->msg[1] = CEC_MSG_SET_DIGITAL_TIMER;
+	msg->msg[2] = day;
+	msg->msg[3] = month;
+	/* Hours and minutes are in BCD format */
+	msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10);
+	msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10);
+	msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10);
+	msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10);
+	msg->msg[8] = recording_seq;
+	cec_set_digital_service_id(msg->msg + 9, digital);
+}
+
+static inline void cec_ops_set_digital_timer(const struct cec_msg *msg,
+			__u8 *day,
+			__u8 *month,
+			__u8 *start_hr,
+			__u8 *start_min,
+			__u8 *duration_hr,
+			__u8 *duration_min,
+			__u8 *recording_seq,
+			struct cec_op_digital_service_id *digital)
+{
+	*day = msg->msg[2];
+	*month = msg->msg[3];
+	/* Hours and minutes are in BCD format */
+	*start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf);
+	*start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf);
+	*duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf);
+	*duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf);
+	*recording_seq = msg->msg[8];
+	cec_get_digital_service_id(msg->msg + 9, digital);
+}
+
+static inline void cec_msg_set_ext_timer(struct cec_msg *msg,
+					 bool reply,
+					 __u8 day,
+					 __u8 month,
+					 __u8 start_hr,
+					 __u8 start_min,
+					 __u8 duration_hr,
+					 __u8 duration_min,
+					 __u8 recording_seq,
+					 __u8 ext_src_spec,
+					 __u8 plug,
+					 __u16 phys_addr)
+{
+	msg->len = 13;
+	msg->msg[1] = CEC_MSG_SET_EXT_TIMER;
+	msg->msg[2] = day;
+	msg->msg[3] = month;
+	/* Hours and minutes are in BCD format */
+	msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10);
+	msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10);
+	msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10);
+	msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10);
+	msg->msg[8] = recording_seq;
+	msg->msg[9] = ext_src_spec;
+	msg->msg[10] = plug;
+	msg->msg[11] = phys_addr >> 8;
+	msg->msg[12] = phys_addr & 0xff;
+	msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0;
+}
+
+static inline void cec_ops_set_ext_timer(const struct cec_msg *msg,
+					 __u8 *day,
+					 __u8 *month,
+					 __u8 *start_hr,
+					 __u8 *start_min,
+					 __u8 *duration_hr,
+					 __u8 *duration_min,
+					 __u8 *recording_seq,
+					 __u8 *ext_src_spec,
+					 __u8 *plug,
+					 __u16 *phys_addr)
+{
+	*day = msg->msg[2];
+	*month = msg->msg[3];
+	/* Hours and minutes are in BCD format */
+	*start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf);
+	*start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf);
+	*duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf);
+	*duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf);
+	*recording_seq = msg->msg[8];
+	*ext_src_spec = msg->msg[9];
+	*plug = msg->msg[10];
+	*phys_addr = (msg->msg[11] << 8) | msg->msg[12];
+}
+
+static inline void cec_msg_set_timer_program_title(struct cec_msg *msg,
+						   const char *prog_title)
+{
+	unsigned int len = strlen(prog_title);
+
+	if (len > 14)
+		len = 14;
+	msg->len = 2 + len;
+	msg->msg[1] = CEC_MSG_SET_TIMER_PROGRAM_TITLE;
+	memcpy(msg->msg + 2, prog_title, len);
+}
+
+static inline void cec_ops_set_timer_program_title(const struct cec_msg *msg,
+						   char *prog_title)
+{
+	unsigned int len = msg->len > 2 ? msg->len - 2 : 0;
+
+	if (len > 14)
+		len = 14;
+	memcpy(prog_title, msg->msg + 2, len);
+	prog_title[len] = '\0';
+}
+
+/* System Information Feature */
+static inline void cec_msg_cec_version(struct cec_msg *msg, __u8 cec_version)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_CEC_VERSION;
+	msg->msg[2] = cec_version;
+}
+
+static inline void cec_ops_cec_version(const struct cec_msg *msg,
+				       __u8 *cec_version)
+{
+	*cec_version = msg->msg[2];
+}
+
+static inline void cec_msg_get_cec_version(struct cec_msg *msg,
+					   bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GET_CEC_VERSION;
+	msg->reply = reply ? CEC_MSG_CEC_VERSION : 0;
+}
+
+static inline void cec_msg_report_physical_addr(struct cec_msg *msg,
+					__u16 phys_addr, __u8 prim_devtype)
+{
+	msg->len = 5;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_REPORT_PHYSICAL_ADDR;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+	msg->msg[4] = prim_devtype;
+}
+
+static inline void cec_ops_report_physical_addr(const struct cec_msg *msg,
+					__u16 *phys_addr, __u8 *prim_devtype)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*prim_devtype = msg->msg[4];
+}
+
+static inline void cec_msg_give_physical_addr(struct cec_msg *msg,
+					      bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GIVE_PHYSICAL_ADDR;
+	msg->reply = reply ? CEC_MSG_REPORT_PHYSICAL_ADDR : 0;
+}
+
+static inline void cec_msg_set_menu_language(struct cec_msg *msg,
+					     const char *language)
+{
+	msg->len = 5;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_SET_MENU_LANGUAGE;
+	memcpy(msg->msg + 2, language, 3);
+}
+
+static inline void cec_ops_set_menu_language(const struct cec_msg *msg,
+					     char *language)
+{
+	memcpy(language, msg->msg + 2, 3);
+	language[3] = '\0';
+}
+
+static inline void cec_msg_get_menu_language(struct cec_msg *msg,
+					     bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GET_MENU_LANGUAGE;
+	msg->reply = reply ? CEC_MSG_SET_MENU_LANGUAGE : 0;
+}
+
+/*
+ * Assumes a single RC Profile byte and a single Device Features byte,
+ * i.e. no extended features are supported by this helper function.
+ *
+ * As of CEC 2.0 no extended features are defined, should those be added
+ * in the future, then this function needs to be adapted or a new function
+ * should be added.
+ */
+static inline void cec_msg_report_features(struct cec_msg *msg,
+				__u8 cec_version, __u8 all_device_types,
+				__u8 rc_profile, __u8 dev_features)
+{
+	msg->len = 6;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_REPORT_FEATURES;
+	msg->msg[2] = cec_version;
+	msg->msg[3] = all_device_types;
+	msg->msg[4] = rc_profile;
+	msg->msg[5] = dev_features;
+}
+
+static inline void cec_ops_report_features(const struct cec_msg *msg,
+			__u8 *cec_version, __u8 *all_device_types,
+			const __u8 **rc_profile, const __u8 **dev_features)
+{
+	const __u8 *p = &msg->msg[4];
+
+	*cec_version = msg->msg[2];
+	*all_device_types = msg->msg[3];
+	*rc_profile = p;
+	while (p < &msg->msg[14] && (*p & CEC_OP_FEAT_EXT))
+		p++;
+	if (!(*p & CEC_OP_FEAT_EXT)) {
+		*dev_features = p + 1;
+		while (p < &msg->msg[15] && (*p & CEC_OP_FEAT_EXT))
+			p++;
+	}
+	if (*p & CEC_OP_FEAT_EXT)
+		*rc_profile = *dev_features = NULL;
+}
+
+static inline void cec_msg_give_features(struct cec_msg *msg,
+					 bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GIVE_FEATURES;
+	msg->reply = reply ? CEC_MSG_REPORT_FEATURES : 0;
+}
+
+/* Deck Control Feature */
+static inline void cec_msg_deck_control(struct cec_msg *msg,
+					__u8 deck_control_mode)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_DECK_CONTROL;
+	msg->msg[2] = deck_control_mode;
+}
+
+static inline void cec_ops_deck_control(const struct cec_msg *msg,
+					__u8 *deck_control_mode)
+{
+	*deck_control_mode = msg->msg[2];
+}
+
+static inline void cec_msg_deck_status(struct cec_msg *msg,
+				       __u8 deck_info)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_DECK_STATUS;
+	msg->msg[2] = deck_info;
+}
+
+static inline void cec_ops_deck_status(const struct cec_msg *msg,
+				       __u8 *deck_info)
+{
+	*deck_info = msg->msg[2];
+}
+
+static inline void cec_msg_give_deck_status(struct cec_msg *msg,
+					    bool reply,
+					    __u8 status_req)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_GIVE_DECK_STATUS;
+	msg->msg[2] = status_req;
+	msg->reply = reply ? CEC_MSG_DECK_STATUS : 0;
+}
+
+static inline void cec_ops_give_deck_status(const struct cec_msg *msg,
+					    __u8 *status_req)
+{
+	*status_req = msg->msg[2];
+}
+
+static inline void cec_msg_play(struct cec_msg *msg,
+				__u8 play_mode)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_PLAY;
+	msg->msg[2] = play_mode;
+}
+
+static inline void cec_ops_play(const struct cec_msg *msg,
+				__u8 *play_mode)
+{
+	*play_mode = msg->msg[2];
+}
+
+
+/* Tuner Control Feature */
+struct cec_op_tuner_device_info {
+	__u8 rec_flag;
+	__u8 tuner_display_info;
+	bool is_analog;
+	union {
+		struct cec_op_digital_service_id digital;
+		struct {
+			__u8 ana_bcast_type;
+			__u16 ana_freq;
+			__u8 bcast_system;
+		} analog;
+	};
+};
+
+static inline void cec_msg_tuner_device_status_analog(struct cec_msg *msg,
+						      __u8 rec_flag,
+						      __u8 tuner_display_info,
+						      __u8 ana_bcast_type,
+						      __u16 ana_freq,
+						      __u8 bcast_system)
+{
+	msg->len = 7;
+	msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS;
+	msg->msg[2] = (rec_flag << 7) | tuner_display_info;
+	msg->msg[3] = ana_bcast_type;
+	msg->msg[4] = ana_freq >> 8;
+	msg->msg[5] = ana_freq & 0xff;
+	msg->msg[6] = bcast_system;
+}
+
+static inline void cec_msg_tuner_device_status_digital(struct cec_msg *msg,
+		   __u8 rec_flag, __u8 tuner_display_info,
+		   const struct cec_op_digital_service_id *digital)
+{
+	msg->len = 10;
+	msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS;
+	msg->msg[2] = (rec_flag << 7) | tuner_display_info;
+	cec_set_digital_service_id(msg->msg + 3, digital);
+}
+
+static inline void cec_msg_tuner_device_status(struct cec_msg *msg,
+			const struct cec_op_tuner_device_info *tuner_dev_info)
+{
+	if (tuner_dev_info->is_analog)
+		cec_msg_tuner_device_status_analog(msg,
+			tuner_dev_info->rec_flag,
+			tuner_dev_info->tuner_display_info,
+			tuner_dev_info->analog.ana_bcast_type,
+			tuner_dev_info->analog.ana_freq,
+			tuner_dev_info->analog.bcast_system);
+	else
+		cec_msg_tuner_device_status_digital(msg,
+			tuner_dev_info->rec_flag,
+			tuner_dev_info->tuner_display_info,
+			&tuner_dev_info->digital);
+}
+
+static inline void cec_ops_tuner_device_status(const struct cec_msg *msg,
+				struct cec_op_tuner_device_info *tuner_dev_info)
+{
+	tuner_dev_info->is_analog = msg->len < 10;
+	tuner_dev_info->rec_flag = msg->msg[2] >> 7;
+	tuner_dev_info->tuner_display_info = msg->msg[2] & 0x7f;
+	if (tuner_dev_info->is_analog) {
+		tuner_dev_info->analog.ana_bcast_type = msg->msg[3];
+		tuner_dev_info->analog.ana_freq = (msg->msg[4] << 8) | msg->msg[5];
+		tuner_dev_info->analog.bcast_system = msg->msg[6];
+		return;
+	}
+	cec_get_digital_service_id(msg->msg + 3, &tuner_dev_info->digital);
+}
+
+static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg,
+						    bool reply,
+						    __u8 status_req)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_GIVE_TUNER_DEVICE_STATUS;
+	msg->msg[2] = status_req;
+	msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0;
+}
+
+static inline void cec_ops_give_tuner_device_status(const struct cec_msg *msg,
+						    __u8 *status_req)
+{
+	*status_req = msg->msg[2];
+}
+
+static inline void cec_msg_select_analogue_service(struct cec_msg *msg,
+						   __u8 ana_bcast_type,
+						   __u16 ana_freq,
+						   __u8 bcast_system)
+{
+	msg->len = 6;
+	msg->msg[1] = CEC_MSG_SELECT_ANALOGUE_SERVICE;
+	msg->msg[2] = ana_bcast_type;
+	msg->msg[3] = ana_freq >> 8;
+	msg->msg[4] = ana_freq & 0xff;
+	msg->msg[5] = bcast_system;
+}
+
+static inline void cec_ops_select_analogue_service(const struct cec_msg *msg,
+						   __u8 *ana_bcast_type,
+						   __u16 *ana_freq,
+						   __u8 *bcast_system)
+{
+	*ana_bcast_type = msg->msg[2];
+	*ana_freq = (msg->msg[3] << 8) | msg->msg[4];
+	*bcast_system = msg->msg[5];
+}
+
+static inline void cec_msg_select_digital_service(struct cec_msg *msg,
+				const struct cec_op_digital_service_id *digital)
+{
+	msg->len = 9;
+	msg->msg[1] = CEC_MSG_SELECT_DIGITAL_SERVICE;
+	cec_set_digital_service_id(msg->msg + 2, digital);
+}
+
+static inline void cec_ops_select_digital_service(const struct cec_msg *msg,
+				struct cec_op_digital_service_id *digital)
+{
+	cec_get_digital_service_id(msg->msg + 2, digital);
+}
+
+static inline void cec_msg_tuner_step_decrement(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_TUNER_STEP_DECREMENT;
+}
+
+static inline void cec_msg_tuner_step_increment(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_TUNER_STEP_INCREMENT;
+}
+
+
+/* Vendor Specific Commands Feature */
+static inline void cec_msg_device_vendor_id(struct cec_msg *msg, __u32 vendor_id)
+{
+	msg->len = 5;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_DEVICE_VENDOR_ID;
+	msg->msg[2] = vendor_id >> 16;
+	msg->msg[3] = (vendor_id >> 8) & 0xff;
+	msg->msg[4] = vendor_id & 0xff;
+}
+
+static inline void cec_ops_device_vendor_id(const struct cec_msg *msg,
+					    __u32 *vendor_id)
+{
+	*vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4];
+}
+
+static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg,
+						 bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GIVE_DEVICE_VENDOR_ID;
+	msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0;
+}
+
+static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_UP;
+}
+
+
+/* OSD Display Feature */
+static inline void cec_msg_set_osd_string(struct cec_msg *msg,
+					  __u8 disp_ctl,
+					  const char *osd)
+{
+	unsigned int len = strlen(osd);
+
+	if (len > 13)
+		len = 13;
+	msg->len = 3 + len;
+	msg->msg[1] = CEC_MSG_SET_OSD_STRING;
+	msg->msg[2] = disp_ctl;
+	memcpy(msg->msg + 3, osd, len);
+}
+
+static inline void cec_ops_set_osd_string(const struct cec_msg *msg,
+					  __u8 *disp_ctl,
+					  char *osd)
+{
+	unsigned int len = msg->len > 3 ? msg->len - 3 : 0;
+
+	*disp_ctl = msg->msg[2];
+	if (len > 13)
+		len = 13;
+	memcpy(osd, msg->msg + 3, len);
+	osd[len] = '\0';
+}
+
+
+/* Device OSD Transfer Feature */
+static inline void cec_msg_set_osd_name(struct cec_msg *msg, const char *name)
+{
+	unsigned int len = strlen(name);
+
+	if (len > 14)
+		len = 14;
+	msg->len = 2 + len;
+	msg->msg[1] = CEC_MSG_SET_OSD_NAME;
+	memcpy(msg->msg + 2, name, len);
+}
+
+static inline void cec_ops_set_osd_name(const struct cec_msg *msg,
+					char *name)
+{
+	unsigned int len = msg->len > 2 ? msg->len - 2 : 0;
+
+	if (len > 14)
+		len = 14;
+	memcpy(name, msg->msg + 2, len);
+	name[len] = '\0';
+}
+
+static inline void cec_msg_give_osd_name(struct cec_msg *msg,
+					 bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GIVE_OSD_NAME;
+	msg->reply = reply ? CEC_MSG_SET_OSD_NAME : 0;
+}
+
+
+/* Device Menu Control Feature */
+static inline void cec_msg_menu_status(struct cec_msg *msg,
+				       __u8 menu_state)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_MENU_STATUS;
+	msg->msg[2] = menu_state;
+}
+
+static inline void cec_ops_menu_status(const struct cec_msg *msg,
+				       __u8 *menu_state)
+{
+	*menu_state = msg->msg[2];
+}
+
+static inline void cec_msg_menu_request(struct cec_msg *msg,
+					bool reply,
+					__u8 menu_req)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_MENU_REQUEST;
+	msg->msg[2] = menu_req;
+	msg->reply = reply ? CEC_MSG_MENU_STATUS : 0;
+}
+
+static inline void cec_ops_menu_request(const struct cec_msg *msg,
+					__u8 *menu_req)
+{
+	*menu_req = msg->msg[2];
+}
+
+struct cec_op_ui_command {
+	__u8 ui_cmd;
+	bool has_opt_arg;
+	union {
+		struct cec_op_channel_data channel_identifier;
+		__u8 ui_broadcast_type;
+		__u8 ui_sound_presentation_control;
+		__u8 play_mode;
+		__u8 ui_function_media;
+		__u8 ui_function_select_av_input;
+		__u8 ui_function_select_audio_input;
+	};
+};
+
+static inline void cec_msg_user_control_pressed(struct cec_msg *msg,
+					const struct cec_op_ui_command *ui_cmd)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_USER_CONTROL_PRESSED;
+	msg->msg[2] = ui_cmd->ui_cmd;
+	if (!ui_cmd->has_opt_arg)
+		return;
+	switch (ui_cmd->ui_cmd) {
+	case 0x56:
+	case 0x57:
+	case 0x60:
+	case 0x68:
+	case 0x69:
+	case 0x6a:
+		/* The optional operand is one byte for all these ui commands */
+		msg->len++;
+		msg->msg[3] = ui_cmd->play_mode;
+		break;
+	case 0x67:
+		msg->len += 4;
+		msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) |
+			      (ui_cmd->channel_identifier.major >> 8);
+		msg->msg[4] = ui_cmd->channel_identifier.major && 0xff;
+		msg->msg[5] = ui_cmd->channel_identifier.minor >> 8;
+		msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff;
+		break;
+	}
+}
+
+static inline void cec_ops_user_control_pressed(const struct cec_msg *msg,
+						struct cec_op_ui_command *ui_cmd)
+{
+	ui_cmd->ui_cmd = msg->msg[2];
+	ui_cmd->has_opt_arg = false;
+	if (msg->len == 3)
+		return;
+	switch (ui_cmd->ui_cmd) {
+	case 0x56:
+	case 0x57:
+	case 0x60:
+	case 0x68:
+	case 0x69:
+	case 0x6a:
+		/* The optional operand is one byte for all these ui commands */
+		ui_cmd->play_mode = msg->msg[3];
+		ui_cmd->has_opt_arg = true;
+		break;
+	case 0x67:
+		if (msg->len < 7)
+			break;
+		ui_cmd->has_opt_arg = true;
+		ui_cmd->channel_identifier.channel_number_fmt = msg->msg[3] >> 2;
+		ui_cmd->channel_identifier.major = ((msg->msg[3] & 3) << 6) | msg->msg[4];
+		ui_cmd->channel_identifier.minor = (msg->msg[5] << 8) | msg->msg[6];
+		break;
+	}
+}
+
+static inline void cec_msg_user_control_released(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_USER_CONTROL_RELEASED;
+}
+
+/* Remote Control Passthrough Feature */
+
+/* Power Status Feature */
+static inline void cec_msg_report_power_status(struct cec_msg *msg,
+					       __u8 pwr_state)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_REPORT_POWER_STATUS;
+	msg->msg[2] = pwr_state;
+}
+
+static inline void cec_ops_report_power_status(const struct cec_msg *msg,
+					       __u8 *pwr_state)
+{
+	*pwr_state = msg->msg[2];
+}
+
+static inline void cec_msg_give_device_power_status(struct cec_msg *msg,
+						    bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GIVE_DEVICE_POWER_STATUS;
+	msg->reply = reply ? CEC_MSG_REPORT_POWER_STATUS : 0;
+}
+
+/* General Protocol Messages */
+static inline void cec_msg_feature_abort(struct cec_msg *msg,
+					 __u8 abort_msg, __u8 reason)
+{
+	msg->len = 4;
+	msg->msg[1] = CEC_MSG_FEATURE_ABORT;
+	msg->msg[2] = abort_msg;
+	msg->msg[3] = reason;
+}
+
+static inline void cec_ops_feature_abort(const struct cec_msg *msg,
+					 __u8 *abort_msg, __u8 *reason)
+{
+	*abort_msg = msg->msg[2];
+	*reason = msg->msg[3];
+}
+
+/* This changes the current message into a feature abort message */
+static inline void cec_msg_reply_feature_abort(struct cec_msg *msg, __u8 reason)
+{
+	cec_msg_set_reply_to(msg, msg);
+	msg->len = 4;
+	msg->msg[2] = msg->msg[1];
+	msg->msg[3] = reason;
+	msg->msg[1] = CEC_MSG_FEATURE_ABORT;
+}
+
+static inline void cec_msg_abort(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_ABORT;
+}
+
+
+/* System Audio Control Feature */
+static inline void cec_msg_report_audio_status(struct cec_msg *msg,
+					       __u8 aud_mute_status,
+					       __u8 aud_vol_status)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_REPORT_AUDIO_STATUS;
+	msg->msg[2] = (aud_mute_status << 7) | (aud_vol_status & 0x7f);
+}
+
+static inline void cec_ops_report_audio_status(const struct cec_msg *msg,
+					       __u8 *aud_mute_status,
+					       __u8 *aud_vol_status)
+{
+	*aud_mute_status = msg->msg[2] >> 7;
+	*aud_vol_status = msg->msg[2] & 0x7f;
+}
+
+static inline void cec_msg_give_audio_status(struct cec_msg *msg,
+					     bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GIVE_AUDIO_STATUS;
+	msg->reply = reply ? CEC_MSG_REPORT_AUDIO_STATUS : 0;
+}
+
+static inline void cec_msg_set_system_audio_mode(struct cec_msg *msg,
+						 __u8 sys_aud_status)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_SET_SYSTEM_AUDIO_MODE;
+	msg->msg[2] = sys_aud_status;
+}
+
+static inline void cec_ops_set_system_audio_mode(const struct cec_msg *msg,
+						 __u8 *sys_aud_status)
+{
+	*sys_aud_status = msg->msg[2];
+}
+
+static inline void cec_msg_system_audio_mode_request(struct cec_msg *msg,
+						     bool reply,
+						     __u16 phys_addr)
+{
+	msg->len = phys_addr == 0xffff ? 2 : 4;
+	msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+	msg->reply = reply ? CEC_MSG_SET_SYSTEM_AUDIO_MODE : 0;
+
+}
+
+static inline void cec_ops_system_audio_mode_request(const struct cec_msg *msg,
+						     __u16 *phys_addr)
+{
+	if (msg->len < 4)
+		*phys_addr = 0xffff;
+	else
+		*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+static inline void cec_msg_system_audio_mode_status(struct cec_msg *msg,
+						    __u8 sys_aud_status)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_STATUS;
+	msg->msg[2] = sys_aud_status;
+}
+
+static inline void cec_ops_system_audio_mode_status(const struct cec_msg *msg,
+						    __u8 *sys_aud_status)
+{
+	*sys_aud_status = msg->msg[2];
+}
+
+static inline void cec_msg_give_system_audio_mode_status(struct cec_msg *msg,
+							 bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS;
+	msg->reply = reply ? CEC_MSG_SYSTEM_AUDIO_MODE_STATUS : 0;
+}
+
+static inline void cec_msg_report_short_audio_descriptor(struct cec_msg *msg,
+					__u8 num_descriptors,
+					const __u32 *descriptors)
+{
+	unsigned int i;
+
+	if (num_descriptors > 4)
+		num_descriptors = 4;
+	msg->len = 2 + num_descriptors * 3;
+	msg->msg[1] = CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR;
+	for (i = 0; i < num_descriptors; i++) {
+		msg->msg[2 + i * 3] = (descriptors[i] >> 16) & 0xff;
+		msg->msg[3 + i * 3] = (descriptors[i] >> 8) & 0xff;
+		msg->msg[4 + i * 3] = descriptors[i] & 0xff;
+	}
+}
+
+static inline void cec_ops_report_short_audio_descriptor(const struct cec_msg *msg,
+							 __u8 *num_descriptors,
+							 __u32 *descriptors)
+{
+	unsigned int i;
+
+	*num_descriptors = (msg->len - 2) / 3;
+	if (*num_descriptors > 4)
+		*num_descriptors = 4;
+	for (i = 0; i < *num_descriptors; i++)
+		descriptors[i] = (msg->msg[2 + i * 3] << 16) |
+			(msg->msg[3 + i * 3] << 8) |
+			msg->msg[4 + i * 3];
+}
+
+static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg,
+					bool reply,
+					__u8 num_descriptors,
+					const __u8 *audio_format_id,
+					const __u8 *audio_format_code)
+{
+	unsigned int i;
+
+	if (num_descriptors > 4)
+		num_descriptors = 4;
+	msg->len = 2 + num_descriptors;
+	msg->msg[1] = CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR;
+	msg->reply = reply ? CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR : 0;
+	for (i = 0; i < num_descriptors; i++)
+		msg->msg[2 + i] = (audio_format_id[i] << 6) |
+				  (audio_format_code[i] & 0x3f);
+}
+
+static inline void cec_ops_request_short_audio_descriptor(const struct cec_msg *msg,
+					__u8 *num_descriptors,
+					__u8 *audio_format_id,
+					__u8 *audio_format_code)
+{
+	unsigned int i;
+
+	*num_descriptors = msg->len - 2;
+	if (*num_descriptors > 4)
+		*num_descriptors = 4;
+	for (i = 0; i < *num_descriptors; i++) {
+		audio_format_id[i] = msg->msg[2 + i] >> 6;
+		audio_format_code[i] = msg->msg[2 + i] & 0x3f;
+	}
+}
+
+
+/* Audio Rate Control Feature */
+static inline void cec_msg_set_audio_rate(struct cec_msg *msg,
+					  __u8 audio_rate)
+{
+	msg->len = 3;
+	msg->msg[1] = CEC_MSG_SET_AUDIO_RATE;
+	msg->msg[2] = audio_rate;
+}
+
+static inline void cec_ops_set_audio_rate(const struct cec_msg *msg,
+					  __u8 *audio_rate)
+{
+	*audio_rate = msg->msg[2];
+}
+
+
+/* Audio Return Channel Control Feature */
+static inline void cec_msg_report_arc_initiated(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_REPORT_ARC_INITIATED;
+}
+
+static inline void cec_msg_initiate_arc(struct cec_msg *msg,
+					bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_INITIATE_ARC;
+	msg->reply = reply ? CEC_MSG_REPORT_ARC_INITIATED : 0;
+}
+
+static inline void cec_msg_request_arc_initiation(struct cec_msg *msg,
+						  bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_REQUEST_ARC_INITIATION;
+	msg->reply = reply ? CEC_MSG_INITIATE_ARC : 0;
+}
+
+static inline void cec_msg_report_arc_terminated(struct cec_msg *msg)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_REPORT_ARC_TERMINATED;
+}
+
+static inline void cec_msg_terminate_arc(struct cec_msg *msg,
+					 bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_TERMINATE_ARC;
+	msg->reply = reply ? CEC_MSG_REPORT_ARC_TERMINATED : 0;
+}
+
+static inline void cec_msg_request_arc_termination(struct cec_msg *msg,
+						   bool reply)
+{
+	msg->len = 2;
+	msg->msg[1] = CEC_MSG_REQUEST_ARC_TERMINATION;
+	msg->reply = reply ? CEC_MSG_TERMINATE_ARC : 0;
+}
+
+
+/* Dynamic Audio Lipsync Feature */
+/* Only for CEC 2.0 and up */
+static inline void cec_msg_report_current_latency(struct cec_msg *msg,
+						  __u16 phys_addr,
+						  __u8 video_latency,
+						  __u8 low_latency_mode,
+						  __u8 audio_out_compensated,
+						  __u8 audio_out_delay)
+{
+	msg->len = 7;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+	msg->msg[4] = video_latency;
+	msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated;
+	msg->msg[6] = audio_out_delay;
+}
+
+static inline void cec_ops_report_current_latency(const struct cec_msg *msg,
+						  __u16 *phys_addr,
+						  __u8 *video_latency,
+						  __u8 *low_latency_mode,
+						  __u8 *audio_out_compensated,
+						  __u8 *audio_out_delay)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*video_latency = msg->msg[4];
+	*low_latency_mode = (msg->msg[5] >> 2) & 1;
+	*audio_out_compensated = msg->msg[5] & 3;
+	*audio_out_delay = msg->msg[6];
+}
+
+static inline void cec_msg_request_current_latency(struct cec_msg *msg,
+						   bool reply,
+						   __u16 phys_addr)
+{
+	msg->len = 4;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_REQUEST_CURRENT_LATENCY;
+	msg->msg[2] = phys_addr >> 8;
+	msg->msg[3] = phys_addr & 0xff;
+	msg->reply = reply ? CEC_MSG_REPORT_CURRENT_LATENCY : 0;
+}
+
+static inline void cec_ops_request_current_latency(const struct cec_msg *msg,
+						   __u16 *phys_addr)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+
+/* Capability Discovery and Control Feature */
+static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg,
+						 __u16 phys_addr1,
+						 __u16 phys_addr2)
+{
+	msg->len = 9;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE;
+	msg->msg[5] = phys_addr1 >> 8;
+	msg->msg[6] = phys_addr1 & 0xff;
+	msg->msg[7] = phys_addr2 >> 8;
+	msg->msg[8] = phys_addr2 & 0xff;
+}
+
+static inline void cec_ops_cdc_hec_inquire_state(const struct cec_msg *msg,
+						 __u16 *phys_addr,
+						 __u16 *phys_addr1,
+						 __u16 *phys_addr2)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*phys_addr1 = (msg->msg[5] << 8) | msg->msg[6];
+	*phys_addr2 = (msg->msg[7] << 8) | msg->msg[8];
+}
+
+static inline void cec_msg_cdc_hec_report_state(struct cec_msg *msg,
+						__u16 target_phys_addr,
+						__u8 hec_func_state,
+						__u8 host_func_state,
+						__u8 enc_func_state,
+						__u8 cdc_errcode,
+						__u8 has_field,
+						__u16 hec_field)
+{
+	msg->len = has_field ? 10 : 8;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HEC_REPORT_STATE;
+	msg->msg[5] = target_phys_addr >> 8;
+	msg->msg[6] = target_phys_addr & 0xff;
+	msg->msg[7] = (hec_func_state << 6) |
+		      (host_func_state << 4) |
+		      (enc_func_state << 2) |
+		      cdc_errcode;
+	if (has_field) {
+		msg->msg[8] = hec_field >> 8;
+		msg->msg[9] = hec_field & 0xff;
+	}
+}
+
+static inline void cec_ops_cdc_hec_report_state(const struct cec_msg *msg,
+						__u16 *phys_addr,
+						__u16 *target_phys_addr,
+						__u8 *hec_func_state,
+						__u8 *host_func_state,
+						__u8 *enc_func_state,
+						__u8 *cdc_errcode,
+						__u8 *has_field,
+						__u16 *hec_field)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*target_phys_addr = (msg->msg[5] << 8) | msg->msg[6];
+	*hec_func_state = msg->msg[7] >> 6;
+	*host_func_state = (msg->msg[7] >> 4) & 3;
+	*enc_func_state = (msg->msg[7] >> 4) & 3;
+	*cdc_errcode = msg->msg[7] & 3;
+	*has_field = msg->len >= 10;
+	*hec_field = *has_field ? ((msg->msg[8] << 8) | msg->msg[9]) : 0;
+}
+
+static inline void cec_msg_cdc_hec_set_state(struct cec_msg *msg,
+					     __u16 phys_addr1,
+					     __u16 phys_addr2,
+					     __u8 hec_set_state,
+					     __u16 phys_addr3,
+					     __u16 phys_addr4,
+					     __u16 phys_addr5)
+{
+	msg->len = 10;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE;
+	msg->msg[5] = phys_addr1 >> 8;
+	msg->msg[6] = phys_addr1 & 0xff;
+	msg->msg[7] = phys_addr2 >> 8;
+	msg->msg[8] = phys_addr2 & 0xff;
+	msg->msg[9] = hec_set_state;
+	if (phys_addr3 != CEC_PHYS_ADDR_INVALID) {
+		msg->msg[msg->len++] = phys_addr3 >> 8;
+		msg->msg[msg->len++] = phys_addr3 & 0xff;
+		if (phys_addr4 != CEC_PHYS_ADDR_INVALID) {
+			msg->msg[msg->len++] = phys_addr4 >> 8;
+			msg->msg[msg->len++] = phys_addr4 & 0xff;
+			if (phys_addr5 != CEC_PHYS_ADDR_INVALID) {
+				msg->msg[msg->len++] = phys_addr5 >> 8;
+				msg->msg[msg->len++] = phys_addr5 & 0xff;
+			}
+		}
+	}
+}
+
+static inline void cec_ops_cdc_hec_set_state(const struct cec_msg *msg,
+					     __u16 *phys_addr,
+					     __u16 *phys_addr1,
+					     __u16 *phys_addr2,
+					     __u8 *hec_set_state,
+					     __u16 *phys_addr3,
+					     __u16 *phys_addr4,
+					     __u16 *phys_addr5)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*phys_addr1 = (msg->msg[5] << 8) | msg->msg[6];
+	*phys_addr2 = (msg->msg[7] << 8) | msg->msg[8];
+	*hec_set_state = msg->msg[9];
+	*phys_addr3 = *phys_addr4 = *phys_addr5 = CEC_PHYS_ADDR_INVALID;
+	if (msg->len >= 12)
+		*phys_addr3 = (msg->msg[10] << 8) | msg->msg[11];
+	if (msg->len >= 14)
+		*phys_addr4 = (msg->msg[12] << 8) | msg->msg[13];
+	if (msg->len >= 16)
+		*phys_addr5 = (msg->msg[14] << 8) | msg->msg[15];
+}
+
+static inline void cec_msg_cdc_hec_set_state_adjacent(struct cec_msg *msg,
+						      __u16 phys_addr1,
+						      __u8 hec_set_state)
+{
+	msg->len = 8;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HEC_SET_STATE_ADJACENT;
+	msg->msg[5] = phys_addr1 >> 8;
+	msg->msg[6] = phys_addr1 & 0xff;
+	msg->msg[7] = hec_set_state;
+}
+
+static inline void cec_ops_cdc_hec_set_state_adjacent(const struct cec_msg *msg,
+						      __u16 *phys_addr,
+						      __u16 *phys_addr1,
+						      __u8 *hec_set_state)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*phys_addr1 = (msg->msg[5] << 8) | msg->msg[6];
+	*hec_set_state = msg->msg[7];
+}
+
+static inline void cec_msg_cdc_hec_request_deactivation(struct cec_msg *msg,
+							__u16 phys_addr1,
+							__u16 phys_addr2,
+							__u16 phys_addr3)
+{
+	msg->len = 11;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION;
+	msg->msg[5] = phys_addr1 >> 8;
+	msg->msg[6] = phys_addr1 & 0xff;
+	msg->msg[7] = phys_addr2 >> 8;
+	msg->msg[8] = phys_addr2 & 0xff;
+	msg->msg[9] = phys_addr3 >> 8;
+	msg->msg[10] = phys_addr3 & 0xff;
+}
+
+static inline void cec_ops_cdc_hec_request_deactivation(const struct cec_msg *msg,
+							__u16 *phys_addr,
+							__u16 *phys_addr1,
+							__u16 *phys_addr2,
+							__u16 *phys_addr3)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*phys_addr1 = (msg->msg[5] << 8) | msg->msg[6];
+	*phys_addr2 = (msg->msg[7] << 8) | msg->msg[8];
+	*phys_addr3 = (msg->msg[9] << 8) | msg->msg[10];
+}
+
+static inline void cec_msg_cdc_hec_notify_alive(struct cec_msg *msg)
+{
+	msg->len = 5;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HEC_NOTIFY_ALIVE;
+}
+
+static inline void cec_ops_cdc_hec_notify_alive(const struct cec_msg *msg,
+						__u16 *phys_addr)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+static inline void cec_msg_cdc_hec_discover(struct cec_msg *msg)
+{
+	msg->len = 5;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HEC_DISCOVER;
+}
+
+static inline void cec_ops_cdc_hec_discover(const struct cec_msg *msg,
+					    __u16 *phys_addr)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+}
+
+static inline void cec_msg_cdc_hpd_set_state(struct cec_msg *msg,
+					     __u8 input_port,
+					     __u8 hpd_state)
+{
+	msg->len = 6;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HPD_SET_STATE;
+	msg->msg[5] = (input_port << 4) | hpd_state;
+}
+
+static inline void cec_ops_cdc_hpd_set_state(const struct cec_msg *msg,
+					    __u16 *phys_addr,
+					    __u8 *input_port,
+					    __u8 *hpd_state)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*input_port = msg->msg[5] >> 4;
+	*hpd_state = msg->msg[5] & 0xf;
+}
+
+static inline void cec_msg_cdc_hpd_report_state(struct cec_msg *msg,
+						__u8 hpd_state,
+						__u8 hpd_error)
+{
+	msg->len = 6;
+	msg->msg[0] |= 0xf; /* broadcast */
+	msg->msg[1] = CEC_MSG_CDC_MESSAGE;
+	/* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */
+	msg->msg[4] = CEC_MSG_CDC_HPD_REPORT_STATE;
+	msg->msg[5] = (hpd_state << 4) | hpd_error;
+}
+
+static inline void cec_ops_cdc_hpd_report_state(const struct cec_msg *msg,
+						__u16 *phys_addr,
+						__u8 *hpd_state,
+						__u8 *hpd_error)
+{
+	*phys_addr = (msg->msg[2] << 8) | msg->msg[3];
+	*hpd_state = msg->msg[5] >> 4;
+	*hpd_error = msg->msg[5] & 0xf;
+}
+
+#endif
diff --git a/include/linux/cec.h b/include/linux/cec.h
new file mode 100644
index 000000000000..b3e22893a002
--- /dev/null
+++ b/include/linux/cec.h
@@ -0,0 +1,1011 @@
+/*
+ * cec - HDMI Consumer Electronics Control public header
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * Alternatively you can redistribute this file under the terms of the
+ * BSD license as stated below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ * 3. The names of its contributors may not be used to endorse or promote
+ *    products derived from this software without specific prior written
+ *    permission.
+ *
+ * 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.
+ */
+
+/*
+ * Note: this framework is still in staging and it is likely the API
+ * will change before it goes out of staging.
+ *
+ * Once it is moved out of staging this header will move to uapi.
+ */
+#ifndef _CEC_UAPI_H
+#define _CEC_UAPI_H
+
+#include <linux/types.h>
+
+#define CEC_MAX_MSG_SIZE	16
+
+/**
+ * struct cec_msg - CEC message structure.
+ * @tx_ts:	Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the
+ *		driver when the message transmission has finished.
+ * @rx_ts:	Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the
+ *		driver when the message was received.
+ * @len:	Length in bytes of the message.
+ * @timeout:	The timeout (in ms) that is used to timeout CEC_RECEIVE.
+ *		Set to 0 if you want to wait forever. This timeout can also be
+ *		used with CEC_TRANSMIT as the timeout for waiting for a reply.
+ *		If 0, then it will use a 1 second timeout instead of waiting
+ *		forever as is done with CEC_RECEIVE.
+ * @sequence:	The framework assigns a sequence number to messages that are
+ *		sent. This can be used to track replies to previously sent
+ *		messages.
+ * @flags:	Set to 0.
+ * @msg:	The message payload.
+ * @reply:	This field is ignored with CEC_RECEIVE and is only used by
+ *		CEC_TRANSMIT. If non-zero, then wait for a reply with this
+ *		opcode. Set to CEC_MSG_FEATURE_ABORT if you want to wait for
+ *		a possible ABORT reply. If there was an error when sending the
+ *		msg or FeatureAbort was returned, then reply is set to 0.
+ *		If reply is non-zero upon return, then len/msg are set to
+ *		the received message.
+ *		If reply is zero upon return and status has the
+ *		CEC_TX_STATUS_FEATURE_ABORT bit set, then len/msg are set to
+ *		the received feature abort message.
+ *		If reply is zero upon return and status has the
+ *		CEC_TX_STATUS_MAX_RETRIES bit set, then no reply was seen at
+ *		all. If reply is non-zero for CEC_TRANSMIT and the message is a
+ *		broadcast, then -EINVAL is returned.
+ *		if reply is non-zero, then timeout is set to 1000 (the required
+ *		maximum response time).
+ * @rx_status:	The message receive status bits. Set by the driver.
+ * @tx_status:	The message transmit status bits. Set by the driver.
+ * @tx_arb_lost_cnt: The number of 'Arbitration Lost' events. Set by the driver.
+ * @tx_nack_cnt: The number of 'Not Acknowledged' events. Set by the driver.
+ * @tx_low_drive_cnt: The number of 'Low Drive Detected' events. Set by the
+ *		driver.
+ * @tx_error_cnt: The number of 'Error' events. Set by the driver.
+ */
+struct cec_msg {
+	__u64 tx_ts;
+	__u64 rx_ts;
+	__u32 len;
+	__u32 timeout;
+	__u32 sequence;
+	__u32 flags;
+	__u8 msg[CEC_MAX_MSG_SIZE];
+	__u8 reply;
+	__u8 rx_status;
+	__u8 tx_status;
+	__u8 tx_arb_lost_cnt;
+	__u8 tx_nack_cnt;
+	__u8 tx_low_drive_cnt;
+	__u8 tx_error_cnt;
+};
+
+/**
+ * cec_msg_initiator - return the initiator's logical address.
+ * @msg:	the message structure
+ */
+static inline __u8 cec_msg_initiator(const struct cec_msg *msg)
+{
+	return msg->msg[0] >> 4;
+}
+
+/**
+ * cec_msg_destination - return the destination's logical address.
+ * @msg:	the message structure
+ */
+static inline __u8 cec_msg_destination(const struct cec_msg *msg)
+{
+	return msg->msg[0] & 0xf;
+}
+
+/**
+ * cec_msg_opcode - return the opcode of the message, -1 for poll
+ * @msg:	the message structure
+ */
+static inline int cec_msg_opcode(const struct cec_msg *msg)
+{
+	return msg->len > 1 ? msg->msg[1] : -1;
+}
+
+/**
+ * cec_msg_is_broadcast - return true if this is a broadcast message.
+ * @msg:	the message structure
+ */
+static inline bool cec_msg_is_broadcast(const struct cec_msg *msg)
+{
+	return (msg->msg[0] & 0xf) == 0xf;
+}
+
+/**
+ * cec_msg_init - initialize the message structure.
+ * @msg:	the message structure
+ * @initiator:	the logical address of the initiator
+ * @destination:the logical address of the destination (0xf for broadcast)
+ *
+ * The whole structure is zeroed, the len field is set to 1 (i.e. a poll
+ * message) and the initiator and destination are filled in.
+ */
+static inline void cec_msg_init(struct cec_msg *msg,
+				__u8 initiator, __u8 destination)
+{
+	memset(msg, 0, sizeof(*msg));
+	msg->msg[0] = (initiator << 4) | destination;
+	msg->len = 1;
+}
+
+/**
+ * cec_msg_set_reply_to - fill in destination/initiator in a reply message.
+ * @msg:	the message structure for the reply
+ * @orig:	the original message structure
+ *
+ * Set the msg destination to the orig initiator and the msg initiator to the
+ * orig destination. Note that msg and orig may be the same pointer, in which
+ * case the change is done in place.
+ */
+static inline void cec_msg_set_reply_to(struct cec_msg *msg,
+					struct cec_msg *orig)
+{
+	/* The destination becomes the initiator and vice versa */
+	msg->msg[0] = (cec_msg_destination(orig) << 4) |
+		      cec_msg_initiator(orig);
+	msg->reply = msg->timeout = 0;
+}
+
+/* cec status field */
+#define CEC_TX_STATUS_OK		(1 << 0)
+#define CEC_TX_STATUS_ARB_LOST		(1 << 1)
+#define CEC_TX_STATUS_NACK		(1 << 2)
+#define CEC_TX_STATUS_LOW_DRIVE		(1 << 3)
+#define CEC_TX_STATUS_ERROR		(1 << 4)
+#define CEC_TX_STATUS_MAX_RETRIES	(1 << 5)
+
+#define CEC_RX_STATUS_OK		(1 << 0)
+#define CEC_RX_STATUS_TIMEOUT		(1 << 1)
+#define CEC_RX_STATUS_FEATURE_ABORT	(1 << 2)
+
+static inline bool cec_msg_status_is_ok(const struct cec_msg *msg)
+{
+	if (msg->tx_status && !(msg->tx_status & CEC_TX_STATUS_OK))
+		return false;
+	if (msg->rx_status && !(msg->rx_status & CEC_RX_STATUS_OK))
+		return false;
+	if (!msg->tx_status && !msg->rx_status)
+		return false;
+	return !(msg->rx_status & CEC_RX_STATUS_FEATURE_ABORT);
+}
+
+#define CEC_LOG_ADDR_INVALID		0xff
+#define CEC_PHYS_ADDR_INVALID		0xffff
+
+/*
+ * The maximum number of logical addresses one device can be assigned to.
+ * The CEC 2.0 spec allows for only 2 logical addresses at the moment. The
+ * Analog Devices CEC hardware supports 3. So let's go wild and go for 4.
+ */
+#define CEC_MAX_LOG_ADDRS 4
+
+/* The logical addresses defined by CEC 2.0 */
+#define CEC_LOG_ADDR_TV			0
+#define CEC_LOG_ADDR_RECORD_1		1
+#define CEC_LOG_ADDR_RECORD_2		2
+#define CEC_LOG_ADDR_TUNER_1		3
+#define CEC_LOG_ADDR_PLAYBACK_1		4
+#define CEC_LOG_ADDR_AUDIOSYSTEM	5
+#define CEC_LOG_ADDR_TUNER_2		6
+#define CEC_LOG_ADDR_TUNER_3		7
+#define CEC_LOG_ADDR_PLAYBACK_2		8
+#define CEC_LOG_ADDR_RECORD_3		9
+#define CEC_LOG_ADDR_TUNER_4		10
+#define CEC_LOG_ADDR_PLAYBACK_3		11
+#define CEC_LOG_ADDR_BACKUP_1		12
+#define CEC_LOG_ADDR_BACKUP_2		13
+#define CEC_LOG_ADDR_SPECIFIC		14
+#define CEC_LOG_ADDR_UNREGISTERED	15 /* as initiator address */
+#define CEC_LOG_ADDR_BROADCAST		15 /* ad destination address */
+
+/* The logical address types that the CEC device wants to claim */
+#define CEC_LOG_ADDR_TYPE_TV		0
+#define CEC_LOG_ADDR_TYPE_RECORD	1
+#define CEC_LOG_ADDR_TYPE_TUNER		2
+#define CEC_LOG_ADDR_TYPE_PLAYBACK	3
+#define CEC_LOG_ADDR_TYPE_AUDIOSYSTEM	4
+#define CEC_LOG_ADDR_TYPE_SPECIFIC	5
+#define CEC_LOG_ADDR_TYPE_UNREGISTERED	6
+/*
+ * Switches should use UNREGISTERED.
+ * Processors should use SPECIFIC.
+ */
+
+#define CEC_LOG_ADDR_MASK_TV		(1 << CEC_LOG_ADDR_TV)
+#define CEC_LOG_ADDR_MASK_RECORD	((1 << CEC_LOG_ADDR_RECORD_1) | \
+					 (1 << CEC_LOG_ADDR_RECORD_2) | \
+					 (1 << CEC_LOG_ADDR_RECORD_3))
+#define CEC_LOG_ADDR_MASK_TUNER		((1 << CEC_LOG_ADDR_TUNER_1) | \
+					 (1 << CEC_LOG_ADDR_TUNER_2) | \
+					 (1 << CEC_LOG_ADDR_TUNER_3) | \
+					 (1 << CEC_LOG_ADDR_TUNER_4))
+#define CEC_LOG_ADDR_MASK_PLAYBACK	((1 << CEC_LOG_ADDR_PLAYBACK_1) | \
+					 (1 << CEC_LOG_ADDR_PLAYBACK_2) | \
+					 (1 << CEC_LOG_ADDR_PLAYBACK_3))
+#define CEC_LOG_ADDR_MASK_AUDIOSYSTEM	(1 << CEC_LOG_ADDR_AUDIOSYSTEM)
+#define CEC_LOG_ADDR_MASK_BACKUP	((1 << CEC_LOG_ADDR_BACKUP_1) | \
+					 (1 << CEC_LOG_ADDR_BACKUP_2))
+#define CEC_LOG_ADDR_MASK_SPECIFIC	(1 << CEC_LOG_ADDR_SPECIFIC)
+#define CEC_LOG_ADDR_MASK_UNREGISTERED	(1 << CEC_LOG_ADDR_UNREGISTERED)
+
+static inline bool cec_has_tv(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_TV;
+}
+
+static inline bool cec_has_record(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_RECORD;
+}
+
+static inline bool cec_has_tuner(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_TUNER;
+}
+
+static inline bool cec_has_playback(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_PLAYBACK;
+}
+
+static inline bool cec_has_audiosystem(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_AUDIOSYSTEM;
+}
+
+static inline bool cec_has_backup(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_BACKUP;
+}
+
+static inline bool cec_has_specific(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_SPECIFIC;
+}
+
+static inline bool cec_is_unregistered(__u16 log_addr_mask)
+{
+	return log_addr_mask & CEC_LOG_ADDR_MASK_UNREGISTERED;
+}
+
+static inline bool cec_is_unconfigured(__u16 log_addr_mask)
+{
+	return log_addr_mask == 0;
+}
+
+/*
+ * Use this if there is no vendor ID (CEC_G_VENDOR_ID) or if the vendor ID
+ * should be disabled (CEC_S_VENDOR_ID)
+ */
+#define CEC_VENDOR_ID_NONE		0xffffffff
+
+/* The message handling modes */
+/* Modes for initiator */
+#define CEC_MODE_NO_INITIATOR		(0x0 << 0)
+#define CEC_MODE_INITIATOR		(0x1 << 0)
+#define CEC_MODE_EXCL_INITIATOR		(0x2 << 0)
+#define CEC_MODE_INITIATOR_MSK		0x0f
+
+/* Modes for follower */
+#define CEC_MODE_NO_FOLLOWER		(0x0 << 4)
+#define CEC_MODE_FOLLOWER		(0x1 << 4)
+#define CEC_MODE_EXCL_FOLLOWER		(0x2 << 4)
+#define CEC_MODE_EXCL_FOLLOWER_PASSTHRU	(0x3 << 4)
+#define CEC_MODE_MONITOR		(0xe << 4)
+#define CEC_MODE_MONITOR_ALL		(0xf << 4)
+#define CEC_MODE_FOLLOWER_MSK		0xf0
+
+/* Userspace has to configure the physical address */
+#define CEC_CAP_PHYS_ADDR	(1 << 0)
+/* Userspace has to configure the logical addresses */
+#define CEC_CAP_LOG_ADDRS	(1 << 1)
+/* Userspace can transmit messages (and thus become follower as well) */
+#define CEC_CAP_TRANSMIT	(1 << 2)
+/*
+ * Passthrough all messages instead of processing them.
+ */
+#define CEC_CAP_PASSTHROUGH	(1 << 3)
+/* Supports remote control */
+#define CEC_CAP_RC		(1 << 4)
+/* Hardware can monitor all messages, not just directed and broadcast. */
+#define CEC_CAP_MONITOR_ALL	(1 << 5)
+
+/**
+ * struct cec_caps - CEC capabilities structure.
+ * @driver: name of the CEC device driver.
+ * @name: name of the CEC device. @driver + @name must be unique.
+ * @available_log_addrs: number of available logical addresses.
+ * @capabilities: capabilities of the CEC adapter.
+ * @version: version of the CEC adapter framework.
+ */
+struct cec_caps {
+	char driver[32];
+	char name[32];
+	__u32 available_log_addrs;
+	__u32 capabilities;
+	__u32 version;
+};
+
+/**
+ * struct cec_log_addrs - CEC logical addresses structure.
+ * @log_addr: the claimed logical addresses. Set by the driver.
+ * @log_addr_mask: current logical address mask. Set by the driver.
+ * @cec_version: the CEC version that the adapter should implement. Set by the
+ *	caller.
+ * @num_log_addrs: how many logical addresses should be claimed. Set by the
+ *	caller.
+ * @vendor_id: the vendor ID of the device. Set by the caller.
+ * @flags: set to 0.
+ * @osd_name: the OSD name of the device. Set by the caller.
+ * @primary_device_type: the primary device type for each logical address.
+ *	Set by the caller.
+ * @log_addr_type: the logical address types. Set by the caller.
+ * @all_device_types: CEC 2.0: all device types represented by the logical
+ *	address. Set by the caller.
+ * @features:	CEC 2.0: The logical address features. Set by the caller.
+ */
+struct cec_log_addrs {
+	__u8 log_addr[CEC_MAX_LOG_ADDRS];
+	__u16 log_addr_mask;
+	__u8 cec_version;
+	__u8 num_log_addrs;
+	__u32 vendor_id;
+	__u32 flags;
+	char osd_name[15];
+	__u8 primary_device_type[CEC_MAX_LOG_ADDRS];
+	__u8 log_addr_type[CEC_MAX_LOG_ADDRS];
+
+	/* CEC 2.0 */
+	__u8 all_device_types[CEC_MAX_LOG_ADDRS];
+	__u8 features[CEC_MAX_LOG_ADDRS][12];
+};
+
+/* Events */
+
+/* Event that occurs when the adapter state changes */
+#define CEC_EVENT_STATE_CHANGE		1
+/*
+ * This event is sent when messages are lost because the application
+ * didn't empty the message queue in time
+ */
+#define CEC_EVENT_LOST_MSGS		2
+
+#define CEC_EVENT_FL_INITIAL_STATE	(1 << 0)
+
+/**
+ * struct cec_event_state_change - used when the CEC adapter changes state.
+ * @phys_addr: the current physical address
+ * @log_addr_mask: the current logical address mask
+ */
+struct cec_event_state_change {
+	__u16 phys_addr;
+	__u16 log_addr_mask;
+};
+
+/**
+ * struct cec_event_lost_msgs - tells you how many messages were lost due.
+ * @lost_msgs: how many messages were lost.
+ */
+struct cec_event_lost_msgs {
+	__u32 lost_msgs;
+};
+
+/**
+ * struct cec_event - CEC event structure
+ * @ts: the timestamp of when the event was sent.
+ * @event: the event.
+ * array.
+ * @state_change: the event payload for CEC_EVENT_STATE_CHANGE.
+ * @lost_msgs: the event payload for CEC_EVENT_LOST_MSGS.
+ * @raw: array to pad the union.
+ */
+struct cec_event {
+	__u64 ts;
+	__u32 event;
+	__u32 flags;
+	union {
+		struct cec_event_state_change state_change;
+		struct cec_event_lost_msgs lost_msgs;
+		__u32 raw[16];
+	};
+};
+
+/* ioctls */
+
+/* Adapter capabilities */
+#define CEC_ADAP_G_CAPS		_IOWR('a',  0, struct cec_caps)
+
+/*
+ * phys_addr is either 0 (if this is the CEC root device)
+ * or a valid physical address obtained from the sink's EDID
+ * as read by this CEC device (if this is a source device)
+ * or a physical address obtained and modified from a sink
+ * EDID and used for a sink CEC device.
+ * If nothing is connected, then phys_addr is 0xffff.
+ * See HDMI 1.4b, section 8.7 (Physical Address).
+ *
+ * The CEC_ADAP_S_PHYS_ADDR ioctl may not be available if that is handled
+ * internally.
+ */
+#define CEC_ADAP_G_PHYS_ADDR	_IOR('a',  1, __u16)
+#define CEC_ADAP_S_PHYS_ADDR	_IOW('a',  2, __u16)
+
+/*
+ * Configure the CEC adapter. It sets the device type and which
+ * logical types it will try to claim. It will return which
+ * logical addresses it could actually claim.
+ * An error is returned if the adapter is disabled or if there
+ * is no physical address assigned.
+ */
+
+#define CEC_ADAP_G_LOG_ADDRS	_IOR('a',  3, struct cec_log_addrs)
+#define CEC_ADAP_S_LOG_ADDRS	_IOWR('a',  4, struct cec_log_addrs)
+
+/* Transmit/receive a CEC command */
+#define CEC_TRANSMIT		_IOWR('a',  5, struct cec_msg)
+#define CEC_RECEIVE		_IOWR('a',  6, struct cec_msg)
+
+/* Dequeue CEC events */
+#define CEC_DQEVENT		_IOWR('a',  7, struct cec_event)
+
+/*
+ * Get and set the message handling mode for this filehandle.
+ */
+#define CEC_G_MODE		_IOR('a',  8, __u32)
+#define CEC_S_MODE		_IOW('a',  9, __u32)
+
+/*
+ * The remainder of this header defines all CEC messages and operands.
+ * The format matters since it the cec-ctl utility parses it to generate
+ * code for implementing all these messages.
+ *
+ * Comments ending with 'Feature' group messages for each feature.
+ * If messages are part of multiple features, then the "Has also"
+ * comment is used to list the previously defined messages that are
+ * supported by the feature.
+ *
+ * Before operands are defined a comment is added that gives the
+ * name of the operand and in brackets the variable name of the
+ * corresponding argument in the cec-funcs.h function.
+ */
+
+/* Messages */
+
+/* One Touch Play Feature */
+#define CEC_MSG_ACTIVE_SOURCE				0x82
+#define CEC_MSG_IMAGE_VIEW_ON				0x04
+#define CEC_MSG_TEXT_VIEW_ON				0x0d
+
+
+/* Routing Control Feature */
+
+/*
+ * Has also:
+ *	CEC_MSG_ACTIVE_SOURCE
+ */
+
+#define CEC_MSG_INACTIVE_SOURCE				0x9d
+#define CEC_MSG_REQUEST_ACTIVE_SOURCE			0x85
+#define CEC_MSG_ROUTING_CHANGE				0x80
+#define CEC_MSG_ROUTING_INFORMATION			0x81
+#define CEC_MSG_SET_STREAM_PATH				0x86
+
+
+/* Standby Feature */
+#define CEC_MSG_STANDBY					0x36
+
+
+/* One Touch Record Feature */
+#define CEC_MSG_RECORD_OFF				0x0b
+#define CEC_MSG_RECORD_ON				0x09
+/* Record Source Type Operand (rec_src_type) */
+#define CEC_OP_RECORD_SRC_OWN				1
+#define CEC_OP_RECORD_SRC_DIGITAL			2
+#define CEC_OP_RECORD_SRC_ANALOG			3
+#define CEC_OP_RECORD_SRC_EXT_PLUG			4
+#define CEC_OP_RECORD_SRC_EXT_PHYS_ADDR			5
+/* Service Identification Method Operand (service_id_method) */
+#define CEC_OP_SERVICE_ID_METHOD_BY_DIG_ID		0
+#define CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL		1
+/* Digital Service Broadcast System Operand (dig_bcast_system) */
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_GEN	0x00
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN	0x01
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_GEN		0x02
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_BS		0x08
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_CS		0x09
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_T		0x0a
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE	0x10
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT	0x11
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T		0x12
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_C		0x18
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S		0x19
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S2		0x1a
+#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_T		0x1b
+/* Analogue Broadcast Type Operand (ana_bcast_type) */
+#define CEC_OP_ANA_BCAST_TYPE_CABLE			0
+#define CEC_OP_ANA_BCAST_TYPE_SATELLITE			1
+#define CEC_OP_ANA_BCAST_TYPE_TERRESTRIAL		2
+/* Broadcast System Operand (bcast_system) */
+#define CEC_OP_BCAST_SYSTEM_PAL_BG			0x00
+#define CEC_OP_BCAST_SYSTEM_SECAM_LQ			0x01 /* SECAM L' */
+#define CEC_OP_BCAST_SYSTEM_PAL_M			0x02
+#define CEC_OP_BCAST_SYSTEM_NTSC_M			0x03
+#define CEC_OP_BCAST_SYSTEM_PAL_I			0x04
+#define CEC_OP_BCAST_SYSTEM_SECAM_DK			0x05
+#define CEC_OP_BCAST_SYSTEM_SECAM_BG			0x06
+#define CEC_OP_BCAST_SYSTEM_SECAM_L			0x07
+#define CEC_OP_BCAST_SYSTEM_PAL_DK			0x08
+#define CEC_OP_BCAST_SYSTEM_OTHER			0x1f
+/* Channel Number Format Operand (channel_number_fmt) */
+#define CEC_OP_CHANNEL_NUMBER_FMT_1_PART		0x01
+#define CEC_OP_CHANNEL_NUMBER_FMT_2_PART		0x02
+
+#define CEC_MSG_RECORD_STATUS				0x0a
+/* Record Status Operand (rec_status) */
+#define CEC_OP_RECORD_STATUS_CUR_SRC			0x01
+#define CEC_OP_RECORD_STATUS_DIG_SERVICE		0x02
+#define CEC_OP_RECORD_STATUS_ANA_SERVICE		0x03
+#define CEC_OP_RECORD_STATUS_EXT_INPUT			0x04
+#define CEC_OP_RECORD_STATUS_NO_DIG_SERVICE		0x05
+#define CEC_OP_RECORD_STATUS_NO_ANA_SERVICE		0x06
+#define CEC_OP_RECORD_STATUS_NO_SERVICE			0x07
+#define CEC_OP_RECORD_STATUS_INVALID_EXT_PLUG		0x09
+#define CEC_OP_RECORD_STATUS_INVALID_EXT_PHYS_ADDR	0x0a
+#define CEC_OP_RECORD_STATUS_UNSUP_CA			0x0b
+#define CEC_OP_RECORD_STATUS_NO_CA_ENTITLEMENTS		0x0c
+#define CEC_OP_RECORD_STATUS_CANT_COPY_SRC		0x0d
+#define CEC_OP_RECORD_STATUS_NO_MORE_COPIES		0x0e
+#define CEC_OP_RECORD_STATUS_NO_MEDIA			0x10
+#define CEC_OP_RECORD_STATUS_PLAYING			0x11
+#define CEC_OP_RECORD_STATUS_ALREADY_RECORDING		0x12
+#define CEC_OP_RECORD_STATUS_MEDIA_PROT			0x13
+#define CEC_OP_RECORD_STATUS_NO_SIGNAL			0x14
+#define CEC_OP_RECORD_STATUS_MEDIA_PROBLEM		0x15
+#define CEC_OP_RECORD_STATUS_NO_SPACE			0x16
+#define CEC_OP_RECORD_STATUS_PARENTAL_LOCK		0x17
+#define CEC_OP_RECORD_STATUS_TERMINATED_OK		0x1a
+#define CEC_OP_RECORD_STATUS_ALREADY_TERM		0x1b
+#define CEC_OP_RECORD_STATUS_OTHER			0x1f
+
+#define CEC_MSG_RECORD_TV_SCREEN			0x0f
+
+
+/* Timer Programming Feature */
+#define CEC_MSG_CLEAR_ANALOGUE_TIMER			0x33
+/* Recording Sequence Operand (recording_seq) */
+#define CEC_OP_REC_SEQ_SUNDAY				0x01
+#define CEC_OP_REC_SEQ_MONDAY				0x02
+#define CEC_OP_REC_SEQ_TUESDAY				0x04
+#define CEC_OP_REC_SEQ_WEDNESDAY			0x08
+#define CEC_OP_REC_SEQ_THURSDAY				0x10
+#define CEC_OP_REC_SEQ_FRIDAY				0x20
+#define CEC_OP_REC_SEQ_SATERDAY				0x40
+#define CEC_OP_REC_SEQ_ONCE_ONLY			0x00
+
+#define CEC_MSG_CLEAR_DIGITAL_TIMER			0x99
+
+#define CEC_MSG_CLEAR_EXT_TIMER				0xa1
+/* External Source Specifier Operand (ext_src_spec) */
+#define CEC_OP_EXT_SRC_PLUG				0x04
+#define CEC_OP_EXT_SRC_PHYS_ADDR			0x05
+
+#define CEC_MSG_SET_ANALOGUE_TIMER			0x34
+#define CEC_MSG_SET_DIGITAL_TIMER			0x97
+#define CEC_MSG_SET_EXT_TIMER				0xa2
+
+#define CEC_MSG_SET_TIMER_PROGRAM_TITLE			0x67
+#define CEC_MSG_TIMER_CLEARED_STATUS			0x43
+/* Timer Cleared Status Data Operand (timer_cleared_status) */
+#define CEC_OP_TIMER_CLR_STAT_RECORDING			0x00
+#define CEC_OP_TIMER_CLR_STAT_NO_MATCHING		0x01
+#define CEC_OP_TIMER_CLR_STAT_NO_INFO			0x02
+#define CEC_OP_TIMER_CLR_STAT_CLEARED			0x80
+
+#define CEC_MSG_TIMER_STATUS				0x35
+/* Timer Overlap Warning Operand (timer_overlap_warning) */
+#define CEC_OP_TIMER_OVERLAP_WARNING_NO_OVERLAP		0
+#define CEC_OP_TIMER_OVERLAP_WARNING_OVERLAP		1
+/* Media Info Operand (media_info) */
+#define CEC_OP_MEDIA_INFO_UNPROT_MEDIA			0
+#define CEC_OP_MEDIA_INFO_PROT_MEDIA			1
+#define CEC_OP_MEDIA_INFO_NO_MEDIA			2
+/* Programmed Indicator Operand (prog_indicator) */
+#define CEC_OP_PROG_IND_NOT_PROGRAMMED			0
+#define CEC_OP_PROG_IND_PROGRAMMED			1
+/* Programmed Info Operand (prog_info) */
+#define CEC_OP_PROG_INFO_ENOUGH_SPACE			0x08
+#define CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE		0x09
+#define CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE	0x0b
+#define CEC_OP_PROG_INFO_NONE_AVAILABLE			0x0a
+/* Not Programmed Error Info Operand (prog_error) */
+#define CEC_OP_PROG_ERROR_NO_FREE_TIMER			0x01
+#define CEC_OP_PROG_ERROR_DATE_OUT_OF_RANGE		0x02
+#define CEC_OP_PROG_ERROR_REC_SEQ_ERROR			0x03
+#define CEC_OP_PROG_ERROR_INV_EXT_PLUG			0x04
+#define CEC_OP_PROG_ERROR_INV_EXT_PHYS_ADDR		0x05
+#define CEC_OP_PROG_ERROR_CA_UNSUPP			0x06
+#define CEC_OP_PROG_ERROR_INSUF_CA_ENTITLEMENTS		0x07
+#define CEC_OP_PROG_ERROR_RESOLUTION_UNSUPP		0x08
+#define CEC_OP_PROG_ERROR_PARENTAL_LOCK			0x09
+#define CEC_OP_PROG_ERROR_CLOCK_FAILURE			0x0a
+#define CEC_OP_PROG_ERROR_DUPLICATE			0x0e
+
+
+/* System Information Feature */
+#define CEC_MSG_CEC_VERSION				0x9e
+/* CEC Version Operand (cec_version) */
+#define CEC_OP_CEC_VERSION_1_3A				4
+#define CEC_OP_CEC_VERSION_1_4				5
+#define CEC_OP_CEC_VERSION_2_0				6
+
+#define CEC_MSG_GET_CEC_VERSION				0x9f
+#define CEC_MSG_GIVE_PHYSICAL_ADDR			0x83
+#define CEC_MSG_GET_MENU_LANGUAGE			0x91
+#define CEC_MSG_REPORT_PHYSICAL_ADDR			0x84
+/* Primary Device Type Operand (prim_devtype) */
+#define CEC_OP_PRIM_DEVTYPE_TV				0
+#define CEC_OP_PRIM_DEVTYPE_RECORD			1
+#define CEC_OP_PRIM_DEVTYPE_TUNER			3
+#define CEC_OP_PRIM_DEVTYPE_PLAYBACK			4
+#define CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM			5
+#define CEC_OP_PRIM_DEVTYPE_SWITCH			6
+#define CEC_OP_PRIM_DEVTYPE_PROCESSOR			7
+
+#define CEC_MSG_SET_MENU_LANGUAGE			0x32
+#define CEC_MSG_REPORT_FEATURES				0xa6	/* HDMI 2.0 */
+/* All Device Types Operand (all_device_types) */
+#define CEC_OP_ALL_DEVTYPE_TV				0x80
+#define CEC_OP_ALL_DEVTYPE_RECORD			0x40
+#define CEC_OP_ALL_DEVTYPE_TUNER			0x20
+#define CEC_OP_ALL_DEVTYPE_PLAYBACK			0x10
+#define CEC_OP_ALL_DEVTYPE_AUDIOSYSTEM			0x08
+#define CEC_OP_ALL_DEVTYPE_SWITCH			0x04
+/*
+ * And if you wondering what happened to PROCESSOR devices: those should
+ * be mapped to a SWITCH.
+ */
+
+/* Valid for RC Profile and Device Feature operands */
+#define CEC_OP_FEAT_EXT					0x80	/* Extension bit */
+/* RC Profile Operand (rc_profile) */
+#define CEC_OP_FEAT_RC_TV_PROFILE_NONE			0x00
+#define CEC_OP_FEAT_RC_TV_PROFILE_1			0x02
+#define CEC_OP_FEAT_RC_TV_PROFILE_2			0x06
+#define CEC_OP_FEAT_RC_TV_PROFILE_3			0x0a
+#define CEC_OP_FEAT_RC_TV_PROFILE_4			0x0e
+#define CEC_OP_FEAT_RC_SRC_HAS_DEV_ROOT_MENU		0x50
+#define CEC_OP_FEAT_RC_SRC_HAS_DEV_SETUP_MENU		0x48
+#define CEC_OP_FEAT_RC_SRC_HAS_CONTENTS_MENU		0x44
+#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_TOP_MENU		0x42
+#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_CONTEXT_MENU	0x41
+/* Device Feature Operand (dev_features) */
+#define CEC_OP_FEAT_DEV_HAS_RECORD_TV_SCREEN		0x40
+#define CEC_OP_FEAT_DEV_HAS_SET_OSD_STRING		0x20
+#define CEC_OP_FEAT_DEV_HAS_DECK_CONTROL		0x10
+#define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE		0x08
+#define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX			0x04
+#define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX		0x02
+
+#define CEC_MSG_GIVE_FEATURES				0xa5	/* HDMI 2.0 */
+
+
+/* Deck Control Feature */
+#define CEC_MSG_DECK_CONTROL				0x42
+/* Deck Control Mode Operand (deck_control_mode) */
+#define CEC_OP_DECK_CTL_MODE_SKIP_FWD			1
+#define CEC_OP_DECK_CTL_MODE_SKIP_REV			2
+#define CEC_OP_DECK_CTL_MODE_STOP			3
+#define CEC_OP_DECK_CTL_MODE_EJECT			4
+
+#define CEC_MSG_DECK_STATUS				0x1b
+/* Deck Info Operand (deck_info) */
+#define CEC_OP_DECK_INFO_PLAY				0x11
+#define CEC_OP_DECK_INFO_RECORD				0x12
+#define CEC_OP_DECK_INFO_PLAY_REV			0x13
+#define CEC_OP_DECK_INFO_STILL				0x14
+#define CEC_OP_DECK_INFO_SLOW				0x15
+#define CEC_OP_DECK_INFO_SLOW_REV			0x16
+#define CEC_OP_DECK_INFO_FAST_FWD			0x17
+#define CEC_OP_DECK_INFO_FAST_REV			0x18
+#define CEC_OP_DECK_INFO_NO_MEDIA			0x19
+#define CEC_OP_DECK_INFO_STOP				0x1a
+#define CEC_OP_DECK_INFO_SKIP_FWD			0x1b
+#define CEC_OP_DECK_INFO_SKIP_REV			0x1c
+#define CEC_OP_DECK_INFO_INDEX_SEARCH_FWD		0x1d
+#define CEC_OP_DECK_INFO_INDEX_SEARCH_REV		0x1e
+#define CEC_OP_DECK_INFO_OTHER				0x1f
+
+#define CEC_MSG_GIVE_DECK_STATUS			0x1a
+/* Status Request Operand (status_req) */
+#define CEC_OP_STATUS_REQ_ON				1
+#define CEC_OP_STATUS_REQ_OFF				2
+#define CEC_OP_STATUS_REQ_ONCE				3
+
+#define CEC_MSG_PLAY					0x41
+/* Play Mode Operand (play_mode) */
+#define CEC_OP_PLAY_MODE_PLAY_FWD			0x24
+#define CEC_OP_PLAY_MODE_PLAY_REV			0x20
+#define CEC_OP_PLAY_MODE_PLAY_STILL			0x25
+#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MIN		0x05
+#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MED		0x06
+#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MAX		0x07
+#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MIN		0x09
+#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MED		0x0a
+#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MAX		0x0b
+#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MIN		0x15
+#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MED		0x16
+#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MAX		0x17
+#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MIN		0x19
+#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MED		0x1a
+#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MAX		0x1b
+
+
+/* Tuner Control Feature */
+#define CEC_MSG_GIVE_TUNER_DEVICE_STATUS		0x08
+#define CEC_MSG_SELECT_ANALOGUE_SERVICE			0x92
+#define CEC_MSG_SELECT_DIGITAL_SERVICE			0x93
+#define CEC_MSG_TUNER_DEVICE_STATUS			0x07
+/* Recording Flag Operand (rec_flag) */
+#define CEC_OP_REC_FLAG_USED				0
+#define CEC_OP_REC_FLAG_NOT_USED			1
+/* Tuner Display Info Operand (tuner_display_info) */
+#define CEC_OP_TUNER_DISPLAY_INFO_DIGITAL		0
+#define CEC_OP_TUNER_DISPLAY_INFO_NONE			1
+#define CEC_OP_TUNER_DISPLAY_INFO_ANALOGUE		2
+
+#define CEC_MSG_TUNER_STEP_DECREMENT			0x06
+#define CEC_MSG_TUNER_STEP_INCREMENT			0x05
+
+
+/* Vendor Specific Commands Feature */
+
+/*
+ * Has also:
+ *	CEC_MSG_CEC_VERSION
+ *	CEC_MSG_GET_CEC_VERSION
+ */
+#define CEC_MSG_DEVICE_VENDOR_ID			0x87
+#define CEC_MSG_GIVE_DEVICE_VENDOR_ID			0x8c
+#define CEC_MSG_VENDOR_COMMAND				0x89
+#define CEC_MSG_VENDOR_COMMAND_WITH_ID			0xa0
+#define CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN		0x8a
+#define CEC_MSG_VENDOR_REMOTE_BUTTON_UP			0x8b
+
+
+/* OSD Display Feature */
+#define CEC_MSG_SET_OSD_STRING				0x64
+/* Display Control Operand (disp_ctl) */
+#define CEC_OP_DISP_CTL_DEFAULT				0x00
+#define CEC_OP_DISP_CTL_UNTIL_CLEARED			0x40
+#define CEC_OP_DISP_CTL_CLEAR				0x80
+
+
+/* Device OSD Transfer Feature */
+#define CEC_MSG_GIVE_OSD_NAME				0x46
+#define CEC_MSG_SET_OSD_NAME				0x47
+
+
+/* Device Menu Control Feature */
+#define CEC_MSG_MENU_REQUEST				0x8d
+/* Menu Request Type Operand (menu_req) */
+#define CEC_OP_MENU_REQUEST_ACTIVATE			0x00
+#define CEC_OP_MENU_REQUEST_DEACTIVATE			0x01
+#define CEC_OP_MENU_REQUEST_QUERY			0x02
+
+#define CEC_MSG_MENU_STATUS				0x8e
+/* Menu State Operand (menu_state) */
+#define CEC_OP_MENU_STATE_ACTIVATED			0x00
+#define CEC_OP_MENU_STATE_DEACTIVATED			0x01
+
+#define CEC_MSG_USER_CONTROL_PRESSED			0x44
+/* UI Broadcast Type Operand (ui_bcast_type) */
+#define CEC_OP_UI_BCAST_TYPE_TOGGLE_ALL			0x00
+#define CEC_OP_UI_BCAST_TYPE_TOGGLE_DIG_ANA		0x01
+#define CEC_OP_UI_BCAST_TYPE_ANALOGUE			0x10
+#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_T			0x20
+#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_CABLE		0x30
+#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_SAT		0x40
+#define CEC_OP_UI_BCAST_TYPE_DIGITAL			0x50
+#define CEC_OP_UI_BCAST_TYPE_DIGITAL_T			0x60
+#define CEC_OP_UI_BCAST_TYPE_DIGITAL_CABLE		0x70
+#define CEC_OP_UI_BCAST_TYPE_DIGITAL_SAT		0x80
+#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT		0x90
+#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT2		0x91
+#define CEC_OP_UI_BCAST_TYPE_IP				0xa0
+/* UI Sound Presentation Control Operand (ui_snd_pres_ctl) */
+#define CEC_OP_UI_SND_PRES_CTL_DUAL_MONO		0x10
+#define CEC_OP_UI_SND_PRES_CTL_KARAOKE			0x20
+#define CEC_OP_UI_SND_PRES_CTL_DOWNMIX			0x80
+#define CEC_OP_UI_SND_PRES_CTL_REVERB			0x90
+#define CEC_OP_UI_SND_PRES_CTL_EQUALIZER		0xa0
+#define CEC_OP_UI_SND_PRES_CTL_BASS_UP			0xb1
+#define CEC_OP_UI_SND_PRES_CTL_BASS_NEUTRAL		0xb2
+#define CEC_OP_UI_SND_PRES_CTL_BASS_DOWN		0xb3
+#define CEC_OP_UI_SND_PRES_CTL_TREBLE_UP		0xc1
+#define CEC_OP_UI_SND_PRES_CTL_TREBLE_NEUTRAL		0xc2
+#define CEC_OP_UI_SND_PRES_CTL_TREBLE_DOWN		0xc3
+
+#define CEC_MSG_USER_CONTROL_RELEASED			0x45
+
+
+/* Remote Control Passthrough Feature */
+
+/*
+ * Has also:
+ *	CEC_MSG_USER_CONTROL_PRESSED
+ *	CEC_MSG_USER_CONTROL_RELEASED
+ */
+
+
+/* Power Status Feature */
+#define CEC_MSG_GIVE_DEVICE_POWER_STATUS		0x8f
+#define CEC_MSG_REPORT_POWER_STATUS			0x90
+/* Power Status Operand (pwr_state) */
+#define CEC_OP_POWER_STATUS_ON				0
+#define CEC_OP_POWER_STATUS_STANDBY			1
+#define CEC_OP_POWER_STATUS_TO_ON			2
+#define CEC_OP_POWER_STATUS_TO_STANDBY			3
+
+
+/* General Protocol Messages */
+#define CEC_MSG_FEATURE_ABORT				0x00
+/* Abort Reason Operand (reason) */
+#define CEC_OP_ABORT_UNRECOGNIZED_OP			0
+#define CEC_OP_ABORT_INCORRECT_MODE			1
+#define CEC_OP_ABORT_NO_SOURCE				2
+#define CEC_OP_ABORT_INVALID_OP				3
+#define CEC_OP_ABORT_REFUSED				4
+#define CEC_OP_ABORT_UNDETERMINED			5
+
+#define CEC_MSG_ABORT					0xff
+
+
+/* System Audio Control Feature */
+
+/*
+ * Has also:
+ *	CEC_MSG_USER_CONTROL_PRESSED
+ *	CEC_MSG_USER_CONTROL_RELEASED
+ */
+#define CEC_MSG_GIVE_AUDIO_STATUS			0x71
+#define CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS		0x7d
+#define CEC_MSG_REPORT_AUDIO_STATUS			0x7a
+/* Audio Mute Status Operand (aud_mute_status) */
+#define CEC_OP_AUD_MUTE_STATUS_OFF			0
+#define CEC_OP_AUD_MUTE_STATUS_ON			1
+
+#define CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR		0xa3
+#define CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR		0xa4
+#define CEC_MSG_SET_SYSTEM_AUDIO_MODE			0x72
+/* System Audio Status Operand (sys_aud_status) */
+#define CEC_OP_SYS_AUD_STATUS_OFF			0
+#define CEC_OP_SYS_AUD_STATUS_ON			1
+
+#define CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST		0x70
+#define CEC_MSG_SYSTEM_AUDIO_MODE_STATUS		0x7e
+/* Audio Format ID Operand (audio_format_id) */
+#define CEC_OP_AUD_FMT_ID_CEA861			0
+#define CEC_OP_AUD_FMT_ID_CEA861_CXT			1
+
+
+/* Audio Rate Control Feature */
+#define CEC_MSG_SET_AUDIO_RATE				0x9a
+/* Audio Rate Operand (audio_rate) */
+#define CEC_OP_AUD_RATE_OFF				0
+#define CEC_OP_AUD_RATE_WIDE_STD			1
+#define CEC_OP_AUD_RATE_WIDE_FAST			2
+#define CEC_OP_AUD_RATE_WIDE_SLOW			3
+#define CEC_OP_AUD_RATE_NARROW_STD			4
+#define CEC_OP_AUD_RATE_NARROW_FAST			5
+#define CEC_OP_AUD_RATE_NARROW_SLOW			6
+
+
+/* Audio Return Channel Control Feature */
+#define CEC_MSG_INITIATE_ARC				0xc0
+#define CEC_MSG_REPORT_ARC_INITIATED			0xc1
+#define CEC_MSG_REPORT_ARC_TERMINATED			0xc2
+#define CEC_MSG_REQUEST_ARC_INITIATION			0xc3
+#define CEC_MSG_REQUEST_ARC_TERMINATION			0xc4
+#define CEC_MSG_TERMINATE_ARC				0xc5
+
+
+/* Dynamic Audio Lipsync Feature */
+/* Only for CEC 2.0 and up */
+#define CEC_MSG_REQUEST_CURRENT_LATENCY			0xa7
+#define CEC_MSG_REPORT_CURRENT_LATENCY			0xa8
+/* Low Latency Mode Operand (low_latency_mode) */
+#define CEC_OP_LOW_LATENCY_MODE_OFF			0
+#define CEC_OP_LOW_LATENCY_MODE_ON			1
+/* Audio Output Compensated Operand (audio_out_compensated) */
+#define CEC_OP_AUD_OUT_COMPENSATED_NA			0
+#define CEC_OP_AUD_OUT_COMPENSATED_DELAY		1
+#define CEC_OP_AUD_OUT_COMPENSATED_NO_DELAY		2
+#define CEC_OP_AUD_OUT_COMPENSATED_PARTIAL_DELAY	3
+
+
+/* Capability Discovery and Control Feature */
+#define CEC_MSG_CDC_MESSAGE				0xf8
+/* Ethernet-over-HDMI: nobody ever does this... */
+#define CEC_MSG_CDC_HEC_INQUIRE_STATE			0x00
+#define CEC_MSG_CDC_HEC_REPORT_STATE			0x01
+/* HEC Functionality State Operand (hec_func_state) */
+#define CEC_OP_HEC_FUNC_STATE_NOT_SUPPORTED		0
+#define CEC_OP_HEC_FUNC_STATE_INACTIVE			1
+#define CEC_OP_HEC_FUNC_STATE_ACTIVE			2
+#define CEC_OP_HEC_FUNC_STATE_ACTIVATION_FIELD		3
+/* Host Functionality State Operand (host_func_state) */
+#define CEC_OP_HOST_FUNC_STATE_NOT_SUPPORTED		0
+#define CEC_OP_HOST_FUNC_STATE_INACTIVE			1
+#define CEC_OP_HOST_FUNC_STATE_ACTIVE			2
+/* ENC Functionality State Operand (enc_func_state) */
+#define CEC_OP_ENC_FUNC_STATE_EXT_CON_NOT_SUPPORTED	0
+#define CEC_OP_ENC_FUNC_STATE_EXT_CON_INACTIVE		1
+#define CEC_OP_ENC_FUNC_STATE_EXT_CON_ACTIVE		2
+/* CDC Error Code Operand (cdc_errcode) */
+#define CEC_OP_CDC_ERROR_CODE_NONE			0
+#define CEC_OP_CDC_ERROR_CODE_CAP_UNSUPPORTED		1
+#define CEC_OP_CDC_ERROR_CODE_WRONG_STATE		2
+#define CEC_OP_CDC_ERROR_CODE_OTHER			3
+/* HEC Support Operand (hec_support) */
+#define CEC_OP_HEC_SUPPORT_NO				0
+#define CEC_OP_HEC_SUPPORT_YES				1
+/* HEC Activation Operand (hec_activation) */
+#define CEC_OP_HEC_ACTIVATION_ON			0
+#define CEC_OP_HEC_ACTIVATION_OFF			1
+
+#define CEC_MSG_CDC_HEC_SET_STATE_ADJACENT		0x02
+#define CEC_MSG_CDC_HEC_SET_STATE			0x03
+/* HEC Set State Operand (hec_set_state) */
+#define CEC_OP_HEC_SET_STATE_DEACTIVATE			0
+#define CEC_OP_HEC_SET_STATE_ACTIVATE			1
+
+#define CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION		0x04
+#define CEC_MSG_CDC_HEC_NOTIFY_ALIVE			0x05
+#define CEC_MSG_CDC_HEC_DISCOVER			0x06
+/* Hotplug Detect messages */
+#define CEC_MSG_CDC_HPD_SET_STATE			0x10
+/* HPD State Operand (hpd_state) */
+#define CEC_OP_HPD_STATE_CP_EDID_DISABLE		0
+#define CEC_OP_HPD_STATE_CP_EDID_ENABLE			1
+#define CEC_OP_HPD_STATE_CP_EDID_DISABLE_ENABLE		2
+#define CEC_OP_HPD_STATE_EDID_DISABLE			3
+#define CEC_OP_HPD_STATE_EDID_ENABLE			4
+#define CEC_OP_HPD_STATE_EDID_DISABLE_ENABLE		5
+#define CEC_MSG_CDC_HPD_REPORT_STATE			0x11
+/* HPD Error Code Operand (hpd_error) */
+#define CEC_OP_HPD_ERROR_NONE				0
+#define CEC_OP_HPD_ERROR_INITIATOR_NOT_CAPABLE		1
+#define CEC_OP_HPD_ERROR_INITIATOR_WRONG_STATE		2
+#define CEC_OP_HPD_ERROR_OTHER				3
+#define CEC_OP_HPD_ERROR_NONE_NO_VIDEO			4
+
+#endif
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 4e81e08db752..631ba33bbe9f 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -36,6 +36,12 @@
 
 struct cpufreq_governor;
 
+enum cpufreq_table_sorting {
+	CPUFREQ_TABLE_UNSORTED,
+	CPUFREQ_TABLE_SORTED_ASCENDING,
+	CPUFREQ_TABLE_SORTED_DESCENDING
+};
+
 struct cpufreq_freqs {
 	unsigned int cpu;	/* cpu nr */
 	unsigned int old;
@@ -87,6 +93,7 @@ struct cpufreq_policy {
 
 	struct cpufreq_user_policy user_policy;
 	struct cpufreq_frequency_table	*freq_table;
+	enum cpufreq_table_sorting freq_table_sorted;
 
 	struct list_head        policy_list;
 	struct kobject		kobj;
@@ -113,6 +120,10 @@ struct cpufreq_policy {
 	bool			fast_switch_possible;
 	bool			fast_switch_enabled;
 
+	 /* Cached frequency lookup from cpufreq_driver_resolve_freq. */
+	unsigned int cached_target_freq;
+	int cached_resolved_idx;
+
 	/* Synchronization for frequency transitions */
 	bool			transition_ongoing; /* Tracks transition status */
 	spinlock_t		transition_lock;
@@ -185,6 +196,18 @@ static inline unsigned int cpufreq_quick_get_max(unsigned int cpu)
 static inline void disable_cpufreq(void) { }
 #endif
 
+#ifdef CONFIG_CPU_FREQ_STAT
+void cpufreq_stats_create_table(struct cpufreq_policy *policy);
+void cpufreq_stats_free_table(struct cpufreq_policy *policy);
+void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
+				     unsigned int new_freq);
+#else
+static inline void cpufreq_stats_create_table(struct cpufreq_policy *policy) { }
+static inline void cpufreq_stats_free_table(struct cpufreq_policy *policy) { }
+static inline void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
+						   unsigned int new_freq) { }
+#endif /* CONFIG_CPU_FREQ_STAT */
+
 /*********************************************************************
  *                      CPUFREQ DRIVER INTERFACE                     *
  *********************************************************************/
@@ -251,6 +274,16 @@ struct cpufreq_driver {
 					unsigned int index);
 	unsigned int	(*fast_switch)(struct cpufreq_policy *policy,
 				       unsigned int target_freq);
+
+	/*
+	 * Caches and returns the lowest driver-supported frequency greater than
+	 * or equal to the target frequency, subject to any driver limitations.
+	 * Does not set the frequency. Only to be implemented for drivers with
+	 * target().
+	 */
+	unsigned int	(*resolve_freq)(struct cpufreq_policy *policy,
+					unsigned int target_freq);
+
 	/*
 	 * Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION
 	 * unset.
@@ -455,18 +488,13 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
 #define MIN_LATENCY_MULTIPLIER		(20)
 #define TRANSITION_LATENCY_LIMIT	(10 * 1000 * 1000)
 
-/* Governor Events */
-#define CPUFREQ_GOV_START	1
-#define CPUFREQ_GOV_STOP	2
-#define CPUFREQ_GOV_LIMITS	3
-#define CPUFREQ_GOV_POLICY_INIT	4
-#define CPUFREQ_GOV_POLICY_EXIT	5
-
 struct cpufreq_governor {
 	char	name[CPUFREQ_NAME_LEN];
-	int	initialized;
-	int	(*governor)	(struct cpufreq_policy *policy,
-				 unsigned int event);
+	int	(*init)(struct cpufreq_policy *policy);
+	void	(*exit)(struct cpufreq_policy *policy);
+	int	(*start)(struct cpufreq_policy *policy);
+	void	(*stop)(struct cpufreq_policy *policy);
+	void	(*limits)(struct cpufreq_policy *policy);
 	ssize_t	(*show_setspeed)	(struct cpufreq_policy *policy,
 					 char *buf);
 	int	(*store_setspeed)	(struct cpufreq_policy *policy,
@@ -487,12 +515,22 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
 int __cpufreq_driver_target(struct cpufreq_policy *policy,
 				   unsigned int target_freq,
 				   unsigned int relation);
+unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
+					 unsigned int target_freq);
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
 
 struct cpufreq_governor *cpufreq_default_governor(void);
 struct cpufreq_governor *cpufreq_fallback_governor(void);
 
+static inline void cpufreq_policy_apply_limits(struct cpufreq_policy *policy)
+{
+	if (policy->max < policy->cur)
+		__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
+	else if (policy->min > policy->cur)
+		__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
+}
+
 /* Governor attribute set */
 struct gov_attr_set {
 	struct kobject kobj;
@@ -582,11 +620,9 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 				   struct cpufreq_frequency_table *table);
 int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy);
 
-int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
-				   struct cpufreq_frequency_table *table,
-				   unsigned int target_freq,
-				   unsigned int relation,
-				   unsigned int *index);
+int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
+				 unsigned int target_freq,
+				 unsigned int relation);
 int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 		unsigned int freq);
 
@@ -597,6 +633,227 @@ int cpufreq_boost_trigger_state(int state);
 int cpufreq_boost_enabled(void);
 int cpufreq_enable_boost_support(void);
 bool policy_has_boost_freq(struct cpufreq_policy *policy);
+
+/* Find lowest freq at or above target in a table in ascending order */
+static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy,
+					      unsigned int target_freq)
+{
+	struct cpufreq_frequency_table *table = policy->freq_table;
+	unsigned int freq;
+	int i, best = -1;
+
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		freq = table[i].frequency;
+
+		if (freq >= target_freq)
+			return i;
+
+		best = i;
+	}
+
+	return best;
+}
+
+/* Find lowest freq at or above target in a table in descending order */
+static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy,
+					      unsigned int target_freq)
+{
+	struct cpufreq_frequency_table *table = policy->freq_table;
+	unsigned int freq;
+	int i, best = -1;
+
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		freq = table[i].frequency;
+
+		if (freq == target_freq)
+			return i;
+
+		if (freq > target_freq) {
+			best = i;
+			continue;
+		}
+
+		/* No freq found above target_freq */
+		if (best == -1)
+			return i;
+
+		return best;
+	}
+
+	return best;
+}
+
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
+					     unsigned int target_freq)
+{
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
+
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
+		return cpufreq_table_find_index_al(policy, target_freq);
+	else
+		return cpufreq_table_find_index_dl(policy, target_freq);
+}
+
+/* Find highest freq at or below target in a table in ascending order */
+static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy,
+					      unsigned int target_freq)
+{
+	struct cpufreq_frequency_table *table = policy->freq_table;
+	unsigned int freq;
+	int i, best = -1;
+
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		freq = table[i].frequency;
+
+		if (freq == target_freq)
+			return i;
+
+		if (freq < target_freq) {
+			best = i;
+			continue;
+		}
+
+		/* No freq found below target_freq */
+		if (best == -1)
+			return i;
+
+		return best;
+	}
+
+	return best;
+}
+
+/* Find highest freq at or below target in a table in descending order */
+static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy,
+					      unsigned int target_freq)
+{
+	struct cpufreq_frequency_table *table = policy->freq_table;
+	unsigned int freq;
+	int i, best = -1;
+
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		freq = table[i].frequency;
+
+		if (freq <= target_freq)
+			return i;
+
+		best = i;
+	}
+
+	return best;
+}
+
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
+					     unsigned int target_freq)
+{
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
+
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
+		return cpufreq_table_find_index_ah(policy, target_freq);
+	else
+		return cpufreq_table_find_index_dh(policy, target_freq);
+}
+
+/* Find closest freq to target in a table in ascending order */
+static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy,
+					      unsigned int target_freq)
+{
+	struct cpufreq_frequency_table *table = policy->freq_table;
+	unsigned int freq;
+	int i, best = -1;
+
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		freq = table[i].frequency;
+
+		if (freq == target_freq)
+			return i;
+
+		if (freq < target_freq) {
+			best = i;
+			continue;
+		}
+
+		/* No freq found below target_freq */
+		if (best == -1)
+			return i;
+
+		/* Choose the closest freq */
+		if (target_freq - table[best].frequency > freq - target_freq)
+			return i;
+
+		return best;
+	}
+
+	return best;
+}
+
+/* Find closest freq to target in a table in descending order */
+static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy,
+					      unsigned int target_freq)
+{
+	struct cpufreq_frequency_table *table = policy->freq_table;
+	unsigned int freq;
+	int i, best = -1;
+
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		freq = table[i].frequency;
+
+		if (freq == target_freq)
+			return i;
+
+		if (freq > target_freq) {
+			best = i;
+			continue;
+		}
+
+		/* No freq found above target_freq */
+		if (best == -1)
+			return i;
+
+		/* Choose the closest freq */
+		if (table[best].frequency - target_freq > target_freq - freq)
+			return i;
+
+		return best;
+	}
+
+	return best;
+}
+
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
+					     unsigned int target_freq)
+{
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
+
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
+		return cpufreq_table_find_index_ac(policy, target_freq);
+	else
+		return cpufreq_table_find_index_dc(policy, target_freq);
+}
+
+static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
+						 unsigned int target_freq,
+						 unsigned int relation)
+{
+	if (unlikely(policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED))
+		return cpufreq_table_index_unsorted(policy, target_freq,
+						    relation);
+
+	switch (relation) {
+	case CPUFREQ_RELATION_L:
+		return cpufreq_table_find_index_l(policy, target_freq);
+	case CPUFREQ_RELATION_H:
+		return cpufreq_table_find_index_h(policy, target_freq);
+	case CPUFREQ_RELATION_C:
+		return cpufreq_table_find_index_c(policy, target_freq);
+	default:
+		pr_err("%s: Invalid relation: %d\n", __func__, relation);
+		return -EINVAL;
+	}
+}
 #else
 static inline int cpufreq_boost_trigger_state(int state)
 {
@@ -617,8 +874,6 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
 	return false;
 }
 #endif
-/* the following funtion is for cpufreq core use only */
-struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu);
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 07b83d32f66c..bb31373c3478 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -252,4 +252,22 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 #define CPUIDLE_DRIVER_STATE_START	0
 #endif
 
+#define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx)	\
+({								\
+	int __ret;						\
+								\
+	if (!idx) {						\
+		cpu_do_idle();					\
+		return idx;					\
+	}							\
+								\
+	__ret = cpu_pm_enter();					\
+	if (!__ret) {						\
+		__ret = low_level_idle_enter(idx);		\
+		cpu_pm_exit();					\
+	}							\
+								\
+	__ret ? -1 : idx;					\
+})
+
 #endif /* _LINUX_CPUIDLE_H */
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 6e28c895c376..7cee5551625b 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -47,16 +47,18 @@
 #define CRYPTO_ALG_TYPE_AEAD		0x00000003
 #define CRYPTO_ALG_TYPE_BLKCIPHER	0x00000004
 #define CRYPTO_ALG_TYPE_ABLKCIPHER	0x00000005
+#define CRYPTO_ALG_TYPE_SKCIPHER	0x00000005
 #define CRYPTO_ALG_TYPE_GIVCIPHER	0x00000006
-#define CRYPTO_ALG_TYPE_DIGEST		0x00000008
-#define CRYPTO_ALG_TYPE_HASH		0x00000008
-#define CRYPTO_ALG_TYPE_SHASH		0x00000009
-#define CRYPTO_ALG_TYPE_AHASH		0x0000000a
+#define CRYPTO_ALG_TYPE_KPP		0x00000008
 #define CRYPTO_ALG_TYPE_RNG		0x0000000c
 #define CRYPTO_ALG_TYPE_AKCIPHER	0x0000000d
+#define CRYPTO_ALG_TYPE_DIGEST		0x0000000e
+#define CRYPTO_ALG_TYPE_HASH		0x0000000e
+#define CRYPTO_ALG_TYPE_SHASH		0x0000000e
+#define CRYPTO_ALG_TYPE_AHASH		0x0000000f
 
 #define CRYPTO_ALG_TYPE_HASH_MASK	0x0000000e
-#define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000c
+#define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000e
 #define CRYPTO_ALG_TYPE_BLKCIPHER_MASK	0x0000000c
 
 #define CRYPTO_ALG_LARVAL		0x00000010
@@ -486,8 +488,6 @@ struct ablkcipher_tfm {
 	              unsigned int keylen);
 	int (*encrypt)(struct ablkcipher_request *req);
 	int (*decrypt)(struct ablkcipher_request *req);
-	int (*givencrypt)(struct skcipher_givcrypt_request *req);
-	int (*givdecrypt)(struct skcipher_givcrypt_request *req);
 
 	struct crypto_ablkcipher *base;
 
@@ -712,23 +712,6 @@ static inline u32 crypto_skcipher_mask(u32 mask)
  * state information is unused by the kernel crypto API.
  */
 
-/**
- * crypto_alloc_ablkcipher() - allocate asynchronous block cipher handle
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      ablkcipher cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Allocate a cipher handle for an ablkcipher. The returned struct
- * crypto_ablkcipher is the cipher handle that is required for any subsequent
- * API invocation for that ablkcipher.
- *
- * Return: allocated cipher handle in case of success; IS_ERR() is true in case
- *	   of an error, PTR_ERR() returns the error code.
- */
-struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name,
-						  u32 type, u32 mask);
-
 static inline struct crypto_tfm *crypto_ablkcipher_tfm(
 	struct crypto_ablkcipher *tfm)
 {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 0830c9e86f0d..b0db857f334b 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -19,6 +19,15 @@ struct dm_table;
 struct mapped_device;
 struct bio_vec;
 
+/*
+ * Type of table, mapped_device's mempool and request_queue
+ */
+#define DM_TYPE_NONE			0
+#define DM_TYPE_BIO_BASED		1
+#define DM_TYPE_REQUEST_BASED		2
+#define DM_TYPE_MQ_REQUEST_BASED	3
+#define DM_TYPE_DAX_BIO_BASED		4
+
 typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;
 
 union map_info {
@@ -116,6 +125,14 @@ typedef void (*dm_io_hints_fn) (struct dm_target *ti,
  */
 typedef int (*dm_busy_fn) (struct dm_target *ti);
 
+/*
+ * Returns:
+ *  < 0 : error
+ * >= 0 : the number of bytes accessible at the address
+ */
+typedef long (*dm_direct_access_fn) (struct dm_target *ti, sector_t sector,
+				     void __pmem **kaddr, pfn_t *pfn, long size);
+
 void dm_error(const char *message);
 
 struct dm_dev {
@@ -162,6 +179,7 @@ struct target_type {
 	dm_busy_fn busy;
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
+	dm_direct_access_fn direct_access;
 
 	/* For internal device-mapper use. */
 	struct list_head list;
@@ -444,6 +462,14 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb);
 
 /*
+ * Target can use this to set the table's type.
+ * Can only ever be called from a target's ctr.
+ * Useful for "hybrid" target (supports both bio-based
+ * and request-based).
+ */
+void dm_table_set_type(struct dm_table *t, unsigned type);
+
+/*
  * Finally call this to make the table ready for use.
  */
 int dm_table_complete(struct dm_table *t);
diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h
index a68cbe59e6ad..b91b023deffb 100644
--- a/include/linux/dm-io.h
+++ b/include/linux/dm-io.h
@@ -57,7 +57,8 @@ struct dm_io_notify {
  */
 struct dm_io_client;
 struct dm_io_request {
-	int bi_rw;			/* READ|WRITE - not READA */
+	int bi_op;			/* REQ_OP */
+	int bi_op_flags;		/* rq_flag_bits */
 	struct dm_io_memory mem;	/* Memory to use for io */
 	struct dm_io_notify notify;	/* Synchronous if notify.fn is NULL */
 	struct dm_io_client *client;	/* Client memory handler */
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index d6b3c9943a2c..002611c85318 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -51,7 +51,7 @@
 #endif
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.4.6"
+#define REL_VERSION "8.4.7"
 #define API_VERSION 1
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 101
@@ -370,6 +370,14 @@ enum drbd_notification_type {
 	NOTIFY_FLAGS = NOTIFY_CONTINUES,
 };
 
+enum drbd_peer_state {
+	P_INCONSISTENT = 3,
+	P_OUTDATED = 4,
+	P_DOWN = 5,
+	P_PRIMARY = 6,
+	P_FENCING = 7,
+};
+
 #define UUID_JUST_CREATED ((__u64)4)
 
 enum write_ordering_e {
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 2d0e5ad5de9d..c934d3a96b5e 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -123,15 +123,16 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__u32_field_def(13,	DRBD_GENLA_F_MANDATORY,	c_fill_target, DRBD_C_FILL_TARGET_DEF)
 	__u32_field_def(14,	DRBD_GENLA_F_MANDATORY,	c_max_rate, DRBD_C_MAX_RATE_DEF)
 	__u32_field_def(15,	DRBD_GENLA_F_MANDATORY,	c_min_rate, DRBD_C_MIN_RATE_DEF)
+	__u32_field_def(20,     DRBD_GENLA_F_MANDATORY, disk_timeout, DRBD_DISK_TIMEOUT_DEF)
+	__u32_field_def(21,     0 /* OPTIONAL */,       read_balancing, DRBD_READ_BALANCING_DEF)
+	__u32_field_def(25,     0 /* OPTIONAL */,       rs_discard_granularity, DRBD_RS_DISCARD_GRANULARITY_DEF)
 
 	__flg_field_def(16, DRBD_GENLA_F_MANDATORY,	disk_barrier, DRBD_DISK_BARRIER_DEF)
 	__flg_field_def(17, DRBD_GENLA_F_MANDATORY,	disk_flushes, DRBD_DISK_FLUSHES_DEF)
 	__flg_field_def(18, DRBD_GENLA_F_MANDATORY,	disk_drain, DRBD_DISK_DRAIN_DEF)
 	__flg_field_def(19, DRBD_GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
-	__u32_field_def(20,	DRBD_GENLA_F_MANDATORY,	disk_timeout, DRBD_DISK_TIMEOUT_DEF)
-	__u32_field_def(21,	0 /* OPTIONAL */,       read_balancing, DRBD_READ_BALANCING_DEF)
-	/* 9: __u32_field_def(22,	DRBD_GENLA_F_MANDATORY,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF) */
 	__flg_field_def(23,     0 /* OPTIONAL */,	al_updates, DRBD_AL_UPDATES_DEF)
+	__flg_field_def(24,     0 /* OPTIONAL */,	discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 8ac8c5d9a3ad..ddac68422a96 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -126,8 +126,7 @@
 #define DRBD_RESYNC_RATE_DEF 250
 #define DRBD_RESYNC_RATE_SCALE 'k'  /* kilobytes */
 
-  /* less than 7 would hit performance unnecessarily. */
-#define DRBD_AL_EXTENTS_MIN  7
+#define DRBD_AL_EXTENTS_MIN  67
   /* we use u16 as "slot number", (u16)~0 is "FREE".
    * If you use >= 292 kB on-disk ring buffer,
    * this is the maximum you can use: */
@@ -210,6 +209,12 @@
 #define DRBD_MD_FLUSHES_DEF	1
 #define DRBD_TCP_CORK_DEF	1
 #define DRBD_AL_UPDATES_DEF     1
+/* We used to ignore the discard_zeroes_data setting.
+ * To not change established (and expected) behaviour,
+ * by default assume that, for discard_zeroes_data=0,
+ * we can make that an effective discard_zeroes_data=1,
+ * if we only explicitly zero-out unaligned partial chunks. */
+#define DRBD_DISCARD_ZEROES_IF_ALIGNED 1
 
 #define DRBD_ALLOW_TWO_PRIMARIES_DEF	0
 #define DRBD_ALWAYS_ASBP_DEF	0
@@ -230,4 +235,10 @@
 #define DRBD_SOCKET_CHECK_TIMEO_MAX DRBD_PING_TIMEO_MAX
 #define DRBD_SOCKET_CHECK_TIMEO_DEF 0
 #define DRBD_SOCKET_CHECK_TIMEO_SCALE '1'
+
+#define DRBD_RS_DISCARD_GRANULARITY_MIN 0
+#define DRBD_RS_DISCARD_GRANULARITY_MAX (1<<20)  /* 1MiByte */
+#define DRBD_RS_DISCARD_GRANULARITY_DEF 0     /* disabled by default */
+#define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */
+
 #endif
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 638b324f0291..e7f358d2e5fc 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -16,7 +16,11 @@ typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *,
 
 typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int);
 
-typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *);
+typedef int (elevator_allow_bio_merge_fn) (struct request_queue *,
+					   struct request *, struct bio *);
+
+typedef int (elevator_allow_rq_merge_fn) (struct request_queue *,
+					  struct request *, struct request *);
 
 typedef void (elevator_bio_merged_fn) (struct request_queue *,
 						struct request *, struct bio *);
@@ -26,7 +30,7 @@ typedef int (elevator_dispatch_fn) (struct request_queue *, int);
 typedef void (elevator_add_req_fn) (struct request_queue *, struct request *);
 typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *);
 typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *);
-typedef int (elevator_may_queue_fn) (struct request_queue *, int);
+typedef int (elevator_may_queue_fn) (struct request_queue *, int, int);
 
 typedef void (elevator_init_icq_fn) (struct io_cq *);
 typedef void (elevator_exit_icq_fn) (struct io_cq *);
@@ -46,7 +50,8 @@ struct elevator_ops
 	elevator_merge_fn *elevator_merge_fn;
 	elevator_merged_fn *elevator_merged_fn;
 	elevator_merge_req_fn *elevator_merge_req_fn;
-	elevator_allow_merge_fn *elevator_allow_merge_fn;
+	elevator_allow_bio_merge_fn *elevator_allow_bio_merge_fn;
+	elevator_allow_rq_merge_fn *elevator_allow_rq_merge_fn;
 	elevator_bio_merged_fn *elevator_bio_merged_fn;
 
 	elevator_dispatch_fn *elevator_dispatch_fn;
@@ -134,7 +139,7 @@ extern struct request *elv_former_request(struct request_queue *, struct request
 extern struct request *elv_latter_request(struct request_queue *, struct request *);
 extern int elv_register_queue(struct request_queue *q);
 extern void elv_unregister_queue(struct request_queue *q);
-extern int elv_may_queue(struct request_queue *, int);
+extern int elv_may_queue(struct request_queue *, int, int);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *q, struct request *rq,
 			   struct bio *bio, gfp_t gfp_mask);
@@ -157,7 +162,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 extern int elevator_init(struct request_queue *, char *);
 extern void elevator_exit(struct elevator_queue *);
 extern int elevator_change(struct request_queue *, const char *);
-extern bool elv_rq_merge_ok(struct request *, struct bio *);
+extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,
 					struct elevator_type *);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 97fe08d17d89..f2a69f20926f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -152,9 +152,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define CHECK_IOVEC_ONLY -1
 
 /*
- * The below are the various read and write types that we support. Some of
+ * The below are the various read and write flags that we support. Some of
  * them include behavioral modifiers that send information down to the
- * block layer and IO scheduler. Terminology:
+ * block layer and IO scheduler. They should be used along with a req_op.
+ * Terminology:
  *
  *	The block layer uses device plugging to defer IO a little bit, in
  *	the hope that we will see more IO very shortly. This increases
@@ -177,9 +178,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
  * READ_SYNC		A synchronous read. Device is not plugged, caller can
  *			immediately wait on this read without caring about
  *			unplugging.
- * READA		Used for read-ahead operations. Lower priority, and the
- *			block layer could (in theory) choose to ignore this
- *			request if it runs into resource problems.
  * WRITE		A normal async write. Device will be plugged.
  * WRITE_SYNC		Synchronous write. Identical to WRITE, but passes down
  *			the hint that someone will be waiting on this IO
@@ -193,19 +191,17 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
  *			non-volatile media on completion.
  *
  */
-#define RW_MASK			REQ_WRITE
-#define RWA_MASK		REQ_RAHEAD
+#define RW_MASK			REQ_OP_WRITE
 
-#define READ			0
-#define WRITE			RW_MASK
-#define READA			RWA_MASK
+#define READ			REQ_OP_READ
+#define WRITE			REQ_OP_WRITE
 
-#define READ_SYNC		(READ | REQ_SYNC)
-#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
-#define WRITE_ODIRECT		(WRITE | REQ_SYNC)
-#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
-#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
-#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
+#define READ_SYNC		REQ_SYNC
+#define WRITE_SYNC		(REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT		REQ_SYNC
+#define WRITE_FLUSH		(REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH)
+#define WRITE_FUA		(REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA		(REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA)
 
 /*
  * Attribute flags.  These should be or-ed together to figure out what
@@ -2470,15 +2466,18 @@ extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
 #ifdef CONFIG_BLOCK
-/*
- * return READ, READA, or WRITE
- */
-#define bio_rw(bio)		((bio)->bi_rw & (RW_MASK | RWA_MASK))
+static inline bool op_is_write(unsigned int op)
+{
+	return op == REQ_OP_READ ? false : true;
+}
 
 /*
  * return data direction, READ or WRITE
  */
-#define bio_data_dir(bio)	((bio)->bi_rw & 1)
+static inline int bio_data_dir(struct bio *bio)
+{
+	return op_is_write(bio_op(bio)) ? WRITE : READ;
+}
 
 extern void check_disk_size_change(struct gendisk *disk,
 				   struct block_device *bdev);
@@ -2753,7 +2752,7 @@ static inline void remove_inode_hash(struct inode *inode)
 extern void inode_sb_list_add(struct inode *inode);
 
 #ifdef CONFIG_BLOCK
-extern blk_qc_t submit_bio(int, struct bio *);
+extern blk_qc_t submit_bio(struct bio *);
 extern int bdev_read_only(struct block_device *);
 #endif
 extern int set_blocksize(struct block_device *, int);
@@ -2808,7 +2807,7 @@ extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_BLOCK
-typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
+typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
 			    loff_t file_offset);
 
 enum {
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 359a8e4bd44d..1dbf52f9c24b 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -205,7 +205,6 @@ struct gendisk {
 	void *private_data;
 
 	int flags;
-	struct device *driverfs_dev;  // FIXME: remove
 	struct kobject *slave_dir;
 
 	struct timer_rand_state *random;
@@ -414,7 +413,12 @@ static inline void free_part_info(struct hd_struct *part)
 extern void part_round_stats(int cpu, struct hd_struct *part);
 
 /* block/genhd.c */
-extern void add_disk(struct gendisk *disk);
+extern void device_add_disk(struct device *parent, struct gendisk *disk);
+static inline void add_disk(struct gendisk *disk)
+{
+	device_add_disk(NULL, disk);
+}
+
 extern void del_gendisk(struct gendisk *gp);
 extern struct gendisk *get_gendisk(dev_t dev, int *partno);
 extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index efb232c5f668..dfaa1f4dcb0c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -491,10 +491,6 @@ struct jbd2_journal_handle
 
 	unsigned long		h_start_jiffies;
 	unsigned int		h_requested_credits;
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	h_lockdep_map;
-#endif
 };
 
 
@@ -793,6 +789,7 @@ jbd2_time_diff(unsigned long start, unsigned long end)
  * @j_proc_entry: procfs entry for the jbd statistics directory
  * @j_stats: Overall statistics
  * @j_private: An opaque pointer to fs-private information.
+ * @j_trans_commit_map: Lockdep entity to track transaction commit dependencies
  */
 
 struct journal_s
@@ -1035,8 +1032,26 @@ struct journal_s
 
 	/* Precomputed journal UUID checksum for seeding other checksums */
 	__u32 j_csum_seed;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Lockdep entity to track transaction commit dependencies. Handles
+	 * hold this "lock" for read, when we wait for commit, we acquire the
+	 * "lock" for writing. This matches the properties of jbd2 journalling
+	 * where the running transaction has to wait for all handles to be
+	 * dropped to commit that transaction and also acquiring a handle may
+	 * require transaction commit to finish.
+	 */
+	struct lockdep_map	j_trans_commit_map;
+#endif
 };
 
+#define jbd2_might_wait_for_commit(j) \
+	do { \
+		rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \
+		rwsem_release(&j->j_trans_commit_map, 1, _THIS_IP_); \
+	} while (0)
+
 /* journal feature predicate functions */
 #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \
 static inline bool jbd2_has_feature_##name(journal_t *j) \
diff --git a/include/linux/libata.h b/include/linux/libata.h
index d15c19e331d1..e37d4f99f510 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -146,13 +146,6 @@ enum {
 	ATA_TFLAG_FUA		= (1 << 5), /* enable FUA */
 	ATA_TFLAG_POLLING	= (1 << 6), /* set nIEN to 1 and use polling */
 
-	/* protocol flags */
-	ATA_PROT_FLAG_PIO	= (1 << 0), /* is PIO */
-	ATA_PROT_FLAG_DMA	= (1 << 1), /* is DMA */
-	ATA_PROT_FLAG_DATA	= ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA,
-	ATA_PROT_FLAG_NCQ	= (1 << 2), /* is NCQ */
-	ATA_PROT_FLAG_ATAPI	= (1 << 3), /* is ATAPI */
-
 	/* struct ata_device stuff */
 	ATA_DFLAG_LBA		= (1 << 0), /* device supports LBA */
 	ATA_DFLAG_LBA48		= (1 << 1), /* device supports LBA48 */
@@ -1039,58 +1032,29 @@ extern const unsigned long sata_deb_timing_long[];
 extern struct ata_port_operations ata_dummy_port_ops;
 extern const struct ata_port_info ata_dummy_port_info;
 
-/*
- * protocol tests
- */
-static inline unsigned int ata_prot_flags(u8 prot)
-{
-	switch (prot) {
-	case ATA_PROT_NODATA:
-		return 0;
-	case ATA_PROT_PIO:
-		return ATA_PROT_FLAG_PIO;
-	case ATA_PROT_DMA:
-		return ATA_PROT_FLAG_DMA;
-	case ATA_PROT_NCQ:
-		return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ;
-	case ATAPI_PROT_NODATA:
-		return ATA_PROT_FLAG_ATAPI;
-	case ATAPI_PROT_PIO:
-		return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO;
-	case ATAPI_PROT_DMA:
-		return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA;
-	}
-	return 0;
-}
-
-static inline int ata_is_atapi(u8 prot)
-{
-	return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI;
-}
-
-static inline int ata_is_nodata(u8 prot)
+static inline bool ata_is_atapi(u8 prot)
 {
-	return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA);
+	return prot & ATA_PROT_FLAG_ATAPI;
 }
 
-static inline int ata_is_pio(u8 prot)
+static inline bool ata_is_pio(u8 prot)
 {
-	return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO;
+	return prot & ATA_PROT_FLAG_PIO;
 }
 
-static inline int ata_is_dma(u8 prot)
+static inline bool ata_is_dma(u8 prot)
 {
-	return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA;
+	return prot & ATA_PROT_FLAG_DMA;
 }
 
-static inline int ata_is_ncq(u8 prot)
+static inline bool ata_is_ncq(u8 prot)
 {
-	return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ;
+	return prot & ATA_PROT_FLAG_NCQ;
 }
 
-static inline int ata_is_data(u8 prot)
+static inline bool ata_is_data(u8 prot)
 {
-	return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA;
+	return prot & (ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA);
 }
 
 static inline int is_multi_taskfile(struct ata_taskfile *tf)
@@ -1407,7 +1371,7 @@ static inline bool sata_pmp_attached(struct ata_port *ap)
 	return ap->nr_pmp_links != 0;
 }
 
-static inline int ata_is_host_link(const struct ata_link *link)
+static inline bool ata_is_host_link(const struct ata_link *link)
 {
 	return link == &link->ap->link || link == link->ap->slave_link;
 }
@@ -1422,7 +1386,7 @@ static inline bool sata_pmp_attached(struct ata_port *ap)
 	return false;
 }
 
-static inline int ata_is_host_link(const struct ata_link *link)
+static inline bool ata_is_host_link(const struct ata_link *link)
 {
 	return 1;
 }
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index ef2c7d2e76c4..ba78b8306674 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -1,7 +1,9 @@
 #ifndef NVM_H
 #define NVM_H
 
+#include <linux/blkdev.h>
 #include <linux/types.h>
+#include <uapi/linux/lightnvm.h>
 
 enum {
 	NVM_IO_OK = 0,
@@ -269,24 +271,15 @@ struct nvm_lun {
 	int lun_id;
 	int chnl_id;
 
-	/* It is up to the target to mark blocks as closed. If the target does
-	 * not do it, all blocks are marked as open, and nr_open_blocks
-	 * represents the number of blocks in use
-	 */
-	unsigned int nr_open_blocks;	/* Number of used, writable blocks */
-	unsigned int nr_closed_blocks;	/* Number of used, read-only blocks */
-	unsigned int nr_free_blocks;	/* Number of unused blocks */
-	unsigned int nr_bad_blocks;	/* Number of bad blocks */
-
 	spinlock_t lock;
 
+	unsigned int nr_free_blocks;	/* Number of unused blocks */
 	struct nvm_block *blocks;
 };
 
 enum {
 	NVM_BLK_ST_FREE =	0x1,	/* Free block */
-	NVM_BLK_ST_OPEN =	0x2,	/* Open block - read-write */
-	NVM_BLK_ST_CLOSED =	0x4,	/* Closed block - read-only */
+	NVM_BLK_ST_TGT =	0x2,	/* Block in use by target */
 	NVM_BLK_ST_BAD =	0x8,	/* Bad block */
 };
 
@@ -385,6 +378,7 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
 {
 	struct ppa_addr l;
 
+	l.ppa = 0;
 	/*
 	 * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc.
 	 */
@@ -455,6 +449,8 @@ struct nvm_tgt_type {
 	struct list_head list;
 };
 
+extern struct nvm_tgt_type *nvm_find_target_type(const char *, int);
+
 extern int nvm_register_tgt_type(struct nvm_tgt_type *);
 extern void nvm_unregister_tgt_type(struct nvm_tgt_type *);
 
@@ -463,6 +459,9 @@ extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t);
 
 typedef int (nvmm_register_fn)(struct nvm_dev *);
 typedef void (nvmm_unregister_fn)(struct nvm_dev *);
+
+typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *);
+typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *);
 typedef struct nvm_block *(nvmm_get_blk_fn)(struct nvm_dev *,
 					      struct nvm_lun *, unsigned long);
 typedef void (nvmm_put_blk_fn)(struct nvm_dev *, struct nvm_block *);
@@ -488,9 +487,10 @@ struct nvmm_type {
 	nvmm_register_fn *register_mgr;
 	nvmm_unregister_fn *unregister_mgr;
 
+	nvmm_create_tgt_fn *create_tgt;
+	nvmm_remove_tgt_fn *remove_tgt;
+
 	/* Block administration callbacks */
-	nvmm_get_blk_fn *get_blk_unlocked;
-	nvmm_put_blk_fn *put_blk_unlocked;
 	nvmm_get_blk_fn *get_blk;
 	nvmm_put_blk_fn *put_blk;
 	nvmm_open_blk_fn *open_blk;
@@ -520,10 +520,6 @@ struct nvmm_type {
 extern int nvm_register_mgr(struct nvmm_type *);
 extern void nvm_unregister_mgr(struct nvmm_type *);
 
-extern struct nvm_block *nvm_get_blk_unlocked(struct nvm_dev *,
-					struct nvm_lun *, unsigned long);
-extern void nvm_put_blk_unlocked(struct nvm_dev *, struct nvm_block *);
-
 extern struct nvm_block *nvm_get_blk(struct nvm_dev *, struct nvm_lun *,
 								unsigned long);
 extern void nvm_put_blk(struct nvm_dev *, struct nvm_block *);
@@ -532,11 +528,13 @@ extern int nvm_register(struct request_queue *, char *,
 						struct nvm_dev_ops *);
 extern void nvm_unregister(char *);
 
+void nvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type);
+
 extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *);
 extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *);
 extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *);
 extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *,
-						struct ppa_addr *, int, int);
+					const struct ppa_addr *, int, int);
 extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *);
 extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int);
 extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *);
diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h
index c72d5344f3b3..cadc6543909d 100644
--- a/include/linux/mfd/rn5t618.h
+++ b/include/linux/mfd/rn5t618.h
@@ -20,6 +20,7 @@
 #define RN5T618_OTPVER			0x01
 #define RN5T618_IODAC			0x02
 #define RN5T618_VINDAC			0x03
+#define RN5T618_OUT32KEN		0x05
 #define RN5T618_CPUCNT			0x06
 #define RN5T618_PSWR			0x07
 #define RN5T618_PONHIS			0x09
@@ -38,6 +39,7 @@
 #define RN5T618_DC1_SLOT		0x16
 #define RN5T618_DC2_SLOT		0x17
 #define RN5T618_DC3_SLOT		0x18
+#define RN5T618_DC4_SLOT		0x19
 #define RN5T618_LDO1_SLOT		0x1b
 #define RN5T618_LDO2_SLOT		0x1c
 #define RN5T618_LDO3_SLOT		0x1d
@@ -54,12 +56,16 @@
 #define RN5T618_DC2CTL2			0x2f
 #define RN5T618_DC3CTL			0x30
 #define RN5T618_DC3CTL2			0x31
+#define RN5T618_DC4CTL			0x32
+#define RN5T618_DC4CTL2			0x33
 #define RN5T618_DC1DAC			0x36
 #define RN5T618_DC2DAC			0x37
 #define RN5T618_DC3DAC			0x38
+#define RN5T618_DC4DAC			0x39
 #define RN5T618_DC1DAC_SLP		0x3b
 #define RN5T618_DC2DAC_SLP		0x3c
 #define RN5T618_DC3DAC_SLP		0x3d
+#define RN5T618_DC4DAC_SLP		0x3e
 #define RN5T618_DCIREN			0x40
 #define RN5T618_DCIRQ			0x41
 #define RN5T618_DCIRMON			0x42
@@ -211,6 +217,7 @@ enum {
 	RN5T618_DCDC1,
 	RN5T618_DCDC2,
 	RN5T618_DCDC3,
+	RN5T618_DCDC4,
 	RN5T618_LDO1,
 	RN5T618_LDO2,
 	RN5T618_LDO3,
@@ -221,8 +228,14 @@ enum {
 	RN5T618_REG_NUM,
 };
 
+enum {
+	RN5T567 = 0,
+	RN5T618,
+};
+
 struct rn5t618 {
 	struct regmap *regmap;
+	long variant;
 };
 
 #endif /* __LINUX_MFD_RN5T618_H */
diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h
index ac7fba44d7e4..1c88231496d3 100644
--- a/include/linux/mfd/tps65217.h
+++ b/include/linux/mfd/tps65217.h
@@ -257,6 +257,7 @@ struct tps65217 {
 	unsigned long id;
 	struct regulator_desc desc[TPS65217_NUM_REGULATOR];
 	struct regmap *regmap;
+	u8 *strobes;
 };
 
 static inline struct tps65217 *dev_to_tps65217(struct device *dev)
diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h
index d58f3b5f585a..7fdf5326f34e 100644
--- a/include/linux/mfd/tps65218.h
+++ b/include/linux/mfd/tps65218.h
@@ -246,6 +246,7 @@ enum tps65218_irqs {
  * @name:		Voltage regulator name
  * @min_uV:		minimum micro volts
  * @max_uV:		minimum micro volts
+ * @strobe:		sequencing strobe value for the regulator
  *
  * This data is used to check the regualtor voltage limits while setting.
  */
@@ -254,6 +255,7 @@ struct tps_info {
 	const char *name;
 	int min_uV;
 	int max_uV;
+	int strobe;
 };
 
 /**
diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 3a5abe95affd..1cc5ffb769af 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -80,8 +80,7 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign);
 int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 		    int *sign);
 void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign);
-int mpi_set_buffer(MPI a, const void *buffer, unsigned nbytes, int sign);
-int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned *nbytes,
+int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes,
 		     int *sign);
 
 #define log_mpidump g10_log_mpidump
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
new file mode 100644
index 000000000000..bf240a3cbf99
--- /dev/null
+++ b/include/linux/nvme-rdma.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _LINUX_NVME_RDMA_H
+#define _LINUX_NVME_RDMA_H
+
+enum nvme_rdma_cm_fmt {
+	NVME_RDMA_CM_FMT_1_0 = 0x0,
+};
+
+enum nvme_rdma_cm_status {
+	NVME_RDMA_CM_INVALID_LEN	= 0x01,
+	NVME_RDMA_CM_INVALID_RECFMT	= 0x02,
+	NVME_RDMA_CM_INVALID_QID	= 0x03,
+	NVME_RDMA_CM_INVALID_HSQSIZE	= 0x04,
+	NVME_RDMA_CM_INVALID_HRQSIZE	= 0x05,
+	NVME_RDMA_CM_NO_RSC		= 0x06,
+	NVME_RDMA_CM_INVALID_IRD	= 0x07,
+	NVME_RDMA_CM_INVALID_ORD	= 0x08,
+};
+
+/**
+ * struct nvme_rdma_cm_req - rdma connect request
+ *
+ * @recfmt:        format of the RDMA Private Data
+ * @qid:           queue Identifier for the Admin or I/O Queue
+ * @hrqsize:       host receive queue size to be created
+ * @hsqsize:       host send queue size to be created
+ */
+struct nvme_rdma_cm_req {
+	__le16		recfmt;
+	__le16		qid;
+	__le16		hrqsize;
+	__le16		hsqsize;
+	u8		rsvd[24];
+};
+
+/**
+ * struct nvme_rdma_cm_rep - rdma connect reply
+ *
+ * @recfmt:        format of the RDMA Private Data
+ * @crqsize:       controller receive queue size
+ */
+struct nvme_rdma_cm_rep {
+	__le16		recfmt;
+	__le16		crqsize;
+	u8		rsvd[28];
+};
+
+/**
+ * struct nvme_rdma_cm_rej - rdma connect reject
+ *
+ * @recfmt:        format of the RDMA Private Data
+ * @fsts:          error status for the associated connect request
+ */
+struct nvme_rdma_cm_rej {
+	__le16		recfmt;
+	__le16		sts;
+};
+
+#endif /* _LINUX_NVME_RDMA_H */
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 7d51b2904cb7..d8b37bab2887 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -16,6 +16,78 @@
 #define _LINUX_NVME_H
 
 #include <linux/types.h>
+#include <linux/uuid.h>
+
+/* NQN names in commands fields specified one size */
+#define NVMF_NQN_FIELD_LEN	256
+
+/* However the max length of a qualified name is another size */
+#define NVMF_NQN_SIZE		223
+
+#define NVMF_TRSVCID_SIZE	32
+#define NVMF_TRADDR_SIZE	256
+#define NVMF_TSAS_SIZE		256
+
+#define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
+
+#define NVME_RDMA_IP_PORT	4420
+
+enum nvme_subsys_type {
+	NVME_NQN_DISC	= 1,		/* Discovery type target subsystem */
+	NVME_NQN_NVME	= 2,		/* NVME type target subsystem */
+};
+
+/* Address Family codes for Discovery Log Page entry ADRFAM field */
+enum {
+	NVMF_ADDR_FAMILY_PCI	= 0,	/* PCIe */
+	NVMF_ADDR_FAMILY_IP4	= 1,	/* IP4 */
+	NVMF_ADDR_FAMILY_IP6	= 2,	/* IP6 */
+	NVMF_ADDR_FAMILY_IB	= 3,	/* InfiniBand */
+	NVMF_ADDR_FAMILY_FC	= 4,	/* Fibre Channel */
+};
+
+/* Transport Type codes for Discovery Log Page entry TRTYPE field */
+enum {
+	NVMF_TRTYPE_RDMA	= 1,	/* RDMA */
+	NVMF_TRTYPE_FC		= 2,	/* Fibre Channel */
+	NVMF_TRTYPE_LOOP	= 254,	/* Reserved for host usage */
+	NVMF_TRTYPE_MAX,
+};
+
+/* Transport Requirements codes for Discovery Log Page entry TREQ field */
+enum {
+	NVMF_TREQ_NOT_SPECIFIED	= 0,	/* Not specified */
+	NVMF_TREQ_REQUIRED	= 1,	/* Required */
+	NVMF_TREQ_NOT_REQUIRED	= 2,	/* Not Required */
+};
+
+/* RDMA QP Service Type codes for Discovery Log Page entry TSAS
+ * RDMA_QPTYPE field
+ */
+enum {
+	NVMF_RDMA_QPTYPE_CONNECTED	= 0, /* Reliable Connected */
+	NVMF_RDMA_QPTYPE_DATAGRAM	= 1, /* Reliable Datagram */
+};
+
+/* RDMA QP Service Type codes for Discovery Log Page entry TSAS
+ * RDMA_QPTYPE field
+ */
+enum {
+	NVMF_RDMA_PRTYPE_NOT_SPECIFIED	= 0, /* No Provider Specified */
+	NVMF_RDMA_PRTYPE_IB		= 1, /* InfiniBand */
+	NVMF_RDMA_PRTYPE_ROCE		= 2, /* InfiniBand RoCE */
+	NVMF_RDMA_PRTYPE_ROCEV2		= 3, /* InfiniBand RoCEV2 */
+	NVMF_RDMA_PRTYPE_IWARP		= 4, /* IWARP */
+};
+
+/* RDMA Connection Management Service Type codes for Discovery Log Page
+ * entry TSAS RDMA_CMS field
+ */
+enum {
+	NVMF_RDMA_CMS_RDMA_CM	= 0, /* Sockets based enpoint addressing */
+};
+
+#define NVMF_AQ_DEPTH		32
 
 enum {
 	NVME_REG_CAP	= 0x0000,	/* Controller Capabilities */
@@ -50,6 +122,13 @@ enum {
 #define NVME_CMB_CQS(cmbsz)	((cmbsz) & 0x2)
 #define NVME_CMB_SQS(cmbsz)	((cmbsz) & 0x1)
 
+/*
+ * Submission and Completion Queue Entry Sizes for the NVM command set.
+ * (In bytes and specified as a power of two (2^n)).
+ */
+#define NVME_NVM_IOSQES		6
+#define NVME_NVM_IOCQES		4
+
 enum {
 	NVME_CC_ENABLE		= 1 << 0,
 	NVME_CC_CSS_NVM		= 0 << 4,
@@ -61,8 +140,8 @@ enum {
 	NVME_CC_SHN_NORMAL	= 1 << 14,
 	NVME_CC_SHN_ABRUPT	= 2 << 14,
 	NVME_CC_SHN_MASK	= 3 << 14,
-	NVME_CC_IOSQES		= 6 << 16,
-	NVME_CC_IOCQES		= 4 << 20,
+	NVME_CC_IOSQES		= NVME_NVM_IOSQES << 16,
+	NVME_CC_IOCQES		= NVME_NVM_IOCQES << 20,
 	NVME_CSTS_RDY		= 1 << 0,
 	NVME_CSTS_CFS		= 1 << 1,
 	NVME_CSTS_NSSRO		= 1 << 4,
@@ -107,7 +186,11 @@ struct nvme_id_ctrl {
 	__u8			mdts;
 	__le16			cntlid;
 	__le32			ver;
-	__u8			rsvd84[172];
+	__le32			rtd3r;
+	__le32			rtd3e;
+	__le32			oaes;
+	__le32			ctratt;
+	__u8			rsvd100[156];
 	__le16			oacs;
 	__u8			acl;
 	__u8			aerl;
@@ -119,10 +202,12 @@ struct nvme_id_ctrl {
 	__u8			apsta;
 	__le16			wctemp;
 	__le16			cctemp;
-	__u8			rsvd270[242];
+	__u8			rsvd270[50];
+	__le16			kas;
+	__u8			rsvd322[190];
 	__u8			sqes;
 	__u8			cqes;
-	__u8			rsvd514[2];
+	__le16			maxcmd;
 	__le32			nn;
 	__le16			oncs;
 	__le16			fuses;
@@ -135,7 +220,15 @@ struct nvme_id_ctrl {
 	__le16			acwu;
 	__u8			rsvd534[2];
 	__le32			sgls;
-	__u8			rsvd540[1508];
+	__u8			rsvd540[228];
+	char			subnqn[256];
+	__u8			rsvd1024[768];
+	__le32			ioccsz;
+	__le32			iorcsz;
+	__le16			icdoff;
+	__u8			ctrattr;
+	__u8			msdbd;
+	__u8			rsvd1804[244];
 	struct nvme_id_power_state	psd[32];
 	__u8			vs[1024];
 };
@@ -274,6 +367,12 @@ struct nvme_reservation_status {
 	} regctl_ds[];
 };
 
+enum nvme_async_event_type {
+	NVME_AER_TYPE_ERROR	= 0,
+	NVME_AER_TYPE_SMART	= 1,
+	NVME_AER_TYPE_NOTICE	= 2,
+};
+
 /* I/O commands */
 
 enum nvme_opcode {
@@ -290,6 +389,84 @@ enum nvme_opcode {
 	nvme_cmd_resv_release	= 0x15,
 };
 
+/*
+ * Descriptor subtype - lower 4 bits of nvme_(keyed_)sgl_desc identifier
+ *
+ * @NVME_SGL_FMT_ADDRESS:     absolute address of the data block
+ * @NVME_SGL_FMT_OFFSET:      relative offset of the in-capsule data block
+ * @NVME_SGL_FMT_INVALIDATE:  RDMA transport specific remote invalidation
+ *                            request subtype
+ */
+enum {
+	NVME_SGL_FMT_ADDRESS		= 0x00,
+	NVME_SGL_FMT_OFFSET		= 0x01,
+	NVME_SGL_FMT_INVALIDATE		= 0x0f,
+};
+
+/*
+ * Descriptor type - upper 4 bits of nvme_(keyed_)sgl_desc identifier
+ *
+ * For struct nvme_sgl_desc:
+ *   @NVME_SGL_FMT_DATA_DESC:		data block descriptor
+ *   @NVME_SGL_FMT_SEG_DESC:		sgl segment descriptor
+ *   @NVME_SGL_FMT_LAST_SEG_DESC:	last sgl segment descriptor
+ *
+ * For struct nvme_keyed_sgl_desc:
+ *   @NVME_KEY_SGL_FMT_DATA_DESC:	keyed data block descriptor
+ */
+enum {
+	NVME_SGL_FMT_DATA_DESC		= 0x00,
+	NVME_SGL_FMT_SEG_DESC		= 0x02,
+	NVME_SGL_FMT_LAST_SEG_DESC	= 0x03,
+	NVME_KEY_SGL_FMT_DATA_DESC	= 0x04,
+};
+
+struct nvme_sgl_desc {
+	__le64	addr;
+	__le32	length;
+	__u8	rsvd[3];
+	__u8	type;
+};
+
+struct nvme_keyed_sgl_desc {
+	__le64	addr;
+	__u8	length[3];
+	__u8	key[4];
+	__u8	type;
+};
+
+union nvme_data_ptr {
+	struct {
+		__le64	prp1;
+		__le64	prp2;
+	};
+	struct nvme_sgl_desc	sgl;
+	struct nvme_keyed_sgl_desc ksgl;
+};
+
+/*
+ * Lowest two bits of our flags field (FUSE field in the spec):
+ *
+ * @NVME_CMD_FUSE_FIRST:   Fused Operation, first command
+ * @NVME_CMD_FUSE_SECOND:  Fused Operation, second command
+ *
+ * Highest two bits in our flags field (PSDT field in the spec):
+ *
+ * @NVME_CMD_PSDT_SGL_METABUF:	Use SGLS for this transfer,
+ *	If used, MPTR contains addr of single physical buffer (byte aligned).
+ * @NVME_CMD_PSDT_SGL_METASEG:	Use SGLS for this transfer,
+ *	If used, MPTR contains an address of an SGL segment containing
+ *	exactly 1 SGL descriptor (qword aligned).
+ */
+enum {
+	NVME_CMD_FUSE_FIRST	= (1 << 0),
+	NVME_CMD_FUSE_SECOND	= (1 << 1),
+
+	NVME_CMD_SGL_METABUF	= (1 << 6),
+	NVME_CMD_SGL_METASEG	= (1 << 7),
+	NVME_CMD_SGL_ALL	= NVME_CMD_SGL_METABUF | NVME_CMD_SGL_METASEG,
+};
+
 struct nvme_common_command {
 	__u8			opcode;
 	__u8			flags;
@@ -297,8 +474,7 @@ struct nvme_common_command {
 	__le32			nsid;
 	__le32			cdw2[2];
 	__le64			metadata;
-	__le64			prp1;
-	__le64			prp2;
+	union nvme_data_ptr	dptr;
 	__le32			cdw10[6];
 };
 
@@ -309,8 +485,7 @@ struct nvme_rw_command {
 	__le32			nsid;
 	__u64			rsvd2;
 	__le64			metadata;
-	__le64			prp1;
-	__le64			prp2;
+	union nvme_data_ptr	dptr;
 	__le64			slba;
 	__le16			length;
 	__le16			control;
@@ -350,8 +525,7 @@ struct nvme_dsm_cmd {
 	__u16			command_id;
 	__le32			nsid;
 	__u64			rsvd2[2];
-	__le64			prp1;
-	__le64			prp2;
+	union nvme_data_ptr	dptr;
 	__le32			nr;
 	__le32			attributes;
 	__u32			rsvd12[4];
@@ -384,6 +558,7 @@ enum nvme_admin_opcode {
 	nvme_admin_async_event		= 0x0c,
 	nvme_admin_activate_fw		= 0x10,
 	nvme_admin_download_fw		= 0x11,
+	nvme_admin_keep_alive		= 0x18,
 	nvme_admin_format_nvm		= 0x80,
 	nvme_admin_security_send	= 0x81,
 	nvme_admin_security_recv	= 0x82,
@@ -408,6 +583,7 @@ enum {
 	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
 	NVME_FEAT_ASYNC_EVENT	= 0x0b,
 	NVME_FEAT_AUTO_PST	= 0x0c,
+	NVME_FEAT_KATO		= 0x0f,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
@@ -415,6 +591,7 @@ enum {
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
+	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
 	NVME_FWACT_REPL_ACTV	= (1 << 3),
@@ -427,8 +604,7 @@ struct nvme_identify {
 	__u16			command_id;
 	__le32			nsid;
 	__u64			rsvd2[2];
-	__le64			prp1;
-	__le64			prp2;
+	union nvme_data_ptr	dptr;
 	__le32			cns;
 	__u32			rsvd11[5];
 };
@@ -439,8 +615,7 @@ struct nvme_features {
 	__u16			command_id;
 	__le32			nsid;
 	__u64			rsvd2[2];
-	__le64			prp1;
-	__le64			prp2;
+	union nvme_data_ptr	dptr;
 	__le32			fid;
 	__le32			dword11;
 	__u32			rsvd12[4];
@@ -499,8 +674,7 @@ struct nvme_download_firmware {
 	__u8			flags;
 	__u16			command_id;
 	__u32			rsvd1[5];
-	__le64			prp1;
-	__le64			prp2;
+	union nvme_data_ptr	dptr;
 	__le32			numd;
 	__le32			offset;
 	__u32			rsvd12[4];
@@ -516,6 +690,143 @@ struct nvme_format_cmd {
 	__u32			rsvd11[5];
 };
 
+struct nvme_get_log_page_command {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__u64			rsvd2[2];
+	union nvme_data_ptr	dptr;
+	__u8			lid;
+	__u8			rsvd10;
+	__le16			numdl;
+	__le16			numdu;
+	__u16			rsvd11;
+	__le32			lpol;
+	__le32			lpou;
+	__u32			rsvd14[2];
+};
+
+/*
+ * Fabrics subcommands.
+ */
+enum nvmf_fabrics_opcode {
+	nvme_fabrics_command		= 0x7f,
+};
+
+enum nvmf_capsule_command {
+	nvme_fabrics_type_property_set	= 0x00,
+	nvme_fabrics_type_connect	= 0x01,
+	nvme_fabrics_type_property_get	= 0x04,
+};
+
+struct nvmf_common_command {
+	__u8	opcode;
+	__u8	resv1;
+	__u16	command_id;
+	__u8	fctype;
+	__u8	resv2[35];
+	__u8	ts[24];
+};
+
+/*
+ * The legal cntlid range a NVMe Target will provide.
+ * Note that cntlid of value 0 is considered illegal in the fabrics world.
+ * Devices based on earlier specs did not have the subsystem concept;
+ * therefore, those devices had their cntlid value set to 0 as a result.
+ */
+#define NVME_CNTLID_MIN		1
+#define NVME_CNTLID_MAX		0xffef
+#define NVME_CNTLID_DYNAMIC	0xffff
+
+#define MAX_DISC_LOGS	255
+
+/* Discovery log page entry */
+struct nvmf_disc_rsp_page_entry {
+	__u8		trtype;
+	__u8		adrfam;
+	__u8		nqntype;
+	__u8		treq;
+	__le16		portid;
+	__le16		cntlid;
+	__le16		asqsz;
+	__u8		resv8[22];
+	char		trsvcid[NVMF_TRSVCID_SIZE];
+	__u8		resv64[192];
+	char		subnqn[NVMF_NQN_FIELD_LEN];
+	char		traddr[NVMF_TRADDR_SIZE];
+	union tsas {
+		char		common[NVMF_TSAS_SIZE];
+		struct rdma {
+			__u8	qptype;
+			__u8	prtype;
+			__u8	cms;
+			__u8	resv3[5];
+			__u16	pkey;
+			__u8	resv10[246];
+		} rdma;
+	} tsas;
+};
+
+/* Discovery log page header */
+struct nvmf_disc_rsp_page_hdr {
+	__le64		genctr;
+	__le64		numrec;
+	__le16		recfmt;
+	__u8		resv14[1006];
+	struct nvmf_disc_rsp_page_entry entries[0];
+};
+
+struct nvmf_connect_command {
+	__u8		opcode;
+	__u8		resv1;
+	__u16		command_id;
+	__u8		fctype;
+	__u8		resv2[19];
+	union nvme_data_ptr dptr;
+	__le16		recfmt;
+	__le16		qid;
+	__le16		sqsize;
+	__u8		cattr;
+	__u8		resv3;
+	__le32		kato;
+	__u8		resv4[12];
+};
+
+struct nvmf_connect_data {
+	uuid_le		hostid;
+	__le16		cntlid;
+	char		resv4[238];
+	char		subsysnqn[NVMF_NQN_FIELD_LEN];
+	char		hostnqn[NVMF_NQN_FIELD_LEN];
+	char		resv5[256];
+};
+
+struct nvmf_property_set_command {
+	__u8		opcode;
+	__u8		resv1;
+	__u16		command_id;
+	__u8		fctype;
+	__u8		resv2[35];
+	__u8		attrib;
+	__u8		resv3[3];
+	__le32		offset;
+	__le64		value;
+	__u8		resv4[8];
+};
+
+struct nvmf_property_get_command {
+	__u8		opcode;
+	__u8		resv1;
+	__u16		command_id;
+	__u8		fctype;
+	__u8		resv2[35];
+	__u8		attrib;
+	__u8		resv3[3];
+	__le32		offset;
+	__u8		resv4[16];
+};
+
 struct nvme_command {
 	union {
 		struct nvme_common_command common;
@@ -529,10 +840,30 @@ struct nvme_command {
 		struct nvme_format_cmd format;
 		struct nvme_dsm_cmd dsm;
 		struct nvme_abort_cmd abort;
+		struct nvme_get_log_page_command get_log_page;
+		struct nvmf_common_command fabrics;
+		struct nvmf_connect_command connect;
+		struct nvmf_property_set_command prop_set;
+		struct nvmf_property_get_command prop_get;
 	};
 };
 
+static inline bool nvme_is_write(struct nvme_command *cmd)
+{
+	/*
+	 * What a mess...
+	 *
+	 * Why can't we simply have a Fabrics In and Fabrics out command?
+	 */
+	if (unlikely(cmd->common.opcode == nvme_fabrics_command))
+		return cmd->fabrics.opcode & 1;
+	return cmd->common.opcode & 1;
+}
+
 enum {
+	/*
+	 * Generic Command Status:
+	 */
 	NVME_SC_SUCCESS			= 0x0,
 	NVME_SC_INVALID_OPCODE		= 0x1,
 	NVME_SC_INVALID_FIELD		= 0x2,
@@ -551,10 +882,18 @@ enum {
 	NVME_SC_SGL_INVALID_DATA	= 0xf,
 	NVME_SC_SGL_INVALID_METADATA	= 0x10,
 	NVME_SC_SGL_INVALID_TYPE	= 0x11,
+
+	NVME_SC_SGL_INVALID_OFFSET	= 0x16,
+	NVME_SC_SGL_INVALID_SUBTYPE	= 0x17,
+
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
 	NVME_SC_NS_NOT_READY		= 0x82,
 	NVME_SC_RESERVATION_CONFLICT	= 0x83,
+
+	/*
+	 * Command Specific Status:
+	 */
 	NVME_SC_CQ_INVALID		= 0x100,
 	NVME_SC_QID_INVALID		= 0x101,
 	NVME_SC_QUEUE_SIZE		= 0x102,
@@ -572,9 +911,29 @@ enum {
 	NVME_SC_FEATURE_NOT_CHANGEABLE	= 0x10e,
 	NVME_SC_FEATURE_NOT_PER_NS	= 0x10f,
 	NVME_SC_FW_NEEDS_RESET_SUBSYS	= 0x110,
+
+	/*
+	 * I/O Command Set Specific - NVM commands:
+	 */
 	NVME_SC_BAD_ATTRIBUTES		= 0x180,
 	NVME_SC_INVALID_PI		= 0x181,
 	NVME_SC_READ_ONLY		= 0x182,
+
+	/*
+	 * I/O Command Set Specific - Fabrics commands:
+	 */
+	NVME_SC_CONNECT_FORMAT		= 0x180,
+	NVME_SC_CONNECT_CTRL_BUSY	= 0x181,
+	NVME_SC_CONNECT_INVALID_PARAM	= 0x182,
+	NVME_SC_CONNECT_RESTART_DISC	= 0x183,
+	NVME_SC_CONNECT_INVALID_HOST	= 0x184,
+
+	NVME_SC_DISCOVERY_RESTART	= 0x190,
+	NVME_SC_AUTH_REQUIRED		= 0x191,
+
+	/*
+	 * Media and Data Integrity Errors:
+	 */
 	NVME_SC_WRITE_FAULT		= 0x280,
 	NVME_SC_READ_ERROR		= 0x281,
 	NVME_SC_GUARD_CHECK		= 0x282,
@@ -582,12 +941,19 @@ enum {
 	NVME_SC_REFTAG_CHECK		= 0x284,
 	NVME_SC_COMPARE_FAILED		= 0x285,
 	NVME_SC_ACCESS_DENIED		= 0x286,
+
 	NVME_SC_DNR			= 0x4000,
 };
 
 struct nvme_completion {
-	__le32	result;		/* Used by admin commands to return data */
-	__u32	rsvd;
+	/*
+	 * Used by Admin and Fabrics commands to return data:
+	 */
+	union {
+		__le16	result16;
+		__le32	result;
+		__le64	result64;
+	};
 	__le16	sq_head;	/* how much of this queue may be reclaimed */
 	__le16	sq_id;		/* submission queue that generated this entry */
 	__u16	command_id;	/* of the command which completed */
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
index c201060e0c6d..f8e1992d6423 100644
--- a/include/linux/of_reserved_mem.h
+++ b/include/linux/of_reserved_mem.h
@@ -1,7 +1,8 @@
 #ifndef __OF_RESERVED_MEM_H
 #define __OF_RESERVED_MEM_H
 
-struct device;
+#include <linux/device.h>
+
 struct of_phandle_args;
 struct reserved_mem_ops;
 
@@ -28,7 +29,9 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem);
 	_OF_DECLARE(reservedmem, name, compat, init, reservedmem_of_init_fn)
 
 #ifdef CONFIG_OF_RESERVED_MEM
-int of_reserved_mem_device_init(struct device *dev);
+
+int of_reserved_mem_device_init_by_idx(struct device *dev,
+				       struct device_node *np, int idx);
 void of_reserved_mem_device_release(struct device *dev);
 
 int early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
@@ -42,7 +45,8 @@ void fdt_init_reserved_mem(void);
 void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
 			       phys_addr_t base, phys_addr_t size);
 #else
-static inline int of_reserved_mem_device_init(struct device *dev)
+static inline int of_reserved_mem_device_init_by_idx(struct device *dev,
+					struct device_node *np, int idx)
 {
 	return -ENOSYS;
 }
@@ -53,4 +57,19 @@ static inline void fdt_reserved_mem_save_node(unsigned long node,
 		const char *uname, phys_addr_t base, phys_addr_t size) { }
 #endif
 
+/**
+ * of_reserved_mem_device_init() - assign reserved memory region to given device
+ * @dev:	Pointer to the device to configure
+ *
+ * This function assigns respective DMA-mapping operations based on the first
+ * reserved memory region specified by 'memory-region' property in device tree
+ * node of the given device.
+ *
+ * Returns error code or zero on success.
+ */
+static inline int of_reserved_mem_device_init(struct device *dev)
+{
+	return of_reserved_mem_device_init_by_idx(dev, dev->of_node, 0);
+}
+
 #endif /* __OF_RESERVED_MEM_H */
diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h
index 308d6044f153..09779b0ae720 100644
--- a/include/linux/pm_clock.h
+++ b/include/linux/pm_clock.h
@@ -42,6 +42,7 @@ extern int pm_clk_create(struct device *dev);
 extern void pm_clk_destroy(struct device *dev);
 extern int pm_clk_add(struct device *dev, const char *con_id);
 extern int pm_clk_add_clk(struct device *dev, struct clk *clk);
+extern int of_pm_clk_add_clk(struct device *dev, const char *name);
 extern int of_pm_clk_add_clks(struct device *dev);
 extern void pm_clk_remove(struct device *dev, const char *con_id);
 extern void pm_clk_remove_clk(struct device *dev, struct clk *clk);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 39285c7bd3f5..31fec858088c 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -57,7 +57,6 @@ struct generic_pm_domain {
 	unsigned int device_count;	/* Number of devices */
 	unsigned int suspended_count;	/* System suspend device counter */
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
-	bool suspend_power_off;	/* Power status before system suspend */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
 	struct gpd_dev_ops dev_ops;
@@ -128,8 +127,8 @@ extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 				  struct generic_pm_domain *new_subdomain);
 extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 				     struct generic_pm_domain *target);
-extern void pm_genpd_init(struct generic_pm_domain *genpd,
-			  struct dev_power_governor *gov, bool is_off);
+extern int pm_genpd_init(struct generic_pm_domain *genpd,
+			 struct dev_power_governor *gov, bool is_off);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
@@ -164,9 +163,10 @@ static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 {
 	return -ENOSYS;
 }
-static inline void pm_genpd_init(struct generic_pm_domain *genpd,
-				 struct dev_power_governor *gov, bool is_off)
+static inline int pm_genpd_init(struct generic_pm_domain *genpd,
+				struct dev_power_governor *gov, bool is_off)
 {
+	return -ENOSYS;
 }
 #endif
 
diff --git a/include/linux/power/max8903_charger.h b/include/linux/power/max8903_charger.h
index 24f51db8a83f..89d3f1cb3433 100644
--- a/include/linux/power/max8903_charger.h
+++ b/include/linux/power/max8903_charger.h
@@ -26,8 +26,8 @@
 struct max8903_pdata {
 	/*
 	 * GPIOs
-	 * cen, chg, flt, and usus are optional.
-	 * dok, dcm, and uok are not optional depending on the status of
+	 * cen, chg, flt, dcm and usus are optional.
+	 * dok and uok are not optional depending on the status of
 	 * dc_valid and usb_valid.
 	 */
 	int cen;	/* Charger Enable input */
@@ -41,7 +41,7 @@ struct max8903_pdata {
 	/*
 	 * DC(Adapter/TA) is wired
 	 * When dc_valid is true,
-	 *	dok and dcm should be valid.
+	 *	dok should be valid.
 	 *
 	 * At least one of dc_valid or usb_valid should be true.
 	 */
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 751061790626..3965503315ef 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -248,6 +248,7 @@ struct power_supply {
 	struct delayed_work deferred_register_work;
 	spinlock_t changed_lock;
 	bool changed;
+	bool initialized;
 	atomic_t use_cnt;
 #ifdef CONFIG_THERMAL
 	struct thermal_zone_device *tzd;
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index 831479f8df8f..899e95e84400 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -58,7 +58,8 @@ struct pstore_info {
 	int		(*close)(struct pstore_info *psi);
 	ssize_t		(*read)(u64 *id, enum pstore_type_id *type,
 			int *count, struct timespec *time, char **buf,
-			bool *compressed, struct pstore_info *psi);
+			bool *compressed, ssize_t *ecc_notice_size,
+			struct pstore_info *psi);
 	int		(*write)(enum pstore_type_id type,
 			enum kmsg_dump_reason reason, u64 *id,
 			unsigned int part, int count, bool compressed,
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 3dc08ce15426..2c12cc5af744 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -95,6 +95,45 @@ struct reg_sequence {
 #define	regmap_fields_force_update_bits(field, id, mask, val) \
 	regmap_fields_update_bits_base(field, id, mask, val, NULL, false, true)
 
+/**
+ * regmap_read_poll_timeout - Poll until a condition is met or a timeout occurs
+ * @map: Regmap to read from
+ * @addr: Address to poll
+ * @val: Unsigned integer variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0
+ *            tight-loops).  Should be less than ~20ms since usleep_range
+ *            is used (see Documentation/timers/timers-howto.txt).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ *
+ * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read
+ * error return value in case of a error read. In the two former cases,
+ * the last read value at @addr is stored in @val. Must not be called
+ * from atomic context if sleep_us or timeout_us are used.
+ *
+ * This is modelled after the readx_poll_timeout macros in linux/iopoll.h.
+ */
+#define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \
+({ \
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+	int ret; \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		ret = regmap_read((map), (addr), &(val)); \
+		if (ret) \
+			break; \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+			ret = regmap_read((map), (addr), &(val)); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	ret ?: ((cond) ? 0 : -ETIMEDOUT); \
+})
+
 #ifdef CONFIG_REGMAP
 
 enum regmap_endian {
@@ -851,6 +890,12 @@ struct regmap_irq {
  * @num_type_reg:    Number of type registers.
  * @type_reg_stride: Stride to use for chips where type registers are not
  *			contiguous.
+ * @handle_pre_irq:  Driver specific callback to handle interrupt from device
+ *		     before regmap_irq_handler process the interrupts.
+ * @handle_post_irq: Driver specific callback to handle interrupt from device
+ *		     after handling the interrupts in regmap_irq_handler().
+ * @irq_drv_data:    Driver specific IRQ data which is passed as parameter when
+ *		     driver specific pre/post interrupt handler is called.
  */
 struct regmap_irq_chip {
 	const char *name;
@@ -877,6 +922,10 @@ struct regmap_irq_chip {
 
 	int num_type_reg;
 	unsigned int type_reg_stride;
+
+	int (*handle_pre_irq)(void *irq_drv_data);
+	int (*handle_post_irq)(void *irq_drv_data);
+	void *irq_drv_data;
 };
 
 struct regmap_irq_chip_data;
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 48603506f8de..cae500b2c1d7 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -224,7 +224,6 @@ int regulator_bulk_force_disable(int num_consumers,
 void regulator_bulk_free(int num_consumers,
 			 struct regulator_bulk_data *consumers);
 
-int regulator_can_change_voltage(struct regulator *regulator);
 int regulator_count_voltages(struct regulator *regulator);
 int regulator_list_voltage(struct regulator *regulator, unsigned selector);
 int regulator_is_supported_voltage(struct regulator *regulator,
@@ -436,11 +435,6 @@ static inline void regulator_bulk_free(int num_consumers,
 {
 }
 
-static inline int regulator_can_change_voltage(struct regulator *regulator)
-{
-	return 0;
-}
-
 static inline int regulator_set_voltage(struct regulator *regulator,
 					int min_uV, int max_uV)
 {
diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h
index a43a5ca1167b..80cb40b7c88d 100644
--- a/include/linux/regulator/da9211.h
+++ b/include/linux/regulator/da9211.h
@@ -1,5 +1,6 @@
 /*
- * da9211.h - Regulator device driver for DA9211/DA9213/DA9215
+ * da9211.h - Regulator device driver for DA9211/DA9212
+ * /DA9213/DA9214/DA9215
  * Copyright (C) 2015  Dialog Semiconductor Ltd.
  *
  * This program is free software; you can redistribute it and/or
@@ -22,7 +23,9 @@
 
 enum da9211_chip_id {
 	DA9211,
+	DA9212,
 	DA9213,
+	DA9214,
 	DA9215,
 };
 
diff --git a/include/linux/regulator/mt6323-regulator.h b/include/linux/regulator/mt6323-regulator.h
new file mode 100644
index 000000000000..67011cd1ce55
--- /dev/null
+++ b/include/linux/regulator/mt6323-regulator.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Chen Zhong <chen.zhong@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_REGULATOR_MT6323_H
+#define __LINUX_REGULATOR_MT6323_H
+
+enum {
+	MT6323_ID_VPROC = 0,
+	MT6323_ID_VSYS,
+	MT6323_ID_VPA,
+	MT6323_ID_VTCXO,
+	MT6323_ID_VCN28,
+	MT6323_ID_VCN33_BT,
+	MT6323_ID_VCN33_WIFI,
+	MT6323_ID_VA,
+	MT6323_ID_VCAMA,
+	MT6323_ID_VIO28 = 9,
+	MT6323_ID_VUSB,
+	MT6323_ID_VMC,
+	MT6323_ID_VMCH,
+	MT6323_ID_VEMC3V3,
+	MT6323_ID_VGP1,
+	MT6323_ID_VGP2,
+	MT6323_ID_VGP3,
+	MT6323_ID_VCN18,
+	MT6323_ID_VSIM1,
+	MT6323_ID_VSIM2,
+	MT6323_ID_VRTC,
+	MT6323_ID_VCAMAF,
+	MT6323_ID_VIBR,
+	MT6323_ID_VRF18,
+	MT6323_ID_VM,
+	MT6323_ID_VIO18,
+	MT6323_ID_VCAMD,
+	MT6323_ID_VCAMIO,
+	MT6323_ID_RG_MAX,
+};
+
+#define MT6323_MAX_REGULATOR	MT6323_ID_RG_MAX
+
+#endif /* __LINUX_REGULATOR_MT6323_H */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 8b6ec7ef0854..7693e39b14fe 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -18,12 +18,11 @@ static inline void pm_set_vt_switch(int do_switch)
 #endif
 
 #ifdef CONFIG_VT_CONSOLE_SLEEP
-extern int pm_prepare_console(void);
+extern void pm_prepare_console(void);
 extern void pm_restore_console(void);
 #else
-static inline int pm_prepare_console(void)
+static inline void pm_prepare_console(void)
 {
-	return 0;
 }
 
 static inline void pm_restore_console(void)
diff --git a/include/media/cec-edid.h b/include/media/cec-edid.h
new file mode 100644
index 000000000000..bdf731ecba1a
--- /dev/null
+++ b/include/media/cec-edid.h
@@ -0,0 +1,104 @@
+/*
+ * cec-edid - HDMI Consumer Electronics Control & EDID helpers
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#ifndef _MEDIA_CEC_EDID_H
+#define _MEDIA_CEC_EDID_H
+
+#include <linux/types.h>
+
+#define CEC_PHYS_ADDR_INVALID		0xffff
+#define cec_phys_addr_exp(pa) \
+	((pa) >> 12), ((pa) >> 8) & 0xf, ((pa) >> 4) & 0xf, (pa) & 0xf
+
+/**
+ * cec_get_edid_phys_addr() - find and return the physical address
+ *
+ * @edid:	pointer to the EDID data
+ * @size:	size in bytes of the EDID data
+ * @offset:	If not %NULL then the location of the physical address
+ *		bytes in the EDID will be returned here. This is set to 0
+ *		if there is no physical address found.
+ *
+ * Return: the physical address or CEC_PHYS_ADDR_INVALID if there is none.
+ */
+u16 cec_get_edid_phys_addr(const u8 *edid, unsigned int size,
+			   unsigned int *offset);
+
+/**
+ * cec_set_edid_phys_addr() - find and set the physical address
+ *
+ * @edid:	pointer to the EDID data
+ * @size:	size in bytes of the EDID data
+ * @phys_addr:	the new physical address
+ *
+ * This function finds the location of the physical address in the EDID
+ * and fills in the given physical address and updates the checksum
+ * at the end of the EDID block. It does nothing if the EDID doesn't
+ * contain a physical address.
+ */
+void cec_set_edid_phys_addr(u8 *edid, unsigned int size, u16 phys_addr);
+
+/**
+ * cec_phys_addr_for_input() - calculate the PA for an input
+ *
+ * @phys_addr:	the physical address of the parent
+ * @input:	the number of the input port, must be between 1 and 15
+ *
+ * This function calculates a new physical address based on the input
+ * port number. For example:
+ *
+ * PA = 0.0.0.0 and input = 2 becomes 2.0.0.0
+ *
+ * PA = 3.0.0.0 and input = 1 becomes 3.1.0.0
+ *
+ * PA = 3.2.1.0 and input = 5 becomes 3.2.1.5
+ *
+ * PA = 3.2.1.3 and input = 5 becomes f.f.f.f since it maxed out the depth.
+ *
+ * Return: the new physical address or CEC_PHYS_ADDR_INVALID.
+ */
+u16 cec_phys_addr_for_input(u16 phys_addr, u8 input);
+
+/**
+ * cec_phys_addr_validate() - validate a physical address from an EDID
+ *
+ * @phys_addr:	the physical address to validate
+ * @parent:	if not %NULL, then this is filled with the parents PA.
+ * @port:	if not %NULL, then this is filled with the input port.
+ *
+ * This validates a physical address as read from an EDID. If the
+ * PA is invalid (such as 1.0.1.0 since '0' is only allowed at the end),
+ * then it will return -EINVAL.
+ *
+ * The parent PA is passed into %parent and the input port is passed into
+ * %port. For example:
+ *
+ * PA = 0.0.0.0: has parent 0.0.0.0 and input port 0.
+ *
+ * PA = 1.0.0.0: has parent 0.0.0.0 and input port 1.
+ *
+ * PA = 3.2.0.0: has parent 3.0.0.0 and input port 2.
+ *
+ * PA = f.f.f.f: has parent f.f.f.f and input port 0.
+ *
+ * Return: 0 if the PA is valid, -EINVAL if not.
+ */
+int cec_phys_addr_validate(u16 phys_addr, u16 *parent, u16 *port);
+
+#endif /* _MEDIA_CEC_EDID_H */
diff --git a/include/media/cec.h b/include/media/cec.h
new file mode 100644
index 000000000000..dc7854b855f3
--- /dev/null
+++ b/include/media/cec.h
@@ -0,0 +1,241 @@
+/*
+ * cec - HDMI Consumer Electronics Control support header
+ *
+ * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ */
+
+#ifndef _MEDIA_CEC_H
+#define _MEDIA_CEC_H
+
+#include <linux/poll.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/cdev.h>
+#include <linux/kthread.h>
+#include <linux/timer.h>
+#include <linux/cec-funcs.h>
+#include <media/rc-core.h>
+#include <media/cec-edid.h>
+
+/**
+ * struct cec_devnode - cec device node
+ * @dev:	cec device
+ * @cdev:	cec character device
+ * @parent:	parent device
+ * @minor:	device node minor number
+ * @registered:	the device was correctly registered
+ * @unregistered: the device was unregistered
+ * @fhs_lock:	lock to control access to the filehandle list
+ * @fhs:	the list of open filehandles (cec_fh)
+ *
+ * This structure represents a cec-related device node.
+ *
+ * The @parent is a physical device. It must be set by core or device drivers
+ * before registering the node.
+ */
+struct cec_devnode {
+	/* sysfs */
+	struct device dev;
+	struct cdev cdev;
+	struct device *parent;
+
+	/* device info */
+	int minor;
+	bool registered;
+	bool unregistered;
+	struct mutex fhs_lock;
+	struct list_head fhs;
+};
+
+struct cec_adapter;
+struct cec_data;
+
+struct cec_data {
+	struct list_head list;
+	struct list_head xfer_list;
+	struct cec_adapter *adap;
+	struct cec_msg msg;
+	struct cec_fh *fh;
+	struct delayed_work work;
+	struct completion c;
+	u8 attempts;
+	bool new_initiator;
+	bool blocking;
+	bool completed;
+};
+
+struct cec_msg_entry {
+	struct list_head	list;
+	struct cec_msg		msg;
+};
+
+#define CEC_NUM_EVENTS		CEC_EVENT_LOST_MSGS
+
+struct cec_fh {
+	struct list_head	list;
+	struct list_head	xfer_list;
+	struct cec_adapter	*adap;
+	u8			mode_initiator;
+	u8			mode_follower;
+
+	/* Events */
+	wait_queue_head_t	wait;
+	unsigned int		pending_events;
+	struct cec_event	events[CEC_NUM_EVENTS];
+	struct mutex		lock;
+	struct list_head	msgs; /* queued messages */
+	unsigned int		queued_msgs;
+};
+
+#define CEC_SIGNAL_FREE_TIME_RETRY		3
+#define CEC_SIGNAL_FREE_TIME_NEW_INITIATOR	5
+#define CEC_SIGNAL_FREE_TIME_NEXT_XFER		7
+
+/* The nominal data bit period is 2.4 ms */
+#define CEC_FREE_TIME_TO_USEC(ft)		((ft) * 2400)
+
+struct cec_adap_ops {
+	/* Low-level callbacks */
+	int (*adap_enable)(struct cec_adapter *adap, bool enable);
+	int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable);
+	int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr);
+	int (*adap_transmit)(struct cec_adapter *adap, u8 attempts,
+			     u32 signal_free_time, struct cec_msg *msg);
+	void (*adap_status)(struct cec_adapter *adap, struct seq_file *file);
+
+	/* High-level CEC message callback */
+	int (*received)(struct cec_adapter *adap, struct cec_msg *msg);
+};
+
+/*
+ * The minimum message length you can receive (excepting poll messages) is 2.
+ * With a transfer rate of at most 36 bytes per second this makes 18 messages
+ * per second worst case.
+ *
+ * We queue at most 3 seconds worth of received messages. The CEC specification
+ * requires that messages are replied to within a second, so 3 seconds should
+ * give more than enough margin. Since most messages are actually more than 2
+ * bytes, this is in practice a lot more than 3 seconds.
+ */
+#define CEC_MAX_MSG_RX_QUEUE_SZ		(18 * 3)
+
+/*
+ * The transmit queue is limited to 1 second worth of messages (worst case).
+ * Messages can be transmitted by userspace and kernel space. But for both it
+ * makes no sense to have a lot of messages queued up. One second seems
+ * reasonable.
+ */
+#define CEC_MAX_MSG_TX_QUEUE_SZ		(18 * 1)
+
+struct cec_adapter {
+	struct module *owner;
+	char name[32];
+	struct cec_devnode devnode;
+	struct mutex lock;
+	struct rc_dev *rc;
+
+	struct list_head transmit_queue;
+	unsigned int transmit_queue_sz;
+	struct list_head wait_queue;
+	struct cec_data *transmitting;
+
+	struct task_struct *kthread_config;
+	struct completion config_completion;
+
+	struct task_struct *kthread;
+	wait_queue_head_t kthread_waitq;
+	wait_queue_head_t waitq;
+
+	const struct cec_adap_ops *ops;
+	void *priv;
+	u32 capabilities;
+	u8 available_log_addrs;
+
+	u16 phys_addr;
+	bool is_configuring;
+	bool is_configured;
+	u32 monitor_all_cnt;
+	u32 follower_cnt;
+	struct cec_fh *cec_follower;
+	struct cec_fh *cec_initiator;
+	bool passthrough;
+	struct cec_log_addrs log_addrs;
+
+	struct dentry *cec_dir;
+	struct dentry *status_file;
+
+	u16 phys_addrs[15];
+	u32 sequence;
+
+	char input_name[32];
+	char input_phys[32];
+	char input_drv[32];
+};
+
+static inline bool cec_has_log_addr(const struct cec_adapter *adap, u8 log_addr)
+{
+	return adap->log_addrs.log_addr_mask & (1 << log_addr);
+}
+
+static inline bool cec_is_sink(const struct cec_adapter *adap)
+{
+	return adap->phys_addr == 0;
+}
+
+#if IS_ENABLED(CONFIG_MEDIA_CEC)
+struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops,
+		void *priv, const char *name, u32 caps, u8 available_las,
+		struct device *parent);
+int cec_register_adapter(struct cec_adapter *adap);
+void cec_unregister_adapter(struct cec_adapter *adap);
+void cec_delete_adapter(struct cec_adapter *adap);
+
+int cec_s_log_addrs(struct cec_adapter *adap, struct cec_log_addrs *log_addrs,
+		    bool block);
+void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr,
+		     bool block);
+int cec_transmit_msg(struct cec_adapter *adap, struct cec_msg *msg,
+		     bool block);
+
+/* Called by the adapter */
+void cec_transmit_done(struct cec_adapter *adap, u8 status, u8 arb_lost_cnt,
+		       u8 nack_cnt, u8 low_drive_cnt, u8 error_cnt);
+void cec_received_msg(struct cec_adapter *adap, struct cec_msg *msg);
+
+#else
+
+static inline int cec_register_adapter(struct cec_adapter *adap)
+{
+	return 0;
+}
+
+static inline void cec_unregister_adapter(struct cec_adapter *adap)
+{
+}
+
+static inline void cec_delete_adapter(struct cec_adapter *adap)
+{
+}
+
+static inline void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr,
+				   bool block)
+{
+}
+
+#endif
+
+#endif /* _MEDIA_CEC_H */
diff --git a/include/media/davinci/vpbe_display.h b/include/media/davinci/vpbe_display.h
index e14a9370b67e..12783fd823f8 100644
--- a/include/media/davinci/vpbe_display.h
+++ b/include/media/davinci/vpbe_display.h
@@ -81,8 +81,6 @@ struct vpbe_layer {
 	 * Buffer queue used in video-buf
 	 */
 	struct vb2_queue buffer_queue;
-	/* allocator-specific contexts for each plane */
-	struct vb2_alloc_ctx *alloc_ctx;
 	/* Queue of filled frames */
 	struct list_head dma_queue;
 	/* Used in video-buf */
diff --git a/include/media/i2c/adv7511.h b/include/media/i2c/adv7511.h
index d83b91d80764..61c3d711cc69 100644
--- a/include/media/i2c/adv7511.h
+++ b/include/media/i2c/adv7511.h
@@ -32,11 +32,7 @@ struct adv7511_monitor_detect {
 struct adv7511_edid_detect {
 	int present;
 	int segment;
-};
-
-struct adv7511_cec_arg {
-	void *arg;
-	u32 f_flags;
+	uint16_t phys_addr;
 };
 
 struct adv7511_platform_data {
diff --git a/include/media/i2c/adv7604.h b/include/media/i2c/adv7604.h
index a913859bfd30..2e6857dee0cc 100644
--- a/include/media/i2c/adv7604.h
+++ b/include/media/i2c/adv7604.h
@@ -121,8 +121,6 @@ struct adv76xx_platform_data {
 
 	/* IO register 0x02 */
 	unsigned alt_gamma:1;
-	unsigned op_656_range:1;
-	unsigned alt_data_sat:1;
 
 	/* IO register 0x05 */
 	unsigned blank_data:1;
diff --git a/include/media/i2c/adv7842.h b/include/media/i2c/adv7842.h
index bc249709bf35..7f53ada9bdf1 100644
--- a/include/media/i2c/adv7842.h
+++ b/include/media/i2c/adv7842.h
@@ -165,8 +165,6 @@ struct adv7842_platform_data {
 
 	/* IO register 0x02 */
 	unsigned alt_gamma:1;
-	unsigned op_656_range:1;
-	unsigned alt_data_sat:1;
 
 	/* IO register 0x05 */
 	unsigned blank_data:1;
diff --git a/include/media/media-device.h b/include/media/media-device.h
index a9b33c47310d..f743ae2210ee 100644
--- a/include/media/media-device.h
+++ b/include/media/media-device.h
@@ -347,7 +347,7 @@ struct media_entity_notify {
 struct media_device {
 	/* dev->driver_data points to this struct. */
 	struct device *dev;
-	struct media_devnode devnode;
+	struct media_devnode *devnode;
 
 	char model[32];
 	char driver_name[32];
@@ -393,9 +393,6 @@ struct usb_device;
 #define MEDIA_DEV_NOTIFY_PRE_LINK_CH	0
 #define MEDIA_DEV_NOTIFY_POST_LINK_CH	1
 
-/* media_devnode to media_device */
-#define to_media_device(node) container_of(node, struct media_device, devnode)
-
 /**
  * media_entity_enum_init - Initialise an entity enumeration
  *
diff --git a/include/media/media-devnode.h b/include/media/media-devnode.h
index fe42f08e72bd..37d494805944 100644
--- a/include/media/media-devnode.h
+++ b/include/media/media-devnode.h
@@ -33,6 +33,8 @@
 #include <linux/device.h>
 #include <linux/cdev.h>
 
+struct media_device;
+
 /*
  * Flag to mark the media_devnode struct as registered. Drivers must not touch
  * this flag directly, it will be set and cleared by media_devnode_register and
@@ -67,8 +69,9 @@ struct media_file_operations {
 
 /**
  * struct media_devnode - Media device node
+ * @media_dev:	pointer to struct &media_device
  * @fops:	pointer to struct &media_file_operations with media device ops
- * @dev:	struct device pointer for the media controller device
+ * @dev:	pointer to struct &device containing the media controller device
  * @cdev:	struct cdev pointer character device
  * @parent:	parent device
  * @minor:	device node minor number
@@ -81,6 +84,8 @@ struct media_file_operations {
  * before registering the node.
  */
 struct media_devnode {
+	struct media_device *media_dev;
+
 	/* device ops */
 	const struct media_file_operations *fops;
 
@@ -94,7 +99,7 @@ struct media_devnode {
 	unsigned long flags;		/* Use bitops to access flags */
 
 	/* callbacks */
-	void (*release)(struct media_devnode *mdev);
+	void (*release)(struct media_devnode *devnode);
 };
 
 /* dev to media_devnode */
@@ -103,7 +108,8 @@ struct media_devnode {
 /**
  * media_devnode_register - register a media device node
  *
- * @mdev: media device node structure we want to register
+ * @mdev: struct media_device we want to register a device node
+ * @devnode: media device node structure we want to register
  * @owner: should be filled with %THIS_MODULE
  *
  * The registration code assigns minor numbers and registers the new device node
@@ -116,20 +122,33 @@ struct media_devnode {
  * the media_devnode structure is *not* called, so the caller is responsible for
  * freeing any data.
  */
-int __must_check media_devnode_register(struct media_devnode *mdev,
+int __must_check media_devnode_register(struct media_device *mdev,
+					struct media_devnode *devnode,
 					struct module *owner);
 
 /**
+ * media_devnode_unregister_prepare - clear the media device node register bit
+ * @devnode: the device node to prepare for unregister
+ *
+ * This clears the passed device register bit. Future open calls will be met
+ * with errors. Should be called before media_devnode_unregister() to avoid
+ * races with unregister and device file open calls.
+ *
+ * This function can safely be called if the device node has never been
+ * registered or has already been unregistered.
+ */
+void media_devnode_unregister_prepare(struct media_devnode *devnode);
+
+/**
  * media_devnode_unregister - unregister a media device node
- * @mdev: the device node to unregister
+ * @devnode: the device node to unregister
  *
  * This unregisters the passed device. Future open calls will be met with
  * errors.
  *
- * This function can safely be called if the device node has never been
- * registered or has already been unregistered.
+ * Should be called after media_devnode_unregister_prepare()
  */
-void media_devnode_unregister(struct media_devnode *mdev);
+void media_devnode_unregister(struct media_devnode *devnode);
 
 /**
  * media_devnode_data - returns a pointer to the &media_devnode
@@ -145,11 +164,16 @@ static inline struct media_devnode *media_devnode_data(struct file *filp)
  * media_devnode_is_registered - returns true if &media_devnode is registered;
  *	false otherwise.
  *
- * @mdev: pointer to struct &media_devnode.
+ * @devnode: pointer to struct &media_devnode.
+ *
+ * Note: If mdev is NULL, it also returns false.
  */
-static inline int media_devnode_is_registered(struct media_devnode *mdev)
+static inline int media_devnode_is_registered(struct media_devnode *devnode)
 {
-	return test_bit(MEDIA_FLAG_REGISTERED, &mdev->flags);
+	if (!devnode)
+		return false;
+
+	return test_bit(MEDIA_FLAG_REGISTERED, &devnode->flags);
 }
 
 #endif /* _MEDIA_DEVNODE_H */
diff --git a/include/media/rc-core.h b/include/media/rc-core.h
index b6586a91129c..324232cfc08d 100644
--- a/include/media/rc-core.h
+++ b/include/media/rc-core.h
@@ -119,6 +119,7 @@ enum rc_filter_type {
  * @s_carrier_report: enable carrier reports
  * @s_filter: set the scancode filter
  * @s_wakeup_filter: set the wakeup scancode filter
+ * @s_timeout: set hardware timeout in ns
  */
 struct rc_dev {
 	struct device			dev;
@@ -174,6 +175,8 @@ struct rc_dev {
 						    struct rc_scancode_filter *filter);
 	int				(*s_wakeup_filter)(struct rc_dev *dev,
 							   struct rc_scancode_filter *filter);
+	int				(*s_timeout)(struct rc_dev *dev,
+						     unsigned int timeout);
 };
 
 #define to_rc_dev(d) container_of(d, struct rc_dev, dev)
diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index 7844e9879497..a459129dd554 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -31,6 +31,7 @@ enum rc_type {
 	RC_TYPE_RC6_MCE		= 16,	/* MCE (Philips RC6-6A-32 subtype) protocol */
 	RC_TYPE_SHARP		= 17,	/* Sharp protocol */
 	RC_TYPE_XMP		= 18,	/* XMP protocol */
+	RC_TYPE_CEC		= 19,	/* CEC protocol */
 };
 
 #define RC_BIT_NONE		0ULL
@@ -53,6 +54,7 @@ enum rc_type {
 #define RC_BIT_RC6_MCE		(1ULL << RC_TYPE_RC6_MCE)
 #define RC_BIT_SHARP		(1ULL << RC_TYPE_SHARP)
 #define RC_BIT_XMP		(1ULL << RC_TYPE_XMP)
+#define RC_BIT_CEC		(1ULL << RC_TYPE_CEC)
 
 #define RC_BIT_ALL	(RC_BIT_UNKNOWN | RC_BIT_OTHER | \
 			 RC_BIT_RC5 | RC_BIT_RC5X | RC_BIT_RC5_SZ | \
@@ -61,7 +63,7 @@ enum rc_type {
 			 RC_BIT_NEC | RC_BIT_SANYO | RC_BIT_MCE_KBD | \
 			 RC_BIT_RC6_0 | RC_BIT_RC6_6A_20 | RC_BIT_RC6_6A_24 | \
 			 RC_BIT_RC6_6A_32 | RC_BIT_RC6_MCE | RC_BIT_SHARP | \
-			 RC_BIT_XMP)
+			 RC_BIT_XMP | RC_BIT_CEC)
 
 
 #define RC_SCANCODE_UNKNOWN(x)			(x)
@@ -123,6 +125,7 @@ void rc_map_init(void);
 #define RC_MAP_BEHOLD_COLUMBUS           "rc-behold-columbus"
 #define RC_MAP_BEHOLD                    "rc-behold"
 #define RC_MAP_BUDGET_CI_OLD             "rc-budget-ci-old"
+#define RC_MAP_CEC                       "rc-cec"
 #define RC_MAP_CINERGY_1400              "rc-cinergy-1400"
 #define RC_MAP_CINERGY                   "rc-cinergy"
 #define RC_MAP_DELOCK_61959              "rc-delock-61959"
@@ -133,6 +136,7 @@ void rc_map_init(void);
 #define RC_MAP_DM1105_NEC                "rc-dm1105-nec"
 #define RC_MAP_DNTV_LIVE_DVBT_PRO        "rc-dntv-live-dvbt-pro"
 #define RC_MAP_DNTV_LIVE_DVB_T           "rc-dntv-live-dvb-t"
+#define RC_MAP_DTT200U                   "rc-dtt200u"
 #define RC_MAP_DVBSKY                    "rc-dvbsky"
 #define RC_MAP_EMPTY                     "rc-empty"
 #define RC_MAP_EM_TERRATEC               "rc-em-terratec"
diff --git a/include/media/rcar-fcp.h b/include/media/rcar-fcp.h
new file mode 100644
index 000000000000..4c7fc77eaf29
--- /dev/null
+++ b/include/media/rcar-fcp.h
@@ -0,0 +1,37 @@
+/*
+ * rcar-fcp.h  --  R-Car Frame Compression Processor Driver
+ *
+ * Copyright (C) 2016 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __MEDIA_RCAR_FCP_H__
+#define __MEDIA_RCAR_FCP_H__
+
+struct device_node;
+struct rcar_fcp_device;
+
+#if IS_ENABLED(CONFIG_VIDEO_RENESAS_FCP)
+struct rcar_fcp_device *rcar_fcp_get(const struct device_node *np);
+void rcar_fcp_put(struct rcar_fcp_device *fcp);
+int rcar_fcp_enable(struct rcar_fcp_device *fcp);
+void rcar_fcp_disable(struct rcar_fcp_device *fcp);
+#else
+static inline struct rcar_fcp_device *rcar_fcp_get(const struct device_node *np)
+{
+	return ERR_PTR(-ENOENT);
+}
+static inline void rcar_fcp_put(struct rcar_fcp_device *fcp) { }
+static inline int rcar_fcp_enable(struct rcar_fcp_device *fcp)
+{
+	return -ENOSYS;
+}
+static inline void rcar_fcp_disable(struct rcar_fcp_device *fcp) { }
+#endif
+
+#endif /* __MEDIA_RCAR_FCP_H__ */
diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index 0bc9b35b8f3e..8b59336b2217 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -759,9 +759,9 @@ s32 v4l2_ctrl_g_ctrl(struct v4l2_ctrl *ctrl);
  * @ctrl:	The control.
  * @val:	The new value.
  *
- * This set the control's new value safely by going through the control
- * framework. This function will lock the control's handler, so it cannot be
- * used from within the &v4l2_ctrl_ops functions.
+ * This sets the control's new value safely by going through the control
+ * framework. This function assumes the control's handler is already locked,
+ * allowing it to be used from within the &v4l2_ctrl_ops functions.
  *
  * This function is for integer type controls only.
  */
@@ -771,7 +771,7 @@ int __v4l2_ctrl_s_ctrl(struct v4l2_ctrl *ctrl, s32 val);
  * @ctrl:	The control.
  * @val:	The new value.
  *
- * This set the control's new value safely by going through the control
+ * This sets the control's new value safely by going through the control
  * framework. This function will lock the control's handler, so it cannot be
  * used from within the &v4l2_ctrl_ops functions.
  *
@@ -807,9 +807,9 @@ s64 v4l2_ctrl_g_ctrl_int64(struct v4l2_ctrl *ctrl);
  * @ctrl:	The control.
  * @val:	The new value.
  *
- * This set the control's new value safely by going through the control
- * framework. This function will lock the control's handler, so it cannot be
- * used from within the &v4l2_ctrl_ops functions.
+ * This sets the control's new value safely by going through the control
+ * framework. This function assumes the control's handler is already locked,
+ * allowing it to be used from within the &v4l2_ctrl_ops functions.
  *
  * This function is for 64-bit integer type controls only.
  */
@@ -821,7 +821,7 @@ int __v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val);
  * @ctrl:	The control.
  * @val:	The new value.
  *
- * This set the control's new value safely by going through the control
+ * This sets the control's new value safely by going through the control
  * framework. This function will lock the control's handler, so it cannot be
  * used from within the &v4l2_ctrl_ops functions.
  *
@@ -843,9 +843,9 @@ static inline int v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val)
  * @ctrl:	The control.
  * @s:		The new string.
  *
- * This set the control's new string safely by going through the control
- * framework. This function will lock the control's handler, so it cannot be
- * used from within the &v4l2_ctrl_ops functions.
+ * This sets the control's new string safely by going through the control
+ * framework. This function assumes the control's handler is already locked,
+ * allowing it to be used from within the &v4l2_ctrl_ops functions.
  *
  * This function is for string type controls only.
  */
@@ -857,7 +857,7 @@ int __v4l2_ctrl_s_ctrl_string(struct v4l2_ctrl *ctrl, const char *s);
  * @ctrl:	The control.
  * @s:		The new string.
  *
- * This set the control's new string safely by going through the control
+ * This sets the control's new string safely by going through the control
  * framework. This function will lock the control's handler, so it cannot be
  * used from within the &v4l2_ctrl_ops functions.
  *
@@ -903,16 +903,6 @@ int v4l2_try_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *
 int v4l2_s_ext_ctrls(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl,
 						struct v4l2_ext_controls *c);
 
-/* Helpers for subdevices. If the associated ctrl_handler == NULL then they
-   will all return -EINVAL. */
-int v4l2_subdev_queryctrl(struct v4l2_subdev *sd, struct v4l2_queryctrl *qc);
-int v4l2_subdev_querymenu(struct v4l2_subdev *sd, struct v4l2_querymenu *qm);
-int v4l2_subdev_g_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs);
-int v4l2_subdev_try_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs);
-int v4l2_subdev_s_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs);
-int v4l2_subdev_g_ctrl(struct v4l2_subdev *sd, struct v4l2_control *ctrl);
-int v4l2_subdev_s_ctrl(struct v4l2_subdev *sd, struct v4l2_control *ctrl);
-
 /* Can be used as a subscribe_event function that just subscribes control
    events. */
 int v4l2_ctrl_subdev_subscribe_event(struct v4l2_subdev *sd, struct v4l2_fh *fh,
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 32fc7a4beb5e..c672efc4f87b 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -143,20 +143,6 @@ struct v4l2_subdev_io_pin_config {
  * @s_gpio: set GPIO pins. Very simple right now, might need to be extended with
  *	a direction argument if needed.
  *
- * @queryctrl: callback for VIDIOC_QUERYCTL ioctl handler code.
- *
- * @g_ctrl: callback for VIDIOC_G_CTRL ioctl handler code.
- *
- * @s_ctrl: callback for VIDIOC_S_CTRL ioctl handler code.
- *
- * @g_ext_ctrls: callback for VIDIOC_G_EXT_CTRLS ioctl handler code.
- *
- * @s_ext_ctrls: callback for VIDIOC_S_EXT_CTRLS ioctl handler code.
- *
- * @try_ext_ctrls: callback for VIDIOC_TRY_EXT_CTRLS ioctl handler code.
- *
- * @querymenu: callback for VIDIOC_QUERYMENU ioctl handler code.
- *
  * @ioctl: called at the end of ioctl() syscall handler at the V4L2 core.
  *	   used to provide support for private ioctls used on the driver.
  *
@@ -190,13 +176,6 @@ struct v4l2_subdev_core_ops {
 	int (*load_fw)(struct v4l2_subdev *sd);
 	int (*reset)(struct v4l2_subdev *sd, u32 val);
 	int (*s_gpio)(struct v4l2_subdev *sd, u32 val);
-	int (*queryctrl)(struct v4l2_subdev *sd, struct v4l2_queryctrl *qc);
-	int (*g_ctrl)(struct v4l2_subdev *sd, struct v4l2_control *ctrl);
-	int (*s_ctrl)(struct v4l2_subdev *sd, struct v4l2_control *ctrl);
-	int (*g_ext_ctrls)(struct v4l2_subdev *sd, struct v4l2_ext_controls *ctrls);
-	int (*s_ext_ctrls)(struct v4l2_subdev *sd, struct v4l2_ext_controls *ctrls);
-	int (*try_ext_ctrls)(struct v4l2_subdev *sd, struct v4l2_ext_controls *ctrls);
-	int (*querymenu)(struct v4l2_subdev *sd, struct v4l2_querymenu *qm);
 	long (*ioctl)(struct v4l2_subdev *sd, unsigned int cmd, void *arg);
 #ifdef CONFIG_COMPAT
 	long (*compat_ioctl32)(struct v4l2_subdev *sd, unsigned int cmd,
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 88e3ab496e8f..bea81c9e3758 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -27,7 +27,6 @@ enum vb2_memory {
 	VB2_MEMORY_DMABUF	= 4,
 };
 
-struct vb2_alloc_ctx;
 struct vb2_fileio_data;
 struct vb2_threadio_data;
 
@@ -57,7 +56,7 @@ struct vb2_threadio_data;
  * @put_userptr: inform the allocator that a USERPTR buffer will no longer
  *		 be used.
  * @attach_dmabuf: attach a shared struct dma_buf for a hardware operation;
- *		   used for DMABUF memory types; alloc_ctx is the alloc context
+ *		   used for DMABUF memory types; dev is the alloc device
  *		   dbuf is the shared dma_buf; returns NULL on failure;
  *		   allocator private per-buffer structure on success;
  *		   this needs to be used for further accesses to the buffer.
@@ -93,13 +92,13 @@ struct vb2_threadio_data;
  *				  unmap_dmabuf.
  */
 struct vb2_mem_ops {
-	void		*(*alloc)(void *alloc_ctx, unsigned long size,
-				  enum dma_data_direction dma_dir,
+	void		*(*alloc)(struct device *dev, const struct dma_attrs *attrs,
+				  unsigned long size, enum dma_data_direction dma_dir,
 				  gfp_t gfp_flags);
 	void		(*put)(void *buf_priv);
 	struct dma_buf *(*get_dmabuf)(void *buf_priv, unsigned long flags);
 
-	void		*(*get_userptr)(void *alloc_ctx, unsigned long vaddr,
+	void		*(*get_userptr)(struct device *dev, unsigned long vaddr,
 					unsigned long size,
 					enum dma_data_direction dma_dir);
 	void		(*put_userptr)(void *buf_priv);
@@ -107,7 +106,7 @@ struct vb2_mem_ops {
 	void		(*prepare)(void *buf_priv);
 	void		(*finish)(void *buf_priv);
 
-	void		*(*attach_dmabuf)(void *alloc_ctx, struct dma_buf *dbuf,
+	void		*(*attach_dmabuf)(struct device *dev, struct dma_buf *dbuf,
 					  unsigned long size,
 					  enum dma_data_direction dma_dir);
 	void		(*detach_dmabuf)(void *buf_priv);
@@ -282,7 +281,7 @@ struct vb2_buffer {
  *			in *num_buffers, the required number of planes per
  *			buffer in *num_planes, the size of each plane should be
  *			set in the sizes[] array and optional per-plane
- *			allocator specific context in the alloc_ctxs[] array.
+ *			allocator specific device in the alloc_devs[] array.
  *			When called from VIDIOC_REQBUFS, *num_planes == 0, the
  *			driver has to use the currently configured format to
  *			determine the plane sizes and *num_buffers is the total
@@ -356,7 +355,7 @@ struct vb2_buffer {
 struct vb2_ops {
 	int (*queue_setup)(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
-			   unsigned int sizes[], void *alloc_ctxs[]);
+			   unsigned int sizes[], struct device *alloc_devs[]);
 
 	void (*wait_prepare)(struct vb2_queue *q);
 	void (*wait_finish)(struct vb2_queue *q);
@@ -401,6 +400,9 @@ struct vb2_buf_ops {
  *		caller. For example, for V4L2, it should match
  *		the V4L2_BUF_TYPE_* in include/uapi/linux/videodev2.h
  * @io_modes:	supported io methods (see vb2_io_modes enum)
+ * @dev:	device to use for the default allocation context if the driver
+ *		doesn't fill in the @alloc_devs array.
+ * @dma_attrs:	DMA attributes to use for the DMA. May be NULL.
  * @fileio_read_once:		report EOF after reading the first buffer
  * @fileio_write_immediately:	queue buffer after each write() call
  * @allow_zero_bytesused:	allow bytesused == 0 to be passed to the driver
@@ -447,7 +449,7 @@ struct vb2_buf_ops {
  * @done_list:	list of buffers ready to be dequeued to userspace
  * @done_lock:	lock to protect done_list list
  * @done_wq:	waitqueue for processes waiting for buffers ready to be dequeued
- * @alloc_ctx:	memory type/allocator-specific contexts for each plane
+ * @alloc_devs:	memory type/allocator-specific per-plane device
  * @streaming:	current streaming state
  * @start_streaming_called: start_streaming() was called successfully and we
  *		started streaming.
@@ -467,6 +469,8 @@ struct vb2_buf_ops {
 struct vb2_queue {
 	unsigned int			type;
 	unsigned int			io_modes;
+	struct device			*dev;
+	const struct dma_attrs		*dma_attrs;
 	unsigned			fileio_read_once:1;
 	unsigned			fileio_write_immediately:1;
 	unsigned			allow_zero_bytesused:1;
@@ -499,7 +503,7 @@ struct vb2_queue {
 	spinlock_t			done_lock;
 	wait_queue_head_t		done_wq;
 
-	void				*alloc_ctx[VB2_MAX_PLANES];
+	struct device			*alloc_devs[VB2_MAX_PLANES];
 
 	unsigned int			streaming:1;
 	unsigned int			start_streaming_called:1;
diff --git a/include/media/videobuf2-dma-contig.h b/include/media/videobuf2-dma-contig.h
index 2087c9a68be3..df2aabee3401 100644
--- a/include/media/videobuf2-dma-contig.h
+++ b/include/media/videobuf2-dma-contig.h
@@ -26,15 +26,8 @@ vb2_dma_contig_plane_dma_addr(struct vb2_buffer *vb, unsigned int plane_no)
 	return *addr;
 }
 
-void *vb2_dma_contig_init_ctx_attrs(struct device *dev,
-				    struct dma_attrs *attrs);
-
-static inline void *vb2_dma_contig_init_ctx(struct device *dev)
-{
-	return vb2_dma_contig_init_ctx_attrs(dev, NULL);
-}
-
-void vb2_dma_contig_cleanup_ctx(void *alloc_ctx);
+int vb2_dma_contig_set_max_seg_size(struct device *dev, unsigned int size);
+void vb2_dma_contig_clear_max_seg_size(struct device *dev);
 
 extern const struct vb2_mem_ops vb2_dma_contig_memops;
 
diff --git a/include/media/videobuf2-dma-sg.h b/include/media/videobuf2-dma-sg.h
index 8d1083f83c3d..52afa0e2bb17 100644
--- a/include/media/videobuf2-dma-sg.h
+++ b/include/media/videobuf2-dma-sg.h
@@ -21,9 +21,6 @@ static inline struct sg_table *vb2_dma_sg_plane_desc(
 	return (struct sg_table *)vb2_plane_cookie(vb, plane_no);
 }
 
-void *vb2_dma_sg_init_ctx(struct device *dev);
-void vb2_dma_sg_cleanup_ctx(void *alloc_ctx);
-
 extern const struct vb2_mem_ops vb2_dma_sg_memops;
 
 #endif
diff --git a/include/media/vsp1.h b/include/media/vsp1.h
index 3e654a0455bd..9322d9775fb7 100644
--- a/include/media/vsp1.h
+++ b/include/media/vsp1.h
@@ -14,31 +14,28 @@
 #define __MEDIA_VSP1_H__
 
 #include <linux/types.h>
+#include <linux/videodev2.h>
 
 struct device;
-struct v4l2_rect;
 
 int vsp1_du_init(struct device *dev);
 
 int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 		      unsigned int height);
 
+struct vsp1_du_atomic_config {
+	u32 pixelformat;
+	unsigned int pitch;
+	dma_addr_t mem[2];
+	struct v4l2_rect src;
+	struct v4l2_rect dst;
+	unsigned int alpha;
+	unsigned int zpos;
+};
+
 void vsp1_du_atomic_begin(struct device *dev);
-int vsp1_du_atomic_update_ext(struct device *dev, unsigned int rpf,
-			      u32 pixelformat, unsigned int pitch,
-			      dma_addr_t mem[2], const struct v4l2_rect *src,
-			      const struct v4l2_rect *dst, unsigned int alpha,
-			      unsigned int zpos);
+int vsp1_du_atomic_update(struct device *dev, unsigned int rpf,
+			  const struct vsp1_du_atomic_config *cfg);
 void vsp1_du_atomic_flush(struct device *dev);
 
-static inline int vsp1_du_atomic_update(struct device *dev,
-					unsigned int rpf_index, u32 pixelformat,
-					unsigned int pitch, dma_addr_t mem[2],
-					const struct v4l2_rect *src,
-					const struct v4l2_rect *dst)
-{
-	return vsp1_du_atomic_update_ext(dev, rpf_index, pixelformat, pitch,
-					 mem, src, dst, 255, 0);
-}
-
 #endif /* __MEDIA_VSP1_H__ */
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index 981acf74b14f..65673d8b81ac 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -27,7 +27,8 @@ DECLARE_EVENT_CLASS(bcache_request,
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->orig_sector	= bio->bi_iter.bi_sector - 16;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u (from %d,%d @ %llu)",
@@ -101,7 +102,8 @@ DECLARE_EVENT_CLASS(bcache_bio,
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d  %s %llu + %u",
@@ -136,7 +138,8 @@ TRACE_EVENT(bcache_read,
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 		__entry->cache_hit = hit;
 		__entry->bypass = bypass;
 	),
@@ -167,7 +170,8 @@ TRACE_EVENT(bcache_write,
 		__entry->inode		= inode;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 		__entry->writeback = writeback;
 		__entry->bypass = bypass;
 	),
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index e8a5eca1dbe5..5a2a7592068f 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -84,7 +84,8 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 					0 : blk_rq_sectors(rq);
 		__entry->errors    = rq->errors;
 
-		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
+		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags,
+			      blk_rq_bytes(rq));
 		blk_dump_cmd(__get_str(cmd), rq);
 	),
 
@@ -162,7 +163,7 @@ TRACE_EVENT(block_rq_complete,
 		__entry->nr_sector = nr_bytes >> 9;
 		__entry->errors    = rq->errors;
 
-		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, nr_bytes);
 		blk_dump_cmd(__get_str(cmd), rq);
 	),
 
@@ -198,7 +199,8 @@ DECLARE_EVENT_CLASS(block_rq,
 		__entry->bytes     = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
 					blk_rq_bytes(rq) : 0;
 
-		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
+		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags,
+			      blk_rq_bytes(rq));
 		blk_dump_cmd(__get_str(cmd), rq);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
@@ -272,7 +274,8 @@ TRACE_EVENT(block_bio_bounce,
 					  bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -310,7 +313,8 @@ TRACE_EVENT(block_bio_complete,
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		__entry->error		= error;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u [%d]",
@@ -337,7 +341,8 @@ DECLARE_EVENT_CLASS(block_bio_merge,
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -404,7 +409,8 @@ TRACE_EVENT(block_bio_queue,
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -432,7 +438,7 @@ DECLARE_EVENT_CLASS(block_get_rq,
 		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio ? bio->bi_iter.bi_sector : 0;
 		__entry->nr_sector	= bio ? bio_sectors(bio) : 0;
-		blk_fill_rwbs(__entry->rwbs,
+		blk_fill_rwbs(__entry->rwbs, bio ? bio_op(bio) : 0,
 			      bio ? bio->bi_rw : 0, __entry->nr_sector);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
         ),
@@ -567,7 +573,8 @@ TRACE_EVENT(block_split,
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->new_sector	= new_sector;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -610,7 +617,8 @@ TRACE_EVENT(block_bio_remap,
 		__entry->nr_sector	= bio_sectors(bio);
 		__entry->old_dev	= dev;
 		__entry->old_sector	= from;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw,
+			      bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
@@ -656,7 +664,8 @@ TRACE_EVENT(block_rq_remap,
 		__entry->old_dev	= dev;
 		__entry->old_sector	= from;
 		__entry->nr_bios	= blk_rq_count_bios(rq);
-		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
+		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags,
+			      blk_rq_bytes(rq));
 	),
 
 	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u",
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 3a09bb4dc3b2..ff95fd02116f 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -31,10 +31,9 @@ TRACE_DEFINE_ENUM(BG_GC);
 TRACE_DEFINE_ENUM(LFS);
 TRACE_DEFINE_ENUM(SSR);
 TRACE_DEFINE_ENUM(__REQ_RAHEAD);
-TRACE_DEFINE_ENUM(__REQ_WRITE);
 TRACE_DEFINE_ENUM(__REQ_SYNC);
 TRACE_DEFINE_ENUM(__REQ_NOIDLE);
-TRACE_DEFINE_ENUM(__REQ_FLUSH);
+TRACE_DEFINE_ENUM(__REQ_PREFLUSH);
 TRACE_DEFINE_ENUM(__REQ_FUA);
 TRACE_DEFINE_ENUM(__REQ_PRIO);
 TRACE_DEFINE_ENUM(__REQ_META);
@@ -56,17 +55,21 @@ TRACE_DEFINE_ENUM(CP_DISCARD);
 		{ IPU,		"IN-PLACE" },				\
 		{ OPU,		"OUT-OF-PLACE" })
 
-#define F2FS_BIO_MASK(t)	(t & (READA | WRITE_FLUSH_FUA))
+#define F2FS_BIO_FLAG_MASK(t)	(t & (REQ_RAHEAD | WRITE_FLUSH_FUA))
 #define F2FS_BIO_EXTRA_MASK(t)	(t & (REQ_META | REQ_PRIO))
 
-#define show_bio_type(type)	show_bio_base(type), show_bio_extra(type)
+#define show_bio_type(op, op_flags) show_bio_op(op),			\
+			show_bio_op_flags(op_flags), show_bio_extra(op_flags)
 
-#define show_bio_base(type)						\
-	__print_symbolic(F2FS_BIO_MASK(type),				\
+#define show_bio_op(op)							\
+	__print_symbolic(op,						\
 		{ READ, 		"READ" },			\
-		{ READA, 		"READAHEAD" },			\
+		{ WRITE,		"WRITE" })
+
+#define show_bio_op_flags(flags)					\
+	__print_symbolic(F2FS_BIO_FLAG_MASK(flags),			\
+		{ REQ_RAHEAD, 		"READAHEAD" },			\
 		{ READ_SYNC, 		"READ_SYNC" },			\
-		{ WRITE, 		"WRITE" },			\
 		{ WRITE_SYNC, 		"WRITE_SYNC" },			\
 		{ WRITE_FLUSH,		"WRITE_FLUSH" },		\
 		{ WRITE_FUA, 		"WRITE_FUA" },			\
@@ -734,7 +737,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__field(pgoff_t, index)
 		__field(block_t, old_blkaddr)
 		__field(block_t, new_blkaddr)
-		__field(int, rw)
+		__field(int, op)
+		__field(int, op_flags)
 		__field(int, type)
 	),
 
@@ -744,17 +748,18 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__entry->index		= page->index;
 		__entry->old_blkaddr	= fio->old_blkaddr;
 		__entry->new_blkaddr	= fio->new_blkaddr;
-		__entry->rw		= fio->rw;
+		__entry->op		= fio->op;
+		__entry->op_flags	= fio->op_flags;
 		__entry->type		= fio->type;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
-		"oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%s, type = %s",
+		"oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%si%s, type = %s",
 		show_dev_ino(__entry),
 		(unsigned long)__entry->index,
 		(unsigned long long)__entry->old_blkaddr,
 		(unsigned long long)__entry->new_blkaddr,
-		show_bio_type(__entry->rw),
+		show_bio_type(__entry->op, __entry->op_flags),
 		show_block_type(__entry->type))
 );
 
@@ -785,7 +790,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
-		__field(int,	rw)
+		__field(int,	op)
+		__field(int,	op_flags)
 		__field(int,	type)
 		__field(sector_t,	sector)
 		__field(unsigned int,	size)
@@ -793,15 +799,16 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->rw		= fio->rw;
+		__entry->op		= fio->op;
+		__entry->op_flags	= fio->op_flags;
 		__entry->type		= fio->type;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->size		= bio->bi_iter.bi_size;
 	),
 
-	TP_printk("dev = (%d,%d), %s%s, %s, sector = %lld, size = %u",
+	TP_printk("dev = (%d,%d), %s%s%s, %s, sector = %lld, size = %u",
 		show_dev(__entry),
-		show_bio_type(__entry->rw),
+		show_bio_type(__entry->op, __entry->op_flags),
 		show_block_type(__entry->type),
 		(unsigned long long)__entry->sector,
 		__entry->size)
diff --git a/include/trace/events/libata.h b/include/trace/events/libata.h
index 75fff8696bae..2fbbf990e4b3 100644
--- a/include/trace/events/libata.h
+++ b/include/trace/events/libata.h
@@ -126,6 +126,7 @@
 		ata_protocol_name(ATA_PROT_PIO),	\
 		ata_protocol_name(ATA_PROT_DMA),	\
 		ata_protocol_name(ATA_PROT_NCQ),	\
+		ata_protocol_name(ATA_PROT_NCQ_NODATA),	\
 		ata_protocol_name(ATAPI_PROT_NODATA),	\
 		ata_protocol_name(ATAPI_PROT_PIO),	\
 		ata_protocol_name(ATAPI_PROT_DMA))
diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h
index 2e67bb64c1da..79b5ded2001a 100644
--- a/include/uapi/linux/cryptouser.h
+++ b/include/uapi/linux/cryptouser.h
@@ -45,6 +45,7 @@ enum crypto_attr_type_t {
 	CRYPTOCFGA_REPORT_RNG,		/* struct crypto_report_rng */
 	CRYPTOCFGA_REPORT_CIPHER,	/* struct crypto_report_cipher */
 	CRYPTOCFGA_REPORT_AKCIPHER,	/* struct crypto_report_akcipher */
+	CRYPTOCFGA_REPORT_KPP,		/* struct crypto_report_kpp */
 	__CRYPTOCFGA_MAX
 
 #define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1)
@@ -107,5 +108,9 @@ struct crypto_report_akcipher {
 	char type[CRYPTO_MAX_NAME];
 };
 
+struct crypto_report_kpp {
+	char type[CRYPTO_MAX_NAME];
+};
+
 #define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \
 			       sizeof(struct crypto_report_blkcipher))
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 30afd0a23c4b..4bf9f1eabffc 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	34
+#define DM_VERSION_MINOR	35
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2015-10-28)"
+#define DM_VERSION_EXTRA	"-ioctl (2016-06-23)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h
index d0a3cac72250..333d3544c964 100644
--- a/include/uapi/linux/gpio.h
+++ b/include/uapi/linux/gpio.h
@@ -1,7 +1,7 @@
 /*
  * <linux/gpio.h> - userspace ABI for the GPIO character devices
  *
- * Copyright (C) 2015 Linus Walleij
+ * Copyright (C) 2016 Linus Walleij
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published by
@@ -26,8 +26,8 @@ struct gpiochip_info {
 	__u32 lines;
 };
 
-/* Line is in use by the kernel */
-#define GPIOLINE_FLAG_KERNEL		(1UL << 0)
+/* Informational flags */
+#define GPIOLINE_FLAG_KERNEL		(1UL << 0) /* Line used by the kernel */
 #define GPIOLINE_FLAG_IS_OUT		(1UL << 1)
 #define GPIOLINE_FLAG_ACTIVE_LOW	(1UL << 2)
 #define GPIOLINE_FLAG_OPEN_DRAIN	(1UL << 3)
@@ -52,7 +52,106 @@ struct gpioline_info {
 	char consumer[32];
 };
 
+/* Maximum number of requested handles */
+#define GPIOHANDLES_MAX 64
+
+/* Linerequest flags */
+#define GPIOHANDLE_REQUEST_INPUT	(1UL << 0)
+#define GPIOHANDLE_REQUEST_OUTPUT	(1UL << 1)
+#define GPIOHANDLE_REQUEST_ACTIVE_LOW	(1UL << 2)
+#define GPIOHANDLE_REQUEST_OPEN_DRAIN	(1UL << 3)
+#define GPIOHANDLE_REQUEST_OPEN_SOURCE	(1UL << 4)
+
+/**
+ * struct gpiohandle_request - Information about a GPIO handle request
+ * @lineoffsets: an array desired lines, specified by offset index for the
+ * associated GPIO device
+ * @flags: desired flags for the desired GPIO lines, such as
+ * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed
+ * together. Note that even if multiple lines are requested, the same flags
+ * must be applicable to all of them, if you want lines with individual
+ * flags set, request them one by one. It is possible to select
+ * a batch of input or output lines, but they must all have the same
+ * characteristics, i.e. all inputs or all outputs, all active low etc
+ * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested
+ * line, this specifies the default output value, should be 0 (low) or
+ * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
+ * @consumer_label: a desired consumer label for the selected GPIO line(s)
+ * such as "my-bitbanged-relay"
+ * @lines: number of lines requested in this request, i.e. the number of
+ * valid fields in the above arrays, set to 1 to request a single line
+ * @fd: if successful this field will contain a valid anonymous file handle
+ * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
+ * means error
+ */
+struct gpiohandle_request {
+	__u32 lineoffsets[GPIOHANDLES_MAX];
+	__u32 flags;
+	__u8 default_values[GPIOHANDLES_MAX];
+	char consumer_label[32];
+	__u32 lines;
+	int fd;
+};
+
+/**
+ * struct gpiohandle_data - Information of values on a GPIO handle
+ * @values: when getting the state of lines this contains the current
+ * state of a line, when setting the state of lines these should contain
+ * the desired target state
+ */
+struct gpiohandle_data {
+	__u8 values[GPIOHANDLES_MAX];
+};
+
+#define GPIOHANDLE_GET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x08, struct gpiohandle_data)
+#define GPIOHANDLE_SET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x09, struct gpiohandle_data)
+
+/* Eventrequest flags */
+#define GPIOEVENT_REQUEST_RISING_EDGE	(1UL << 0)
+#define GPIOEVENT_REQUEST_FALLING_EDGE	(1UL << 1)
+#define GPIOEVENT_REQUEST_BOTH_EDGES	((1UL << 0) | (1UL << 1))
+
+/**
+ * struct gpioevent_request - Information about a GPIO event request
+ * @lineoffset: the desired line to subscribe to events from, specified by
+ * offset index for the associated GPIO device
+ * @handleflags: desired handle flags for the desired GPIO line, such as
+ * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN
+ * @eventflags: desired flags for the desired GPIO event line, such as
+ * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE
+ * @consumer_label: a desired consumer label for the selected GPIO line(s)
+ * such as "my-listener"
+ * @fd: if successful this field will contain a valid anonymous file handle
+ * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
+ * means error
+ */
+struct gpioevent_request {
+	__u32 lineoffset;
+	__u32 handleflags;
+	__u32 eventflags;
+	char consumer_label[32];
+	int fd;
+};
+
+/**
+ * GPIO event types
+ */
+#define GPIOEVENT_EVENT_RISING_EDGE 0x01
+#define GPIOEVENT_EVENT_FALLING_EDGE 0x02
+
+/**
+ * struct gpioevent_data - The actual event being pushed to userspace
+ * @timestamp: best estimate of time of event occurrence, in nanoseconds
+ * @id: event identifier
+ */
+struct gpioevent_data {
+	__u64 timestamp;
+	__u32 id;
+};
+
 #define GPIO_GET_CHIPINFO_IOCTL _IOR(0xB4, 0x01, struct gpiochip_info)
 #define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info)
+#define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request)
+#define GPIO_GET_LINEEVENT_IOCTL _IOWR(0xB4, 0x04, struct gpioevent_request)
 
 #endif /* _UAPI_GPIO_H_ */
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index df59edee25d1..7acf0f634f70 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -95,6 +95,16 @@ struct media_device_info {
 #define MEDIA_ENT_F_AUDIO_MIXER		(MEDIA_ENT_F_BASE + 0x03003)
 
 /*
+ * Processing entities
+ */
+#define MEDIA_ENT_F_PROC_VIDEO_COMPOSER		(MEDIA_ENT_F_BASE + 0x4001)
+#define MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER	(MEDIA_ENT_F_BASE + 0x4002)
+#define MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV	(MEDIA_ENT_F_BASE + 0x4003)
+#define MEDIA_ENT_F_PROC_VIDEO_LUT		(MEDIA_ENT_F_BASE + 0x4004)
+#define MEDIA_ENT_F_PROC_VIDEO_SCALER		(MEDIA_ENT_F_BASE + 0x4005)
+#define MEDIA_ENT_F_PROC_VIDEO_STATISTICS	(MEDIA_ENT_F_BASE + 0x4006)
+
+/*
  * Connectors
  */
 /* It is a responsibility of the entity drivers to add connectors and links */
diff --git a/include/uapi/linux/serio.h b/include/uapi/linux/serio.h
index c2ea1698257f..f2447a83ac8d 100644
--- a/include/uapi/linux/serio.h
+++ b/include/uapi/linux/serio.h
@@ -78,5 +78,6 @@
 #define SERIO_TSC40	0x3d
 #define SERIO_WACOM_IV	0x3e
 #define SERIO_EGALAX	0x3f
+#define SERIO_PULSE8_CEC	0x40
 
 #endif /* _UAPI_SERIO_H */
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 8f951917be74..724f43e69d03 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -504,22 +504,16 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_UV8     v4l2_fourcc('U', 'V', '8', ' ') /*  8  UV 4:4 */
 
 /* Luminance+Chrominance formats */
-#define V4L2_PIX_FMT_YVU410  v4l2_fourcc('Y', 'V', 'U', '9') /*  9  YVU 4:1:0     */
-#define V4L2_PIX_FMT_YVU420  v4l2_fourcc('Y', 'V', '1', '2') /* 12  YVU 4:2:0     */
 #define V4L2_PIX_FMT_YUYV    v4l2_fourcc('Y', 'U', 'Y', 'V') /* 16  YUV 4:2:2     */
 #define V4L2_PIX_FMT_YYUV    v4l2_fourcc('Y', 'Y', 'U', 'V') /* 16  YUV 4:2:2     */
 #define V4L2_PIX_FMT_YVYU    v4l2_fourcc('Y', 'V', 'Y', 'U') /* 16 YVU 4:2:2 */
 #define V4L2_PIX_FMT_UYVY    v4l2_fourcc('U', 'Y', 'V', 'Y') /* 16  YUV 4:2:2     */
 #define V4L2_PIX_FMT_VYUY    v4l2_fourcc('V', 'Y', 'U', 'Y') /* 16  YUV 4:2:2     */
-#define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4', '2', '2', 'P') /* 16  YVU422 planar */
-#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4', '1', '1', 'P') /* 16  YVU411 planar */
 #define V4L2_PIX_FMT_Y41P    v4l2_fourcc('Y', '4', '1', 'P') /* 12  YUV 4:1:1     */
 #define V4L2_PIX_FMT_YUV444  v4l2_fourcc('Y', '4', '4', '4') /* 16  xxxxyyyy uuuuvvvv */
 #define V4L2_PIX_FMT_YUV555  v4l2_fourcc('Y', 'U', 'V', 'O') /* 16  YUV-5-5-5     */
 #define V4L2_PIX_FMT_YUV565  v4l2_fourcc('Y', 'U', 'V', 'P') /* 16  YUV-5-6-5     */
 #define V4L2_PIX_FMT_YUV32   v4l2_fourcc('Y', 'U', 'V', '4') /* 32  YUV-8-8-8-8   */
-#define V4L2_PIX_FMT_YUV410  v4l2_fourcc('Y', 'U', 'V', '9') /*  9  YUV 4:1:0     */
-#define V4L2_PIX_FMT_YUV420  v4l2_fourcc('Y', 'U', '1', '2') /* 12  YUV 4:2:0     */
 #define V4L2_PIX_FMT_HI240   v4l2_fourcc('H', 'I', '2', '4') /*  8  8-bit color   */
 #define V4L2_PIX_FMT_HM12    v4l2_fourcc('H', 'M', '1', '2') /*  8  YUV 4:2:0 16x16 macroblocks */
 #define V4L2_PIX_FMT_M420    v4l2_fourcc('M', '4', '2', '0') /* 12  YUV 4:2:0 2 lines y, 1 line uv interleaved */
@@ -540,6 +534,14 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_NV12MT  v4l2_fourcc('T', 'M', '1', '2') /* 12  Y/CbCr 4:2:0 64x32 macroblocks */
 #define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12  Y/CbCr 4:2:0 16x16 macroblocks */
 
+/* three planes - Y Cb, Cr */
+#define V4L2_PIX_FMT_YUV410  v4l2_fourcc('Y', 'U', 'V', '9') /*  9  YUV 4:1:0     */
+#define V4L2_PIX_FMT_YVU410  v4l2_fourcc('Y', 'V', 'U', '9') /*  9  YVU 4:1:0     */
+#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4', '1', '1', 'P') /* 12  YVU411 planar */
+#define V4L2_PIX_FMT_YUV420  v4l2_fourcc('Y', 'U', '1', '2') /* 12  YUV 4:2:0     */
+#define V4L2_PIX_FMT_YVU420  v4l2_fourcc('Y', 'V', '1', '2') /* 12  YVU 4:2:0     */
+#define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4', '2', '2', 'P') /* 16  YVU422 planar */
+
 /* three non contiguous planes - Y, Cb, Cr */
 #define V4L2_PIX_FMT_YUV420M v4l2_fourcc('Y', 'M', '1', '2') /* 12  YUV420 planar */
 #define V4L2_PIX_FMT_YVU420M v4l2_fourcc('Y', 'M', '2', '1') /* 12  YVU420 planar */
diff --git a/include/uapi/linux/vsp1.h b/include/uapi/linux/vsp1.h
deleted file mode 100644
index 9a823696d816..000000000000
--- a/include/uapi/linux/vsp1.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * vsp1.h
- *
- * Renesas R-Car VSP1 - User-space API
- *
- * Copyright (C) 2013 Renesas Corporation
- *
- * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __VSP1_USER_H__
-#define __VSP1_USER_H__
-
-#include <linux/types.h>
-#include <linux/videodev2.h>
-
-/*
- * Private IOCTLs
- *
- * VIDIOC_VSP1_LUT_CONFIG - Configure the lookup table
- */
-
-#define VIDIOC_VSP1_LUT_CONFIG \
-	_IOWR('V', BASE_VIDIOC_PRIVATE + 1, struct vsp1_lut_config)
-
-struct vsp1_lut_config {
-	__u32 lut[256];
-};
-
-#endif	/* __VSP1_USER_H__ */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index fa943843a32f..33a2f63d4a10 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -61,7 +61,6 @@
 #include <linux/cpuset.h>
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
-#include <linux/proc_ns.h>
 #include <net/sock.h>
 
 /*
@@ -5140,6 +5139,8 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 	lockdep_assert_held(&cgroup_mutex);
 
 	css = ss->css_alloc(parent_css);
+	if (!css)
+		css = ERR_PTR(-ENOMEM);
 	if (IS_ERR(css))
 		return css;
 
diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c
index 303097b37429..2bd673783f1a 100644
--- a/kernel/cgroup_pids.c
+++ b/kernel/cgroup_pids.c
@@ -49,6 +49,12 @@ struct pids_cgroup {
 	 */
 	atomic64_t			counter;
 	int64_t				limit;
+
+	/* Handle for "pids.events" */
+	struct cgroup_file		events_file;
+
+	/* Number of times fork failed because limit was hit. */
+	atomic64_t			events_limit;
 };
 
 static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css)
@@ -72,6 +78,7 @@ pids_css_alloc(struct cgroup_subsys_state *parent)
 
 	pids->limit = PIDS_MAX;
 	atomic64_set(&pids->counter, 0);
+	atomic64_set(&pids->events_limit, 0);
 	return &pids->css;
 }
 
@@ -213,10 +220,21 @@ static int pids_can_fork(struct task_struct *task)
 {
 	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids;
+	int err;
 
 	css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
-	return pids_try_charge(pids, 1);
+	err = pids_try_charge(pids, 1);
+	if (err) {
+		/* Only log the first time events_limit is incremented. */
+		if (atomic64_inc_return(&pids->events_limit) == 1) {
+			pr_info("cgroup: fork rejected by pids controller in ");
+			pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id));
+			pr_cont("\n");
+		}
+		cgroup_file_notify(&pids->events_file);
+	}
+	return err;
 }
 
 static void pids_cancel_fork(struct task_struct *task)
@@ -288,6 +306,14 @@ static s64 pids_current_read(struct cgroup_subsys_state *css,
 	return atomic64_read(&pids->counter);
 }
 
+static int pids_events_show(struct seq_file *sf, void *v)
+{
+	struct pids_cgroup *pids = css_pids(seq_css(sf));
+
+	seq_printf(sf, "max %lld\n", (s64)atomic64_read(&pids->events_limit));
+	return 0;
+}
+
 static struct cftype pids_files[] = {
 	{
 		.name = "max",
@@ -300,6 +326,12 @@ static struct cftype pids_files[] = {
 		.read_s64 = pids_current_read,
 		.flags = CFTYPE_NOT_ON_ROOT,
 	},
+	{
+		.name = "events",
+		.seq_show = pids_events_show,
+		.file_offset = offsetof(struct pids_cgroup, events_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
 	{ }	/* terminate */
 };
 
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index cb880a14cc39..eb4f717705ba 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -1,6 +1,8 @@
 
 ccflags-$(CONFIG_PM_DEBUG)	:= -DDEBUG
 
+KASAN_SANITIZE_snapshot.o	:= n
+
 obj-y				+= qos.o
 obj-$(CONFIG_PM)		+= main.o
 obj-$(CONFIG_VT_CONSOLE_SLEEP)	+= console.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index aba9c545a0e3..0e781798b0b3 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -126,17 +126,17 @@ out:
 	return ret;
 }
 
-int pm_prepare_console(void)
+void pm_prepare_console(void)
 {
 	if (!pm_vt_switch())
-		return 0;
+		return;
 
 	orig_fgconsole = vt_move_to_console(SUSPEND_CONSOLE, 1);
 	if (orig_fgconsole < 0)
-		return 1;
+		return;
 
 	orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE);
-	return 0;
+	return;
 }
 
 void pm_restore_console(void)
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9021387c6ff4..a881c6a7ba74 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -52,6 +52,7 @@ enum {
 #ifdef CONFIG_SUSPEND
 	HIBERNATION_SUSPEND,
 #endif
+	HIBERNATION_TEST_RESUME,
 	/* keep last */
 	__HIBERNATION_AFTER_LAST
 };
@@ -409,6 +410,11 @@ int hibernation_snapshot(int platform_mode)
 	goto Close;
 }
 
+int __weak hibernate_resume_nonboot_cpu_disable(void)
+{
+	return disable_nonboot_cpus();
+}
+
 /**
  * resume_target_kernel - Restore system state from a hibernation image.
  * @platform_mode: Whether or not to use the platform driver.
@@ -433,7 +439,7 @@ static int resume_target_kernel(bool platform_mode)
 	if (error)
 		goto Cleanup;
 
-	error = disable_nonboot_cpus();
+	error = hibernate_resume_nonboot_cpu_disable();
 	if (error)
 		goto Enable_cpus;
 
@@ -642,12 +648,39 @@ static void power_down(void)
 		cpu_relax();
 }
 
+static int load_image_and_restore(void)
+{
+	int error;
+	unsigned int flags;
+
+	pr_debug("PM: Loading hibernation image.\n");
+
+	lock_device_hotplug();
+	error = create_basic_memory_bitmaps();
+	if (error)
+		goto Unlock;
+
+	error = swsusp_read(&flags);
+	swsusp_close(FMODE_READ);
+	if (!error)
+		hibernation_restore(flags & SF_PLATFORM_MODE);
+
+	printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n");
+	swsusp_free();
+	free_basic_memory_bitmaps();
+ Unlock:
+	unlock_device_hotplug();
+
+	return error;
+}
+
 /**
  * hibernate - Carry out system hibernation, including saving the image.
  */
 int hibernate(void)
 {
-	int error;
+	int error, nr_calls = 0;
+	bool snapshot_test = false;
 
 	if (!hibernation_available()) {
 		pr_debug("PM: Hibernation not available.\n");
@@ -662,9 +695,11 @@ int hibernate(void)
 	}
 
 	pm_prepare_console();
-	error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
-	if (error)
+	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
 		goto Exit;
+	}
 
 	printk(KERN_INFO "PM: Syncing filesystems ... ");
 	sys_sync();
@@ -697,8 +732,12 @@ int hibernate(void)
 		pr_debug("PM: writing image.\n");
 		error = swsusp_write(flags);
 		swsusp_free();
-		if (!error)
-			power_down();
+		if (!error) {
+			if (hibernation_mode == HIBERNATION_TEST_RESUME)
+				snapshot_test = true;
+			else
+				power_down();
+		}
 		in_suspend = 0;
 		pm_restore_gfp_mask();
 	} else {
@@ -709,12 +748,18 @@ int hibernate(void)
 	free_basic_memory_bitmaps();
  Thaw:
 	unlock_device_hotplug();
+	if (snapshot_test) {
+		pr_debug("PM: Checking hibernation image\n");
+		error = swsusp_check();
+		if (!error)
+			error = load_image_and_restore();
+	}
 	thaw_processes();
 
 	/* Don't bother checking whether freezer_test_done is true */
 	freezer_test_done = false;
  Exit:
-	pm_notifier_call_chain(PM_POST_HIBERNATION);
+	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
 	pm_restore_console();
 	atomic_inc(&snapshot_device_available);
  Unlock:
@@ -740,8 +785,7 @@ int hibernate(void)
  */
 static int software_resume(void)
 {
-	int error;
-	unsigned int flags;
+	int error, nr_calls = 0;
 
 	/*
 	 * If the user said "noresume".. bail out early.
@@ -827,35 +871,20 @@ static int software_resume(void)
 	}
 
 	pm_prepare_console();
-	error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
-	if (error)
+	error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
 		goto Close_Finish;
+	}
 
 	pr_debug("PM: Preparing processes for restore.\n");
 	error = freeze_processes();
 	if (error)
 		goto Close_Finish;
-
-	pr_debug("PM: Loading hibernation image.\n");
-
-	lock_device_hotplug();
-	error = create_basic_memory_bitmaps();
-	if (error)
-		goto Thaw;
-
-	error = swsusp_read(&flags);
-	swsusp_close(FMODE_READ);
-	if (!error)
-		hibernation_restore(flags & SF_PLATFORM_MODE);
-
-	printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n");
-	swsusp_free();
-	free_basic_memory_bitmaps();
- Thaw:
-	unlock_device_hotplug();
+	error = load_image_and_restore();
 	thaw_processes();
  Finish:
-	pm_notifier_call_chain(PM_POST_RESTORE);
+	__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	pm_restore_console();
 	atomic_inc(&snapshot_device_available);
 	/* For success case, the suspend path will release the lock */
@@ -878,6 +907,7 @@ static const char * const hibernation_modes[] = {
 #ifdef CONFIG_SUSPEND
 	[HIBERNATION_SUSPEND]	= "suspend",
 #endif
+	[HIBERNATION_TEST_RESUME]	= "test_resume",
 };
 
 /*
@@ -924,6 +954,7 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
 #ifdef CONFIG_SUSPEND
 		case HIBERNATION_SUSPEND:
 #endif
+		case HIBERNATION_TEST_RESUME:
 			break;
 		case HIBERNATION_PLATFORM:
 			if (hibernation_ops)
@@ -970,6 +1001,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 #ifdef CONFIG_SUSPEND
 		case HIBERNATION_SUSPEND:
 #endif
+		case HIBERNATION_TEST_RESUME:
 			hibernation_mode = mode;
 			break;
 		case HIBERNATION_PLATFORM:
@@ -1115,13 +1147,16 @@ static int __init resume_offset_setup(char *str)
 
 static int __init hibernate_setup(char *str)
 {
-	if (!strncmp(str, "noresume", 8))
+	if (!strncmp(str, "noresume", 8)) {
 		noresume = 1;
-	else if (!strncmp(str, "nocompress", 10))
+	} else if (!strncmp(str, "nocompress", 10)) {
 		nocompress = 1;
-	else if (!strncmp(str, "no", 2)) {
+	} else if (!strncmp(str, "no", 2)) {
 		noresume = 1;
 		nohibernate = 1;
+	} else if (IS_ENABLED(CONFIG_DEBUG_RODATA)
+		   && !strncmp(str, "protect_image", 13)) {
+		enable_restore_image_protection();
 	}
 	return 1;
 }
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 27946975eff0..5ea50b1b7595 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -38,12 +38,19 @@ int unregister_pm_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_pm_notifier);
 
-int pm_notifier_call_chain(unsigned long val)
+int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls)
 {
-	int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL);
+	int ret;
+
+	ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL,
+						nr_to_call, nr_calls);
 
 	return notifier_to_errno(ret);
 }
+int pm_notifier_call_chain(unsigned long val)
+{
+	return __pm_notifier_call_chain(val, -1, NULL);
+}
 
 /* If set, devices may be suspended and resumed asynchronously. */
 int pm_async_enabled = 1;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index efe1b3b17c88..242d8b827dd5 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -38,6 +38,8 @@ static inline char *check_image_kernel(struct swsusp_info *info)
 }
 #endif /* CONFIG_ARCH_HIBERNATION_HEADER */
 
+extern int hibernate_resume_nonboot_cpu_disable(void);
+
 /*
  * Keep some memory free so that I/O operations can succeed without paging
  * [Might this be more than 4 MB?]
@@ -59,6 +61,13 @@ extern int hibernation_snapshot(int platform_mode);
 extern int hibernation_restore(int platform_mode);
 extern int hibernation_platform_enter(void);
 
+#ifdef CONFIG_DEBUG_RODATA
+/* kernel/power/snapshot.c */
+extern void enable_restore_image_protection(void);
+#else
+static inline void enable_restore_image_protection(void) {}
+#endif /* CONFIG_DEBUG_RODATA */
+
 #else /* !CONFIG_HIBERNATION */
 
 static inline void hibernate_reserved_size_init(void) {}
@@ -200,6 +209,8 @@ static inline void suspend_test_finish(const char *label) {}
 
 #ifdef CONFIG_PM_SLEEP
 /* kernel/power/main.c */
+extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call,
+				    int *nr_calls);
 extern int pm_notifier_call_chain(unsigned long val);
 #endif
 
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 0c2ee9761d57..8f27d5a8adf6 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -89,6 +89,9 @@ static int try_to_freeze_tasks(bool user_only)
 		       elapsed_msecs / 1000, elapsed_msecs % 1000,
 		       todo - wq_busy, wq_busy);
 
+		if (wq_busy)
+			show_workqueue_state();
+
 		if (!wakeup) {
 			read_lock(&tasklist_lock);
 			for_each_process_thread(g, p) {
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 3a970604308f..d90df926b59f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -38,6 +38,43 @@
 
 #include "power.h"
 
+#ifdef CONFIG_DEBUG_RODATA
+static bool hibernate_restore_protection;
+static bool hibernate_restore_protection_active;
+
+void enable_restore_image_protection(void)
+{
+	hibernate_restore_protection = true;
+}
+
+static inline void hibernate_restore_protection_begin(void)
+{
+	hibernate_restore_protection_active = hibernate_restore_protection;
+}
+
+static inline void hibernate_restore_protection_end(void)
+{
+	hibernate_restore_protection_active = false;
+}
+
+static inline void hibernate_restore_protect_page(void *page_address)
+{
+	if (hibernate_restore_protection_active)
+		set_memory_ro((unsigned long)page_address, 1);
+}
+
+static inline void hibernate_restore_unprotect_page(void *page_address)
+{
+	if (hibernate_restore_protection_active)
+		set_memory_rw((unsigned long)page_address, 1);
+}
+#else
+static inline void hibernate_restore_protection_begin(void) {}
+static inline void hibernate_restore_protection_end(void) {}
+static inline void hibernate_restore_protect_page(void *page_address) {}
+static inline void hibernate_restore_unprotect_page(void *page_address) {}
+#endif /* CONFIG_DEBUG_RODATA */
+
 static int swsusp_page_is_free(struct page *);
 static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
@@ -67,25 +104,32 @@ void __init hibernate_image_size_init(void)
 	image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE;
 }
 
-/* List of PBEs needed for restoring the pages that were allocated before
+/*
+ * List of PBEs needed for restoring the pages that were allocated before
  * the suspend and included in the suspend image, but have also been
  * allocated by the "resume" kernel, so their contents cannot be written
  * directly to their "original" page frames.
  */
 struct pbe *restore_pblist;
 
-/* Pointer to an auxiliary buffer (1 page) */
-static void *buffer;
+/* struct linked_page is used to build chains of pages */
 
-/**
- *	@safe_needed - on resume, for storing the PBE list and the image,
- *	we can only use memory pages that do not conflict with the pages
- *	used before suspend.  The unsafe pages have PageNosaveFree set
- *	and we count them using unsafe_pages.
- *
- *	Each allocated image page is marked as PageNosave and PageNosaveFree
- *	so that swsusp_free() can release it.
+#define LINKED_PAGE_DATA_SIZE	(PAGE_SIZE - sizeof(void *))
+
+struct linked_page {
+	struct linked_page *next;
+	char data[LINKED_PAGE_DATA_SIZE];
+} __packed;
+
+/*
+ * List of "safe" pages (ie. pages that were not used by the image kernel
+ * before hibernation) that may be used as temporary storage for image kernel
+ * memory contents.
  */
+static struct linked_page *safe_pages_list;
+
+/* Pointer to an auxiliary buffer (1 page) */
+static void *buffer;
 
 #define PG_ANY		0
 #define PG_SAFE		1
@@ -94,6 +138,19 @@ static void *buffer;
 
 static unsigned int allocated_unsafe_pages;
 
+/**
+ * get_image_page - Allocate a page for a hibernation image.
+ * @gfp_mask: GFP mask for the allocation.
+ * @safe_needed: Get pages that were not used before hibernation (restore only)
+ *
+ * During image restoration, for storing the PBE list and the image data, we can
+ * only use memory pages that do not conflict with the pages used before
+ * hibernation.  The "unsafe" pages have PageNosaveFree set and we count them
+ * using allocated_unsafe_pages.
+ *
+ * Each allocated image page is marked as PageNosave and PageNosaveFree so that
+ * swsusp_free() can release it.
+ */
 static void *get_image_page(gfp_t gfp_mask, int safe_needed)
 {
 	void *res;
@@ -113,9 +170,21 @@ static void *get_image_page(gfp_t gfp_mask, int safe_needed)
 	return res;
 }
 
+static void *__get_safe_page(gfp_t gfp_mask)
+{
+	if (safe_pages_list) {
+		void *ret = safe_pages_list;
+
+		safe_pages_list = safe_pages_list->next;
+		memset(ret, 0, PAGE_SIZE);
+		return ret;
+	}
+	return get_image_page(gfp_mask, PG_SAFE);
+}
+
 unsigned long get_safe_page(gfp_t gfp_mask)
 {
-	return (unsigned long)get_image_page(gfp_mask, PG_SAFE);
+	return (unsigned long)__get_safe_page(gfp_mask);
 }
 
 static struct page *alloc_image_page(gfp_t gfp_mask)
@@ -130,11 +199,22 @@ static struct page *alloc_image_page(gfp_t gfp_mask)
 	return page;
 }
 
+static void recycle_safe_page(void *page_address)
+{
+	struct linked_page *lp = page_address;
+
+	lp->next = safe_pages_list;
+	safe_pages_list = lp;
+}
+
 /**
- *	free_image_page - free page represented by @addr, allocated with
- *	get_image_page (page flags set by it must be cleared)
+ * free_image_page - Free a page allocated for hibernation image.
+ * @addr: Address of the page to free.
+ * @clear_nosave_free: If set, clear the PageNosaveFree bit for the page.
+ *
+ * The page to free should have been allocated by get_image_page() (page flags
+ * set by it are affected).
  */
-
 static inline void free_image_page(void *addr, int clear_nosave_free)
 {
 	struct page *page;
@@ -150,17 +230,8 @@ static inline void free_image_page(void *addr, int clear_nosave_free)
 	__free_page(page);
 }
 
-/* struct linked_page is used to build chains of pages */
-
-#define LINKED_PAGE_DATA_SIZE	(PAGE_SIZE - sizeof(void *))
-
-struct linked_page {
-	struct linked_page *next;
-	char data[LINKED_PAGE_DATA_SIZE];
-} __packed;
-
-static inline void
-free_list_of_pages(struct linked_page *list, int clear_page_nosave)
+static inline void free_list_of_pages(struct linked_page *list,
+				      int clear_page_nosave)
 {
 	while (list) {
 		struct linked_page *lp = list->next;
@@ -170,30 +241,28 @@ free_list_of_pages(struct linked_page *list, int clear_page_nosave)
 	}
 }
 
-/**
-  *	struct chain_allocator is used for allocating small objects out of
-  *	a linked list of pages called 'the chain'.
-  *
-  *	The chain grows each time when there is no room for a new object in
-  *	the current page.  The allocated objects cannot be freed individually.
-  *	It is only possible to free them all at once, by freeing the entire
-  *	chain.
-  *
-  *	NOTE: The chain allocator may be inefficient if the allocated objects
-  *	are not much smaller than PAGE_SIZE.
-  */
-
+/*
+ * struct chain_allocator is used for allocating small objects out of
+ * a linked list of pages called 'the chain'.
+ *
+ * The chain grows each time when there is no room for a new object in
+ * the current page.  The allocated objects cannot be freed individually.
+ * It is only possible to free them all at once, by freeing the entire
+ * chain.
+ *
+ * NOTE: The chain allocator may be inefficient if the allocated objects
+ * are not much smaller than PAGE_SIZE.
+ */
 struct chain_allocator {
 	struct linked_page *chain;	/* the chain */
 	unsigned int used_space;	/* total size of objects allocated out
-					 * of the current page
-					 */
+					   of the current page */
 	gfp_t gfp_mask;		/* mask for allocating pages */
 	int safe_needed;	/* if set, only "safe" pages are allocated */
 };
 
-static void
-chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed)
+static void chain_init(struct chain_allocator *ca, gfp_t gfp_mask,
+		       int safe_needed)
 {
 	ca->chain = NULL;
 	ca->used_space = LINKED_PAGE_DATA_SIZE;
@@ -208,7 +277,8 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 	if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) {
 		struct linked_page *lp;
 
-		lp = get_image_page(ca->gfp_mask, ca->safe_needed);
+		lp = ca->safe_needed ? __get_safe_page(ca->gfp_mask) :
+					get_image_page(ca->gfp_mask, PG_ANY);
 		if (!lp)
 			return NULL;
 
@@ -222,44 +292,44 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 }
 
 /**
- *	Data types related to memory bitmaps.
+ * Data types related to memory bitmaps.
  *
- *	Memory bitmap is a structure consiting of many linked lists of
- *	objects.  The main list's elements are of type struct zone_bitmap
- *	and each of them corresonds to one zone.  For each zone bitmap
- *	object there is a list of objects of type struct bm_block that
- *	represent each blocks of bitmap in which information is stored.
+ * Memory bitmap is a structure consiting of many linked lists of
+ * objects.  The main list's elements are of type struct zone_bitmap
+ * and each of them corresonds to one zone.  For each zone bitmap
+ * object there is a list of objects of type struct bm_block that
+ * represent each blocks of bitmap in which information is stored.
  *
- *	struct memory_bitmap contains a pointer to the main list of zone
- *	bitmap objects, a struct bm_position used for browsing the bitmap,
- *	and a pointer to the list of pages used for allocating all of the
- *	zone bitmap objects and bitmap block objects.
+ * struct memory_bitmap contains a pointer to the main list of zone
+ * bitmap objects, a struct bm_position used for browsing the bitmap,
+ * and a pointer to the list of pages used for allocating all of the
+ * zone bitmap objects and bitmap block objects.
  *
- *	NOTE: It has to be possible to lay out the bitmap in memory
- *	using only allocations of order 0.  Additionally, the bitmap is
- *	designed to work with arbitrary number of zones (this is over the
- *	top for now, but let's avoid making unnecessary assumptions ;-).
+ * NOTE: It has to be possible to lay out the bitmap in memory
+ * using only allocations of order 0.  Additionally, the bitmap is
+ * designed to work with arbitrary number of zones (this is over the
+ * top for now, but let's avoid making unnecessary assumptions ;-).
  *
- *	struct zone_bitmap contains a pointer to a list of bitmap block
- *	objects and a pointer to the bitmap block object that has been
- *	most recently used for setting bits.  Additionally, it contains the
- *	pfns that correspond to the start and end of the represented zone.
+ * struct zone_bitmap contains a pointer to a list of bitmap block
+ * objects and a pointer to the bitmap block object that has been
+ * most recently used for setting bits.  Additionally, it contains the
+ * PFNs that correspond to the start and end of the represented zone.
  *
- *	struct bm_block contains a pointer to the memory page in which
- *	information is stored (in the form of a block of bitmap)
- *	It also contains the pfns that correspond to the start and end of
- *	the represented memory area.
+ * struct bm_block contains a pointer to the memory page in which
+ * information is stored (in the form of a block of bitmap)
+ * It also contains the pfns that correspond to the start and end of
+ * the represented memory area.
  *
- *	The memory bitmap is organized as a radix tree to guarantee fast random
- *	access to the bits. There is one radix tree for each zone (as returned
- *	from create_mem_extents).
+ * The memory bitmap is organized as a radix tree to guarantee fast random
+ * access to the bits. There is one radix tree for each zone (as returned
+ * from create_mem_extents).
  *
- *	One radix tree is represented by one struct mem_zone_bm_rtree. There are
- *	two linked lists for the nodes of the tree, one for the inner nodes and
- *	one for the leave nodes. The linked leave nodes are used for fast linear
- *	access of the memory bitmap.
+ * One radix tree is represented by one struct mem_zone_bm_rtree. There are
+ * two linked lists for the nodes of the tree, one for the inner nodes and
+ * one for the leave nodes. The linked leave nodes are used for fast linear
+ * access of the memory bitmap.
  *
- *	The struct rtree_node represents one node of the radix tree.
+ * The struct rtree_node represents one node of the radix tree.
  */
 
 #define BM_END_OF_MAP	(~0UL)
@@ -305,9 +375,8 @@ struct bm_position {
 struct memory_bitmap {
 	struct list_head zones;
 	struct linked_page *p_list;	/* list of pages used to store zone
-					 * bitmap objects and bitmap block
-					 * objects
-					 */
+					   bitmap objects and bitmap block
+					   objects */
 	struct bm_position cur;	/* most recently used bit position */
 };
 
@@ -321,12 +390,12 @@ struct memory_bitmap {
 #endif
 #define BM_RTREE_LEVEL_MASK	((1UL << BM_RTREE_LEVEL_SHIFT) - 1)
 
-/*
- *	alloc_rtree_node - Allocate a new node and add it to the radix tree.
+/**
+ * alloc_rtree_node - Allocate a new node and add it to the radix tree.
  *
- *	This function is used to allocate inner nodes as well as the
- *	leave nodes of the radix tree. It also adds the node to the
- *	corresponding linked list passed in by the *list parameter.
+ * This function is used to allocate inner nodes as well as the
+ * leave nodes of the radix tree. It also adds the node to the
+ * corresponding linked list passed in by the *list parameter.
  */
 static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed,
 					   struct chain_allocator *ca,
@@ -347,12 +416,12 @@ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed,
 	return node;
 }
 
-/*
- *	add_rtree_block - Add a new leave node to the radix tree
+/**
+ * add_rtree_block - Add a new leave node to the radix tree.
  *
- *	The leave nodes need to be allocated in order to keep the leaves
- *	linked list in order. This is guaranteed by the zone->blocks
- *	counter.
+ * The leave nodes need to be allocated in order to keep the leaves
+ * linked list in order. This is guaranteed by the zone->blocks
+ * counter.
  */
 static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask,
 			   int safe_needed, struct chain_allocator *ca)
@@ -417,17 +486,18 @@ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask,
 static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone,
 			       int clear_nosave_free);
 
-/*
- *	create_zone_bm_rtree - create a radix tree for one zone
+/**
+ * create_zone_bm_rtree - Create a radix tree for one zone.
  *
- *	Allocated the mem_zone_bm_rtree structure and initializes it.
- *	This function also allocated and builds the radix tree for the
- *	zone.
+ * Allocated the mem_zone_bm_rtree structure and initializes it.
+ * This function also allocated and builds the radix tree for the
+ * zone.
  */
-static struct mem_zone_bm_rtree *
-create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed,
-		     struct chain_allocator *ca,
-		     unsigned long start, unsigned long end)
+static struct mem_zone_bm_rtree *create_zone_bm_rtree(gfp_t gfp_mask,
+						      int safe_needed,
+						      struct chain_allocator *ca,
+						      unsigned long start,
+						      unsigned long end)
 {
 	struct mem_zone_bm_rtree *zone;
 	unsigned int i, nr_blocks;
@@ -454,12 +524,12 @@ create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed,
 	return zone;
 }
 
-/*
- *	free_zone_bm_rtree - Free the memory of the radix tree
+/**
+ * free_zone_bm_rtree - Free the memory of the radix tree.
  *
- *	Free all node pages of the radix tree. The mem_zone_bm_rtree
- *	structure itself is not freed here nor are the rtree_node
- *	structs.
+ * Free all node pages of the radix tree. The mem_zone_bm_rtree
+ * structure itself is not freed here nor are the rtree_node
+ * structs.
  */
 static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone,
 			       int clear_nosave_free)
@@ -492,8 +562,8 @@ struct mem_extent {
 };
 
 /**
- *	free_mem_extents - free a list of memory extents
- *	@list - list of extents to empty
+ * free_mem_extents - Free a list of memory extents.
+ * @list: List of extents to free.
  */
 static void free_mem_extents(struct list_head *list)
 {
@@ -506,10 +576,11 @@ static void free_mem_extents(struct list_head *list)
 }
 
 /**
- *	create_mem_extents - create a list of memory extents representing
- *	                     contiguous ranges of PFNs
- *	@list - list to put the extents into
- *	@gfp_mask - mask to use for memory allocations
+ * create_mem_extents - Create a list of memory extents.
+ * @list: List to put the extents into.
+ * @gfp_mask: Mask to use for memory allocations.
+ *
+ * The extents represent contiguous ranges of PFNs.
  */
 static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 {
@@ -565,10 +636,10 @@ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 }
 
 /**
-  *	memory_bm_create - allocate memory for a memory bitmap
-  */
-static int
-memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
+ * memory_bm_create - Allocate memory for a memory bitmap.
+ */
+static int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask,
+			    int safe_needed)
 {
 	struct chain_allocator ca;
 	struct list_head mem_extents;
@@ -607,8 +678,9 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
 }
 
 /**
-  *	memory_bm_free - free memory occupied by the memory bitmap @bm
-  */
+ * memory_bm_free - Free memory occupied by the memory bitmap.
+ * @bm: Memory bitmap.
+ */
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
 {
 	struct mem_zone_bm_rtree *zone;
@@ -622,14 +694,13 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
 }
 
 /**
- *	memory_bm_find_bit - Find the bit for pfn in the memory
- *			     bitmap
+ * memory_bm_find_bit - Find the bit for a given PFN in a memory bitmap.
  *
- *	Find the bit in the bitmap @bm that corresponds to given pfn.
- *	The cur.zone, cur.block and cur.node_pfn member of @bm are
- *	updated.
- *	It walks the radix tree to find the page which contains the bit for
- *	pfn and returns the bit position in **addr and *bit_nr.
+ * Find the bit in memory bitmap @bm that corresponds to the given PFN.
+ * The cur.zone, cur.block and cur.node_pfn members of @bm are updated.
+ *
+ * Walk the radix tree to find the page containing the bit that represents @pfn
+ * and return the position of the bit in @addr and @bit_nr.
  */
 static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 			      void **addr, unsigned int *bit_nr)
@@ -658,10 +729,9 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 
 zone_found:
 	/*
-	 * We have a zone. Now walk the radix tree to find the leave
-	 * node for our pfn.
+	 * We have found the zone. Now walk the radix tree to find the leaf node
+	 * for our PFN.
 	 */
-
 	node = bm->cur.node;
 	if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
 		goto node_found;
@@ -754,14 +824,14 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
 }
 
 /*
- *	rtree_next_node - Jumps to the next leave node
+ * rtree_next_node - Jump to the next leaf node.
  *
- *	Sets the position to the beginning of the next node in the
- *	memory bitmap. This is either the next node in the current
- *	zone's radix tree or the first node in the radix tree of the
- *	next zone.
+ * Set the position to the beginning of the next node in the
+ * memory bitmap. This is either the next node in the current
+ * zone's radix tree or the first node in the radix tree of the
+ * next zone.
  *
- *	Returns true if there is a next node, false otherwise.
+ * Return true if there is a next node, false otherwise.
  */
 static bool rtree_next_node(struct memory_bitmap *bm)
 {
@@ -790,14 +860,15 @@ static bool rtree_next_node(struct memory_bitmap *bm)
 }
 
 /**
- *	memory_bm_rtree_next_pfn - Find the next set bit in the bitmap @bm
+ * memory_bm_rtree_next_pfn - Find the next set bit in a memory bitmap.
+ * @bm: Memory bitmap.
  *
- *	Starting from the last returned position this function searches
- *	for the next set bit in the memory bitmap and returns its
- *	number. If no more bit is set BM_END_OF_MAP is returned.
+ * Starting from the last returned position this function searches for the next
+ * set bit in @bm and returns the PFN represented by it.  If no more bits are
+ * set, BM_END_OF_MAP is returned.
  *
- *	It is required to run memory_bm_position_reset() before the
- *	first call to this function.
+ * It is required to run memory_bm_position_reset() before the first call to
+ * this function for the given memory bitmap.
  */
 static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
@@ -819,11 +890,10 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 	return BM_END_OF_MAP;
 }
 
-/**
- *	This structure represents a range of page frames the contents of which
- *	should not be saved during the suspend.
+/*
+ * This structure represents a range of page frames the contents of which
+ * should not be saved during hibernation.
  */
-
 struct nosave_region {
 	struct list_head list;
 	unsigned long start_pfn;
@@ -832,15 +902,42 @@ struct nosave_region {
 
 static LIST_HEAD(nosave_regions);
 
+static void recycle_zone_bm_rtree(struct mem_zone_bm_rtree *zone)
+{
+	struct rtree_node *node;
+
+	list_for_each_entry(node, &zone->nodes, list)
+		recycle_safe_page(node->data);
+
+	list_for_each_entry(node, &zone->leaves, list)
+		recycle_safe_page(node->data);
+}
+
+static void memory_bm_recycle(struct memory_bitmap *bm)
+{
+	struct mem_zone_bm_rtree *zone;
+	struct linked_page *p_list;
+
+	list_for_each_entry(zone, &bm->zones, list)
+		recycle_zone_bm_rtree(zone);
+
+	p_list = bm->p_list;
+	while (p_list) {
+		struct linked_page *lp = p_list;
+
+		p_list = lp->next;
+		recycle_safe_page(lp);
+	}
+}
+
 /**
- *	register_nosave_region - register a range of page frames the contents
- *	of which should not be saved during the suspend (to be used in the early
- *	initialization code)
+ * register_nosave_region - Register a region of unsaveable memory.
+ *
+ * Register a range of page frames the contents of which should not be saved
+ * during hibernation (to be used in the early initialization code).
  */
-
-void __init
-__register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
-			 int use_kmalloc)
+void __init __register_nosave_region(unsigned long start_pfn,
+				     unsigned long end_pfn, int use_kmalloc)
 {
 	struct nosave_region *region;
 
@@ -857,12 +954,13 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
 		}
 	}
 	if (use_kmalloc) {
-		/* during init, this shouldn't fail */
+		/* During init, this shouldn't fail */
 		region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL);
 		BUG_ON(!region);
-	} else
+	} else {
 		/* This allocation cannot fail */
 		region = memblock_virt_alloc(sizeof(struct nosave_region), 0);
+	}
 	region->start_pfn = start_pfn;
 	region->end_pfn = end_pfn;
 	list_add_tail(&region->list, &nosave_regions);
@@ -923,10 +1021,12 @@ static void swsusp_unset_page_forbidden(struct page *page)
 }
 
 /**
- *	mark_nosave_pages - set bits corresponding to the page frames the
- *	contents of which should not be saved in a given bitmap.
+ * mark_nosave_pages - Mark pages that should not be saved.
+ * @bm: Memory bitmap.
+ *
+ * Set the bits in @bm that correspond to the page frames the contents of which
+ * should not be saved.
  */
-
 static void mark_nosave_pages(struct memory_bitmap *bm)
 {
 	struct nosave_region *region;
@@ -956,13 +1056,13 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 }
 
 /**
- *	create_basic_memory_bitmaps - create bitmaps needed for marking page
- *	frames that should not be saved and free page frames.  The pointers
- *	forbidden_pages_map and free_pages_map are only modified if everything
- *	goes well, because we don't want the bits to be used before both bitmaps
- *	are set up.
+ * create_basic_memory_bitmaps - Create bitmaps to hold basic page information.
+ *
+ * Create bitmaps needed for marking page frames that should not be saved and
+ * free page frames.  The forbidden_pages_map and free_pages_map pointers are
+ * only modified if everything goes well, because we don't want the bits to be
+ * touched before both bitmaps are set up.
  */
-
 int create_basic_memory_bitmaps(void)
 {
 	struct memory_bitmap *bm1, *bm2;
@@ -1007,12 +1107,12 @@ int create_basic_memory_bitmaps(void)
 }
 
 /**
- *	free_basic_memory_bitmaps - free memory bitmaps allocated by
- *	create_basic_memory_bitmaps().  The auxiliary pointers are necessary
- *	so that the bitmaps themselves are not referred to while they are being
- *	freed.
+ * free_basic_memory_bitmaps - Free memory bitmaps holding basic information.
+ *
+ * Free memory bitmaps allocated by create_basic_memory_bitmaps().  The
+ * auxiliary pointers are necessary so that the bitmaps themselves are not
+ * referred to while they are being freed.
  */
-
 void free_basic_memory_bitmaps(void)
 {
 	struct memory_bitmap *bm1, *bm2;
@@ -1033,11 +1133,13 @@ void free_basic_memory_bitmaps(void)
 }
 
 /**
- *	snapshot_additional_pages - estimate the number of additional pages
- *	be needed for setting up the suspend image data structures for given
- *	zone (usually the returned value is greater than the exact number)
+ * snapshot_additional_pages - Estimate the number of extra pages needed.
+ * @zone: Memory zone to carry out the computation for.
+ *
+ * Estimate the number of additional pages needed for setting up a hibernation
+ * image data structures for @zone (usually, the returned value is greater than
+ * the exact number).
  */
-
 unsigned int snapshot_additional_pages(struct zone *zone)
 {
 	unsigned int rtree, nodes;
@@ -1055,10 +1157,10 @@ unsigned int snapshot_additional_pages(struct zone *zone)
 
 #ifdef CONFIG_HIGHMEM
 /**
- *	count_free_highmem_pages - compute the total number of free highmem
- *	pages, system-wide.
+ * count_free_highmem_pages - Compute the total number of free highmem pages.
+ *
+ * The returned number is system-wide.
  */
-
 static unsigned int count_free_highmem_pages(void)
 {
 	struct zone *zone;
@@ -1072,11 +1174,12 @@ static unsigned int count_free_highmem_pages(void)
 }
 
 /**
- *	saveable_highmem_page - Determine whether a highmem page should be
- *	included in the suspend image.
+ * saveable_highmem_page - Check if a highmem page is saveable.
  *
- *	We should save the page if it isn't Nosave or NosaveFree, or Reserved,
- *	and it isn't a part of a free chunk of pages.
+ * Determine whether a highmem page should be included in a hibernation image.
+ *
+ * We should save the page if it isn't Nosave or NosaveFree, or Reserved,
+ * and it isn't part of a free chunk of pages.
  */
 static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
 {
@@ -1102,10 +1205,8 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
 }
 
 /**
- *	count_highmem_pages - compute the total number of saveable highmem
- *	pages.
+ * count_highmem_pages - Compute the total number of saveable highmem pages.
  */
-
 static unsigned int count_highmem_pages(void)
 {
 	struct zone *zone;
@@ -1133,12 +1234,14 @@ static inline void *saveable_highmem_page(struct zone *z, unsigned long p)
 #endif /* CONFIG_HIGHMEM */
 
 /**
- *	saveable_page - Determine whether a non-highmem page should be included
- *	in the suspend image.
+ * saveable_page - Check if the given page is saveable.
  *
- *	We should save the page if it isn't Nosave, and is not in the range
- *	of pages statically defined as 'unsaveable', and it isn't a part of
- *	a free chunk of pages.
+ * Determine whether a non-highmem page should be included in a hibernation
+ * image.
+ *
+ * We should save the page if it isn't Nosave, and is not in the range
+ * of pages statically defined as 'unsaveable', and it isn't part of
+ * a free chunk of pages.
  */
 static struct page *saveable_page(struct zone *zone, unsigned long pfn)
 {
@@ -1167,10 +1270,8 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn)
 }
 
 /**
- *	count_data_pages - compute the total number of saveable non-highmem
- *	pages.
+ * count_data_pages - Compute the total number of saveable non-highmem pages.
  */
-
 static unsigned int count_data_pages(void)
 {
 	struct zone *zone;
@@ -1190,7 +1291,8 @@ static unsigned int count_data_pages(void)
 	return n;
 }
 
-/* This is needed, because copy_page and memcpy are not usable for copying
+/*
+ * This is needed, because copy_page and memcpy are not usable for copying
  * task structs.
  */
 static inline void do_copy_page(long *dst, long *src)
@@ -1201,12 +1303,12 @@ static inline void do_copy_page(long *dst, long *src)
 		*dst++ = *src++;
 }
 
-
 /**
- *	safe_copy_page - check if the page we are going to copy is marked as
- *		present in the kernel page tables (this always is the case if
- *		CONFIG_DEBUG_PAGEALLOC is not set and in that case
- *		kernel_page_present() always returns 'true').
+ * safe_copy_page - Copy a page in a safe way.
+ *
+ * Check if the page we are going to copy is marked as present in the kernel
+ * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set
+ * and in that case kernel_page_present() always returns 'true').
  */
 static void safe_copy_page(void *dst, struct page *s_page)
 {
@@ -1219,10 +1321,8 @@ static void safe_copy_page(void *dst, struct page *s_page)
 	}
 }
 
-
 #ifdef CONFIG_HIGHMEM
-static inline struct page *
-page_is_saveable(struct zone *zone, unsigned long pfn)
+static inline struct page *page_is_saveable(struct zone *zone, unsigned long pfn)
 {
 	return is_highmem(zone) ?
 		saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn);
@@ -1243,7 +1343,8 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 		kunmap_atomic(src);
 	} else {
 		if (PageHighMem(d_page)) {
-			/* Page pointed to by src may contain some kernel
+			/*
+			 * The page pointed to by src may contain some kernel
 			 * data modified by kmap_atomic()
 			 */
 			safe_copy_page(buffer, s_page);
@@ -1265,8 +1366,8 @@ static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 }
 #endif /* CONFIG_HIGHMEM */
 
-static void
-copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
+static void copy_data_pages(struct memory_bitmap *copy_bm,
+			    struct memory_bitmap *orig_bm)
 {
 	struct zone *zone;
 	unsigned long pfn;
@@ -1315,12 +1416,11 @@ static struct memory_bitmap orig_bm;
 static struct memory_bitmap copy_bm;
 
 /**
- *	swsusp_free - free pages allocated for the suspend.
+ * swsusp_free - Free pages allocated for hibernation image.
  *
- *	Suspend pages are alocated before the atomic copy is made, so we
- *	need to release them after the resume.
+ * Image pages are alocated before snapshot creation, so they need to be
+ * released after resume.
  */
-
 void swsusp_free(void)
 {
 	unsigned long fb_pfn, fr_pfn;
@@ -1351,6 +1451,7 @@ loop:
 
 		memory_bm_clear_current(forbidden_pages_map);
 		memory_bm_clear_current(free_pages_map);
+		hibernate_restore_unprotect_page(page_address(page));
 		__free_page(page);
 		goto loop;
 	}
@@ -1362,6 +1463,7 @@ out:
 	buffer = NULL;
 	alloc_normal = 0;
 	alloc_highmem = 0;
+	hibernate_restore_protection_end();
 }
 
 /* Helper functions used for the shrinking of memory. */
@@ -1369,7 +1471,7 @@ out:
 #define GFP_IMAGE	(GFP_KERNEL | __GFP_NOWARN)
 
 /**
- * preallocate_image_pages - Allocate a number of pages for hibernation image
+ * preallocate_image_pages - Allocate a number of pages for hibernation image.
  * @nr_pages: Number of page frames to allocate.
  * @mask: GFP flags to use for the allocation.
  *
@@ -1419,7 +1521,7 @@ static unsigned long preallocate_image_highmem(unsigned long nr_pages)
 }
 
 /**
- *  __fraction - Compute (an approximation of) x * (multiplier / base)
+ *  __fraction - Compute (an approximation of) x * (multiplier / base).
  */
 static unsigned long __fraction(u64 x, u64 multiplier, u64 base)
 {
@@ -1429,8 +1531,8 @@ static unsigned long __fraction(u64 x, u64 multiplier, u64 base)
 }
 
 static unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
-						unsigned long highmem,
-						unsigned long total)
+						  unsigned long highmem,
+						  unsigned long total)
 {
 	unsigned long alloc = __fraction(nr_pages, highmem, total);
 
@@ -1443,15 +1545,15 @@ static inline unsigned long preallocate_image_highmem(unsigned long nr_pages)
 }
 
 static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
-						unsigned long highmem,
-						unsigned long total)
+							 unsigned long highmem,
+							 unsigned long total)
 {
 	return 0;
 }
 #endif /* CONFIG_HIGHMEM */
 
 /**
- * free_unnecessary_pages - Release preallocated pages not needed for the image
+ * free_unnecessary_pages - Release preallocated pages not needed for the image.
  */
 static unsigned long free_unnecessary_pages(void)
 {
@@ -1505,7 +1607,7 @@ static unsigned long free_unnecessary_pages(void)
 }
 
 /**
- * minimum_image_size - Estimate the minimum acceptable size of an image
+ * minimum_image_size - Estimate the minimum acceptable size of an image.
  * @saveable: Number of saveable pages in the system.
  *
  * We want to avoid attempting to free too much memory too hard, so estimate the
@@ -1535,7 +1637,7 @@ static unsigned long minimum_image_size(unsigned long saveable)
 }
 
 /**
- * hibernate_preallocate_memory - Preallocate memory for hibernation image
+ * hibernate_preallocate_memory - Preallocate memory for hibernation image.
  *
  * To create a hibernation image it is necessary to make a copy of every page
  * frame in use.  We also need a number of page frames to be free during
@@ -1708,10 +1810,11 @@ int hibernate_preallocate_memory(void)
 
 #ifdef CONFIG_HIGHMEM
 /**
-  *	count_pages_for_highmem - compute the number of non-highmem pages
-  *	that will be necessary for creating copies of highmem pages.
-  */
-
+ * count_pages_for_highmem - Count non-highmem pages needed for copying highmem.
+ *
+ * Compute the number of non-highmem pages that will be necessary for creating
+ * copies of highmem pages.
+ */
 static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
 {
 	unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem;
@@ -1724,15 +1827,12 @@ static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
 	return nr_highmem;
 }
 #else
-static unsigned int
-count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
+static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
 #endif /* CONFIG_HIGHMEM */
 
 /**
- *	enough_free_mem - Make sure we have enough free memory for the
- *	snapshot image.
+ * enough_free_mem - Check if there is enough free memory for the image.
  */
-
 static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
 {
 	struct zone *zone;
@@ -1751,10 +1851,11 @@ static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
 
 #ifdef CONFIG_HIGHMEM
 /**
- *	get_highmem_buffer - if there are some highmem pages in the suspend
- *	image, we may need the buffer to copy them and/or load their data.
+ * get_highmem_buffer - Allocate a buffer for highmem pages.
+ *
+ * If there are some highmem pages in the hibernation image, we may need a
+ * buffer to copy them and/or load their data.
  */
-
 static inline int get_highmem_buffer(int safe_needed)
 {
 	buffer = get_image_page(GFP_ATOMIC | __GFP_COLD, safe_needed);
@@ -1762,13 +1863,13 @@ static inline int get_highmem_buffer(int safe_needed)
 }
 
 /**
- *	alloc_highmem_image_pages - allocate some highmem pages for the image.
- *	Try to allocate as many pages as needed, but if the number of free
- *	highmem pages is lesser than that, allocate them all.
+ * alloc_highmem_image_pages - Allocate some highmem pages for the image.
+ *
+ * Try to allocate as many pages as needed, but if the number of free highmem
+ * pages is less than that, allocate them all.
  */
-
-static inline unsigned int
-alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
+static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm,
+					       unsigned int nr_highmem)
 {
 	unsigned int to_alloc = count_free_highmem_pages();
 
@@ -1787,25 +1888,24 @@ alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 #else
 static inline int get_highmem_buffer(int safe_needed) { return 0; }
 
-static inline unsigned int
-alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
+static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm,
+					       unsigned int n) { return 0; }
 #endif /* CONFIG_HIGHMEM */
 
 /**
- *	swsusp_alloc - allocate memory for the suspend image
+ * swsusp_alloc - Allocate memory for hibernation image.
  *
- *	We first try to allocate as many highmem pages as there are
- *	saveable highmem pages in the system.  If that fails, we allocate
- *	non-highmem pages for the copies of the remaining highmem ones.
+ * We first try to allocate as many highmem pages as there are
+ * saveable highmem pages in the system.  If that fails, we allocate
+ * non-highmem pages for the copies of the remaining highmem ones.
  *
- *	In this approach it is likely that the copies of highmem pages will
- *	also be located in the high memory, because of the way in which
- *	copy_data_pages() works.
+ * In this approach it is likely that the copies of highmem pages will
+ * also be located in the high memory, because of the way in which
+ * copy_data_pages() works.
  */
-
-static int
-swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
-		unsigned int nr_pages, unsigned int nr_highmem)
+static int swsusp_alloc(struct memory_bitmap *orig_bm,
+			struct memory_bitmap *copy_bm,
+			unsigned int nr_pages, unsigned int nr_highmem)
 {
 	if (nr_highmem > 0) {
 		if (get_highmem_buffer(PG_ANY))
@@ -1855,7 +1955,8 @@ asmlinkage __visible int swsusp_save(void)
 		return -ENOMEM;
 	}
 
-	/* During allocating of suspend pagedir, new cold pages may appear.
+	/*
+	 * During allocating of suspend pagedir, new cold pages may appear.
 	 * Kill them.
 	 */
 	drain_local_pages(NULL);
@@ -1918,12 +2019,14 @@ static int init_header(struct swsusp_info *info)
 }
 
 /**
- *	pack_pfns - pfns corresponding to the set bits found in the bitmap @bm
- *	are stored in the array @buf[] (1 page at a time)
+ * pack_pfns - Prepare PFNs for saving.
+ * @bm: Memory bitmap.
+ * @buf: Memory buffer to store the PFNs in.
+ *
+ * PFNs corresponding to set bits in @bm are stored in the area of memory
+ * pointed to by @buf (1 page at a time).
  */
-
-static inline void
-pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
+static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
 {
 	int j;
 
@@ -1937,22 +2040,21 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
 }
 
 /**
- *	snapshot_read_next - used for reading the system memory snapshot.
+ * snapshot_read_next - Get the address to read the next image page from.
+ * @handle: Snapshot handle to be used for the reading.
  *
- *	On the first call to it @handle should point to a zeroed
- *	snapshot_handle structure.  The structure gets updated and a pointer
- *	to it should be passed to this function every next time.
+ * On the first call, @handle should point to a zeroed snapshot_handle
+ * structure.  The structure gets populated then and a pointer to it should be
+ * passed to this function every next time.
  *
- *	On success the function returns a positive number.  Then, the caller
- *	is allowed to read up to the returned number of bytes from the memory
- *	location computed by the data_of() macro.
+ * On success, the function returns a positive number.  Then, the caller
+ * is allowed to read up to the returned number of bytes from the memory
+ * location computed by the data_of() macro.
  *
- *	The function returns 0 to indicate the end of data stream condition,
- *	and a negative number is returned on error.  In such cases the
- *	structure pointed to by @handle is not updated and should not be used
- *	any more.
+ * The function returns 0 to indicate the end of the data stream condition,
+ * and negative numbers are returned on errors.  If that happens, the structure
+ * pointed to by @handle is not updated and should not be used any more.
  */
-
 int snapshot_read_next(struct snapshot_handle *handle)
 {
 	if (handle->cur > nr_meta_pages + nr_copy_pages)
@@ -1981,7 +2083,8 @@ int snapshot_read_next(struct snapshot_handle *handle)
 
 		page = pfn_to_page(memory_bm_next_pfn(&copy_bm));
 		if (PageHighMem(page)) {
-			/* Highmem pages are copied to the buffer,
+			/*
+			 * Highmem pages are copied to the buffer,
 			 * because we can't return with a kmapped
 			 * highmem page (we may not be called again).
 			 */
@@ -1999,53 +2102,41 @@ int snapshot_read_next(struct snapshot_handle *handle)
 	return PAGE_SIZE;
 }
 
-/**
- *	mark_unsafe_pages - mark the pages that cannot be used for storing
- *	the image during resume, because they conflict with the pages that
- *	had been used before suspend
- */
-
-static int mark_unsafe_pages(struct memory_bitmap *bm)
+static void duplicate_memory_bitmap(struct memory_bitmap *dst,
+				    struct memory_bitmap *src)
 {
-	struct zone *zone;
-	unsigned long pfn, max_zone_pfn;
+	unsigned long pfn;
 
-	/* Clear page flags */
-	for_each_populated_zone(zone) {
-		max_zone_pfn = zone_end_pfn(zone);
-		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if (pfn_valid(pfn))
-				swsusp_unset_page_free(pfn_to_page(pfn));
+	memory_bm_position_reset(src);
+	pfn = memory_bm_next_pfn(src);
+	while (pfn != BM_END_OF_MAP) {
+		memory_bm_set_bit(dst, pfn);
+		pfn = memory_bm_next_pfn(src);
 	}
-
-	/* Mark pages that correspond to the "original" pfns as "unsafe" */
-	memory_bm_position_reset(bm);
-	do {
-		pfn = memory_bm_next_pfn(bm);
-		if (likely(pfn != BM_END_OF_MAP)) {
-			if (likely(pfn_valid(pfn)))
-				swsusp_set_page_free(pfn_to_page(pfn));
-			else
-				return -EFAULT;
-		}
-	} while (pfn != BM_END_OF_MAP);
-
-	allocated_unsafe_pages = 0;
-
-	return 0;
 }
 
-static void
-duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src)
+/**
+ * mark_unsafe_pages - Mark pages that were used before hibernation.
+ *
+ * Mark the pages that cannot be used for storing the image during restoration,
+ * because they conflict with the pages that had been used before hibernation.
+ */
+static void mark_unsafe_pages(struct memory_bitmap *bm)
 {
 	unsigned long pfn;
 
-	memory_bm_position_reset(src);
-	pfn = memory_bm_next_pfn(src);
+	/* Clear the "free"/"unsafe" bit for all PFNs */
+	memory_bm_position_reset(free_pages_map);
+	pfn = memory_bm_next_pfn(free_pages_map);
 	while (pfn != BM_END_OF_MAP) {
-		memory_bm_set_bit(dst, pfn);
-		pfn = memory_bm_next_pfn(src);
+		memory_bm_clear_current(free_pages_map);
+		pfn = memory_bm_next_pfn(free_pages_map);
 	}
+
+	/* Mark pages that correspond to the "original" PFNs as "unsafe" */
+	duplicate_memory_bitmap(free_pages_map, bm);
+
+	allocated_unsafe_pages = 0;
 }
 
 static int check_header(struct swsusp_info *info)
@@ -2063,11 +2154,9 @@ static int check_header(struct swsusp_info *info)
 }
 
 /**
- *	load header - check the image header and copy data from it
+ * load header - Check the image header and copy the data from it.
  */
-
-static int
-load_header(struct swsusp_info *info)
+static int load_header(struct swsusp_info *info)
 {
 	int error;
 
@@ -2081,8 +2170,12 @@ load_header(struct swsusp_info *info)
 }
 
 /**
- *	unpack_orig_pfns - for each element of @buf[] (1 page at a time) set
- *	the corresponding bit in the memory bitmap @bm
+ * unpack_orig_pfns - Set bits corresponding to given PFNs in a memory bitmap.
+ * @bm: Memory bitmap.
+ * @buf: Area of memory containing the PFNs.
+ *
+ * For each element of the array pointed to by @buf (1 page at a time), set the
+ * corresponding bit in @bm.
  */
 static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 {
@@ -2095,7 +2188,7 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 		/* Extract and buffer page key for data page (s390 only). */
 		page_key_memorize(buf + j);
 
-		if (memory_bm_pfn_present(bm, buf[j]))
+		if (pfn_valid(buf[j]) && memory_bm_pfn_present(bm, buf[j]))
 			memory_bm_set_bit(bm, buf[j]);
 		else
 			return -EFAULT;
@@ -2104,13 +2197,9 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 	return 0;
 }
 
-/* List of "safe" pages that may be used to store data loaded from the suspend
- * image
- */
-static struct linked_page *safe_pages_list;
-
 #ifdef CONFIG_HIGHMEM
-/* struct highmem_pbe is used for creating the list of highmem pages that
+/*
+ * struct highmem_pbe is used for creating the list of highmem pages that
  * should be restored atomically during the resume from disk, because the page
  * frames they have occupied before the suspend are in use.
  */
@@ -2120,7 +2209,8 @@ struct highmem_pbe {
 	struct highmem_pbe *next;
 };
 
-/* List of highmem PBEs needed for restoring the highmem pages that were
+/*
+ * List of highmem PBEs needed for restoring the highmem pages that were
  * allocated before the suspend and included in the suspend image, but have
  * also been allocated by the "resume" kernel, so their contents cannot be
  * written directly to their "original" page frames.
@@ -2128,11 +2218,11 @@ struct highmem_pbe {
 static struct highmem_pbe *highmem_pblist;
 
 /**
- *	count_highmem_image_pages - compute the number of highmem pages in the
- *	suspend image.  The bits in the memory bitmap @bm that correspond to the
- *	image pages are assumed to be set.
+ * count_highmem_image_pages - Compute the number of highmem pages in the image.
+ * @bm: Memory bitmap.
+ *
+ * The bits in @bm that correspond to image pages are assumed to be set.
  */
-
 static unsigned int count_highmem_image_pages(struct memory_bitmap *bm)
 {
 	unsigned long pfn;
@@ -2149,24 +2239,25 @@ static unsigned int count_highmem_image_pages(struct memory_bitmap *bm)
 	return cnt;
 }
 
-/**
- *	prepare_highmem_image - try to allocate as many highmem pages as
- *	there are highmem image pages (@nr_highmem_p points to the variable
- *	containing the number of highmem image pages).  The pages that are
- *	"safe" (ie. will not be overwritten when the suspend image is
- *	restored) have the corresponding bits set in @bm (it must be
- *	unitialized).
- *
- *	NOTE: This function should not be called if there are no highmem
- *	image pages.
- */
-
 static unsigned int safe_highmem_pages;
 
 static struct memory_bitmap *safe_highmem_bm;
 
-static int
-prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
+/**
+ * prepare_highmem_image - Allocate memory for loading highmem data from image.
+ * @bm: Pointer to an uninitialized memory bitmap structure.
+ * @nr_highmem_p: Pointer to the number of highmem image pages.
+ *
+ * Try to allocate as many highmem pages as there are highmem image pages
+ * (@nr_highmem_p points to the variable containing the number of highmem image
+ * pages).  The pages that are "safe" (ie. will not be overwritten when the
+ * hibernation image is restored entirely) have the corresponding bits set in
+ * @bm (it must be unitialized).
+ *
+ * NOTE: This function should not be called if there are no highmem image pages.
+ */
+static int prepare_highmem_image(struct memory_bitmap *bm,
+				 unsigned int *nr_highmem_p)
 {
 	unsigned int to_alloc;
 
@@ -2201,39 +2292,42 @@ prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
 	return 0;
 }
 
+static struct page *last_highmem_page;
+
 /**
- *	get_highmem_page_buffer - for given highmem image page find the buffer
- *	that suspend_write_next() should set for its caller to write to.
+ * get_highmem_page_buffer - Prepare a buffer to store a highmem image page.
  *
- *	If the page is to be saved to its "original" page frame or a copy of
- *	the page is to be made in the highmem, @buffer is returned.  Otherwise,
- *	the copy of the page is to be made in normal memory, so the address of
- *	the copy is returned.
+ * For a given highmem image page get a buffer that suspend_write_next() should
+ * return to its caller to write to.
  *
- *	If @buffer is returned, the caller of suspend_write_next() will write
- *	the page's contents to @buffer, so they will have to be copied to the
- *	right location on the next call to suspend_write_next() and it is done
- *	with the help of copy_last_highmem_page().  For this purpose, if
- *	@buffer is returned, @last_highmem page is set to the page to which
- *	the data will have to be copied from @buffer.
+ * If the page is to be saved to its "original" page frame or a copy of
+ * the page is to be made in the highmem, @buffer is returned.  Otherwise,
+ * the copy of the page is to be made in normal memory, so the address of
+ * the copy is returned.
+ *
+ * If @buffer is returned, the caller of suspend_write_next() will write
+ * the page's contents to @buffer, so they will have to be copied to the
+ * right location on the next call to suspend_write_next() and it is done
+ * with the help of copy_last_highmem_page().  For this purpose, if
+ * @buffer is returned, @last_highmem_page is set to the page to which
+ * the data will have to be copied from @buffer.
  */
-
-static struct page *last_highmem_page;
-
-static void *
-get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
+static void *get_highmem_page_buffer(struct page *page,
+				     struct chain_allocator *ca)
 {
 	struct highmem_pbe *pbe;
 	void *kaddr;
 
 	if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) {
-		/* We have allocated the "original" page frame and we can
+		/*
+		 * We have allocated the "original" page frame and we can
 		 * use it directly to store the loaded page.
 		 */
 		last_highmem_page = page;
 		return buffer;
 	}
-	/* The "original" page frame has not been allocated and we have to
+	/*
+	 * The "original" page frame has not been allocated and we have to
 	 * use a "safe" page frame to store the loaded page.
 	 */
 	pbe = chain_alloc(ca, sizeof(struct highmem_pbe));
@@ -2263,11 +2357,12 @@ get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
 }
 
 /**
- *	copy_last_highmem_page - copy the contents of a highmem image from
- *	@buffer, where the caller of snapshot_write_next() has place them,
- *	to the right location represented by @last_highmem_page .
+ * copy_last_highmem_page - Copy most the most recent highmem image page.
+ *
+ * Copy the contents of a highmem image from @buffer, where the caller of
+ * snapshot_write_next() has stored them, to the right location represented by
+ * @last_highmem_page .
  */
-
 static void copy_last_highmem_page(void)
 {
 	if (last_highmem_page) {
@@ -2294,17 +2389,13 @@ static inline void free_highmem_data(void)
 		free_image_page(buffer, PG_UNSAFE_CLEAR);
 }
 #else
-static unsigned int
-count_highmem_image_pages(struct memory_bitmap *bm) { return 0; }
+static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { return 0; }
 
-static inline int
-prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
-{
-	return 0;
-}
+static inline int prepare_highmem_image(struct memory_bitmap *bm,
+					unsigned int *nr_highmem_p) { return 0; }
 
-static inline void *
-get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
+static inline void *get_highmem_page_buffer(struct page *page,
+					    struct chain_allocator *ca)
 {
 	return ERR_PTR(-EINVAL);
 }
@@ -2314,27 +2405,27 @@ static inline int last_highmem_page_copied(void) { return 1; }
 static inline void free_highmem_data(void) {}
 #endif /* CONFIG_HIGHMEM */
 
+#define PBES_PER_LINKED_PAGE	(LINKED_PAGE_DATA_SIZE / sizeof(struct pbe))
+
 /**
- *	prepare_image - use the memory bitmap @bm to mark the pages that will
- *	be overwritten in the process of restoring the system memory state
- *	from the suspend image ("unsafe" pages) and allocate memory for the
- *	image.
+ * prepare_image - Make room for loading hibernation image.
+ * @new_bm: Unitialized memory bitmap structure.
+ * @bm: Memory bitmap with unsafe pages marked.
+ *
+ * Use @bm to mark the pages that will be overwritten in the process of
+ * restoring the system memory state from the suspend image ("unsafe" pages)
+ * and allocate memory for the image.
  *
- *	The idea is to allocate a new memory bitmap first and then allocate
- *	as many pages as needed for the image data, but not to assign these
- *	pages to specific tasks initially.  Instead, we just mark them as
- *	allocated and create a lists of "safe" pages that will be used
- *	later.  On systems with high memory a list of "safe" highmem pages is
- *	also created.
+ * The idea is to allocate a new memory bitmap first and then allocate
+ * as many pages as needed for image data, but without specifying what those
+ * pages will be used for just yet.  Instead, we mark them all as allocated and
+ * create a lists of "safe" pages to be used later.  On systems with high
+ * memory a list of "safe" highmem pages is created too.
  */
-
-#define PBES_PER_LINKED_PAGE	(LINKED_PAGE_DATA_SIZE / sizeof(struct pbe))
-
-static int
-prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
+static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 {
 	unsigned int nr_pages, nr_highmem;
-	struct linked_page *sp_list, *lp;
+	struct linked_page *lp;
 	int error;
 
 	/* If there is no highmem, the buffer will not be necessary */
@@ -2342,9 +2433,7 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 	buffer = NULL;
 
 	nr_highmem = count_highmem_image_pages(bm);
-	error = mark_unsafe_pages(bm);
-	if (error)
-		goto Free;
+	mark_unsafe_pages(bm);
 
 	error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE);
 	if (error)
@@ -2357,14 +2446,15 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 		if (error)
 			goto Free;
 	}
-	/* Reserve some safe pages for potential later use.
+	/*
+	 * Reserve some safe pages for potential later use.
 	 *
 	 * NOTE: This way we make sure there will be enough safe pages for the
 	 * chain_alloc() in get_buffer().  It is a bit wasteful, but
 	 * nr_copy_pages cannot be greater than 50% of the memory anyway.
+	 *
+	 * nr_copy_pages cannot be less than allocated_unsafe_pages too.
 	 */
-	sp_list = NULL;
-	/* nr_copy_pages cannot be lesser than allocated_unsafe_pages */
 	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
 	nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE);
 	while (nr_pages > 0) {
@@ -2373,12 +2463,11 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 			error = -ENOMEM;
 			goto Free;
 		}
-		lp->next = sp_list;
-		sp_list = lp;
+		lp->next = safe_pages_list;
+		safe_pages_list = lp;
 		nr_pages--;
 	}
 	/* Preallocate memory for the image */
-	safe_pages_list = NULL;
 	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
 	while (nr_pages > 0) {
 		lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC);
@@ -2396,12 +2485,6 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 		swsusp_set_page_free(virt_to_page(lp));
 		nr_pages--;
 	}
-	/* Free the reserved safe pages so that chain_alloc() can use them */
-	while (sp_list) {
-		lp = sp_list->next;
-		free_image_page(sp_list, PG_UNSAFE_CLEAR);
-		sp_list = lp;
-	}
 	return 0;
 
  Free:
@@ -2410,10 +2493,11 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 }
 
 /**
- *	get_buffer - compute the address that snapshot_write_next() should
- *	set for its caller to write to.
+ * get_buffer - Get the address to store the next image data page.
+ *
+ * Get the address that snapshot_write_next() should return to its caller to
+ * write to.
  */
-
 static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 {
 	struct pbe *pbe;
@@ -2428,12 +2512,14 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 		return get_highmem_page_buffer(page, ca);
 
 	if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page))
-		/* We have allocated the "original" page frame and we can
+		/*
+		 * We have allocated the "original" page frame and we can
 		 * use it directly to store the loaded page.
 		 */
 		return page_address(page);
 
-	/* The "original" page frame has not been allocated and we have to
+	/*
+	 * The "original" page frame has not been allocated and we have to
 	 * use a "safe" page frame to store the loaded page.
 	 */
 	pbe = chain_alloc(ca, sizeof(struct pbe));
@@ -2450,22 +2536,21 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 }
 
 /**
- *	snapshot_write_next - used for writing the system memory snapshot.
+ * snapshot_write_next - Get the address to store the next image page.
+ * @handle: Snapshot handle structure to guide the writing.
  *
- *	On the first call to it @handle should point to a zeroed
- *	snapshot_handle structure.  The structure gets updated and a pointer
- *	to it should be passed to this function every next time.
+ * On the first call, @handle should point to a zeroed snapshot_handle
+ * structure.  The structure gets populated then and a pointer to it should be
+ * passed to this function every next time.
  *
- *	On success the function returns a positive number.  Then, the caller
- *	is allowed to write up to the returned number of bytes to the memory
- *	location computed by the data_of() macro.
+ * On success, the function returns a positive number.  Then, the caller
+ * is allowed to write up to the returned number of bytes to the memory
+ * location computed by the data_of() macro.
  *
- *	The function returns 0 to indicate the "end of file" condition,
- *	and a negative number is returned on error.  In such cases the
- *	structure pointed to by @handle is not updated and should not be used
- *	any more.
+ * The function returns 0 to indicate the "end of file" condition.  Negative
+ * numbers are returned on errors, in which cases the structure pointed to by
+ * @handle is not updated and should not be used any more.
  */
-
 int snapshot_write_next(struct snapshot_handle *handle)
 {
 	static struct chain_allocator ca;
@@ -2491,6 +2576,8 @@ int snapshot_write_next(struct snapshot_handle *handle)
 		if (error)
 			return error;
 
+		safe_pages_list = NULL;
+
 		error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
 		if (error)
 			return error;
@@ -2500,6 +2587,7 @@ int snapshot_write_next(struct snapshot_handle *handle)
 		if (error)
 			return error;
 
+		hibernate_restore_protection_begin();
 	} else if (handle->cur <= nr_meta_pages + 1) {
 		error = unpack_orig_pfns(buffer, &copy_bm);
 		if (error)
@@ -2522,6 +2610,7 @@ int snapshot_write_next(struct snapshot_handle *handle)
 		copy_last_highmem_page();
 		/* Restore page key for data page (s390 only). */
 		page_key_write(handle->buffer);
+		hibernate_restore_protect_page(handle->buffer);
 		handle->buffer = get_buffer(&orig_bm, &ca);
 		if (IS_ERR(handle->buffer))
 			return PTR_ERR(handle->buffer);
@@ -2533,22 +2622,23 @@ int snapshot_write_next(struct snapshot_handle *handle)
 }
 
 /**
- *	snapshot_write_finalize - must be called after the last call to
- *	snapshot_write_next() in case the last page in the image happens
- *	to be a highmem page and its contents should be stored in the
- *	highmem.  Additionally, it releases the memory that will not be
- *	used any more.
+ * snapshot_write_finalize - Complete the loading of a hibernation image.
+ *
+ * Must be called after the last call to snapshot_write_next() in case the last
+ * page in the image happens to be a highmem page and its contents should be
+ * stored in highmem.  Additionally, it recycles bitmap memory that's not
+ * necessary any more.
  */
-
 void snapshot_write_finalize(struct snapshot_handle *handle)
 {
 	copy_last_highmem_page();
 	/* Restore page key for data page (s390 only). */
 	page_key_write(handle->buffer);
 	page_key_free();
-	/* Free only if we have loaded the image entirely */
+	hibernate_restore_protect_page(handle->buffer);
+	/* Do that only if we have loaded the image entirely */
 	if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) {
-		memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR);
+		memory_bm_recycle(&orig_bm);
 		free_highmem_data();
 	}
 }
@@ -2561,8 +2651,8 @@ int snapshot_image_loaded(struct snapshot_handle *handle)
 
 #ifdef CONFIG_HIGHMEM
 /* Assumes that @buf is ready and points to a "safe" page */
-static inline void
-swap_two_pages_data(struct page *p1, struct page *p2, void *buf)
+static inline void swap_two_pages_data(struct page *p1, struct page *p2,
+				       void *buf)
 {
 	void *kaddr1, *kaddr2;
 
@@ -2576,15 +2666,15 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf)
 }
 
 /**
- *	restore_highmem - for each highmem page that was allocated before
- *	the suspend and included in the suspend image, and also has been
- *	allocated by the "resume" kernel swap its current (ie. "before
- *	resume") contents with the previous (ie. "before suspend") one.
+ * restore_highmem - Put highmem image pages into their original locations.
+ *
+ * For each highmem page that was in use before hibernation and is included in
+ * the image, and also has been allocated by the "restore" kernel, swap its
+ * current contents with the previous (ie. "before hibernation") ones.
  *
- *	If the resume eventually fails, we can call this function once
- *	again and restore the "before resume" highmem state.
+ * If the restore eventually fails, we can call this function once again and
+ * restore the highmem state as seen by the restore kernel.
  */
-
 int restore_highmem(void)
 {
 	struct highmem_pbe *pbe = highmem_pblist;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 5b70d64b871e..0acab9d7f96f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -266,16 +266,18 @@ static int suspend_test(int level)
  */
 static int suspend_prepare(suspend_state_t state)
 {
-	int error;
+	int error, nr_calls = 0;
 
 	if (!sleep_state_supported(state))
 		return -EPERM;
 
 	pm_prepare_console();
 
-	error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
-	if (error)
+	error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
 		goto Finish;
+	}
 
 	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
@@ -286,7 +288,7 @@ static int suspend_prepare(suspend_state_t state)
 	suspend_stats.failed_freeze++;
 	dpm_save_failed_step(SUSPEND_FREEZE);
  Finish:
-	pm_notifier_call_chain(PM_POST_SUSPEND);
+	__pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL);
 	pm_restore_console();
 	return error;
 }
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 160e1006640d..a3b1e617bcdc 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -261,7 +261,7 @@ static void hib_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
-static int hib_submit_io(int rw, pgoff_t page_off, void *addr,
+static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr,
 		struct hib_bio_batch *hb)
 {
 	struct page *page = virt_to_page(addr);
@@ -271,6 +271,7 @@ static int hib_submit_io(int rw, pgoff_t page_off, void *addr,
 	bio = bio_alloc(__GFP_RECLAIM | __GFP_HIGH, 1);
 	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
 	bio->bi_bdev = hib_resume_bdev;
+	bio_set_op_attrs(bio, op, op_flags);
 
 	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
@@ -283,9 +284,9 @@ static int hib_submit_io(int rw, pgoff_t page_off, void *addr,
 		bio->bi_end_io = hib_end_io;
 		bio->bi_private = hb;
 		atomic_inc(&hb->count);
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	} else {
-		error = submit_bio_wait(rw, bio);
+		error = submit_bio_wait(bio);
 		bio_put(bio);
 	}
 
@@ -306,7 +307,8 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 {
 	int error;
 
-	hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL);
+	hib_submit_io(REQ_OP_READ, READ_SYNC, swsusp_resume_block,
+		      swsusp_header, NULL);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
@@ -315,8 +317,8 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 		swsusp_header->flags = flags;
 		if (flags & SF_CRC32_MODE)
 			swsusp_header->crc32 = handle->crc32;
-		error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
-					swsusp_header, NULL);
+		error = hib_submit_io(REQ_OP_WRITE, WRITE_SYNC,
+				      swsusp_resume_block, swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Swap header not found!\n");
 		error = -ENODEV;
@@ -348,6 +350,12 @@ static int swsusp_swap_check(void)
 	if (res < 0)
 		blkdev_put(hib_resume_bdev, FMODE_WRITE);
 
+	/*
+	 * Update the resume device to the one actually used,
+	 * so the test_resume mode can use it in case it is
+	 * invoked from hibernate() to test the snapshot.
+	 */
+	swsusp_resume_device = hib_resume_bdev->bd_dev;
 	return res;
 }
 
@@ -389,7 +397,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
 	} else {
 		src = buf;
 	}
-	return hib_submit_io(WRITE_SYNC, offset, src, hb);
+	return hib_submit_io(REQ_OP_WRITE, WRITE_SYNC, offset, src, hb);
 }
 
 static void release_swap_writer(struct swap_map_handle *handle)
@@ -992,7 +1000,8 @@ static int get_swap_reader(struct swap_map_handle *handle,
 			return -ENOMEM;
 		}
 
-		error = hib_submit_io(READ_SYNC, offset, tmp->map, NULL);
+		error = hib_submit_io(REQ_OP_READ, READ_SYNC, offset,
+				      tmp->map, NULL);
 		if (error) {
 			release_swap_reader(handle);
 			return error;
@@ -1016,7 +1025,7 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = hib_submit_io(READ_SYNC, offset, buf, hb);
+	error = hib_submit_io(REQ_OP_READ, READ_SYNC, offset, buf, hb);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
@@ -1525,7 +1534,8 @@ int swsusp_check(void)
 	if (!IS_ERR(hib_resume_bdev)) {
 		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		clear_page(swsusp_header);
-		error = hib_submit_io(READ_SYNC, swsusp_resume_block,
+		error = hib_submit_io(REQ_OP_READ, READ_SYNC,
+					swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
 			goto put;
@@ -1533,7 +1543,8 @@ int swsusp_check(void)
 		if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
-			error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
+			error = hib_submit_io(REQ_OP_WRITE, WRITE_SYNC,
+						swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
 			error = -EINVAL;
@@ -1577,10 +1588,12 @@ int swsusp_unmark(void)
 {
 	int error;
 
-	hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL);
+	hib_submit_io(REQ_OP_READ, READ_SYNC, swsusp_resume_block,
+		      swsusp_header, NULL);
 	if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10);
-		error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
+		error = hib_submit_io(REQ_OP_WRITE, WRITE_SYNC,
+					swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Cannot find swsusp signature!\n");
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 526e8911460a..35310b627388 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -47,7 +47,7 @@ atomic_t snapshot_device_available = ATOMIC_INIT(1);
 static int snapshot_open(struct inode *inode, struct file *filp)
 {
 	struct snapshot_data *data;
-	int error;
+	int error, nr_calls = 0;
 
 	if (!hibernation_available())
 		return -EPERM;
@@ -74,9 +74,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
 		data->free_bitmaps = false;
-		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+		error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
 		if (error)
-			pm_notifier_call_chain(PM_POST_HIBERNATION);
+			__pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL);
 	} else {
 		/*
 		 * Resuming.  We may need to wait for the image device to
@@ -86,13 +86,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 
 		data->swap = -1;
 		data->mode = O_WRONLY;
-		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+		error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
 		if (!error) {
 			error = create_basic_memory_bitmaps();
 			data->free_bitmaps = !error;
-		}
+		} else
+			nr_calls--;
+
 		if (error)
-			pm_notifier_call_chain(PM_POST_RESTORE);
+			__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	}
 	if (error)
 		atomic_inc(&snapshot_device_available);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 14c4aa25cc45..a84641b222c1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -47,6 +47,8 @@ struct sugov_cpu {
 	struct update_util_data update_util;
 	struct sugov_policy *sg_policy;
 
+	unsigned int cached_raw_freq;
+
 	/* The fields below are only needed when sharing a policy. */
 	unsigned long util;
 	unsigned long max;
@@ -106,7 +108,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
 
 /**
  * get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @policy: cpufreq policy object to compute the new frequency for.
+ * @sg_cpu: schedutil cpu object to compute the new frequency for.
  * @util: Current CPU utilization.
  * @max: CPU capacity.
  *
@@ -121,14 +123,25 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
  * next_freq = C * curr_freq * util_raw / max
  *
  * Take C = 1.25 for the frequency tipping point at (util / max) = 0.8.
+ *
+ * The lowest driver-supported frequency which is equal or greater than the raw
+ * next_freq (as calculated above) is returned, subject to policy min/max and
+ * cpufreq driver limitations.
  */
-static unsigned int get_next_freq(struct cpufreq_policy *policy,
-				  unsigned long util, unsigned long max)
+static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
+				  unsigned long max)
 {
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	struct cpufreq_policy *policy = sg_policy->policy;
 	unsigned int freq = arch_scale_freq_invariant() ?
 				policy->cpuinfo.max_freq : policy->cur;
 
-	return (freq + (freq >> 2)) * util / max;
+	freq = (freq + (freq >> 2)) * util / max;
+
+	if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+		return sg_policy->next_freq;
+	sg_cpu->cached_raw_freq = freq;
+	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
 static void sugov_update_single(struct update_util_data *hook, u64 time,
@@ -143,13 +156,14 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 		return;
 
 	next_f = util == ULONG_MAX ? policy->cpuinfo.max_freq :
-			get_next_freq(policy, util, max);
+			get_next_freq(sg_cpu, util, max);
 	sugov_update_commit(sg_policy, time, next_f);
 }
 
-static unsigned int sugov_next_freq_shared(struct sugov_policy *sg_policy,
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 					   unsigned long util, unsigned long max)
 {
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
 	unsigned int max_f = policy->cpuinfo.max_freq;
 	u64 last_freq_update_time = sg_policy->last_freq_update_time;
@@ -189,7 +203,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_policy *sg_policy,
 		}
 	}
 
-	return get_next_freq(policy, util, max);
+	return get_next_freq(sg_cpu, util, max);
 }
 
 static void sugov_update_shared(struct update_util_data *hook, u64 time,
@@ -206,7 +220,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
 	sg_cpu->last_update = time;
 
 	if (sugov_should_update_freq(sg_policy, time)) {
-		next_f = sugov_next_freq_shared(sg_policy, util, max);
+		next_f = sugov_next_freq_shared(sg_cpu, util, max);
 		sugov_update_commit(sg_policy, time, next_f);
 	}
 
@@ -394,7 +408,7 @@ static int sugov_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
-static int sugov_exit(struct cpufreq_policy *policy)
+static void sugov_exit(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
 	struct sugov_tunables *tunables = sg_policy->tunables;
@@ -412,7 +426,6 @@ static int sugov_exit(struct cpufreq_policy *policy)
 	mutex_unlock(&global_tunables_lock);
 
 	sugov_policy_free(sg_policy);
-	return 0;
 }
 
 static int sugov_start(struct cpufreq_policy *policy)
@@ -434,6 +447,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 			sg_cpu->util = ULONG_MAX;
 			sg_cpu->max = 0;
 			sg_cpu->last_update = 0;
+			sg_cpu->cached_raw_freq = 0;
 			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
 						     sugov_update_shared);
 		} else {
@@ -444,7 +458,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static int sugov_stop(struct cpufreq_policy *policy)
+static void sugov_stop(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
 	unsigned int cpu;
@@ -456,53 +470,29 @@ static int sugov_stop(struct cpufreq_policy *policy)
 
 	irq_work_sync(&sg_policy->irq_work);
 	cancel_work_sync(&sg_policy->work);
-	return 0;
 }
 
-static int sugov_limits(struct cpufreq_policy *policy)
+static void sugov_limits(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
 
 	if (!policy->fast_switch_enabled) {
 		mutex_lock(&sg_policy->work_lock);
-
-		if (policy->max < policy->cur)
-			__cpufreq_driver_target(policy, policy->max,
-						CPUFREQ_RELATION_H);
-		else if (policy->min > policy->cur)
-			__cpufreq_driver_target(policy, policy->min,
-						CPUFREQ_RELATION_L);
-
+		cpufreq_policy_apply_limits(policy);
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
 	sg_policy->need_freq_update = true;
-	return 0;
-}
-
-int sugov_governor(struct cpufreq_policy *policy, unsigned int event)
-{
-	if (event == CPUFREQ_GOV_POLICY_INIT) {
-		return sugov_init(policy);
-	} else if (policy->governor_data) {
-		switch (event) {
-		case CPUFREQ_GOV_POLICY_EXIT:
-			return sugov_exit(policy);
-		case CPUFREQ_GOV_START:
-			return sugov_start(policy);
-		case CPUFREQ_GOV_STOP:
-			return sugov_stop(policy);
-		case CPUFREQ_GOV_LIMITS:
-			return sugov_limits(policy);
-		}
-	}
-	return -EINVAL;
 }
 
 static struct cpufreq_governor schedutil_gov = {
 	.name = "schedutil",
-	.governor = sugov_governor,
 	.owner = THIS_MODULE,
+	.init = sugov_init,
+	.exit = sugov_exit,
+	.start = sugov_start,
+	.stop = sugov_stop,
+	.limits = sugov_limits,
 };
 
 static int __init sugov_module_init(void)
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9aef8654e90d..fb345cd11883 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -127,12 +127,13 @@ static void trace_note_tsk(struct task_struct *tsk)
 
 static void trace_note_time(struct blk_trace *bt)
 {
-	struct timespec now;
+	struct timespec64 now;
 	unsigned long flags;
 	u32 words[2];
 
-	getnstimeofday(&now);
-	words[0] = now.tv_sec;
+	/* need to check user space to see if this breaks in y2038 or y2106 */
+	ktime_get_real_ts64(&now);
+	words[0] = (u32)now.tv_sec;
 	words[1] = now.tv_nsec;
 
 	local_irq_save(flags);
@@ -189,6 +190,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
 				 BLK_TC_ACT(BLK_TC_WRITE) };
 
 #define BLK_TC_RAHEAD		BLK_TC_AHEAD
+#define BLK_TC_PREFLUSH		BLK_TC_FLUSH
 
 /* The ilog2() calls fall out because they're constant */
 #define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
@@ -199,7 +201,8 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
  * blk_io_trace structure and places it in a per-cpu subbuffer.
  */
 static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
-		     int rw, u32 what, int error, int pdu_len, void *pdu_data)
+		     int op, int op_flags, u32 what, int error, int pdu_len,
+		     void *pdu_data)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
@@ -214,13 +217,16 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
 
-	what |= ddir_act[rw & WRITE];
-	what |= MASK_TC_BIT(rw, SYNC);
-	what |= MASK_TC_BIT(rw, RAHEAD);
-	what |= MASK_TC_BIT(rw, META);
-	what |= MASK_TC_BIT(rw, DISCARD);
-	what |= MASK_TC_BIT(rw, FLUSH);
-	what |= MASK_TC_BIT(rw, FUA);
+	what |= ddir_act[op_is_write(op) ? WRITE : READ];
+	what |= MASK_TC_BIT(op_flags, SYNC);
+	what |= MASK_TC_BIT(op_flags, RAHEAD);
+	what |= MASK_TC_BIT(op_flags, META);
+	what |= MASK_TC_BIT(op_flags, PREFLUSH);
+	what |= MASK_TC_BIT(op_flags, FUA);
+	if (op == REQ_OP_DISCARD)
+		what |= BLK_TC_ACT(BLK_TC_DISCARD);
+	if (op == REQ_OP_FLUSH)
+		what |= BLK_TC_ACT(BLK_TC_FLUSH);
 
 	pid = tsk->pid;
 	if (act_log_check(bt, what, sector, pid))
@@ -708,11 +714,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
+		__blk_add_trace(bt, 0, nr_bytes, req_op(rq), rq->cmd_flags,
 				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
+		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, req_op(rq),
 				rq->cmd_flags, what, rq->errors, 0, NULL);
 	}
 }
@@ -770,7 +776,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 		return;
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio->bi_rw, what, error, 0, NULL);
+			bio_op(bio), bio->bi_rw, what, error, 0, NULL);
 }
 
 static void blk_add_trace_bio_bounce(void *ignore,
@@ -818,7 +824,8 @@ static void blk_add_trace_getrq(void *ignore,
 		struct blk_trace *bt = q->blk_trace;
 
 		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0, NULL);
+			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
+					NULL);
 	}
 }
 
@@ -833,7 +840,7 @@ static void blk_add_trace_sleeprq(void *ignore,
 		struct blk_trace *bt = q->blk_trace;
 
 		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ,
+			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
 					0, 0, NULL);
 	}
 }
@@ -843,7 +850,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 	struct blk_trace *bt = q->blk_trace;
 
 	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
+		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
 }
 
 static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
@@ -860,7 +867,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 		else
 			what = BLK_TA_UNPLUG_TIMER;
 
-		__blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
+		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
 	}
 }
 
@@ -874,8 +881,9 @@ static void blk_add_trace_split(void *ignore,
 		__be64 rpdu = cpu_to_be64(pdu);
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
-				bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT,
-				bio->bi_error, sizeof(rpdu), &rpdu);
+				bio->bi_iter.bi_size, bio_op(bio), bio->bi_rw,
+				BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu),
+				&rpdu);
 	}
 }
 
@@ -907,7 +915,7 @@ static void blk_add_trace_bio_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio->bi_rw, BLK_TA_REMAP, bio->bi_error,
+			bio_op(bio), bio->bi_rw, BLK_TA_REMAP, bio->bi_error,
 			sizeof(r), &r);
 }
 
@@ -940,7 +948,7 @@ static void blk_add_trace_rq_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-			rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
+			rq_data_dir(rq), 0, BLK_TA_REMAP, !!rq->errors,
 			sizeof(r), &r);
 }
 
@@ -965,10 +973,10 @@ void blk_add_driver_data(struct request_queue *q,
 		return;
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), 0,
+		__blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, rq->errors, len, data);
 	else
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0,
+		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, rq->errors, len, data);
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
@@ -1769,21 +1777,34 @@ void blk_dump_cmd(char *buf, struct request *rq)
 	}
 }
 
-void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
+void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes)
 {
 	int i = 0;
 
-	if (rw & REQ_FLUSH)
+	if (rw & REQ_PREFLUSH)
 		rwbs[i++] = 'F';
 
-	if (rw & WRITE)
+	switch (op) {
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_SAME:
 		rwbs[i++] = 'W';
-	else if (rw & REQ_DISCARD)
+		break;
+	case REQ_OP_DISCARD:
+		rwbs[i++] = 'D';
+		break;
+	case REQ_OP_SECURE_ERASE:
 		rwbs[i++] = 'D';
-	else if (bytes)
+		rwbs[i++] = 'E';
+		break;
+	case REQ_OP_FLUSH:
+		rwbs[i++] = 'F';
+		break;
+	case REQ_OP_READ:
 		rwbs[i++] = 'R';
-	else
+		break;
+	default:
 		rwbs[i++] = 'N';
+	}
 
 	if (rw & REQ_FUA)
 		rwbs[i++] = 'F';
@@ -1793,8 +1814,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 		rwbs[i++] = 'S';
 	if (rw & REQ_META)
 		rwbs[i++] = 'M';
-	if (rw & REQ_SECURE)
-		rwbs[i++] = 'E';
 
 	rwbs[i] = '\0';
 }
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 97e7b793df35..d12bd958077e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4369,8 +4369,8 @@ static void show_pwq(struct pool_workqueue *pwq)
 /**
  * show_workqueue_state - dump workqueue state
  *
- * Called from a sysrq handler and prints out all busy workqueues and
- * pools.
+ * Called from a sysrq handler or try_to_freeze_tasks() and prints out
+ * all busy workqueues and pools.
  */
 void show_workqueue_state(void)
 {
diff --git a/lib/digsig.c b/lib/digsig.c
index 07be6c1ef4e2..55b8b2f41a9e 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -104,21 +104,25 @@ static int digsig_verify_rsa(struct key *key,
 	datap = pkh->mpi;
 	endp = ukp->data + ukp->datalen;
 
-	err = -ENOMEM;
-
 	for (i = 0; i < pkh->nmpi; i++) {
 		unsigned int remaining = endp - datap;
 		pkey[i] = mpi_read_from_buffer(datap, &remaining);
-		if (!pkey[i])
+		if (IS_ERR(pkey[i])) {
+			err = PTR_ERR(pkey[i]);
 			goto err;
+		}
 		datap += remaining;
 	}
 
 	mblen = mpi_get_nbits(pkey[0]);
 	mlen = DIV_ROUND_UP(mblen, 8);
 
-	if (mlen == 0)
+	if (mlen == 0) {
+		err = -EINVAL;
 		goto err;
+	}
+
+	err = -ENOMEM;
 
 	out1 = kzalloc(mlen, GFP_KERNEL);
 	if (!out1)
@@ -126,8 +130,10 @@ static int digsig_verify_rsa(struct key *key,
 
 	nret = siglen;
 	in = mpi_read_from_buffer(sig, &nret);
-	if (!in)
+	if (IS_ERR(in)) {
+		err = PTR_ERR(in);
 		goto err;
+	}
 
 	res = mpi_alloc(mpi_get_nlimbs(in) * 2);
 	if (!res)
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 0cd522753ff5..d67c8288d95d 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -56,37 +56,24 @@
 	n = wanted;					\
 }
 
-#define iterate_bvec(i, n, __v, __p, skip, STEP) {	\
-	size_t wanted = n;				\
-	__p = i->bvec;					\
-	__v.bv_len = min_t(size_t, n, __p->bv_len - skip);	\
-	if (likely(__v.bv_len)) {			\
-		__v.bv_page = __p->bv_page;		\
-		__v.bv_offset = __p->bv_offset + skip; 	\
-		(void)(STEP);				\
-		skip += __v.bv_len;			\
-		n -= __v.bv_len;			\
-	}						\
-	while (unlikely(n)) {				\
-		__p++;					\
-		__v.bv_len = min_t(size_t, n, __p->bv_len);	\
-		if (unlikely(!__v.bv_len))		\
+#define iterate_bvec(i, n, __v, __bi, skip, STEP) {	\
+	struct bvec_iter __start;			\
+	__start.bi_size = n;				\
+	__start.bi_bvec_done = skip;			\
+	__start.bi_idx = 0;				\
+	for_each_bvec(__v, i->bvec, __bi, __start) {	\
+		if (!__v.bv_len)			\
 			continue;			\
-		__v.bv_page = __p->bv_page;		\
-		__v.bv_offset = __p->bv_offset;		\
 		(void)(STEP);				\
-		skip = __v.bv_len;			\
-		n -= __v.bv_len;			\
 	}						\
-	n = wanted;					\
 }
 
 #define iterate_all_kinds(i, n, v, I, B, K) {			\
 	size_t skip = i->iov_offset;				\
 	if (unlikely(i->type & ITER_BVEC)) {			\
-		const struct bio_vec *bvec;			\
 		struct bio_vec v;				\
-		iterate_bvec(i, n, v, bvec, skip, (B))		\
+		struct bvec_iter __bi;				\
+		iterate_bvec(i, n, v, __bi, skip, (B))		\
 	} else if (unlikely(i->type & ITER_KVEC)) {		\
 		const struct kvec *kvec;			\
 		struct kvec v;					\
@@ -104,15 +91,13 @@
 	if (i->count) {						\
 		size_t skip = i->iov_offset;			\
 		if (unlikely(i->type & ITER_BVEC)) {		\
-			const struct bio_vec *bvec;		\
+			const struct bio_vec *bvec = i->bvec;	\
 			struct bio_vec v;			\
-			iterate_bvec(i, n, v, bvec, skip, (B))	\
-			if (skip == bvec->bv_len) {		\
-				bvec++;				\
-				skip = 0;			\
-			}					\
-			i->nr_segs -= bvec - i->bvec;		\
-			i->bvec = bvec;				\
+			struct bvec_iter __bi;			\
+			iterate_bvec(i, n, v, __bi, skip, (B))	\
+			i->bvec = __bvec_iter_bvec(i->bvec, __bi);	\
+			i->nr_segs -= i->bvec - bvec;		\
+			skip = __bi.bi_bvec_done;		\
 		} else if (unlikely(i->type & ITER_KVEC)) {	\
 			const struct kvec *kvec;		\
 			struct kvec v;				\
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 747606f9e4a3..c6272ae2015e 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -21,6 +21,7 @@
 #include <linux/bitops.h>
 #include <linux/count_zeros.h>
 #include <linux/byteorder/generic.h>
+#include <linux/scatterlist.h>
 #include <linux/string.h>
 #include "mpi-internal.h"
 
@@ -50,9 +51,7 @@ MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes)
 		return NULL;
 	}
 	if (nbytes > 0)
-		nbits -= count_leading_zeros(buffer[0]);
-	else
-		nbits = 0;
+		nbits -= count_leading_zeros(buffer[0]) - (BITS_PER_LONG - 8);
 
 	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
 	val = mpi_alloc(nlimbs);
@@ -82,50 +81,30 @@ EXPORT_SYMBOL_GPL(mpi_read_raw_data);
 MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread)
 {
 	const uint8_t *buffer = xbuffer;
-	int i, j;
-	unsigned nbits, nbytes, nlimbs, nread = 0;
-	mpi_limb_t a;
-	MPI val = NULL;
+	unsigned int nbits, nbytes;
+	MPI val;
 
 	if (*ret_nread < 2)
-		goto leave;
+		return ERR_PTR(-EINVAL);
 	nbits = buffer[0] << 8 | buffer[1];
 
 	if (nbits > MAX_EXTERN_MPI_BITS) {
 		pr_info("MPI: mpi too large (%u bits)\n", nbits);
-		goto leave;
+		return ERR_PTR(-EINVAL);
 	}
-	buffer += 2;
-	nread = 2;
 
 	nbytes = DIV_ROUND_UP(nbits, 8);
-	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
-	val = mpi_alloc(nlimbs);
-	if (!val)
-		return NULL;
-	i = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB;
-	i %= BYTES_PER_MPI_LIMB;
-	val->nbits = nbits;
-	j = val->nlimbs = nlimbs;
-	val->sign = 0;
-	for (; j > 0; j--) {
-		a = 0;
-		for (; i < BYTES_PER_MPI_LIMB; i++) {
-			if (++nread > *ret_nread) {
-				printk
-				    ("MPI: mpi larger than buffer nread=%d ret_nread=%d\n",
-				     nread, *ret_nread);
-				goto leave;
-			}
-			a <<= 8;
-			a |= *buffer++;
-		}
-		i = 0;
-		val->d[j - 1] = a;
+	if (nbytes + 2 > *ret_nread) {
+		pr_info("MPI: mpi larger than buffer nbytes=%u ret_nread=%u\n",
+				nbytes, *ret_nread);
+		return ERR_PTR(-EINVAL);
 	}
 
-leave:
-	*ret_nread = nread;
+	val = mpi_read_raw_data(buffer + 2, nbytes);
+	if (!val)
+		return ERR_PTR(-ENOMEM);
+
+	*ret_nread = nbytes + 2;
 	return val;
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
@@ -250,82 +229,6 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 }
 EXPORT_SYMBOL_GPL(mpi_get_buffer);
 
-/****************
- * Use BUFFER to update MPI.
- */
-int mpi_set_buffer(MPI a, const void *xbuffer, unsigned nbytes, int sign)
-{
-	const uint8_t *buffer = xbuffer, *p;
-	mpi_limb_t alimb;
-	int nlimbs;
-	int i;
-
-	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
-	if (RESIZE_IF_NEEDED(a, nlimbs) < 0)
-		return -ENOMEM;
-	a->sign = sign;
-
-	for (i = 0, p = buffer + nbytes - 1; p >= buffer + BYTES_PER_MPI_LIMB;) {
-#if BYTES_PER_MPI_LIMB == 4
-		alimb = (mpi_limb_t) *p--;
-		alimb |= (mpi_limb_t) *p-- << 8;
-		alimb |= (mpi_limb_t) *p-- << 16;
-		alimb |= (mpi_limb_t) *p-- << 24;
-#elif BYTES_PER_MPI_LIMB == 8
-		alimb = (mpi_limb_t) *p--;
-		alimb |= (mpi_limb_t) *p-- << 8;
-		alimb |= (mpi_limb_t) *p-- << 16;
-		alimb |= (mpi_limb_t) *p-- << 24;
-		alimb |= (mpi_limb_t) *p-- << 32;
-		alimb |= (mpi_limb_t) *p-- << 40;
-		alimb |= (mpi_limb_t) *p-- << 48;
-		alimb |= (mpi_limb_t) *p-- << 56;
-#else
-#error please implement for this limb size.
-#endif
-		a->d[i++] = alimb;
-	}
-	if (p >= buffer) {
-#if BYTES_PER_MPI_LIMB == 4
-		alimb = *p--;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 8;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 16;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 24;
-#elif BYTES_PER_MPI_LIMB == 8
-		alimb = (mpi_limb_t) *p--;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 8;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 16;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 24;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 32;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 40;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 48;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 56;
-#else
-#error please implement for this limb size.
-#endif
-		a->d[i++] = alimb;
-	}
-	a->nlimbs = i;
-
-	if (i != nlimbs) {
-		pr_emerg("MPI: mpi_set_buffer: Assertion failed (%d != %d)", i,
-		       nlimbs);
-		BUG();
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mpi_set_buffer);
-
 /**
  * mpi_write_to_sgl() - Funnction exports MPI to an sgl (msb first)
  *
@@ -335,16 +238,13 @@ EXPORT_SYMBOL_GPL(mpi_set_buffer);
  * @a:		a multi precision integer
  * @sgl:	scatterlist to write to. Needs to be at least
  *		mpi_get_size(a) long.
- * @nbytes:	in/out param - it has the be set to the maximum number of
- *		bytes that can be written to sgl. This has to be at least
- *		the size of the integer a. On return it receives the actual
- *		length of the data written on success or the data that would
- *		be written if buffer was too small.
+ * @nbytes:	the number of bytes to write.  Leading bytes will be
+ *		filled with zero.
  * @sign:	if not NULL, it will be set to the sign of a.
  *
  * Return:	0 on success or error code in case of error
  */
-int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
+int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned nbytes,
 		     int *sign)
 {
 	u8 *p, *p2;
@@ -356,55 +256,60 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 #error please implement for this limb size.
 #endif
 	unsigned int n = mpi_get_size(a);
-	int i, x, y = 0, lzeros, buf_len;
-
-	if (!nbytes)
-		return -EINVAL;
+	struct sg_mapping_iter miter;
+	int i, x, buf_len;
+	int nents;
 
 	if (sign)
 		*sign = a->sign;
 
-	lzeros = count_lzeros(a);
-
-	if (*nbytes < n - lzeros) {
-		*nbytes = n - lzeros;
+	if (nbytes < n)
 		return -EOVERFLOW;
-	}
 
-	*nbytes = n - lzeros;
-	buf_len = sgl->length;
-	p2 = sg_virt(sgl);
+	nents = sg_nents_for_len(sgl, nbytes);
+	if (nents < 0)
+		return -EINVAL;
 
-	for (i = a->nlimbs - 1 - lzeros / BYTES_PER_MPI_LIMB,
-			lzeros %= BYTES_PER_MPI_LIMB;
-		i >= 0; i--) {
+	sg_miter_start(&miter, sgl, nents, SG_MITER_ATOMIC | SG_MITER_TO_SG);
+	sg_miter_next(&miter);
+	buf_len = miter.length;
+	p2 = miter.addr;
+
+	while (nbytes > n) {
+		i = min_t(unsigned, nbytes - n, buf_len);
+		memset(p2, 0, i);
+		p2 += i;
+		nbytes -= i;
+
+		buf_len -= i;
+		if (!buf_len) {
+			sg_miter_next(&miter);
+			buf_len = miter.length;
+			p2 = miter.addr;
+		}
+	}
+
+	for (i = a->nlimbs - 1; i >= 0; i--) {
 #if BYTES_PER_MPI_LIMB == 4
-		alimb = cpu_to_be32(a->d[i]);
+		alimb = a->d[i] ? cpu_to_be32(a->d[i]) : 0;
 #elif BYTES_PER_MPI_LIMB == 8
-		alimb = cpu_to_be64(a->d[i]);
+		alimb = a->d[i] ? cpu_to_be64(a->d[i]) : 0;
 #else
 #error please implement for this limb size.
 #endif
-		if (lzeros) {
-			y = lzeros;
-			lzeros = 0;
-		}
+		p = (u8 *)&alimb;
 
-		p = (u8 *)&alimb + y;
-
-		for (x = 0; x < sizeof(alimb) - y; x++) {
-			if (!buf_len) {
-				sgl = sg_next(sgl);
-				if (!sgl)
-					return -EINVAL;
-				buf_len = sgl->length;
-				p2 = sg_virt(sgl);
-			}
+		for (x = 0; x < sizeof(alimb); x++) {
 			*p2++ = *p++;
-			buf_len--;
+			if (!--buf_len) {
+				sg_miter_next(&miter);
+				buf_len = miter.length;
+				p2 = miter.addr;
+			}
 		}
-		y = 0;
 	}
+
+	sg_miter_stop(&miter);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mpi_write_to_sgl);
@@ -424,19 +329,23 @@ EXPORT_SYMBOL_GPL(mpi_write_to_sgl);
  */
 MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 {
-	struct scatterlist *sg;
-	int x, i, j, z, lzeros, ents;
+	struct sg_mapping_iter miter;
 	unsigned int nbits, nlimbs;
+	int x, j, z, lzeros, ents;
+	unsigned int len;
+	const u8 *buff;
 	mpi_limb_t a;
 	MPI val = NULL;
 
-	lzeros = 0;
-	ents = sg_nents(sgl);
+	ents = sg_nents_for_len(sgl, nbytes);
+	if (ents < 0)
+		return NULL;
 
-	for_each_sg(sgl, sg, ents, i) {
-		const u8 *buff = sg_virt(sg);
-		int len = sg->length;
+	sg_miter_start(&miter, sgl, ents, SG_MITER_ATOMIC | SG_MITER_FROM_SG);
 
+	lzeros = 0;
+	len = 0;
+	while (nbytes > 0) {
 		while (len && !*buff) {
 			lzeros++;
 			len--;
@@ -446,12 +355,14 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 		if (len && *buff)
 			break;
 
-		ents--;
+		sg_miter_next(&miter);
+		buff = miter.addr;
+		len = miter.length;
+
 		nbytes -= lzeros;
 		lzeros = 0;
 	}
 
-	sgl = sg;
 	nbytes -= lzeros;
 	nbits = nbytes * 8;
 	if (nbits > MAX_EXTERN_MPI_BITS) {
@@ -460,8 +371,7 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 	}
 
 	if (nbytes > 0)
-		nbits -= count_leading_zeros(*(u8 *)(sg_virt(sgl) + lzeros)) -
-			(BITS_PER_LONG - 8);
+		nbits -= count_leading_zeros(*buff) - (BITS_PER_LONG - 8);
 
 	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
 	val = mpi_alloc(nlimbs);
@@ -480,21 +390,24 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 	z = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB;
 	z %= BYTES_PER_MPI_LIMB;
 
-	for_each_sg(sgl, sg, ents, i) {
-		const u8 *buffer = sg_virt(sg) + lzeros;
-		int len = sg->length - lzeros;
-
+	for (;;) {
 		for (x = 0; x < len; x++) {
 			a <<= 8;
-			a |= *buffer++;
+			a |= *buff++;
 			if (((z + x + 1) % BYTES_PER_MPI_LIMB) == 0) {
 				val->d[j--] = a;
 				a = 0;
 			}
 		}
 		z += x;
-		lzeros = 0;
+
+		if (!sg_miter_next(&miter))
+			break;
+
+		buff = miter.addr;
+		len = miter.length;
 	}
+
 	return val;
 }
 EXPORT_SYMBOL_GPL(mpi_read_raw_from_sgl);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a9a8c313d133..abc1c5fb7222 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1022,7 +1022,9 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 		((node = hstate_next_node_to_free(hs, mask)) || 1);	\
 		nr_nodes--)
 
-#if defined(CONFIG_X86_64) && ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA))
+#if (defined(CONFIG_X86_64) || defined(CONFIG_S390)) && \
+	((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || \
+	defined(CONFIG_CMA))
 static void destroy_compound_gigantic_page(struct page *page,
 					unsigned int order)
 {
diff --git a/mm/page_io.c b/mm/page_io.c
index 242dba07545b..dcc5d3769608 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -259,7 +259,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		bio_end_io_t end_write_func)
 {
 	struct bio *bio;
-	int ret, rw = WRITE;
+	int ret;
 	struct swap_info_struct *sis = page_swap_info(page);
 
 	if (sis->flags & SWP_FILE) {
@@ -317,12 +317,13 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		ret = -ENOMEM;
 		goto out;
 	}
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		rw |= REQ_SYNC;
+		bio->bi_rw |= REQ_SYNC;
 	count_vm_event(PSWPOUT);
 	set_page_writeback(page);
 	unlock_page(page);
-	submit_bio(rw, bio);
+	submit_bio(bio);
 out:
 	return ret;
 }
@@ -369,8 +370,9 @@ int swap_readpage(struct page *page)
 		ret = -ENOMEM;
 		goto out;
 	}
+	bio_set_op_attrs(bio, REQ_OP_READ, 0);
 	count_vm_event(PSWPIN);
-	submit_bio(READ, bio);
+	submit_bio(bio);
 out:
 	return ret;
 }
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 7eaa000c9258..88a2a3ba4212 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -320,21 +320,29 @@ static union iucv_param *iucv_param_irq[NR_CPUS];
  *
  * Returns the result of the CP IUCV call.
  */
-static inline int iucv_call_b2f0(int command, union iucv_param *parm)
+static inline int __iucv_call_b2f0(int command, union iucv_param *parm)
 {
 	register unsigned long reg0 asm ("0");
 	register unsigned long reg1 asm ("1");
 	int ccode;
 
 	reg0 = command;
-	reg1 = virt_to_phys(parm);
+	reg1 = (unsigned long)parm;
 	asm volatile(
 		"	.long 0xb2f01000\n"
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
 		: "=d" (ccode), "=m" (*parm), "+d" (reg0), "+a" (reg1)
 		:  "m" (*parm) : "cc");
-	return (ccode == 1) ? parm->ctrl.iprcode : ccode;
+	return ccode;
+}
+
+static inline int iucv_call_b2f0(int command, union iucv_param *parm)
+{
+	int ccode;
+
+	ccode = __iucv_call_b2f0(command, parm);
+	return ccode == 1 ? parm->ctrl.iprcode : ccode;
 }
 
 /**
@@ -345,16 +353,12 @@ static inline int iucv_call_b2f0(int command, union iucv_param *parm)
  * Returns the maximum number of connections or -EPERM is IUCV is not
  * available.
  */
-static int iucv_query_maxconn(void)
+static int __iucv_query_maxconn(void *param, unsigned long *max_pathid)
 {
 	register unsigned long reg0 asm ("0");
 	register unsigned long reg1 asm ("1");
-	void *param;
 	int ccode;
 
-	param = kzalloc(sizeof(union iucv_param), GFP_KERNEL|GFP_DMA);
-	if (!param)
-		return -ENOMEM;
 	reg0 = IUCV_QUERY;
 	reg1 = (unsigned long) param;
 	asm volatile (
@@ -362,8 +366,22 @@ static int iucv_query_maxconn(void)
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
 		: "=d" (ccode), "+d" (reg0), "+d" (reg1) : : "cc");
+	*max_pathid = reg1;
+	return ccode;
+}
+
+static int iucv_query_maxconn(void)
+{
+	unsigned long max_pathid;
+	void *param;
+	int ccode;
+
+	param = kzalloc(sizeof(union iucv_param), GFP_KERNEL | GFP_DMA);
+	if (!param)
+		return -ENOMEM;
+	ccode = __iucv_query_maxconn(param, &max_pathid);
 	if (ccode == 0)
-		iucv_max_pathid = reg1;
+		iucv_max_pathid = max_pathid;
 	kfree(param);
 	return ccode ? -EPERM : 0;
 }
diff --git a/samples/v4l/v4l2-pci-skeleton.c b/samples/v4l/v4l2-pci-skeleton.c
index a55cf94ac907..93b76c3220fd 100644
--- a/samples/v4l/v4l2-pci-skeleton.c
+++ b/samples/v4l/v4l2-pci-skeleton.c
@@ -56,7 +56,6 @@ MODULE_LICENSE("GPL v2");
  * @format: current pix format
  * @input: current video input (0 = SDTV, 1 = HDTV)
  * @queue: vb2 video capture queue
- * @alloc_ctx: vb2 contiguous DMA context
  * @qlock: spinlock controlling access to buf_list and sequence
  * @buf_list: list of buffers queued for DMA
  * @sequence: frame sequence counter
@@ -73,7 +72,6 @@ struct skeleton {
 	unsigned input;
 
 	struct vb2_queue queue;
-	struct vb2_alloc_ctx *alloc_ctx;
 
 	spinlock_t qlock;
 	struct list_head buf_list;
@@ -165,7 +163,7 @@ static irqreturn_t skeleton_irq(int irq, void *dev_id)
  */
 static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
-		       unsigned int sizes[], void *alloc_ctxs[])
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct skeleton *skel = vb2_get_drv_priv(vq);
 
@@ -182,7 +180,6 @@ static int queue_setup(struct vb2_queue *vq,
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
-	alloc_ctxs[0] = skel->alloc_ctx;
 
 	if (*nplanes)
 		return sizes[0] < skel->format.sizeimage ? -EINVAL : 0;
@@ -820,6 +817,7 @@ static int skeleton_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	q = &skel->queue;
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
+	q->dev = &pdev->dev;
 	q->drv_priv = skel;
 	q->buf_struct_size = sizeof(struct skel_buffer);
 	q->ops = &skel_qops;
@@ -850,12 +848,6 @@ static int skeleton_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		goto free_hdl;
 
-	skel->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(skel->alloc_ctx)) {
-		dev_err(&pdev->dev, "Can't allocate buffer context");
-		ret = PTR_ERR(skel->alloc_ctx);
-		goto free_hdl;
-	}
 	INIT_LIST_HEAD(&skel->buf_list);
 	spin_lock_init(&skel->qlock);
 
@@ -885,13 +877,11 @@ static int skeleton_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
 	if (ret)
-		goto free_ctx;
+		goto free_hdl;
 
 	dev_info(&pdev->dev, "V4L2 PCI Skeleton Driver loaded\n");
 	return 0;
 
-free_ctx:
-	vb2_dma_contig_cleanup_ctx(skel->alloc_ctx);
 free_hdl:
 	v4l2_ctrl_handler_free(&skel->ctrl_handler);
 	v4l2_device_unregister(&skel->v4l2_dev);
@@ -907,7 +897,6 @@ static void skeleton_remove(struct pci_dev *pdev)
 
 	video_unregister_device(&skel->vdev);
 	v4l2_ctrl_handler_free(&skel->ctrl_handler);
-	vb2_dma_contig_cleanup_ctx(skel->alloc_ctx);
 	v4l2_device_unregister(&skel->v4l2_dev);
 	pci_disable_device(skel->pdev);
 }
diff --git a/scripts/analyze_suspend.py b/scripts/analyze_suspend.py
index 93e1fd40f430..a0ba48fa2c5e 100755
--- a/scripts/analyze_suspend.py
+++ b/scripts/analyze_suspend.py
@@ -19,6 +19,17 @@
 # Authors:
 #	 Todd Brandt <todd.e.brandt@linux.intel.com>
 #
+# Links:
+#	 Home Page
+#	   https://01.org/suspendresume
+#	 Source repo
+#	   https://github.com/01org/suspendresume
+#	 Documentation
+#	   Getting Started
+#	     https://01.org/suspendresume/documentation/getting-started
+#	   Command List:
+#	     https://01.org/suspendresume/documentation/command-list
+#
 # Description:
 #	 This tool is designed to assist kernel and OS developers in optimizing
 #	 their linux stack's suspend/resume time. Using a kernel image built
@@ -35,6 +46,8 @@
 #		 CONFIG_FTRACE=y
 #		 CONFIG_FUNCTION_TRACER=y
 #		 CONFIG_FUNCTION_GRAPH_TRACER=y
+#		 CONFIG_KPROBES=y
+#		 CONFIG_KPROBES_ON_FTRACE=y
 #
 #	 For kernel versions older than 3.15:
 #	 The following additional kernel parameters are required:
@@ -52,6 +65,7 @@ import re
 import platform
 from datetime import datetime
 import struct
+import ConfigParser
 
 # ----------------- CLASSES --------------------
 
@@ -60,8 +74,15 @@ import struct
 #	 A global, single-instance container used to
 #	 store system values and test parameters
 class SystemValues:
-	version = 3.0
+	ansi = False
+	version = '4.2'
 	verbose = False
+	addlogs = False
+	mindevlen = 0.001
+	mincglen = 1.0
+	srgap = 0
+	cgexp = False
+	outdir = ''
 	testdir = '.'
 	tpath = '/sys/kernel/debug/tracing/'
 	fpdtpath = '/sys/firmware/acpi/tables/FPDT'
@@ -71,26 +92,21 @@ class SystemValues:
 		'device_pm_callback_end',
 		'device_pm_callback_start'
 	]
-	modename = {
-		'freeze': 'Suspend-To-Idle (S0)',
-		'standby': 'Power-On Suspend (S1)',
-		'mem': 'Suspend-to-RAM (S3)',
-		'disk': 'Suspend-to-disk (S4)'
-	}
+	testcommand = ''
 	mempath = '/dev/mem'
 	powerfile = '/sys/power/state'
 	suspendmode = 'mem'
 	hostname = 'localhost'
 	prefix = 'test'
 	teststamp = ''
+	dmesgstart = 0.0
 	dmesgfile = ''
 	ftracefile = ''
 	htmlfile = ''
+	embedded = False
 	rtcwake = False
 	rtcwaketime = 10
 	rtcpath = ''
-	android = False
-	adb = 'adb'
 	devicefilter = []
 	stamp = 0
 	execcount = 1
@@ -98,16 +114,90 @@ class SystemValues:
 	usecallgraph = False
 	usetraceevents = False
 	usetraceeventsonly = False
+	usetracemarkers = True
+	usekprobes = True
+	usedevsrc = False
 	notestrun = False
-	altdevname = dict()
+	devprops = dict()
 	postresumetime = 0
+	devpropfmt = '# Device Properties: .*'
 	tracertypefmt = '# tracer: (?P<t>.*)'
 	firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$'
 	postresumefmt = '# post resume time (?P<t>[0-9]*)$'
 	stampfmt = '# suspend-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\
 				'(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\
 				' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$'
+	kprobecolor = 'rgba(204,204,204,0.5)'
+	synccolor = 'rgba(204,204,204,0.5)'
+	debugfuncs = []
+	tracefuncs = {
+		'sys_sync': dict(),
+		'pm_prepare_console': dict(),
+		'pm_notifier_call_chain': dict(),
+		'freeze_processes': dict(),
+		'freeze_kernel_threads': dict(),
+		'pm_restrict_gfp_mask': dict(),
+		'acpi_suspend_begin': dict(),
+		'suspend_console': dict(),
+		'acpi_pm_prepare': dict(),
+		'syscore_suspend': dict(),
+		'arch_enable_nonboot_cpus_end': dict(),
+		'syscore_resume': dict(),
+		'acpi_pm_finish': dict(),
+		'resume_console': dict(),
+		'acpi_pm_end': dict(),
+		'pm_restore_gfp_mask': dict(),
+		'thaw_processes': dict(),
+		'pm_restore_console': dict(),
+		'CPU_OFF': {
+			'func':'_cpu_down',
+			'args_x86_64': {'cpu':'%di:s32'},
+			'format': 'CPU_OFF[{cpu}]',
+			'mask': 'CPU_.*_DOWN'
+		},
+		'CPU_ON': {
+			'func':'_cpu_up',
+			'args_x86_64': {'cpu':'%di:s32'},
+			'format': 'CPU_ON[{cpu}]',
+			'mask': 'CPU_.*_UP'
+		},
+	}
+	dev_tracefuncs = {
+		# general wait/delay/sleep
+		'msleep': { 'args_x86_64': {'time':'%di:s32'} },
+		'udelay': { 'func':'__const_udelay', 'args_x86_64': {'loops':'%di:s32'} },
+		'acpi_os_stall': dict(),
+		# ACPI
+		'acpi_resume_power_resources': dict(),
+		'acpi_ps_parse_aml': dict(),
+		# filesystem
+		'ext4_sync_fs': dict(),
+		# ATA
+		'ata_eh_recover': { 'args_x86_64': {'port':'+36(%di):s32'} },
+		# i915
+		'i915_gem_restore_gtt_mappings': dict(),
+		'intel_opregion_setup': dict(),
+		'intel_dp_detect': dict(),
+		'intel_hdmi_detect': dict(),
+		'intel_opregion_init': dict(),
+	}
+	kprobes_postresume = [
+		{
+			'name': 'ataportrst',
+			'func': 'ata_eh_recover',
+			'args': {'port':'+36(%di):s32'},
+			'format': 'ata{port}_port_reset',
+			'mask': 'ata.*_port_reset'
+		}
+	]
+	kprobes = dict()
+	timeformat = '%.3f'
 	def __init__(self):
+		# if this is a phoronix test run, set some default options
+		if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ):
+			self.embedded = True
+			self.addlogs = True
+			self.htmlfile = os.environ['LOG_FILE']
 		self.hostname = platform.node()
 		if(self.hostname == ''):
 			self.hostname = 'localhost'
@@ -118,6 +208,12 @@ class SystemValues:
 		if os.path.exists(rtc) and os.path.exists(rtc+'/date') and \
 			os.path.exists(rtc+'/time') and os.path.exists(rtc+'/wakealarm'):
 			self.rtcpath = rtc
+		if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()):
+			self.ansi = True
+	def setPrecision(self, num):
+		if num < 0 or num > 6:
+			return
+		self.timeformat = '%.{0}f'.format(num)
 	def setOutputFile(self):
 		if((self.htmlfile == '') and (self.dmesgfile != '')):
 			m = re.match('(?P<name>.*)_dmesg\.txt$', self.dmesgfile)
@@ -129,32 +225,37 @@ class SystemValues:
 				self.htmlfile = m.group('name')+'.html'
 		if(self.htmlfile == ''):
 			self.htmlfile = 'output.html'
-	def initTestOutput(self, subdir):
-		if(not self.android):
-			self.prefix = self.hostname
-			v = open('/proc/version', 'r').read().strip()
-			kver = string.split(v)[2]
-		else:
-			self.prefix = 'android'
-			v = os.popen(self.adb+' shell cat /proc/version').read().strip()
-			kver = string.split(v)[2]
-		testtime = datetime.now().strftime('suspend-%m%d%y-%H%M%S')
+	def initTestOutput(self, subdir, testpath=''):
+		self.prefix = self.hostname
+		v = open('/proc/version', 'r').read().strip()
+		kver = string.split(v)[2]
+		n = datetime.now()
+		testtime = n.strftime('suspend-%m%d%y-%H%M%S')
+		if not testpath:
+			testpath = n.strftime('suspend-%y%m%d-%H%M%S')
 		if(subdir != "."):
-			self.testdir = subdir+"/"+testtime
+			self.testdir = subdir+"/"+testpath
 		else:
-			self.testdir = testtime
+			self.testdir = testpath
 		self.teststamp = \
 			'# '+testtime+' '+self.prefix+' '+self.suspendmode+' '+kver
+		if(self.embedded):
+			self.dmesgfile = \
+				'/tmp/'+testtime+'_'+self.suspendmode+'_dmesg.txt'
+			self.ftracefile = \
+				'/tmp/'+testtime+'_'+self.suspendmode+'_ftrace.txt'
+			return
 		self.dmesgfile = \
 			self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_dmesg.txt'
 		self.ftracefile = \
 			self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_ftrace.txt'
 		self.htmlfile = \
 			self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html'
-		os.mkdir(self.testdir)
+		if not os.path.isdir(self.testdir):
+			os.mkdir(self.testdir)
 	def setDeviceFilter(self, devnames):
 		self.devicefilter = string.split(devnames)
-	def rtcWakeAlarm(self):
+	def rtcWakeAlarmOn(self):
 		os.system('echo 0 > '+self.rtcpath+'/wakealarm')
 		outD = open(self.rtcpath+'/date', 'r').read().strip()
 		outT = open(self.rtcpath+'/time', 'r').read().strip()
@@ -172,9 +273,361 @@ class SystemValues:
 			nowtime = int(datetime.now().strftime('%s'))
 		alarm = nowtime + self.rtcwaketime
 		os.system('echo %d > %s/wakealarm' % (alarm, self.rtcpath))
+	def rtcWakeAlarmOff(self):
+		os.system('echo 0 > %s/wakealarm' % self.rtcpath)
+	def initdmesg(self):
+		# get the latest time stamp from the dmesg log
+		fp = os.popen('dmesg')
+		ktime = '0'
+		for line in fp:
+			line = line.replace('\r\n', '')
+			idx = line.find('[')
+			if idx > 1:
+				line = line[idx:]
+			m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
+			if(m):
+				ktime = m.group('ktime')
+		fp.close()
+		self.dmesgstart = float(ktime)
+	def getdmesg(self):
+		# store all new dmesg lines since initdmesg was called
+		fp = os.popen('dmesg')
+		op = open(self.dmesgfile, 'a')
+		for line in fp:
+			line = line.replace('\r\n', '')
+			idx = line.find('[')
+			if idx > 1:
+				line = line[idx:]
+			m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
+			if(not m):
+				continue
+			ktime = float(m.group('ktime'))
+			if ktime > self.dmesgstart:
+				op.write(line)
+		fp.close()
+		op.close()
+	def addFtraceFilterFunctions(self, file):
+		fp = open(file)
+		list = fp.read().split('\n')
+		fp.close()
+		for i in list:
+			if len(i) < 2:
+				continue
+			self.tracefuncs[i] = dict()
+	def getFtraceFilterFunctions(self, current):
+		rootCheck(True)
+		if not current:
+			os.system('cat '+self.tpath+'available_filter_functions')
+			return
+		fp = open(self.tpath+'available_filter_functions')
+		master = fp.read().split('\n')
+		fp.close()
+		if len(self.debugfuncs) > 0:
+			for i in self.debugfuncs:
+				if i in master:
+					print i
+				else:
+					print self.colorText(i)
+		else:
+			for i in self.tracefuncs:
+				if 'func' in self.tracefuncs[i]:
+					i = self.tracefuncs[i]['func']
+				if i in master:
+					print i
+				else:
+					print self.colorText(i)
+	def setFtraceFilterFunctions(self, list):
+		fp = open(self.tpath+'available_filter_functions')
+		master = fp.read().split('\n')
+		fp.close()
+		flist = ''
+		for i in list:
+			if i not in master:
+				continue
+			if ' [' in i:
+				flist += i.split(' ')[0]+'\n'
+			else:
+				flist += i+'\n'
+		fp = open(self.tpath+'set_graph_function', 'w')
+		fp.write(flist)
+		fp.close()
+	def kprobeMatch(self, name, target):
+		if name not in self.kprobes:
+			return False
+		if re.match(self.kprobes[name]['mask'], target):
+			return True
+		return False
+	def basicKprobe(self, name):
+		self.kprobes[name] = {'name': name,'func': name,'args': dict(),'format': name,'mask': name}
+	def defaultKprobe(self, name, kdata):
+		k = kdata
+		for field in ['name', 'format', 'mask', 'func']:
+			if field not in k:
+				k[field] = name
+		archargs = 'args_'+platform.machine()
+		if archargs in k:
+			k['args'] = k[archargs]
+		else:
+			k['args'] = dict()
+			k['format'] = name
+		self.kprobes[name] = k
+	def kprobeColor(self, name):
+		if name not in self.kprobes or 'color' not in self.kprobes[name]:
+			return ''
+		return self.kprobes[name]['color']
+	def kprobeDisplayName(self, name, dataraw):
+		if name not in self.kprobes:
+			self.basicKprobe(name)
+		data = ''
+		quote=0
+		# first remvoe any spaces inside quotes, and the quotes
+		for c in dataraw:
+			if c == '"':
+				quote = (quote + 1) % 2
+			if quote and c == ' ':
+				data += '_'
+			elif c != '"':
+				data += c
+		fmt, args = self.kprobes[name]['format'], self.kprobes[name]['args']
+		arglist = dict()
+		# now process the args
+		for arg in sorted(args):
+			arglist[arg] = ''
+			m = re.match('.* '+arg+'=(?P<arg>.*) ', data);
+			if m:
+				arglist[arg] = m.group('arg')
+			else:
+				m = re.match('.* '+arg+'=(?P<arg>.*)', data);
+				if m:
+					arglist[arg] = m.group('arg')
+		out = fmt.format(**arglist)
+		out = out.replace(' ', '_').replace('"', '')
+		return out
+	def kprobeText(self, kprobe):
+		name, fmt, func, args = kprobe['name'], kprobe['format'], kprobe['func'], kprobe['args']
+		if re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', func):
+			doError('Kprobe "%s" has format info in the function name "%s"' % (name, func), False)
+		for arg in re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', fmt):
+			if arg not in args:
+				doError('Kprobe "%s" is missing argument "%s"' % (name, arg), False)
+		val = 'p:%s_cal %s' % (name, func)
+		for i in sorted(args):
+			val += ' %s=%s' % (i, args[i])
+		val += '\nr:%s_ret %s $retval\n' % (name, func)
+		return val
+	def addKprobes(self):
+		# first test each kprobe
+		print('INITIALIZING KPROBES...')
+		rejects = []
+		for name in sorted(self.kprobes):
+			if not self.testKprobe(self.kprobes[name]):
+				rejects.append(name)
+		# remove all failed ones from the list
+		for name in rejects:
+			vprint('Skipping KPROBE: %s' % name)
+			self.kprobes.pop(name)
+		self.fsetVal('', 'kprobe_events')
+		kprobeevents = ''
+		# set the kprobes all at once
+		for kp in self.kprobes:
+			val = self.kprobeText(self.kprobes[kp])
+			vprint('Adding KPROBE: %s\n%s' % (kp, val.strip()))
+			kprobeevents += self.kprobeText(self.kprobes[kp])
+		self.fsetVal(kprobeevents, 'kprobe_events')
+		# verify that the kprobes were set as ordered
+		check = self.fgetVal('kprobe_events')
+		linesout = len(kprobeevents.split('\n'))
+		linesack = len(check.split('\n'))
+		if linesack < linesout:
+			# if not, try appending the kprobes 1 by 1
+			for kp in self.kprobes:
+				kprobeevents = self.kprobeText(self.kprobes[kp])
+				self.fsetVal(kprobeevents, 'kprobe_events', 'a')
+		self.fsetVal('1', 'events/kprobes/enable')
+	def testKprobe(self, kprobe):
+		kprobeevents = self.kprobeText(kprobe)
+		if not kprobeevents:
+			return False
+		try:
+			self.fsetVal(kprobeevents, 'kprobe_events')
+			check = self.fgetVal('kprobe_events')
+		except:
+			return False
+		linesout = len(kprobeevents.split('\n'))
+		linesack = len(check.split('\n'))
+		if linesack < linesout:
+			return False
+		return True
+	def fsetVal(self, val, path, mode='w'):
+		file = self.tpath+path
+		if not os.path.exists(file):
+			return False
+		try:
+			fp = open(file, mode)
+			fp.write(val)
+			fp.close()
+		except:
+			pass
+		return True
+	def fgetVal(self, path):
+		file = self.tpath+path
+		res = ''
+		if not os.path.exists(file):
+			return res
+		try:
+			fp = open(file, 'r')
+			res = fp.read()
+			fp.close()
+		except:
+			pass
+		return res
+	def cleanupFtrace(self):
+		if(self.usecallgraph or self.usetraceevents):
+			self.fsetVal('0', 'events/kprobes/enable')
+			self.fsetVal('', 'kprobe_events')
+	def setupAllKprobes(self):
+		for name in self.tracefuncs:
+			self.defaultKprobe(name, self.tracefuncs[name])
+		for name in self.dev_tracefuncs:
+			self.defaultKprobe(name, self.dev_tracefuncs[name])
+	def isCallgraphFunc(self, name):
+		if len(self.debugfuncs) < 1 and self.suspendmode == 'command':
+			return True
+		if name in self.debugfuncs:
+			return True
+		funclist = []
+		for i in self.tracefuncs:
+			if 'func' in self.tracefuncs[i]:
+				funclist.append(self.tracefuncs[i]['func'])
+			else:
+				funclist.append(i)
+		if name in funclist:
+			return True
+		return False
+	def initFtrace(self, testing=False):
+		tp = self.tpath
+		print('INITIALIZING FTRACE...')
+		# turn trace off
+		self.fsetVal('0', 'tracing_on')
+		self.cleanupFtrace()
+		# set the trace clock to global
+		self.fsetVal('global', 'trace_clock')
+		# set trace buffer to a huge value
+		self.fsetVal('nop', 'current_tracer')
+		self.fsetVal('100000', 'buffer_size_kb')
+		# go no further if this is just a status check
+		if testing:
+			return
+		if self.usekprobes:
+			# add tracefunc kprobes so long as were not using full callgraph
+			if(not self.usecallgraph or len(self.debugfuncs) > 0):
+				for name in self.tracefuncs:
+					self.defaultKprobe(name, self.tracefuncs[name])
+				if self.usedevsrc:
+					for name in self.dev_tracefuncs:
+						self.defaultKprobe(name, self.dev_tracefuncs[name])
+			else:
+				self.usedevsrc = False
+			self.addKprobes()
+		# initialize the callgraph trace, unless this is an x2 run
+		if(self.usecallgraph):
+			# set trace type
+			self.fsetVal('function_graph', 'current_tracer')
+			self.fsetVal('', 'set_ftrace_filter')
+			# set trace format options
+			self.fsetVal('print-parent', 'trace_options')
+			self.fsetVal('funcgraph-abstime', 'trace_options')
+			self.fsetVal('funcgraph-cpu', 'trace_options')
+			self.fsetVal('funcgraph-duration', 'trace_options')
+			self.fsetVal('funcgraph-proc', 'trace_options')
+			self.fsetVal('funcgraph-tail', 'trace_options')
+			self.fsetVal('nofuncgraph-overhead', 'trace_options')
+			self.fsetVal('context-info', 'trace_options')
+			self.fsetVal('graph-time', 'trace_options')
+			self.fsetVal('0', 'max_graph_depth')
+			if len(self.debugfuncs) > 0:
+				self.setFtraceFilterFunctions(self.debugfuncs)
+			elif self.suspendmode == 'command':
+				self.fsetVal('', 'set_graph_function')
+			else:
+				cf = ['dpm_run_callback']
+				if(self.usetraceeventsonly):
+					cf += ['dpm_prepare', 'dpm_complete']
+				for fn in self.tracefuncs:
+					if 'func' in self.tracefuncs[fn]:
+						cf.append(self.tracefuncs[fn]['func'])
+					else:
+						cf.append(fn)
+				self.setFtraceFilterFunctions(cf)
+		if(self.usetraceevents):
+			# turn trace events on
+			events = iter(self.traceevents)
+			for e in events:
+				self.fsetVal('1', 'events/power/'+e+'/enable')
+		# clear the trace buffer
+		self.fsetVal('', 'trace')
+	def verifyFtrace(self):
+		# files needed for any trace data
+		files = ['buffer_size_kb', 'current_tracer', 'trace', 'trace_clock',
+				 'trace_marker', 'trace_options', 'tracing_on']
+		# files needed for callgraph trace data
+		tp = self.tpath
+		if(self.usecallgraph):
+			files += [
+				'available_filter_functions',
+				'set_ftrace_filter',
+				'set_graph_function'
+			]
+		for f in files:
+			if(os.path.exists(tp+f) == False):
+				return False
+		return True
+	def verifyKprobes(self):
+		# files needed for kprobes to work
+		files = ['kprobe_events', 'events']
+		tp = self.tpath
+		for f in files:
+			if(os.path.exists(tp+f) == False):
+				return False
+		return True
+	def colorText(self, str):
+		if not self.ansi:
+			return str
+		return '\x1B[31;40m'+str+'\x1B[m'
 
 sysvals = SystemValues()
 
+# Class: DevProps
+# Description:
+#	 Simple class which holds property values collected
+#	 for all the devices used in the timeline.
+class DevProps:
+	syspath = ''
+	altname = ''
+	async = True
+	xtraclass = ''
+	xtrainfo = ''
+	def out(self, dev):
+		return '%s,%s,%d;' % (dev, self.altname, self.async)
+	def debug(self, dev):
+		print '%s:\n\taltname = %s\n\t  async = %s' % (dev, self.altname, self.async)
+	def altName(self, dev):
+		if not self.altname or self.altname == dev:
+			return dev
+		return '%s [%s]' % (self.altname, dev)
+	def xtraClass(self):
+		if self.xtraclass:
+			return ' '+self.xtraclass
+		if not self.async:
+			return ' sync'
+		return ''
+	def xtraInfo(self):
+		if self.xtraclass:
+			return ' '+self.xtraclass
+		if self.async:
+			return ' async'
+		return ' sync'
+
 # Class: DeviceNode
 # Description:
 #	 A container used to create a device hierachy, with a single root node
@@ -228,6 +681,7 @@ class Data:
 	html_device_id = 0
 	stamp = 0
 	outfile = ''
+	dev_ubiquitous = ['msleep', 'udelay']
 	def __init__(self, num):
 		idchar = 'abcdefghijklmnopqrstuvwxyz'
 		self.testnumber = num
@@ -257,6 +711,9 @@ class Data:
 								'row': 0, 'color': '#FFFFCC', 'order': 9}
 		}
 		self.phases = self.sortedPhases()
+		self.devicegroups = []
+		for phase in self.phases:
+			self.devicegroups.append([phase])
 	def getStart(self):
 		return self.dmesg[self.phases[0]]['start']
 	def setStart(self, time):
@@ -273,51 +730,61 @@ class Data:
 			for dev in list:
 				d = list[dev]
 				if(d['pid'] == pid and time >= d['start'] and
-					time <= d['end']):
+					time < d['end']):
 					return False
 		return True
-	def addIntraDevTraceEvent(self, action, name, pid, time):
-		if(action == 'mutex_lock_try'):
-			color = 'red'
-		elif(action == 'mutex_lock_pass'):
-			color = 'green'
-		elif(action == 'mutex_unlock'):
-			color = 'blue'
-		else:
-			# create separate colors based on the name
-			v1 = len(name)*10 % 256
-			v2 = string.count(name, 'e')*100 % 256
-			v3 = ord(name[0])*20 % 256
-			color = '#%06X' % ((v1*0x10000) + (v2*0x100) + v3)
-		for phase in self.phases:
-			list = self.dmesg[phase]['list']
-			for dev in list:
-				d = list[dev]
-				if(d['pid'] == pid and time >= d['start'] and
-					time <= d['end']):
-					e = TraceEvent(action, name, color, time)
-					if('traceevents' not in d):
-						d['traceevents'] = []
-					d['traceevents'].append(e)
-					return d
-					break
-		return 0
-	def capIntraDevTraceEvent(self, action, name, pid, time):
-		for phase in self.phases:
+	def targetDevice(self, phaselist, start, end, pid=-1):
+		tgtdev = ''
+		for phase in phaselist:
 			list = self.dmesg[phase]['list']
-			for dev in list:
-				d = list[dev]
-				if(d['pid'] == pid and time >= d['start'] and
-					time <= d['end']):
-					if('traceevents' not in d):
-						return
-					for e in d['traceevents']:
-						if(e.action == action and
-							e.name == name and not e.ready):
-							e.length = time - e.time
-							e.ready = True
-							break
-					return
+			for devname in list:
+				dev = list[devname]
+				if(pid >= 0 and dev['pid'] != pid):
+					continue
+				devS = dev['start']
+				devE = dev['end']
+				if(start < devS or start >= devE or end <= devS or end > devE):
+					continue
+				tgtdev = dev
+				break
+		return tgtdev
+	def addDeviceFunctionCall(self, displayname, kprobename, proc, pid, start, end, cdata, rdata):
+		machstart = self.dmesg['suspend_machine']['start']
+		machend = self.dmesg['resume_machine']['end']
+		tgtdev = self.targetDevice(self.phases, start, end, pid)
+		if not tgtdev and start >= machstart and end < machend:
+			# device calls in machine phases should be serial
+			tgtdev = self.targetDevice(['suspend_machine', 'resume_machine'], start, end)
+		if not tgtdev:
+			if 'scsi_eh' in proc:
+				self.newActionGlobal(proc, start, end, pid)
+				self.addDeviceFunctionCall(displayname, kprobename, proc, pid, start, end, cdata, rdata)
+			else:
+				vprint('IGNORE: %s[%s](%d) [%f - %f] | %s | %s | %s' % (displayname, kprobename,
+					pid, start, end, cdata, rdata, proc))
+			return False
+		# detail block fits within tgtdev
+		if('src' not in tgtdev):
+			tgtdev['src'] = []
+		title = cdata+' '+rdata
+		mstr = '\(.*\) *(?P<args>.*) *\((?P<caller>.*)\+.* arg1=(?P<ret>.*)'
+		m = re.match(mstr, title)
+		if m:
+			c = m.group('caller')
+			a = m.group('args').strip()
+			r = m.group('ret')
+			if len(r) > 6:
+				r = ''
+			else:
+				r = 'ret=%s ' % r
+			l = '%0.3fms' % ((end - start) * 1000)
+			if kprobename in self.dev_ubiquitous:
+				title = '%s(%s) <- %s, %s(%s)' % (displayname, a, c, r, l)
+			else:
+				title = '%s(%s) %s(%s)' % (displayname, a, r, l)
+		e = TraceEvent(title, kprobename, start, end - start)
+		tgtdev['src'].append(e)
+		return True
 	def trimTimeVal(self, t, t0, dT, left):
 		if left:
 			if(t > t0):
@@ -353,11 +820,11 @@ class Data:
 					cg.end = self.trimTimeVal(cg.end, t0, dT, left)
 					for line in cg.list:
 						line.time = self.trimTimeVal(line.time, t0, dT, left)
-				if('traceevents' in d):
-					for e in d['traceevents']:
+				if('src' in d):
+					for e in d['src']:
 						e.time = self.trimTimeVal(e.time, t0, dT, left)
 	def normalizeTime(self, tZero):
-		# first trim out any standby or freeze clock time
+		# trim out any standby or freeze clock time
 		if(self.tSuspended != self.tResumed):
 			if(self.tResumed > tZero):
 				self.trimTime(self.tSuspended, \
@@ -365,29 +832,6 @@ class Data:
 			else:
 				self.trimTime(self.tSuspended, \
 					self.tResumed-self.tSuspended, False)
-		# shift the timeline so that tZero is the new 0
-		self.tSuspended -= tZero
-		self.tResumed -= tZero
-		self.start -= tZero
-		self.end -= tZero
-		for phase in self.phases:
-			p = self.dmesg[phase]
-			p['start'] -= tZero
-			p['end'] -= tZero
-			list = p['list']
-			for name in list:
-				d = list[name]
-				d['start'] -= tZero
-				d['end'] -= tZero
-				if('ftrace' in d):
-					cg = d['ftrace']
-					cg.start -= tZero
-					cg.end -= tZero
-					for line in cg.list:
-						line.time -= tZero
-				if('traceevents' in d):
-					for e in d['traceevents']:
-						e.time -= tZero
 	def newPhaseWithSingleAction(self, phasename, devname, start, end, color):
 		for phase in self.phases:
 			self.dmesg[phase]['order'] += 1
@@ -417,6 +861,7 @@ class Data:
 			{'list': list, 'start': start, 'end': end,
 			'row': 0, 'color': color, 'order': order}
 		self.phases = self.sortedPhases()
+		self.devicegroups.append([phasename])
 	def setPhase(self, phase, ktime, isbegin):
 		if(isbegin):
 			self.dmesg[phase]['start'] = ktime
@@ -442,7 +887,10 @@ class Data:
 		for devname in phaselist:
 			dev = phaselist[devname]
 			if(dev['end'] < 0):
-				dev['end'] = end
+				for p in self.phases:
+					if self.dmesg[p]['end'] > dev['start']:
+						dev['end'] = self.dmesg[p]['end']
+						break
 				vprint('%s (%s): callback didnt return' % (devname, phase))
 	def deviceFilter(self, devicefilter):
 		# remove all by the relatives of the filter devnames
@@ -472,22 +920,58 @@ class Data:
 		# if any calls never returned, clip them at system resume end
 		for phase in self.phases:
 			self.fixupInitcalls(phase, self.getEnd())
-	def newActionGlobal(self, name, start, end):
+	def isInsideTimeline(self, start, end):
+		if(self.start <= start and self.end > start):
+			return True
+		return False
+	def phaseOverlap(self, phases):
+		rmgroups = []
+		newgroup = []
+		for group in self.devicegroups:
+			for phase in phases:
+				if phase not in group:
+					continue
+				for p in group:
+					if p not in newgroup:
+						newgroup.append(p)
+				if group not in rmgroups:
+					rmgroups.append(group)
+		for group in rmgroups:
+			self.devicegroups.remove(group)
+		self.devicegroups.append(newgroup)
+	def newActionGlobal(self, name, start, end, pid=-1, color=''):
+		# if event starts before timeline start, expand timeline
+		if(start < self.start):
+			self.setStart(start)
+		# if event ends after timeline end, expand the timeline
+		if(end > self.end):
+			self.setEnd(end)
 		# which phase is this device callback or action "in"
 		targetphase = "none"
+		htmlclass = ''
 		overlap = 0.0
+		phases = []
 		for phase in self.phases:
 			pstart = self.dmesg[phase]['start']
 			pend = self.dmesg[phase]['end']
 			o = max(0, min(end, pend) - max(start, pstart))
-			if(o > overlap):
+			if o > 0:
+				phases.append(phase)
+			if o > overlap:
+				if overlap > 0 and phase == 'post_resume':
+					continue
 				targetphase = phase
 				overlap = o
+		if pid == -2:
+			htmlclass = ' bg'
+		if len(phases) > 1:
+			htmlclass = ' bg'
+			self.phaseOverlap(phases)
 		if targetphase in self.phases:
-			self.newAction(targetphase, name, -1, '', start, end, '')
-			return True
+			newname = self.newAction(targetphase, name, pid, '', start, end, '', htmlclass, color)
+			return (targetphase, newname)
 		return False
-	def newAction(self, phase, name, pid, parent, start, end, drv):
+	def newAction(self, phase, name, pid, parent, start, end, drv, htmlclass='', color=''):
 		# new device callback for a specific phase
 		self.html_device_id += 1
 		devid = '%s%d' % (self.idstr, self.html_device_id)
@@ -495,8 +979,19 @@ class Data:
 		length = -1.0
 		if(start >= 0 and end >= 0):
 			length = end - start
+		if pid == -2:
+			i = 2
+			origname = name
+			while(name in list):
+				name = '%s[%d]' % (origname, i)
+				i += 1
 		list[name] = {'start': start, 'end': end, 'pid': pid, 'par': parent,
 					  'length': length, 'row': 0, 'id': devid, 'drv': drv }
+		if htmlclass:
+			list[name]['htmlclass'] = htmlclass
+		if color:
+			list[name]['color'] = color
+		return name
 	def deviceIDs(self, devlist, phase):
 		idlist = []
 		list = self.dmesg[phase]['list']
@@ -536,10 +1031,21 @@ class Data:
 			vprint('    %16s: %f - %f (%d devices)' % (phase, \
 				self.dmesg[phase]['start'], self.dmesg[phase]['end'], dc))
 		vprint('            test end: %f' % self.end)
+	def deviceChildrenAllPhases(self, devname):
+		devlist = []
+		for phase in self.phases:
+			list = self.deviceChildren(devname, phase)
+			for dev in list:
+				if dev not in devlist:
+					devlist.append(dev)
+		return devlist
 	def masterTopology(self, name, list, depth):
 		node = DeviceNode(name, depth)
 		for cname in list:
-			clist = self.deviceChildren(cname, 'resume')
+			# avoid recursions
+			if name == cname:
+				continue
+			clist = self.deviceChildrenAllPhases(cname)
 			cnode = self.masterTopology(cname, clist, depth+1)
 			node.children.append(cnode)
 		return node
@@ -580,7 +1086,8 @@ class Data:
 			list = self.dmesg[phase]['list']
 			for dev in list:
 				pdev = list[dev]['par']
-				if(re.match('[0-9]*-[0-9]*\.[0-9]*[\.0-9]*\:[\.0-9]*$', pdev)):
+				pid = list[dev]['pid']
+				if(pid < 0 or re.match('[0-9]*-[0-9]*\.[0-9]*[\.0-9]*\:[\.0-9]*$', pdev)):
 					continue
 				if pdev and pdev not in real and pdev not in rootlist:
 					rootlist.append(pdev)
@@ -589,22 +1096,33 @@ class Data:
 		rootlist = self.rootDeviceList()
 		master = self.masterTopology('', rootlist, 0)
 		return self.printTopology(master)
+	def selectTimelineDevices(self, widfmt, tTotal, mindevlen):
+		# only select devices that will actually show up in html
+		self.tdevlist = dict()
+		for phase in self.dmesg:
+			devlist = []
+			list = self.dmesg[phase]['list']
+			for dev in list:
+				length = (list[dev]['end'] - list[dev]['start']) * 1000
+				width = widfmt % (((list[dev]['end']-list[dev]['start'])*100)/tTotal)
+				if width != '0.000000' and length >= mindevlen:
+					devlist.append(dev)
+			self.tdevlist[phase] = devlist
 
 # Class: TraceEvent
 # Description:
 #	 A container for trace event data found in the ftrace file
 class TraceEvent:
-	ready = False
-	name = ''
+	text = ''
 	time = 0.0
-	color = '#FFFFFF'
 	length = 0.0
-	action = ''
-	def __init__(self, a, n, c, t):
-		self.action = a
-		self.name = n
-		self.color = c
+	title = ''
+	row = 0
+	def __init__(self, a, n, t, l):
+		self.title = a
+		self.text = n
 		self.time = t
+		self.length = l
 
 # Class: FTraceLine
 # Description:
@@ -623,11 +1141,14 @@ class FTraceLine:
 	fcall = False
 	freturn = False
 	fevent = False
+	fkprobe = False
 	depth = 0
 	name = ''
 	type = ''
-	def __init__(self, t, m, d):
+	def __init__(self, t, m='', d=''):
 		self.time = float(t)
+		if not m and not d:
+			return
 		# is this a trace event
 		if(d == 'traceevent' or re.match('^ *\/\* *(?P<msg>.*) \*\/ *$', m)):
 			if(d == 'traceevent'):
@@ -644,6 +1165,18 @@ class FTraceLine:
 				self.type = emm.group('call')
 			else:
 				self.name = msg
+			km = re.match('^(?P<n>.*)_cal$', self.type)
+			if km:
+				self.fcall = True
+				self.fkprobe = True
+				self.type = km.group('n')
+				return
+			km = re.match('^(?P<n>.*)_ret$', self.type)
+			if km:
+				self.freturn = True
+				self.fkprobe = True
+				self.type = km.group('n')
+				return
 			self.fevent = True
 			return
 		# convert the duration to seconds
@@ -662,7 +1195,7 @@ class FTraceLine:
 				# includes comment with function name
 				match = re.match('^} *\/\* *(?P<n>.*) *\*\/$', m)
 				if(match):
-					self.name = match.group('n')
+					self.name = match.group('n').strip()
 		# function call
 		else:
 			self.fcall = True
@@ -670,19 +1203,19 @@ class FTraceLine:
 			if(m[-1] == '{'):
 				match = re.match('^(?P<n>.*) *\(.*', m)
 				if(match):
-					self.name = match.group('n')
+					self.name = match.group('n').strip()
 			# function call with no children (leaf)
 			elif(m[-1] == ';'):
 				self.freturn = True
 				match = re.match('^(?P<n>.*) *\(.*', m)
 				if(match):
-					self.name = match.group('n')
+					self.name = match.group('n').strip()
 			# something else (possibly a trace marker)
 			else:
 				self.name = m
 	def getDepth(self, str):
 		return len(str)/2
-	def debugPrint(self, dev):
+	def debugPrint(self, dev=''):
 		if(self.freturn and self.fcall):
 			print('%s -- %f (%02d): %s(); (%.3f us)' % (dev, self.time, \
 				self.depth, self.name, self.length*1000000))
@@ -692,6 +1225,33 @@ class FTraceLine:
 		else:
 			print('%s -- %f (%02d): %s() { (%.3f us)' % (dev, self.time, \
 				self.depth, self.name, self.length*1000000))
+	def startMarker(self):
+		global sysvals
+		# Is this the starting line of a suspend?
+		if not self.fevent:
+			return False
+		if sysvals.usetracemarkers:
+			if(self.name == 'SUSPEND START'):
+				return True
+			return False
+		else:
+			if(self.type == 'suspend_resume' and
+				re.match('suspend_enter\[.*\] begin', self.name)):
+				return True
+			return False
+	def endMarker(self):
+		# Is this the ending line of a resume?
+		if not self.fevent:
+			return False
+		if sysvals.usetracemarkers:
+			if(self.name == 'RESUME COMPLETE'):
+				return True
+			return False
+		else:
+			if(self.type == 'suspend_resume' and
+				re.match('thaw_processes\[.*\] end', self.name)):
+				return True
+			return False
 
 # Class: FTraceCallGraph
 # Description:
@@ -705,54 +1265,124 @@ class FTraceCallGraph:
 	list = []
 	invalid = False
 	depth = 0
-	def __init__(self):
+	pid = 0
+	def __init__(self, pid):
 		self.start = -1.0
 		self.end = -1.0
 		self.list = []
 		self.depth = 0
-	def setDepth(self, line):
+		self.pid = pid
+	def addLine(self, line, debug=False):
+		# if this is already invalid, just leave
+		if(self.invalid):
+			return False
+		# invalidate on too much data or bad depth
+		if(len(self.list) >= 1000000 or self.depth < 0):
+			self.invalidate(line)
+			return False
+		# compare current depth with this lines pre-call depth
+		prelinedep = line.depth
+		if(line.freturn and not line.fcall):
+			prelinedep += 1
+		last = 0
+		lasttime = line.time
+		virtualfname = 'execution_misalignment'
+		if len(self.list) > 0:
+			last = self.list[-1]
+			lasttime = last.time
+		# handle low misalignments by inserting returns
+		if prelinedep < self.depth:
+			if debug and last:
+				print '-------- task %d --------' % self.pid
+				last.debugPrint()
+			idx = 0
+			# add return calls to get the depth down
+			while prelinedep < self.depth:
+				if debug:
+					print 'MISALIGN LOW (add returns): C%d - eC%d' % (self.depth, prelinedep)
+				self.depth -= 1
+				if idx == 0 and last and last.fcall and not last.freturn:
+					# special case, turn last call into a leaf
+					last.depth = self.depth
+					last.freturn = True
+					last.length = line.time - last.time
+					if debug:
+						last.debugPrint()
+				else:
+					vline = FTraceLine(lasttime)
+					vline.depth = self.depth
+					vline.name = virtualfname
+					vline.freturn = True
+					self.list.append(vline)
+					if debug:
+						vline.debugPrint()
+				idx += 1
+			if debug:
+				line.debugPrint()
+				print ''
+		# handle high misalignments by inserting calls
+		elif prelinedep > self.depth:
+			if debug and last:
+				print '-------- task %d --------' % self.pid
+				last.debugPrint()
+			idx = 0
+			# add calls to get the depth up
+			while prelinedep > self.depth:
+				if debug:
+					print 'MISALIGN HIGH (add calls): C%d - eC%d' % (self.depth, prelinedep)
+				if idx == 0 and line.freturn and not line.fcall:
+					# special case, turn this return into a leaf
+					line.fcall = True
+					prelinedep -= 1
+				else:
+					vline = FTraceLine(lasttime)
+					vline.depth = self.depth
+					vline.name = virtualfname
+					vline.fcall = True
+					if debug:
+						vline.debugPrint()
+					self.list.append(vline)
+					self.depth += 1
+					if not last:
+						self.start = vline.time
+				idx += 1
+			if debug:
+				line.debugPrint()
+				print ''
+		# process the call and set the new depth
 		if(line.fcall and not line.freturn):
-			line.depth = self.depth
 			self.depth += 1
 		elif(line.freturn and not line.fcall):
 			self.depth -= 1
-			line.depth = self.depth
-		else:
-			line.depth = self.depth
-	def addLine(self, line, match):
-		if(not self.invalid):
-			self.setDepth(line)
+		if len(self.list) < 1:
+			self.start = line.time
+		self.list.append(line)
 		if(line.depth == 0 and line.freturn):
 			if(self.start < 0):
 				self.start = line.time
 			self.end = line.time
-			self.list.append(line)
+			if line.fcall:
+				self.end += line.length
+			if self.list[0].name == virtualfname:
+				self.invalid = True
 			return True
-		if(self.invalid):
-			return False
-		if(len(self.list) >= 1000000 or self.depth < 0):
-			if(len(self.list) > 0):
-				first = self.list[0]
-				self.list = []
-				self.list.append(first)
-			self.invalid = True
-			if(not match):
-				return False
-			id = 'task %s cpu %s' % (match.group('pid'), match.group('cpu'))
-			window = '(%f - %f)' % (self.start, line.time)
-			if(self.depth < 0):
-				print('Too much data for '+id+\
-					' (buffer overflow), ignoring this callback')
-			else:
-				print('Too much data for '+id+\
-					' '+window+', ignoring this callback')
-			return False
-		self.list.append(line)
-		if(self.start < 0):
-			self.start = line.time
 		return False
+	def invalidate(self, line):
+		if(len(self.list) > 0):
+			first = self.list[0]
+			self.list = []
+			self.list.append(first)
+		self.invalid = True
+		id = 'task %s' % (self.pid)
+		window = '(%f - %f)' % (self.start, line.time)
+		if(self.depth < 0):
+			vprint('Too much data for '+id+\
+				' (buffer overflow), ignoring this callback')
+		else:
+			vprint('Too much data for '+id+\
+				' '+window+', ignoring this callback')
 	def slice(self, t0, tN):
-		minicg = FTraceCallGraph()
+		minicg = FTraceCallGraph(0)
 		count = -1
 		firstdepth = 0
 		for l in self.list:
@@ -764,13 +1394,26 @@ class FTraceCallGraph:
 				firstdepth = l.depth
 				count = 0
 			l.depth -= firstdepth
-			minicg.addLine(l, 0)
+			minicg.addLine(l)
 			if((count == 0 and l.freturn and l.fcall) or
 				(count > 0 and l.depth <= 0)):
 				break
 			count += 1
 		return minicg
-	def sanityCheck(self):
+	def repair(self, enddepth):
+		# bring the depth back to 0 with additional returns
+		fixed = False
+		last = self.list[-1]
+		for i in reversed(range(enddepth)):
+			t = FTraceLine(last.time)
+			t.depth = i
+			t.freturn = True
+			fixed = self.addLine(t)
+			if fixed:
+				self.end = last.time
+				return True
+		return False
+	def postProcess(self, debug=False):
 		stack = dict()
 		cnt = 0
 		for l in self.list:
@@ -779,98 +1422,317 @@ class FTraceCallGraph:
 				cnt += 1
 			elif(l.freturn and not l.fcall):
 				if(l.depth not in stack):
+					if debug:
+						print 'Post Process Error: Depth missing'
+						l.debugPrint()
 					return False
+				# transfer total time from return line to call line
 				stack[l.depth].length = l.length
-				stack[l.depth] = 0
+				stack.pop(l.depth)
 				l.length = 0
 				cnt -= 1
 		if(cnt == 0):
+			# trace caught the whole call tree
 			return True
-		return False
-	def debugPrint(self, filename):
-		if(filename == 'stdout'):
-			print('[%f - %f]') % (self.start, self.end)
-			for l in self.list:
-				if(l.freturn and l.fcall):
-					print('%f (%02d): %s(); (%.3f us)' % (l.time, \
-						l.depth, l.name, l.length*1000000))
-				elif(l.freturn):
-					print('%f (%02d): %s} (%.3f us)' % (l.time, \
-						l.depth, l.name, l.length*1000000))
-				else:
-					print('%f (%02d): %s() { (%.3f us)' % (l.time, \
-						l.depth, l.name, l.length*1000000))
-			print(' ')
-		else:
-			fp = open(filename, 'w')
-			print(filename)
-			for l in self.list:
-				if(l.freturn and l.fcall):
-					fp.write('%f (%02d): %s(); (%.3f us)\n' % (l.time, \
-						l.depth, l.name, l.length*1000000))
-				elif(l.freturn):
-					fp.write('%f (%02d): %s} (%.3f us)\n' % (l.time, \
-						l.depth, l.name, l.length*1000000))
-				else:
-					fp.write('%f (%02d): %s() { (%.3f us)\n' % (l.time, \
-						l.depth, l.name, l.length*1000000))
-			fp.close()
+		elif(cnt < 0):
+			if debug:
+				print 'Post Process Error: Depth is less than 0'
+			return False
+		# trace ended before call tree finished
+		return self.repair(cnt)
+	def deviceMatch(self, pid, data):
+		found = False
+		# add the callgraph data to the device hierarchy
+		borderphase = {
+			'dpm_prepare': 'suspend_prepare',
+			'dpm_complete': 'resume_complete'
+		}
+		if(self.list[0].name in borderphase):
+			p = borderphase[self.list[0].name]
+			list = data.dmesg[p]['list']
+			for devname in list:
+				dev = list[devname]
+				if(pid == dev['pid'] and
+					self.start <= dev['start'] and
+					self.end >= dev['end']):
+					dev['ftrace'] = self.slice(dev['start'], dev['end'])
+					found = True
+			return found
+		for p in data.phases:
+			if(data.dmesg[p]['start'] <= self.start and
+				self.start <= data.dmesg[p]['end']):
+				list = data.dmesg[p]['list']
+				for devname in list:
+					dev = list[devname]
+					if(pid == dev['pid'] and
+						self.start <= dev['start'] and
+						self.end >= dev['end']):
+						dev['ftrace'] = self
+						found = True
+						break
+				break
+		return found
+	def newActionFromFunction(self, data):
+		name = self.list[0].name
+		if name in ['dpm_run_callback', 'dpm_prepare', 'dpm_complete']:
+			return
+		fs = self.start
+		fe = self.end
+		if fs < data.start or fe > data.end:
+			return
+		phase = ''
+		for p in data.phases:
+			if(data.dmesg[p]['start'] <= self.start and
+				self.start < data.dmesg[p]['end']):
+				phase = p
+				break
+		if not phase:
+			return
+		out = data.newActionGlobal(name, fs, fe, -2)
+		if out:
+			phase, myname = out
+			data.dmesg[phase]['list'][myname]['ftrace'] = self
+	def debugPrint(self):
+		print('[%f - %f] %s (%d)') % (self.start, self.end, self.list[0].name, self.pid)
+		for l in self.list:
+			if(l.freturn and l.fcall):
+				print('%f (%02d): %s(); (%.3f us)' % (l.time, \
+					l.depth, l.name, l.length*1000000))
+			elif(l.freturn):
+				print('%f (%02d): %s} (%.3f us)' % (l.time, \
+					l.depth, l.name, l.length*1000000))
+			else:
+				print('%f (%02d): %s() { (%.3f us)' % (l.time, \
+					l.depth, l.name, l.length*1000000))
+		print(' ')
 
 # Class: Timeline
 # Description:
-#	 A container for a suspend/resume html timeline. In older versions
-#	 of the script there were multiple timelines, but in the latest
-#	 there is only one.
+#	 A container for a device timeline which calculates
+#	 all the html properties to display it correctly
 class Timeline:
 	html = {}
-	scaleH = 0.0 # height of the row as a percent of the timeline height
-	rowH = 0.0 # height of each row in percent of the timeline height
-	row_height_pixels = 30
-	maxrows = 0
-	height = 0
-	def __init__(self):
+	height = 0	# total timeline height
+	scaleH = 20	# timescale (top) row height
+	rowH = 30	# device row height
+	bodyH = 0	# body height
+	rows = 0	# total timeline rows
+	phases = []
+	rowmaxlines = dict()
+	rowcount = dict()
+	rowheight = dict()
+	def __init__(self, rowheight):
+		self.rowH = rowheight
 		self.html = {
+			'header': '',
 			'timeline': '',
 			'legend': '',
-			'scale': ''
 		}
-	def setRows(self, rows):
-		self.maxrows = int(rows)
-		self.scaleH = 100.0/float(self.maxrows)
-		self.height = self.maxrows*self.row_height_pixels
-		r = float(self.maxrows - 1)
-		if(r < 1.0):
-			r = 1.0
-		self.rowH = (100.0 - self.scaleH)/r
+	# Function: getDeviceRows
+	# Description:
+	#    determine how may rows the device funcs will take
+	# Arguments:
+	#	 rawlist: the list of devices/actions for a single phase
+	# Output:
+	#	 The total number of rows needed to display this phase of the timeline
+	def getDeviceRows(self, rawlist):
+		# clear all rows and set them to undefined
+		lendict = dict()
+		for item in rawlist:
+			item.row = -1
+			lendict[item] = item.length
+		list = []
+		for i in sorted(lendict, key=lendict.get, reverse=True):
+			list.append(i)
+		remaining = len(list)
+		rowdata = dict()
+		row = 1
+		# try to pack each row with as many ranges as possible
+		while(remaining > 0):
+			if(row not in rowdata):
+				rowdata[row] = []
+			for i in list:
+				if(i.row >= 0):
+					continue
+				s = i.time
+				e = i.time + i.length
+				valid = True
+				for ritem in rowdata[row]:
+					rs = ritem.time
+					re = ritem.time + ritem.length
+					if(not (((s <= rs) and (e <= rs)) or
+						((s >= re) and (e >= re)))):
+						valid = False
+						break
+				if(valid):
+					rowdata[row].append(i)
+					i.row = row
+					remaining -= 1
+			row += 1
+		return row
+	# Function: getPhaseRows
+	# Description:
+	#	 Organize the timeline entries into the smallest
+	#	 number of rows possible, with no entry overlapping
+	# Arguments:
+	#	 list: the list of devices/actions for a single phase
+	#	 devlist: string list of device names to use
+	# Output:
+	#	 The total number of rows needed to display this phase of the timeline
+	def getPhaseRows(self, dmesg, devlist):
+		# clear all rows and set them to undefined
+		remaining = len(devlist)
+		rowdata = dict()
+		row = 0
+		lendict = dict()
+		myphases = []
+		for item in devlist:
+			if item[0] not in self.phases:
+				self.phases.append(item[0])
+			if item[0] not in myphases:
+				myphases.append(item[0])
+				self.rowmaxlines[item[0]] = dict()
+				self.rowheight[item[0]] = dict()
+			dev = dmesg[item[0]]['list'][item[1]]
+			dev['row'] = -1
+			lendict[item] = float(dev['end']) - float(dev['start'])
+			if 'src' in dev:
+				dev['devrows'] = self.getDeviceRows(dev['src'])
+		lenlist = []
+		for i in sorted(lendict, key=lendict.get, reverse=True):
+			lenlist.append(i)
+		orderedlist = []
+		for item in lenlist:
+			dev = dmesg[item[0]]['list'][item[1]]
+			if dev['pid'] == -2:
+				orderedlist.append(item)
+		for item in lenlist:
+			if item not in orderedlist:
+				orderedlist.append(item)
+		# try to pack each row with as many ranges as possible
+		while(remaining > 0):
+			rowheight = 1
+			if(row not in rowdata):
+				rowdata[row] = []
+			for item in orderedlist:
+				dev = dmesg[item[0]]['list'][item[1]]
+				if(dev['row'] < 0):
+					s = dev['start']
+					e = dev['end']
+					valid = True
+					for ritem in rowdata[row]:
+						rs = ritem['start']
+						re = ritem['end']
+						if(not (((s <= rs) and (e <= rs)) or
+							((s >= re) and (e >= re)))):
+							valid = False
+							break
+					if(valid):
+						rowdata[row].append(dev)
+						dev['row'] = row
+						remaining -= 1
+						if 'devrows' in dev and dev['devrows'] > rowheight:
+							rowheight = dev['devrows']
+			for phase in myphases:
+				self.rowmaxlines[phase][row] = rowheight
+				self.rowheight[phase][row] = rowheight * self.rowH
+			row += 1
+		if(row > self.rows):
+			self.rows = int(row)
+		for phase in myphases:
+			self.rowcount[phase] = row
+		return row
+	def phaseRowHeight(self, phase, row):
+		return self.rowheight[phase][row]
+	def phaseRowTop(self, phase, row):
+		top = 0
+		for i in sorted(self.rowheight[phase]):
+			if i >= row:
+				break
+			top += self.rowheight[phase][i]
+		return top
+	# Function: calcTotalRows
+	# Description:
+	#	 Calculate the heights and offsets for the header and rows
+	def calcTotalRows(self):
+		maxrows = 0
+		standardphases = []
+		for phase in self.phases:
+			total = 0
+			for i in sorted(self.rowmaxlines[phase]):
+				total += self.rowmaxlines[phase][i]
+			if total > maxrows:
+				maxrows = total
+			if total == self.rowcount[phase]:
+				standardphases.append(phase)
+		self.height = self.scaleH + (maxrows*self.rowH)
+		self.bodyH = self.height - self.scaleH
+		for phase in standardphases:
+			for i in sorted(self.rowheight[phase]):
+				self.rowheight[phase][i] = self.bodyH/self.rowcount[phase]
+	# Function: createTimeScale
+	# Description:
+	#	 Create the timescale for a timeline block
+	# Arguments:
+	#	 m0: start time (mode begin)
+	#	 mMax: end time (mode end)
+	#	 tTotal: total timeline time
+	#	 mode: suspend or resume
+	# Output:
+	#	 The html code needed to display the time scale
+	def createTimeScale(self, m0, mMax, tTotal, mode):
+		timescale = '<div class="t" style="right:{0}%">{1}</div>\n'
+		rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">Resume</div>\n'
+		output = '<div class="timescale">\n'
+		# set scale for timeline
+		mTotal = mMax - m0
+		tS = 0.1
+		if(tTotal <= 0):
+			return output+'</div>\n'
+		if(tTotal > 4):
+			tS = 1
+		divTotal = int(mTotal/tS) + 1
+		divEdge = (mTotal - tS*(divTotal-1))*100/mTotal
+		for i in range(divTotal):
+			htmlline = ''
+			if(mode == 'resume'):
+				pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal))
+				val = '%0.fms' % (float(i)*tS*1000)
+				htmlline = timescale.format(pos, val)
+				if(i == 0):
+					htmlline = rline
+			else:
+				pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal) - divEdge)
+				val = '%0.fms' % (float(i-divTotal+1)*tS*1000)
+				if(i == divTotal - 1):
+					val = 'Suspend'
+				htmlline = timescale.format(pos, val)
+			output += htmlline
+		output += '</div>\n'
+		return output
 
-# Class: TestRun
+# Class: TestProps
 # Description:
-#	 A container for a suspend/resume test run. This is necessary as
-#	 there could be more than one, and they need to be separate.
-class TestRun:
+#	 A list of values describing the properties of these test runs
+class TestProps:
+	stamp = ''
+	tracertype = ''
+	S0i3 = False
+	fwdata = []
 	ftrace_line_fmt_fg = \
 		'^ *(?P<time>[0-9\.]*) *\| *(?P<cpu>[0-9]*)\)'+\
 		' *(?P<proc>.*)-(?P<pid>[0-9]*) *\|'+\
-		'[ +!]*(?P<dur>[0-9\.]*) .*\|  (?P<msg>.*)'
+		'[ +!#\*@$]*(?P<dur>[0-9\.]*) .*\|  (?P<msg>.*)'
 	ftrace_line_fmt_nop = \
 		' *(?P<proc>.*)-(?P<pid>[0-9]*) *\[(?P<cpu>[0-9]*)\] *'+\
 		'(?P<flags>.{4}) *(?P<time>[0-9\.]*): *'+\
 		'(?P<msg>.*)'
 	ftrace_line_fmt = ftrace_line_fmt_nop
 	cgformat = False
-	ftemp = dict()
-	ttemp = dict()
-	inthepipe = False
-	tracertype = ''
 	data = 0
-	def __init__(self, dataobj):
-		self.data = dataobj
-		self.ftemp = dict()
-		self.ttemp = dict()
-	def isReady(self):
-		if(tracertype == '' or not data):
-			return False
-		return True
+	ktemp = dict()
+	def __init__(self):
+		self.ktemp = dict()
 	def setTracerType(self, tracer):
 		self.tracertype = tracer
 		if(tracer == 'function_graph'):
@@ -881,6 +1743,19 @@ class TestRun:
 		else:
 			doError('Invalid tracer format: [%s]' % tracer, False)
 
+# Class: TestRun
+# Description:
+#	 A container for a suspend/resume test run. This is necessary as
+#	 there could be more than one, and they need to be separate.
+class TestRun:
+	ftemp = dict()
+	ttemp = dict()
+	data = 0
+	def __init__(self, dataobj):
+		self.data = dataobj
+		self.ftemp = dict()
+		self.ttemp = dict()
+
 # ----------------- FUNCTIONS --------------------
 
 # Function: vprint
@@ -893,104 +1768,16 @@ def vprint(msg):
 	if(sysvals.verbose):
 		print(msg)
 
-# Function: initFtrace
-# Description:
-#	 Configure ftrace to use trace events and/or a callgraph
-def initFtrace():
-	global sysvals
-
-	tp = sysvals.tpath
-	cf = 'dpm_run_callback'
-	if(sysvals.usetraceeventsonly):
-		cf = '-e dpm_prepare -e dpm_complete -e dpm_run_callback'
-	if(sysvals.usecallgraph or sysvals.usetraceevents):
-		print('INITIALIZING FTRACE...')
-		# turn trace off
-		os.system('echo 0 > '+tp+'tracing_on')
-		# set the trace clock to global
-		os.system('echo global > '+tp+'trace_clock')
-		# set trace buffer to a huge value
-		os.system('echo nop > '+tp+'current_tracer')
-		os.system('echo 100000 > '+tp+'buffer_size_kb')
-		# initialize the callgraph trace, unless this is an x2 run
-		if(sysvals.usecallgraph and sysvals.execcount == 1):
-			# set trace type
-			os.system('echo function_graph > '+tp+'current_tracer')
-			os.system('echo "" > '+tp+'set_ftrace_filter')
-			# set trace format options
-			os.system('echo funcgraph-abstime > '+tp+'trace_options')
-			os.system('echo funcgraph-proc > '+tp+'trace_options')
-			# focus only on device suspend and resume
-			os.system('cat '+tp+'available_filter_functions | grep '+\
-				cf+' > '+tp+'set_graph_function')
-		if(sysvals.usetraceevents):
-			# turn trace events on
-			events = iter(sysvals.traceevents)
-			for e in events:
-				os.system('echo 1 > '+sysvals.epath+e+'/enable')
-		# clear the trace buffer
-		os.system('echo "" > '+tp+'trace')
-
-# Function: initFtraceAndroid
-# Description:
-#	 Configure ftrace to capture trace events
-def initFtraceAndroid():
-	global sysvals
-
-	tp = sysvals.tpath
-	if(sysvals.usetraceevents):
-		print('INITIALIZING FTRACE...')
-		# turn trace off
-		os.system(sysvals.adb+" shell 'echo 0 > "+tp+"tracing_on'")
-		# set the trace clock to global
-		os.system(sysvals.adb+" shell 'echo global > "+tp+"trace_clock'")
-		# set trace buffer to a huge value
-		os.system(sysvals.adb+" shell 'echo nop > "+tp+"current_tracer'")
-		os.system(sysvals.adb+" shell 'echo 10000 > "+tp+"buffer_size_kb'")
-		# turn trace events on
-		events = iter(sysvals.traceevents)
-		for e in events:
-			os.system(sysvals.adb+" shell 'echo 1 > "+\
-				sysvals.epath+e+"/enable'")
-		# clear the trace buffer
-		os.system(sysvals.adb+" shell 'echo \"\" > "+tp+"trace'")
-
-# Function: verifyFtrace
-# Description:
-#	 Check that ftrace is working on the system
-# Output:
-#	 True or False
-def verifyFtrace():
-	global sysvals
-	# files needed for any trace data
-	files = ['buffer_size_kb', 'current_tracer', 'trace', 'trace_clock',
-			 'trace_marker', 'trace_options', 'tracing_on']
-	# files needed for callgraph trace data
-	tp = sysvals.tpath
-	if(sysvals.usecallgraph):
-		files += [
-			'available_filter_functions',
-			'set_ftrace_filter',
-			'set_graph_function'
-		]
-	for f in files:
-		if(sysvals.android):
-			out = os.popen(sysvals.adb+' shell ls '+tp+f).read().strip()
-			if(out != tp+f):
-				return False
-		else:
-			if(os.path.exists(tp+f) == False):
-				return False
-	return True
-
 # Function: parseStamp
 # Description:
 #	 Pull in the stamp comment line from the data file(s),
 #	 create the stamp, and add it to the global sysvals object
 # Arguments:
 #	 m: the valid re.match output for the stamp line
-def parseStamp(m, data):
+def parseStamp(line, data):
 	global sysvals
+
+	m = re.match(sysvals.stampfmt, line)
 	data.stamp = {'time': '', 'host': '', 'mode': ''}
 	dt = datetime(int(m.group('y'))+2000, int(m.group('m')),
 		int(m.group('d')), int(m.group('H')), int(m.group('M')),
@@ -999,6 +1786,7 @@ def parseStamp(m, data):
 	data.stamp['host'] = m.group('host')
 	data.stamp['mode'] = m.group('mode')
 	data.stamp['kernel'] = m.group('kernel')
+	sysvals.hostname = data.stamp['host']
 	sysvals.suspendmode = data.stamp['mode']
 	if not sysvals.stamp:
 		sysvals.stamp = data.stamp
@@ -1031,14 +1819,35 @@ def diffStamp(stamp1, stamp2):
 def doesTraceLogHaveTraceEvents():
 	global sysvals
 
+	# check for kprobes
+	sysvals.usekprobes = False
+	out = os.system('grep -q "_cal: (" '+sysvals.ftracefile)
+	if(out == 0):
+		sysvals.usekprobes = True
+	# check for callgraph data on trace event blocks
+	out = os.system('grep -q "_cpu_down()" '+sysvals.ftracefile)
+	if(out == 0):
+		sysvals.usekprobes = True
+	out = os.popen('head -1 '+sysvals.ftracefile).read().replace('\n', '')
+	m = re.match(sysvals.stampfmt, out)
+	if m and m.group('mode') == 'command':
+		sysvals.usetraceeventsonly = True
+		sysvals.usetraceevents = True
+		return
+	# figure out what level of trace events are supported
 	sysvals.usetraceeventsonly = True
 	sysvals.usetraceevents = False
 	for e in sysvals.traceevents:
-		out = os.popen('cat '+sysvals.ftracefile+' | grep "'+e+': "').read()
-		if(not out):
+		out = os.system('grep -q "'+e+': " '+sysvals.ftracefile)
+		if(out != 0):
 			sysvals.usetraceeventsonly = False
-		if(e == 'suspend_resume' and out):
+		if(e == 'suspend_resume' and out == 0):
 			sysvals.usetraceevents = True
+	# determine is this log is properly formatted
+	for e in ['SUSPEND START', 'RESUME COMPLETE']:
+		out = os.system('grep -q "'+e+'" '+sysvals.ftracefile)
+		if(out != 0):
+			sysvals.usetracemarkers = False
 
 # Function: appendIncompleteTraceLog
 # Description:
@@ -1055,44 +1864,42 @@ def appendIncompleteTraceLog(testruns):
 
 	# create TestRun vessels for ftrace parsing
 	testcnt = len(testruns)
-	testidx = -1
+	testidx = 0
 	testrun = []
 	for data in testruns:
 		testrun.append(TestRun(data))
 
 	# extract the callgraph and traceevent data
 	vprint('Analyzing the ftrace data...')
+	tp = TestProps()
 	tf = open(sysvals.ftracefile, 'r')
+	data = 0
 	for line in tf:
 		# remove any latent carriage returns
 		line = line.replace('\r\n', '')
-		# grab the time stamp first (signifies the start of the test run)
+		# grab the time stamp
 		m = re.match(sysvals.stampfmt, line)
 		if(m):
-			testidx += 1
-			parseStamp(m, testrun[testidx].data)
-			continue
-		# pull out any firmware data
-		if(re.match(sysvals.firmwarefmt, line)):
-			continue
-		# if we havent found a test time stamp yet keep spinning til we do
-		if(testidx < 0):
+			tp.stamp = line
 			continue
 		# determine the trace data type (required for further parsing)
 		m = re.match(sysvals.tracertypefmt, line)
 		if(m):
-			tracer = m.group('t')
-			testrun[testidx].setTracerType(tracer)
+			tp.setTracerType(m.group('t'))
+			continue
+		# device properties line
+		if(re.match(sysvals.devpropfmt, line)):
+			devProps(line)
 			continue
-		# parse only valid lines, if this isnt one move on
-		m = re.match(testrun[testidx].ftrace_line_fmt, line)
+		# parse only valid lines, if this is not one move on
+		m = re.match(tp.ftrace_line_fmt, line)
 		if(not m):
 			continue
 		# gather the basic message data from the line
 		m_time = m.group('time')
 		m_pid = m.group('pid')
 		m_msg = m.group('msg')
-		if(testrun[testidx].cgformat):
+		if(tp.cgformat):
 			m_param3 = m.group('dur')
 		else:
 			m_param3 = 'traceevent'
@@ -1104,119 +1911,114 @@ def appendIncompleteTraceLog(testruns):
 		# the line should be a call, return, or event
 		if(not t.fcall and not t.freturn and not t.fevent):
 			continue
-		# only parse the ftrace data during suspend/resume
-		data = testrun[testidx].data
-		if(not testrun[testidx].inthepipe):
-			# look for the suspend start marker
-			if(t.fevent):
-				if(t.name == 'SUSPEND START'):
-					testrun[testidx].inthepipe = True
-					data.setStart(t.time)
+		# look for the suspend start marker
+		if(t.startMarker()):
+			data = testrun[testidx].data
+			parseStamp(tp.stamp, data)
+			data.setStart(t.time)
+			continue
+		if(not data):
+			continue
+		# find the end of resume
+		if(t.endMarker()):
+			data.setEnd(t.time)
+			testidx += 1
+			if(testidx >= testcnt):
+				break
+			continue
+		# trace event processing
+		if(t.fevent):
+			# general trace events have two types, begin and end
+			if(re.match('(?P<name>.*) begin$', t.name)):
+				isbegin = True
+			elif(re.match('(?P<name>.*) end$', t.name)):
+				isbegin = False
+			else:
 				continue
-		else:
-			# trace event processing
-			if(t.fevent):
-				if(t.name == 'RESUME COMPLETE'):
-					testrun[testidx].inthepipe = False
-					data.setEnd(t.time)
-					if(testidx == testcnt - 1):
-						break
-					continue
-				# general trace events have two types, begin and end
-				if(re.match('(?P<name>.*) begin$', t.name)):
-					isbegin = True
-				elif(re.match('(?P<name>.*) end$', t.name)):
-					isbegin = False
+			m = re.match('(?P<name>.*)\[(?P<val>[0-9]*)\] .*', t.name)
+			if(m):
+				val = m.group('val')
+				if val == '0':
+					name = m.group('name')
 				else:
-					continue
-				m = re.match('(?P<name>.*)\[(?P<val>[0-9]*)\] .*', t.name)
-				if(m):
-					val = m.group('val')
-					if val == '0':
-						name = m.group('name')
-					else:
-						name = m.group('name')+'['+val+']'
+					name = m.group('name')+'['+val+']'
+			else:
+				m = re.match('(?P<name>.*) .*', t.name)
+				name = m.group('name')
+			# special processing for trace events
+			if re.match('dpm_prepare\[.*', name):
+				continue
+			elif re.match('machine_suspend.*', name):
+				continue
+			elif re.match('suspend_enter\[.*', name):
+				if(not isbegin):
+					data.dmesg['suspend_prepare']['end'] = t.time
+				continue
+			elif re.match('dpm_suspend\[.*', name):
+				if(not isbegin):
+					data.dmesg['suspend']['end'] = t.time
+				continue
+			elif re.match('dpm_suspend_late\[.*', name):
+				if(isbegin):
+					data.dmesg['suspend_late']['start'] = t.time
 				else:
-					m = re.match('(?P<name>.*) .*', t.name)
-					name = m.group('name')
-				# special processing for trace events
-				if re.match('dpm_prepare\[.*', name):
-					continue
-				elif re.match('machine_suspend.*', name):
-					continue
-				elif re.match('suspend_enter\[.*', name):
-					if(not isbegin):
-						data.dmesg['suspend_prepare']['end'] = t.time
-					continue
-				elif re.match('dpm_suspend\[.*', name):
-					if(not isbegin):
-						data.dmesg['suspend']['end'] = t.time
-					continue
-				elif re.match('dpm_suspend_late\[.*', name):
-					if(isbegin):
-						data.dmesg['suspend_late']['start'] = t.time
-					else:
-						data.dmesg['suspend_late']['end'] = t.time
-					continue
-				elif re.match('dpm_suspend_noirq\[.*', name):
-					if(isbegin):
-						data.dmesg['suspend_noirq']['start'] = t.time
-					else:
-						data.dmesg['suspend_noirq']['end'] = t.time
-					continue
-				elif re.match('dpm_resume_noirq\[.*', name):
-					if(isbegin):
-						data.dmesg['resume_machine']['end'] = t.time
-						data.dmesg['resume_noirq']['start'] = t.time
-					else:
-						data.dmesg['resume_noirq']['end'] = t.time
-					continue
-				elif re.match('dpm_resume_early\[.*', name):
-					if(isbegin):
-						data.dmesg['resume_early']['start'] = t.time
-					else:
-						data.dmesg['resume_early']['end'] = t.time
-					continue
-				elif re.match('dpm_resume\[.*', name):
-					if(isbegin):
-						data.dmesg['resume']['start'] = t.time
-					else:
-						data.dmesg['resume']['end'] = t.time
-					continue
-				elif re.match('dpm_complete\[.*', name):
-					if(isbegin):
-						data.dmesg['resume_complete']['start'] = t.time
-					else:
-						data.dmesg['resume_complete']['end'] = t.time
-					continue
-				# is this trace event outside of the devices calls
-				if(data.isTraceEventOutsideDeviceCalls(pid, t.time)):
-					# global events (outside device calls) are simply graphed
-					if(isbegin):
-						# store each trace event in ttemp
-						if(name not in testrun[testidx].ttemp):
-							testrun[testidx].ttemp[name] = []
-						testrun[testidx].ttemp[name].append(\
-							{'begin': t.time, 'end': t.time})
-					else:
-						# finish off matching trace event in ttemp
-						if(name in testrun[testidx].ttemp):
-							testrun[testidx].ttemp[name][-1]['end'] = t.time
+					data.dmesg['suspend_late']['end'] = t.time
+				continue
+			elif re.match('dpm_suspend_noirq\[.*', name):
+				if(isbegin):
+					data.dmesg['suspend_noirq']['start'] = t.time
 				else:
-					if(isbegin):
-						data.addIntraDevTraceEvent('', name, pid, t.time)
-					else:
-						data.capIntraDevTraceEvent('', name, pid, t.time)
-			# call/return processing
-			elif sysvals.usecallgraph:
-				# create a callgraph object for the data
-				if(pid not in testrun[testidx].ftemp):
-					testrun[testidx].ftemp[pid] = []
-					testrun[testidx].ftemp[pid].append(FTraceCallGraph())
-				# when the call is finished, see which device matches it
-				cg = testrun[testidx].ftemp[pid][-1]
-				if(cg.addLine(t, m)):
-					testrun[testidx].ftemp[pid].append(FTraceCallGraph())
+					data.dmesg['suspend_noirq']['end'] = t.time
+				continue
+			elif re.match('dpm_resume_noirq\[.*', name):
+				if(isbegin):
+					data.dmesg['resume_machine']['end'] = t.time
+					data.dmesg['resume_noirq']['start'] = t.time
+				else:
+					data.dmesg['resume_noirq']['end'] = t.time
+				continue
+			elif re.match('dpm_resume_early\[.*', name):
+				if(isbegin):
+					data.dmesg['resume_early']['start'] = t.time
+				else:
+					data.dmesg['resume_early']['end'] = t.time
+				continue
+			elif re.match('dpm_resume\[.*', name):
+				if(isbegin):
+					data.dmesg['resume']['start'] = t.time
+				else:
+					data.dmesg['resume']['end'] = t.time
+				continue
+			elif re.match('dpm_complete\[.*', name):
+				if(isbegin):
+					data.dmesg['resume_complete']['start'] = t.time
+				else:
+					data.dmesg['resume_complete']['end'] = t.time
+				continue
+			# skip trace events inside devices calls
+			if(not data.isTraceEventOutsideDeviceCalls(pid, t.time)):
+				continue
+			# global events (outside device calls) are simply graphed
+			if(isbegin):
+				# store each trace event in ttemp
+				if(name not in testrun[testidx].ttemp):
+					testrun[testidx].ttemp[name] = []
+				testrun[testidx].ttemp[name].append(\
+					{'begin': t.time, 'end': t.time})
+			else:
+				# finish off matching trace event in ttemp
+				if(name in testrun[testidx].ttemp):
+					testrun[testidx].ttemp[name][-1]['end'] = t.time
+		# call/return processing
+		elif sysvals.usecallgraph:
+			# create a callgraph object for the data
+			if(pid not in testrun[testidx].ftemp):
+				testrun[testidx].ftemp[pid] = []
+				testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid))
+			# when the call is finished, see which device matches it
+			cg = testrun[testidx].ftemp[pid][-1]
+			if(cg.addLine(t)):
+				testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid))
 	tf.close()
 
 	for test in testrun:
@@ -1224,20 +2026,14 @@ def appendIncompleteTraceLog(testruns):
 		if(sysvals.usetraceevents):
 			for name in test.ttemp:
 				for event in test.ttemp[name]:
-					begin = event['begin']
-					end = event['end']
-					# if event starts before timeline start, expand timeline
-					if(begin < test.data.start):
-						test.data.setStart(begin)
-					# if event ends after timeline end, expand the timeline
-					if(end > test.data.end):
-						test.data.setEnd(end)
-					test.data.newActionGlobal(name, begin, end)
+					test.data.newActionGlobal(name, event['begin'], event['end'])
 
 		# add the callgraph data to the device hierarchy
 		for pid in test.ftemp:
 			for cg in test.ftemp[pid]:
-				if(not cg.sanityCheck()):
+				if len(cg.list) < 1 or cg.invalid:
+					continue
+				if(not cg.postProcess()):
 					id = 'task %s cpu %s' % (pid, m.group('cpu'))
 					vprint('Sanity check failed for '+\
 						id+', ignoring this callback')
@@ -1259,14 +2055,6 @@ def appendIncompleteTraceLog(testruns):
 		if(sysvals.verbose):
 			test.data.printDetails()
 
-
-	# add the time in between the tests as a new phase so we can see it
-	if(len(testruns) > 1):
-		t1e = testruns[0].getEnd()
-		t2s = testruns[-1].getStart()
-		testruns[-1].newPhaseWithSingleAction('user mode', \
-			'user mode', t1e, t2s, '#FF9966')
-
 # Function: parseTraceLog
 # Description:
 #	 Analyze an ftrace log output file generated from this app during
@@ -1280,9 +2068,16 @@ def parseTraceLog():
 
 	vprint('Analyzing the ftrace data...')
 	if(os.path.exists(sysvals.ftracefile) == False):
-		doError('%s doesnt exist' % sysvals.ftracefile, False)
+		doError('%s does not exist' % sysvals.ftracefile, False)
+
+	sysvals.setupAllKprobes()
+	tracewatch = ['suspend_enter']
+	if sysvals.usekprobes:
+		tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend',
+			'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON', 'CPU_OFF']
 
 	# extract the callgraph and traceevent data
+	tp = TestProps()
 	testruns = []
 	testdata = []
 	testrun = 0
@@ -1295,27 +2090,17 @@ def parseTraceLog():
 		# stamp line: each stamp means a new test run
 		m = re.match(sysvals.stampfmt, line)
 		if(m):
-			data = Data(len(testdata))
-			testdata.append(data)
-			testrun = TestRun(data)
-			testruns.append(testrun)
-			parseStamp(m, data)
-			continue
-		if(not data):
+			tp.stamp = line
 			continue
 		# firmware line: pull out any firmware data
 		m = re.match(sysvals.firmwarefmt, line)
 		if(m):
-			data.fwSuspend = int(m.group('s'))
-			data.fwResume = int(m.group('r'))
-			if(data.fwSuspend > 0 or data.fwResume > 0):
-				data.fwValid = True
+			tp.fwdata.append((int(m.group('s')), int(m.group('r'))))
 			continue
 		# tracer type line: determine the trace data type
 		m = re.match(sysvals.tracertypefmt, line)
 		if(m):
-			tracer = m.group('t')
-			testrun.setTracerType(tracer)
+			tp.setTracerType(m.group('t'))
 			continue
 		# post resume time line: did this test run include post-resume data
 		m = re.match(sysvals.postresumefmt, line)
@@ -1324,15 +2109,20 @@ def parseTraceLog():
 			if(t > 0):
 				sysvals.postresumetime = t
 			continue
+		# device properties line
+		if(re.match(sysvals.devpropfmt, line)):
+			devProps(line)
+			continue
 		# ftrace line: parse only valid lines
-		m = re.match(testrun.ftrace_line_fmt, line)
+		m = re.match(tp.ftrace_line_fmt, line)
 		if(not m):
 			continue
 		# gather the basic message data from the line
 		m_time = m.group('time')
+		m_proc = m.group('proc')
 		m_pid = m.group('pid')
 		m_msg = m.group('msg')
-		if(testrun.cgformat):
+		if(tp.cgformat):
 			m_param3 = m.group('dur')
 		else:
 			m_param3 = 'traceevent'
@@ -1344,24 +2134,38 @@ def parseTraceLog():
 		# the line should be a call, return, or event
 		if(not t.fcall and not t.freturn and not t.fevent):
 			continue
-		# only parse the ftrace data during suspend/resume
-		if(not testrun.inthepipe):
-			# look for the suspend start marker
-			if(t.fevent):
-				if(t.name == 'SUSPEND START'):
-					testrun.inthepipe = True
-					data.setStart(t.time)
+		# find the start of suspend
+		if(t.startMarker()):
+			phase = 'suspend_prepare'
+			data = Data(len(testdata))
+			testdata.append(data)
+			testrun = TestRun(data)
+			testruns.append(testrun)
+			parseStamp(tp.stamp, data)
+			if len(tp.fwdata) > data.testnumber:
+				data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
+				if(data.fwSuspend > 0 or data.fwResume > 0):
+					data.fwValid = True
+			data.setStart(t.time)
+			continue
+		if(not data):
+			continue
+		# find the end of resume
+		if(t.endMarker()):
+			if(sysvals.usetracemarkers and sysvals.postresumetime > 0):
+				phase = 'post_resume'
+				data.newPhase(phase, t.time, t.time, '#F0F0F0', -1)
+			data.setEnd(t.time)
+			if(not sysvals.usetracemarkers):
+				# no trace markers? then quit and be sure to finish recording
+				# the event we used to trigger resume end
+				if(len(testrun.ttemp['thaw_processes']) > 0):
+					# if an entry exists, assume this is its end
+					testrun.ttemp['thaw_processes'][-1]['end'] = t.time
+				break
 			continue
 		# trace event processing
 		if(t.fevent):
-			if(t.name == 'RESUME COMPLETE'):
-				if(sysvals.postresumetime > 0):
-					phase = 'post_resume'
-					data.newPhase(phase, t.time, t.time, '#FF9966', -1)
-				else:
-					testrun.inthepipe = False
-				data.setEnd(t.time)
-				continue
 			if(phase == 'post_resume'):
 				data.setEnd(t.time)
 			if(t.type == 'suspend_resume'):
@@ -1383,8 +2187,7 @@ def parseTraceLog():
 					m = re.match('(?P<name>.*) .*', t.name)
 					name = m.group('name')
 				# ignore these events
-				if(re.match('acpi_suspend\[.*', t.name) or
-					re.match('suspend_enter\[.*', name)):
+				if(name.split('[')[0] in tracewatch):
 					continue
 				# -- phase changes --
 				# suspend_prepare start
@@ -1418,7 +2221,7 @@ def parseTraceLog():
 						data.dmesg[phase]['end'] = t.time
 						data.tSuspended = t.time
 					else:
-						if(sysvals.suspendmode in ['mem', 'disk']):
+						if(sysvals.suspendmode in ['mem', 'disk'] and not tp.S0i3):
 							data.dmesg['suspend_machine']['end'] = t.time
 							data.tSuspended = t.time
 						phase = 'resume_machine'
@@ -1426,6 +2229,15 @@ def parseTraceLog():
 						data.tResumed = t.time
 						data.tLow = data.tResumed - data.tSuspended
 					continue
+				# acpi_suspend
+				elif(re.match('acpi_suspend\[.*', t.name)):
+					# acpi_suspend[0] S0i3
+					if(re.match('acpi_suspend\[0\] begin', t.name)):
+						if(sysvals.suspendmode == 'mem'):
+							tp.S0i3 = True
+							data.dmesg['suspend_machine']['end'] = t.time
+							data.tSuspended = t.time
+					continue
 				# resume_noirq start
 				elif(re.match('dpm_resume_noirq\[.*', t.name)):
 					phase = 'resume_noirq'
@@ -1449,30 +2261,25 @@ def parseTraceLog():
 					if(isbegin):
 						data.dmesg[phase]['start'] = t.time
 					continue
-
-				# is this trace event outside of the devices calls
-				if(data.isTraceEventOutsideDeviceCalls(pid, t.time)):
-					# global events (outside device calls) are simply graphed
-					if(name not in testrun.ttemp):
-						testrun.ttemp[name] = []
-					if(isbegin):
-						# create a new list entry
-						testrun.ttemp[name].append(\
-							{'begin': t.time, 'end': t.time})
-					else:
-						if(len(testrun.ttemp[name]) > 0):
-							# if an antry exists, assume this is its end
-							testrun.ttemp[name][-1]['end'] = t.time
-						elif(phase == 'post_resume'):
-							# post resume events can just have ends
-							testrun.ttemp[name].append({
-								'begin': data.dmesg[phase]['start'],
-								'end': t.time})
+				# skip trace events inside devices calls
+				if(not data.isTraceEventOutsideDeviceCalls(pid, t.time)):
+					continue
+				# global events (outside device calls) are graphed
+				if(name not in testrun.ttemp):
+					testrun.ttemp[name] = []
+				if(isbegin):
+					# create a new list entry
+					testrun.ttemp[name].append(\
+						{'begin': t.time, 'end': t.time, 'pid': pid})
 				else:
-					if(isbegin):
-						data.addIntraDevTraceEvent('', name, pid, t.time)
-					else:
-						data.capIntraDevTraceEvent('', name, pid, t.time)
+					if(len(testrun.ttemp[name]) > 0):
+						# if an entry exists, assume this is its end
+						testrun.ttemp[name][-1]['end'] = t.time
+					elif(phase == 'post_resume'):
+						# post resume events can just have ends
+						testrun.ttemp[name].append({
+							'begin': data.dmesg[phase]['start'],
+							'end': t.time})
 			# device callback start
 			elif(t.type == 'device_pm_callback_start'):
 				m = re.match('(?P<drv>.*) (?P<d>.*), parent: *(?P<p>.*), .*',\
@@ -1495,75 +2302,127 @@ def parseTraceLog():
 					dev = list[n]
 					dev['length'] = t.time - dev['start']
 					dev['end'] = t.time
+		# kprobe event processing
+		elif(t.fkprobe):
+			kprobename = t.type
+			kprobedata = t.name
+			key = (kprobename, pid)
+			# displayname is generated from kprobe data
+			displayname = ''
+			if(t.fcall):
+				displayname = sysvals.kprobeDisplayName(kprobename, kprobedata)
+				if not displayname:
+					continue
+				if(key not in tp.ktemp):
+					tp.ktemp[key] = []
+				tp.ktemp[key].append({
+					'pid': pid,
+					'begin': t.time,
+					'end': t.time,
+					'name': displayname,
+					'cdata': kprobedata,
+					'proc': m_proc,
+				})
+			elif(t.freturn):
+				if(key not in tp.ktemp) or len(tp.ktemp[key]) < 1:
+					continue
+				e = tp.ktemp[key][-1]
+				if e['begin'] < 0.0 or t.time - e['begin'] < 0.000001:
+					tp.ktemp[key].pop()
+				else:
+					e['end'] = t.time
+					e['rdata'] = kprobedata
 		# callgraph processing
 		elif sysvals.usecallgraph:
-			# this shouldn't happen, but JIC, ignore callgraph data post-res
-			if(phase == 'post_resume'):
-				continue
 			# create a callgraph object for the data
-			if(pid not in testrun.ftemp):
-				testrun.ftemp[pid] = []
-				testrun.ftemp[pid].append(FTraceCallGraph())
+			key = (m_proc, pid)
+			if(key not in testrun.ftemp):
+				testrun.ftemp[key] = []
+				testrun.ftemp[key].append(FTraceCallGraph(pid))
 			# when the call is finished, see which device matches it
-			cg = testrun.ftemp[pid][-1]
-			if(cg.addLine(t, m)):
-				testrun.ftemp[pid].append(FTraceCallGraph())
+			cg = testrun.ftemp[key][-1]
+			if(cg.addLine(t)):
+				testrun.ftemp[key].append(FTraceCallGraph(pid))
 	tf.close()
 
+	if sysvals.suspendmode == 'command':
+		for test in testruns:
+			for p in test.data.phases:
+				if p == 'resume_complete':
+					test.data.dmesg[p]['start'] = test.data.start
+					test.data.dmesg[p]['end'] = test.data.end
+				else:
+					test.data.dmesg[p]['start'] = test.data.start
+					test.data.dmesg[p]['end'] = test.data.start
+			test.data.tSuspended = test.data.start
+			test.data.tResumed = test.data.start
+			test.data.tLow = 0
+			test.data.fwValid = False
+
 	for test in testruns:
 		# add the traceevent data to the device hierarchy
 		if(sysvals.usetraceevents):
+			# add actual trace funcs
 			for name in test.ttemp:
 				for event in test.ttemp[name]:
-					begin = event['begin']
-					end = event['end']
-					# if event starts before timeline start, expand timeline
-					if(begin < test.data.start):
-						test.data.setStart(begin)
-					# if event ends after timeline end, expand the timeline
-					if(end > test.data.end):
-						test.data.setEnd(end)
-					test.data.newActionGlobal(name, begin, end)
-
-		# add the callgraph data to the device hierarchy
-		borderphase = {
-			'dpm_prepare': 'suspend_prepare',
-			'dpm_complete': 'resume_complete'
-		}
-		for pid in test.ftemp:
-			for cg in test.ftemp[pid]:
-				if len(cg.list) < 2:
+					test.data.newActionGlobal(name, event['begin'], event['end'], event['pid'])
+			# add the kprobe based virtual tracefuncs as actual devices
+			for key in tp.ktemp:
+				name, pid = key
+				if name not in sysvals.tracefuncs:
 					continue
-				if(not cg.sanityCheck()):
-					id = 'task %s cpu %s' % (pid, m.group('cpu'))
-					vprint('Sanity check failed for '+\
-						id+', ignoring this callback')
+				for e in tp.ktemp[key]:
+					kb, ke = e['begin'], e['end']
+					if kb == ke or not test.data.isInsideTimeline(kb, ke):
+						continue
+					test.data.newActionGlobal(e['name'], kb, ke, pid)
+			# add config base kprobes and dev kprobes
+			for key in tp.ktemp:
+				name, pid = key
+				if name in sysvals.tracefuncs:
 					continue
-				callstart = cg.start
-				callend = cg.end
-				if(cg.list[0].name in borderphase):
-					p = borderphase[cg.list[0].name]
-					list = test.data.dmesg[p]['list']
-					for devname in list:
-						dev = list[devname]
-						if(pid == dev['pid'] and
-							callstart <= dev['start'] and
-							callend >= dev['end']):
-							dev['ftrace'] = cg.slice(dev['start'], dev['end'])
-					continue
-				if(cg.list[0].name != 'dpm_run_callback'):
-					continue
-				for p in test.data.phases:
-					if(test.data.dmesg[p]['start'] <= callstart and
-						callstart <= test.data.dmesg[p]['end']):
-						list = test.data.dmesg[p]['list']
-						for devname in list:
-							dev = list[devname]
-							if(pid == dev['pid'] and
-								callstart <= dev['start'] and
-								callend >= dev['end']):
-								dev['ftrace'] = cg
-						break
+				for e in tp.ktemp[key]:
+					kb, ke = e['begin'], e['end']
+					if kb == ke or not test.data.isInsideTimeline(kb, ke):
+						continue
+					color = sysvals.kprobeColor(e['name'])
+					if name not in sysvals.dev_tracefuncs:
+						# config base kprobe
+						test.data.newActionGlobal(e['name'], kb, ke, -2, color)
+					elif sysvals.usedevsrc:
+						# dev kprobe
+						data.addDeviceFunctionCall(e['name'], name, e['proc'], pid, kb,
+							ke, e['cdata'], e['rdata'])
+		if sysvals.usecallgraph:
+			# add the callgraph data to the device hierarchy
+			sortlist = dict()
+			for key in test.ftemp:
+				proc, pid = key
+				for cg in test.ftemp[key]:
+					if len(cg.list) < 1 or cg.invalid:
+						continue
+					if(not cg.postProcess()):
+						id = 'task %s' % (pid)
+						vprint('Sanity check failed for '+\
+							id+', ignoring this callback')
+						continue
+					# match cg data to devices
+					if sysvals.suspendmode == 'command' or not cg.deviceMatch(pid, test.data):
+						sortkey = '%f%f%d' % (cg.start, cg.end, pid)
+						sortlist[sortkey] = cg
+			# create blocks for orphan cg data
+			for sortkey in sorted(sortlist):
+				cg = sortlist[sortkey]
+				name = cg.list[0].name
+				if sysvals.isCallgraphFunc(name):
+					vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name))
+					cg.newActionFromFunction(test.data)
+
+	if sysvals.suspendmode == 'command':
+		if(sysvals.verbose):
+			for data in testdata:
+				data.printDetails()
+		return testdata
 
 	# fill in any missing phases
 	for data in testdata:
@@ -1587,14 +2446,52 @@ def parseTraceLog():
 		if(sysvals.verbose):
 			data.printDetails()
 
-	# add the time in between the tests as a new phase so we can see it
-	if(len(testdata) > 1):
-		t1e = testdata[0].getEnd()
-		t2s = testdata[-1].getStart()
-		testdata[-1].newPhaseWithSingleAction('user mode', \
-			'user mode', t1e, t2s, '#FF9966')
 	return testdata
 
+# Function: loadRawKernelLog
+# Description:
+#	 Load a raw kernel log that wasn't created by this tool, it might be
+#	 possible to extract a valid suspend/resume log
+def loadRawKernelLog(dmesgfile):
+	global sysvals
+
+	stamp = {'time': '', 'host': '', 'mode': 'mem', 'kernel': ''}
+	stamp['time'] = datetime.now().strftime('%B %d %Y, %I:%M:%S %p')
+	stamp['host'] = sysvals.hostname
+
+	testruns = []
+	data = 0
+	lf = open(dmesgfile, 'r')
+	for line in lf:
+		line = line.replace('\r\n', '')
+		idx = line.find('[')
+		if idx > 1:
+			line = line[idx:]
+		m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
+		if(not m):
+			continue
+		msg = m.group("msg")
+		m = re.match('PM: Syncing filesystems.*', msg)
+		if(m):
+			if(data):
+				testruns.append(data)
+			data = Data(len(testruns))
+			data.stamp = stamp
+		if(data):
+			m = re.match('.* *(?P<k>[0-9]\.[0-9]{2}\.[0-9]-.*) .*', msg)
+			if(m):
+				stamp['kernel'] = m.group('k')
+			m = re.match('PM: Preparing system for (?P<m>.*) sleep', msg)
+			if(m):
+				stamp['mode'] = m.group('m')
+			data.dmesgtext.append(line)
+	if(data):
+		testruns.append(data)
+		sysvals.stamp = stamp
+		sysvals.suspendmode = stamp['mode']
+	lf.close()
+	return testruns
+
 # Function: loadKernelLog
 # Description:
 #	 [deprecated for kernel 3.15.0 or newer]
@@ -1607,9 +2504,10 @@ def loadKernelLog():
 
 	vprint('Analyzing the dmesg data...')
 	if(os.path.exists(sysvals.dmesgfile) == False):
-		doError('%s doesnt exist' % sysvals.dmesgfile, False)
+		doError('%s does not exist' % sysvals.dmesgfile, False)
 
-	# there can be multiple test runs in a single file delineated by stamps
+	# there can be multiple test runs in a single file
+	tp = TestProps()
 	testruns = []
 	data = 0
 	lf = open(sysvals.dmesgfile, 'r')
@@ -1620,35 +2518,43 @@ def loadKernelLog():
 			line = line[idx:]
 		m = re.match(sysvals.stampfmt, line)
 		if(m):
-			if(data):
-				testruns.append(data)
-			data = Data(len(testruns))
-			parseStamp(m, data)
-			continue
-		if(not data):
+			tp.stamp = line
 			continue
 		m = re.match(sysvals.firmwarefmt, line)
 		if(m):
-			data.fwSuspend = int(m.group('s'))
-			data.fwResume = int(m.group('r'))
-			if(data.fwSuspend > 0 or data.fwResume > 0):
-				data.fwValid = True
+			tp.fwdata.append((int(m.group('s')), int(m.group('r'))))
 			continue
 		m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
-		if(m):
-			data.dmesgtext.append(line)
-			if(re.match('ACPI: resume from mwait', m.group('msg'))):
-				print('NOTE: This suspend appears to be freeze rather than'+\
-					' %s, it will be treated as such' % sysvals.suspendmode)
-				sysvals.suspendmode = 'freeze'
-		else:
-			vprint('ignoring dmesg line: %s' % line.replace('\n', ''))
-	testruns.append(data)
+		if(not m):
+			continue
+		msg = m.group("msg")
+		if(re.match('PM: Syncing filesystems.*', msg)):
+			if(data):
+				testruns.append(data)
+			data = Data(len(testruns))
+			parseStamp(tp.stamp, data)
+			if len(tp.fwdata) > data.testnumber:
+				data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
+				if(data.fwSuspend > 0 or data.fwResume > 0):
+					data.fwValid = True
+		if(re.match('ACPI: resume from mwait', msg)):
+			print('NOTE: This suspend appears to be freeze rather than'+\
+				' %s, it will be treated as such' % sysvals.suspendmode)
+			sysvals.suspendmode = 'freeze'
+		if(not data):
+			continue
+		data.dmesgtext.append(line)
+	if(data):
+		testruns.append(data)
 	lf.close()
 
-	if(not data):
-		print('ERROR: analyze_suspend header missing from dmesg log')
-		sys.exit()
+	if(len(testruns) < 1):
+		# bad log, but see if you can extract something meaningful anyway
+		testruns = loadRawKernelLog(sysvals.dmesgfile)
+
+	if(len(testruns) < 1):
+		doError(' dmesg log is completely unreadable: %s' \
+			% sysvals.dmesgfile, False)
 
 	# fix lines with same timestamp/function with the call and return swapped
 	for data in testruns:
@@ -1865,7 +2771,8 @@ def parseKernelLog(data):
 						actions[a] = []
 					actions[a].append({'begin': ktime, 'end': ktime})
 				if(re.match(at[a]['emsg'], msg)):
-					actions[a][-1]['end'] = ktime
+					if(a in actions):
+						actions[a][-1]['end'] = ktime
 			# now look for CPU on/off events
 			if(re.match('Disabling non-boot CPUs .*', msg)):
 				# start of first cpu suspend
@@ -1912,15 +2819,7 @@ def parseKernelLog(data):
 	# fill in any actions we've found
 	for name in actions:
 		for event in actions[name]:
-			begin = event['begin']
-			end = event['end']
-			# if event starts before timeline start, expand timeline
-			if(begin < data.start):
-				data.setStart(begin)
-			# if event ends after timeline end, expand the timeline
-			if(end > data.end):
-				data.setEnd(end)
-			data.newActionGlobal(name, begin, end)
+			data.newActionGlobal(name, event['begin'], event['end'])
 
 	if(sysvals.verbose):
 		data.printDetails()
@@ -1929,92 +2828,6 @@ def parseKernelLog(data):
 	data.fixupInitcallsThatDidntReturn()
 	return True
 
-# Function: setTimelineRows
-# Description:
-#	 Organize the timeline entries into the smallest
-#	 number of rows possible, with no entry overlapping
-# Arguments:
-#	 list: the list of devices/actions for a single phase
-#	 sortedkeys: cronologically sorted key list to use
-# Output:
-#	 The total number of rows needed to display this phase of the timeline
-def setTimelineRows(list, sortedkeys):
-
-	# clear all rows and set them to undefined
-	remaining = len(list)
-	rowdata = dict()
-	row = 0
-	for item in list:
-		list[item]['row'] = -1
-
-	# try to pack each row with as many ranges as possible
-	while(remaining > 0):
-		if(row not in rowdata):
-			rowdata[row] = []
-		for item in sortedkeys:
-			if(list[item]['row'] < 0):
-				s = list[item]['start']
-				e = list[item]['end']
-				valid = True
-				for ritem in rowdata[row]:
-					rs = ritem['start']
-					re = ritem['end']
-					if(not (((s <= rs) and (e <= rs)) or
-						((s >= re) and (e >= re)))):
-						valid = False
-						break
-				if(valid):
-					rowdata[row].append(list[item])
-					list[item]['row'] = row
-					remaining -= 1
-		row += 1
-	return row
-
-# Function: createTimeScale
-# Description:
-#	 Create the timescale header for the html timeline
-# Arguments:
-#	 t0: start time (suspend begin)
-#	 tMax: end time (resume end)
-#	 tSuspend: time when suspend occurs, i.e. the zero time
-# Output:
-#	 The html code needed to display the time scale
-def createTimeScale(t0, tMax, tSuspended):
-	timescale = '<div class="t" style="right:{0}%">{1}</div>\n'
-	output = '<div id="timescale">\n'
-
-	# set scale for timeline
-	tTotal = tMax - t0
-	tS = 0.1
-	if(tTotal <= 0):
-		return output
-	if(tTotal > 4):
-		tS = 1
-	if(tSuspended < 0):
-		for i in range(int(tTotal/tS)+1):
-			pos = '%0.3f' % (100 - ((float(i)*tS*100)/tTotal))
-			if(i > 0):
-				val = '%0.fms' % (float(i)*tS*1000)
-			else:
-				val = ''
-			output += timescale.format(pos, val)
-	else:
-		tSuspend = tSuspended - t0
-		divTotal = int(tTotal/tS) + 1
-		divSuspend = int(tSuspend/tS)
-		s0 = (tSuspend - tS*divSuspend)*100/tTotal
-		for i in range(divTotal):
-			pos = '%0.3f' % (100 - ((float(i)*tS*100)/tTotal) - s0)
-			if((i == 0) and (s0 < 3)):
-				val = ''
-			elif(i == divSuspend):
-				val = 'S/R'
-			else:
-				val = '%0.fms' % (float(i-divSuspend)*tS*1000)
-			output += timescale.format(pos, val)
-	output += '</div>\n'
-	return output
-
 # Function: createHTMLSummarySimple
 # Description:
 #	 Create summary html file for a series of tests
@@ -2146,6 +2959,32 @@ def createHTMLSummarySimple(testruns, htmlfile):
 	hf.write('</body>\n</html>\n')
 	hf.close()
 
+def htmlTitle():
+	global sysvals
+	modename = {
+		'freeze': 'Freeze (S0)',
+		'standby': 'Standby (S1)',
+		'mem': 'Suspend (S3)',
+		'disk': 'Hibernate (S4)'
+	}
+	kernel = sysvals.stamp['kernel']
+	host = sysvals.hostname[0].upper()+sysvals.hostname[1:]
+	mode = sysvals.suspendmode
+	if sysvals.suspendmode in modename:
+		mode = modename[sysvals.suspendmode]
+	return host+' '+mode+' '+kernel
+
+def ordinal(value):
+	suffix = 'th'
+	if value < 10 or value > 19:
+		if value % 10 == 1:
+			suffix = 'st'
+		elif value % 10 == 2:
+			suffix = 'nd'
+		elif value % 10 == 3:
+			suffix = 'rd'
+	return '%d%s' % (value, suffix)
+
 # Function: createHTML
 # Description:
 #	 Create the output html file from the resident test data
@@ -2156,6 +2995,10 @@ def createHTMLSummarySimple(testruns, htmlfile):
 def createHTML(testruns):
 	global sysvals
 
+	if len(testruns) < 1:
+		print('ERROR: Not enough test data to build a timeline')
+		return
+
 	for data in testruns:
 		data.normalizeTime(testruns[-1].tSuspended)
 
@@ -2163,16 +3006,18 @@ def createHTML(testruns):
 	if len(testruns) > 1:
 		x2changes = ['1', 'relative']
 	# html function templates
+	headline_version = '<div class="version"><a href="https://01.org/suspendresume">AnalyzeSuspend v%s</a></div>' % sysvals.version
 	headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
 	html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail%s</button>' % x2changes[0]
 	html_zoombox = '<center><button id="zoomin">ZOOM IN</button><button id="zoomout">ZOOM OUT</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
 	html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
 	html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
-	html_device = '<div id="{0}" title="{1}" class="thread" style="left:{2}%;top:{3}%;height:{4}%;width:{5}%;">{6}</div>\n'
-	html_traceevent = '<div title="{0}" class="traceevent" style="left:{1}%;top:{2}%;height:{3}%;width:{4}%;border:1px solid {5};background-color:{5}">{6}</div>\n'
-	html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}%;height:{3}%;background-color:{4}">{5}</div>\n'
+	html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;">\n'
+	html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
+	html_traceevent = '<div title="{0}" class="traceevent" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{5}</div>\n'
+	html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background-color:{4}">{5}</div>\n'
 	html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background-color:{3}"></div>\n'
-	html_legend = '<div class="square" style="left:{0}%;background-color:{1}">&nbsp;{2}</div>\n'
+	html_legend = '<div id="p{3}" class="square" style="left:{0}%;background-color:{1}">&nbsp;{2}</div>\n'
 	html_timetotal = '<table class="time1">\n<tr>'\
 		'<td class="green">{2} Suspend Time: <b>{0} ms</b></td>'\
 		'<td class="yellow">{2} Resume Time: <b>{1} ms</b></td>'\
@@ -2182,6 +3027,10 @@ def createHTML(testruns):
 		'<td class="gray">'+sysvals.suspendmode+' time: <b>{1} ms</b></td>'\
 		'<td class="yellow">{3} Resume Time: <b>{2} ms</b></td>'\
 		'</tr>\n</table>\n'
+	html_timetotal3 = '<table class="time1">\n<tr>'\
+		'<td class="green">Execution Time: <b>{0} ms</b></td>'\
+		'<td class="yellow">Command: <b>{1}</b></td>'\
+		'</tr>\n</table>\n'
 	html_timegroups = '<table class="time2">\n<tr>'\
 		'<td class="green">{4}Kernel Suspend: {0} ms</td>'\
 		'<td class="purple">{4}Firmware Suspend: {1} ms</td>'\
@@ -2189,12 +3038,21 @@ def createHTML(testruns):
 		'<td class="yellow">{4}Kernel Resume: {3} ms</td>'\
 		'</tr>\n</table>\n'
 
+	# html format variables
+	rowheight = 30
+	devtextS = '14px'
+	devtextH = '30px'
+	hoverZ = 'z-index:10;'
+
+	if sysvals.usedevsrc:
+		hoverZ = ''
+
 	# device timeline
 	vprint('Creating Device Timeline...')
-	devtl = Timeline()
+
+	devtl = Timeline(rowheight)
 
 	# Generate the header for this timeline
-	textnum = ['First', 'Second']
 	for data in testruns:
 		tTotal = data.end - data.start
 		tEnd = data.dmesg['resume_complete']['end']
@@ -2203,7 +3061,17 @@ def createHTML(testruns):
 			sys.exit()
 		if(data.tLow > 0):
 			low_time = '%.0f'%(data.tLow*1000)
-		if data.fwValid:
+		if sysvals.suspendmode == 'command':
+			run_time = '%.0f'%((data.end-data.start)*1000)
+			if sysvals.testcommand:
+				testdesc = sysvals.testcommand
+			else:
+				testdesc = 'unknown'
+			if(len(testruns) > 1):
+				testdesc = ordinal(data.testnumber+1)+' '+testdesc
+			thtml = html_timetotal3.format(run_time, testdesc)
+			devtl.html['header'] += thtml
+		elif data.fwValid:
 			suspend_time = '%.0f'%((data.tSuspended-data.start)*1000 + \
 				(data.fwSuspend/1000000.0))
 			resume_time = '%.0f'%((tEnd-data.tSuspended)*1000 + \
@@ -2211,7 +3079,7 @@ def createHTML(testruns):
 			testdesc1 = 'Total'
 			testdesc2 = ''
 			if(len(testruns) > 1):
-				testdesc1 = testdesc2 = textnum[data.testnumber]
+				testdesc1 = testdesc2 = ordinal(data.testnumber+1)
 				testdesc2 += ' '
 			if(data.tLow == 0):
 				thtml = html_timetotal.format(suspend_time, \
@@ -2219,28 +3087,28 @@ def createHTML(testruns):
 			else:
 				thtml = html_timetotal2.format(suspend_time, low_time, \
 					resume_time, testdesc1)
-			devtl.html['timeline'] += thtml
+			devtl.html['header'] += thtml
 			sktime = '%.3f'%((data.dmesg['suspend_machine']['end'] - \
 				data.getStart())*1000)
 			sftime = '%.3f'%(data.fwSuspend / 1000000.0)
 			rftime = '%.3f'%(data.fwResume / 1000000.0)
-			rktime = '%.3f'%((data.getEnd() - \
+			rktime = '%.3f'%((data.dmesg['resume_complete']['end'] - \
 				data.dmesg['resume_machine']['start'])*1000)
-			devtl.html['timeline'] += html_timegroups.format(sktime, \
+			devtl.html['header'] += html_timegroups.format(sktime, \
 				sftime, rftime, rktime, testdesc2)
 		else:
 			suspend_time = '%.0f'%((data.tSuspended-data.start)*1000)
 			resume_time = '%.0f'%((tEnd-data.tSuspended)*1000)
 			testdesc = 'Kernel'
 			if(len(testruns) > 1):
-				testdesc = textnum[data.testnumber]+' '+testdesc
+				testdesc = ordinal(data.testnumber+1)+' '+testdesc
 			if(data.tLow == 0):
 				thtml = html_timetotal.format(suspend_time, \
 					resume_time, testdesc)
 			else:
 				thtml = html_timetotal2.format(suspend_time, low_time, \
 					resume_time, testdesc)
-			devtl.html['timeline'] += thtml
+			devtl.html['header'] += thtml
 
 	# time scale for potentially multiple datasets
 	t0 = testruns[0].start
@@ -2249,153 +3117,241 @@ def createHTML(testruns):
 	tTotal = tMax - t0
 
 	# determine the maximum number of rows we need to draw
-	timelinerows = 0
 	for data in testruns:
-		for phase in data.dmesg:
-			list = data.dmesg[phase]['list']
-			rows = setTimelineRows(list, list)
-			data.dmesg[phase]['row'] = rows
-			if(rows > timelinerows):
-				timelinerows = rows
-
-	# calculate the timeline height and create bounding box, add buttons
-	devtl.setRows(timelinerows + 1)
-	devtl.html['timeline'] += html_devlist1
-	if len(testruns) > 1:
-		devtl.html['timeline'] += html_devlist2
+		data.selectTimelineDevices('%f', tTotal, sysvals.mindevlen)
+		for group in data.devicegroups:
+			devlist = []
+			for phase in group:
+				for devname in data.tdevlist[phase]:
+					devlist.append((phase,devname))
+			devtl.getPhaseRows(data.dmesg, devlist)
+	devtl.calcTotalRows()
+
+	# create bounding box, add buttons
+	if sysvals.suspendmode != 'command':
+		devtl.html['timeline'] += html_devlist1
+		if len(testruns) > 1:
+			devtl.html['timeline'] += html_devlist2
 	devtl.html['timeline'] += html_zoombox
 	devtl.html['timeline'] += html_timeline.format('dmesg', devtl.height)
 
-	# draw the colored boxes for each of the phases
-	for data in testruns:
-		for b in data.dmesg:
-			phase = data.dmesg[b]
-			length = phase['end']-phase['start']
-			left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal)
-			width = '%.3f' % ((length*100.0)/tTotal)
-			devtl.html['timeline'] += html_phase.format(left, width, \
-				'%.3f'%devtl.scaleH, '%.3f'%(100-devtl.scaleH), \
-				data.dmesg[b]['color'], '')
+	# draw the full timeline
+	phases = {'suspend':[],'resume':[]}
+	for phase in data.dmesg:
+		if 'resume' in phase:
+			phases['resume'].append(phase)
+		else:
+			phases['suspend'].append(phase)
 
-	# draw the time scale, try to make the number of labels readable
-	devtl.html['scale'] = createTimeScale(t0, tMax, tSuspended)
-	devtl.html['timeline'] += devtl.html['scale']
+	# draw each test run chronologically
 	for data in testruns:
-		for b in data.dmesg:
-			phaselist = data.dmesg[b]['list']
-			for d in phaselist:
-				name = d
-				drv = ''
-				dev = phaselist[d]
-				if(d in sysvals.altdevname):
-					name = sysvals.altdevname[d]
-				if('drv' in dev and dev['drv']):
-					drv = ' {%s}' % dev['drv']
-				height = (100.0 - devtl.scaleH)/data.dmesg[b]['row']
-				top = '%.3f' % ((dev['row']*height) + devtl.scaleH)
-				left = '%.3f' % (((dev['start']-t0)*100)/tTotal)
-				width = '%.3f' % (((dev['end']-dev['start'])*100)/tTotal)
-				length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
-				color = 'rgba(204,204,204,0.5)'
-				devtl.html['timeline'] += html_device.format(dev['id'], \
-					d+drv+length+b, left, top, '%.3f'%height, width, name+drv)
-
-	# draw any trace events found
-	for data in testruns:
-		for b in data.dmesg:
-			phaselist = data.dmesg[b]['list']
-			for name in phaselist:
-				dev = phaselist[name]
-				if('traceevents' in dev):
-					vprint('Debug trace events found for device %s' % name)
-					vprint('%20s %20s %10s %8s' % ('action', \
+		# if nore than one test, draw a block to represent user mode
+		if(data.testnumber > 0):
+			m0 = testruns[data.testnumber-1].end
+			mMax = testruns[data.testnumber].start
+			mTotal = mMax - m0
+			name = 'usermode%d' % data.testnumber
+			top = '%d' % devtl.scaleH
+			left = '%f' % (((m0-t0)*100.0)/tTotal)
+			width = '%f' % ((mTotal*100.0)/tTotal)
+			title = 'user mode (%0.3f ms) ' % (mTotal*1000)
+			devtl.html['timeline'] += html_device.format(name, \
+				title, left, top, '%d'%devtl.bodyH, width, '', '', '')
+		# now draw the actual timeline blocks
+		for dir in phases:
+			# draw suspend and resume blocks separately
+			bname = '%s%d' % (dir[0], data.testnumber)
+			if dir == 'suspend':
+				m0 = testruns[data.testnumber].start
+				mMax = testruns[data.testnumber].tSuspended
+				mTotal = mMax - m0
+				left = '%f' % (((m0-t0)*100.0)/tTotal)
+			else:
+				m0 = testruns[data.testnumber].tSuspended
+				mMax = testruns[data.testnumber].end
+				mTotal = mMax - m0
+				left = '%f' % ((((m0-t0)*100.0)+sysvals.srgap/2)/tTotal)
+			# if a timeline block is 0 length, skip altogether
+			if mTotal == 0:
+				continue
+			width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal)
+			devtl.html['timeline'] += html_tblock.format(bname, left, width)
+			for b in sorted(phases[dir]):
+				# draw the phase color background
+				phase = data.dmesg[b]
+				length = phase['end']-phase['start']
+				left = '%f' % (((phase['start']-m0)*100.0)/mTotal)
+				width = '%f' % ((length*100.0)/mTotal)
+				devtl.html['timeline'] += html_phase.format(left, width, \
+					'%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
+					data.dmesg[b]['color'], '')
+				# draw the devices for this phase
+				phaselist = data.dmesg[b]['list']
+				for d in data.tdevlist[b]:
+					name = d
+					drv = ''
+					dev = phaselist[d]
+					xtraclass = ''
+					xtrainfo = ''
+					xtrastyle = ''
+					if 'htmlclass' in dev:
+						xtraclass = dev['htmlclass']
+						xtrainfo = dev['htmlclass']
+					if 'color' in dev:
+						xtrastyle = 'background-color:%s;' % dev['color']
+					if(d in sysvals.devprops):
+						name = sysvals.devprops[d].altName(d)
+						xtraclass = sysvals.devprops[d].xtraClass()
+						xtrainfo = sysvals.devprops[d].xtraInfo()
+					if('drv' in dev and dev['drv']):
+						drv = ' {%s}' % dev['drv']
+					rowheight = devtl.phaseRowHeight(b, dev['row'])
+					rowtop = devtl.phaseRowTop(b, dev['row'])
+					top = '%.3f' % (rowtop + devtl.scaleH)
+					left = '%f' % (((dev['start']-m0)*100)/mTotal)
+					width = '%f' % (((dev['end']-dev['start'])*100)/mTotal)
+					length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
+					if sysvals.suspendmode == 'command':
+						title = name+drv+xtrainfo+length+'cmdexec'
+					else:
+						title = name+drv+xtrainfo+length+b
+					devtl.html['timeline'] += html_device.format(dev['id'], \
+						title, left, top, '%.3f'%rowheight, width, \
+						d+drv, xtraclass, xtrastyle)
+					if('src' not in dev):
+						continue
+					# draw any trace events for this device
+					vprint('Debug trace events found for device %s' % d)
+					vprint('%20s %20s %10s %8s' % ('title', \
 						'name', 'time(ms)', 'length(ms)'))
-					for e in dev['traceevents']:
-						vprint('%20s %20s %10.3f %8.3f' % (e.action, \
-							e.name, e.time*1000, e.length*1000))
-						height = (100.0 - devtl.scaleH)/data.dmesg[b]['row']
-						top = '%.3f' % ((dev['row']*height) + devtl.scaleH)
-						left = '%.3f' % (((e.time-t0)*100)/tTotal)
-						width = '%.3f' % (e.length*100/tTotal)
+					for e in dev['src']:
+						vprint('%20s %20s %10.3f %8.3f' % (e.title, \
+							e.text, e.time*1000, e.length*1000))
+						height = devtl.rowH
+						top = '%.3f' % (rowtop + devtl.scaleH + (e.row*devtl.rowH))
+						left = '%f' % (((e.time-m0)*100)/mTotal)
+						width = '%f' % (e.length*100/mTotal)
 						color = 'rgba(204,204,204,0.5)'
 						devtl.html['timeline'] += \
-							html_traceevent.format(e.action+' '+e.name, \
+							html_traceevent.format(e.title, \
 								left, top, '%.3f'%height, \
-								width, e.color, '')
+								width, e.text)
+			# draw the time scale, try to make the number of labels readable
+			devtl.html['timeline'] += devtl.createTimeScale(m0, mMax, tTotal, dir)
+			devtl.html['timeline'] += '</div>\n'
 
 	# timeline is finished
 	devtl.html['timeline'] += '</div>\n</div>\n'
 
 	# draw a legend which describes the phases by color
-	data = testruns[-1]
-	devtl.html['legend'] = '<div class="legend">\n'
-	pdelta = 100.0/len(data.phases)
-	pmargin = pdelta / 4.0
-	for phase in data.phases:
-		order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
-		name = string.replace(phase, '_', ' &nbsp;')
-		devtl.html['legend'] += html_legend.format(order, \
-			data.dmesg[phase]['color'], name)
-	devtl.html['legend'] += '</div>\n'
+	if sysvals.suspendmode != 'command':
+		data = testruns[-1]
+		devtl.html['legend'] = '<div class="legend">\n'
+		pdelta = 100.0/len(data.phases)
+		pmargin = pdelta / 4.0
+		for phase in data.phases:
+			tmp = phase.split('_')
+			id = tmp[0][0]
+			if(len(tmp) > 1):
+				id += tmp[1][0]
+			order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
+			name = string.replace(phase, '_', ' &nbsp;')
+			devtl.html['legend'] += html_legend.format(order, \
+				data.dmesg[phase]['color'], name, id)
+		devtl.html['legend'] += '</div>\n'
 
 	hf = open(sysvals.htmlfile, 'w')
-	thread_height = 0
+
+	if not sysvals.cgexp:
+		cgchk = 'checked'
+		cgnchk = 'not(:checked)'
+	else:
+		cgchk = 'not(:checked)'
+		cgnchk = 'checked'
 
 	# write the html header first (html head, css code, up to body start)
 	html_header = '<!DOCTYPE html>\n<html>\n<head>\n\
 	<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
-	<title>AnalyzeSuspend</title>\n\
+	<title>'+htmlTitle()+'</title>\n\
 	<style type=\'text/css\'>\n\
-		body {overflow-y: scroll;}\n\
-		.stamp {width: 100%;text-align:center;background-color:gray;line-height:30px;color:white;font: 25px Arial;}\n\
-		.callgraph {margin-top: 30px;box-shadow: 5px 5px 20px black;}\n\
-		.callgraph article * {padding-left: 28px;}\n\
-		h1 {color:black;font: bold 30px Times;}\n\
-		t0 {color:black;font: bold 30px Times;}\n\
-		t1 {color:black;font: 30px Times;}\n\
-		t2 {color:black;font: 25px Times;}\n\
-		t3 {color:black;font: 20px Times;white-space:nowrap;}\n\
-		t4 {color:black;font: bold 30px Times;line-height:60px;white-space:nowrap;}\n\
+		body {overflow-y:scroll;}\n\
+		.stamp {width:100%;text-align:center;background-color:gray;line-height:30px;color:white;font:25px Arial;}\n\
+		.callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
+		.callgraph article * {padding-left:28px;}\n\
+		h1 {color:black;font:bold 30px Times;}\n\
+		t0 {color:black;font:bold 30px Times;}\n\
+		t1 {color:black;font:30px Times;}\n\
+		t2 {color:black;font:25px Times;}\n\
+		t3 {color:black;font:20px Times;white-space:nowrap;}\n\
+		t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
+		cS {color:blue;font:bold 11px Times;}\n\
+		cR {color:red;font:bold 11px Times;}\n\
 		table {width:100%;}\n\
 		.gray {background-color:rgba(80,80,80,0.1);}\n\
 		.green {background-color:rgba(204,255,204,0.4);}\n\
 		.purple {background-color:rgba(128,0,128,0.2);}\n\
 		.yellow {background-color:rgba(255,255,204,0.4);}\n\
-		.time1 {font: 22px Arial;border:1px solid;}\n\
-		.time2 {font: 15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
-		td {text-align: center;}\n\
+		.time1 {font:22px Arial;border:1px solid;}\n\
+		.time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
+		td {text-align:center;}\n\
 		r {color:#500000;font:15px Tahoma;}\n\
 		n {color:#505050;font:15px Tahoma;}\n\
-		.tdhl {color: red;}\n\
-		.hide {display: none;}\n\
-		.pf {display: none;}\n\
-		.pf:checked + label {background: url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
-		.pf:not(:checked) ~ label {background: url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
-		.pf:checked ~ *:not(:nth-child(2)) {display: none;}\n\
-		.zoombox {position: relative; width: 100%; overflow-x: scroll;}\n\
-		.timeline {position: relative; font-size: 14px;cursor: pointer;width: 100%; overflow: hidden; background-color:#dddddd;}\n\
-		.thread {position: absolute; height: '+'%.3f'%thread_height+'%; overflow: hidden; line-height: 30px; border:1px solid;text-align:center;white-space:nowrap;background-color:rgba(204,204,204,0.5);}\n\
-		.thread:hover {background-color:white;border:1px solid red;z-index:10;}\n\
-		.hover {background-color:white;border:1px solid red;z-index:10;}\n\
-		.traceevent {position: absolute;opacity: 0.3;height: '+'%.3f'%thread_height+'%;width:0;overflow:hidden;line-height:30px;text-align:center;white-space:nowrap;}\n\
-		.phase {position: absolute;overflow: hidden;border:0px;text-align:center;}\n\
+		.tdhl {color:red;}\n\
+		.hide {display:none;}\n\
+		.pf {display:none;}\n\
+		.pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
+		.pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
+		.pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
+		.zoombox {position:relative;width:100%;overflow-x:scroll;}\n\
+		.timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
+		.thread {position:absolute;height:0%;overflow:hidden;line-height:'+devtextH+';font-size:'+devtextS+';border:1px solid;text-align:center;white-space:nowrap;background-color:rgba(204,204,204,0.5);}\n\
+		.thread.sync {background-color:'+sysvals.synccolor+';}\n\
+		.thread.bg {background-color:'+sysvals.kprobecolor+';}\n\
+		.thread:hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
+		.hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
+		.hover.sync {background-color:white;}\n\
+		.hover.bg {background-color:white;}\n\
+		.traceevent {position:absolute;font-size:10px;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,rgba(204,204,204,1),rgba(150,150,150,1));}\n\
+		.traceevent:hover {background:white;}\n\
+		.phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
 		.phaselet {position:absolute;overflow:hidden;border:0px;text-align:center;height:100px;font-size:24px;}\n\
-		.t {position:absolute;top:0%;height:100%;border-right:1px solid black;}\n\
-		.legend {position: relative; width: 100%; height: 40px; text-align: center;margin-bottom:20px}\n\
-		.legend .square {position:absolute;top:10px; width: 0px;height: 20px;border:1px solid;padding-left:20px;}\n\
+		.t {z-index:2;position:absolute;pointer-events:none;top:0%;height:100%;border-right:1px solid black;}\n\
+		.legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
+		.legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
 		button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
+		.logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
 		.devlist {position:'+x2changes[1]+';width:190px;}\n\
-		#devicedetail {height:100px;box-shadow: 5px 5px 20px black;}\n\
+		a:link {color:white;text-decoration:none;}\n\
+		a:visited {color:white;}\n\
+		a:hover {color:white;}\n\
+		a:active {color:white;}\n\
+		.version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
+		#devicedetail {height:100px;box-shadow:5px 5px 20px black;}\n\
+		.tblock {position:absolute;height:100%;}\n\
+		.bg {z-index:1;}\n\
 	</style>\n</head>\n<body>\n'
-	hf.write(html_header)
+
+	# no header or css if its embedded
+	if(sysvals.embedded):
+		hf.write('pass True tSus %.3f tRes %.3f tLow %.3f fwvalid %s tSus %.3f tRes %.3f\n' %
+			(data.tSuspended-data.start, data.end-data.tSuspended, data.tLow, data.fwValid, \
+				data.fwSuspend/1000000, data.fwResume/1000000))
+	else:
+		hf.write(html_header)
 
 	# write the test title and general info header
 	if(sysvals.stamp['time'] != ""):
+		hf.write(headline_version)
+		if sysvals.addlogs and sysvals.dmesgfile:
+			hf.write('<button id="showdmesg" class="logbtn">dmesg</button>')
+		if sysvals.addlogs and sysvals.ftracefile:
+			hf.write('<button id="showftrace" class="logbtn">ftrace</button>')
 		hf.write(headline_stamp.format(sysvals.stamp['host'],
 			sysvals.stamp['kernel'], sysvals.stamp['mode'], \
 				sysvals.stamp['time']))
 
 	# write the device timeline
+	hf.write(devtl.html['header'])
 	hf.write(devtl.html['timeline'])
 	hf.write(devtl.html['legend'])
 	hf.write('<div id="devicedetailtitle"></div>\n')
@@ -2410,12 +3366,15 @@ def createHTML(testruns):
 			width = '%.3f' % ((length*100.0)/tTotal)
 			hf.write(html_phaselet.format(b, left, width, \
 				data.dmesg[b]['color']))
+		if sysvals.suspendmode == 'command':
+			hf.write(html_phaselet.format('cmdexec', '0', '0', \
+				data.dmesg['resume_complete']['color']))
 		hf.write('</div>\n')
 	hf.write('</div>\n')
 
 	# write the ftrace data (callgraph)
 	data = testruns[-1]
-	if(sysvals.usecallgraph):
+	if(sysvals.usecallgraph and not sysvals.embedded):
 		hf.write('<section id="callgraphs" class="callgraph">\n')
 		# write out the ftrace data converted to html
 		html_func_top = '<article id="{0}" class="atop" style="background-color:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n'
@@ -2428,22 +3387,29 @@ def createHTML(testruns):
 			for devname in data.sortedDevices(p):
 				if('ftrace' not in list[devname]):
 					continue
-				name = devname
-				if(devname in sysvals.altdevname):
-					name = sysvals.altdevname[devname]
 				devid = list[devname]['id']
 				cg = list[devname]['ftrace']
-				flen = '<r>(%.3f ms @ %.3f to %.3f)</r>' % \
-					((cg.end - cg.start)*1000, cg.start*1000, cg.end*1000)
+				clen = (cg.end - cg.start) * 1000
+				if clen < sysvals.mincglen:
+					continue
+				fmt = '<r>(%.3f ms @ '+sysvals.timeformat+' to '+sysvals.timeformat+')</r>'
+				flen = fmt % (clen, cg.start, cg.end)
+				name = devname
+				if(devname in sysvals.devprops):
+					name = sysvals.devprops[devname].altName(devname)
+				if sysvals.suspendmode == 'command':
+					ftitle = name
+				else:
+					ftitle = name+' '+p
 				hf.write(html_func_top.format(devid, data.dmesg[p]['color'], \
-					num, name+' '+p, flen))
+					num, ftitle, flen))
 				num += 1
 				for line in cg.list:
 					if(line.length < 0.000000001):
 						flen = ''
 					else:
-						flen = '<n>(%.3f ms @ %.3f)</n>' % (line.length*1000, \
-							line.time*1000)
+						fmt = '<n>(%.3f ms @ '+sysvals.timeformat+')</n>'
+						flen = fmt % (line.length*1000, line.time)
 					if(line.freturn and line.fcall):
 						hf.write(html_func_leaf.format(line.name, flen))
 					elif(line.freturn):
@@ -2453,9 +3419,40 @@ def createHTML(testruns):
 						num += 1
 				hf.write(html_func_end)
 		hf.write('\n\n    </section>\n')
-	# write the footer and close
-	addScriptCode(hf, testruns)
-	hf.write('</body>\n</html>\n')
+
+	# add the dmesg log as a hidden div
+	if sysvals.addlogs and sysvals.dmesgfile:
+		hf.write('<div id="dmesglog" style="display:none;">\n')
+		lf = open(sysvals.dmesgfile, 'r')
+		for line in lf:
+			hf.write(line)
+		lf.close()
+		hf.write('</div>\n')
+	# add the ftrace log as a hidden div
+	if sysvals.addlogs and sysvals.ftracefile:
+		hf.write('<div id="ftracelog" style="display:none;">\n')
+		lf = open(sysvals.ftracefile, 'r')
+		for line in lf:
+			hf.write(line)
+		lf.close()
+		hf.write('</div>\n')
+
+	if(not sysvals.embedded):
+		# write the footer and close
+		addScriptCode(hf, testruns)
+		hf.write('</body>\n</html>\n')
+	else:
+		# embedded out will be loaded in a page, skip the js
+		t0 = (testruns[0].start - testruns[-1].tSuspended) * 1000
+		tMax = (testruns[-1].end - testruns[-1].tSuspended) * 1000
+		# add js code in a div entry for later evaluation
+		detail = 'var bounds = [%f,%f];\n' % (t0, tMax)
+		detail += 'var devtable = [\n'
+		for data in testruns:
+			topo = data.deviceTopology()
+			detail += '\t"%s",\n' % (topo)
+		detail += '];\n'
+		hf.write('<div id=customcode style=display:none>\n'+detail+'</div>\n')
 	hf.close()
 	return True
 
@@ -2466,8 +3463,8 @@ def createHTML(testruns):
 #	 hf: the open html file pointer
 #	 testruns: array of Data objects from parseKernelLog or parseTraceLog
 def addScriptCode(hf, testruns):
-	t0 = (testruns[0].start - testruns[-1].tSuspended) * 1000
-	tMax = (testruns[-1].end - testruns[-1].tSuspended) * 1000
+	t0 = testruns[0].start * 1000
+	tMax = testruns[-1].end * 1000
 	# create an array in javascript memory with the device details
 	detail = '	var devtable = [];\n'
 	for data in testruns:
@@ -2477,8 +3474,43 @@ def addScriptCode(hf, testruns):
 	# add the code which will manipulate the data in the browser
 	script_code = \
 	'<script type="text/javascript">\n'+detail+\
+	'	var resolution = -1;\n'\
+	'	function redrawTimescale(t0, tMax, tS) {\n'\
+	'		var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;"><cR><-R</cR></div>\';\n'\
+	'		var tTotal = tMax - t0;\n'\
+	'		var list = document.getElementsByClassName("tblock");\n'\
+	'		for (var i = 0; i < list.length; i++) {\n'\
+	'			var timescale = list[i].getElementsByClassName("timescale")[0];\n'\
+	'			var m0 = t0 + (tTotal*parseFloat(list[i].style.left)/100);\n'\
+	'			var mTotal = tTotal*parseFloat(list[i].style.width)/100;\n'\
+	'			var mMax = m0 + mTotal;\n'\
+	'			var html = "";\n'\
+	'			var divTotal = Math.floor(mTotal/tS) + 1;\n'\
+	'			if(divTotal > 1000) continue;\n'\
+	'			var divEdge = (mTotal - tS*(divTotal-1))*100/mTotal;\n'\
+	'			var pos = 0.0, val = 0.0;\n'\
+	'			for (var j = 0; j < divTotal; j++) {\n'\
+	'				var htmlline = "";\n'\
+	'				if(list[i].id[5] == "r") {\n'\
+	'					pos = 100 - (((j)*tS*100)/mTotal);\n'\
+	'					val = (j)*tS;\n'\
+	'					htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
+	'					if(j == 0)\n'\
+	'						htmlline = rline;\n'\
+	'				} else {\n'\
+	'					pos = 100 - (((j)*tS*100)/mTotal) - divEdge;\n'\
+	'					val = (j-divTotal+1)*tS;\n'\
+	'					if(j == divTotal - 1)\n'\
+	'						htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S-></cS></div>\';\n'\
+	'					else\n'\
+	'						htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
+	'				}\n'\
+	'				html += htmlline;\n'\
+	'			}\n'\
+	'			timescale.innerHTML = html;\n'\
+	'		}\n'\
+	'	}\n'\
 	'	function zoomTimeline() {\n'\
-	'		var timescale = document.getElementById("timescale");\n'\
 	'		var dmesg = document.getElementById("dmesg");\n'\
 	'		var zoombox = document.getElementById("dmesgzoombox");\n'\
 	'		var val = parseFloat(dmesg.style.width);\n'\
@@ -2486,7 +3518,7 @@ def addScriptCode(hf, testruns):
 	'		var sh = window.outerWidth / 2;\n'\
 	'		if(this.id == "zoomin") {\n'\
 	'			newval = val * 1.2;\n'\
-	'			if(newval > 40000) newval = 40000;\n'\
+	'			if(newval > 910034) newval = 910034;\n'\
 	'			dmesg.style.width = newval+"%";\n'\
 	'			zoombox.scrollLeft = ((zoombox.scrollLeft + sh) * newval / val) - sh;\n'\
 	'		} else if (this.id == "zoomout") {\n'\
@@ -2498,19 +3530,17 @@ def addScriptCode(hf, testruns):
 	'			zoombox.scrollLeft = 0;\n'\
 	'			dmesg.style.width = "100%";\n'\
 	'		}\n'\
-	'		var html = "";\n'\
+	'		var tS = [10000, 5000, 2000, 1000, 500, 200, 100, 50, 20, 10, 5, 2, 1];\n'\
 	'		var t0 = bounds[0];\n'\
 	'		var tMax = bounds[1];\n'\
 	'		var tTotal = tMax - t0;\n'\
 	'		var wTotal = tTotal * 100.0 / newval;\n'\
-	'		for(var tS = 1000; (wTotal / tS) < 3; tS /= 10);\n'\
-	'		if(tS < 1) tS = 1;\n'\
-	'		for(var s = ((t0 / tS)|0) * tS; s < tMax; s += tS) {\n'\
-	'			var pos = (tMax - s) * 100.0 / tTotal;\n'\
-	'			var name = (s == 0)?"S/R":(s+"ms");\n'\
-	'			html += "<div class=\\"t\\" style=\\"right:"+pos+"%\\">"+name+"</div>";\n'\
-	'		}\n'\
-	'		timescale.innerHTML = html;\n'\
+	'		var idx = 7*window.innerWidth/1100;\n'\
+	'		for(var i = 0; (i < tS.length)&&((wTotal / tS[i]) < idx); i++);\n'\
+	'		if(i >= tS.length) i = tS.length - 1;\n'\
+	'		if(tS[i] == resolution) return;\n'\
+	'		resolution = tS[i];\n'\
+	'		redrawTimescale(t0, tMax, tS[i]);\n'\
 	'	}\n'\
 	'	function deviceHover() {\n'\
 	'		var name = this.title.slice(0, this.title.indexOf(" ("));\n'\
@@ -2523,12 +3553,13 @@ def addScriptCode(hf, testruns):
 	'			cpu = parseInt(name.slice(8));\n'\
 	'		for (var i = 0; i < dev.length; i++) {\n'\
 	'			dname = dev[i].title.slice(0, dev[i].title.indexOf(" ("));\n'\
+	'			var cname = dev[i].className.slice(dev[i].className.indexOf("thread"));\n'\
 	'			if((cpu >= 0 && dname.match("CPU_O[NF]*\\\[*"+cpu+"\\\]")) ||\n'\
 	'				(name == dname))\n'\
 	'			{\n'\
-	'				dev[i].className = "thread hover";\n'\
+	'				dev[i].className = "hover "+cname;\n'\
 	'			} else {\n'\
-	'				dev[i].className = "thread";\n'\
+	'				dev[i].className = cname;\n'\
 	'			}\n'\
 	'		}\n'\
 	'	}\n'\
@@ -2536,7 +3567,7 @@ def addScriptCode(hf, testruns):
 	'		var dmesg = document.getElementById("dmesg");\n'\
 	'		var dev = dmesg.getElementsByClassName("thread");\n'\
 	'		for (var i = 0; i < dev.length; i++) {\n'\
-	'			dev[i].className = "thread";\n'\
+	'			dev[i].className = dev[i].className.slice(dev[i].className.indexOf("thread"));\n'\
 	'		}\n'\
 	'	}\n'\
 	'	function deviceTitle(title, total, cpu) {\n'\
@@ -2547,7 +3578,7 @@ def addScriptCode(hf, testruns):
 	'			total[2] = (total[2]+total[4])/2;\n'\
 	'		}\n'\
 	'		var devtitle = document.getElementById("devicedetailtitle");\n'\
-	'		var name = title.slice(0, title.indexOf(" "));\n'\
+	'		var name = title.slice(0, title.indexOf(" ("));\n'\
 	'		if(cpu >= 0) name = "CPU"+cpu;\n'\
 	'		var driver = "";\n'\
 	'		var tS = "<t2>(</t2>";\n'\
@@ -2579,6 +3610,8 @@ def addScriptCode(hf, testruns):
 	'		var dev = dmesg.getElementsByClassName("thread");\n'\
 	'		var idlist = [];\n'\
 	'		var pdata = [[]];\n'\
+	'		if(document.getElementById("devicedetail1"))\n'\
+	'			pdata = [[], []];\n'\
 	'		var pd = pdata[0];\n'\
 	'		var total = [0.0, 0.0, 0.0];\n'\
 	'		for (var i = 0; i < dev.length; i++) {\n'\
@@ -2634,6 +3667,7 @@ def addScriptCode(hf, testruns):
 	'		var cglist = document.getElementById("callgraphs");\n'\
 	'		if(!cglist) return;\n'\
 	'		var cg = cglist.getElementsByClassName("atop");\n'\
+	'		if(cg.length < 10) return;\n'\
 	'		for (var i = 0; i < cg.length; i++) {\n'\
 	'			if(idlist.indexOf(cg[i].id) >= 0) {\n'\
 	'				cg[i].style.display = "block";\n'\
@@ -2658,15 +3692,32 @@ def addScriptCode(hf, testruns):
 	'			dt = devtable[1];\n'\
 	'		win.document.write(html+dt);\n'\
 	'	}\n'\
+	'	function logWindow(e) {\n'\
+	'		var name = e.target.id.slice(4);\n'\
+	'		var win = window.open();\n'\
+	'		var log = document.getElementById(name+"log");\n'\
+	'		var title = "<title>"+document.title.split(" ")[0]+" "+name+" log</title>";\n'\
+	'		win.document.write(title+"<pre>"+log.innerHTML+"</pre>");\n'\
+	'		win.document.close();\n'\
+	'	}\n'\
+	'	function onClickPhase(e) {\n'\
+	'	}\n'\
+	'	window.addEventListener("resize", function () {zoomTimeline();});\n'\
 	'	window.addEventListener("load", function () {\n'\
 	'		var dmesg = document.getElementById("dmesg");\n'\
 	'		dmesg.style.width = "100%"\n'\
 	'		document.getElementById("zoomin").onclick = zoomTimeline;\n'\
 	'		document.getElementById("zoomout").onclick = zoomTimeline;\n'\
 	'		document.getElementById("zoomdef").onclick = zoomTimeline;\n'\
-	'		var devlist = document.getElementsByClassName("devlist");\n'\
-	'		for (var i = 0; i < devlist.length; i++)\n'\
-	'			devlist[i].onclick = devListWindow;\n'\
+	'		var list = document.getElementsByClassName("square");\n'\
+	'		for (var i = 0; i < list.length; i++)\n'\
+	'			list[i].onclick = onClickPhase;\n'\
+	'		var list = document.getElementsByClassName("logbtn");\n'\
+	'		for (var i = 0; i < list.length; i++)\n'\
+	'			list[i].onclick = logWindow;\n'\
+	'		list = document.getElementsByClassName("devlist");\n'\
+	'		for (var i = 0; i < list.length; i++)\n'\
+	'			list[i].onclick = devListWindow;\n'\
 	'		var dev = dmesg.getElementsByClassName("thread");\n'\
 	'		for (var i = 0; i < dev.length; i++) {\n'\
 	'			dev[i].onclick = deviceDetail;\n'\
@@ -2685,141 +3736,87 @@ def addScriptCode(hf, testruns):
 def executeSuspend():
 	global sysvals
 
-	detectUSB(False)
 	t0 = time.time()*1000
 	tp = sysvals.tpath
+	fwdata = []
+	# mark the start point in the kernel ring buffer just as we start
+	sysvals.initdmesg()
+	# start ftrace
+	if(sysvals.usecallgraph or sysvals.usetraceevents):
+		print('START TRACING')
+		sysvals.fsetVal('1', 'tracing_on')
 	# execute however many s/r runs requested
 	for count in range(1,sysvals.execcount+1):
-		# clear the kernel ring buffer just as we start
-		os.system('dmesg -C')
-		# enable callgraph ftrace only for the second run
-		if(sysvals.usecallgraph and count == 2):
-			# set trace type
-			os.system('echo function_graph > '+tp+'current_tracer')
-			os.system('echo "" > '+tp+'set_ftrace_filter')
-			# set trace format options
-			os.system('echo funcgraph-abstime > '+tp+'trace_options')
-			os.system('echo funcgraph-proc > '+tp+'trace_options')
-			# focus only on device suspend and resume
-			os.system('cat '+tp+'available_filter_functions | '+\
-				'grep dpm_run_callback > '+tp+'set_graph_function')
 		# if this is test2 and there's a delay, start here
 		if(count > 1 and sysvals.x2delay > 0):
 			tN = time.time()*1000
 			while (tN - t0) < sysvals.x2delay:
 				tN = time.time()*1000
 				time.sleep(0.001)
-		# start ftrace
-		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			print('START TRACING')
-			os.system('echo 1 > '+tp+'tracing_on')
 		# initiate suspend
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			os.system('echo SUSPEND START > '+tp+'trace_marker')
-		if(sysvals.rtcwake):
-			print('SUSPEND START')
-			print('will autoresume in %d seconds' % sysvals.rtcwaketime)
-			sysvals.rtcWakeAlarm()
+			sysvals.fsetVal('SUSPEND START', 'trace_marker')
+		if sysvals.suspendmode == 'command':
+			print('COMMAND START')
+			if(sysvals.rtcwake):
+				print('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
+				sysvals.rtcWakeAlarmOn()
+			os.system(sysvals.testcommand)
 		else:
-			print('SUSPEND START (press a key to resume)')
-		pf = open(sysvals.powerfile, 'w')
-		pf.write(sysvals.suspendmode)
-		# execution will pause here
-		pf.close()
+			if(sysvals.rtcwake):
+				print('SUSPEND START')
+				print('will autoresume in %d seconds' % sysvals.rtcwaketime)
+				sysvals.rtcWakeAlarmOn()
+			else:
+				print('SUSPEND START (press a key to resume)')
+			pf = open(sysvals.powerfile, 'w')
+			pf.write(sysvals.suspendmode)
+			# execution will pause here
+			try:
+				pf.close()
+			except:
+				pass
 		t0 = time.time()*1000
+		if(sysvals.rtcwake):
+			sysvals.rtcWakeAlarmOff()
 		# return from suspend
 		print('RESUME COMPLETE')
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			os.system('echo RESUME COMPLETE > '+tp+'trace_marker')
-		# see if there's firmware timing data to be had
-		t = sysvals.postresumetime
-		if(t > 0):
-			print('Waiting %d seconds for POST-RESUME trace events...' % t)
-			time.sleep(t)
-		# stop ftrace
-		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			os.system('echo 0 > '+tp+'tracing_on')
-			print('CAPTURING TRACE')
-			writeDatafileHeader(sysvals.ftracefile)
-			os.system('cat '+tp+'trace >> '+sysvals.ftracefile)
-			os.system('echo "" > '+tp+'trace')
-		# grab a copy of the dmesg output
-		print('CAPTURING DMESG')
-		writeDatafileHeader(sysvals.dmesgfile)
-		os.system('dmesg -c >> '+sysvals.dmesgfile)
-
-def writeDatafileHeader(filename):
+			sysvals.fsetVal('RESUME COMPLETE', 'trace_marker')
+		if(sysvals.suspendmode == 'mem'):
+			fwdata.append(getFPDT(False))
+	# look for post resume events after the last test run
+	t = sysvals.postresumetime
+	if(t > 0):
+		print('Waiting %d seconds for POST-RESUME trace events...' % t)
+		time.sleep(t)
+	# stop ftrace
+	if(sysvals.usecallgraph or sysvals.usetraceevents):
+		sysvals.fsetVal('0', 'tracing_on')
+		print('CAPTURING TRACE')
+		writeDatafileHeader(sysvals.ftracefile, fwdata)
+		os.system('cat '+tp+'trace >> '+sysvals.ftracefile)
+		sysvals.fsetVal('', 'trace')
+		devProps()
+	# grab a copy of the dmesg output
+	print('CAPTURING DMESG')
+	writeDatafileHeader(sysvals.dmesgfile, fwdata)
+	sysvals.getdmesg()
+
+def writeDatafileHeader(filename, fwdata):
 	global sysvals
 
-	fw = getFPDT(False)
 	prt = sysvals.postresumetime
 	fp = open(filename, 'a')
 	fp.write(sysvals.teststamp+'\n')
-	if(fw):
-		fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1]))
+	if(sysvals.suspendmode == 'mem'):
+		for fw in fwdata:
+			if(fw):
+				fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1]))
 	if(prt > 0):
 		fp.write('# post resume time %u\n' % prt)
 	fp.close()
 
-# Function: executeAndroidSuspend
-# Description:
-#	 Execute system suspend through the sysfs interface
-#	 on a remote android device, then transfer the output
-#	 dmesg and ftrace files to the local output directory.
-def executeAndroidSuspend():
-	global sysvals
-
-	# check to see if the display is currently off
-	tp = sysvals.tpath
-	out = os.popen(sysvals.adb+\
-		' shell dumpsys power | grep mScreenOn').read().strip()
-	# if so we need to turn it on so we can issue a new suspend
-	if(out.endswith('false')):
-		print('Waking the device up for the test...')
-		# send the KEYPAD_POWER keyevent to wake it up
-		os.system(sysvals.adb+' shell input keyevent 26')
-		# wait a few seconds so the user can see the device wake up
-		time.sleep(3)
-	# execute however many s/r runs requested
-	for count in range(1,sysvals.execcount+1):
-		# clear the kernel ring buffer just as we start
-		os.system(sysvals.adb+' shell dmesg -c > /dev/null 2>&1')
-		# start ftrace
-		if(sysvals.usetraceevents):
-			print('START TRACING')
-			os.system(sysvals.adb+" shell 'echo 1 > "+tp+"tracing_on'")
-		# initiate suspend
-		for count in range(1,sysvals.execcount+1):
-			if(sysvals.usetraceevents):
-				os.system(sysvals.adb+\
-					" shell 'echo SUSPEND START > "+tp+"trace_marker'")
-			print('SUSPEND START (press a key on the device to resume)')
-			os.system(sysvals.adb+" shell 'echo "+sysvals.suspendmode+\
-				" > "+sysvals.powerfile+"'")
-			# execution will pause here, then adb will exit
-			while(True):
-				check = os.popen(sysvals.adb+\
-					' shell pwd 2>/dev/null').read().strip()
-				if(len(check) > 0):
-					break
-				time.sleep(1)
-			if(sysvals.usetraceevents):
-				os.system(sysvals.adb+" shell 'echo RESUME COMPLETE > "+tp+\
-					"trace_marker'")
-		# return from suspend
-		print('RESUME COMPLETE')
-		# stop ftrace
-		if(sysvals.usetraceevents):
-			os.system(sysvals.adb+" shell 'echo 0 > "+tp+"tracing_on'")
-			print('CAPTURING TRACE')
-			os.system('echo "'+sysvals.teststamp+'" > '+sysvals.ftracefile)
-			os.system(sysvals.adb+' shell cat '+tp+\
-				'trace >> '+sysvals.ftracefile)
-		# grab a copy of the dmesg output
-		print('CAPTURING DMESG')
-		os.system('echo "'+sysvals.teststamp+'" > '+sysvals.dmesgfile)
-		os.system(sysvals.adb+' shell dmesg >> '+sysvals.dmesgfile)
-
 # Function: setUSBDevicesAuto
 # Description:
 #	 Set the autosuspend control parameter of all USB devices to auto
@@ -2829,7 +3826,7 @@ def executeAndroidSuspend():
 def setUSBDevicesAuto():
 	global sysvals
 
-	rootCheck()
+	rootCheck(True)
 	for dirname, dirnames, filenames in os.walk('/sys/devices'):
 		if(re.match('.*/usb[0-9]*.*', dirname) and
 			'idVendor' in filenames and 'idProduct' in filenames):
@@ -2874,9 +3871,7 @@ def ms2nice(val):
 # Description:
 #	 Detect all the USB hosts and devices currently connected and add
 #	 a list of USB device names to sysvals for better timeline readability
-# Arguments:
-#	 output: True to output the info to stdout, False otherwise
-def detectUSB(output):
+def detectUSB():
 	global sysvals
 
 	field = {'idVendor':'', 'idProduct':'', 'product':'', 'speed':''}
@@ -2887,18 +3882,18 @@ def detectUSB(output):
 			'runtime_suspended_time':'',
 			'active_duration':'',
 			'connected_duration':''}
-	if(output):
-		print('LEGEND')
-		print('---------------------------------------------------------------------------------------------')
-		print('  A = async/sync PM queue Y/N                       D = autosuspend delay (seconds)')
-		print('  S = autosuspend Y/N                         rACTIVE = runtime active (min/sec)')
-		print('  P = persist across suspend Y/N              rSUSPEN = runtime suspend (min/sec)')
-		print('  E = runtime suspend enabled/forbidden Y/N    ACTIVE = active duration (min/sec)')
-		print('  R = runtime status active/suspended Y/N     CONNECT = connected duration (min/sec)')
-		print('  U = runtime usage count')
-		print('---------------------------------------------------------------------------------------------')
-		print('  NAME       ID      DESCRIPTION         SPEED A S P E R U D rACTIVE rSUSPEN  ACTIVE CONNECT')
-		print('---------------------------------------------------------------------------------------------')
+
+	print('LEGEND')
+	print('---------------------------------------------------------------------------------------------')
+	print('  A = async/sync PM queue Y/N                       D = autosuspend delay (seconds)')
+	print('  S = autosuspend Y/N                         rACTIVE = runtime active (min/sec)')
+	print('  P = persist across suspend Y/N              rSUSPEN = runtime suspend (min/sec)')
+	print('  E = runtime suspend enabled/forbidden Y/N    ACTIVE = active duration (min/sec)')
+	print('  R = runtime status active/suspended Y/N     CONNECT = connected duration (min/sec)')
+	print('  U = runtime usage count')
+	print('---------------------------------------------------------------------------------------------')
+	print('  NAME       ID      DESCRIPTION         SPEED A S P E R U D rACTIVE rSUSPEN  ACTIVE CONNECT')
+	print('---------------------------------------------------------------------------------------------')
 
 	for dirname, dirnames, filenames in os.walk('/sys/devices'):
 		if(re.match('.*/usb[0-9]*.*', dirname) and
@@ -2907,35 +3902,149 @@ def detectUSB(output):
 				field[i] = os.popen('cat %s/%s 2>/dev/null' % \
 					(dirname, i)).read().replace('\n', '')
 			name = dirname.split('/')[-1]
-			if(len(field['product']) > 0):
-				sysvals.altdevname[name] = \
-					'%s [%s]' % (field['product'], name)
+			for i in power:
+				power[i] = os.popen('cat %s/power/%s 2>/dev/null' % \
+					(dirname, i)).read().replace('\n', '')
+			if(re.match('usb[0-9]*', name)):
+				first = '%-8s' % name
 			else:
-				sysvals.altdevname[name] = \
-					'%s:%s [%s]' % (field['idVendor'], \
-						field['idProduct'], name)
-			if(output):
-				for i in power:
-					power[i] = os.popen('cat %s/power/%s 2>/dev/null' % \
-						(dirname, i)).read().replace('\n', '')
-				if(re.match('usb[0-9]*', name)):
-					first = '%-8s' % name
-				else:
-					first = '%8s' % name
-				print('%s [%s:%s] %-20s %-4s %1s %1s %1s %1s %1s %1s %1s %s %s %s %s' % \
-					(first, field['idVendor'], field['idProduct'], \
-					field['product'][0:20], field['speed'], \
-					yesno(power['async']), \
-					yesno(power['control']), \
-					yesno(power['persist']), \
-					yesno(power['runtime_enabled']), \
-					yesno(power['runtime_status']), \
-					power['runtime_usage'], \
-					power['autosuspend'], \
-					ms2nice(power['runtime_active_time']), \
-					ms2nice(power['runtime_suspended_time']), \
-					ms2nice(power['active_duration']), \
-					ms2nice(power['connected_duration'])))
+				first = '%8s' % name
+			print('%s [%s:%s] %-20s %-4s %1s %1s %1s %1s %1s %1s %1s %s %s %s %s' % \
+				(first, field['idVendor'], field['idProduct'], \
+				field['product'][0:20], field['speed'], \
+				yesno(power['async']), \
+				yesno(power['control']), \
+				yesno(power['persist']), \
+				yesno(power['runtime_enabled']), \
+				yesno(power['runtime_status']), \
+				power['runtime_usage'], \
+				power['autosuspend'], \
+				ms2nice(power['runtime_active_time']), \
+				ms2nice(power['runtime_suspended_time']), \
+				ms2nice(power['active_duration']), \
+				ms2nice(power['connected_duration'])))
+
+# Function: devProps
+# Description:
+#	 Retrieve a list of properties for all devices in the trace log
+def devProps(data=0):
+	global sysvals
+	props = dict()
+
+	if data:
+		idx = data.index(': ') + 2
+		if idx >= len(data):
+			return
+		devlist = data[idx:].split(';')
+		for dev in devlist:
+			f = dev.split(',')
+			if len(f) < 3:
+				continue
+			dev = f[0]
+			props[dev] = DevProps()
+			props[dev].altname = f[1]
+			if int(f[2]):
+				props[dev].async = True
+			else:
+				props[dev].async = False
+			sysvals.devprops = props
+		if sysvals.suspendmode == 'command' and 'testcommandstring' in props:
+			sysvals.testcommand = props['testcommandstring'].altname
+		return
+
+	if(os.path.exists(sysvals.ftracefile) == False):
+		doError('%s does not exist' % sysvals.ftracefile, False)
+
+	# first get the list of devices we need properties for
+	msghead = 'Additional data added by AnalyzeSuspend'
+	alreadystamped = False
+	tp = TestProps()
+	tf = open(sysvals.ftracefile, 'r')
+	for line in tf:
+		if msghead in line:
+			alreadystamped = True
+			continue
+		# determine the trace data type (required for further parsing)
+		m = re.match(sysvals.tracertypefmt, line)
+		if(m):
+			tp.setTracerType(m.group('t'))
+			continue
+		# parse only valid lines, if this is not one move on
+		m = re.match(tp.ftrace_line_fmt, line)
+		if(not m or 'device_pm_callback_start' not in line):
+			continue
+		m = re.match('.*: (?P<drv>.*) (?P<d>.*), parent: *(?P<p>.*), .*', m.group('msg'));
+		if(not m):
+			continue
+		drv, dev, par = m.group('drv'), m.group('d'), m.group('p')
+		if dev not in props:
+			props[dev] = DevProps()
+	tf.close()
+
+	if not alreadystamped and sysvals.suspendmode == 'command':
+		out = '#\n# '+msghead+'\n# Device Properties: '
+		out += 'testcommandstring,%s,0;' % (sysvals.testcommand)
+		with open(sysvals.ftracefile, 'a') as fp:
+			fp.write(out+'\n')
+		sysvals.devprops = props
+		return
+
+	# now get the syspath for each of our target devices
+	for dirname, dirnames, filenames in os.walk('/sys/devices'):
+		if(re.match('.*/power', dirname) and 'async' in filenames):
+			dev = dirname.split('/')[-2]
+			if dev in props and (not props[dev].syspath or len(dirname) < len(props[dev].syspath)):
+				props[dev].syspath = dirname[:-6]
+
+	# now fill in the properties for our target devices
+	for dev in props:
+		dirname = props[dev].syspath
+		if not dirname or not os.path.exists(dirname):
+			continue
+		with open(dirname+'/power/async') as fp:
+			text = fp.read()
+			props[dev].async = False
+			if 'enabled' in text:
+				props[dev].async = True
+		fields = os.listdir(dirname)
+		if 'product' in fields:
+			with open(dirname+'/product') as fp:
+				props[dev].altname = fp.read()
+		elif 'name' in fields:
+			with open(dirname+'/name') as fp:
+				props[dev].altname = fp.read()
+		elif 'model' in fields:
+			with open(dirname+'/model') as fp:
+				props[dev].altname = fp.read()
+		elif 'description' in fields:
+			with open(dirname+'/description') as fp:
+				props[dev].altname = fp.read()
+		elif 'id' in fields:
+			with open(dirname+'/id') as fp:
+				props[dev].altname = fp.read()
+		elif 'idVendor' in fields and 'idProduct' in fields:
+			idv, idp = '', ''
+			with open(dirname+'/idVendor') as fp:
+				idv = fp.read().strip()
+			with open(dirname+'/idProduct') as fp:
+				idp = fp.read().strip()
+			props[dev].altname = '%s:%s' % (idv, idp)
+
+		if props[dev].altname:
+			out = props[dev].altname.strip().replace('\n', ' ')
+			out = out.replace(',', ' ')
+			out = out.replace(';', ' ')
+			props[dev].altname = out
+
+	# and now write the data to the ftrace file
+	if not alreadystamped:
+		out = '#\n# '+msghead+'\n# Device Properties: '
+		for dev in sorted(props):
+			out += props[dev].out(dev)
+		with open(sysvals.ftracefile, 'a') as fp:
+			fp.write(out+'\n')
+
+	sysvals.devprops = props
 
 # Function: getModes
 # Description:
@@ -2945,15 +4054,10 @@ def detectUSB(output):
 def getModes():
 	global sysvals
 	modes = ''
-	if(not sysvals.android):
-		if(os.path.exists(sysvals.powerfile)):
-			fp = open(sysvals.powerfile, 'r')
-			modes = string.split(fp.read())
-			fp.close()
-	else:
-		line = os.popen(sysvals.adb+' shell cat '+\
-			sysvals.powerfile).read().strip()
-		modes = string.split(line)
+	if(os.path.exists(sysvals.powerfile)):
+		fp = open(sysvals.powerfile, 'r')
+		modes = string.split(fp.read())
+		fp.close()
 	return modes
 
 # Function: getFPDT
@@ -2971,22 +4075,22 @@ def getFPDT(output):
 	prectype[0] = 'Basic S3 Resume Performance Record'
 	prectype[1] = 'Basic S3 Suspend Performance Record'
 
-	rootCheck()
+	rootCheck(True)
 	if(not os.path.exists(sysvals.fpdtpath)):
 		if(output):
-			doError('file doesnt exist: %s' % sysvals.fpdtpath, False)
+			doError('file does not exist: %s' % sysvals.fpdtpath, False)
 		return False
 	if(not os.access(sysvals.fpdtpath, os.R_OK)):
 		if(output):
-			doError('file isnt readable: %s' % sysvals.fpdtpath, False)
+			doError('file is not readable: %s' % sysvals.fpdtpath, False)
 		return False
 	if(not os.path.exists(sysvals.mempath)):
 		if(output):
-			doError('file doesnt exist: %s' % sysvals.mempath, False)
+			doError('file does not exist: %s' % sysvals.mempath, False)
 		return False
 	if(not os.access(sysvals.mempath, os.R_OK)):
 		if(output):
-			doError('file isnt readable: %s' % sysvals.mempath, False)
+			doError('file is not readable: %s' % sysvals.mempath, False)
 		return False
 
 	fp = open(sysvals.fpdtpath, 'rb')
@@ -3027,15 +4131,19 @@ def getFPDT(output):
 	while(i < len(records)):
 		header = struct.unpack('HBB', records[i:i+4])
 		if(header[0] not in rectype):
+			i += header[1]
 			continue
 		if(header[1] != 16):
+			i += header[1]
 			continue
 		addr = struct.unpack('Q', records[i+8:i+16])[0]
 		try:
 			fp.seek(addr)
 			first = fp.read(8)
 		except:
-			doError('Bad address 0x%x in %s' % (addr, sysvals.mempath), False)
+			if(output):
+				print('Bad address 0x%x in %s' % (addr, sysvals.mempath))
+			return [0, 0]
 		rechead = struct.unpack('4sI', first)
 		recdata = fp.read(rechead[1]-8)
 		if(rechead[0] == 'FBPT'):
@@ -3090,89 +4198,60 @@ def getFPDT(output):
 #	 print the results to the terminal
 # Output:
 #	 True if the test will work, False if not
-def statusCheck():
+def statusCheck(probecheck=False):
 	global sysvals
 	status = True
 
-	if(sysvals.android):
-		print('Checking the android system ...')
-	else:
-		print('Checking this system (%s)...' % platform.node())
-
-	# check if adb is connected to a device
-	if(sysvals.android):
-		res = 'NO'
-		out = os.popen(sysvals.adb+' get-state').read().strip()
-		if(out == 'device'):
-			res = 'YES'
-		print('    is android device connected: %s' % res)
-		if(res != 'YES'):
-			print('    Please connect the device before using this tool')
-			return False
+	print('Checking this system (%s)...' % platform.node())
 
 	# check we have root access
-	res = 'NO (No features of this tool will work!)'
-	if(sysvals.android):
-		out = os.popen(sysvals.adb+' shell id').read().strip()
-		if('root' in out):
-			res = 'YES'
-	else:
-		if(os.environ['USER'] == 'root'):
-			res = 'YES'
+	res = sysvals.colorText('NO (No features of this tool will work!)')
+	if(rootCheck(False)):
+		res = 'YES'
 	print('    have root access: %s' % res)
 	if(res != 'YES'):
-		if(sysvals.android):
-			print('    Try running "adb root" to restart the daemon as root')
-		else:
-			print('    Try running this script with sudo')
+		print('    Try running this script with sudo')
 		return False
 
 	# check sysfs is mounted
-	res = 'NO (No features of this tool will work!)'
-	if(sysvals.android):
-		out = os.popen(sysvals.adb+' shell ls '+\
-			sysvals.powerfile).read().strip()
-		if(out == sysvals.powerfile):
-			res = 'YES'
-	else:
-		if(os.path.exists(sysvals.powerfile)):
-			res = 'YES'
+	res = sysvals.colorText('NO (No features of this tool will work!)')
+	if(os.path.exists(sysvals.powerfile)):
+		res = 'YES'
 	print('    is sysfs mounted: %s' % res)
 	if(res != 'YES'):
 		return False
 
 	# check target mode is a valid mode
-	res = 'NO'
-	modes = getModes()
-	if(sysvals.suspendmode in modes):
-		res = 'YES'
-	else:
-		status = False
-	print('    is "%s" a valid power mode: %s' % (sysvals.suspendmode, res))
-	if(res == 'NO'):
-		print('      valid power modes are: %s' % modes)
-		print('      please choose one with -m')
-
-	# check if the tool can unlock the device
-	if(sysvals.android):
-		res = 'YES'
-		out1 = os.popen(sysvals.adb+\
-			' shell dumpsys power | grep mScreenOn').read().strip()
-		out2 = os.popen(sysvals.adb+\
-			' shell input').read().strip()
-		if(not out1.startswith('mScreenOn') or not out2.startswith('usage')):
-			res = 'NO (wake the android device up before running the test)'
-		print('    can I unlock the screen: %s' % res)
+	if sysvals.suspendmode != 'command':
+		res = sysvals.colorText('NO')
+		modes = getModes()
+		if(sysvals.suspendmode in modes):
+			res = 'YES'
+		else:
+			status = False
+		print('    is "%s" a valid power mode: %s' % (sysvals.suspendmode, res))
+		if(res == 'NO'):
+			print('      valid power modes are: %s' % modes)
+			print('      please choose one with -m')
 
 	# check if ftrace is available
-	res = 'NO'
-	ftgood = verifyFtrace()
+	res = sysvals.colorText('NO')
+	ftgood = sysvals.verifyFtrace()
 	if(ftgood):
 		res = 'YES'
 	elif(sysvals.usecallgraph):
 		status = False
 	print('    is ftrace supported: %s' % res)
 
+	# check if kprobes are available
+	res = sysvals.colorText('NO')
+	sysvals.usekprobes = sysvals.verifyKprobes()
+	if(sysvals.usekprobes):
+		res = 'YES'
+	else:
+		sysvals.usedevsrc = False
+	print('    are kprobes supported: %s' % res)
+
 	# what data source are we using
 	res = 'DMESG'
 	if(ftgood):
@@ -3180,14 +4259,8 @@ def statusCheck():
 		sysvals.usetraceevents = False
 		for e in sysvals.traceevents:
 			check = False
-			if(sysvals.android):
-				out = os.popen(sysvals.adb+' shell ls -d '+\
-					sysvals.epath+e).read().strip()
-				if(out == sysvals.epath+e):
-					check = True
-			else:
-				if(os.path.exists(sysvals.epath+e)):
-					check = True
+			if(os.path.exists(sysvals.epath+e)):
+				check = True
 			if(not check):
 				sysvals.usetraceeventsonly = False
 			if(e == 'suspend_resume' and check):
@@ -3199,13 +4272,48 @@ def statusCheck():
 	print('    timeline data source: %s' % res)
 
 	# check if rtcwake
-	res = 'NO'
+	res = sysvals.colorText('NO')
 	if(sysvals.rtcpath != ''):
 		res = 'YES'
 	elif(sysvals.rtcwake):
 		status = False
 	print('    is rtcwake supported: %s' % res)
 
+	if not probecheck:
+		return status
+
+	if (sysvals.usecallgraph and len(sysvals.debugfuncs) > 0) or len(sysvals.kprobes) > 0:
+		sysvals.initFtrace(True)
+
+	# verify callgraph debugfuncs
+	if sysvals.usecallgraph and len(sysvals.debugfuncs) > 0:
+		print('    verifying these ftrace callgraph functions work:')
+		sysvals.setFtraceFilterFunctions(sysvals.debugfuncs)
+		fp = open(sysvals.tpath+'set_graph_function', 'r')
+		flist = fp.read().split('\n')
+		fp.close()
+		for func in sysvals.debugfuncs:
+			res = sysvals.colorText('NO')
+			if func in flist:
+				res = 'YES'
+			else:
+				for i in flist:
+					if ' [' in i and func == i.split(' ')[0]:
+						res = 'YES'
+						break
+			print('         %s: %s' % (func, res))
+
+	# verify kprobes
+	if len(sysvals.kprobes) > 0:
+		print('    verifying these kprobes work:')
+		for name in sorted(sysvals.kprobes):
+			if name in sysvals.tracefuncs:
+				continue
+			res = sysvals.colorText('NO')
+			if sysvals.testKprobe(sysvals.kprobes[name]):
+				res = 'YES'
+			print('         %s: %s' % (name, res))
+
 	return status
 
 # Function: doError
@@ -3226,7 +4334,7 @@ def doError(msg, help):
 # Arguments:
 #	 msg: the warning message to print
 #	 file: If not empty, a filename to request be sent to the owner for debug
-def doWarning(msg, file):
+def doWarning(msg, file=''):
 	print('/* %s */') % msg
 	if(file):
 		print('/* For a fix, please send this'+\
@@ -3235,18 +4343,25 @@ def doWarning(msg, file):
 # Function: rootCheck
 # Description:
 #	 quick check to see if we have root access
-def rootCheck():
-	if(os.environ['USER'] != 'root'):
-		doError('This script must be run as root', False)
+def rootCheck(fatal):
+	global sysvals
+	if(os.access(sysvals.powerfile, os.W_OK)):
+		return True
+	if fatal:
+		doError('This command must be run as root', False)
+	return False
 
 # Function: getArgInt
 # Description:
 #	 pull out an integer argument from the command line with checks
-def getArgInt(name, args, min, max):
-	try:
-		arg = args.next()
-	except:
-		doError(name+': no argument supplied', True)
+def getArgInt(name, args, min, max, main=True):
+	if main:
+		try:
+			arg = args.next()
+		except:
+			doError(name+': no argument supplied', True)
+	else:
+		arg = args
 	try:
 		val = int(arg)
 	except:
@@ -3255,6 +4370,25 @@ def getArgInt(name, args, min, max):
 		doError(name+': value should be between %d and %d' % (min, max), True)
 	return val
 
+# Function: getArgFloat
+# Description:
+#	 pull out a float argument from the command line with checks
+def getArgFloat(name, args, min, max, main=True):
+	if main:
+		try:
+			arg = args.next()
+		except:
+			doError(name+': no argument supplied', True)
+	else:
+		arg = args
+	try:
+		val = float(arg)
+	except:
+		doError(name+': non-numerical value given', True)
+	if(val < min or val > max):
+		doError(name+': value should be between %f and %f' % (min, max), True)
+	return val
+
 # Function: rerunTest
 # Description:
 #	 generate an output from an existing set of ftrace/dmesg logs
@@ -3282,15 +4416,12 @@ def rerunTest():
 # Function: runTest
 # Description:
 #	 execute a suspend/resume, gather the logs, and generate the output
-def runTest(subdir):
+def runTest(subdir, testpath=''):
 	global sysvals
 
 	# prepare for the test
-	if(not sysvals.android):
-		initFtrace()
-	else:
-		initFtraceAndroid()
-	sysvals.initTestOutput(subdir)
+	sysvals.initFtrace()
+	sysvals.initTestOutput(subdir, testpath)
 
 	vprint('Output files:\n    %s' % sysvals.dmesgfile)
 	if(sysvals.usecallgraph or
@@ -3300,10 +4431,8 @@ def runTest(subdir):
 	vprint('    %s' % sysvals.htmlfile)
 
 	# execute the test
-	if(not sysvals.android):
-		executeSuspend()
-	else:
-		executeAndroidSuspend()
+	executeSuspend()
+	sysvals.cleanupFtrace()
 
 	# analyze the data and create the html output
 	print('PROCESSING DATA')
@@ -3367,6 +4496,153 @@ def runSummary(subdir, output):
 
 	createHTMLSummarySimple(testruns, subdir+'/summary.html')
 
+# Function: checkArgBool
+# Description:
+#	 check if a boolean string value is true or false
+def checkArgBool(value):
+	yes = ['1', 'true', 'yes', 'on']
+	if value.lower() in yes:
+		return True
+	return False
+
+# Function: configFromFile
+# Description:
+#	 Configure the script via the info in a config file
+def configFromFile(file):
+	global sysvals
+	Config = ConfigParser.ConfigParser()
+
+	ignorekprobes = False
+	Config.read(file)
+	sections = Config.sections()
+	if 'Settings' in sections:
+		for opt in Config.options('Settings'):
+			value = Config.get('Settings', opt).lower()
+			if(opt.lower() == 'verbose'):
+				sysvals.verbose = checkArgBool(value)
+			elif(opt.lower() == 'addlogs'):
+				sysvals.addlogs = checkArgBool(value)
+			elif(opt.lower() == 'dev'):
+				sysvals.usedevsrc = checkArgBool(value)
+			elif(opt.lower() == 'ignorekprobes'):
+				ignorekprobes = checkArgBool(value)
+			elif(opt.lower() == 'x2'):
+				if checkArgBool(value):
+					sysvals.execcount = 2
+			elif(opt.lower() == 'callgraph'):
+				sysvals.usecallgraph = checkArgBool(value)
+			elif(opt.lower() == 'callgraphfunc'):
+				sysvals.debugfuncs = []
+				if value:
+					value = value.split(',')
+				for i in value:
+					sysvals.debugfuncs.append(i.strip())
+			elif(opt.lower() == 'expandcg'):
+				sysvals.cgexp = checkArgBool(value)
+			elif(opt.lower() == 'srgap'):
+				if checkArgBool(value):
+					sysvals.srgap = 5
+			elif(opt.lower() == 'mode'):
+				sysvals.suspendmode = value
+			elif(opt.lower() == 'command'):
+				sysvals.testcommand = value
+			elif(opt.lower() == 'x2delay'):
+				sysvals.x2delay = getArgInt('-x2delay', value, 0, 60000, False)
+			elif(opt.lower() == 'postres'):
+				sysvals.postresumetime = getArgInt('-postres', value, 0, 3600, False)
+			elif(opt.lower() == 'rtcwake'):
+				sysvals.rtcwake = True
+				sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False)
+			elif(opt.lower() == 'timeprec'):
+				sysvals.setPrecision(getArgInt('-timeprec', value, 0, 6, False))
+			elif(opt.lower() == 'mindev'):
+				sysvals.mindevlen = getArgFloat('-mindev', value, 0.0, 10000.0, False)
+			elif(opt.lower() == 'mincg'):
+				sysvals.mincglen = getArgFloat('-mincg', value, 0.0, 10000.0, False)
+			elif(opt.lower() == 'kprobecolor'):
+				try:
+					val = int(value, 16)
+					sysvals.kprobecolor = '#'+value
+				except:
+					sysvals.kprobecolor = value
+			elif(opt.lower() == 'synccolor'):
+				try:
+					val = int(value, 16)
+					sysvals.synccolor = '#'+value
+				except:
+					sysvals.synccolor = value
+			elif(opt.lower() == 'output-dir'):
+				args = dict()
+				n = datetime.now()
+				args['date'] = n.strftime('%y%m%d')
+				args['time'] = n.strftime('%H%M%S')
+				args['hostname'] = sysvals.hostname
+				sysvals.outdir = value.format(**args)
+
+	if sysvals.suspendmode == 'command' and not sysvals.testcommand:
+		doError('No command supplied for mode "command"', False)
+	if sysvals.usedevsrc and sysvals.usecallgraph:
+		doError('dev and callgraph cannot both be true', False)
+	if sysvals.usecallgraph and sysvals.execcount > 1:
+		doError('-x2 is not compatible with -f', False)
+
+	if ignorekprobes:
+		return
+
+	kprobes = dict()
+	archkprobe = 'Kprobe_'+platform.machine()
+	if archkprobe in sections:
+		for name in Config.options(archkprobe):
+			kprobes[name] = Config.get(archkprobe, name)
+	if 'Kprobe' in sections:
+		for name in Config.options('Kprobe'):
+			kprobes[name] = Config.get('Kprobe', name)
+
+	for name in kprobes:
+		function = name
+		format = name
+		color = ''
+		args = dict()
+		data = kprobes[name].split()
+		i = 0
+		for val in data:
+			# bracketted strings are special formatting, read them separately
+			if val[0] == '[' and val[-1] == ']':
+				for prop in val[1:-1].split(','):
+					p = prop.split('=')
+					if p[0] == 'color':
+						try:
+							color = int(p[1], 16)
+							color = '#'+p[1]
+						except:
+							color = p[1]
+				continue
+			# first real arg should be the format string
+			if i == 0:
+				format = val
+			# all other args are actual function args
+			else:
+				d = val.split('=')
+				args[d[0]] = d[1]
+			i += 1
+		if not function or not format:
+			doError('Invalid kprobe: %s' % name, False)
+		for arg in re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', format):
+			if arg not in args:
+				doError('Kprobe "%s" is missing argument "%s"' % (name, arg), False)
+		if name in sysvals.kprobes:
+			doError('Duplicate kprobe found "%s"' % (name), False)
+		vprint('Adding KPROBE: %s %s %s %s' % (name, function, format, args))
+		sysvals.kprobes[name] = {
+			'name': name,
+			'func': function,
+			'format': format,
+			'args': args,
+			'mask': re.sub('{(?P<n>[a-z,A-Z,0-9]*)}', '.*', format)
+		}
+		if color:
+			sysvals.kprobes[name]['color'] = color
+
 # Function: printHelp
 # Description:
 #	 print out the help text
@@ -3375,7 +4651,7 @@ def printHelp():
 	modes = getModes()
 
 	print('')
-	print('AnalyzeSuspend v%.1f' % sysvals.version)
+	print('AnalyzeSuspend v%s' % sysvals.version)
 	print('Usage: sudo analyze_suspend.py <options>')
 	print('')
 	print('Description:')
@@ -3396,27 +4672,38 @@ def printHelp():
 	print('  [general]')
 	print('    -h          Print this help text')
 	print('    -v          Print the current tool version')
+	print('    -config file Pull arguments and config options from a file')
 	print('    -verbose    Print extra information during execution and analysis')
 	print('    -status     Test to see if the system is enabled to run this tool')
 	print('    -modes      List available suspend modes')
 	print('    -m mode     Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode)
-	print('    -rtcwake t  Use rtcwake to autoresume after <t> seconds (default: disabled)')
+	print('    -o subdir   Override the output subdirectory')
 	print('  [advanced]')
+	print('    -rtcwake t  Use rtcwake to autoresume after <t> seconds (default: disabled)')
+	print('    -addlogs    Add the dmesg and ftrace logs to the html output')
+	print('    -multi n d  Execute <n> consecutive tests at <d> seconds intervals. The outputs will')
+	print('                be created in a new subdirectory with a summary page.')
+	print('    -srgap      Add a visible gap in the timeline between sus/res (default: disabled)')
+	print('    -cmd {s}    Instead of suspend/resume, run a command, e.g. "sync -d"')
+	print('    -mindev ms  Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)')
+	print('    -mincg  ms  Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
+	print('    -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
+	print('  [debug]')
 	print('    -f          Use ftrace to create device callgraphs (default: disabled)')
-	print('    -filter "d1 d2 ..." Filter out all but this list of dev names')
+	print('    -expandcg   pre-expand the callgraph data in the html output (default: disabled)')
+	print('    -flist      Print the list of functions currently being captured in ftrace')
+	print('    -flistall   Print all functions capable of being captured in ftrace')
+	print('    -fadd file  Add functions to be graphed in the timeline from a list in a text file')
+	print('    -filter "d1 d2 ..." Filter out all but this list of device names')
+	print('    -dev        Display common low level functions in the timeline')
+	print('  [post-resume task analysis]')
 	print('    -x2         Run two suspend/resumes back to back (default: disabled)')
 	print('    -x2delay t  Minimum millisecond delay <t> between the two test runs (default: 0 ms)')
 	print('    -postres t  Time after resume completion to wait for post-resume events (default: 0 S)')
-	print('    -multi n d  Execute <n> consecutive tests at <d> seconds intervals. The outputs will')
-	print('                be created in a new subdirectory with a summary page.')
 	print('  [utilities]')
 	print('    -fpdt       Print out the contents of the ACPI Firmware Performance Data Table')
 	print('    -usbtopo    Print out the current USB topology with power info')
 	print('    -usbauto    Enable autosuspend for all connected USB devices')
-	print('  [android testing]')
-	print('    -adb binary Use the given adb binary to run the test on an android device.')
-	print('                The device should already be connected and with root access.')
-	print('                Commands will be executed on the device using "adb shell"')
 	print('  [re-analyze data from previous runs]')
 	print('    -ftrace ftracefile  Create HTML output using ftrace input')
 	print('    -dmesg dmesgfile    Create HTML output using dmesg (not needed for kernel >= 3.15)')
@@ -3430,6 +4717,7 @@ if __name__ == '__main__':
 	cmd = ''
 	cmdarg = ''
 	multitest = {'run': False, 'count': 0, 'delay': 0}
+	simplecmds = ['-modes', '-fpdt', '-flist', '-flistall', '-usbtopo', '-usbauto', '-status']
 	# loop through the command line arguments
 	args = iter(sys.argv[1:])
 	for arg in args:
@@ -3438,58 +4726,85 @@ if __name__ == '__main__':
 				val = args.next()
 			except:
 				doError('No mode supplied', True)
+			if val == 'command' and not sysvals.testcommand:
+				doError('No command supplied for mode "command"', True)
 			sysvals.suspendmode = val
-		elif(arg == '-adb'):
-			try:
-				val = args.next()
-			except:
-				doError('No adb binary supplied', True)
-			if(not os.path.exists(val)):
-				doError('file doesnt exist: %s' % val, False)
-			if(not os.access(val, os.X_OK)):
-				doError('file isnt executable: %s' % val, False)
-			try:
-				check = os.popen(val+' version').read().strip()
-			except:
-				doError('adb version failed to execute', False)
-			if(not re.match('Android Debug Bridge .*', check)):
-				doError('adb version failed to execute', False)
-			sysvals.adb = val
-			sysvals.android = True
+		elif(arg in simplecmds):
+			cmd = arg[1:]
+		elif(arg == '-h'):
+			printHelp()
+			sys.exit()
+		elif(arg == '-v'):
+			print("Version %s" % sysvals.version)
+			sys.exit()
 		elif(arg == '-x2'):
-			if(sysvals.postresumetime > 0):
-				doError('-x2 is not compatible with -postres', False)
 			sysvals.execcount = 2
+			if(sysvals.usecallgraph):
+				doError('-x2 is not compatible with -f', False)
 		elif(arg == '-x2delay'):
 			sysvals.x2delay = getArgInt('-x2delay', args, 0, 60000)
 		elif(arg == '-postres'):
-			if(sysvals.execcount != 1):
-				doError('-x2 is not compatible with -postres', False)
 			sysvals.postresumetime = getArgInt('-postres', args, 0, 3600)
 		elif(arg == '-f'):
 			sysvals.usecallgraph = True
-		elif(arg == '-modes'):
-			cmd = 'modes'
-		elif(arg == '-fpdt'):
-			cmd = 'fpdt'
-		elif(arg == '-usbtopo'):
-			cmd = 'usbtopo'
-		elif(arg == '-usbauto'):
-			cmd = 'usbauto'
-		elif(arg == '-status'):
-			cmd = 'status'
+			if(sysvals.execcount > 1):
+				doError('-x2 is not compatible with -f', False)
+			if(sysvals.usedevsrc):
+				doError('-dev is not compatible with -f', False)
+		elif(arg == '-addlogs'):
+			sysvals.addlogs = True
 		elif(arg == '-verbose'):
 			sysvals.verbose = True
-		elif(arg == '-v'):
-			print("Version %.1f" % sysvals.version)
-			sys.exit()
+		elif(arg == '-dev'):
+			sysvals.usedevsrc = True
+			if(sysvals.usecallgraph):
+				doError('-dev is not compatible with -f', False)
 		elif(arg == '-rtcwake'):
 			sysvals.rtcwake = True
 			sysvals.rtcwaketime = getArgInt('-rtcwake', args, 0, 3600)
+		elif(arg == '-timeprec'):
+			sysvals.setPrecision(getArgInt('-timeprec', args, 0, 6))
+		elif(arg == '-mindev'):
+			sysvals.mindevlen = getArgFloat('-mindev', args, 0.0, 10000.0)
+		elif(arg == '-mincg'):
+			sysvals.mincglen = getArgFloat('-mincg', args, 0.0, 10000.0)
+		elif(arg == '-cmd'):
+			try:
+				val = args.next()
+			except:
+				doError('No command string supplied', True)
+			sysvals.testcommand = val
+			sysvals.suspendmode = 'command'
+		elif(arg == '-expandcg'):
+			sysvals.cgexp = True
+		elif(arg == '-srgap'):
+			sysvals.srgap = 5
 		elif(arg == '-multi'):
 			multitest['run'] = True
 			multitest['count'] = getArgInt('-multi n (exec count)', args, 2, 1000000)
 			multitest['delay'] = getArgInt('-multi d (delay between tests)', args, 0, 3600)
+		elif(arg == '-o'):
+			try:
+				val = args.next()
+			except:
+				doError('No subdirectory name supplied', True)
+			sysvals.outdir = val
+		elif(arg == '-config'):
+			try:
+				val = args.next()
+			except:
+				doError('No text file supplied', True)
+			if(os.path.exists(val) == False):
+				doError('%s does not exist' % val, False)
+			configFromFile(val)
+		elif(arg == '-fadd'):
+			try:
+				val = args.next()
+			except:
+				doError('No text file supplied', True)
+			if(os.path.exists(val) == False):
+				doError('%s does not exist' % val, False)
+			sysvals.addFtraceFilterFunctions(val)
 		elif(arg == '-dmesg'):
 			try:
 				val = args.next()
@@ -3498,17 +4813,16 @@ if __name__ == '__main__':
 			sysvals.notestrun = True
 			sysvals.dmesgfile = val
 			if(os.path.exists(sysvals.dmesgfile) == False):
-				doError('%s doesnt exist' % sysvals.dmesgfile, False)
+				doError('%s does not exist' % sysvals.dmesgfile, False)
 		elif(arg == '-ftrace'):
 			try:
 				val = args.next()
 			except:
 				doError('No ftrace file supplied', True)
 			sysvals.notestrun = True
-			sysvals.usecallgraph = True
 			sysvals.ftracefile = val
 			if(os.path.exists(sysvals.ftracefile) == False):
-				doError('%s doesnt exist' % sysvals.ftracefile, False)
+				doError('%s does not exist' % sysvals.ftracefile, False)
 		elif(arg == '-summary'):
 			try:
 				val = args.next()
@@ -3518,35 +4832,35 @@ if __name__ == '__main__':
 			cmdarg = val
 			sysvals.notestrun = True
 			if(os.path.isdir(val) == False):
-				doError('%s isnt accesible' % val, False)
+				doError('%s is not accesible' % val, False)
 		elif(arg == '-filter'):
 			try:
 				val = args.next()
 			except:
 				doError('No devnames supplied', True)
 			sysvals.setDeviceFilter(val)
-		elif(arg == '-h'):
-			printHelp()
-			sys.exit()
 		else:
 			doError('Invalid argument: '+arg, True)
 
+	# callgraph size cannot exceed device size
+	if sysvals.mincglen < sysvals.mindevlen:
+		sysvals.mincglen = sysvals.mindevlen
+
 	# just run a utility command and exit
 	if(cmd != ''):
 		if(cmd == 'status'):
-			statusCheck()
+			statusCheck(True)
 		elif(cmd == 'fpdt'):
-			if(sysvals.android):
-				doError('cannot read FPDT on android device', False)
 			getFPDT(True)
 		elif(cmd == 'usbtopo'):
-			if(sysvals.android):
-				doError('cannot read USB topology '+\
-					'on an android device', False)
-			detectUSB(True)
+			detectUSB()
 		elif(cmd == 'modes'):
 			modes = getModes()
 			print modes
+		elif(cmd == 'flist'):
+			sysvals.getFtraceFilterFunctions(True)
+		elif(cmd == 'flistall'):
+			sysvals.getFtraceFilterFunctions(False)
 		elif(cmd == 'usbauto'):
 			setUSBDevicesAuto()
 		elif(cmd == 'summary'):
@@ -3554,15 +4868,6 @@ if __name__ == '__main__':
 			runSummary(cmdarg, True)
 		sys.exit()
 
-	# run test on android device
-	if(sysvals.android):
-		if(sysvals.usecallgraph):
-			doError('ftrace (-f) is not yet supported '+\
-				'in the android kernel', False)
-		if(sysvals.notestrun):
-			doError('cannot analyze test files on the '+\
-				'android device', False)
-
 	# if instructed, re-analyze existing data files
 	if(sysvals.notestrun):
 		rerunTest()
@@ -3574,18 +4879,20 @@ if __name__ == '__main__':
 		sys.exit()
 
 	if multitest['run']:
-		# run multiple tests in a separte subdirectory
+		# run multiple tests in a separate subdirectory
 		s = 'x%d' % multitest['count']
-		subdir = datetime.now().strftime('suspend-'+s+'-%m%d%y-%H%M%S')
-		os.mkdir(subdir)
+		if not sysvals.outdir:
+			sysvals.outdir = datetime.now().strftime('suspend-'+s+'-%m%d%y-%H%M%S')
+		if not os.path.isdir(sysvals.outdir):
+			os.mkdir(sysvals.outdir)
 		for i in range(multitest['count']):
 			if(i != 0):
 				print('Waiting %d seconds...' % (multitest['delay']))
 				time.sleep(multitest['delay'])
 			print('TEST (%d/%d) START' % (i+1, multitest['count']))
-			runTest(subdir)
+			runTest(sysvals.outdir)
 			print('TEST (%d/%d) COMPLETE' % (i+1, multitest['count']))
-		runSummary(subdir, False)
+		runSummary(sysvals.outdir, False)
 	else:
 		# run the test in the current directory
-		runTest(".")
+		runTest('.', sysvals.outdir)
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 2fc8fad5195e..4f2e9049e8fa 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -59,6 +59,12 @@ Output format selection (mutually exclusive):
   -text			Output plain text format.
 
 Output selection (mutually exclusive):
+  -export		Only output documentation for symbols that have been
+			exported using EXPORT_SYMBOL() or EXPORT_SYMBOL_GPL()
+                        in any input FILE or -export-file FILE.
+  -internal		Only output documentation for symbols that have NOT been
+			exported using EXPORT_SYMBOL() or EXPORT_SYMBOL_GPL()
+                        in any input FILE or -export-file FILE.
   -function NAME	Only output documentation for the given function(s)
 			or DOC: section title(s). All other functions and DOC:
 			sections are ignored. May be specified multiple times.
@@ -68,6 +74,11 @@ Output selection (mutually exclusive):
 
 Output selection modifiers:
   -no-doc-sections	Do not output DOC: sections.
+  -enable-lineno        Enable output of #define LINENO lines. Only works with
+                        reStructuredText format.
+  -export-file FILE     Specify an additional FILE in which to look for
+                        EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL(). To be used with
+                        -export or -internal. May be specified multiple times.
 
 Other parameters:
   -v			Verbose output, more warnings and other information.
@@ -206,6 +217,10 @@ my $type_struct_xml = '\\&amp;((struct\s*)*[_\w]+)';
 my $type_env = '(\$\w+)';
 my $type_enum_full = '\&(enum)\s*([_\w]+)';
 my $type_struct_full = '\&(struct)\s*([_\w]+)';
+my $type_typedef_full = '\&(typedef)\s*([_\w]+)';
+my $type_union_full = '\&(union)\s*([_\w]+)';
+my $type_member = '\&([_\w]+)((\.|->)[_\w]+)';
+my $type_member_func = $type_member . '\(\)';
 
 # Output conversion substitutions.
 #  One for each output format
@@ -274,10 +289,16 @@ my $blankline_text = "";
 # rst-mode
 my @highlights_rst = (
                        [$type_constant, "``\$1``"],
-                       [$type_func, "\\:c\\:func\\:`\$1`"],
+                       # Note: need to escape () to avoid func matching later
+                       [$type_member_func, "\\:c\\:type\\:`\$1\$2\\\\(\\\\) <\$1>`"],
+                       [$type_member, "\\:c\\:type\\:`\$1\$2 <\$1>`"],
+                       [$type_func, "\\:c\\:func\\:`\$1()`"],
                        [$type_struct_full, "\\:c\\:type\\:`\$1 \$2 <\$2>`"],
                        [$type_enum_full, "\\:c\\:type\\:`\$1 \$2 <\$2>`"],
-                       [$type_struct, "\\:c\\:type\\:`struct \$1 <\$1>`"],
+                       [$type_typedef_full, "\\:c\\:type\\:`\$1 \$2 <\$2>`"],
+                       [$type_union_full, "\\:c\\:type\\:`\$1 \$2 <\$2>`"],
+                       # in rst this can refer to any type
+                       [$type_struct, "\\:c\\:type\\:`\$1`"],
                        [$type_param, "**\$1**"]
 		      );
 my $blankline_rst = "\n";
@@ -303,12 +324,23 @@ my $verbose = 0;
 my $output_mode = "man";
 my $output_preformatted = 0;
 my $no_doc_sections = 0;
+my $enable_lineno = 0;
 my @highlights = @highlights_man;
 my $blankline = $blankline_man;
 my $modulename = "Kernel API";
-my $function_only = 0;
+
+use constant {
+    OUTPUT_ALL          => 0, # output all symbols and doc sections
+    OUTPUT_INCLUDE      => 1, # output only specified symbols
+    OUTPUT_EXCLUDE      => 2, # output everything except specified symbols
+    OUTPUT_EXPORTED     => 3, # output exported symbols
+    OUTPUT_INTERNAL     => 4, # output non-exported symbols
+};
+my $output_selection = OUTPUT_ALL;
 my $show_not_found = 0;
 
+my @export_file_list;
+
 my @build_time;
 if (defined($ENV{'KBUILD_BUILD_TIMESTAMP'}) &&
     (my $seconds = `date -d"${ENV{'KBUILD_BUILD_TIMESTAMP'}}" +%s`) ne '') {
@@ -327,6 +359,7 @@ my $man_date = ('January', 'February', 'March', 'April', 'May', 'June',
 # CAVEAT EMPTOR!  Some of the others I localised may not want to be, which
 # could cause "use of undefined value" or other bugs.
 my ($function, %function_table, %parametertypes, $declaration_purpose);
+my $declaration_start_line;
 my ($type, $declaration_name, $return_type);
 my ($newsection, $newcontents, $prototype, $brcount, %source_map);
 
@@ -344,52 +377,62 @@ my $section_counter = 0;
 
 my $lineprefix="";
 
-# states
-# 0 - normal code
-# 1 - looking for function name
-# 2 - scanning field start.
-# 3 - scanning prototype.
-# 4 - documentation block
-# 5 - gathering documentation outside main block
+# Parser states
+use constant {
+    STATE_NORMAL        => 0, # normal code
+    STATE_NAME          => 1, # looking for function name
+    STATE_FIELD         => 2, # scanning field start
+    STATE_PROTO         => 3, # scanning prototype
+    STATE_DOCBLOCK      => 4, # documentation block
+    STATE_INLINE        => 5, # gathering documentation outside main block
+};
 my $state;
 my $in_doc_sect;
 
-# Split Doc State
-# 0 - Invalid (Before start or after finish)
-# 1 - Is started (the /** was found inside a struct)
-# 2 - The @parameter header was found, start accepting multi paragraph text.
-# 3 - Finished (the */ was found)
-# 4 - Error - Comment without header was found. Spit a warning as it's not
-#     proper kernel-doc and ignore the rest.
-my $split_doc_state;
+# Inline documentation state
+use constant {
+    STATE_INLINE_NA     => 0, # not applicable ($state != STATE_INLINE)
+    STATE_INLINE_NAME   => 1, # looking for member name (@foo:)
+    STATE_INLINE_TEXT   => 2, # looking for member documentation
+    STATE_INLINE_END    => 3, # done
+    STATE_INLINE_ERROR  => 4, # error - Comment without header was found.
+                              # Spit a warning as it's not
+                              # proper kernel-doc and ignore the rest.
+};
+my $inline_doc_state;
 
 #declaration types: can be
 # 'function', 'struct', 'union', 'enum', 'typedef'
 my $decl_type;
 
-my $doc_special = "\@\%\$\&";
-
 my $doc_start = '^/\*\*\s*$'; # Allow whitespace at end of comment start.
 my $doc_end = '\*/';
 my $doc_com = '\s*\*\s*';
 my $doc_com_body = '\s*\* ?';
 my $doc_decl = $doc_com . '(\w+)';
-my $doc_sect = $doc_com . '([' . $doc_special . ']?[\w\s]+):(.*)';
+# @params and a strictly limited set of supported section names
+my $doc_sect = $doc_com . 
+    '\s*(\@\w+|description|context|returns?|notes?|examples?)\s*:(.*)';
 my $doc_content = $doc_com_body . '(.*)';
 my $doc_block = $doc_com . 'DOC:\s*(.*)?';
-my $doc_split_start = '^\s*/\*\*\s*$';
-my $doc_split_sect = '\s*\*\s*(@[\w\s]+):(.*)';
-my $doc_split_end = '^\s*\*/\s*$';
+my $doc_inline_start = '^\s*/\*\*\s*$';
+my $doc_inline_sect = '\s*\*\s*(@[\w\s]+):(.*)';
+my $doc_inline_end = '^\s*\*/\s*$';
+my $export_symbol = '^\s*EXPORT_SYMBOL(_GPL)?\s*\(\s*(\w+)\s*\)\s*;';
 
-my %constants;
 my %parameterdescs;
+my %parameterdesc_start_lines;
 my @parameterlist;
 my %sections;
 my @sectionlist;
+my %section_start_lines;
 my $sectcheck;
 my $struct_actual;
 
 my $contents = "";
+my $new_start_line = 0;
+
+# the canonical section names. see also $doc_sect above.
 my $section_default = "Description";	# default section
 my $section_intro = "Introduction";
 my $section = $section_default;
@@ -437,19 +480,30 @@ while ($ARGV[0] =~ m/^-(.*)/) {
     } elsif ($cmd eq "-module") { # not needed for XML, inherits from calling document
 	$modulename = shift @ARGV;
     } elsif ($cmd eq "-function") { # to only output specific functions
-	$function_only = 1;
+	$output_selection = OUTPUT_INCLUDE;
 	$function = shift @ARGV;
 	$function_table{$function} = 1;
-    } elsif ($cmd eq "-nofunction") { # to only output specific functions
-	$function_only = 2;
+    } elsif ($cmd eq "-nofunction") { # output all except specific functions
+	$output_selection = OUTPUT_EXCLUDE;
 	$function = shift @ARGV;
 	$function_table{$function} = 1;
+    } elsif ($cmd eq "-export") { # only exported symbols
+	$output_selection = OUTPUT_EXPORTED;
+	%function_table = ();
+    } elsif ($cmd eq "-internal") { # only non-exported symbols
+	$output_selection = OUTPUT_INTERNAL;
+	%function_table = ();
+    } elsif ($cmd eq "-export-file") {
+	my $file = shift @ARGV;
+	push(@export_file_list, $file);
     } elsif ($cmd eq "-v") {
 	$verbose = 1;
     } elsif (($cmd eq "-h") || ($cmd eq "--help")) {
 	usage();
     } elsif ($cmd eq '-no-doc-sections') {
 	    $no_doc_sections = 1;
+    } elsif ($cmd eq '-enable-lineno') {
+	    $enable_lineno = 1;
     } elsif ($cmd eq '-show-not-found') {
 	$show_not_found = 1;
     }
@@ -467,6 +521,13 @@ sub get_kernel_version() {
     return $version;
 }
 
+#
+sub print_lineno {
+    my $lineno = shift;
+    if ($enable_lineno && defined($lineno)) {
+        print "#define LINENO " . $lineno . "\n";
+    }
+}
 ##
 # dumps section contents to arrays/hashes intended for that purpose.
 #
@@ -475,28 +536,32 @@ sub dump_section {
     my $name = shift;
     my $contents = join "\n", @_;
 
-    if ($name =~ m/$type_constant/) {
-	$name = $1;
-#	print STDERR "constant section '$1' = '$contents'\n";
-	$constants{$name} = $contents;
-    } elsif ($name =~ m/$type_param/) {
-#	print STDERR "parameter def '$1' = '$contents'\n";
+    if ($name =~ m/$type_param/) {
 	$name = $1;
 	$parameterdescs{$name} = $contents;
 	$sectcheck = $sectcheck . $name . " ";
+        $parameterdesc_start_lines{$name} = $new_start_line;
+        $new_start_line = 0;
     } elsif ($name eq "@\.\.\.") {
-#	print STDERR "parameter def '...' = '$contents'\n";
 	$name = "...";
 	$parameterdescs{$name} = $contents;
 	$sectcheck = $sectcheck . $name . " ";
+        $parameterdesc_start_lines{$name} = $new_start_line;
+        $new_start_line = 0;
     } else {
-#	print STDERR "other section '$name' = '$contents'\n";
 	if (defined($sections{$name}) && ($sections{$name} ne "")) {
-		print STDERR "${file}:$.: error: duplicate section name '$name'\n";
-		++$errors;
+	    # Only warn on user specified duplicate section names.
+	    if ($name ne $section_default) {
+		print STDERR "${file}:$.: warning: duplicate section name '$name'\n";
+		++$warnings;
+	    }
+	    $sections{$name} .= $contents;
+	} else {
+	    $sections{$name} = $contents;
+	    push @sectionlist, $name;
+            $section_start_lines{$name} = $new_start_line;
+            $new_start_line = 0;
 	}
-	$sections{$name} = $contents;
-	push @sectionlist, $name;
     }
 }
 
@@ -512,15 +577,17 @@ sub dump_doc_section {
         return;
     }
 
-    if (($function_only == 0) ||
-	( $function_only == 1 && defined($function_table{$name})) ||
-	( $function_only == 2 && !defined($function_table{$name})))
+    if (($output_selection == OUTPUT_ALL) ||
+	($output_selection == OUTPUT_INCLUDE &&
+	 defined($function_table{$name})) ||
+	($output_selection == OUTPUT_EXCLUDE &&
+	 !defined($function_table{$name})))
     {
 	dump_section($file, $name, $contents);
 	output_blockhead({'sectionlist' => \@sectionlist,
 			  'sections' => \%sections,
 			  'module' => $modulename,
-			  'content-only' => ($function_only != 0), });
+			  'content-only' => ($output_selection != OUTPUT_ALL), });
     }
 }
 
@@ -1736,7 +1803,10 @@ sub output_blockhead_rst(%) {
     my ($parameter, $section);
 
     foreach $section (@{$args{'sectionlist'}}) {
-	print "**$section**\n\n";
+	if ($output_selection != OUTPUT_INCLUDE) {
+	    print "**$section**\n\n";
+	}
+        print_lineno($section_start_lines{$section});
 	output_highlight_rst($args{'sections'}{$section});
 	print "\n";
     }
@@ -1753,19 +1823,14 @@ sub output_highlight_rst {
     die $@ if $@;
 
     foreach $line (split "\n", $contents) {
-	if ($line eq "") {
-	    print $lineprefix, $blankline;
-	} else {
-	    $line =~ s/\\\\\\/\&/g;
-	    print $lineprefix, $line;
-	}
-	print "\n";
+	print $lineprefix . $line . "\n";
     }
 }
 
 sub output_function_rst(%) {
     my %args = %{$_[0]};
     my ($parameter, $section);
+    my $oldprefix = $lineprefix;
     my $start;
 
     print ".. c:function:: ";
@@ -1783,6 +1848,10 @@ sub output_function_rst(%) {
 	}
 	$count++;
 	$type = $args{'parametertypes'}{$parameter};
+
+	# RST doesn't like address_space tags at function prototypes
+	$type =~ s/__(user|kernel|iomem|percpu|pmem|rcu)\s*//;
+
 	if ($type =~ m/([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)/) {
 	    # pointer-to-function
 	    print $1 . $parameter . ") (" . $2;
@@ -1790,29 +1859,37 @@ sub output_function_rst(%) {
 	    print $type . " " . $parameter;
 	}
     }
-    print ")\n\n    " . $args{'purpose'} . "\n\n";
+    print ")\n\n";
+    print_lineno($declaration_start_line);
+    $lineprefix = "   ";
+    output_highlight_rst($args{'purpose'});
+    print "\n";
 
-    print ":Parameters:\n\n";
+    print "**Parameters**\n\n";
+    $lineprefix = "  ";
     foreach $parameter (@{$args{'parameterlist'}}) {
 	my $parameter_name = $parameter;
 	#$parameter_name =~ s/\[.*//;
 	$type = $args{'parametertypes'}{$parameter};
 
 	if ($type ne "") {
-	    print "      ``$type $parameter``\n";
+	    print "``$type $parameter``\n";
 	} else {
-	    print "      ``$parameter``\n";
+	    print "``$parameter``\n";
 	}
-	if ($args{'parameterdescs'}{$parameter_name} ne $undescribed) {
-	    my $oldprefix = $lineprefix;
-	    $lineprefix = "        ";
+
+        print_lineno($parameterdesc_start_lines{$parameter_name});
+
+	if (defined($args{'parameterdescs'}{$parameter_name}) &&
+	    $args{'parameterdescs'}{$parameter_name} ne $undescribed) {
 	    output_highlight_rst($args{'parameterdescs'}{$parameter_name});
-	    $lineprefix = $oldprefix;
 	} else {
-	    print "\n        _undescribed_\n";
+	    print "  *undescribed*\n";
 	}
 	print "\n";
     }
+
+    $lineprefix = $oldprefix;
     output_section_rst(@_);
 }
 
@@ -1820,10 +1897,11 @@ sub output_section_rst(%) {
     my %args = %{$_[0]};
     my $section;
     my $oldprefix = $lineprefix;
-    $lineprefix = "        ";
+    $lineprefix = "";
 
     foreach $section (@{$args{'sectionlist'}}) {
-	print ":$section:\n\n";
+	print "**$section**\n\n";
+        print_lineno($section_start_lines{$section});
 	output_highlight_rst($args{'sections'}{$section});
 	print "\n";
     }
@@ -1834,24 +1912,28 @@ sub output_section_rst(%) {
 sub output_enum_rst(%) {
     my %args = %{$_[0]};
     my ($parameter);
+    my $oldprefix = $lineprefix;
     my $count;
     my $name = "enum " . $args{'enum'};
 
     print "\n\n.. c:type:: " . $name . "\n\n";
-    print "    " . $args{'purpose'} . "\n\n";
+    print_lineno($declaration_start_line);
+    $lineprefix = "   ";
+    output_highlight_rst($args{'purpose'});
+    print "\n";
 
-    print "..\n\n:Constants:\n\n";
-    my $oldprefix = $lineprefix;
-    $lineprefix = "    ";
+    print "**Constants**\n\n";
+    $lineprefix = "  ";
     foreach $parameter (@{$args{'parameterlist'}}) {
-	print "  `$parameter`\n";
+	print "``$parameter``\n";
 	if ($args{'parameterdescs'}{$parameter} ne $undescribed) {
 	    output_highlight_rst($args{'parameterdescs'}{$parameter});
 	} else {
-	    print "    undescribed\n";
+	    print "  *undescribed*\n";
 	}
 	print "\n";
     }
+
     $lineprefix = $oldprefix;
     output_section_rst(@_);
 }
@@ -1859,30 +1941,37 @@ sub output_enum_rst(%) {
 sub output_typedef_rst(%) {
     my %args = %{$_[0]};
     my ($parameter);
-    my $count;
+    my $oldprefix = $lineprefix;
     my $name = "typedef " . $args{'typedef'};
 
-    ### FIXME: should the name below contain "typedef" or not?
     print "\n\n.. c:type:: " . $name . "\n\n";
-    print "    " . $args{'purpose'} . "\n\n";
+    print_lineno($declaration_start_line);
+    $lineprefix = "   ";
+    output_highlight_rst($args{'purpose'});
+    print "\n";
 
+    $lineprefix = $oldprefix;
     output_section_rst(@_);
 }
 
 sub output_struct_rst(%) {
     my %args = %{$_[0]};
     my ($parameter);
+    my $oldprefix = $lineprefix;
     my $name = $args{'type'} . " " . $args{'struct'};
 
     print "\n\n.. c:type:: " . $name . "\n\n";
-    print "    " . $args{'purpose'} . "\n\n";
+    print_lineno($declaration_start_line);
+    $lineprefix = "   ";
+    output_highlight_rst($args{'purpose'});
+    print "\n";
 
-    print ":Definition:\n\n";
-    print " ::\n\n";
+    print "**Definition**\n\n";
+    print "::\n\n";
     print "  " . $args{'type'} . " " . $args{'struct'} . " {\n";
     foreach $parameter (@{$args{'parameterlist'}}) {
 	if ($parameter =~ /^#/) {
-	    print "    " . "$parameter\n";
+	    print "  " . "$parameter\n";
 	    next;
 	}
 
@@ -1903,7 +1992,8 @@ sub output_struct_rst(%) {
     }
     print "  };\n\n";
 
-    print ":Members:\n\n";
+    print "**Members**\n\n";
+    $lineprefix = "  ";
     foreach $parameter (@{$args{'parameterlist'}}) {
 	($parameter =~ /^#/) && next;
 
@@ -1912,14 +2002,14 @@ sub output_struct_rst(%) {
 
 	($args{'parameterdescs'}{$parameter_name} ne $undescribed) || next;
 	$type = $args{'parametertypes'}{$parameter};
-	print "      `$type $parameter`" . "\n";
-	my $oldprefix = $lineprefix;
-	$lineprefix = "        ";
+        print_lineno($parameterdesc_start_lines{$parameter_name});
+	print "``$type $parameter``\n";
 	output_highlight_rst($args{'parameterdescs'}{$parameter_name});
-	$lineprefix = $oldprefix;
 	print "\n";
     }
     print "\n";
+
+    $lineprefix = $oldprefix;
     output_section_rst(@_);
 }
 
@@ -1969,9 +2059,13 @@ sub output_declaration {
     my $name = shift;
     my $functype = shift;
     my $func = "output_${functype}_$output_mode";
-    if (($function_only==0) ||
-	( $function_only == 1 && defined($function_table{$name})) ||
-	( $function_only == 2 && !($functype eq "function" && defined($function_table{$name}))))
+    if (($output_selection == OUTPUT_ALL) ||
+	(($output_selection == OUTPUT_INCLUDE ||
+	  $output_selection == OUTPUT_EXPORTED) &&
+	 defined($function_table{$name})) ||
+	(($output_selection == OUTPUT_EXCLUDE ||
+	  $output_selection == OUTPUT_INTERNAL) &&
+	 !($functype eq "function" && defined($function_table{$name}))))
     {
 	&$func(@_);
 	$section_counter++;
@@ -2471,7 +2565,6 @@ sub dump_function($$) {
 
 sub reset_state {
     $function = "";
-    %constants = ();
     %parameterdescs = ();
     %parametertypes = ();
     @parameterlist = ();
@@ -2481,8 +2574,8 @@ sub reset_state {
     $struct_actual = "";
     $prototype = "";
 
-    $state = 0;
-    $split_doc_state = 0;
+    $state = STATE_NORMAL;
+    $inline_doc_state = STATE_INLINE_NA;
 }
 
 sub tracepoint_munge($) {
@@ -2545,7 +2638,7 @@ sub syscall_munge() {
 	}
 }
 
-sub process_state3_function($$) {
+sub process_proto_function($$) {
     my $x = shift;
     my $file = shift;
 
@@ -2575,7 +2668,7 @@ sub process_state3_function($$) {
     }
 }
 
-sub process_state3_type($$) {
+sub process_proto_type($$) {
     my $x = shift;
     my $file = shift;
 
@@ -2649,25 +2742,54 @@ sub local_unescape($) {
 	return $text;
 }
 
-sub process_file($) {
+sub map_filename($) {
     my $file;
-    my $identifier;
-    my $func;
-    my $descr;
-    my $in_purpose = 0;
-    my $initial_section_counter = $section_counter;
     my ($orig_file) = @_;
 
     if (defined($ENV{'SRCTREE'})) {
 	$file = "$ENV{'SRCTREE'}" . "/" . $orig_file;
-    }
-    else {
+    } else {
 	$file = $orig_file;
     }
+
     if (defined($source_map{$file})) {
 	$file = $source_map{$file};
     }
 
+    return $file;
+}
+
+sub process_export_file($) {
+    my ($orig_file) = @_;
+    my $file = map_filename($orig_file);
+
+    if (!open(IN,"<$file")) {
+	print STDERR "Error: Cannot open file $file\n";
+	++$errors;
+	return;
+    }
+
+    while (<IN>) {
+	if (/$export_symbol/) {
+	    $function_table{$2} = 1;
+	}
+    }
+
+    close(IN);
+}
+
+sub process_file($) {
+    my $file;
+    my $identifier;
+    my $func;
+    my $descr;
+    my $in_purpose = 0;
+    my $initial_section_counter = $section_counter;
+    my ($orig_file) = @_;
+    my $leading_space;
+
+    $file = map_filename($orig_file);
+
     if (!open(IN,"<$file")) {
 	print STDERR "Error: Cannot open file $file\n";
 	++$errors;
@@ -2681,15 +2803,18 @@ sub process_file($) {
 	while (s/\\\s*$//) {
 	    $_ .= <IN>;
 	}
-	if ($state == 0) {
+	if ($state == STATE_NORMAL) {
 	    if (/$doc_start/o) {
-		$state = 1;		# next line is always the function name
+		$state = STATE_NAME;	# next line is always the function name
 		$in_doc_sect = 0;
+		$declaration_start_line = $. + 1;
 	    }
-	} elsif ($state == 1) {	# this line is the function name (always)
+	} elsif ($state == STATE_NAME) {# this line is the function name (always)
 	    if (/$doc_block/o) {
-		$state = 4;
+		$state = STATE_DOCBLOCK;
 		$contents = "";
+                $new_start_line = $. + 1;
+
 		if ( $1 eq "" ) {
 			$section = $section_intro;
 		} else {
@@ -2702,7 +2827,12 @@ sub process_file($) {
 		    $identifier = $1;
 		}
 
-		$state = 2;
+		$state = STATE_FIELD;
+		# if there's no @param blocks need to set up default section
+		# here
+		$contents = "";
+		$section = $section_default;
+		$new_start_line = $. + 1;
 		if (/-(.*)/) {
 		    # strip leading/trailing/multiple spaces
 		    $descr= $1;
@@ -2740,13 +2870,25 @@ sub process_file($) {
 		print STDERR "${file}:$.: warning: Cannot understand $_ on line $.",
 		" - I thought it was a doc line\n";
 		++$warnings;
-		$state = 0;
+		$state = STATE_NORMAL;
 	    }
-	} elsif ($state == 2) {	# look for head: lines, and include content
-	    if (/$doc_sect/o) {
+	} elsif ($state == STATE_FIELD) {	# look for head: lines, and include content
+	    if (/$doc_sect/i) { # case insensitive for supported section names
 		$newsection = $1;
 		$newcontents = $2;
 
+		# map the supported section names to the canonical names
+		if ($newsection =~ m/^description$/i) {
+		    $newsection = $section_default;
+		} elsif ($newsection =~ m/^context$/i) {
+		    $newsection = $section_context;
+		} elsif ($newsection =~ m/^returns?$/i) {
+		    $newsection = $section_return;
+		} elsif ($newsection =~ m/^\@return$/) {
+		    # special: @return is a section, not a param description
+		    $newsection = $section_return;
+		}
+
 		if (($contents ne "") && ($contents ne "\n")) {
 		    if (!$in_doc_sect && $verbose) {
 			print STDERR "${file}:$.: warning: contents before sections\n";
@@ -2759,14 +2901,16 @@ sub process_file($) {
 		$in_doc_sect = 1;
 		$in_purpose = 0;
 		$contents = $newcontents;
+                $new_start_line = $.;
+		while ((substr($contents, 0, 1) eq " ") ||
+		       substr($contents, 0, 1) eq "\t") {
+		    $contents = substr($contents, 1);
+		}
 		if ($contents ne "") {
-		    while ((substr($contents, 0, 1) eq " ") ||
-			substr($contents, 0, 1) eq "\t") {
-			    $contents = substr($contents, 1);
-		    }
 		    $contents .= "\n";
 		}
 		$section = $newsection;
+		$leading_space = undef;
 	    } elsif (/$doc_end/) {
 		if (($contents ne "") && ($contents ne "\n")) {
 		    dump_section($file, $section, xml_escape($contents));
@@ -2780,7 +2924,7 @@ sub process_file($) {
 		}
 
 		$prototype = "";
-		$state = 3;
+		$state = STATE_PROTO;
 		$brcount = 0;
 #		print STDERR "end of doc comment, looking for prototype\n";
 	    } elsif (/$doc_content/) {
@@ -2791,6 +2935,7 @@ sub process_file($) {
 			dump_section($file, $section, xml_escape($contents));
 			$section = $section_default;
 			$contents = "";
+                        $new_start_line = $.;
 		    } else {
 			$contents .= "\n";
 		    }
@@ -2801,87 +2946,86 @@ sub process_file($) {
 		    $declaration_purpose .= " " . xml_escape($1);
 		    $declaration_purpose =~ s/\s+/ /g;
 		} else {
-		    $contents .= $1 . "\n";
+		    my $cont = $1;
+		    if ($section =~ m/^@/ || $section eq $section_context) {
+			if (!defined $leading_space) {
+			    if ($cont =~ m/^(\s+)/) {
+				$leading_space = $1;
+			    } else {
+				$leading_space = "";
+			    }
+			}
+
+			$cont =~ s/^$leading_space//;
+		    }
+		    $contents .= $cont . "\n";
 		}
 	    } else {
 		# i dont know - bad line?  ignore.
 		print STDERR "${file}:$.: warning: bad line: $_";
 		++$warnings;
 	    }
-	} elsif ($state == 5) { # scanning for split parameters
+	} elsif ($state == STATE_INLINE) { # scanning for inline parameters
 	    # First line (state 1) needs to be a @parameter
-	    if ($split_doc_state == 1 && /$doc_split_sect/o) {
+	    if ($inline_doc_state == STATE_INLINE_NAME && /$doc_inline_sect/o) {
 		$section = $1;
 		$contents = $2;
+                $new_start_line = $.;
 		if ($contents ne "") {
 		    while ((substr($contents, 0, 1) eq " ") ||
 		           substr($contents, 0, 1) eq "\t") {
 			$contents = substr($contents, 1);
 		    }
-		$contents .= "\n";
+		    $contents .= "\n";
 		}
-		$split_doc_state = 2;
+		$inline_doc_state = STATE_INLINE_TEXT;
 	    # Documentation block end */
-	    } elsif (/$doc_split_end/) {
+	    } elsif (/$doc_inline_end/) {
 		if (($contents ne "") && ($contents ne "\n")) {
 		    dump_section($file, $section, xml_escape($contents));
 		    $section = $section_default;
 		    $contents = "";
 		}
-		$state = 3;
-		$split_doc_state = 0;
+		$state = STATE_PROTO;
+		$inline_doc_state = STATE_INLINE_NA;
 	    # Regular text
 	    } elsif (/$doc_content/) {
-		if ($split_doc_state == 2) {
+		if ($inline_doc_state == STATE_INLINE_TEXT) {
 		    $contents .= $1 . "\n";
-		} elsif ($split_doc_state == 1) {
-		    $split_doc_state = 4;
-		    print STDERR "Warning(${file}:$.): ";
+		    # nuke leading blank lines
+		    if ($contents =~ /^\s*$/) {
+			$contents = "";
+		    }
+		} elsif ($inline_doc_state == STATE_INLINE_NAME) {
+		    $inline_doc_state = STATE_INLINE_ERROR;
+		    print STDERR "${file}:$.: warning: ";
 		    print STDERR "Incorrect use of kernel-doc format: $_";
 		    ++$warnings;
 		}
 	    }
-	} elsif ($state == 3) {	# scanning for function '{' (end of prototype)
-	    if (/$doc_split_start/) {
-		$state = 5;
-		$split_doc_state = 1;
+	} elsif ($state == STATE_PROTO) {	# scanning for function '{' (end of prototype)
+	    if (/$doc_inline_start/) {
+		$state = STATE_INLINE;
+		$inline_doc_state = STATE_INLINE_NAME;
 	    } elsif ($decl_type eq 'function') {
-		process_state3_function($_, $file);
+		process_proto_function($_, $file);
 	    } else {
-		process_state3_type($_, $file);
+		process_proto_type($_, $file);
 	    }
-	} elsif ($state == 4) {
-		# Documentation block
-		if (/$doc_block/) {
-			dump_doc_section($file, $section, xml_escape($contents));
-			$contents = "";
-			$function = "";
-			%constants = ();
-			%parameterdescs = ();
-			%parametertypes = ();
-			@parameterlist = ();
-			%sections = ();
-			@sectionlist = ();
-			$prototype = "";
-			if ( $1 eq "" ) {
-				$section = $section_intro;
-			} else {
-				$section = $1;
-			}
-		}
-		elsif (/$doc_end/)
+	} elsif ($state == STATE_DOCBLOCK) {
+		if (/$doc_end/)
 		{
 			dump_doc_section($file, $section, xml_escape($contents));
+			$section = $section_default;
 			$contents = "";
 			$function = "";
-			%constants = ();
 			%parameterdescs = ();
 			%parametertypes = ();
 			@parameterlist = ();
 			%sections = ();
 			@sectionlist = ();
 			$prototype = "";
-			$state = 0;
+			$state = STATE_NORMAL;
 		}
 		elsif (/$doc_content/)
 		{
@@ -2898,7 +3042,7 @@ sub process_file($) {
     }
     if ($initial_section_counter == $section_counter) {
 	print STDERR "${file}:1: warning: no structured comments found\n";
-	if (($function_only == 1) && ($show_not_found == 1)) {
+	if (($output_selection == OUTPUT_INCLUDE) && ($show_not_found == 1)) {
 	    print STDERR "    Was looking for '$_'.\n" for keys %function_table;
 	}
 	if ($output_mode eq "xml") {
@@ -2957,6 +3101,17 @@ if (open(SOURCE_MAP, "<.tmp_filelist.txt")) {
 	close(SOURCE_MAP);
 }
 
+if ($output_selection == OUTPUT_EXPORTED ||
+    $output_selection == OUTPUT_INTERNAL) {
+
+    push(@export_file_list, @ARGV);
+
+    foreach (@export_file_list) {
+	chomp;
+	process_export_file($_);
+    }
+}
+
 foreach (@ARGV) {
     chomp;
     process_file($_);
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 9e443fccad4c..c0b3030b5634 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -18,6 +18,7 @@
 #include <keys/user-type.h>
 #include <keys/big_key-type.h>
 #include <crypto/rng.h>
+#include <crypto/skcipher.h>
 
 /*
  * Layout of key payload words.
@@ -74,7 +75,7 @@ static const char big_key_alg_name[] = "ecb(aes)";
  * Crypto algorithms for big_key data encryption
  */
 static struct crypto_rng *big_key_rng;
-static struct crypto_blkcipher *big_key_blkcipher;
+static struct crypto_skcipher *big_key_skcipher;
 
 /*
  * Generate random key to encrypt big_key data
@@ -91,22 +92,26 @@ static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key)
 {
 	int ret = -EINVAL;
 	struct scatterlist sgio;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher);
 
-	if (crypto_blkcipher_setkey(big_key_blkcipher, key, ENC_KEY_SIZE)) {
+	if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) {
 		ret = -EAGAIN;
 		goto error;
 	}
 
-	desc.flags = 0;
-	desc.tfm = big_key_blkcipher;
+	skcipher_request_set_tfm(req, big_key_skcipher);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
 
 	sg_init_one(&sgio, data, datalen);
+	skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL);
 
 	if (op == BIG_KEY_ENC)
-		ret = crypto_blkcipher_encrypt(&desc, &sgio, &sgio, datalen);
+		ret = crypto_skcipher_encrypt(req);
 	else
-		ret = crypto_blkcipher_decrypt(&desc, &sgio, &sgio, datalen);
+		ret = crypto_skcipher_decrypt(req);
+
+	skcipher_request_zero(req);
 
 error:
 	return ret;
@@ -140,7 +145,7 @@ int big_key_preparse(struct key_preparsed_payload *prep)
 		 *
 		 * File content is stored encrypted with randomly generated key.
 		 */
-		size_t enclen = ALIGN(datalen, crypto_blkcipher_blocksize(big_key_blkcipher));
+		size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
 
 		/* prepare aligned data to encrypt */
 		data = kmalloc(enclen, GFP_KERNEL);
@@ -288,7 +293,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
 		struct file *file;
 		u8 *data;
 		u8 *enckey = (u8 *)key->payload.data[big_key_data];
-		size_t enclen = ALIGN(datalen, crypto_blkcipher_blocksize(big_key_blkcipher));
+		size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
 
 		data = kmalloc(enclen, GFP_KERNEL);
 		if (!data)
@@ -359,9 +364,10 @@ static int __init big_key_crypto_init(void)
 		goto error;
 
 	/* init block cipher */
-	big_key_blkcipher = crypto_alloc_blkcipher(big_key_alg_name, 0, 0);
-	if (IS_ERR(big_key_blkcipher)) {
-		big_key_blkcipher = NULL;
+	big_key_skcipher = crypto_alloc_skcipher(big_key_alg_name,
+						 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(big_key_skcipher)) {
+		big_key_skcipher = NULL;
 		ret = -EFAULT;
 		goto error;
 	}
diff --git a/tools/Makefile b/tools/Makefile
index f10b64d8c674..daa8fb3e4363 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -85,7 +85,7 @@ tmon: FORCE
 freefall: FORCE
 	$(call descend,laptop/$@)
 
-all: acpi cgroup cpupower hv firewire lguest \
+all: acpi cgroup cpupower gpio hv firewire lguest \
 		perf selftests turbostat usb \
 		virtio vm net x86_energy_perf_policy \
 		tmon freefall objtool
@@ -96,7 +96,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install:
+cgroup_install firewire_install gpio_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install:
 	$(call descend,$(@:_install=),install)
 
 selftests_install:
@@ -114,7 +114,8 @@ freefall_install:
 kvm_stat_install:
 	$(call descend,kvm/$(@:_install=),install)
 
-install: acpi_install cgroup_install cpupower_install hv_install firewire_install lguest_install \
+install: acpi_install cgroup_install cpupower_install gpio_install \
+		hv_install firewire_install lguest_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install vm_install net_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install
diff --git a/tools/gpio/Build b/tools/gpio/Build
new file mode 100644
index 000000000000..620c1937d957
--- /dev/null
+++ b/tools/gpio/Build
@@ -0,0 +1,3 @@
+lsgpio-y += lsgpio.o gpio-utils.o
+gpio-hammer-y += gpio-hammer.o gpio-utils.o
+gpio-event-mon-y += gpio-event-mon.o gpio-utils.o
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index c155d6bc47a7..250a891e6ef0 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -1,12 +1,75 @@
+include ../scripts/Makefile.include
+
+bindir ?= /usr/bin
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
 CC = $(CROSS_COMPILE)gcc
-CFLAGS += -O2 -Wall -g -D_GNU_SOURCE
+LD = $(CROSS_COMPILE)ld
+CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+
+ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
 
-all: lsgpio
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
 
-lsgpio: lsgpio.o gpio-utils.o
+#
+# We need the following to be outside of kernel tree
+#
+$(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h
+	mkdir -p $(OUTPUT)include/linux 2>&1 || true
+	ln -sf $(CURDIR)/../../include/uapi/linux/gpio.h $@
 
-%.o: %.c gpio-utils.h
+prepare: $(OUTPUT)include/linux/gpio.h
+
+#
+# lsgpio
+#
+LSGPIO_IN := $(OUTPUT)lsgpio-in.o
+$(LSGPIO_IN): prepare FORCE
+	$(Q)$(MAKE) $(build)=lsgpio
+$(OUTPUT)lsgpio: $(LSGPIO_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+
+#
+# gpio-hammer
+#
+GPIO_HAMMER_IN := $(OUTPUT)gpio-hammer-in.o
+$(GPIO_HAMMER_IN): prepare FORCE
+	$(Q)$(MAKE) $(build)=gpio-hammer
+$(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+
+#
+# gpio-event-mon
+#
+GPIO_EVENT_MON_IN := $(OUTPUT)gpio-event-mon-in.o
+$(GPIO_EVENT_MON_IN): prepare FORCE
+	$(Q)$(MAKE) $(build)=gpio-event-mon
+$(OUTPUT)gpio-event-mon: $(GPIO_EVENT_MON_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
 
-.PHONY: clean
 clean:
-	rm -f *.o lsgpio
+	rm -f $(ALL_PROGRAMS)
+	rm -f $(OUTPUT)include/linux/gpio.h
+	find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+
+install: $(ALL_PROGRAMS)
+	install -d -m 755 $(DESTDIR)$(bindir);		\
+	for program in $(ALL_PROGRAMS); do		\
+		install $$program $(DESTDIR)$(bindir);	\
+	done
+
+FORCE:
+
+.PHONY: all install clean FORCE prepare
diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c
new file mode 100644
index 000000000000..448ed96b3b4f
--- /dev/null
+++ b/tools/gpio/gpio-event-mon.c
@@ -0,0 +1,192 @@
+/*
+ * gpio-hammer - example swiss army knife to shake GPIO lines on a system
+ *
+ * Copyright (C) 2016 Linus Walleij
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * Usage:
+ *	gpio-event-mon -n <device-name> -o <offset>
+ */
+
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <dirent.h>
+#include <errno.h>
+#include <string.h>
+#include <poll.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <inttypes.h>
+#include <sys/ioctl.h>
+#include <linux/gpio.h>
+
+int monitor_device(const char *device_name,
+		   unsigned int line,
+		   u_int32_t handleflags,
+		   u_int32_t eventflags,
+		   unsigned int loops)
+{
+	struct gpioevent_request req;
+	struct gpiohandle_data data;
+	char *chrdev_name;
+	int fd;
+	int ret;
+	int i = 0;
+
+	ret = asprintf(&chrdev_name, "/dev/%s", device_name);
+	if (ret < 0)
+		return -ENOMEM;
+
+	fd = open(chrdev_name, 0);
+	if (fd == -1) {
+		ret = -errno;
+		fprintf(stderr, "Failed to open %s\n", chrdev_name);
+		goto exit_close_error;
+	}
+
+	req.lineoffset = line;
+	req.handleflags = handleflags;
+	req.eventflags = eventflags;
+	strcpy(req.consumer_label, "gpio-event-mon");
+
+	ret = ioctl(fd, GPIO_GET_LINEEVENT_IOCTL, &req);
+	if (ret == -1) {
+		ret = -errno;
+		fprintf(stderr, "Failed to issue GET EVENT "
+			"IOCTL (%d)\n",
+			ret);
+		goto exit_close_error;
+	}
+
+	/* Read initial states */
+	ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data);
+	if (ret == -1) {
+		ret = -errno;
+		fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE "
+			"VALUES IOCTL (%d)\n",
+			ret);
+		goto exit_close_error;
+	}
+
+	fprintf(stdout, "Monitoring line %d on %s\n", line, device_name);
+	fprintf(stdout, "Initial line value: %d\n", data.values[0]);
+
+	while (1) {
+		struct gpioevent_data event;
+
+		ret = read(req.fd, &event, sizeof(event));
+		if (ret == -1) {
+			if (errno == -EAGAIN) {
+				fprintf(stderr, "nothing available\n");
+				continue;
+			} else {
+				ret = -errno;
+				fprintf(stderr, "Failed to read event (%d)\n",
+					ret);
+				break;
+			}
+		}
+
+		if (ret != sizeof(event)) {
+			fprintf(stderr, "Reading event failed\n");
+			ret = -EIO;
+			break;
+		}
+		fprintf(stdout, "GPIO EVENT %" PRIu64 ": ", event.timestamp);
+		switch (event.id) {
+		case GPIOEVENT_EVENT_RISING_EDGE:
+			fprintf(stdout, "rising edge");
+			break;
+		case GPIOEVENT_EVENT_FALLING_EDGE:
+			fprintf(stdout, "falling edge");
+			break;
+		default:
+			fprintf(stdout, "unknown event");
+		}
+		fprintf(stdout, "\n");
+
+		i++;
+		if (i == loops)
+			break;
+	}
+
+exit_close_error:
+	if (close(fd) == -1)
+		perror("Failed to close GPIO character device file");
+	free(chrdev_name);
+	return ret;
+}
+
+void print_usage(void)
+{
+	fprintf(stderr, "Usage: gpio-event-mon [options]...\n"
+		"Listen to events on GPIO lines, 0->1 1->0\n"
+		"  -n <name>  Listen on GPIOs on a named device (must be stated)\n"
+		"  -o <n>     Offset to monitor\n"
+		"  -d         Set line as open drain\n"
+		"  -s         Set line as open source\n"
+		"  -r         Listen for rising edges\n"
+		"  -f         Listen for falling edges\n"
+		" [-c <n>]    Do <n> loops (optional, infinite loop if not stated)\n"
+		"  -?         This helptext\n"
+		"\n"
+		"Example:\n"
+		"gpio-event-mon -n gpiochip0 -o 4 -r -f\n"
+	);
+}
+
+int main(int argc, char **argv)
+{
+	const char *device_name = NULL;
+	unsigned int line = -1;
+	unsigned int loops = 0;
+	u_int32_t handleflags = GPIOHANDLE_REQUEST_INPUT;
+	u_int32_t eventflags = 0;
+	int c;
+
+	while ((c = getopt(argc, argv, "c:n:o:dsrf?")) != -1) {
+		switch (c) {
+		case 'c':
+			loops = strtoul(optarg, NULL, 10);
+			break;
+		case 'n':
+			device_name = optarg;
+			break;
+		case 'o':
+			line = strtoul(optarg, NULL, 10);
+			break;
+		case 'd':
+			handleflags |= GPIOHANDLE_REQUEST_OPEN_DRAIN;
+			break;
+		case 's':
+			handleflags |= GPIOHANDLE_REQUEST_OPEN_SOURCE;
+			break;
+		case 'r':
+			eventflags |= GPIOEVENT_REQUEST_RISING_EDGE;
+			break;
+		case 'f':
+			eventflags |= GPIOEVENT_REQUEST_FALLING_EDGE;
+			break;
+		case '?':
+			print_usage();
+			return -1;
+		}
+	}
+
+	if (!device_name || line == -1) {
+		print_usage();
+		return -1;
+	}
+	if (!eventflags) {
+		printf("No flags specified, listening on both rising and "
+		       "falling edges\n");
+		eventflags = GPIOEVENT_REQUEST_BOTH_EDGES;
+	}
+	return monitor_device(device_name, line, handleflags,
+			      eventflags, loops);
+}
diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c
new file mode 100644
index 000000000000..37b3f141053d
--- /dev/null
+++ b/tools/gpio/gpio-hammer.c
@@ -0,0 +1,189 @@
+/*
+ * gpio-hammer - example swiss army knife to shake GPIO lines on a system
+ *
+ * Copyright (C) 2016 Linus Walleij
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * Usage:
+ *	gpio-hammer -n <device-name> -o <offset1> -o <offset2>
+ */
+
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <dirent.h>
+#include <errno.h>
+#include <string.h>
+#include <poll.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <sys/ioctl.h>
+#include <linux/gpio.h>
+
+int hammer_device(const char *device_name, unsigned int *lines, int nlines,
+		  unsigned int loops)
+{
+	struct gpiohandle_request req;
+	struct gpiohandle_data data;
+	char *chrdev_name;
+	char swirr[] = "-\\|/";
+	int fd;
+	int ret;
+	int i, j;
+	unsigned int iteration = 0;
+
+	ret = asprintf(&chrdev_name, "/dev/%s", device_name);
+	if (ret < 0)
+		return -ENOMEM;
+
+	fd = open(chrdev_name, 0);
+	if (fd == -1) {
+		ret = -errno;
+		fprintf(stderr, "Failed to open %s\n", chrdev_name);
+		goto exit_close_error;
+	}
+
+	/* Request lines as output */
+	for (i = 0; i < nlines; i++)
+		req.lineoffsets[i] = lines[i];
+	req.flags = GPIOHANDLE_REQUEST_OUTPUT; /* Request as output */
+	strcpy(req.consumer_label, "gpio-hammer");
+	req.lines = nlines;
+	ret = ioctl(fd, GPIO_GET_LINEHANDLE_IOCTL, &req);
+	if (ret == -1) {
+		ret = -errno;
+		fprintf(stderr, "Failed to issue GET LINEHANDLE "
+			"IOCTL (%d)\n",
+			ret);
+		goto exit_close_error;
+	}
+
+	/* Read initial states */
+	ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data);
+	if (ret == -1) {
+		ret = -errno;
+		fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE "
+			"VALUES IOCTL (%d)\n",
+			ret);
+		goto exit_close_error;
+	}
+	fprintf(stdout, "Hammer lines [");
+	for (i = 0; i < nlines; i++) {
+		fprintf(stdout, "%d", lines[i]);
+		if (i != (nlines - 1))
+			fprintf(stdout, ", ");
+	}
+	fprintf(stdout, "] on %s, initial states: [", device_name);
+	for (i = 0; i < nlines; i++) {
+		fprintf(stdout, "%d", data.values[i]);
+		if (i != (nlines - 1))
+			fprintf(stdout, ", ");
+	}
+	fprintf(stdout, "]\n");
+
+	/* Hammertime! */
+	j = 0;
+	while (1) {
+		/* Invert all lines so we blink */
+		for (i = 0; i < nlines; i++)
+			data.values[i] = !data.values[i];
+
+		ret = ioctl(req.fd, GPIOHANDLE_SET_LINE_VALUES_IOCTL, &data);
+		if (ret == -1) {
+			ret = -errno;
+			fprintf(stderr, "Failed to issue GPIOHANDLE SET LINE "
+				"VALUES IOCTL (%d)\n",
+				ret);
+			goto exit_close_error;
+		}
+		/* Re-read values to get status */
+		ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data);
+		if (ret == -1) {
+			ret = -errno;
+			fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE "
+				"VALUES IOCTL (%d)\n",
+				ret);
+			goto exit_close_error;
+		}
+
+		fprintf(stdout, "[%c] ", swirr[j]);
+		j++;
+		if (j == sizeof(swirr)-1)
+			j = 0;
+
+		fprintf(stdout, "[");
+		for (i = 0; i < nlines; i++) {
+			fprintf(stdout, "%d: %d", lines[i], data.values[i]);
+			if (i != (nlines - 1))
+				fprintf(stdout, ", ");
+		}
+		fprintf(stdout, "]\r");
+		fflush(stdout);
+		sleep(1);
+		iteration++;
+		if (loops && iteration == loops)
+			break;
+	}
+	fprintf(stdout, "\n");
+	ret = 0;
+
+exit_close_error:
+	if (close(fd) == -1)
+		perror("Failed to close GPIO character device file");
+	free(chrdev_name);
+	return ret;
+}
+
+void print_usage(void)
+{
+	fprintf(stderr, "Usage: gpio-hammer [options]...\n"
+		"Hammer GPIO lines, 0->1->0->1...\n"
+		"  -n <name>  Hammer GPIOs on a named device (must be stated)\n"
+		"  -o <n>     Offset[s] to hammer, at least one, several can be stated\n"
+		" [-c <n>]    Do <n> loops (optional, infinite loop if not stated)\n"
+		"  -?         This helptext\n"
+		"\n"
+		"Example:\n"
+		"gpio-hammer -n gpiochip0 -o 4\n"
+	);
+}
+
+int main(int argc, char **argv)
+{
+	const char *device_name = NULL;
+	unsigned int lines[GPIOHANDLES_MAX];
+	unsigned int loops = 0;
+	int nlines;
+	int c;
+	int i;
+
+	i = 0;
+	while ((c = getopt(argc, argv, "c:n:o:?")) != -1) {
+		switch (c) {
+		case 'c':
+			loops = strtoul(optarg, NULL, 10);
+			break;
+		case 'n':
+			device_name = optarg;
+			break;
+		case 'o':
+			lines[i] = strtoul(optarg, NULL, 10);
+			i++;
+			break;
+		case '?':
+			print_usage();
+			return -1;
+		}
+	}
+	nlines = i;
+
+	if (!device_name || !nlines) {
+		print_usage();
+		return -1;
+	}
+	return hammer_device(device_name, lines, nlines, loops);
+}
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 2457916a3943..d6cdece5e58b 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -1,4 +1,4 @@
-objtool-y += arch/$(ARCH)/
+objtool-y += arch/$(SRCARCH)/
 objtool-y += builtin-check.o
 objtool-y += elf.o
 objtool-y += special.o
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 1f75b0a046cc..0b437700f688 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -1,11 +1,9 @@
 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
-ifndef ($(ARCH))
-ARCH ?= $(shell uname -m)
 ifeq ($(ARCH),x86_64)
 ARCH := x86
 endif
-endif
 
 # always use the host compiler
 CC = gcc
@@ -26,7 +24,7 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi
 CFLAGS   += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
 
@@ -35,7 +33,7 @@ elfshdr := $(shell echo '\#include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | gre
 CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
 
 AWK = awk
-export srctree OUTPUT CFLAGS ARCH AWK
+export srctree OUTPUT CFLAGS SRCARCH AWK
 include $(srctree)/tools/build/Makefile.include
 
 $(OBJTOOL_IN): fixdep FORCE
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
index 3b491cfe204e..3918dd52e903 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
@@ -6,6 +6,1016 @@
 
 {{0x0f, 0x31, }, 2, 0, "", "",
 "0f 31                \trdtsc  ",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 81 78 56 34 12    \tbound  %eax,0x12345678(%ecx)",},
+{{0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 88 78 56 34 12    \tbound  %ecx,0x12345678(%eax)",},
+{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 90 78 56 34 12    \tbound  %edx,0x12345678(%eax)",},
+{{0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 98 78 56 34 12    \tbound  %ebx,0x12345678(%eax)",},
+{{0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 a0 78 56 34 12    \tbound  %esp,0x12345678(%eax)",},
+{{0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 a8 78 56 34 12    \tbound  %ebp,0x12345678(%eax)",},
+{{0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 b0 78 56 34 12    \tbound  %esi,0x12345678(%eax)",},
+{{0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 b8 78 56 34 12    \tbound  %edi,0x12345678(%eax)",},
+{{0x62, 0x08, }, 2, 0, "", "",
+"62 08                \tbound  %ecx,(%eax)",},
+{{0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 05 78 56 34 12    \tbound  %eax,0x12345678",},
+{{0x62, 0x14, 0x01, }, 3, 0, "", "",
+"62 14 01             \tbound  %edx,(%ecx,%eax,1)",},
+{{0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 14 05 78 56 34 12 \tbound  %edx,0x12345678(,%eax,1)",},
+{{0x62, 0x14, 0x08, }, 3, 0, "", "",
+"62 14 08             \tbound  %edx,(%eax,%ecx,1)",},
+{{0x62, 0x14, 0xc8, }, 3, 0, "", "",
+"62 14 c8             \tbound  %edx,(%eax,%ecx,8)",},
+{{0x62, 0x50, 0x12, }, 3, 0, "", "",
+"62 50 12             \tbound  %edx,0x12(%eax)",},
+{{0x62, 0x55, 0x12, }, 3, 0, "", "",
+"62 55 12             \tbound  %edx,0x12(%ebp)",},
+{{0x62, 0x54, 0x01, 0x12, }, 4, 0, "", "",
+"62 54 01 12          \tbound  %edx,0x12(%ecx,%eax,1)",},
+{{0x62, 0x54, 0x05, 0x12, }, 4, 0, "", "",
+"62 54 05 12          \tbound  %edx,0x12(%ebp,%eax,1)",},
+{{0x62, 0x54, 0x08, 0x12, }, 4, 0, "", "",
+"62 54 08 12          \tbound  %edx,0x12(%eax,%ecx,1)",},
+{{0x62, 0x54, 0xc8, 0x12, }, 4, 0, "", "",
+"62 54 c8 12          \tbound  %edx,0x12(%eax,%ecx,8)",},
+{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 90 78 56 34 12    \tbound  %edx,0x12345678(%eax)",},
+{{0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 95 78 56 34 12    \tbound  %edx,0x12345678(%ebp)",},
+{{0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 01 78 56 34 12 \tbound  %edx,0x12345678(%ecx,%eax,1)",},
+{{0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 05 78 56 34 12 \tbound  %edx,0x12345678(%ebp,%eax,1)",},
+{{0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 08 78 56 34 12 \tbound  %edx,0x12345678(%eax,%ecx,1)",},
+{{0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 c8 78 56 34 12 \tbound  %edx,0x12345678(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 81 78 56 34 12 \tbound  %ax,0x12345678(%ecx)",},
+{{0x66, 0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 88 78 56 34 12 \tbound  %cx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 90 78 56 34 12 \tbound  %dx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 98 78 56 34 12 \tbound  %bx,0x12345678(%eax)",},
+{{0x66, 0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 a0 78 56 34 12 \tbound  %sp,0x12345678(%eax)",},
+{{0x66, 0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 a8 78 56 34 12 \tbound  %bp,0x12345678(%eax)",},
+{{0x66, 0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 b0 78 56 34 12 \tbound  %si,0x12345678(%eax)",},
+{{0x66, 0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 b8 78 56 34 12 \tbound  %di,0x12345678(%eax)",},
+{{0x66, 0x62, 0x08, }, 3, 0, "", "",
+"66 62 08             \tbound  %cx,(%eax)",},
+{{0x66, 0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 05 78 56 34 12 \tbound  %ax,0x12345678",},
+{{0x66, 0x62, 0x14, 0x01, }, 4, 0, "", "",
+"66 62 14 01          \tbound  %dx,(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 14 05 78 56 34 12 \tbound  %dx,0x12345678(,%eax,1)",},
+{{0x66, 0x62, 0x14, 0x08, }, 4, 0, "", "",
+"66 62 14 08          \tbound  %dx,(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x14, 0xc8, }, 4, 0, "", "",
+"66 62 14 c8          \tbound  %dx,(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x50, 0x12, }, 4, 0, "", "",
+"66 62 50 12          \tbound  %dx,0x12(%eax)",},
+{{0x66, 0x62, 0x55, 0x12, }, 4, 0, "", "",
+"66 62 55 12          \tbound  %dx,0x12(%ebp)",},
+{{0x66, 0x62, 0x54, 0x01, 0x12, }, 5, 0, "", "",
+"66 62 54 01 12       \tbound  %dx,0x12(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x54, 0x05, 0x12, }, 5, 0, "", "",
+"66 62 54 05 12       \tbound  %dx,0x12(%ebp,%eax,1)",},
+{{0x66, 0x62, 0x54, 0x08, 0x12, }, 5, 0, "", "",
+"66 62 54 08 12       \tbound  %dx,0x12(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x54, 0xc8, 0x12, }, 5, 0, "", "",
+"66 62 54 c8 12       \tbound  %dx,0x12(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 90 78 56 34 12 \tbound  %dx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 95 78 56 34 12 \tbound  %dx,0x12345678(%ebp)",},
+{{0x66, 0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 01 78 56 34 12 \tbound  %dx,0x12345678(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 05 78 56 34 12 \tbound  %dx,0x12345678(%ebp,%eax,1)",},
+{{0x66, 0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 08 78 56 34 12 \tbound  %dx,0x12345678(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 c8 78 56 34 12 \tbound  %dx,0x12345678(%eax,%ecx,8)",},
+{{0x0f, 0x41, 0xd8, }, 3, 0, "", "",
+"0f 41 d8             \tcmovno %eax,%ebx",},
+{{0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%ecx",},
+{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%cx",},
+{{0x0f, 0x44, 0xd8, }, 3, 0, "", "",
+"0f 44 d8             \tcmove  %eax,%ebx",},
+{{0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 44 88 78 56 34 12 \tcmove  0x12345678(%eax),%ecx",},
+{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 44 88 78 56 34 12 \tcmove  0x12345678(%eax),%cx",},
+{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 90 80 78 56 34 12 \tseto   0x12345678(%eax)",},
+{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 91 80 78 56 34 12 \tsetno  0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 98 80 78 56 34 12 \tsets   0x12345678(%eax)",},
+{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 99 80 78 56 34 12 \tsetns  0x12345678(%eax)",},
+{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cc 41 ef          \tkandw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 41 ef       \tkandq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cd 41 ef          \tkandb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 41 ef       \tkandd  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cc 42 ef          \tkandnw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 42 ef       \tkandnq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cd 42 ef          \tkandnb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 42 ef       \tkandnd %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f8 44 f7          \tknotw  %k7,%k6",},
+{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f8 44 f7       \tknotq  %k7,%k6",},
+{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f9 44 f7          \tknotb  %k7,%k6",},
+{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f9 44 f7       \tknotd  %k7,%k6",},
+{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cc 45 ef          \tkorw   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 45 ef       \tkorq   %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cd 45 ef          \tkorb   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 45 ef       \tkord   %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cc 46 ef          \tkxnorw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 46 ef       \tkxnorq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cd 46 ef          \tkxnorb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 46 ef       \tkxnord %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cc 47 ef          \tkxorw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 47 ef       \tkxorq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cd 47 ef          \tkxorb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 47 ef       \tkxord  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cc 4a ef          \tkaddw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4a ef       \tkaddq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cd 4a ef          \tkaddb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 4a ef       \tkaddd  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cd 4b ef          \tkunpckbw %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cc 4b ef          \tkunpckwd %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4b ef       \tkunpckdq %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f8 90 ee          \tkmovw  %k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f8 90 29          \tkmovw  (%ecx),%k5",},
+{{0xc5, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f8 90 ac c8 23 01 00 00 \tkmovw  0x123(%eax,%ecx,8),%k5",},
+{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f8 91 29          \tkmovw  %k5,(%ecx)",},
+{{0xc5, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f8 91 ac c8 23 01 00 00 \tkmovw  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f8 92 e8          \tkmovw  %eax,%k5",},
+{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f8 92 ed          \tkmovw  %ebp,%k5",},
+{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f8 93 c5          \tkmovw  %k5,%eax",},
+{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f8 93 ed          \tkmovw  %k5,%ebp",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 90 ee       \tkmovq  %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 90 29       \tkmovq  (%ecx),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f8 90 ac c8 23 01 00 00 \tkmovq  0x123(%eax,%ecx,8),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 91 29       \tkmovq  %k5,(%ecx)",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f8 91 ac c8 23 01 00 00 \tkmovq  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f9 90 ee          \tkmovb  %k6,%k5",},
+{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f9 90 29          \tkmovb  (%ecx),%k5",},
+{{0xc5, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f9 90 ac c8 23 01 00 00 \tkmovb  0x123(%eax,%ecx,8),%k5",},
+{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f9 91 29          \tkmovb  %k5,(%ecx)",},
+{{0xc5, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f9 91 ac c8 23 01 00 00 \tkmovb  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f9 92 e8          \tkmovb  %eax,%k5",},
+{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f9 92 ed          \tkmovb  %ebp,%k5",},
+{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f9 93 c5          \tkmovb  %k5,%eax",},
+{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f9 93 ed          \tkmovb  %k5,%ebp",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 90 ee       \tkmovd  %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 90 29       \tkmovd  (%ecx),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f9 90 ac c8 23 01 00 00 \tkmovd  0x123(%eax,%ecx,8),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 91 29       \tkmovd  %k5,(%ecx)",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f9 91 ac c8 23 01 00 00 \tkmovd  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 fb 92 e8          \tkmovd  %eax,%k5",},
+{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "",
+"c5 fb 92 ed          \tkmovd  %ebp,%k5",},
+{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 fb 93 c5          \tkmovd  %k5,%eax",},
+{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "",
+"c5 fb 93 ed          \tkmovd  %k5,%ebp",},
+{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f8 98 ee          \tkortestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 98 ee       \tkortestq %k6,%k5",},
+{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f9 98 ee          \tkortestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 98 ee       \tkortestd %k6,%k5",},
+{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f8 99 ee          \tktestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 99 ee       \tktestq %k6,%k5",},
+{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f9 99 ee          \tktestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 99 ee       \tktestd %k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 30 ee 12    \tkshiftrw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 31 ee 5b    \tkshiftrq $0x5b,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 32 ee 12    \tkshiftlw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 33 ee 5b    \tkshiftlq $0x5b,%k6,%k5",},
+{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f8 5b f5          \tvcvtdq2ps %xmm5,%xmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 5b f5    \tvcvtqq2ps %zmm5,%ymm6{%k7}",},
+{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f9 5b f5          \tvcvtps2dq %xmm5,%xmm6",},
+{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 fa 5b f5          \tvcvttps2dq %xmm5,%xmm6",},
+{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "",
+"0f 6f e0             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fd 6f f4          \tvmovdqa %ymm4,%ymm6",},
+{{0x62, 0xf1, 0x7d, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 48 6f f5    \tvmovdqa32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 6f f5    \tvmovdqa64 %zmm5,%zmm6",},
+{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fe 6f f4          \tvmovdqu %ymm4,%ymm6",},
+{{0x62, 0xf1, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 48 6f f5    \tvmovdqu32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 6f f5    \tvmovdqu64 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7f 48 6f f5    \tvmovdqu8 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 ff 48 6f f5    \tvmovdqu16 %zmm5,%zmm6",},
+{{0x0f, 0x78, 0xc3, }, 3, 0, "", "",
+"0f 78 c3             \tvmread %eax,%ebx",},
+{{0x62, 0xf1, 0x7c, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 7c 48 78 f5    \tvcvttps2udq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 78 f5    \tvcvttpd2udq %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7f, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 7f 08 78 c6    \tvcvttsd2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7e, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 7e 08 78 c6    \tvcvttss2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 78 f5    \tvcvttps2uqq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 78 f5    \tvcvttpd2uqq %zmm5,%zmm6",},
+{{0x0f, 0x79, 0xd8, }, 3, 0, "", "",
+"0f 79 d8             \tvmwrite %eax,%ebx",},
+{{0x62, 0xf1, 0x7c, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 7c 48 79 f5    \tvcvtps2udq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 79 f5    \tvcvtpd2udq %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7f, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 7f 08 79 c6    \tvcvtsd2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7e, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 7e 08 79 c6    \tvcvtss2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 79 f5    \tvcvtps2uqq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 79 f5    \tvcvtpd2uqq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7e, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 4f 7a f5    \tvcvtudq2pd %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 7a f5    \tvcvtuqq2pd %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7f 48 7a f5    \tvcvtudq2ps %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 ff 4f 7a f5    \tvcvtuqq2ps %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 7a f5    \tvcvttps2qq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 7a f5    \tvcvttpd2qq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 57 08 7b f0    \tvcvtusi2sd %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 56 08 7b f0    \tvcvtusi2ss %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 7b f5    \tvcvtps2qq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 7b f5    \tvcvtpd2qq %zmm5,%zmm6",},
+{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "",
+"0f 7f c4             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x7f, 0xee, }, 4, 0, "", "",
+"c5 fd 7f ee          \tvmovdqa %ymm5,%ymm6",},
+{{0x62, 0xf1, 0x7d, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7d 48 7f ee    \tvmovdqa32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 fd 48 7f ee    \tvmovdqa64 %zmm5,%zmm6",},
+{{0xc5, 0xfe, 0x7f, 0xee, }, 4, 0, "", "",
+"c5 fe 7f ee          \tvmovdqu %ymm5,%ymm6",},
+{{0x62, 0xf1, 0x7e, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7e 48 7f ee    \tvmovdqu32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 fe 48 7f ee    \tvmovdqu64 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7f 48 7f ee    \tvmovdqu8 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 ff 48 7f ee    \tvmovdqu16 %zmm5,%zmm6",},
+{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "",
+"0f db d1             \tpand   %mm1,%mm2",},
+{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "",
+"66 0f db d1          \tpand   %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "",
+"c5 cd db d4          \tvpand  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xdb, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 db f4    \tvpandd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xdb, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 db f4    \tvpandq %zmm4,%zmm5,%zmm6",},
+{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "",
+"0f df d1             \tpandn  %mm1,%mm2",},
+{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "",
+"66 0f df d1          \tpandn  %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "",
+"c5 cd df d4          \tvpandn %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xdf, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 df f4    \tvpandnd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xdf, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 df f4    \tvpandnq %zmm4,%zmm5,%zmm6",},
+{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 f9 e6 d1          \tvcvttpd2dq %xmm1,%xmm2",},
+{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "",
+"c5 fa e6 f5          \tvcvtdq2pd %xmm5,%xmm6",},
+{{0x62, 0xf1, 0x7e, 0x4f, 0xe6, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 4f e6 f5    \tvcvtdq2pd %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfe, 0x48, 0xe6, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 e6 f5    \tvcvtqq2pd %zmm5,%zmm6",},
+{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 fb e6 d1          \tvcvtpd2dq %xmm1,%xmm2",},
+{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "",
+"0f eb f4             \tpor    %mm4,%mm6",},
+{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "",
+"c5 cd eb d4          \tvpor   %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xeb, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 eb f4    \tvpord  %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xeb, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 eb f4    \tvporq  %zmm4,%zmm5,%zmm6",},
+{{0x0f, 0xef, 0xf4, }, 3, 0, "", "",
+"0f ef f4             \tpxor   %mm4,%mm6",},
+{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "",
+"c5 cd ef d4          \tvpxor  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xef, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 ef f4    \tvpxord %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xef, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 ef f4    \tvpxorq %zmm4,%zmm5,%zmm6",},
+{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "",
+"66 0f 38 10 c1       \tpblendvb %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x10, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 10 f4    \tvpsrlvw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x10, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 10 ee    \tvpmovuswb %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x11, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 11 ee    \tvpmovusdb %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x11, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 11 f4    \tvpsravw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x12, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 12 ee    \tvpmovusqb %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x12, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 12 f4    \tvpsllvw %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0xf2, 0x7d, 0x4f, 0x13, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 4f 13 f5    \tvcvtph2ps %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x13, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 13 ee    \tvpmovusdw %zmm5,%ymm6{%k7}",},
+{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "",
+"66 0f 38 14 c1       \tblendvps %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x14, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 14 ee    \tvpmovusqw %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0x55, 0x48, 0x14, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 14 f4    \tvprorvd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x14, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 14 f4    \tvprorvq %zmm4,%zmm5,%zmm6",},
+{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "",
+"66 0f 38 15 c1       \tblendvpd %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x15, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 15 ee    \tvpmovusqd %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x55, 0x48, 0x15, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 15 f4    \tvprolvd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x15, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 15 f4    \tvprolvq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 16 d4       \tvpermps %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x4d, 0x2f, 0x16, 0xd4, }, 6, 0, "", "",
+"62 f2 4d 2f 16 d4    \tvpermps %ymm4,%ymm6,%ymm2{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x2f, 0x16, 0xd4, }, 6, 0, "", "",
+"62 f2 cd 2f 16 d4    \tvpermpd %ymm4,%ymm6,%ymm2{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 19 f4       \tvbroadcastsd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x19, 0xf7, }, 6, 0, "", "",
+"62 f2 7d 48 19 f7    \tvbroadcastf32x2 %xmm7,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 1a 21       \tvbroadcastf128 (%ecx),%ymm4",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x1a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 1a 31    \tvbroadcastf32x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 1a 31    \tvbroadcastf64x2 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x1b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 1b 31    \tvbroadcastf32x8 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 1b 31    \tvbroadcastf64x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1f, 0xf4, }, 6, 0, "", "",
+"62 f2 fd 48 1f f4    \tvpabsq %zmm4,%zmm6",},
+{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "",
+"c4 e2 79 20 ec       \tvpmovsxbw %xmm4,%xmm5",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x20, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 20 ee    \tvpmovswb %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 21 f4       \tvpmovsxbd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x21, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 21 ee    \tvpmovsdb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 22 e4       \tvpmovsxbq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x22, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 22 ee    \tvpmovsqb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 23 e4       \tvpmovsxwd %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x23, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 23 ee    \tvpmovsdw %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 24 f4       \tvpmovsxwq %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x24, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 24 ee    \tvpmovsqw %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 25 e4       \tvpmovsxdq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x25, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 25 ee    \tvpmovsqd %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x4d, 0x48, 0x26, 0xed, }, 6, 0, "", "",
+"62 f2 4d 48 26 ed    \tvptestmb %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0xcd, 0x48, 0x26, 0xed, }, 6, 0, "", "",
+"62 f2 cd 48 26 ed    \tvptestmw %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0x56, 0x48, 0x26, 0xec, }, 6, 0, "", "",
+"62 f2 56 48 26 ec    \tvptestnmb %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0xd6, 0x48, 0x26, 0xec, }, 6, 0, "", "",
+"62 f2 d6 48 26 ec    \tvptestnmw %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0x4d, 0x48, 0x27, 0xed, }, 6, 0, "", "",
+"62 f2 4d 48 27 ed    \tvptestmd %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0xcd, 0x48, 0x27, 0xed, }, 6, 0, "", "",
+"62 f2 cd 48 27 ed    \tvptestmq %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0x56, 0x48, 0x27, 0xec, }, 6, 0, "", "",
+"62 f2 56 48 27 ec    \tvptestnmd %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0xd6, 0x48, 0x27, 0xec, }, 6, 0, "", "",
+"62 f2 d6 48 27 ec    \tvptestnmq %zmm4,%zmm5,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 28 d4       \tvpmuldq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x28, 0xf5, }, 6, 0, "", "",
+"62 f2 7e 48 28 f5    \tvpmovm2b %k5,%zmm6",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x28, 0xf5, }, 6, 0, "", "",
+"62 f2 fe 48 28 f5    \tvpmovm2w %k5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 29 d4       \tvpcmpeqq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x29, 0xee, }, 6, 0, "", "",
+"62 f2 7e 48 29 ee    \tvpmovb2m %zmm6,%k5",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x29, 0xee, }, 6, 0, "", "",
+"62 f2 fe 48 29 ee    \tvpmovw2m %zmm6,%k5",},
+{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 2a 21       \tvmovntdqa (%ecx),%ymm4",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x2a, 0xce, }, 6, 0, "", "",
+"62 f2 fe 48 2a ce    \tvpbroadcastmb2q %k6,%zmm1",},
+{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2c 31       \tvmaskmovps (%ecx),%ymm4,%ymm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x2c, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 2c f4    \tvscalefps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x2c, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 2c f4    \tvscalefpd %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2d 31       \tvmaskmovpd (%ecx),%ymm4,%ymm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 2d f4    \tvscalefss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 2d f4    \tvscalefsd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 30 e4       \tvpmovzxbw %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x30, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 30 ee    \tvpmovwb %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 31 f4       \tvpmovzxbd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x31, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 31 ee    \tvpmovdb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 32 e4       \tvpmovzxbq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x32, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 32 ee    \tvpmovqb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 33 e4       \tvpmovzxwd %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x33, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 33 ee    \tvpmovdw %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 34 f4       \tvpmovzxwq %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x34, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 34 ee    \tvpmovqw %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 35 e4       \tvpmovzxdq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x35, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 35 ee    \tvpmovqd %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 36 d4       \tvpermd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x4d, 0x2f, 0x36, 0xd4, }, 6, 0, "", "",
+"62 f2 4d 2f 36 d4    \tvpermd %ymm4,%ymm6,%ymm2{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x2f, 0x36, 0xd4, }, 6, 0, "", "",
+"62 f2 cd 2f 36 d4    \tvpermq %ymm4,%ymm6,%ymm2{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 38 d4       \tvpminsb %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x38, 0xf5, }, 6, 0, "", "",
+"62 f2 7e 48 38 f5    \tvpmovm2d %k5,%zmm6",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x38, 0xf5, }, 6, 0, "", "",
+"62 f2 fe 48 38 f5    \tvpmovm2q %k5,%zmm6",},
+{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "",
+"c4 e2 69 39 d9       \tvpminsd %xmm1,%xmm2,%xmm3",},
+{{0x62, 0xf2, 0x55, 0x48, 0x39, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 39 f4    \tvpminsd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x39, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 39 f4    \tvpminsq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x39, 0xee, }, 6, 0, "", "",
+"62 f2 7e 48 39 ee    \tvpmovd2m %zmm6,%k5",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x39, 0xee, }, 6, 0, "", "",
+"62 f2 fe 48 39 ee    \tvpmovq2m %zmm6,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3a d4       \tvpminuw %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x3a, 0xf6, }, 6, 0, "", "",
+"62 f2 7e 48 3a f6    \tvpbroadcastmw2d %k6,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3b d4       \tvpminud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3b, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3b f4    \tvpminud %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3b, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3b f4    \tvpminuq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3d d4       \tvpmaxsd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3d f4    \tvpmaxsd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3d f4    \tvpmaxsq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3f d4       \tvpmaxud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3f f4    \tvpmaxud %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3f f4    \tvpmaxuq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 40 d4       \tvpmulld %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x40, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 40 f4    \tvpmulld %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x40, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 40 f4    \tvpmullq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x42, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 42 f5    \tvgetexpps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x42, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 42 f5    \tvgetexppd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x43, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 43 f4    \tvgetexpss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xe5, 0x0f, 0x43, 0xe2, }, 6, 0, "", "",
+"62 f2 e5 0f 43 e2    \tvgetexpsd %xmm2,%xmm3,%xmm4{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x44, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 44 f5    \tvplzcntd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x44, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 44 f5    \tvplzcntq %zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 46 d4       \tvpsravd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x46, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 46 f4    \tvpsravd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x46, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 46 f4    \tvpsravq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x4c, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 4c f5    \tvrcp14ps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x4c, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 4c f5    \tvrcp14pd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 4d f4    \tvrcp14ss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 4d f4    \tvrcp14sd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x4e, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 4e f5    \tvrsqrt14ps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x4e, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 4e f5    \tvrsqrt14pd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 4f f4    \tvrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 4f f4    \tvrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "",
+"c4 e2 79 59 f4       \tvpbroadcastq %xmm4,%xmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x59, 0xf7, }, 6, 0, "", "",
+"62 f2 7d 48 59 f7    \tvbroadcasti32x2 %xmm7,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 5a 21       \tvbroadcasti128 (%ecx),%ymm4",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x5a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 5a 31    \tvbroadcasti32x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x5a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 5a 31    \tvbroadcasti64x2 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x5b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 5b 31    \tvbroadcasti32x8 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x5b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 5b 31    \tvbroadcasti64x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x64, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 64 f4    \tvpblendmd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x64, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 64 f4    \tvpblendmq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x65, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 65 f4    \tvblendmps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x65, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 65 f4    \tvblendmpd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x66, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 66 f4    \tvpblendmb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x66, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 66 f4    \tvpblendmw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x75, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 75 f4    \tvpermi2b %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x75, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 75 f4    \tvpermi2w %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x76, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 76 f4    \tvpermi2d %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x76, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 76 f4    \tvpermi2q %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x77, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 77 f4    \tvpermi2ps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x77, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 77 f4    \tvpermi2pd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7a, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7a d8    \tvpbroadcastb %eax,%xmm3",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7b, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7b d8    \tvpbroadcastw %eax,%xmm3",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7c, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7c d8    \tvpbroadcastd %eax,%xmm3",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7d f4    \tvpermt2b %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7d f4    \tvpermt2w %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7e, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7e f4    \tvpermt2d %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7e, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7e f4    \tvpermt2q %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7f f4    \tvpermt2ps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7f f4    \tvpermt2pd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x83, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 83 f4    \tvpmultishiftqb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x88, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 88 31    \tvexpandps (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x88, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 88 31    \tvexpandpd (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x89, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 89 31    \tvpexpandd (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x89, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 89 31    \tvpexpandq (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x8a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 8a 31    \tvcompressps %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x8a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 8a 31    \tvcompresspd %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x8b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 8b 31    \tvpcompressd %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x8b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 8b 31    \tvpcompressq %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0x55, 0x48, 0x8d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 8d f4    \tvpermb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x8d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 8d f4    \tvpermw %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "",
+"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%ebp,%xmm7,2),%xmm1",},
+{{0x62, 0xf2, 0x7d, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 90 b4 fd 7b 00 00 00 \tvpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 90 b4 fd 7b 00 00 00 \tvpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}",},
+{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0x62, 0xf2, 0x7d, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 91 b4 fd 7b 00 00 00 \tvpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 91 b4 fd 7b 00 00 00 \tvpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a0 b4 fd 7b 00 00 00 \tvpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a0 b4 fd 7b 00 00 00 \tvpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a1 b4 fd 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x29, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 29 a1 b4 fd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a2 b4 fd 7b 00 00 00 \tvscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a2 b4 fd 7b 00 00 00 \tvscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a3 b4 fd 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a3 b4 fd 7b 00 00 00 \tvscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0xb4, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 b4 f4    \tvpmadd52luq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0xb5, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 b5 f4    \tvpmadd52huq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xc4, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 c4 f5    \tvpconflictd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xc4, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 c4 f5    \tvpconflictq %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xc8, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 c8 fe    \tvexp2ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xc8, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 c8 fe    \tvexp2pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xca, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 ca fe    \tvrcp28ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xca, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 ca fe    \tvrcp28pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x4d, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "",
+"62 f2 4d 0f cb fd    \tvrcp28ss %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "",
+"62 f2 cd 0f cb fd    \tvrcp28sd %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xcc, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 cc fe    \tvrsqrt28ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xcc, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 cc fe    \tvrsqrt28pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x4d, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "",
+"62 f2 4d 0f cd fd    \tvrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "",
+"62 f2 cd 0f cd fd    \tvrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 03 fd 12 \tvalignd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 03 fd 12 \tvalignq $0x12,%zmm5,%zmm6,%zmm7",},
+{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 08 d6 05    \tvroundps $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x08, 0xf5, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 08 f5 12 \tvrndscaleps $0x12,%zmm5,%zmm6",},
+{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 09 d6 05    \tvroundpd $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x09, 0xf5, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 09 f5 12 \tvrndscalepd $0x12,%zmm5,%zmm6",},
+{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0a d4 05    \tvroundss $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0xf3, 0x55, 0x0f, 0x0a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 0f 0a f4 12 \tvrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0b d4 05    \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0xf3, 0xd5, 0x0f, 0x0b, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 0f 0b f4 12 \tvrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 18 f4 05    \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0xf3, 0x55, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 4f 18 f4 12 \tvinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf3, 0xd5, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 4f 18 f4 12 \tvinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 19 e4 05    \tvextractf128 $0x5,%ymm4,%xmm4",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 19 ee 12 \tvextractf32x4 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 19 ee 12 \tvextractf64x2 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 4f 1a fd 12 \tvinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 4f 1a fd 12 \tvinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 1b f7 12 \tvextractf32x8 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 1b f7 12 \tvextractf64x4 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0x45, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 1e ee 12 \tvpcmpud $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 1e ee 12 \tvpcmpuq $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x45, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 1f ee 12 \tvpcmpd $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 1f ee 12 \tvpcmpq $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 23 fd 12 \tvshuff32x4 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 23 fd 12 \tvshuff64x2 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 25 fd 12 \tvpternlogd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 25 fd 12 \tvpternlogq $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 26 fe 12 \tvgetmantps $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 26 fe 12 \tvgetmantpd $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 0f 27 fd 12 \tvgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 0f 27 fd 12 \tvgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 38 f4 05    \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0xf3, 0x55, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 4f 38 f4 12 \tvinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf3, 0xd5, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 4f 38 f4 12 \tvinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 39 e6 05    \tvextracti128 $0x5,%ymm4,%xmm6",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 39 ee 12 \tvextracti32x4 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 39 ee 12 \tvextracti64x2 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 4f 3a fd 12 \tvinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 4f 3a fd 12 \tvinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 3b f7 12 \tvextracti32x8 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 3b f7 12 \tvextracti64x4 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0x45, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 3e ee 12 \tvpcmpub $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 3e ee 12 \tvpcmpuw $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x45, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 3f ee 12 \tvpcmpb $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 3f ee 12 \tvpcmpw $0x12,%zmm6,%zmm7,%k5",},
+{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 4d 42 d4 05    \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 43 fd 12 \tvshufi32x4 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 43 fd 12 \tvshufi64x2 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 50 fd 12 \tvrangeps $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 50 fd 12 \tvrangepd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 08 51 fd 12 \tvrangess $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0xcd, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 08 51 fd 12 \tvrangesd $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 54 fd 12 \tvfixupimmps $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 54 fd 12 \tvfixupimmpd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 0f 55 fd 12 \tvfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 0f 55 fd 12 \tvfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 56 fe 12 \tvreduceps $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 56 fe 12 \tvreducepd $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 08 57 fd 12 \tvreducess $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0xcd, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 08 57 fd 12 \tvreducesd $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 66 ef 12 \tvfpclassps $0x12,%zmm7,%k5",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 66 ef 12 \tvfpclasspd $0x12,%zmm7,%k5",},
+{{0x62, 0xf3, 0x7d, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 7d 08 67 ef 12 \tvfpclassss $0x12,%xmm7,%k5",},
+{{0x62, 0xf3, 0xfd, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 fd 08 67 ef 12 \tvfpclasssd $0x12,%xmm7,%k5",},
+{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "",
+"62 f1 4d 48 72 c5 12 \tvprord $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "",
+"62 f1 cd 48 72 c5 12 \tvprorq $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 f1 4d 48 72 cd 12 \tvprold $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 f1 cd 48 72 cd 12 \tvprolq $0x12,%zmm5,%zmm6",},
+{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "",
+"0f 72 e6 02          \tpsrad  $0x2,%mm6",},
+{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "",
+"c5 ed 72 e6 05       \tvpsrad $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x6d, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "",
+"62 f1 6d 48 72 e6 05 \tvpsrad $0x5,%zmm6,%zmm2",},
+{{0x62, 0xf1, 0xed, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "",
+"62 f1 ed 48 72 e6 05 \tvpsraq $0x5,%zmm6,%zmm2",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x4f, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 4f 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xd5, 0xcf, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 cf 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6{%k7}{z}",},
+{{0x62, 0xf1, 0xd5, 0x18, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 18 58 f4    \tvaddpd {rn-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 58 58 f4    \tvaddpd {ru-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x38, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 38 58 f4    \tvaddpd {rd-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x78, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 78 58 f4    \tvaddpd {rz-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x31, }, 6, 0, "", "",
+"62 f1 d5 48 58 31    \tvaddpd (%ecx),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xb4, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "",
+"62 f1 d5 48 58 b4 c8 23 01 00 00 \tvaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x31, }, 6, 0, "", "",
+"62 f1 d5 58 58 31    \tvaddpd (%ecx){1to8},%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 f1 d5 48 58 72 7f \tvaddpd 0x1fc0(%edx),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 f1 d5 58 58 72 7f \tvaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6",},
+{{0x62, 0xf1, 0x4c, 0x58, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "",
+"62 f1 4c 58 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5",},
+{{0x62, 0xf1, 0xe7, 0x0f, 0xc2, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "",
+"62 f1 e7 0f c2 ac c8 23 01 00 00 01 \tvcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}",},
+{{0x62, 0xf1, 0xd7, 0x1f, 0xc2, 0xec, 0x02, }, 7, 0, "", "",
+"62 f1 d7 1f c2 ec 02 \tvcmplesd {sae},%xmm4,%xmm5,%k5{%k7}",},
+{{0x62, 0xf3, 0x5d, 0x0f, 0x27, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "",
+"62 f3 5d 0f 27 ac c8 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}",},
 {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "",
 "f3 0f 1b 00          \tbndmk  (%eax),%bnd0",},
 {{0xf3, 0x0f, 0x1b, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
@@ -309,19 +1319,19 @@
 {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
 "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%eax,%ecx,1)",},
 {{0xf2, 0xe8, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "call", "unconditional",
-"f2 e8 fc ff ff ff    \tbnd call 3c3 <main+0x3c3>",},
+"f2 e8 fc ff ff ff    \tbnd call fce <main+0xfce>",},
 {{0xf2, 0xff, 0x10, }, 3, 0, "call", "indirect",
 "f2 ff 10             \tbnd call *(%eax)",},
 {{0xf2, 0xc3, }, 2, 0, "ret", "indirect",
 "f2 c3                \tbnd ret ",},
 {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional",
-"f2 e9 fc ff ff ff    \tbnd jmp 3ce <main+0x3ce>",},
+"f2 e9 fc ff ff ff    \tbnd jmp fd9 <main+0xfd9>",},
 {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional",
-"f2 e9 fc ff ff ff    \tbnd jmp 3d4 <main+0x3d4>",},
+"f2 e9 fc ff ff ff    \tbnd jmp fdf <main+0xfdf>",},
 {{0xf2, 0xff, 0x21, }, 3, 0, "jmp", "indirect",
 "f2 ff 21             \tbnd jmp *(%ecx)",},
 {{0xf2, 0x0f, 0x85, 0xfc, 0xff, 0xff, 0xff, }, 7, 0xfffffffc, "jcc", "conditional",
-"f2 0f 85 fc ff ff ff \tbnd jne 3de <main+0x3de>",},
+"f2 0f 85 fc ff ff ff \tbnd jne fe9 <main+0xfe9>",},
 {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
 "0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
 {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
index 4fe7cce179c4..9c8c61e06d5a 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -6,6 +6,938 @@
 
 {{0x0f, 0x31, }, 2, 0, "", "",
 "0f 31                \trdtsc  ",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x48, 0x0f, 0x41, 0xd8, }, 4, 0, "", "",
+"48 0f 41 d8          \tcmovno %rax,%rbx",},
+{{0x48, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"48 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%rcx",},
+{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%cx",},
+{{0x48, 0x0f, 0x44, 0xd8, }, 4, 0, "", "",
+"48 0f 44 d8          \tcmove  %rax,%rbx",},
+{{0x48, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"48 0f 44 88 78 56 34 12 \tcmove  0x12345678(%rax),%rcx",},
+{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 44 88 78 56 34 12 \tcmove  0x12345678(%rax),%cx",},
+{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 90 80 78 56 34 12 \tseto   0x12345678(%rax)",},
+{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 91 80 78 56 34 12 \tsetno  0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 98 80 78 56 34 12 \tsets   0x12345678(%rax)",},
+{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 99 80 78 56 34 12 \tsetns  0x12345678(%rax)",},
+{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cc 41 ef          \tkandw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 41 ef       \tkandq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cd 41 ef          \tkandb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 41 ef       \tkandd  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cc 42 ef          \tkandnw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 42 ef       \tkandnq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cd 42 ef          \tkandnb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 42 ef       \tkandnd %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f8 44 f7          \tknotw  %k7,%k6",},
+{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f8 44 f7       \tknotq  %k7,%k6",},
+{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f9 44 f7          \tknotb  %k7,%k6",},
+{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f9 44 f7       \tknotd  %k7,%k6",},
+{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cc 45 ef          \tkorw   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 45 ef       \tkorq   %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cd 45 ef          \tkorb   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 45 ef       \tkord   %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cc 46 ef          \tkxnorw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 46 ef       \tkxnorq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cd 46 ef          \tkxnorb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 46 ef       \tkxnord %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cc 47 ef          \tkxorw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 47 ef       \tkxorq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cd 47 ef          \tkxorb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 47 ef       \tkxord  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cc 4a ef          \tkaddw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4a ef       \tkaddq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cd 4a ef          \tkaddb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 4a ef       \tkaddd  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cd 4b ef          \tkunpckbw %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cc 4b ef          \tkunpckwd %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4b ef       \tkunpckdq %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f8 90 ee          \tkmovw  %k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f8 90 29          \tkmovw  (%rcx),%k5",},
+{{0xc4, 0xa1, 0x78, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 78 90 ac f0 23 01 00 00 \tkmovw  0x123(%rax,%r14,8),%k5",},
+{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f8 91 29          \tkmovw  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0x78, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 78 91 ac f0 23 01 00 00 \tkmovw  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f8 92 e8          \tkmovw  %eax,%k5",},
+{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f8 92 ed          \tkmovw  %ebp,%k5",},
+{{0xc4, 0xc1, 0x78, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 78 92 ed       \tkmovw  %r13d,%k5",},
+{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f8 93 c5          \tkmovw  %k5,%eax",},
+{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f8 93 ed          \tkmovw  %k5,%ebp",},
+{{0xc5, 0x78, 0x93, 0xed, }, 4, 0, "", "",
+"c5 78 93 ed          \tkmovw  %k5,%r13d",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 90 ee       \tkmovq  %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 90 29       \tkmovq  (%rcx),%k5",},
+{{0xc4, 0xa1, 0xf8, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f8 90 ac f0 23 01 00 00 \tkmovq  0x123(%rax,%r14,8),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 91 29       \tkmovq  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0xf8, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f8 91 ac f0 23 01 00 00 \tkmovq  %k5,0x123(%rax,%r14,8)",},
+{{0xc4, 0xe1, 0xfb, 0x92, 0xe8, }, 5, 0, "", "",
+"c4 e1 fb 92 e8       \tkmovq  %rax,%k5",},
+{{0xc4, 0xe1, 0xfb, 0x92, 0xed, }, 5, 0, "", "",
+"c4 e1 fb 92 ed       \tkmovq  %rbp,%k5",},
+{{0xc4, 0xc1, 0xfb, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 fb 92 ed       \tkmovq  %r13,%k5",},
+{{0xc4, 0xe1, 0xfb, 0x93, 0xc5, }, 5, 0, "", "",
+"c4 e1 fb 93 c5       \tkmovq  %k5,%rax",},
+{{0xc4, 0xe1, 0xfb, 0x93, 0xed, }, 5, 0, "", "",
+"c4 e1 fb 93 ed       \tkmovq  %k5,%rbp",},
+{{0xc4, 0x61, 0xfb, 0x93, 0xed, }, 5, 0, "", "",
+"c4 61 fb 93 ed       \tkmovq  %k5,%r13",},
+{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f9 90 ee          \tkmovb  %k6,%k5",},
+{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f9 90 29          \tkmovb  (%rcx),%k5",},
+{{0xc4, 0xa1, 0x79, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 79 90 ac f0 23 01 00 00 \tkmovb  0x123(%rax,%r14,8),%k5",},
+{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f9 91 29          \tkmovb  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0x79, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 79 91 ac f0 23 01 00 00 \tkmovb  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f9 92 e8          \tkmovb  %eax,%k5",},
+{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f9 92 ed          \tkmovb  %ebp,%k5",},
+{{0xc4, 0xc1, 0x79, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 79 92 ed       \tkmovb  %r13d,%k5",},
+{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f9 93 c5          \tkmovb  %k5,%eax",},
+{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f9 93 ed          \tkmovb  %k5,%ebp",},
+{{0xc5, 0x79, 0x93, 0xed, }, 4, 0, "", "",
+"c5 79 93 ed          \tkmovb  %k5,%r13d",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 90 ee       \tkmovd  %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 90 29       \tkmovd  (%rcx),%k5",},
+{{0xc4, 0xa1, 0xf9, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f9 90 ac f0 23 01 00 00 \tkmovd  0x123(%rax,%r14,8),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 91 29       \tkmovd  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0xf9, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f9 91 ac f0 23 01 00 00 \tkmovd  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 fb 92 e8          \tkmovd  %eax,%k5",},
+{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "",
+"c5 fb 92 ed          \tkmovd  %ebp,%k5",},
+{{0xc4, 0xc1, 0x7b, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 7b 92 ed       \tkmovd  %r13d,%k5",},
+{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 fb 93 c5          \tkmovd  %k5,%eax",},
+{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "",
+"c5 fb 93 ed          \tkmovd  %k5,%ebp",},
+{{0xc5, 0x7b, 0x93, 0xed, }, 4, 0, "", "",
+"c5 7b 93 ed          \tkmovd  %k5,%r13d",},
+{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f8 98 ee          \tkortestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 98 ee       \tkortestq %k6,%k5",},
+{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f9 98 ee          \tkortestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 98 ee       \tkortestd %k6,%k5",},
+{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f8 99 ee          \tktestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 99 ee       \tktestq %k6,%k5",},
+{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f9 99 ee          \tktestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 99 ee       \tktestd %k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 30 ee 12    \tkshiftrw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 31 ee 5b    \tkshiftrq $0x5b,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 32 ee 12    \tkshiftlw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 33 ee 5b    \tkshiftlq $0x5b,%k6,%k5",},
+{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f8 5b f5          \tvcvtdq2ps %xmm5,%xmm6",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 5b f5    \tvcvtqq2ps %zmm29,%ymm6{%k7}",},
+{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f9 5b f5          \tvcvtps2dq %xmm5,%xmm6",},
+{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 fa 5b f5          \tvcvttps2dq %xmm5,%xmm6",},
+{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "",
+"0f 6f e0             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fd 6f f4          \tvmovdqa %ymm4,%ymm6",},
+{{0x62, 0x01, 0x7d, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 7d 48 6f d1    \tvmovdqa32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfd, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 fd 48 6f d1    \tvmovdqa64 %zmm25,%zmm26",},
+{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fe 6f f4          \tvmovdqu %ymm4,%ymm6",},
+{{0x62, 0x01, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 01 7e 48 6f f5    \tvmovdqu32 %zmm29,%zmm30",},
+{{0x62, 0x01, 0xfe, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 6f d1    \tvmovdqu64 %zmm25,%zmm26",},
+{{0x62, 0x01, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 01 7f 48 6f f5    \tvmovdqu8 %zmm29,%zmm30",},
+{{0x62, 0x01, 0xff, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 ff 48 6f d1    \tvmovdqu16 %zmm25,%zmm26",},
+{{0x0f, 0x78, 0xc3, }, 3, 0, "", "",
+"0f 78 c3             \tvmread %rax,%rbx",},
+{{0x62, 0x01, 0x7c, 0x48, 0x78, 0xd1, }, 6, 0, "", "",
+"62 01 7c 48 78 d1    \tvcvttps2udq %zmm25,%zmm26",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 78 f5    \tvcvttpd2udq %zmm29,%ymm6{%k7}",},
+{{0x62, 0xf1, 0xff, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 ff 08 78 c6    \tvcvttsd2usi %xmm6,%rax",},
+{{0x62, 0xf1, 0xfe, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 fe 08 78 c6    \tvcvttss2usi %xmm6,%rax",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x78, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 78 d5    \tvcvttps2uqq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 78 f5    \tvcvttpd2uqq %zmm29,%zmm30",},
+{{0x0f, 0x79, 0xd8, }, 3, 0, "", "",
+"0f 79 d8             \tvmwrite %rax,%rbx",},
+{{0x62, 0x01, 0x7c, 0x48, 0x79, 0xd1, }, 6, 0, "", "",
+"62 01 7c 48 79 d1    \tvcvtps2udq %zmm25,%zmm26",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 79 f5    \tvcvtpd2udq %zmm29,%ymm6{%k7}",},
+{{0x62, 0xf1, 0xff, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 ff 08 79 c6    \tvcvtsd2usi %xmm6,%rax",},
+{{0x62, 0xf1, 0xfe, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 fe 08 79 c6    \tvcvtss2usi %xmm6,%rax",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x79, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 79 d5    \tvcvtps2uqq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 79 f5    \tvcvtpd2uqq %zmm29,%zmm30",},
+{{0x62, 0x61, 0x7e, 0x4f, 0x7a, 0xed, }, 6, 0, "", "",
+"62 61 7e 4f 7a ed    \tvcvtudq2pd %ymm5,%zmm29{%k7}",},
+{{0x62, 0x01, 0xfe, 0x48, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 7a d1    \tvcvtuqq2pd %zmm25,%zmm26",},
+{{0x62, 0x01, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 01 7f 48 7a f5    \tvcvtudq2ps %zmm29,%zmm30",},
+{{0x62, 0x01, 0xff, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 ff 4f 7a d1    \tvcvtuqq2ps %zmm25,%ymm26{%k7}",},
+{{0x62, 0x01, 0x7d, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 7d 4f 7a d1    \tvcvttps2qq %ymm25,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 7a f5    \tvcvttpd2qq %zmm29,%zmm30",},
+{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 57 08 7b f0    \tvcvtusi2sd %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 56 08 7b f0    \tvcvtusi2ss %eax,%xmm5,%xmm6",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x7b, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 7b d5    \tvcvtps2qq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 7b f5    \tvcvtpd2qq %zmm29,%zmm30",},
+{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "",
+"0f 7f c4             \tmovq   %mm0,%mm4",},
+{{0xc5, 0x7d, 0x7f, 0xc6, }, 4, 0, "", "",
+"c5 7d 7f c6          \tvmovdqa %ymm8,%ymm6",},
+{{0x62, 0x01, 0x7d, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 7d 48 7f ca    \tvmovdqa32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 fd 48 7f ca    \tvmovdqa64 %zmm25,%zmm26",},
+{{0xc5, 0x7e, 0x7f, 0xc6, }, 4, 0, "", "",
+"c5 7e 7f c6          \tvmovdqu %ymm8,%ymm6",},
+{{0x62, 0x01, 0x7e, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 7e 48 7f ca    \tvmovdqu32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfe, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 fe 48 7f ca    \tvmovdqu64 %zmm25,%zmm26",},
+{{0x62, 0x61, 0x7f, 0x48, 0x7f, 0x31, }, 6, 0, "", "",
+"62 61 7f 48 7f 31    \tvmovdqu8 %zmm30,(%rcx)",},
+{{0x62, 0x01, 0xff, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 ff 48 7f ca    \tvmovdqu16 %zmm25,%zmm26",},
+{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "",
+"0f db d1             \tpand   %mm1,%mm2",},
+{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "",
+"66 0f db d1          \tpand   %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "",
+"c5 cd db d4          \tvpand  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xdb, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 db d0    \tvpandd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xdb, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 db d0    \tvpandq %zmm24,%zmm25,%zmm26",},
+{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "",
+"0f df d1             \tpandn  %mm1,%mm2",},
+{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "",
+"66 0f df d1          \tpandn  %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "",
+"c5 cd df d4          \tvpandn %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xdf, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 df d0    \tvpandnd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xdf, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 df d0    \tvpandnq %zmm24,%zmm25,%zmm26",},
+{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 f9 e6 d1          \tvcvttpd2dq %xmm1,%xmm2",},
+{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "",
+"c5 fa e6 f5          \tvcvtdq2pd %xmm5,%xmm6",},
+{{0x62, 0x61, 0x7e, 0x4f, 0xe6, 0xd5, }, 6, 0, "", "",
+"62 61 7e 4f e6 d5    \tvcvtdq2pd %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfe, 0x48, 0xe6, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 e6 d1    \tvcvtqq2pd %zmm25,%zmm26",},
+{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 fb e6 d1          \tvcvtpd2dq %xmm1,%xmm2",},
+{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "",
+"0f eb f4             \tpor    %mm4,%mm6",},
+{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "",
+"c5 cd eb d4          \tvpor   %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xeb, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 eb d0    \tvpord  %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xeb, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 eb d0    \tvporq  %zmm24,%zmm25,%zmm26",},
+{{0x0f, 0xef, 0xf4, }, 3, 0, "", "",
+"0f ef f4             \tpxor   %mm4,%mm6",},
+{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "",
+"c5 cd ef d4          \tvpxor  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xef, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 ef d0    \tvpxord %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xef, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 ef d0    \tvpxorq %zmm24,%zmm25,%zmm26",},
+{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "",
+"66 0f 38 10 c1       \tpblendvb %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x02, 0x9d, 0x40, 0x10, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 10 eb    \tvpsrlvw %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x10, 0xe6, }, 6, 0, "", "",
+"62 62 7e 4f 10 e6    \tvpmovuswb %zmm28,%ymm6{%k7}",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x11, 0xe6, }, 6, 0, "", "",
+"62 62 7e 4f 11 e6    \tvpmovusdb %zmm28,%xmm6{%k7}",},
+{{0x62, 0x02, 0x9d, 0x40, 0x11, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 11 eb    \tvpsravw %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x12, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 12 de    \tvpmovusqb %zmm27,%xmm6{%k7}",},
+{{0x62, 0x02, 0x9d, 0x40, 0x12, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 12 eb    \tvpsllvw %zmm27,%zmm28,%zmm29",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0x62, 0x7d, 0x4f, 0x13, 0xdd, }, 6, 0, "", "",
+"62 62 7d 4f 13 dd    \tvcvtph2ps %ymm5,%zmm27{%k7}",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x13, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 13 de    \tvpmovusdw %zmm27,%ymm6{%k7}",},
+{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "",
+"66 0f 38 14 c1       \tblendvps %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x14, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 14 de    \tvpmovusqw %zmm27,%xmm6{%k7}",},
+{{0x62, 0x02, 0x1d, 0x40, 0x14, 0xeb, }, 6, 0, "", "",
+"62 02 1d 40 14 eb    \tvprorvd %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x02, 0x9d, 0x40, 0x14, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 14 eb    \tvprorvq %zmm27,%zmm28,%zmm29",},
+{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "",
+"66 0f 38 15 c1       \tblendvpd %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x15, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 15 de    \tvpmovusqd %zmm27,%ymm6{%k7}",},
+{{0x62, 0x02, 0x1d, 0x40, 0x15, 0xeb, }, 6, 0, "", "",
+"62 02 1d 40 15 eb    \tvprolvd %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x02, 0x9d, 0x40, 0x15, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 15 eb    \tvprolvq %zmm27,%zmm28,%zmm29",},
+{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 16 d4       \tvpermps %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x82, 0x2d, 0x27, 0x16, 0xf0, }, 6, 0, "", "",
+"62 82 2d 27 16 f0    \tvpermps %ymm24,%ymm26,%ymm22{%k7}",},
+{{0x62, 0x82, 0xad, 0x27, 0x16, 0xf0, }, 6, 0, "", "",
+"62 82 ad 27 16 f0    \tvpermpd %ymm24,%ymm26,%ymm22{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 19 f4       \tvbroadcastsd %xmm4,%ymm6",},
+{{0x62, 0x02, 0x7d, 0x48, 0x19, 0xd3, }, 6, 0, "", "",
+"62 02 7d 48 19 d3    \tvbroadcastf32x2 %xmm27,%zmm26",},
+{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 1a 21       \tvbroadcastf128 (%rcx),%ymm4",},
+{{0x62, 0x62, 0x7d, 0x48, 0x1a, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 1a 11    \tvbroadcastf32x4 (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x1a, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 1a 11    \tvbroadcastf64x2 (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x1b, 0x19, }, 6, 0, "", "",
+"62 62 7d 48 1b 19    \tvbroadcastf32x8 (%rcx),%zmm27",},
+{{0x62, 0x62, 0xfd, 0x48, 0x1b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 1b 11    \tvbroadcastf64x4 (%rcx),%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x1f, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 1f e3    \tvpabsq %zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "",
+"c4 e2 79 20 ec       \tvpmovsxbw %xmm4,%xmm5",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x20, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 20 de    \tvpmovswb %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 21 f4       \tvpmovsxbd %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x21, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 21 de    \tvpmovsdb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 22 e4       \tvpmovsxbq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x22, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 22 de    \tvpmovsqb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 23 e4       \tvpmovsxwd %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x23, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 23 de    \tvpmovsdw %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 24 f4       \tvpmovsxwq %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x24, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 24 de    \tvpmovsqw %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 25 e4       \tvpmovsxdq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x25, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 25 de    \tvpmovsqd %zmm27,%ymm6{%k7}",},
+{{0x62, 0x92, 0x1d, 0x40, 0x26, 0xeb, }, 6, 0, "", "",
+"62 92 1d 40 26 eb    \tvptestmb %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x9d, 0x40, 0x26, 0xeb, }, 6, 0, "", "",
+"62 92 9d 40 26 eb    \tvptestmw %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x26, 0x40, 0x26, 0xea, }, 6, 0, "", "",
+"62 92 26 40 26 ea    \tvptestnmb %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0xa6, 0x40, 0x26, 0xea, }, 6, 0, "", "",
+"62 92 a6 40 26 ea    \tvptestnmw %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0x1d, 0x40, 0x27, 0xeb, }, 6, 0, "", "",
+"62 92 1d 40 27 eb    \tvptestmd %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x9d, 0x40, 0x27, 0xeb, }, 6, 0, "", "",
+"62 92 9d 40 27 eb    \tvptestmq %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x26, 0x40, 0x27, 0xea, }, 6, 0, "", "",
+"62 92 26 40 27 ea    \tvptestnmd %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0xa6, 0x40, 0x27, 0xea, }, 6, 0, "", "",
+"62 92 a6 40 27 ea    \tvptestnmq %zmm26,%zmm27,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 28 d4       \tvpmuldq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x28, 0xe5, }, 6, 0, "", "",
+"62 62 7e 48 28 e5    \tvpmovm2b %k5,%zmm28",},
+{{0x62, 0x62, 0xfe, 0x48, 0x28, 0xe5, }, 6, 0, "", "",
+"62 62 fe 48 28 e5    \tvpmovm2w %k5,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 29 d4       \tvpcmpeqq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x92, 0x7e, 0x48, 0x29, 0xec, }, 6, 0, "", "",
+"62 92 7e 48 29 ec    \tvpmovb2m %zmm28,%k5",},
+{{0x62, 0x92, 0xfe, 0x48, 0x29, 0xec, }, 6, 0, "", "",
+"62 92 fe 48 29 ec    \tvpmovw2m %zmm28,%k5",},
+{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 2a 21       \tvmovntdqa (%rcx),%ymm4",},
+{{0x62, 0x62, 0xfe, 0x48, 0x2a, 0xf6, }, 6, 0, "", "",
+"62 62 fe 48 2a f6    \tvpbroadcastmb2q %k6,%zmm30",},
+{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2c 31       \tvmaskmovps (%rcx),%ymm4,%ymm6",},
+{{0x62, 0x02, 0x35, 0x40, 0x2c, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 2c d0    \tvscalefps %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x2c, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 2c d0    \tvscalefpd %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2d 31       \tvmaskmovpd (%rcx),%ymm4,%ymm6",},
+{{0x62, 0x02, 0x35, 0x07, 0x2d, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 2d d0    \tvscalefss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x2d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 2d d0    \tvscalefsd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 30 e4       \tvpmovzxbw %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x30, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 30 de    \tvpmovwb %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 31 f4       \tvpmovzxbd %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x31, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 31 de    \tvpmovdb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 32 e4       \tvpmovzxbq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x32, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 32 de    \tvpmovqb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 33 e4       \tvpmovzxwd %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x33, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 33 de    \tvpmovdw %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 34 f4       \tvpmovzxwq %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x34, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 34 de    \tvpmovqw %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 35 e4       \tvpmovzxdq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x35, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 35 de    \tvpmovqd %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 36 d4       \tvpermd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x82, 0x2d, 0x27, 0x36, 0xf0, }, 6, 0, "", "",
+"62 82 2d 27 36 f0    \tvpermd %ymm24,%ymm26,%ymm22{%k7}",},
+{{0x62, 0x82, 0xad, 0x27, 0x36, 0xf0, }, 6, 0, "", "",
+"62 82 ad 27 36 f0    \tvpermq %ymm24,%ymm26,%ymm22{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 38 d4       \tvpminsb %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x38, 0xe5, }, 6, 0, "", "",
+"62 62 7e 48 38 e5    \tvpmovm2d %k5,%zmm28",},
+{{0x62, 0x62, 0xfe, 0x48, 0x38, 0xe5, }, 6, 0, "", "",
+"62 62 fe 48 38 e5    \tvpmovm2q %k5,%zmm28",},
+{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "",
+"c4 e2 69 39 d9       \tvpminsd %xmm1,%xmm2,%xmm3",},
+{{0x62, 0x02, 0x35, 0x40, 0x39, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 39 d0    \tvpminsd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x39, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 39 d0    \tvpminsq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x92, 0x7e, 0x48, 0x39, 0xec, }, 6, 0, "", "",
+"62 92 7e 48 39 ec    \tvpmovd2m %zmm28,%k5",},
+{{0x62, 0x92, 0xfe, 0x48, 0x39, 0xec, }, 6, 0, "", "",
+"62 92 fe 48 39 ec    \tvpmovq2m %zmm28,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3a d4       \tvpminuw %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x3a, 0xe6, }, 6, 0, "", "",
+"62 62 7e 48 3a e6    \tvpbroadcastmw2d %k6,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3b d4       \tvpminud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3b, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3b d0    \tvpminud %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3b, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3b d0    \tvpminuq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3d d4       \tvpmaxsd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3d, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3d d0    \tvpmaxsd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3d d0    \tvpmaxsq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3f d4       \tvpmaxud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3f, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3f d0    \tvpmaxud %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3f, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3f d0    \tvpmaxuq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 40 d4       \tvpmulld %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x40, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 40 d0    \tvpmulld %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x40, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 40 d0    \tvpmullq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0x7d, 0x48, 0x42, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 42 d1    \tvgetexpps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x42, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 42 e3    \tvgetexppd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x43, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 43 d0    \tvgetexpss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0x95, 0x07, 0x43, 0xf4, }, 6, 0, "", "",
+"62 02 95 07 43 f4    \tvgetexpsd %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0x44, 0xe3, }, 6, 0, "", "",
+"62 02 7d 48 44 e3    \tvplzcntd %zmm27,%zmm28",},
+{{0x62, 0x02, 0xfd, 0x48, 0x44, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 44 e3    \tvplzcntq %zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 46 d4       \tvpsravd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x46, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 46 d0    \tvpsravd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x46, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 46 d0    \tvpsravq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0x7d, 0x48, 0x4c, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 4c d1    \tvrcp14ps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x4c, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 4c e3    \tvrcp14pd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x4d, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 4d d0    \tvrcp14ss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x4d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 4d d0    \tvrcp14sd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0x4e, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 4e d1    \tvrsqrt14ps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x4e, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 4e e3    \tvrsqrt14pd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x4f, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 4f d0    \tvrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x4f, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 4f d0    \tvrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "",
+"c4 e2 79 59 f4       \tvpbroadcastq %xmm4,%xmm6",},
+{{0x62, 0x02, 0x7d, 0x48, 0x59, 0xd3, }, 6, 0, "", "",
+"62 02 7d 48 59 d3    \tvbroadcasti32x2 %xmm27,%zmm26",},
+{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 5a 21       \tvbroadcasti128 (%rcx),%ymm4",},
+{{0x62, 0x62, 0x7d, 0x48, 0x5a, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 5a 11    \tvbroadcasti32x4 (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x5a, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 5a 11    \tvbroadcasti64x2 (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x5b, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 5b 21    \tvbroadcasti32x8 (%rcx),%zmm28",},
+{{0x62, 0x62, 0xfd, 0x48, 0x5b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 5b 11    \tvbroadcasti64x4 (%rcx),%zmm26",},
+{{0x62, 0x02, 0x25, 0x40, 0x64, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 64 e2    \tvpblendmd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x64, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 64 e2    \tvpblendmq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x40, 0x65, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 65 d0    \tvblendmps %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xa5, 0x40, 0x65, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 65 e2    \tvblendmpd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x66, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 66 e2    \tvpblendmb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x66, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 66 e2    \tvpblendmw %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x40, 0x75, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 75 d0    \tvpermi2b %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xa5, 0x40, 0x75, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 75 e2    \tvpermi2w %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x76, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 76 e2    \tvpermi2d %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x76, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 76 e2    \tvpermi2q %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x77, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 77 e2    \tvpermi2ps %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x77, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 77 e2    \tvpermi2pd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7a, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7a f0    \tvpbroadcastb %eax,%xmm30",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7b f0    \tvpbroadcastw %eax,%xmm30",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7c, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7c f0    \tvpbroadcastd %eax,%xmm30",},
+{{0x62, 0x62, 0xfd, 0x48, 0x7c, 0xf0, }, 6, 0, "", "",
+"62 62 fd 48 7c f0    \tvpbroadcastq %rax,%zmm30",},
+{{0x62, 0x02, 0x25, 0x40, 0x7d, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7d e2    \tvpermt2b %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7d, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7d e2    \tvpermt2w %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x7e, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7e e2    \tvpermt2d %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7e, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7e e2    \tvpermt2q %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x7f, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7f e2    \tvpermt2ps %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7f, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7f e2    \tvpermt2pd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x83, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 83 e2    \tvpmultishiftqb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x62, 0x7d, 0x48, 0x88, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 88 11    \tvexpandps (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x88, 0x21, }, 6, 0, "", "",
+"62 62 fd 48 88 21    \tvexpandpd (%rcx),%zmm28",},
+{{0x62, 0x62, 0x7d, 0x48, 0x89, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 89 21    \tvpexpandd (%rcx),%zmm28",},
+{{0x62, 0x62, 0xfd, 0x48, 0x89, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 89 11    \tvpexpandq (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x8a, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 8a 21    \tvcompressps %zmm28,(%rcx)",},
+{{0x62, 0x62, 0xfd, 0x48, 0x8a, 0x21, }, 6, 0, "", "",
+"62 62 fd 48 8a 21    \tvcompresspd %zmm28,(%rcx)",},
+{{0x62, 0x62, 0x7d, 0x48, 0x8b, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 8b 21    \tvpcompressd %zmm28,(%rcx)",},
+{{0x62, 0x62, 0xfd, 0x48, 0x8b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 8b 11    \tvpcompressq %zmm26,(%rcx)",},
+{{0x62, 0x02, 0x25, 0x40, 0x8d, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 8d e2    \tvpermb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x8d, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 8d e2    \tvpermw %zmm26,%zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "",
+"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%rbp,%xmm7,2),%xmm1",},
+{{0x62, 0x22, 0x7d, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 90 94 dd 7b 00 00 00 \tvpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 90 94 dd 7b 00 00 00 \tvpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}",},
+{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0x62, 0x22, 0x7d, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 91 94 dd 7b 00 00 00 \tvpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 91 94 dd 7b 00 00 00 \tvpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",},
+{{0x62, 0x22, 0x7d, 0x41, 0xa0, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 a0 a4 ed 7b 00 00 00 \tvpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa0, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a0 94 dd 7b 00 00 00 \tvpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0xb2, 0x7d, 0x41, 0xa1, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 7d 41 a1 b4 ed 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0xb2, 0xfd, 0x21, 0xa1, 0xb4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 fd 21 a1 b4 dd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0x22, 0x7d, 0x41, 0xa2, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 a2 a4 ed 7b 00 00 00 \tvscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa2, 0xa4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a2 a4 dd 7b 00 00 00 \tvscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0xb2, 0x7d, 0x41, 0xa3, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 7d 41 a3 b4 ed 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa3, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a3 a4 ed 7b 00 00 00 \tvscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x02, 0xa5, 0x40, 0xb4, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 b4 e2    \tvpmadd52luq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0xb5, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 b5 e2    \tvpmadd52huq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x7d, 0x48, 0xc4, 0xda, }, 6, 0, "", "",
+"62 02 7d 48 c4 da    \tvpconflictd %zmm26,%zmm27",},
+{{0x62, 0x02, 0xfd, 0x48, 0xc4, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 c4 da    \tvpconflictq %zmm26,%zmm27",},
+{{0x62, 0x02, 0x7d, 0x48, 0xc8, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 c8 f5    \tvexp2ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xc8, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 c8 da    \tvexp2pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x7d, 0x48, 0xca, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 ca f5    \tvrcp28ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xca, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 ca da    \tvrcp28pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x15, 0x07, 0xcb, 0xf4, }, 6, 0, "", "",
+"62 02 15 07 cb f4    \tvrcp28ss %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0xad, 0x07, 0xcb, 0xd9, }, 6, 0, "", "",
+"62 02 ad 07 cb d9    \tvrcp28sd %xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0xcc, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 cc f5    \tvrsqrt28ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xcc, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 cc da    \tvrsqrt28pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x15, 0x07, 0xcd, 0xf4, }, 6, 0, "", "",
+"62 02 15 07 cd f4    \tvrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0xad, 0x07, 0xcd, 0xd9, }, 6, 0, "", "",
+"62 02 ad 07 cd d9    \tvrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x15, 0x40, 0x03, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 03 f4 12 \tvalignd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x03, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 03 d9 12 \tvalignq $0x12,%zmm25,%zmm26,%zmm27",},
+{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 08 d6 05    \tvroundps $0x5,%ymm6,%ymm2",},
+{{0x62, 0x03, 0x7d, 0x48, 0x08, 0xd1, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 08 d1 12 \tvrndscaleps $0x12,%zmm25,%zmm26",},
+{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 09 d6 05    \tvroundpd $0x5,%ymm6,%ymm2",},
+{{0x62, 0x03, 0xfd, 0x48, 0x09, 0xd1, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 09 d1 12 \tvrndscalepd $0x12,%zmm25,%zmm26",},
+{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0a d4 05    \tvroundss $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0x03, 0x35, 0x07, 0x0a, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 07 0a d0 12 \tvrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0b d4 05    \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0x03, 0xb5, 0x07, 0x0b, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 07 0b d0 12 \tvrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 18 f4 05    \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0x03, 0x35, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 47 18 d0 12 \tvinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0x62, 0x03, 0xb5, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 47 18 d0 12 \tvinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 19 e4 05    \tvextractf128 $0x5,%ymm4,%xmm4",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 19 ca 12 \tvextractf32x4 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 19 ca 12 \tvextractf64x2 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0x2d, 0x47, 0x1a, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 47 1a d9 12 \tvinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}",},
+{{0x62, 0x03, 0x95, 0x47, 0x1a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 47 1a f4 12 \tvinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x1b, 0xee, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 1b ee 12 \tvextractf32x8 $0x12,%zmm29,%ymm30{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x1b, 0xd3, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 1b d3 12 \tvextractf64x4 $0x12,%zmm26,%ymm27{%k7}",},
+{{0x62, 0x93, 0x0d, 0x40, 0x1e, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 1e ed 12 \tvpcmpud $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x1e, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 1e ea 12 \tvpcmpuq $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x93, 0x0d, 0x40, 0x1f, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 1f ed 12 \tvpcmpd $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x1f, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 1f ea 12 \tvpcmpq $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x03, 0x15, 0x40, 0x23, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 23 f4 12 \tvshuff32x4 $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x23, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 23 d9 12 \tvshuff64x2 $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x15, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 25 f4 12 \tvpternlogd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x95, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 25 f4 12 \tvpternlogq $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x7d, 0x48, 0x26, 0xda, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 26 da 12 \tvgetmantps $0x12,%zmm26,%zmm27",},
+{{0x62, 0x03, 0xfd, 0x48, 0x26, 0xf5, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 26 f5 12 \tvgetmantpd $0x12,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x07, 0x27, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 07 27 d9 12 \tvgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x95, 0x07, 0x27, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 07 27 f4 12 \tvgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 38 f4 05    \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0x03, 0x35, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 47 38 d0 12 \tvinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0x62, 0x03, 0xb5, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 47 38 d0 12 \tvinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 39 e6 05    \tvextracti128 $0x5,%ymm4,%xmm6",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 39 ca 12 \tvextracti32x4 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 39 ca 12 \tvextracti64x2 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0x15, 0x47, 0x3a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 47 3a f4 12 \tvinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x03, 0xad, 0x47, 0x3a, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 47 3a d9 12 \tvinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x3b, 0xee, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 3b ee 12 \tvextracti32x8 $0x12,%zmm29,%ymm30{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x3b, 0xd3, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 3b d3 12 \tvextracti64x4 $0x12,%zmm26,%ymm27{%k7}",},
+{{0x62, 0x93, 0x0d, 0x40, 0x3e, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 3e ed 12 \tvpcmpub $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x3e, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 3e ea 12 \tvpcmpuw $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x93, 0x0d, 0x40, 0x3f, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 3f ed 12 \tvpcmpb $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x3f, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 3f ea 12 \tvpcmpw $0x12,%zmm26,%zmm27,%k5",},
+{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 4d 42 d4 05    \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",},
+{{0x62, 0x03, 0x2d, 0x40, 0x43, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 40 43 d9 12 \tvshufi32x4 $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x95, 0x40, 0x43, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 43 f4 12 \tvshufi64x2 $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x40, 0x50, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 40 50 d9 12 \tvrangeps $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x95, 0x40, 0x50, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 50 f4 12 \tvrangepd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x00, 0x51, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 00 51 d9 12 \tvrangess $0x12,%xmm25,%xmm26,%xmm27",},
+{{0x62, 0x03, 0x95, 0x00, 0x51, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 00 51 f4 12 \tvrangesd $0x12,%xmm28,%xmm29,%xmm30",},
+{{0x62, 0x03, 0x15, 0x40, 0x54, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 54 f4 12 \tvfixupimmps $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x54, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 54 d9 12 \tvfixupimmpd $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x15, 0x07, 0x55, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 07 55 f4 12 \tvfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x03, 0xad, 0x07, 0x55, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 07 55 d9 12 \tvfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x7d, 0x48, 0x56, 0xda, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 56 da 12 \tvreduceps $0x12,%zmm26,%zmm27",},
+{{0x62, 0x03, 0xfd, 0x48, 0x56, 0xf5, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 56 f5 12 \tvreducepd $0x12,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x00, 0x57, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 00 57 d9 12 \tvreducess $0x12,%xmm25,%xmm26,%xmm27",},
+{{0x62, 0x03, 0x95, 0x00, 0x57, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 00 57 f4 12 \tvreducesd $0x12,%xmm28,%xmm29,%xmm30",},
+{{0x62, 0x93, 0x7d, 0x48, 0x66, 0xeb, 0x12, }, 7, 0, "", "",
+"62 93 7d 48 66 eb 12 \tvfpclassps $0x12,%zmm27,%k5",},
+{{0x62, 0x93, 0xfd, 0x48, 0x66, 0xee, 0x12, }, 7, 0, "", "",
+"62 93 fd 48 66 ee 12 \tvfpclasspd $0x12,%zmm30,%k5",},
+{{0x62, 0x93, 0x7d, 0x08, 0x67, 0xeb, 0x12, }, 7, 0, "", "",
+"62 93 7d 08 67 eb 12 \tvfpclassss $0x12,%xmm27,%k5",},
+{{0x62, 0x93, 0xfd, 0x08, 0x67, 0xee, 0x12, }, 7, 0, "", "",
+"62 93 fd 08 67 ee 12 \tvfpclasssd $0x12,%xmm30,%k5",},
+{{0x62, 0x91, 0x2d, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "",
+"62 91 2d 40 72 c1 12 \tvprord $0x12,%zmm25,%zmm26",},
+{{0x62, 0x91, 0xad, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "",
+"62 91 ad 40 72 c1 12 \tvprorq $0x12,%zmm25,%zmm26",},
+{{0x62, 0x91, 0x0d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 91 0d 40 72 cd 12 \tvprold $0x12,%zmm29,%zmm30",},
+{{0x62, 0x91, 0x8d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 91 8d 40 72 cd 12 \tvprolq $0x12,%zmm29,%zmm30",},
+{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "",
+"0f 72 e6 02          \tpsrad  $0x2,%mm6",},
+{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "",
+"c5 ed 72 e6 05       \tvpsrad $0x5,%ymm6,%ymm2",},
+{{0x62, 0x91, 0x4d, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "",
+"62 91 4d 40 72 e2 05 \tvpsrad $0x5,%zmm26,%zmm22",},
+{{0x62, 0x91, 0xcd, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "",
+"62 91 cd 40 72 e2 05 \tvpsraq $0x5,%zmm26,%zmm22",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x01, 0x95, 0x40, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 40 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x47, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 47 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x01, 0x95, 0xc7, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 c7 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30{%k7}{z}",},
+{{0x62, 0x01, 0x95, 0x10, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 10 58 f4    \tvaddpd {rn-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x50, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 50 58 f4    \tvaddpd {ru-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x30, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 30 58 f4    \tvaddpd {rd-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x70, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 70 58 f4    \tvaddpd {rz-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x40, 0x58, 0x31, }, 6, 0, "", "",
+"62 61 95 40 58 31    \tvaddpd (%rcx),%zmm29,%zmm30",},
+{{0x62, 0x21, 0x95, 0x40, 0x58, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "",
+"62 21 95 40 58 b4 f0 23 01 00 00 \tvaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x50, 0x58, 0x31, }, 6, 0, "", "",
+"62 61 95 50 58 31    \tvaddpd (%rcx){1to8},%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x40, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 61 95 40 58 72 7f \tvaddpd 0x1fc0(%rdx),%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x50, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 61 95 50 58 72 7f \tvaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30",},
+{{0x62, 0xf1, 0x0c, 0x50, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "",
+"62 f1 0c 50 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5",},
+{{0x62, 0xb1, 0x97, 0x07, 0xc2, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "",
+"62 b1 97 07 c2 ac f0 23 01 00 00 01 \tvcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}",},
+{{0x62, 0x91, 0x97, 0x17, 0xc2, 0xec, 0x02, }, 7, 0, "", "",
+"62 91 97 17 c2 ec 02 \tvcmplesd {sae},%xmm28,%xmm29,%k5{%k7}",},
+{{0x62, 0x23, 0x15, 0x07, 0x27, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "",
+"62 23 15 07 27 b4 f0 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}",},
 {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "",
 "f3 0f 1b 00          \tbndmk  (%rax),%bnd0",},
 {{0xf3, 0x41, 0x0f, 0x1b, 0x00, }, 5, 0, "", "",
@@ -325,19 +1257,19 @@
 {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
 "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%rax,%rcx,1)",},
 {{0xf2, 0xe8, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "call", "unconditional",
-"f2 e8 00 00 00 00    \tbnd callq 3f6 <main+0x3f6>",},
+"f2 e8 00 00 00 00    \tbnd callq f22 <main+0xf22>",},
 {{0x67, 0xf2, 0xff, 0x10, }, 4, 0, "call", "indirect",
 "67 f2 ff 10          \tbnd callq *(%eax)",},
 {{0xf2, 0xc3, }, 2, 0, "ret", "indirect",
 "f2 c3                \tbnd retq ",},
 {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional",
-"f2 e9 00 00 00 00    \tbnd jmpq 402 <main+0x402>",},
+"f2 e9 00 00 00 00    \tbnd jmpq f2e <main+0xf2e>",},
 {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional",
-"f2 e9 00 00 00 00    \tbnd jmpq 408 <main+0x408>",},
+"f2 e9 00 00 00 00    \tbnd jmpq f34 <main+0xf34>",},
 {{0x67, 0xf2, 0xff, 0x21, }, 4, 0, "jmp", "indirect",
 "67 f2 ff 21          \tbnd jmpq *(%ecx)",},
 {{0xf2, 0x0f, 0x85, 0x00, 0x00, 0x00, 0x00, }, 7, 0, "jcc", "conditional",
-"f2 0f 85 00 00 00 00 \tbnd jne 413 <main+0x413>",},
+"f2 0f 85 00 00 00 00 \tbnd jne f3f <main+0xf3f>",},
 {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
 "0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
 {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
index 41b1b1c62660..76e0ec379c8b 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -19,8 +19,882 @@ int main(void)
 	/* Following line is a marker for the awk script - do not change */
 	asm volatile("rdtsc"); /* Start here */
 
+	/* Test fix for vcvtph2ps in x86-opcode-map.txt */
+
+	asm volatile("vcvtph2ps %xmm3,%ymm5");
+
 #ifdef __x86_64__
 
+	/* AVX-512: Instructions with the same op codes as Mask Instructions  */
+
+	asm volatile("cmovno %rax,%rbx");
+	asm volatile("cmovno 0x12345678(%rax),%rcx");
+	asm volatile("cmovno 0x12345678(%rax),%cx");
+
+	asm volatile("cmove  %rax,%rbx");
+	asm volatile("cmove 0x12345678(%rax),%rcx");
+	asm volatile("cmove 0x12345678(%rax),%cx");
+
+	asm volatile("seto    0x12345678(%rax)");
+	asm volatile("setno   0x12345678(%rax)");
+	asm volatile("setb    0x12345678(%rax)");
+	asm volatile("setc    0x12345678(%rax)");
+	asm volatile("setnae  0x12345678(%rax)");
+	asm volatile("setae   0x12345678(%rax)");
+	asm volatile("setnb   0x12345678(%rax)");
+	asm volatile("setnc   0x12345678(%rax)");
+	asm volatile("sets    0x12345678(%rax)");
+	asm volatile("setns   0x12345678(%rax)");
+
+	/* AVX-512: Mask Instructions */
+
+	asm volatile("kandw  %k7,%k6,%k5");
+	asm volatile("kandq  %k7,%k6,%k5");
+	asm volatile("kandb  %k7,%k6,%k5");
+	asm volatile("kandd  %k7,%k6,%k5");
+
+	asm volatile("kandnw  %k7,%k6,%k5");
+	asm volatile("kandnq  %k7,%k6,%k5");
+	asm volatile("kandnb  %k7,%k6,%k5");
+	asm volatile("kandnd  %k7,%k6,%k5");
+
+	asm volatile("knotw  %k7,%k6");
+	asm volatile("knotq  %k7,%k6");
+	asm volatile("knotb  %k7,%k6");
+	asm volatile("knotd  %k7,%k6");
+
+	asm volatile("korw  %k7,%k6,%k5");
+	asm volatile("korq  %k7,%k6,%k5");
+	asm volatile("korb  %k7,%k6,%k5");
+	asm volatile("kord  %k7,%k6,%k5");
+
+	asm volatile("kxnorw  %k7,%k6,%k5");
+	asm volatile("kxnorq  %k7,%k6,%k5");
+	asm volatile("kxnorb  %k7,%k6,%k5");
+	asm volatile("kxnord  %k7,%k6,%k5");
+
+	asm volatile("kxorw  %k7,%k6,%k5");
+	asm volatile("kxorq  %k7,%k6,%k5");
+	asm volatile("kxorb  %k7,%k6,%k5");
+	asm volatile("kxord  %k7,%k6,%k5");
+
+	asm volatile("kaddw  %k7,%k6,%k5");
+	asm volatile("kaddq  %k7,%k6,%k5");
+	asm volatile("kaddb  %k7,%k6,%k5");
+	asm volatile("kaddd  %k7,%k6,%k5");
+
+	asm volatile("kunpckbw %k7,%k6,%k5");
+	asm volatile("kunpckwd %k7,%k6,%k5");
+	asm volatile("kunpckdq %k7,%k6,%k5");
+
+	asm volatile("kmovw  %k6,%k5");
+	asm volatile("kmovw  (%rcx),%k5");
+	asm volatile("kmovw  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovw  %k5,(%rcx)");
+	asm volatile("kmovw  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovw  %eax,%k5");
+	asm volatile("kmovw  %ebp,%k5");
+	asm volatile("kmovw  %r13d,%k5");
+	asm volatile("kmovw  %k5,%eax");
+	asm volatile("kmovw  %k5,%ebp");
+	asm volatile("kmovw  %k5,%r13d");
+
+	asm volatile("kmovq  %k6,%k5");
+	asm volatile("kmovq  (%rcx),%k5");
+	asm volatile("kmovq  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovq  %k5,(%rcx)");
+	asm volatile("kmovq  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovq  %rax,%k5");
+	asm volatile("kmovq  %rbp,%k5");
+	asm volatile("kmovq  %r13,%k5");
+	asm volatile("kmovq  %k5,%rax");
+	asm volatile("kmovq  %k5,%rbp");
+	asm volatile("kmovq  %k5,%r13");
+
+	asm volatile("kmovb  %k6,%k5");
+	asm volatile("kmovb  (%rcx),%k5");
+	asm volatile("kmovb  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovb  %k5,(%rcx)");
+	asm volatile("kmovb  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovb  %eax,%k5");
+	asm volatile("kmovb  %ebp,%k5");
+	asm volatile("kmovb  %r13d,%k5");
+	asm volatile("kmovb  %k5,%eax");
+	asm volatile("kmovb  %k5,%ebp");
+	asm volatile("kmovb  %k5,%r13d");
+
+	asm volatile("kmovd  %k6,%k5");
+	asm volatile("kmovd  (%rcx),%k5");
+	asm volatile("kmovd  0x123(%rax,%r14,8),%k5");
+	asm volatile("kmovd  %k5,(%rcx)");
+	asm volatile("kmovd  %k5,0x123(%rax,%r14,8)");
+	asm volatile("kmovd  %eax,%k5");
+	asm volatile("kmovd  %ebp,%k5");
+	asm volatile("kmovd  %r13d,%k5");
+	asm volatile("kmovd  %k5,%eax");
+	asm volatile("kmovd  %k5,%ebp");
+	asm volatile("kmovd %k5,%r13d");
+
+	asm volatile("kortestw %k6,%k5");
+	asm volatile("kortestq %k6,%k5");
+	asm volatile("kortestb %k6,%k5");
+	asm volatile("kortestd %k6,%k5");
+
+	asm volatile("ktestw %k6,%k5");
+	asm volatile("ktestq %k6,%k5");
+	asm volatile("ktestb %k6,%k5");
+	asm volatile("ktestd %k6,%k5");
+
+	asm volatile("kshiftrw $0x12,%k6,%k5");
+	asm volatile("kshiftrq $0x5b,%k6,%k5");
+	asm volatile("kshiftlw $0x12,%k6,%k5");
+	asm volatile("kshiftlq $0x5b,%k6,%k5");
+
+	/* AVX-512: Op code 0f 5b */
+	asm volatile("vcvtdq2ps %xmm5,%xmm6");
+	asm volatile("vcvtqq2ps %zmm29,%ymm6{%k7}");
+	asm volatile("vcvtps2dq %xmm5,%xmm6");
+	asm volatile("vcvttps2dq %xmm5,%xmm6");
+
+	/* AVX-512: Op code 0f 6f */
+
+	asm volatile("movq   %mm0,%mm4");
+	asm volatile("vmovdqa %ymm4,%ymm6");
+	asm volatile("vmovdqa32 %zmm25,%zmm26");
+	asm volatile("vmovdqa64 %zmm25,%zmm26");
+	asm volatile("vmovdqu %ymm4,%ymm6");
+	asm volatile("vmovdqu32 %zmm29,%zmm30");
+	asm volatile("vmovdqu64 %zmm25,%zmm26");
+	asm volatile("vmovdqu8 %zmm29,%zmm30");
+	asm volatile("vmovdqu16 %zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 78 */
+
+	asm volatile("vmread %rax,%rbx");
+	asm volatile("vcvttps2udq %zmm25,%zmm26");
+	asm volatile("vcvttpd2udq %zmm29,%ymm6{%k7}");
+	asm volatile("vcvttsd2usi %xmm6,%rax");
+	asm volatile("vcvttss2usi %xmm6,%rax");
+	asm volatile("vcvttps2uqq %ymm5,%zmm26{%k7}");
+	asm volatile("vcvttpd2uqq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 79 */
+
+	asm volatile("vmwrite %rax,%rbx");
+	asm volatile("vcvtps2udq %zmm25,%zmm26");
+	asm volatile("vcvtpd2udq %zmm29,%ymm6{%k7}");
+	asm volatile("vcvtsd2usi %xmm6,%rax");
+	asm volatile("vcvtss2usi %xmm6,%rax");
+	asm volatile("vcvtps2uqq %ymm5,%zmm26{%k7}");
+	asm volatile("vcvtpd2uqq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 7a */
+
+	asm volatile("vcvtudq2pd %ymm5,%zmm29{%k7}");
+	asm volatile("vcvtuqq2pd %zmm25,%zmm26");
+	asm volatile("vcvtudq2ps %zmm29,%zmm30");
+	asm volatile("vcvtuqq2ps %zmm25,%ymm26{%k7}");
+	asm volatile("vcvttps2qq %ymm25,%zmm26{%k7}");
+	asm volatile("vcvttpd2qq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 7b */
+
+	asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6");
+	asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6");
+	asm volatile("vcvtps2qq %ymm5,%zmm26{%k7}");
+	asm volatile("vcvtpd2qq %zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 7f */
+
+	asm volatile("movq.s  %mm0,%mm4");
+	asm volatile("vmovdqa %ymm8,%ymm6");
+	asm volatile("vmovdqa32.s %zmm25,%zmm26");
+	asm volatile("vmovdqa64.s %zmm25,%zmm26");
+	asm volatile("vmovdqu %ymm8,%ymm6");
+	asm volatile("vmovdqu32.s %zmm25,%zmm26");
+	asm volatile("vmovdqu64.s %zmm25,%zmm26");
+	asm volatile("vmovdqu8.s %zmm30,(%rcx)");
+	asm volatile("vmovdqu16.s %zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f db */
+
+	asm volatile("pand  %mm1,%mm2");
+	asm volatile("pand  %xmm1,%xmm2");
+	asm volatile("vpand  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpandq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f df */
+
+	asm volatile("pandn  %mm1,%mm2");
+	asm volatile("pandn  %xmm1,%xmm2");
+	asm volatile("vpandn %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandnd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpandnq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f e6 */
+
+	asm volatile("vcvttpd2dq %xmm1,%xmm2");
+	asm volatile("vcvtdq2pd %xmm5,%xmm6");
+	asm volatile("vcvtdq2pd %ymm5,%zmm26{%k7}");
+	asm volatile("vcvtqq2pd %zmm25,%zmm26");
+	asm volatile("vcvtpd2dq %xmm1,%xmm2");
+
+	/* AVX-512: Op code 0f eb */
+
+	asm volatile("por   %mm4,%mm6");
+	asm volatile("vpor   %ymm4,%ymm6,%ymm2");
+	asm volatile("vpord  %zmm24,%zmm25,%zmm26");
+	asm volatile("vporq  %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f ef */
+
+	asm volatile("pxor   %mm4,%mm6");
+	asm volatile("vpxor  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpxord %zmm24,%zmm25,%zmm26");
+	asm volatile("vpxorq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 10 */
+
+	asm volatile("pblendvb %xmm1,%xmm0");
+	asm volatile("vpsrlvw %zmm27,%zmm28,%zmm29");
+	asm volatile("vpmovuswb %zmm28,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 11 */
+
+	asm volatile("vpmovusdb %zmm28,%xmm6{%k7}");
+	asm volatile("vpsravw %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 12 */
+
+	asm volatile("vpmovusqb %zmm27,%xmm6{%k7}");
+	asm volatile("vpsllvw %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 13 */
+
+	asm volatile("vcvtph2ps %xmm3,%ymm5");
+	asm volatile("vcvtph2ps %ymm5,%zmm27{%k7}");
+	asm volatile("vpmovusdw %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 14 */
+
+	asm volatile("blendvps %xmm1,%xmm0");
+	asm volatile("vpmovusqw %zmm27,%xmm6{%k7}");
+	asm volatile("vprorvd %zmm27,%zmm28,%zmm29");
+	asm volatile("vprorvq %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 15 */
+
+	asm volatile("blendvpd %xmm1,%xmm0");
+	asm volatile("vpmovusqd %zmm27,%ymm6{%k7}");
+	asm volatile("vprolvd %zmm27,%zmm28,%zmm29");
+	asm volatile("vprolvq %zmm27,%zmm28,%zmm29");
+
+	/* AVX-512: Op code 0f 38 16 */
+
+	asm volatile("vpermps %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermps %ymm24,%ymm26,%ymm22{%k7}");
+	asm volatile("vpermpd %ymm24,%ymm26,%ymm22{%k7}");
+
+	/* AVX-512: Op code 0f 38 19 */
+
+	asm volatile("vbroadcastsd %xmm4,%ymm6");
+	asm volatile("vbroadcastf32x2 %xmm27,%zmm26");
+
+	/* AVX-512: Op code 0f 38 1a */
+
+	asm volatile("vbroadcastf128 (%rcx),%ymm4");
+	asm volatile("vbroadcastf32x4 (%rcx),%zmm26");
+	asm volatile("vbroadcastf64x2 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 1b */
+
+	asm volatile("vbroadcastf32x8 (%rcx),%zmm27");
+	asm volatile("vbroadcastf64x4 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 1f */
+
+	asm volatile("vpabsq %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 20 */
+
+	asm volatile("vpmovsxbw %xmm4,%xmm5");
+	asm volatile("vpmovswb %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 21 */
+
+	asm volatile("vpmovsxbd %xmm4,%ymm6");
+	asm volatile("vpmovsdb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 22 */
+
+	asm volatile("vpmovsxbq %xmm4,%ymm4");
+	asm volatile("vpmovsqb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 23 */
+
+	asm volatile("vpmovsxwd %xmm4,%ymm4");
+	asm volatile("vpmovsdw %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 24 */
+
+	asm volatile("vpmovsxwq %xmm4,%ymm6");
+	asm volatile("vpmovsqw %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 25 */
+
+	asm volatile("vpmovsxdq %xmm4,%ymm4");
+	asm volatile("vpmovsqd %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 26 */
+
+	asm volatile("vptestmb %zmm27,%zmm28,%k5");
+	asm volatile("vptestmw %zmm27,%zmm28,%k5");
+	asm volatile("vptestnmb %zmm26,%zmm27,%k5");
+	asm volatile("vptestnmw %zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 38 27 */
+
+	asm volatile("vptestmd %zmm27,%zmm28,%k5");
+	asm volatile("vptestmq %zmm27,%zmm28,%k5");
+	asm volatile("vptestnmd %zmm26,%zmm27,%k5");
+	asm volatile("vptestnmq %zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 38 28 */
+
+	asm volatile("vpmuldq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2b %k5,%zmm28");
+	asm volatile("vpmovm2w %k5,%zmm28");
+
+	/* AVX-512: Op code 0f 38 29 */
+
+	asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovb2m %zmm28,%k5");
+	asm volatile("vpmovw2m %zmm28,%k5");
+
+	/* AVX-512: Op code 0f 38 2a */
+
+	asm volatile("vmovntdqa (%rcx),%ymm4");
+	asm volatile("vpbroadcastmb2q %k6,%zmm30");
+
+	/* AVX-512: Op code 0f 38 2c */
+
+	asm volatile("vmaskmovps (%rcx),%ymm4,%ymm6");
+	asm volatile("vscalefps %zmm24,%zmm25,%zmm26");
+	asm volatile("vscalefpd %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 2d */
+
+	asm volatile("vmaskmovpd (%rcx),%ymm4,%ymm6");
+	asm volatile("vscalefss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vscalefsd %xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 38 30 */
+
+	asm volatile("vpmovzxbw %xmm4,%ymm4");
+	asm volatile("vpmovwb %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 31 */
+
+	asm volatile("vpmovzxbd %xmm4,%ymm6");
+	asm volatile("vpmovdb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 32 */
+
+	asm volatile("vpmovzxbq %xmm4,%ymm4");
+	asm volatile("vpmovqb %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 33 */
+
+	asm volatile("vpmovzxwd %xmm4,%ymm4");
+	asm volatile("vpmovdw %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 34 */
+
+	asm volatile("vpmovzxwq %xmm4,%ymm6");
+	asm volatile("vpmovqw %zmm27,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 35 */
+
+	asm volatile("vpmovzxdq %xmm4,%ymm4");
+	asm volatile("vpmovqd %zmm27,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 38 */
+
+	asm volatile("vpermd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermd %ymm24,%ymm26,%ymm22{%k7}");
+	asm volatile("vpermq %ymm24,%ymm26,%ymm22{%k7}");
+
+	/* AVX-512: Op code 0f 38 38 */
+
+	asm volatile("vpminsb %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2d %k5,%zmm28");
+	asm volatile("vpmovm2q %k5,%zmm28");
+
+	/* AVX-512: Op code 0f 38 39 */
+
+	asm volatile("vpminsd %xmm1,%xmm2,%xmm3");
+	asm volatile("vpminsd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpminsq %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmovd2m %zmm28,%k5");
+	asm volatile("vpmovq2m %zmm28,%k5");
+
+	/* AVX-512: Op code 0f 38 3a */
+
+	asm volatile("vpminuw %ymm4,%ymm6,%ymm2");
+	asm volatile("vpbroadcastmw2d %k6,%zmm28");
+
+	/* AVX-512: Op code 0f 38 3b */
+
+	asm volatile("vpminud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpminud %zmm24,%zmm25,%zmm26");
+	asm volatile("vpminuq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 3d */
+
+	asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxsd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmaxsq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 3f */
+
+	asm volatile("vpmaxud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxud %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmaxuq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 42 */
+
+	asm volatile("vpmulld %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmulld %zmm24,%zmm25,%zmm26");
+	asm volatile("vpmullq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 42 */
+
+	asm volatile("vgetexpps %zmm25,%zmm26");
+	asm volatile("vgetexppd %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 43 */
+
+	asm volatile("vgetexpss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vgetexpsd %xmm28,%xmm29,%xmm30{%k7}");
+
+	/* AVX-512: Op code 0f 38 44 */
+
+	asm volatile("vplzcntd %zmm27,%zmm28");
+	asm volatile("vplzcntq %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 46 */
+
+	asm volatile("vpsravd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpsravd %zmm24,%zmm25,%zmm26");
+	asm volatile("vpsravq %zmm24,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 38 4c */
+
+	asm volatile("vrcp14ps %zmm25,%zmm26");
+	asm volatile("vrcp14pd %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 4d */
+
+	asm volatile("vrcp14ss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vrcp14sd %xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 38 4e */
+
+	asm volatile("vrsqrt14ps %zmm25,%zmm26");
+	asm volatile("vrsqrt14pd %zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 4f */
+
+	asm volatile("vrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}");
+	asm volatile("vrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 38 59 */
+
+	asm volatile("vpbroadcastq %xmm4,%xmm6");
+	asm volatile("vbroadcasti32x2 %xmm27,%zmm26");
+
+	/* AVX-512: Op code 0f 38 5a */
+
+	asm volatile("vbroadcasti128 (%rcx),%ymm4");
+	asm volatile("vbroadcasti32x4 (%rcx),%zmm26");
+	asm volatile("vbroadcasti64x2 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 5b */
+
+	asm volatile("vbroadcasti32x8 (%rcx),%zmm28");
+	asm volatile("vbroadcasti64x4 (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 64 */
+
+	asm volatile("vpblendmd %zmm26,%zmm27,%zmm28");
+	asm volatile("vpblendmq %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 65 */
+
+	asm volatile("vblendmps %zmm24,%zmm25,%zmm26");
+	asm volatile("vblendmpd %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 66 */
+
+	asm volatile("vpblendmb %zmm26,%zmm27,%zmm28");
+	asm volatile("vpblendmw %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 75 */
+
+	asm volatile("vpermi2b %zmm24,%zmm25,%zmm26");
+	asm volatile("vpermi2w %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 76 */
+
+	asm volatile("vpermi2d %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermi2q %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 77 */
+
+	asm volatile("vpermi2ps %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermi2pd %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 7a */
+
+	asm volatile("vpbroadcastb %eax,%xmm30");
+
+	/* AVX-512: Op code 0f 38 7b */
+
+	asm volatile("vpbroadcastw %eax,%xmm30");
+
+	/* AVX-512: Op code 0f 38 7c */
+
+	asm volatile("vpbroadcastd %eax,%xmm30");
+	asm volatile("vpbroadcastq %rax,%zmm30");
+
+	/* AVX-512: Op code 0f 38 7d */
+
+	asm volatile("vpermt2b %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermt2w %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 7e */
+
+	asm volatile("vpermt2d %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermt2q %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 7f */
+
+	asm volatile("vpermt2ps %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermt2pd %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 83 */
+
+	asm volatile("vpmultishiftqb %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 88 */
+
+	asm volatile("vexpandps (%rcx),%zmm26");
+	asm volatile("vexpandpd (%rcx),%zmm28");
+
+	/* AVX-512: Op code 0f 38 89 */
+
+	asm volatile("vpexpandd (%rcx),%zmm28");
+	asm volatile("vpexpandq (%rcx),%zmm26");
+
+	/* AVX-512: Op code 0f 38 8a */
+
+	asm volatile("vcompressps %zmm28,(%rcx)");
+	asm volatile("vcompresspd %zmm28,(%rcx)");
+
+	/* AVX-512: Op code 0f 38 8b */
+
+	asm volatile("vpcompressd %zmm28,(%rcx)");
+	asm volatile("vpcompressq %zmm26,(%rcx)");
+
+	/* AVX-512: Op code 0f 38 8d */
+
+	asm volatile("vpermb %zmm26,%zmm27,%zmm28");
+	asm volatile("vpermw %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 90 */
+
+	asm volatile("vpgatherdd %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdq %xmm2,0x04(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}");
+	asm volatile("vpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}");
+
+	/* AVX-512: Op code 0f 38 91 */
+
+	asm volatile("vpgatherqd %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqq %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}");
+	asm volatile("vpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}");
+
+	/* AVX-512: Op code 0f 38 a0 */
+
+	asm volatile("vpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a1 */
+
+	asm volatile("vpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a2 */
+
+	asm volatile("vscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a3 */
+
+	asm volatile("vscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}");
+	asm volatile("vscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 b4 */
+
+	asm volatile("vpmadd52luq %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 b5 */
+
+	asm volatile("vpmadd52huq %zmm26,%zmm27,%zmm28");
+
+	/* AVX-512: Op code 0f 38 c4 */
+
+	asm volatile("vpconflictd %zmm26,%zmm27");
+	asm volatile("vpconflictq %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 c8 */
+
+	asm volatile("vexp2ps %zmm29,%zmm30");
+	asm volatile("vexp2pd %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 ca */
+
+	asm volatile("vrcp28ps %zmm29,%zmm30");
+	asm volatile("vrcp28pd %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 cb */
+
+	asm volatile("vrcp28ss %xmm28,%xmm29,%xmm30{%k7}");
+	asm volatile("vrcp28sd %xmm25,%xmm26,%xmm27{%k7}");
+
+	/* AVX-512: Op code 0f 38 cc */
+
+	asm volatile("vrsqrt28ps %zmm29,%zmm30");
+	asm volatile("vrsqrt28pd %zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 38 cd */
+
+	asm volatile("vrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}");
+	asm volatile("vrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 03 */
+
+	asm volatile("valignd $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("valignq $0x12,%zmm25,%zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 3a 08 */
+
+	asm volatile("vroundps $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscaleps $0x12,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 3a 09 */
+
+	asm volatile("vroundpd $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscalepd $0x12,%zmm25,%zmm26");
+
+	/* AVX-512: Op code 0f 3a 1a */
+
+	asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 0b */
+
+	asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 18 */
+
+	asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+	asm volatile("vinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 19 */
+
+	asm volatile("vextractf128 $0x5,%ymm4,%xmm4");
+	asm volatile("vextractf32x4 $0x12,%zmm25,%xmm26{%k7}");
+	asm volatile("vextractf64x2 $0x12,%zmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1a */
+
+	asm volatile("vinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}");
+	asm volatile("vinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1b */
+
+	asm volatile("vextractf32x8 $0x12,%zmm29,%ymm30{%k7}");
+	asm volatile("vextractf64x4 $0x12,%zmm26,%ymm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1e */
+
+	asm volatile("vpcmpud $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpuq $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 1f */
+
+	asm volatile("vpcmpd $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpq $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 23 */
+
+	asm volatile("vshuff32x4 $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("vshuff64x2 $0x12,%zmm25,%zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 3a 25 */
+
+	asm volatile("vpternlogd $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("vpternlogq $0x12,%zmm28,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 26 */
+
+	asm volatile("vgetmantps $0x12,%zmm26,%zmm27");
+	asm volatile("vgetmantpd $0x12,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 27 */
+
+	asm volatile("vgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}");
+	asm volatile("vgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}");
+
+	/* AVX-512: Op code 0f 3a 38 */
+
+	asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+	asm volatile("vinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 39 */
+
+	asm volatile("vextracti128 $0x5,%ymm4,%xmm6");
+	asm volatile("vextracti32x4 $0x12,%zmm25,%xmm26{%k7}");
+	asm volatile("vextracti64x2 $0x12,%zmm25,%xmm26{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3a */
+
+	asm volatile("vinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}");
+	asm volatile("vinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3b */
+
+	asm volatile("vextracti32x8 $0x12,%zmm29,%ymm30{%k7}");
+	asm volatile("vextracti64x4 $0x12,%zmm26,%ymm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3e */
+
+	asm volatile("vpcmpub $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpuw $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 3f */
+
+	asm volatile("vpcmpb $0x12,%zmm29,%zmm30,%k5");
+	asm volatile("vpcmpw $0x12,%zmm26,%zmm27,%k5");
+
+	/* AVX-512: Op code 0f 3a 43 */
+
+	asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2");
+	asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 43 */
+
+	asm volatile("vshufi32x4 $0x12,%zmm25,%zmm26,%zmm27");
+	asm volatile("vshufi64x2 $0x12,%zmm28,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 50 */
+
+	asm volatile("vrangeps $0x12,%zmm25,%zmm26,%zmm27");
+	asm volatile("vrangepd $0x12,%zmm28,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 51 */
+
+	asm volatile("vrangess $0x12,%xmm25,%xmm26,%xmm27");
+	asm volatile("vrangesd $0x12,%xmm28,%xmm29,%xmm30");
+
+	/* AVX-512: Op code 0f 3a 54 */
+
+	asm volatile("vfixupimmps $0x12,%zmm28,%zmm29,%zmm30");
+	asm volatile("vfixupimmpd $0x12,%zmm25,%zmm26,%zmm27");
+
+	/* AVX-512: Op code 0f 3a 55 */
+
+	asm volatile("vfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}");
+	asm volatile("vfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}");
+
+	/* AVX-512: Op code 0f 3a 56 */
+
+	asm volatile("vreduceps $0x12,%zmm26,%zmm27");
+	asm volatile("vreducepd $0x12,%zmm29,%zmm30");
+
+	/* AVX-512: Op code 0f 3a 57 */
+
+	asm volatile("vreducess $0x12,%xmm25,%xmm26,%xmm27");
+	asm volatile("vreducesd $0x12,%xmm28,%xmm29,%xmm30");
+
+	/* AVX-512: Op code 0f 3a 66 */
+
+	asm volatile("vfpclassps $0x12,%zmm27,%k5");
+	asm volatile("vfpclasspd $0x12,%zmm30,%k5");
+
+	/* AVX-512: Op code 0f 3a 67 */
+
+	asm volatile("vfpclassss $0x12,%xmm27,%k5");
+	asm volatile("vfpclasssd $0x12,%xmm30,%k5");
+
+	/* AVX-512: Op code 0f 72 (Grp13) */
+
+	asm volatile("vprord $0x12,%zmm25,%zmm26");
+	asm volatile("vprorq $0x12,%zmm25,%zmm26");
+	asm volatile("vprold $0x12,%zmm29,%zmm30");
+	asm volatile("vprolq $0x12,%zmm29,%zmm30");
+	asm volatile("psrad  $0x2,%mm6");
+	asm volatile("vpsrad $0x5,%ymm6,%ymm2");
+	asm volatile("vpsrad $0x5,%zmm26,%zmm22");
+	asm volatile("vpsraq $0x5,%zmm26,%zmm22");
+
+	/* AVX-512: Op code 0f 38 c6 (Grp18) */
+
+	asm volatile("vgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}");
+	asm volatile("vgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}");
+	asm volatile("vscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}");
+	asm volatile("vscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 c7 (Grp19) */
+
+	asm volatile("vgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}");
+	asm volatile("vscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}");
+
+	/* AVX-512: Examples */
+
+	asm volatile("vaddpd %zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}");
+	asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}{z}");
+	asm volatile("vaddpd {rn-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd {ru-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd {rd-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd {rz-sae},%zmm28,%zmm29,%zmm30");
+	asm volatile("vaddpd (%rcx),%zmm29,%zmm30");
+	asm volatile("vaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30");
+	asm volatile("vaddpd (%rcx){1to8},%zmm29,%zmm30");
+	asm volatile("vaddpd 0x1fc0(%rdx),%zmm29,%zmm30");
+	asm volatile("vaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30");
+	asm volatile("vcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5");
+	asm volatile("vcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}");
+	asm volatile("vcmplesd {sae},%xmm28,%xmm29,%k5{%k7}");
+	asm volatile("vgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}");
+
 	/* bndmk m64, bnd */
 
 	asm volatile("bndmk (%rax), %bnd0");
@@ -471,6 +1345,921 @@ int main(void)
 
 #else  /* #ifdef __x86_64__ */
 
+	/* bound r32, mem (same op code as EVEX prefix) */
+
+	asm volatile("bound %eax, 0x12345678(%ecx)");
+	asm volatile("bound %ecx, 0x12345678(%eax)");
+	asm volatile("bound %edx, 0x12345678(%eax)");
+	asm volatile("bound %ebx, 0x12345678(%eax)");
+	asm volatile("bound %esp, 0x12345678(%eax)");
+	asm volatile("bound %ebp, 0x12345678(%eax)");
+	asm volatile("bound %esi, 0x12345678(%eax)");
+	asm volatile("bound %edi, 0x12345678(%eax)");
+	asm volatile("bound %ecx, (%eax)");
+	asm volatile("bound %eax, (0x12345678)");
+	asm volatile("bound %edx, (%ecx,%eax,1)");
+	asm volatile("bound %edx, 0x12345678(,%eax,1)");
+	asm volatile("bound %edx, (%eax,%ecx,1)");
+	asm volatile("bound %edx, (%eax,%ecx,8)");
+	asm volatile("bound %edx, 0x12(%eax)");
+	asm volatile("bound %edx, 0x12(%ebp)");
+	asm volatile("bound %edx, 0x12(%ecx,%eax,1)");
+	asm volatile("bound %edx, 0x12(%ebp,%eax,1)");
+	asm volatile("bound %edx, 0x12(%eax,%ecx,1)");
+	asm volatile("bound %edx, 0x12(%eax,%ecx,8)");
+	asm volatile("bound %edx, 0x12345678(%eax)");
+	asm volatile("bound %edx, 0x12345678(%ebp)");
+	asm volatile("bound %edx, 0x12345678(%ecx,%eax,1)");
+	asm volatile("bound %edx, 0x12345678(%ebp,%eax,1)");
+	asm volatile("bound %edx, 0x12345678(%eax,%ecx,1)");
+	asm volatile("bound %edx, 0x12345678(%eax,%ecx,8)");
+
+	/* bound r16, mem (same op code as EVEX prefix) */
+
+	asm volatile("bound %ax, 0x12345678(%ecx)");
+	asm volatile("bound %cx, 0x12345678(%eax)");
+	asm volatile("bound %dx, 0x12345678(%eax)");
+	asm volatile("bound %bx, 0x12345678(%eax)");
+	asm volatile("bound %sp, 0x12345678(%eax)");
+	asm volatile("bound %bp, 0x12345678(%eax)");
+	asm volatile("bound %si, 0x12345678(%eax)");
+	asm volatile("bound %di, 0x12345678(%eax)");
+	asm volatile("bound %cx, (%eax)");
+	asm volatile("bound %ax, (0x12345678)");
+	asm volatile("bound %dx, (%ecx,%eax,1)");
+	asm volatile("bound %dx, 0x12345678(,%eax,1)");
+	asm volatile("bound %dx, (%eax,%ecx,1)");
+	asm volatile("bound %dx, (%eax,%ecx,8)");
+	asm volatile("bound %dx, 0x12(%eax)");
+	asm volatile("bound %dx, 0x12(%ebp)");
+	asm volatile("bound %dx, 0x12(%ecx,%eax,1)");
+	asm volatile("bound %dx, 0x12(%ebp,%eax,1)");
+	asm volatile("bound %dx, 0x12(%eax,%ecx,1)");
+	asm volatile("bound %dx, 0x12(%eax,%ecx,8)");
+	asm volatile("bound %dx, 0x12345678(%eax)");
+	asm volatile("bound %dx, 0x12345678(%ebp)");
+	asm volatile("bound %dx, 0x12345678(%ecx,%eax,1)");
+	asm volatile("bound %dx, 0x12345678(%ebp,%eax,1)");
+	asm volatile("bound %dx, 0x12345678(%eax,%ecx,1)");
+	asm volatile("bound %dx, 0x12345678(%eax,%ecx,8)");
+
+	/* AVX-512: Instructions with the same op codes as Mask Instructions  */
+
+	asm volatile("cmovno %eax,%ebx");
+	asm volatile("cmovno 0x12345678(%eax),%ecx");
+	asm volatile("cmovno 0x12345678(%eax),%cx");
+
+	asm volatile("cmove  %eax,%ebx");
+	asm volatile("cmove 0x12345678(%eax),%ecx");
+	asm volatile("cmove 0x12345678(%eax),%cx");
+
+	asm volatile("seto    0x12345678(%eax)");
+	asm volatile("setno   0x12345678(%eax)");
+	asm volatile("setb    0x12345678(%eax)");
+	asm volatile("setc    0x12345678(%eax)");
+	asm volatile("setnae  0x12345678(%eax)");
+	asm volatile("setae   0x12345678(%eax)");
+	asm volatile("setnb   0x12345678(%eax)");
+	asm volatile("setnc   0x12345678(%eax)");
+	asm volatile("sets    0x12345678(%eax)");
+	asm volatile("setns   0x12345678(%eax)");
+
+	/* AVX-512: Mask Instructions */
+
+	asm volatile("kandw  %k7,%k6,%k5");
+	asm volatile("kandq  %k7,%k6,%k5");
+	asm volatile("kandb  %k7,%k6,%k5");
+	asm volatile("kandd  %k7,%k6,%k5");
+
+	asm volatile("kandnw  %k7,%k6,%k5");
+	asm volatile("kandnq  %k7,%k6,%k5");
+	asm volatile("kandnb  %k7,%k6,%k5");
+	asm volatile("kandnd  %k7,%k6,%k5");
+
+	asm volatile("knotw  %k7,%k6");
+	asm volatile("knotq  %k7,%k6");
+	asm volatile("knotb  %k7,%k6");
+	asm volatile("knotd  %k7,%k6");
+
+	asm volatile("korw  %k7,%k6,%k5");
+	asm volatile("korq  %k7,%k6,%k5");
+	asm volatile("korb  %k7,%k6,%k5");
+	asm volatile("kord  %k7,%k6,%k5");
+
+	asm volatile("kxnorw  %k7,%k6,%k5");
+	asm volatile("kxnorq  %k7,%k6,%k5");
+	asm volatile("kxnorb  %k7,%k6,%k5");
+	asm volatile("kxnord  %k7,%k6,%k5");
+
+	asm volatile("kxorw  %k7,%k6,%k5");
+	asm volatile("kxorq  %k7,%k6,%k5");
+	asm volatile("kxorb  %k7,%k6,%k5");
+	asm volatile("kxord  %k7,%k6,%k5");
+
+	asm volatile("kaddw  %k7,%k6,%k5");
+	asm volatile("kaddq  %k7,%k6,%k5");
+	asm volatile("kaddb  %k7,%k6,%k5");
+	asm volatile("kaddd  %k7,%k6,%k5");
+
+	asm volatile("kunpckbw %k7,%k6,%k5");
+	asm volatile("kunpckwd %k7,%k6,%k5");
+	asm volatile("kunpckdq %k7,%k6,%k5");
+
+	asm volatile("kmovw  %k6,%k5");
+	asm volatile("kmovw  (%ecx),%k5");
+	asm volatile("kmovw  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovw  %k5,(%ecx)");
+	asm volatile("kmovw  %k5,0x123(%eax,%ecx,8)");
+	asm volatile("kmovw  %eax,%k5");
+	asm volatile("kmovw  %ebp,%k5");
+	asm volatile("kmovw  %k5,%eax");
+	asm volatile("kmovw  %k5,%ebp");
+
+	asm volatile("kmovq  %k6,%k5");
+	asm volatile("kmovq  (%ecx),%k5");
+	asm volatile("kmovq  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovq  %k5,(%ecx)");
+	asm volatile("kmovq  %k5,0x123(%eax,%ecx,8)");
+
+	asm volatile("kmovb  %k6,%k5");
+	asm volatile("kmovb  (%ecx),%k5");
+	asm volatile("kmovb  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovb  %k5,(%ecx)");
+	asm volatile("kmovb  %k5,0x123(%eax,%ecx,8)");
+	asm volatile("kmovb  %eax,%k5");
+	asm volatile("kmovb  %ebp,%k5");
+	asm volatile("kmovb  %k5,%eax");
+	asm volatile("kmovb  %k5,%ebp");
+
+	asm volatile("kmovd  %k6,%k5");
+	asm volatile("kmovd  (%ecx),%k5");
+	asm volatile("kmovd  0x123(%eax,%ecx,8),%k5");
+	asm volatile("kmovd  %k5,(%ecx)");
+	asm volatile("kmovd  %k5,0x123(%eax,%ecx,8)");
+	asm volatile("kmovd  %eax,%k5");
+	asm volatile("kmovd  %ebp,%k5");
+	asm volatile("kmovd  %k5,%eax");
+	asm volatile("kmovd  %k5,%ebp");
+
+	asm volatile("kortestw %k6,%k5");
+	asm volatile("kortestq %k6,%k5");
+	asm volatile("kortestb %k6,%k5");
+	asm volatile("kortestd %k6,%k5");
+
+	asm volatile("ktestw %k6,%k5");
+	asm volatile("ktestq %k6,%k5");
+	asm volatile("ktestb %k6,%k5");
+	asm volatile("ktestd %k6,%k5");
+
+	asm volatile("kshiftrw $0x12,%k6,%k5");
+	asm volatile("kshiftrq $0x5b,%k6,%k5");
+	asm volatile("kshiftlw $0x12,%k6,%k5");
+	asm volatile("kshiftlq $0x5b,%k6,%k5");
+
+	/* AVX-512: Op code 0f 5b */
+	asm volatile("vcvtdq2ps %xmm5,%xmm6");
+	asm volatile("vcvtqq2ps %zmm5,%ymm6{%k7}");
+	asm volatile("vcvtps2dq %xmm5,%xmm6");
+	asm volatile("vcvttps2dq %xmm5,%xmm6");
+
+	/* AVX-512: Op code 0f 6f */
+
+	asm volatile("movq   %mm0,%mm4");
+	asm volatile("vmovdqa %ymm4,%ymm6");
+	asm volatile("vmovdqa32 %zmm5,%zmm6");
+	asm volatile("vmovdqa64 %zmm5,%zmm6");
+	asm volatile("vmovdqu %ymm4,%ymm6");
+	asm volatile("vmovdqu32 %zmm5,%zmm6");
+	asm volatile("vmovdqu64 %zmm5,%zmm6");
+	asm volatile("vmovdqu8 %zmm5,%zmm6");
+	asm volatile("vmovdqu16 %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 78 */
+
+	asm volatile("vmread %eax,%ebx");
+	asm volatile("vcvttps2udq %zmm5,%zmm6");
+	asm volatile("vcvttpd2udq %zmm5,%ymm6{%k7}");
+	asm volatile("vcvttsd2usi %xmm6,%eax");
+	asm volatile("vcvttss2usi %xmm6,%eax");
+	asm volatile("vcvttps2uqq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvttpd2uqq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 79 */
+
+	asm volatile("vmwrite %eax,%ebx");
+	asm volatile("vcvtps2udq %zmm5,%zmm6");
+	asm volatile("vcvtpd2udq %zmm5,%ymm6{%k7}");
+	asm volatile("vcvtsd2usi %xmm6,%eax");
+	asm volatile("vcvtss2usi %xmm6,%eax");
+	asm volatile("vcvtps2uqq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtpd2uqq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 7a */
+
+	asm volatile("vcvtudq2pd %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtuqq2pd %zmm5,%zmm6");
+	asm volatile("vcvtudq2ps %zmm5,%zmm6");
+	asm volatile("vcvtuqq2ps %zmm5,%ymm6{%k7}");
+	asm volatile("vcvttps2qq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvttpd2qq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 7b */
+
+	asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6");
+	asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6");
+	asm volatile("vcvtps2qq %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtpd2qq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 7f */
+
+	asm volatile("movq.s  %mm0,%mm4");
+	asm volatile("vmovdqa.s %ymm5,%ymm6");
+	asm volatile("vmovdqa32.s %zmm5,%zmm6");
+	asm volatile("vmovdqa64.s %zmm5,%zmm6");
+	asm volatile("vmovdqu.s %ymm5,%ymm6");
+	asm volatile("vmovdqu32.s %zmm5,%zmm6");
+	asm volatile("vmovdqu64.s %zmm5,%zmm6");
+	asm volatile("vmovdqu8.s %zmm5,%zmm6");
+	asm volatile("vmovdqu16.s %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f db */
+
+	asm volatile("pand  %mm1,%mm2");
+	asm volatile("pand  %xmm1,%xmm2");
+	asm volatile("vpand  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpandq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f df */
+
+	asm volatile("pandn  %mm1,%mm2");
+	asm volatile("pandn  %xmm1,%xmm2");
+	asm volatile("vpandn %ymm4,%ymm6,%ymm2");
+	asm volatile("vpandnd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpandnq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f e6 */
+
+	asm volatile("vcvttpd2dq %xmm1,%xmm2");
+	asm volatile("vcvtdq2pd %xmm5,%xmm6");
+	asm volatile("vcvtdq2pd %ymm5,%zmm6{%k7}");
+	asm volatile("vcvtqq2pd %zmm5,%zmm6");
+	asm volatile("vcvtpd2dq %xmm1,%xmm2");
+
+	/* AVX-512: Op code 0f eb */
+
+	asm volatile("por   %mm4,%mm6");
+	asm volatile("vpor   %ymm4,%ymm6,%ymm2");
+	asm volatile("vpord  %zmm4,%zmm5,%zmm6");
+	asm volatile("vporq  %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f ef */
+
+	asm volatile("pxor   %mm4,%mm6");
+	asm volatile("vpxor  %ymm4,%ymm6,%ymm2");
+	asm volatile("vpxord %zmm4,%zmm5,%zmm6");
+	asm volatile("vpxorq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 10 */
+
+	asm volatile("pblendvb %xmm1,%xmm0");
+	asm volatile("vpsrlvw %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmovuswb %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 11 */
+
+	asm volatile("vpmovusdb %zmm5,%xmm6{%k7}");
+	asm volatile("vpsravw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 12 */
+
+	asm volatile("vpmovusqb %zmm5,%xmm6{%k7}");
+	asm volatile("vpsllvw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 13 */
+
+	asm volatile("vcvtph2ps %xmm3,%ymm5");
+	asm volatile("vcvtph2ps %ymm5,%zmm6{%k7}");
+	asm volatile("vpmovusdw %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 14 */
+
+	asm volatile("blendvps %xmm1,%xmm0");
+	asm volatile("vpmovusqw %zmm5,%xmm6{%k7}");
+	asm volatile("vprorvd %zmm4,%zmm5,%zmm6");
+	asm volatile("vprorvq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 15 */
+
+	asm volatile("blendvpd %xmm1,%xmm0");
+	asm volatile("vpmovusqd %zmm5,%ymm6{%k7}");
+	asm volatile("vprolvd %zmm4,%zmm5,%zmm6");
+	asm volatile("vprolvq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 16 */
+
+	asm volatile("vpermps %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermps %ymm4,%ymm6,%ymm2{%k7}");
+	asm volatile("vpermpd %ymm4,%ymm6,%ymm2{%k7}");
+
+	/* AVX-512: Op code 0f 38 19 */
+
+	asm volatile("vbroadcastsd %xmm4,%ymm6");
+	asm volatile("vbroadcastf32x2 %xmm7,%zmm6");
+
+	/* AVX-512: Op code 0f 38 1a */
+
+	asm volatile("vbroadcastf128 (%ecx),%ymm4");
+	asm volatile("vbroadcastf32x4 (%ecx),%zmm6");
+	asm volatile("vbroadcastf64x2 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 1b */
+
+	asm volatile("vbroadcastf32x8 (%ecx),%zmm6");
+	asm volatile("vbroadcastf64x4 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 1f */
+
+	asm volatile("vpabsq %zmm4,%zmm6");
+
+	/* AVX-512: Op code 0f 38 20 */
+
+	asm volatile("vpmovsxbw %xmm4,%xmm5");
+	asm volatile("vpmovswb %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 21 */
+
+	asm volatile("vpmovsxbd %xmm4,%ymm6");
+	asm volatile("vpmovsdb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 22 */
+
+	asm volatile("vpmovsxbq %xmm4,%ymm4");
+	asm volatile("vpmovsqb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 23 */
+
+	asm volatile("vpmovsxwd %xmm4,%ymm4");
+	asm volatile("vpmovsdw %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 24 */
+
+	asm volatile("vpmovsxwq %xmm4,%ymm6");
+	asm volatile("vpmovsqw %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 25 */
+
+	asm volatile("vpmovsxdq %xmm4,%ymm4");
+	asm volatile("vpmovsqd %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 26 */
+
+	asm volatile("vptestmb %zmm5,%zmm6,%k5");
+	asm volatile("vptestmw %zmm5,%zmm6,%k5");
+	asm volatile("vptestnmb %zmm4,%zmm5,%k5");
+	asm volatile("vptestnmw %zmm4,%zmm5,%k5");
+
+	/* AVX-512: Op code 0f 38 27 */
+
+	asm volatile("vptestmd %zmm5,%zmm6,%k5");
+	asm volatile("vptestmq %zmm5,%zmm6,%k5");
+	asm volatile("vptestnmd %zmm4,%zmm5,%k5");
+	asm volatile("vptestnmq %zmm4,%zmm5,%k5");
+
+	/* AVX-512: Op code 0f 38 28 */
+
+	asm volatile("vpmuldq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2b %k5,%zmm6");
+	asm volatile("vpmovm2w %k5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 29 */
+
+	asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovb2m %zmm6,%k5");
+	asm volatile("vpmovw2m %zmm6,%k5");
+
+	/* AVX-512: Op code 0f 38 2a */
+
+	asm volatile("vmovntdqa (%ecx),%ymm4");
+	asm volatile("vpbroadcastmb2q %k6,%zmm1");
+
+	/* AVX-512: Op code 0f 38 2c */
+
+	asm volatile("vmaskmovps (%ecx),%ymm4,%ymm6");
+	asm volatile("vscalefps %zmm4,%zmm5,%zmm6");
+	asm volatile("vscalefpd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 2d */
+
+	asm volatile("vmaskmovpd (%ecx),%ymm4,%ymm6");
+	asm volatile("vscalefss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vscalefsd %xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 30 */
+
+	asm volatile("vpmovzxbw %xmm4,%ymm4");
+	asm volatile("vpmovwb %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 31 */
+
+	asm volatile("vpmovzxbd %xmm4,%ymm6");
+	asm volatile("vpmovdb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 32 */
+
+	asm volatile("vpmovzxbq %xmm4,%ymm4");
+	asm volatile("vpmovqb %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 33 */
+
+	asm volatile("vpmovzxwd %xmm4,%ymm4");
+	asm volatile("vpmovdw %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 34 */
+
+	asm volatile("vpmovzxwq %xmm4,%ymm6");
+	asm volatile("vpmovqw %zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 35 */
+
+	asm volatile("vpmovzxdq %xmm4,%ymm4");
+	asm volatile("vpmovqd %zmm5,%ymm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 36 */
+
+	asm volatile("vpermd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpermd %ymm4,%ymm6,%ymm2{%k7}");
+	asm volatile("vpermq %ymm4,%ymm6,%ymm2{%k7}");
+
+	/* AVX-512: Op code 0f 38 38 */
+
+	asm volatile("vpminsb %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmovm2d %k5,%zmm6");
+	asm volatile("vpmovm2q %k5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 39 */
+
+	asm volatile("vpminsd %xmm1,%xmm2,%xmm3");
+	asm volatile("vpminsd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpminsq %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmovd2m %zmm6,%k5");
+	asm volatile("vpmovq2m %zmm6,%k5");
+
+	/* AVX-512: Op code 0f 38 3a */
+
+	asm volatile("vpminuw %ymm4,%ymm6,%ymm2");
+	asm volatile("vpbroadcastmw2d %k6,%zmm6");
+
+	/* AVX-512: Op code 0f 38 3b */
+
+	asm volatile("vpminud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpminud %zmm4,%zmm5,%zmm6");
+	asm volatile("vpminuq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 3d */
+
+	asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxsd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmaxsq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 3f */
+
+	asm volatile("vpmaxud %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmaxud %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmaxuq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 40 */
+
+	asm volatile("vpmulld %ymm4,%ymm6,%ymm2");
+	asm volatile("vpmulld %zmm4,%zmm5,%zmm6");
+	asm volatile("vpmullq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 42 */
+
+	asm volatile("vgetexpps %zmm5,%zmm6");
+	asm volatile("vgetexppd %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 43 */
+
+	asm volatile("vgetexpss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vgetexpsd %xmm2,%xmm3,%xmm4{%k7}");
+
+	/* AVX-512: Op code 0f 38 44 */
+
+	asm volatile("vplzcntd %zmm5,%zmm6");
+	asm volatile("vplzcntq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 46 */
+
+	asm volatile("vpsravd %ymm4,%ymm6,%ymm2");
+	asm volatile("vpsravd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpsravq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 4c */
+
+	asm volatile("vrcp14ps %zmm5,%zmm6");
+	asm volatile("vrcp14pd %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 4d */
+
+	asm volatile("vrcp14ss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vrcp14sd %xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 4e */
+
+	asm volatile("vrsqrt14ps %zmm5,%zmm6");
+	asm volatile("vrsqrt14pd %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 4f */
+
+	asm volatile("vrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}");
+	asm volatile("vrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 38 59 */
+
+	asm volatile("vpbroadcastq %xmm4,%xmm6");
+	asm volatile("vbroadcasti32x2 %xmm7,%zmm6");
+
+	/* AVX-512: Op code 0f 38 5a */
+
+	asm volatile("vbroadcasti128 (%ecx),%ymm4");
+	asm volatile("vbroadcasti32x4 (%ecx),%zmm6");
+	asm volatile("vbroadcasti64x2 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 5b */
+
+	asm volatile("vbroadcasti32x8 (%ecx),%zmm6");
+	asm volatile("vbroadcasti64x4 (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 64 */
+
+	asm volatile("vpblendmd %zmm4,%zmm5,%zmm6");
+	asm volatile("vpblendmq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 65 */
+
+	asm volatile("vblendmps %zmm4,%zmm5,%zmm6");
+	asm volatile("vblendmpd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 66 */
+
+	asm volatile("vpblendmb %zmm4,%zmm5,%zmm6");
+	asm volatile("vpblendmw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 75 */
+
+	asm volatile("vpermi2b %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermi2w %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 76 */
+
+	asm volatile("vpermi2d %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermi2q %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 77 */
+
+	asm volatile("vpermi2ps %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermi2pd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 7a */
+
+	asm volatile("vpbroadcastb %eax,%xmm3");
+
+	/* AVX-512: Op code 0f 38 7b */
+
+	asm volatile("vpbroadcastw %eax,%xmm3");
+
+	/* AVX-512: Op code 0f 38 7c */
+
+	asm volatile("vpbroadcastd %eax,%xmm3");
+
+	/* AVX-512: Op code 0f 38 7d */
+
+	asm volatile("vpermt2b %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermt2w %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 7e */
+
+	asm volatile("vpermt2d %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermt2q %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 7f */
+
+	asm volatile("vpermt2ps %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermt2pd %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 83 */
+
+	asm volatile("vpmultishiftqb %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 88 */
+
+	asm volatile("vexpandps (%ecx),%zmm6");
+	asm volatile("vexpandpd (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 89 */
+
+	asm volatile("vpexpandd (%ecx),%zmm6");
+	asm volatile("vpexpandq (%ecx),%zmm6");
+
+	/* AVX-512: Op code 0f 38 8a */
+
+	asm volatile("vcompressps %zmm6,(%ecx)");
+	asm volatile("vcompresspd %zmm6,(%ecx)");
+
+	/* AVX-512: Op code 0f 38 8b */
+
+	asm volatile("vpcompressd %zmm6,(%ecx)");
+	asm volatile("vpcompressq %zmm6,(%ecx)");
+
+	/* AVX-512: Op code 0f 38 8d */
+
+	asm volatile("vpermb %zmm4,%zmm5,%zmm6");
+	asm volatile("vpermw %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 90 */
+
+	asm volatile("vpgatherdd %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdq %xmm2,0x04(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}");
+	asm volatile("vpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}");
+
+	/* AVX-512: Op code 0f 38 91 */
+
+	asm volatile("vpgatherqd %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqq %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+	asm volatile("vpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}");
+	asm volatile("vpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}");
+
+	/* AVX-512: Op code 0f 38 a0 */
+
+	asm volatile("vpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a1 */
+
+	asm volatile("vpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a2 */
+
+	asm volatile("vscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 a3 */
+
+	asm volatile("vscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 b4 */
+
+	asm volatile("vpmadd52luq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 b5 */
+
+	asm volatile("vpmadd52huq %zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 c4 */
+
+	asm volatile("vpconflictd %zmm5,%zmm6");
+	asm volatile("vpconflictq %zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 38 c8 */
+
+	asm volatile("vexp2ps %zmm6,%zmm7");
+	asm volatile("vexp2pd %zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 38 ca */
+
+	asm volatile("vrcp28ps %zmm6,%zmm7");
+	asm volatile("vrcp28pd %zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 38 cb */
+
+	asm volatile("vrcp28ss %xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vrcp28sd %xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 38 cc */
+
+	asm volatile("vrsqrt28ps %zmm6,%zmm7");
+	asm volatile("vrsqrt28pd %zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 38 cd */
+
+	asm volatile("vrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 03 */
+
+	asm volatile("valignd $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("valignq $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 08 */
+
+	asm volatile("vroundps $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscaleps $0x12,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 09 */
+
+	asm volatile("vroundpd $0x5,%ymm6,%ymm2");
+	asm volatile("vrndscalepd $0x12,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 0a */
+
+	asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 0b */
+
+	asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2");
+	asm volatile("vrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 18 */
+
+	asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+	asm volatile("vinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 19 */
+
+	asm volatile("vextractf128 $0x5,%ymm4,%xmm4");
+	asm volatile("vextractf32x4 $0x12,%zmm5,%xmm6{%k7}");
+	asm volatile("vextractf64x2 $0x12,%zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1a */
+
+	asm volatile("vinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+	asm volatile("vinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1b */
+
+	asm volatile("vextractf32x8 $0x12,%zmm6,%ymm7{%k7}");
+	asm volatile("vextractf64x4 $0x12,%zmm6,%ymm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 1e */
+
+	asm volatile("vpcmpud $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpuq $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 1f */
+
+	asm volatile("vpcmpd $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpq $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 23 */
+
+	asm volatile("vshuff32x4 $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vshuff64x2 $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 25 */
+
+	asm volatile("vpternlogd $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vpternlogq $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 26 */
+
+	asm volatile("vgetmantps $0x12,%zmm6,%zmm7");
+	asm volatile("vgetmantpd $0x12,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 27 */
+
+	asm volatile("vgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 38 */
+
+	asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6");
+	asm volatile("vinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+	asm volatile("vinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 39 */
+
+	asm volatile("vextracti128 $0x5,%ymm4,%xmm6");
+	asm volatile("vextracti32x4 $0x12,%zmm5,%xmm6{%k7}");
+	asm volatile("vextracti64x2 $0x12,%zmm5,%xmm6{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3a */
+
+	asm volatile("vinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+	asm volatile("vinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3b */
+
+	asm volatile("vextracti32x8 $0x12,%zmm6,%ymm7{%k7}");
+	asm volatile("vextracti64x4 $0x12,%zmm6,%ymm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 3e */
+
+	asm volatile("vpcmpub $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpuw $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 3f */
+
+	asm volatile("vpcmpb $0x12,%zmm6,%zmm7,%k5");
+	asm volatile("vpcmpw $0x12,%zmm6,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 42 */
+
+	asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2");
+	asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6");
+
+	/* AVX-512: Op code 0f 3a 43 */
+
+	asm volatile("vshufi32x4 $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vshufi64x2 $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 50 */
+
+	asm volatile("vrangeps $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vrangepd $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 51 */
+
+	asm volatile("vrangess $0x12,%xmm5,%xmm6,%xmm7");
+	asm volatile("vrangesd $0x12,%xmm5,%xmm6,%xmm7");
+
+	/* AVX-512: Op code 0f 3a 54 */
+
+	asm volatile("vfixupimmps $0x12,%zmm5,%zmm6,%zmm7");
+	asm volatile("vfixupimmpd $0x12,%zmm5,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 55 */
+
+	asm volatile("vfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+	asm volatile("vfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+
+	/* AVX-512: Op code 0f 3a 56 */
+
+	asm volatile("vreduceps $0x12,%zmm6,%zmm7");
+	asm volatile("vreducepd $0x12,%zmm6,%zmm7");
+
+	/* AVX-512: Op code 0f 3a 57 */
+
+	asm volatile("vreducess $0x12,%xmm5,%xmm6,%xmm7");
+	asm volatile("vreducesd $0x12,%xmm5,%xmm6,%xmm7");
+
+	/* AVX-512: Op code 0f 3a 66 */
+
+	asm volatile("vfpclassps $0x12,%zmm7,%k5");
+	asm volatile("vfpclasspd $0x12,%zmm7,%k5");
+
+	/* AVX-512: Op code 0f 3a 67 */
+
+	asm volatile("vfpclassss $0x12,%xmm7,%k5");
+	asm volatile("vfpclasssd $0x12,%xmm7,%k5");
+
+	/* AVX-512: Op code 0f 72 (Grp13) */
+
+	asm volatile("vprord $0x12,%zmm5,%zmm6");
+	asm volatile("vprorq $0x12,%zmm5,%zmm6");
+	asm volatile("vprold $0x12,%zmm5,%zmm6");
+	asm volatile("vprolq $0x12,%zmm5,%zmm6");
+	asm volatile("psrad  $0x2,%mm6");
+	asm volatile("vpsrad $0x5,%ymm6,%ymm2");
+	asm volatile("vpsrad $0x5,%zmm6,%zmm2");
+	asm volatile("vpsraq $0x5,%zmm6,%zmm2");
+
+	/* AVX-512: Op code 0f 38 c6 (Grp18) */
+
+	asm volatile("vgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}");
+	asm volatile("vgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}");
+	asm volatile("vscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}");
+	asm volatile("vscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}");
+
+	/* AVX-512: Op code 0f 38 c7 (Grp19) */
+
+	asm volatile("vgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}");
+	asm volatile("vscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}");
+
+	/* AVX-512: Examples */
+
+	asm volatile("vaddpd %zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}");
+	asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}{z}");
+	asm volatile("vaddpd {rn-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd {ru-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd {rd-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd {rz-sae},%zmm4,%zmm5,%zmm6");
+	asm volatile("vaddpd (%ecx),%zmm5,%zmm6");
+	asm volatile("vaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6");
+	asm volatile("vaddpd (%ecx){1to8},%zmm5,%zmm6");
+	asm volatile("vaddpd 0x1fc0(%edx),%zmm5,%zmm6");
+	asm volatile("vaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6");
+	asm volatile("vcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5");
+	asm volatile("vcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}");
+	asm volatile("vcmplesd {sae},%xmm4,%xmm5,%k5{%k7}");
+	asm volatile("vgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}");
+
 	/* bndmk m32, bnd */
 
 	asm volatile("bndmk (%eax), %bnd0");
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index d2af78193153..76f41f249944 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -1,4 +1,5 @@
 #include <stdbool.h>
+#include <stdlib.h>
 #include "tests.h"
 #include "dso.h"
 #include "debug.h"
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b32464b353aa..8d363d5e65a2 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -8,7 +8,6 @@
 #include "map.h"
 #include "build-id.h"
 #include "perf_regs.h"
-#include <asm/perf_regs.h>
 
 struct mmap_event {
 	struct perf_event_header header;
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
index 517567347aac..54e961659514 100644
--- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
+++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
@@ -72,12 +72,14 @@ BEGIN {
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
-	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
 	# accepts VEX prefix
-	vexok_opcode_expr = "^v.*"
+	vexok_opcode_expr = "^[vk].*"
 	vexok_expr = "\\(v1\\)"
 	# All opcodes with (v) superscript supports *only* VEX prefix
 	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
 	clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			flags = add_flags(flags, "INAT_MODRM")
 
 		# check VEX codes
-		if (match(ext, vexonly_expr))
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
 			flags = add_flags(flags, "INAT_VEXOK")
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 611645e903a8..125ecd2a300d 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -89,6 +90,7 @@
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
 	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)
@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-	return attr & INAT_VEXONLY;
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
 }
 #endif
diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c
index 9f26eae6c9f0..ca983e2bea8b 100644
--- a/tools/perf/util/intel-pt-decoder/insn.c
+++ b/tools/perf/util/intel-pt-decoder/insn.c
@@ -155,14 +155,24 @@ found:
 			/*
 			 * In 32-bits mode, if the [7:6] bits (mod bits of
 			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES.
+			 * LDS or LES or BOUND.
 			 */
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
 		insn->vex_prefix.bytes[0] = b;
 		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_vex3_prefix(attr)) {
+		if (inat_is_evex_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+			insn->vex_prefix.bytes[3] = b2;
+			insn->vex_prefix.nbytes = 4;
+			insn->next_byte += 4;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else if (inat_is_vex3_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
 			insn->vex_prefix.bytes[2] = b2;
 			insn->vex_prefix.nbytes = 3;
@@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn)
 		m = insn_vex_m_bits(insn);
 		p = insn_vex_p_bits(insn);
 		insn->attr = inat_get_avx_attribute(op, m, p);
-		if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+		    (!inat_accept_vex(insn->attr) &&
+		     !inat_is_group(insn->attr)))
 			insn->attr = 0;	/* This instruction is bad */
 		goto end;	/* VEX has only 1 byte for opcode */
 	}
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
index dd12da0f4593..e23578c7b1be 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/perf/util/intel-pt-decoder/insn.h
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
 #define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
 #define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
 #define X86_VEX2_M	1			/* VEX2.M always 1 */
 #define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
 	return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
 		return X86_VEX2_M;
-	else
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
 		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index d388de72eaca..ec378cd7b71e 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -13,12 +13,17 @@
 # opcode: escape # escaped-name
 # EndTable
 #
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
 #<group maps>
 # GrpTable: GrpXXX
 # reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
 # EndTable
 #
 # AVX Superscripts
+#  (ev): this opcode requires EVEX prefix.
+#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
 #  (v): this opcode requires VEX prefix.
 #  (v1): this opcode only supports 128bit VEX.
 #
@@ -137,7 +142,7 @@ AVXcode:
 # 0x60 - 0x6f
 60: PUSHA/PUSHAD (i64)
 61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
 64: SEG=FS (Prefix)
 65: SEG=GS (Prefix)
@@ -399,17 +404,17 @@ AVXcode: 1
 3f:
 # 0x0f 0x40-0x4f
 40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev
-42: CMOVB/C/NAE Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
 43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev
-45: CMOVNE/NZ Gv,Ev
-46: CMOVBE/NA Gv,Ev
-47: CMOVA/NBE Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
 48: CMOVS Gv,Ev
 49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev
-4b: CMOVNP/PO Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
 4c: CMOVL/NGE Gv,Ev
 4d: CMOVNL/GE Gv,Ev
 4e: CMOVLE/NG Gv,Ev
@@ -426,7 +431,7 @@ AVXcode: 1
 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
@@ -447,7 +452,7 @@ AVXcode: 1
 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
 # 0x0f 0x70-0x7f
 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
 71: Grp12 (1A)
@@ -458,14 +463,14 @@ AVXcode: 1
 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
 # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
 77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy
-79: VMWRITE Gy,Ey
-7a:
-7b:
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
 80: JO Jz (f64)
@@ -485,16 +490,16 @@ AVXcode: 1
 8e: JLE/JNG Jz (f64)
 8f: JNLE/JG Jz (f64)
 # 0x0f 0x90-0x9f
-90: SETO Eb
-91: SETNO Eb
-92: SETB/C/NAE Eb
-93: SETAE/NB/NC Eb
+90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
+91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
 94: SETE/Z Eb
 95: SETNE/NZ Eb
 96: SETBE/NA Eb
 97: SETA/NBE Eb
-98: SETS Eb
-99: SETNS Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
 9a: SETP/PE Eb
 9b: SETNP/PO Eb
 9c: SETL/NGE Eb
@@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
 d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
 d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
 da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
 dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
 dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
 de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xe0-0xef
 e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
 e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
@@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
 e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
 e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
 e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
 e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
 e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
 e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
 ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
 ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
 ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
 ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xf0-0xff
 f0: vlddqu Vx,Mx (F2)
 f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
@@ -626,81 +631,105 @@ AVXcode: 2
 0e: vtestps Vx,Wx (66),(v)
 0f: vtestpd Vx,Wx (66),(v)
 # 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66)
-11:
-12:
-13: vcvtph2ps Vx,Wx,Ib (66),(v)
-14: blendvps Vdq,Wdq (66)
-15: blendvpd Vdq,Wdq (66)
-16: vpermps Vqq,Hqq,Wqq (66),(v)
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
 17: vptest Vx,Wx (66)
 18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v)
-1a: vbroadcastf128 Vqq,Mdq (66),(v)
-1b:
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f:
+1f: vpabsq Vx,Wx (66),(ev)
 # 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1)
-21: vpmovsxbd Vx,Ux/Md (66),(v1)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1)
-24: vpmovsxwq Vx,Ux/Md (66),(v1)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1)
-26:
-27:
-28: vpmuldq Vx,Hx,Wx (66),(v1)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1)
-2a: vmovntdqa Vx,Mx (66),(v1)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
 2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
 2e: vmaskmovps Mx,Hx,Vx (66),(v)
 2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1)
-31: vpmovzxbd Vx,Ux/Md (66),(v1)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1)
-34: vpmovzxwq Vx,Ux/Md (66),(v1)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1)
-36: vpermd Vqq,Hqq,Wqq (66),(v)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
 37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1)
-39: vpminsd Vx,Hx,Wx (66),(v1)
-3a: vpminuw Vx,Hx,Wx (66),(v1)
-3b: vpminud Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
 3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
 3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1)
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
 41: vphminposuw Vdq,Wdq (66),(v1)
-42:
-43:
-44:
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
 45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
 47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x57
+# Skip 0x48-0x4b
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+# Skip 0x50-0x57
 58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v)
-5a: vbroadcasti128 Vqq,Mdq (66),(v)
-# Skip 0x5b-0x77
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+# Skip 0x5c-0x63
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+# Skip 0x67-0x74
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
 78: vpbroadcastb Vx,Wx (66),(v)
 79: vpbroadcastw Vx,Wx (66),(v)
-# Skip 0x7a-0x7f
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
 81: INVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
 # 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v)
-91: vgatherqd/q Vx,Hx,Wx (66),(v)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
 92: vgatherdps/d Vx,Hx,Wx (66),(v)
 93: vgatherqps/d Vx,Hx,Wx (66),(v)
 94:
@@ -715,6 +744,10 @@ AVXcode: 2
 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
 a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
 a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
 a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
@@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
 af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
 b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
 b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
 b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
-c8: sha1nexte Vdq,Wdq
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
 c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq
-cb: sha256rnds2 Vdq,Wdq
-cc: sha256msg1 Vdq,Wdq
-cd: sha256msg2 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -763,15 +801,15 @@ AVXcode: 3
 00: vpermq Vqq,Wqq,Ib (66),(v)
 01: vpermpd Vqq,Wqq,Ib (66),(v)
 02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03:
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
 04: vpermilps Vx,Wx,Ib (66),(v)
 05: vpermilpd Vx,Wx,Ib (66),(v)
 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
 07:
-08: vroundps Vx,Wx,Ib (66)
-09: vroundpd Vx,Wx,Ib (66)
-0a: vroundss Vss,Wss,Ib (66),(v1)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
 0c: vblendps Vx,Hx,Wx,Ib (66)
 0d: vblendpd Vx,Hx,Wx,Ib (66)
 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
@@ -780,26 +818,51 @@ AVXcode: 3
 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
 16: vpextrd/q Ey,Vdq,Ib (66),(v1)
 17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
-19: vextractf128 Wdq,Vqq,Ib (66),(v)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
 1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
-39: vextracti128 Wdq,Vqq,Ib (66),(v)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
 40: vdpps Vx,Hx,Wx,Ib (66)
 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
 4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
@@ -927,8 +990,10 @@ GrpTable: Grp12
 EndTable
 
 GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 
@@ -963,6 +1028,20 @@ GrpTable: Grp17
 3: BLSI By,Ey (v)
 EndTable
 
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index 552af68d5414..a538ff44b108 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -54,9 +54,10 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM}
 # to something more interesting, like "arm-linux-".  If you want
 # to compile vs uClibc, that can be done here as well.
 CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
-CC = $(CROSS)gcc
-LD = $(CROSS)gcc
-STRIP = $(CROSS)strip
+CROSS_COMPILE ?= $(CROSS)
+CC = $(CROSS_COMPILE)gcc
+LD = $(CROSS_COMPILE)gcc
+STRIP = $(CROSS_COMPILE)strip
 HOSTCC = gcc
 
 # check if compiler option is supported
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index e367b1a85d70..8561e7ddca59 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,7 +1,7 @@
 CC		= $(CROSS_COMPILE)gcc
 BUILD_OUTPUT	:= $(CURDIR)
-PREFIX		:= /usr
-DESTDIR		:=
+PREFIX		?= /usr
+DESTDIR		?=
 
 ifeq ("$(origin O)", "command line")
 	BUILD_OUTPUT := $(O)
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 89a55d5e32f3..492e84fbebfa 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -123,7 +123,7 @@ cpu0: MSR_NHM_PLATFORM_INFO: 0x80838f3012300
 35 * 100 = 3500 MHz TSC frequency
 cpu0: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled)
 cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0)
-cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727
+cpu0: MSR_TURBO_RATIO_LIMIT: 0x25262727
 37 * 100 = 3700 MHz max turbo 4 active cores
 38 * 100 = 3800 MHz max turbo 3 active cores
 39 * 100 = 3900 MHz max turbo 2 active cores
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index acbf7ff2ee6e..3e199b508a96 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1480,7 +1480,7 @@ dump_knl_turbo_ratio_limits(void)
 	unsigned int cores[buckets_no];
 	unsigned int ratio[buckets_no];
 
-	get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
+	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
 
 	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n",
 		base_cpu, msr);
diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch
index e11fbd6fae78..ad85b921a607 100644
--- a/tools/scripts/Makefile.arch
+++ b/tools/scripts/Makefile.arch
@@ -1,8 +1,4 @@
-ifndef ARCH
-ARCH := $(shell uname -m 2>/dev/null || echo not)
-endif
-
-ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
+HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e s/sun4u/sparc/ -e s/sparc64/sparc/ \
                                   -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
@@ -10,6 +6,41 @@ ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
                                   -e s/tile.*/tile/ )
 
+ifndef ARCH
+ARCH := $(HOSTARCH)
+endif
+
+SRCARCH := $(ARCH)
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+        SRCARCH := x86
+endif
+ifeq ($(ARCH),x86_64)
+        SRCARCH := x86
+endif
+
+# Additional ARCH settings for sparc
+ifeq ($(ARCH),sparc32)
+       SRCARCH := sparc
+endif
+ifeq ($(ARCH),sparc64)
+       SRCARCH := sparc
+endif
+
+# Additional ARCH settings for sh
+ifeq ($(ARCH),sh64)
+       SRCARCH := sh
+endif
+
+# Additional ARCH settings for tile
+ifeq ($(ARCH),tilepro)
+       SRCARCH := tile
+endif
+ifeq ($(ARCH),tilegx)
+       SRCARCH := tile
+endif
+
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
 ifeq ($(LP64), 1)
   IS_64_BIT := 1
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 48bd520fc702..ce3d8e5be73e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -148,6 +148,7 @@ int vcpu_load(struct kvm_vcpu *vcpu)
 	put_cpu();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vcpu_load);
 
 void vcpu_put(struct kvm_vcpu *vcpu)
 {
@@ -157,6 +158,7 @@ void vcpu_put(struct kvm_vcpu *vcpu)
 	preempt_enable();
 	mutex_unlock(&vcpu->mutex);
 }
+EXPORT_SYMBOL_GPL(vcpu_put);
 
 static void ack_flush(void *_completed)
 {
@@ -3048,6 +3050,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 {
 	int r;
 	struct kvm *kvm;
+	struct file *file;
 
 	kvm = kvm_create_vm(type);
 	if (IS_ERR(kvm))
@@ -3059,17 +3062,25 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		return r;
 	}
 #endif
-	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
+	r = get_unused_fd_flags(O_CLOEXEC);
 	if (r < 0) {
 		kvm_put_kvm(kvm);
 		return r;
 	}
+	file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+	if (IS_ERR(file)) {
+		put_unused_fd(r);
+		kvm_put_kvm(kvm);
+		return PTR_ERR(file);
+	}
 
 	if (kvm_create_vm_debugfs(kvm, r) < 0) {
-		kvm_put_kvm(kvm);
+		put_unused_fd(r);
+		fput(file);
 		return -ENOMEM;
 	}
 
+	fd_install(r, file);
 	return r;
 }