Merge tag 'v4.5-rc1' into x86/asm, to refresh the branch before merging new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

CREDITS

@@ -534,6 +534,7 @@ N: NeilBrown
 E: neil@brown.name
 P: 4096R/566281B9 1BC6 29EB D390 D870 7B5F  497A 39EC 9EDD 5662 81B9
 D: NFSD Maintainer 2000-2007
+D: MD Maintainer 2001-2016
 
 N: Zach Brown
 E: zab@zabbo.net
@@ -1507,6 +1508,14 @@ S: 312/107 Canberra Avenue
 S: Griffith, ACT 2603 
 S: Australia
 
+N: Andreas Herrmann
+E: herrmann.der.user@gmail.com
+E: herrmann.der.user@googlemail.com
+D: Key developer of x86/AMD64
+D: Author of AMD family 15h processor power monitoring driver
+D: Maintainer of AMD Athlon 64 and Opteron processor frequency driver
+S: Germany
+
 N: Sebastian Hetze
 E: she@lunetix.de
 D: German Linux Documentation,
@@ -1847,6 +1856,16 @@ S: Korte Heul 95
 S: 1403 ND  BUSSUM
 S: The Netherlands
 
+N: Martin Kepplinger
+E: martink@posteo.de
+E: martin.kepplinger@theobroma-systems.com
+W: http://www.martinkepplinger.com
+D: mma8452 accelerators iio driver
+D: Kernel cleanups
+S: Garnisonstraße 26
+S: 4020 Linz
+S: Austria
+
 N: Karl Keyte
 E: karl@koft.com
 D: Disk usage statistics and modifications to line printer driver

Documentation/ABI/testing/configfs-iio

@@ -0,0 +1,21 @@
+What:		/config/iio
+Date:		October 2015
+KernelVersion:	4.4
+Contact:	linux-iio@vger.kernel.org
+Description:
+		This represents Industrial IO configuration entry point
+		directory. It contains sub-groups corresponding to IIO
+		objects.
+
+What:		/config/iio/triggers
+Date:		October 2015
+KernelVersion:	4.4
+Description:
+		Industrial IO software triggers directory.
+
+What:		/config/iio/triggers/hrtimers
+Date:		October 2015
+KernelVersion:	4.4
+Description:
+		High resolution timers directory. Creating a directory here
+		will result in creating a hrtimer trigger in the IIO subsystem.

Documentation/ABI/testing/configfs-rdma_cm

@@ -0,0 +1,22 @@
+What: 		/config/rdma_cm
+Date: 		November 29, 2015
+KernelVersion:  4.4.0
+Description: 	Interface is used to configure RDMA-cable HCAs in respect to
+		RDMA-CM attributes.
+
+		Attributes are visible only when configfs is mounted. To mount
+		configfs in /config directory use:
+		# mount -t configfs none /config/
+
+		In order to set parameters related to a specific HCA, a directory
+		for this HCA has to be created:
+		mkdir -p /config/rdma_cm/<hca>
+
+
+What: 		/config/rdma_cm/<hca>/ports/<port-num>/default_roce_mode
+Date: 		November 29, 2015
+KernelVersion:  4.4.0
+Description: 	RDMA-CM based connections from HCA <hca> at port <port-num>
+		will be initiated with this RoCE type as default.
+		The possible RoCE types are either "IB/RoCE v1" or "RoCE v2".
+		This parameter has RW access.

Documentation/ABI/testing/configfs-usb-gadget-sourcesink

@@ -10,3 +10,5 @@ Description:
 		isoc_mult	- 0..2 (hs/ss only)
 		isoc_maxburst	- 0..15 (ss only)
 		buflen		- buffer length
+		bulk_qlen	- depth of queue for bulk
+		iso_qlen	- depth of queue for iso

Documentation/ABI/testing/configfs-usb-gadget-tcm

@@ -0,0 +1,6 @@
+What:		/config/usb-gadget/gadget/functions/tcm.name
+Date:		Dec 2015
+KernelVersion:	4.5
+Description:
+		There are no attributes because all the configuration
+		is performed in the "target" subsystem of configfs.

Documentation/ABI/testing/sysfs-bus-iio-ina2xx-adc

@@ -0,0 +1,24 @@
+What:		/sys/bus/iio/devices/iio:deviceX/in_allow_async_readout
+Date:		December 2015
+KernelVersion:	4.4
+Contact:	linux-iio@vger.kernel.org
+Description:
+		By default (value '0'), the capture thread checks for the Conversion
+		Ready Flag to being set prior to committing a new value to the sample
+		buffer. This synchronizes the in-chip conversion rate with the
+		in-driver readout rate at the cost of an additional register read.
+
+		Writing '1' will remove the polling for the Conversion Ready Flags to
+		save the additional i2c transaction, which will improve the bandwidth
+		available for reading data. However, samples can be occasionally skipped
+		or repeated, depending on the beat between the capture and conversion
+		rates.
+
+What:		/sys/bus/iio/devices/iio:deviceX/in_shunt_resistor
+Date:		December 2015
+KernelVersion:	4.4
+Contact:	linux-iio@vger.kernel.org
+Description:
+		The value of the shunt resistor may be known only at runtime fom an
+		eeprom content read by a client application. This attribute allows to
+		set its value in ohms.

Documentation/ABI/testing/sysfs-bus-usb

@@ -134,19 +134,21 @@ Description:
 		enabled for the device. Developer can write y/Y/1 or n/N/0 to
 		the file to enable/disable the feature.
 
-What:		/sys/bus/usb/devices/.../power/usb3_hardware_lpm
-Date:		June 2015
+What:		/sys/bus/usb/devices/.../power/usb3_hardware_lpm_u1
+		/sys/bus/usb/devices/.../power/usb3_hardware_lpm_u2
+Date:		November 2015
 Contact:	Kevin Strasser <kevin.strasser@linux.intel.com>
+		Lu Baolu <baolu.lu@linux.intel.com>
 Description:
 		If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged
 		in to a xHCI host which supports link PM, it will check if U1
 		and U2 exit latencies have been set in the BOS descriptor; if
-		the check is is passed and the host supports USB3 hardware LPM,
+		the check is passed and the host supports USB3 hardware LPM,
 		USB3 hardware LPM will be enabled for the device and the USB
-		device directory will contain a file named
-		power/usb3_hardware_lpm. The file holds a string value (enable
-		or disable) indicating whether or not USB3 hardware LPM is
-		enabled for the device.
+		device directory will contain two files named
+		power/usb3_hardware_lpm_u1 and power/usb3_hardware_lpm_u2. These
+		files hold a string value (enable or disable) indicating whether
+		or not USB3 hardware LPM U1 or U2 is enabled for the device.
 
 What:		/sys/bus/usb/devices/.../removable
 Date:		February 2012
@@ -187,6 +189,17 @@ Description:
 		The file will read "hotplug", "wired" and "not used" if the
 		information is available, and "unknown" otherwise.
 
+What:		/sys/bus/usb/devices/.../(hub interface)/portX/usb3_lpm_permit
+Date:		November 2015
+Contact:	Lu Baolu <baolu.lu@linux.intel.com>
+Description:
+		Some USB3.0 devices are not friendly to USB3 LPM.  usb3_lpm_permit
+		attribute allows enabling/disabling usb3 lpm of a port. It takes
+		effect both before and after a usb device is enumerated. Supported
+		values are "0" if both u1 and u2 are NOT permitted, "u1" if only u1
+		is permitted, "u2" if only u2 is permitted, "u1_u2" if both u1 and
+		u2 are permitted.
+
 What:		/sys/bus/usb/devices/.../power/usb2_lpm_l1_timeout
 Date:		May 2013
 Contact:	Mathias Nyman <mathias.nyman@linux.intel.com>

Documentation/ABI/testing/sysfs-class-infiniband

@@ -0,0 +1,16 @@
+What:		/sys/class/infiniband/<hca>/ports/<port-number>/gid_attrs/ndevs/<gid-index>
+Date:		November 29, 2015
+KernelVersion:	4.4.0
+Contact:	linux-rdma@vger.kernel.org
+Description: 	The net-device's name associated with the GID resides
+		at index <gid-index>.
+
+What:		/sys/class/infiniband/<hca>/ports/<port-number>/gid_attrs/types/<gid-index>
+Date:		November 29, 2015
+KernelVersion:	4.4.0
+Contact:	linux-rdma@vger.kernel.org
+Description: 	The RoCE type of the associated GID resides at index <gid-index>.
+		This could either be "IB/RoCE v1" for IB and RoCE v1 based GODs
+		or "RoCE v2" for RoCE v2 based GIDs.
+
+

Documentation/ABI/testing/sysfs-class-net-cdc_ncm

@@ -19,6 +19,25 @@ Description:
 		Set to 0 to pad all frames. Set greater than tx_max to
 		disable all padding.
 
+What:		/sys/class/net/<iface>/cdc_ncm/ndp_to_end
+Date:		Dec 2015
+KernelVersion:	4.5
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Boolean attribute showing the status of the "NDP to
+		end" quirk.  Defaults to 'N', except for devices
+		already known to need it enabled.
+
+		The "NDP to end" quirk makes the driver place the NDP
+		(the packet index table) after the payload.  The NCM
+		specification does not mandate this, but some devices
+		are known to be more restrictive. Write 'Y' to this
+		attribute for temporary testing of a suspect device
+		failing to work with the default driver settings.
+
+		A device entry should be added to the driver if this
+		quirk is found to be required.
+
 What:		/sys/class/net/<iface>/cdc_ncm/rx_max
 Date:		May 2014
 KernelVersion:	3.16

Documentation/ABI/testing/sysfs-class-net-mesh

@@ -8,7 +8,7 @@ Description:
 
 What:           /sys/class/net/<mesh_iface>/mesh/<vlan_subdir>/ap_isolation
 Date:           May 2011
-Contact:        Antonio Quartulli <antonio@meshcoding.com>
+Contact:        Antonio Quartulli <a@unstable.cc>
 Description:
                 Indicates whether the data traffic going from a
                 wireless client to another wireless client will be
@@ -70,7 +70,7 @@ Description:
 
 What:		/sys/class/net/<mesh_iface>/mesh/isolation_mark
 Date:		Nov 2013
-Contact:	Antonio Quartulli <antonio@meshcoding.com>
+Contact:	Antonio Quartulli <a@unstable.cc>
 Description:
 		Defines the isolation mark (and its bitmask) which
 		is used to classify clients as "isolated" by the

Documentation/ABI/testing/sysfs-class-net-qmi

@@ -0,0 +1,23 @@
+What:		/sys/class/net/<iface>/qmi/raw_ip
+Date:		Dec 2015
+KernelVersion:	4.4
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Boolean.  Default: 'N'
+
+		Set this to 'Y' to change the network device link
+		framing from '802.3' to 'raw-ip'.
+
+		The netdev will change to reflect the link framing
+		mode.  The netdev is an ordinary ethernet device in
+		'802.3' mode, and the driver expects to exchange
+		frames with an ethernet header over the USB link. The
+		netdev is a headerless p-t-p device in 'raw-ip' mode,
+		and the driver expects to echange IPv4 or IPv6 packets
+		without any L2 header over the USB link.
+
+		Userspace is in full control of firmware configuration
+		through the delegation of the QMI protocol. Userspace
+		is responsible for coordination of driver and firmware
+		link framing mode, changing this setting to 'Y' if the
+		firmware is configured for 'raw-ip' mode.

Documentation/ABI/testing/sysfs-class-watchdog

@@ -0,0 +1,51 @@
+What:		/sys/class/watchdog/watchdogn/bootstatus
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains status of the watchdog
+		device at boot. It is equivalent to WDIOC_GETBOOTSTATUS of
+		ioctl interface.
+
+What:		/sys/class/watchdog/watchdogn/identity
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains identity string of
+		watchdog device.
+
+What:		/sys/class/watchdog/watchdogn/nowayout
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. While reading, it gives '1' if that
+		device supports nowayout feature else, it gives '0'.
+
+What:		/sys/class/watchdog/watchdogn/state
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It gives active/inactive status of
+		watchdog device.
+
+What:		/sys/class/watchdog/watchdogn/status
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains watchdog device's
+		internal status bits. It is equivalent to WDIOC_GETSTATUS
+		of ioctl interface.
+
+What:		/sys/class/watchdog/watchdogn/timeleft
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It contains value of time left for
+		reset generation. It is equivalent to WDIOC_GETTIMELEFT of
+		ioctl interface.
+
+What:		/sys/class/watchdog/watchdogn/timeout
+Date:		August 2015
+Contact:	Wim Van Sebroeck <wim@iguana.be>
+Description:
+		It is a read only file. It is read to know about current
+		value of timeout programmed.

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -87,6 +87,12 @@ Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:
 		 Controls the checkpoint timing.
 
+What:		/sys/fs/f2fs/<disk>/idle_interval
+Date:		January 2016
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the idle timing.
+
 What:		/sys/fs/f2fs/<disk>/ra_nid_pages
 Date:		October 2015
 Contact:	"Chao Yu" <chao2.yu@samsung.com>

Documentation/ABI/testing/sysfs-kernel-livepatch

@@ -33,7 +33,7 @@ Description:
 		The object directory contains subdirectories for each function
 		that is patched within the object.
 
-What:		/sys/kernel/livepatch/<patch>/<object>/<function>
+What:		/sys/kernel/livepatch/<patch>/<object>/<function,sympos>
 Date:		Nov 2014
 KernelVersion:	3.19.0
 Contact:	live-patching@vger.kernel.org
@@ -41,4 +41,8 @@ Description:
 		The function directory contains attributes regarding the
 		properties and state of the patched function.
 
+		The directory name contains the patched function name and a
+		sympos number corresponding to the nth occurrence of the symbol
+		name in kallsyms for the patched object.
+
 		There are currently no such attributes.

Documentation/ABI/testing/sysfs-ptp

@@ -74,7 +74,7 @@ Description:
 		assignment may be changed by two writing numbers into
 		the file.
 
-What:		/sys/class/ptp/ptpN/pps_avaiable
+What:		/sys/class/ptp/ptpN/pps_available
 Date:		September 2010
 Contact:	Richard Cochran <richardcochran@gmail.com>
 Description:

Documentation/CodingStyle

@@ -430,7 +430,7 @@ The rationale for using gotos is:
 		return result;
 	}
 
-A common type of bug to be aware of it "one err bugs" which look like this:
+A common type of bug to be aware of is "one err bugs" which look like this:
 
 	err:
 		kfree(foo->bar);

Documentation/DMA-API-HOWTO.txt

@@ -951,16 +951,6 @@ to "Closing".
    alignment constraints (e.g. the alignment constraints about 64-bit
    objects).
 
-3) Supporting multiple types of IOMMUs
-
-   If your architecture needs to support multiple types of IOMMUs, you
-   can use include/linux/asm-generic/dma-mapping-common.h. It's a
-   library to support the DMA API with multiple types of IOMMUs. Lots
-   of architectures (x86, powerpc, sh, alpha, ia64, microblaze and
-   sparc) use it. Choose one to see how it can be used. If you need to
-   support multiple types of IOMMUs in a single system, the example of
-   x86 or powerpc helps.
-
 			   Closing
 
 This document, and the API itself, would not be in its current

Documentation/DMA-API.txt

@@ -236,7 +236,7 @@ are guaranteed also to be cache line boundaries).
 
 DMA_TO_DEVICE synchronisation must be done after the last modification
 of the memory region by the software and before it is handed off to
-the driver.  Once this primitive is used, memory covered by this
+the device.  Once this primitive is used, memory covered by this
 primitive should be treated as read-only by the device.  If the device
 may write to it at any point, it should be DMA_BIDIRECTIONAL (see
 below).

Documentation/DocBook/Makefile

@@ -50,8 +50,7 @@ pdfdocs: $(PDF)
 
 HTML := $(sort $(patsubst %.xml, %.html, $(BOOKS)))
 htmldocs: $(HTML)
-	$(call build_main_index)
-	$(call build_images)
+	$(call cmd,build_main_index)
 	$(call install_media_images)
 
 MAN := $(patsubst %.xml, %.9, $(BOOKS))
@@ -139,7 +138,8 @@ quiet_cmd_db2pdf = PDF     $@
 
 index = index.html
 main_idx = $(obj)/$(index)
-build_main_index = rm -rf $(main_idx); \
+quiet_cmd_build_main_index = HTML    $(main_idx)
+      cmd_build_main_index = rm -rf $(main_idx); \
 		   echo '<h1>Linux Kernel HTML Documentation</h1>' >> $(main_idx) && \
 		   echo '<h2>Kernel Version: $(KERNELVERSION)</h2>' >> $(main_idx) && \
 		   cat $(HTML) >> $(main_idx)
@@ -227,6 +227,10 @@ dochelp:
 	@echo  '  mandocs         - man pages'
 	@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  '  valid values for DOCBOOKS are: $(DOCBOOKS)'
+
 
 ###
 # Temporary files left by various tools

Documentation/DocBook/device-drivers.tmpl

@@ -238,83 +238,32 @@ X!Isound/sound_firmware.c
 !Iinclude/media/videobuf2-memops.h
      </sect1>
      <sect1><title>Digital TV (DVB) devices</title>
-!Idrivers/media/dvb-core/dvb_ca_en50221.h
-!Idrivers/media/dvb-core/dvb_frontend.h
+	<sect1><title>Digital TV Common functions</title>
 !Idrivers/media/dvb-core/dvb_math.h
 !Idrivers/media/dvb-core/dvb_ringbuffer.h
 !Idrivers/media/dvb-core/dvbdev.h
-	<sect1><title>Digital TV Demux API</title>
-	    <para>The kernel demux API defines a driver-internal interface for
-	    registering low-level, hardware specific driver to a hardware
-	    independent demux layer. It is only of interest for Digital TV
-	    device driver writers. The header file for this API is named
-	    <constant>demux.h</constant> and located in
-	    <constant>drivers/media/dvb-core</constant>.</para>
-
-	<para>The demux API should be implemented for each demux in the
-	system. It is used to select the TS source of a demux and to manage
-	the demux resources. When the demux client allocates a resource via
-	the demux API, it receives a pointer to the API of that
-	resource.</para>
-	<para>Each demux receives its TS input from a DVB front-end or from
-	memory, as set via this demux API. In a system with more than one
-	front-end, the API can be used to select one of the DVB front-ends
-	as a TS source for a demux, unless this is fixed in the HW platform.
-	The demux API only controls front-ends regarding to their connections
-	with demuxes; the APIs used to set the other front-end parameters,
-	such as tuning, are not defined in this document.</para>
-	<para>The functions that implement the abstract interface demux should
-	be defined static or module private and registered to the Demux
-	core for external access. It is not necessary to implement every
-	function in the struct <constant>dmx_demux</constant>. For example,
-	a demux interface might support Section filtering, but not PES
-	filtering. The API client is expected to check the value of any
-	function pointer before calling the function: the value of NULL means
-	that the &#8220;function is not available&#8221;.</para>
-	<para>Whenever the functions of the demux API modify shared data,
-	the possibilities of lost update and race condition problems should
-	be addressed, e.g. by protecting parts of code with mutexes.</para>
-	<para>Note that functions called from a bottom half context must not
-	sleep. Even a simple memory allocation without using GFP_ATOMIC can
-	result in a kernel thread being put to sleep if swapping is needed.
-	For example, the Linux kernel calls the functions of a network device
-	interface from a bottom half context. Thus, if a demux API function
-	is called from network device code, the function must not sleep.
-	</para>
-    </sect1>
-
-    <section id="demux_callback_api">
-	<title>Demux Callback API</title>
-	<para>This kernel-space API comprises the callback functions that
-	deliver filtered data to the demux client. Unlike the other DVB
-	kABIs, these functions are provided by the client and called from
-	the demux code.</para>
-	<para>The function pointers of this abstract interface are not
-	packed into a structure as in the other demux APIs, because the
-	callback functions are registered and used independent of each
-	other. As an example, it is possible for the API client to provide
-	several callback functions for receiving TS packets and no
-	callbacks for PES packets or sections.</para>
-	<para>The functions that implement the callback API need not be
-	re-entrant: when a demux driver calls one of these functions,
-	the driver is not allowed to call the function again before
-	the original call returns. If a callback is triggered by a
-	hardware interrupt, it is recommended to use the Linux
-	&#8220;bottom half&#8221; mechanism or start a tasklet instead of
-	making the callback function call directly from a hardware
-	interrupt.</para>
-	<para>This mechanism is implemented by
-	<link linkend='API-dmx-ts-cb'>dmx_ts_cb()</link> and
-	<link linkend='API-dmx-section-cb'>dmx_section_cb()</link>.</para>
-    </section>
-
+	</sect1>
+	<sect1><title>Digital TV Frontend kABI</title>
+!Pdrivers/media/dvb-core/dvb_frontend.h Digital TV Frontend
+!Idrivers/media/dvb-core/dvb_frontend.h
+	</sect1>
+	<sect1><title>Digital TV Demux kABI</title>
+!Pdrivers/media/dvb-core/demux.h Digital TV Demux
+	<sect1><title>Demux Callback API</title>
+!Pdrivers/media/dvb-core/demux.h Demux Callback
+	</sect1>
 !Idrivers/media/dvb-core/demux.h
-    </sect1>
+	</sect1>
+	<sect1><title>Digital TV Conditional Access kABI</title>
+!Idrivers/media/dvb-core/dvb_ca_en50221.h
+	</sect1>
+     </sect1>
     <sect1><title>Remote Controller devices</title>
 !Iinclude/media/rc-core.h
 !Iinclude/media/lirc_dev.h
     </sect1>
     <sect1><title>Media Controller devices</title>
+!Pinclude/media/media-device.h Media Controller
 !Iinclude/media/media-device.h
 !Iinclude/media/media-devnode.h
 !Iinclude/media/media-entity.h

Documentation/DocBook/gpu.tmpl

@@ -124,6 +124,43 @@
     <para>
       [Insert diagram of typical DRM stack here]
     </para>
+  <sect1>
+    <title>Style Guidelines</title>
+    <para>
+      For consistency this documentation uses American English. Abbreviations
+      are written as all-uppercase, for example: DRM, KMS, IOCTL, CRTC, and so
+      on. To aid in reading, documentations make full use of the markup
+      characters kerneldoc provides: @parameter for function parameters, @member
+      for structure members, &amp;structure to reference structures and
+      function() for functions. These all get automatically hyperlinked if
+      kerneldoc for the referenced objects exists. When referencing entries in
+      function vtables please use -&gt;vfunc(). Note that kerneldoc does
+      not support referencing struct members directly, so please add a reference
+      to the vtable struct somewhere in the same paragraph or at least section.
+    </para>
+    <para>
+      Except in special situations (to separate locked from unlocked variants)
+      locking requirements for functions aren't documented in the kerneldoc.
+      Instead locking should be check at runtime using e.g.
+      <code>WARN_ON(!mutex_is_locked(...));</code>. Since it's much easier to
+      ignore documentation than runtime noise this provides more value. And on
+      top of that runtime checks do need to be updated when the locking rules
+      change, increasing the chances that they're correct. Within the
+      documentation the locking rules should be explained in the relevant
+      structures: Either in the comment for the lock explaining what it
+      protects, or data fields need a note about which lock protects them, or
+      both.
+    </para>
+    <para>
+      Functions which have a non-<code>void</code> return value should have a
+      section called "Returns" explaining the expected return values in
+      different cases and their meanings. Currently there's no consensus whether
+      that section name should be all upper-case or not, and whether it should
+      end in a colon or not. Go with the file-local style. Other common section
+      names are "Notes" with information for dangerous or tricky corner cases,
+      and "FIXME" where the interface could be cleaned up.
+    </para>
+  </sect1>
   </chapter>
 
   <!-- Internals -->
@@ -615,18 +652,6 @@ char *date;</synopsis>
           <function>drm_gem_object_init</function>. Storage for private GEM
           objects must be managed by drivers.
         </para>
-        <para>
-          Drivers that do not need to extend GEM objects with private information
-          can call the <function>drm_gem_object_alloc</function> function to
-          allocate and initialize a struct <structname>drm_gem_object</structname>
-          instance. The GEM core will call the optional driver
-          <methodname>gem_init_object</methodname> operation after initializing
-          the GEM object with <function>drm_gem_object_init</function>.
-          <synopsis>int (*gem_init_object) (struct drm_gem_object *obj);</synopsis>
-        </para>
-        <para>
-          No alloc-and-init function exists for private GEM objects.
-        </para>
       </sect3>
       <sect3>
         <title>GEM Objects Lifetime</title>
@@ -635,10 +660,10 @@ char *date;</synopsis>
           acquired and release by <function>calling drm_gem_object_reference</function>
           and <function>drm_gem_object_unreference</function> respectively. The
           caller must hold the <structname>drm_device</structname>
-          <structfield>struct_mutex</structfield> lock. As a convenience, GEM
-          provides the <function>drm_gem_object_reference_unlocked</function> and
-          <function>drm_gem_object_unreference_unlocked</function> functions that
-          can be called without holding the lock.
+	  <structfield>struct_mutex</structfield> lock when calling
+	  <function>drm_gem_object_reference</function>. As a convenience, GEM
+	  provides <function>drm_gem_object_unreference_unlocked</function>
+	  functions that can be called without holding the lock.
         </para>
         <para>
           When the last reference to a GEM object is released the GEM core calls
@@ -649,15 +674,9 @@ char *date;</synopsis>
         </para>
         <para>
           <synopsis>void (*gem_free_object) (struct drm_gem_object *obj);</synopsis>
-          Drivers are responsible for freeing all GEM object resources, including
-          the resources created by the GEM core. If an mmap offset has been
-          created for the object (in which case
-          <structname>drm_gem_object</structname>::<structfield>map_list</structfield>::<structfield>map</structfield>
-          is not NULL) it must be freed by a call to
-          <function>drm_gem_free_mmap_offset</function>. The shmfs backing store
-          must be released by calling <function>drm_gem_object_release</function>
-          (that function can safely be called if no shmfs backing store has been
-          created).
+          Drivers are responsible for freeing all GEM object resources. This includes
+          the resources created by the GEM core, which need to be released with
+          <function>drm_gem_object_release</function>.
         </para>
       </sect3>
       <sect3>
@@ -740,17 +759,10 @@ char *date;</synopsis>
           DRM identifies the GEM object to be mapped by a fake offset passed
           through the mmap offset argument. Prior to being mapped, a GEM object
           must thus be associated with a fake offset. To do so, drivers must call
-          <function>drm_gem_create_mmap_offset</function> on the object. The
-          function allocates a fake offset range from a pool and stores the
-          offset divided by PAGE_SIZE in
-          <literal>obj-&gt;map_list.hash.key</literal>. Care must be taken not to
-          call <function>drm_gem_create_mmap_offset</function> if a fake offset
-          has already been allocated for the object. This can be tested by
-          <literal>obj-&gt;map_list.map</literal> being non-NULL.
+          <function>drm_gem_create_mmap_offset</function> on the object.
         </para>
         <para>
           Once allocated, the fake offset value
-          (<literal>obj-&gt;map_list.hash.key &lt;&lt; PAGE_SHIFT</literal>)
           must be passed to the application in a driver-specific way and can then
           be used as the mmap offset argument.
         </para>
@@ -836,10 +848,11 @@ char *date;</synopsis>
           abstracted from the client in libdrm.
         </para>
       </sect3>
-      <sect3>
-        <title>GEM Function Reference</title>
+    </sect2>
+    <sect2>
+      <title>GEM Function Reference</title>
 !Edrivers/gpu/drm/drm_gem.c
-      </sect3>
+!Iinclude/drm/drm_gem.h
     </sect2>
     <sect2>
       <title>VMA Offset Manager</title>
@@ -970,12 +983,10 @@ int max_width, max_height;</synopsis>
     <sect2>
       <title>Atomic Mode Setting Function Reference</title>
 !Edrivers/gpu/drm/drm_atomic.c
+!Idrivers/gpu/drm/drm_atomic.c
     </sect2>
     <sect2>
-      <title>Frame Buffer Creation</title>
-      <synopsis>struct drm_framebuffer *(*fb_create)(struct drm_device *dev,
-				     struct drm_file *file_priv,
-				     struct drm_mode_fb_cmd2 *mode_cmd);</synopsis>
+      <title>Frame Buffer Abstraction</title>
       <para>
         Frame buffers are abstract memory objects that provide a source of
         pixels to scanout to a CRTC. Applications explicitly request the
@@ -993,73 +1004,6 @@ int max_width, max_height;</synopsis>
 	handles, e.g. vmwgfx directly exposes special TTM handles to userspace
 	and so expects TTM handles in the create ioctl and not GEM handles.
       </para>
-      <para>
-        Drivers must first validate the requested frame buffer parameters passed
-        through the mode_cmd argument. In particular this is where invalid
-        sizes, pixel formats or pitches can be caught.
-      </para>
-      <para>
-        If the parameters are deemed valid, drivers then create, initialize and
-        return an instance of struct <structname>drm_framebuffer</structname>.
-        If desired the instance can be embedded in a larger driver-specific
-	structure. Drivers must fill its <structfield>width</structfield>,
-	<structfield>height</structfield>, <structfield>pitches</structfield>,
-        <structfield>offsets</structfield>, <structfield>depth</structfield>,
-        <structfield>bits_per_pixel</structfield> and
-        <structfield>pixel_format</structfield> fields from the values passed
-        through the <parameter>drm_mode_fb_cmd2</parameter> argument. They
-        should call the <function>drm_helper_mode_fill_fb_struct</function>
-        helper function to do so.
-      </para>
-
-      <para>
-	The initialization of the new framebuffer instance is finalized with a
-	call to <function>drm_framebuffer_init</function> which takes a pointer
-	to DRM frame buffer operations (struct
-	<structname>drm_framebuffer_funcs</structname>). Note that this function
-	publishes the framebuffer and so from this point on it can be accessed
-	concurrently from other threads. Hence it must be the last step in the
-	driver's framebuffer initialization sequence. Frame buffer operations
-	are
-        <itemizedlist>
-          <listitem>
-            <synopsis>int (*create_handle)(struct drm_framebuffer *fb,
-		     struct drm_file *file_priv, unsigned int *handle);</synopsis>
-            <para>
-              Create a handle to the frame buffer underlying memory object. If
-              the frame buffer uses a multi-plane format, the handle will
-              reference the memory object associated with the first plane.
-            </para>
-            <para>
-              Drivers call <function>drm_gem_handle_create</function> to create
-              the handle.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>void (*destroy)(struct drm_framebuffer *framebuffer);</synopsis>
-            <para>
-              Destroy the frame buffer object and frees all associated
-              resources. Drivers must call
-              <function>drm_framebuffer_cleanup</function> to free resources
-              allocated by the DRM core for the frame buffer object, and must
-              make sure to unreference all memory objects associated with the
-              frame buffer. Handles created by the
-              <methodname>create_handle</methodname> operation are released by
-              the DRM core.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>int (*dirty)(struct drm_framebuffer *framebuffer,
-	     struct drm_file *file_priv, unsigned flags, unsigned color,
-	     struct drm_clip_rect *clips, unsigned num_clips);</synopsis>
-            <para>
-              This optional operation notifies the driver that a region of the
-              frame buffer has changed in response to a DRM_IOCTL_MODE_DIRTYFB
-              ioctl call.
-            </para>
-          </listitem>
-        </itemizedlist>
-      </para>
       <para>
 	The lifetime of a drm framebuffer is controlled with a reference count,
 	drivers can grab additional references with
@@ -1197,137 +1141,6 @@ int max_width, max_height;</synopsis>
           pointer to CRTC functions.
         </para>
       </sect3>
-      <sect3 id="drm-kms-crtcops">
-        <title>CRTC Operations</title>
-        <sect4>
-          <title>Set Configuration</title>
-          <synopsis>int (*set_config)(struct drm_mode_set *set);</synopsis>
-          <para>
-            Apply a new CRTC configuration to the device. The configuration
-            specifies a CRTC, a frame buffer to scan out from, a (x,y) position in
-            the frame buffer, a display mode and an array of connectors to drive
-            with the CRTC if possible.
-          </para>
-          <para>
-            If the frame buffer specified in the configuration is NULL, the driver
-            must detach all encoders connected to the CRTC and all connectors
-            attached to those encoders and disable them.
-          </para>
-          <para>
-            This operation is called with the mode config lock held.
-          </para>
-          <note><para>
-	    Note that the drm core has no notion of restoring the mode setting
-	    state after resume, since all resume handling is in the full
-	    responsibility of the driver. The common mode setting helper library
-	    though provides a helper which can be used for this:
-	    <function>drm_helper_resume_force_mode</function>.
-          </para></note>
-        </sect4>
-        <sect4>
-          <title>Page Flipping</title>
-          <synopsis>int (*page_flip)(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-                   struct drm_pending_vblank_event *event);</synopsis>
-          <para>
-            Schedule a page flip to the given frame buffer for the CRTC. This
-            operation is called with the mode config mutex held.
-          </para>
-          <para>
-            Page flipping is a synchronization mechanism that replaces the frame
-            buffer being scanned out by the CRTC with a new frame buffer during
-            vertical blanking, avoiding tearing. When an application requests a page
-            flip the DRM core verifies that the new frame buffer is large enough to
-            be scanned out by  the CRTC in the currently configured mode and then
-            calls the CRTC <methodname>page_flip</methodname> operation with a
-            pointer to the new frame buffer.
-          </para>
-          <para>
-            The <methodname>page_flip</methodname> operation schedules a page flip.
-            Once any pending rendering targeting the new frame buffer has
-            completed, the CRTC will be reprogrammed to display that frame buffer
-            after the next vertical refresh. The operation must return immediately
-            without waiting for rendering or page flip to complete and must block
-            any new rendering to the frame buffer until the page flip completes.
-          </para>
-          <para>
-            If a page flip can be successfully scheduled the driver must set the
-            <code>drm_crtc-&gt;fb</code> field to the new framebuffer pointed to
-            by <code>fb</code>. This is important so that the reference counting
-            on framebuffers stays balanced.
-          </para>
-          <para>
-            If a page flip is already pending, the
-            <methodname>page_flip</methodname> operation must return
-            -<errorname>EBUSY</errorname>.
-          </para>
-          <para>
-            To synchronize page flip to vertical blanking the driver will likely
-            need to enable vertical blanking interrupts. It should call
-            <function>drm_vblank_get</function> for that purpose, and call
-            <function>drm_vblank_put</function> after the page flip completes.
-          </para>
-          <para>
-            If the application has requested to be notified when page flip completes
-            the <methodname>page_flip</methodname> operation will be called with a
-            non-NULL <parameter>event</parameter> argument pointing to a
-            <structname>drm_pending_vblank_event</structname> instance. Upon page
-            flip completion the driver must call <methodname>drm_send_vblank_event</methodname>
-            to fill in the event and send to wake up any waiting processes.
-            This can be performed with
-            <programlisting><![CDATA[
-            spin_lock_irqsave(&dev->event_lock, flags);
-            ...
-            drm_send_vblank_event(dev, pipe, event);
-            spin_unlock_irqrestore(&dev->event_lock, flags);
-            ]]></programlisting>
-          </para>
-          <note><para>
-            FIXME: Could drivers that don't need to wait for rendering to complete
-            just add the event to <literal>dev-&gt;vblank_event_list</literal> and
-            let the DRM core handle everything, as for "normal" vertical blanking
-            events?
-          </para></note>
-          <para>
-            While waiting for the page flip to complete, the
-            <literal>event-&gt;base.link</literal> list head can be used freely by
-            the driver to store the pending event in a driver-specific list.
-          </para>
-          <para>
-            If the file handle is closed before the event is signaled, drivers must
-            take care to destroy the event in their
-            <methodname>preclose</methodname> operation (and, if needed, call
-            <function>drm_vblank_put</function>).
-          </para>
-        </sect4>
-        <sect4>
-          <title>Miscellaneous</title>
-          <itemizedlist>
-            <listitem>
-              <synopsis>void (*set_property)(struct drm_crtc *crtc,
-                     struct drm_property *property, uint64_t value);</synopsis>
-              <para>
-                Set the value of the given CRTC property to
-                <parameter>value</parameter>. See <xref linkend="drm-kms-properties"/>
-                for more information about properties.
-              </para>
-            </listitem>
-            <listitem>
-              <synopsis>void (*gamma_set)(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-                        uint32_t start, uint32_t size);</synopsis>
-              <para>
-                Apply a gamma table to the device. The operation is optional.
-              </para>
-            </listitem>
-            <listitem>
-              <synopsis>void (*destroy)(struct drm_crtc *crtc);</synopsis>
-              <para>
-                Destroy the CRTC when not needed anymore. See
-                <xref linkend="drm-kms-init"/>.
-              </para>
-            </listitem>
-          </itemizedlist>
-        </sect4>
-      </sect3>
     </sect2>
     <sect2>
       <title>Planes (struct <structname>drm_plane</structname>)</title>
@@ -1344,7 +1157,7 @@ int max_width, max_height;</synopsis>
         <listitem>
         DRM_PLANE_TYPE_PRIMARY represents a "main" plane for a CRTC.  Primary
         planes are the planes operated upon by CRTC modesetting and flipping
-        operations described in <xref linkend="drm-kms-crtcops"/>.
+	operations described in the page_flip hook in <structname>drm_crtc_funcs</structname>.
         </listitem>
         <listitem>
         DRM_PLANE_TYPE_CURSOR represents a "cursor" plane for a CRTC.  Cursor
@@ -1381,52 +1194,6 @@ int max_width, max_height;</synopsis>
           primary plane with standard capabilities.
         </para>
       </sect3>
-      <sect3>
-        <title>Plane Operations</title>
-        <itemizedlist>
-          <listitem>
-            <synopsis>int (*update_plane)(struct drm_plane *plane, struct drm_crtc *crtc,
-                        struct drm_framebuffer *fb, int crtc_x, int crtc_y,
-                        unsigned int crtc_w, unsigned int crtc_h,
-                        uint32_t src_x, uint32_t src_y,
-                        uint32_t src_w, uint32_t src_h);</synopsis>
-            <para>
-              Enable and configure the plane to use the given CRTC and frame buffer.
-            </para>
-            <para>
-              The source rectangle in frame buffer memory coordinates is given by
-              the <parameter>src_x</parameter>, <parameter>src_y</parameter>,
-              <parameter>src_w</parameter> and <parameter>src_h</parameter>
-              parameters (as 16.16 fixed point values). Devices that don't support
-              subpixel plane coordinates can ignore the fractional part.
-            </para>
-            <para>
-              The destination rectangle in CRTC coordinates is given by the
-              <parameter>crtc_x</parameter>, <parameter>crtc_y</parameter>,
-              <parameter>crtc_w</parameter> and <parameter>crtc_h</parameter>
-              parameters (as integer values). Devices scale the source rectangle to
-              the destination rectangle. If scaling is not supported, and the source
-              rectangle size doesn't match the destination rectangle size, the
-              driver must return a -<errorname>EINVAL</errorname> error.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>int (*disable_plane)(struct drm_plane *plane);</synopsis>
-            <para>
-              Disable the plane. The DRM core calls this method in response to a
-              DRM_IOCTL_MODE_SETPLANE ioctl call with the frame buffer ID set to 0.
-              Disabled planes must not be processed by the CRTC.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>void (*destroy)(struct drm_plane *plane);</synopsis>
-            <para>
-              Destroy the plane when not needed anymore. See
-              <xref linkend="drm-kms-init"/>.
-            </para>
-          </listitem>
-        </itemizedlist>
-      </sect3>
     </sect2>
     <sect2>
       <title>Encoders (struct <structname>drm_encoder</structname>)</title>
@@ -1483,27 +1250,6 @@ int max_width, max_height;</synopsis>
           encoders they want to use to a CRTC.
         </para>
       </sect3>
-      <sect3>
-        <title>Encoder Operations</title>
-        <itemizedlist>
-          <listitem>
-            <synopsis>void (*destroy)(struct drm_encoder *encoder);</synopsis>
-            <para>
-              Called to destroy the encoder when not needed anymore. See
-              <xref linkend="drm-kms-init"/>.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>void (*set_property)(struct drm_plane *plane,
-                     struct drm_property *property, uint64_t value);</synopsis>
-            <para>
-              Set the value of the given plane property to
-              <parameter>value</parameter>. See <xref linkend="drm-kms-properties"/>
-              for more information about properties.
-            </para>
-          </listitem>
-        </itemizedlist>
-      </sect3>
     </sect2>
     <sect2>
       <title>Connectors (struct <structname>drm_connector</structname>)</title>
@@ -1707,27 +1453,6 @@ int max_width, max_height;</synopsis>
             connector_status_unknown.
           </para>
         </sect4>
-        <sect4>
-          <title>Miscellaneous</title>
-          <itemizedlist>
-            <listitem>
-              <synopsis>void (*set_property)(struct drm_connector *connector,
-                     struct drm_property *property, uint64_t value);</synopsis>
-              <para>
-                Set the value of the given connector property to
-                <parameter>value</parameter>. See <xref linkend="drm-kms-properties"/>
-                for more information about properties.
-              </para>
-            </listitem>
-            <listitem>
-              <synopsis>void (*destroy)(struct drm_connector *connector);</synopsis>
-              <para>
-                Destroy the connector when not needed anymore. See
-                <xref linkend="drm-kms-init"/>.
-              </para>
-            </listitem>
-          </itemizedlist>
-        </sect4>
       </sect3>
     </sect2>
     <sect2>
@@ -1853,462 +1578,6 @@ void intel_crt_init(struct drm_device *dev)
       To use it, a driver must provide bottom functions for all of the three KMS
       entities.
     </para>
-    <sect2>
-      <title>Helper Functions</title>
-      <itemizedlist>
-        <listitem>
-          <synopsis>int drm_crtc_helper_set_config(struct drm_mode_set *set);</synopsis>
-          <para>
-            The <function>drm_crtc_helper_set_config</function> helper function
-            is a CRTC <methodname>set_config</methodname> implementation. It
-            first tries to locate the best encoder for each connector by calling
-            the connector <methodname>best_encoder</methodname> helper
-            operation.
-          </para>
-          <para>
-            After locating the appropriate encoders, the helper function will
-            call the <methodname>mode_fixup</methodname> encoder and CRTC helper
-            operations to adjust the requested mode, or reject it completely in
-            which case an error will be returned to the application. If the new
-            configuration after mode adjustment is identical to the current
-            configuration the helper function will return without performing any
-            other operation.
-          </para>
-          <para>
-            If the adjusted mode is identical to the current mode but changes to
-            the frame buffer need to be applied, the
-            <function>drm_crtc_helper_set_config</function> function will call
-            the CRTC <methodname>mode_set_base</methodname> helper operation. If
-            the adjusted mode differs from the current mode, or if the
-            <methodname>mode_set_base</methodname> helper operation is not
-            provided, the helper function performs a full mode set sequence by
-            calling the <methodname>prepare</methodname>,
-            <methodname>mode_set</methodname> and
-            <methodname>commit</methodname> CRTC and encoder helper operations,
-            in that order.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void drm_helper_connector_dpms(struct drm_connector *connector, int mode);</synopsis>
-          <para>
-            The <function>drm_helper_connector_dpms</function> helper function
-            is a connector <methodname>dpms</methodname> implementation that
-            tracks power state of connectors. To use the function, drivers must
-            provide <methodname>dpms</methodname> helper operations for CRTCs
-            and encoders to apply the DPMS state to the device.
-          </para>
-          <para>
-            The mid-layer doesn't track the power state of CRTCs and encoders.
-            The <methodname>dpms</methodname> helper operations can thus be
-            called with a mode identical to the currently active mode.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
-                                            uint32_t maxX, uint32_t maxY);</synopsis>
-          <para>
-            The <function>drm_helper_probe_single_connector_modes</function> helper
-            function is a connector <methodname>fill_modes</methodname>
-            implementation that updates the connection status for the connector
-            and then retrieves a list of modes by calling the connector
-            <methodname>get_modes</methodname> helper operation.
-          </para>
-         <para>
-            If the helper operation returns no mode, and if the connector status
-            is connector_status_connected, standard VESA DMT modes up to
-            1024x768 are automatically added to the modes list by a call to
-            <function>drm_add_modes_noedid</function>.
-          </para>
-          <para>
-            The function then filters out modes larger than
-            <parameter>max_width</parameter> and <parameter>max_height</parameter>
-            if specified. It finally calls the optional connector
-            <methodname>mode_valid</methodname> helper operation for each mode in
-            the probed list to check whether the mode is valid for the connector.
-          </para>
-        </listitem>
-      </itemizedlist>
-    </sect2>
-    <sect2>
-      <title>CRTC Helper Operations</title>
-      <itemizedlist>
-        <listitem id="drm-helper-crtc-mode-fixup">
-          <synopsis>bool (*mode_fixup)(struct drm_crtc *crtc,
-                       const struct drm_display_mode *mode,
-                       struct drm_display_mode *adjusted_mode);</synopsis>
-          <para>
-            Let CRTCs adjust the requested mode or reject it completely. This
-            operation returns true if the mode is accepted (possibly after being
-            adjusted) or false if it is rejected.
-          </para>
-          <para>
-            The <methodname>mode_fixup</methodname> operation should reject the
-            mode if it can't reasonably use it. The definition of "reasonable"
-            is currently fuzzy in this context. One possible behaviour would be
-            to set the adjusted mode to the panel timings when a fixed-mode
-            panel is used with hardware capable of scaling. Another behaviour
-            would be to accept any input mode and adjust it to the closest mode
-            supported by the hardware (FIXME: This needs to be clarified).
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*mode_set_base)(struct drm_crtc *crtc, int x, int y,
-                     struct drm_framebuffer *old_fb)</synopsis>
-          <para>
-            Move the CRTC on the current frame buffer (stored in
-            <literal>crtc-&gt;fb</literal>) to position (x,y). Any of the frame
-            buffer, x position or y position may have been modified.
-          </para>
-          <para>
-            This helper operation is optional. If not provided, the
-            <function>drm_crtc_helper_set_config</function> function will fall
-            back to the <methodname>mode_set</methodname> helper operation.
-          </para>
-          <note><para>
-            FIXME: Why are x and y passed as arguments, as they can be accessed
-            through <literal>crtc-&gt;x</literal> and
-            <literal>crtc-&gt;y</literal>?
-          </para></note>
-        </listitem>
-        <listitem>
-          <synopsis>void (*prepare)(struct drm_crtc *crtc);</synopsis>
-          <para>
-            Prepare the CRTC for mode setting. This operation is called after
-            validating the requested mode. Drivers use it to perform
-            device-specific operations required before setting the new mode.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*mode_set)(struct drm_crtc *crtc, struct drm_display_mode *mode,
-                struct drm_display_mode *adjusted_mode, int x, int y,
-                struct drm_framebuffer *old_fb);</synopsis>
-          <para>
-            Set a new mode, position and frame buffer. Depending on the device
-            requirements, the mode can be stored internally by the driver and
-            applied in the <methodname>commit</methodname> operation, or
-            programmed to the hardware immediately.
-          </para>
-          <para>
-            The <methodname>mode_set</methodname> operation returns 0 on success
-	    or a negative error code if an error occurs.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*commit)(struct drm_crtc *crtc);</synopsis>
-          <para>
-            Commit a mode. This operation is called after setting the new mode.
-            Upon return the device must use the new mode and be fully
-            operational.
-          </para>
-        </listitem>
-      </itemizedlist>
-    </sect2>
-    <sect2>
-      <title>Encoder Helper Operations</title>
-      <itemizedlist>
-        <listitem>
-          <synopsis>bool (*mode_fixup)(struct drm_encoder *encoder,
-                       const struct drm_display_mode *mode,
-                       struct drm_display_mode *adjusted_mode);</synopsis>
-          <para>
-            Let encoders adjust the requested mode or reject it completely. This
-            operation returns true if the mode is accepted (possibly after being
-            adjusted) or false if it is rejected. See the
-            <link linkend="drm-helper-crtc-mode-fixup">mode_fixup CRTC helper
-            operation</link> for an explanation of the allowed adjustments.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*prepare)(struct drm_encoder *encoder);</synopsis>
-          <para>
-            Prepare the encoder for mode setting. This operation is called after
-            validating the requested mode. Drivers use it to perform
-            device-specific operations required before setting the new mode.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*mode_set)(struct drm_encoder *encoder,
-                 struct drm_display_mode *mode,
-                 struct drm_display_mode *adjusted_mode);</synopsis>
-          <para>
-            Set a new mode. Depending on the device requirements, the mode can
-            be stored internally by the driver and applied in the
-            <methodname>commit</methodname> operation, or programmed to the
-            hardware immediately.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>void (*commit)(struct drm_encoder *encoder);</synopsis>
-          <para>
-            Commit a mode. This operation is called after setting the new mode.
-            Upon return the device must use the new mode and be fully
-            operational.
-          </para>
-        </listitem>
-      </itemizedlist>
-    </sect2>
-    <sect2>
-      <title>Connector Helper Operations</title>
-      <itemizedlist>
-        <listitem>
-          <synopsis>struct drm_encoder *(*best_encoder)(struct drm_connector *connector);</synopsis>
-          <para>
-            Return a pointer to the best encoder for the connecter. Device that
-            map connectors to encoders 1:1 simply return the pointer to the
-            associated encoder. This operation is mandatory.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*get_modes)(struct drm_connector *connector);</synopsis>
-          <para>
-            Fill the connector's <structfield>probed_modes</structfield> list
-            by parsing EDID data with <function>drm_add_edid_modes</function>,
-            adding standard VESA DMT modes with <function>drm_add_modes_noedid</function>,
-            or calling <function>drm_mode_probed_add</function> directly for every
-            supported mode and return the number of modes it has detected. This
-            operation is mandatory.
-          </para>
-          <para>
-            Note that the caller function will automatically add standard VESA
-            DMT modes up to 1024x768 if the <methodname>get_modes</methodname>
-            helper operation returns no mode and if the connector status is
-            connector_status_connected. There is no need to call
-            <function>drm_add_edid_modes</function> manually in that case.
-          </para>
-          <para>
-            When adding modes manually the driver creates each mode with a call to
-            <function>drm_mode_create</function> and must fill the following fields.
-            <itemizedlist>
-              <listitem>
-                <synopsis>__u32 type;</synopsis>
-                <para>
-                  Mode type bitmask, a combination of
-                  <variablelist>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_BUILTIN</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_CLOCK_C</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_CRTC_C</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>
-        DRM_MODE_TYPE_PREFERRED - The preferred mode for the connector
-                      </term>
-                      <listitem>
-                        <para>not used?</para>
-                      </listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_DEFAULT</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_USERDEF</term>
-                      <listitem><para>not used?</para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_TYPE_DRIVER</term>
-                      <listitem>
-                        <para>
-                          The mode has been created by the driver (as opposed to
-                          to user-created modes).
-                        </para>
-                      </listitem>
-                    </varlistentry>
-                  </variablelist>
-                  Drivers must set the DRM_MODE_TYPE_DRIVER bit for all modes they
-                  create, and set the DRM_MODE_TYPE_PREFERRED bit for the preferred
-                  mode.
-                </para>
-              </listitem>
-              <listitem>
-                <synopsis>__u32 clock;</synopsis>
-                <para>Pixel clock frequency in kHz unit</para>
-              </listitem>
-              <listitem>
-                <synopsis>__u16 hdisplay, hsync_start, hsync_end, htotal;
-    __u16 vdisplay, vsync_start, vsync_end, vtotal;</synopsis>
-                <para>Horizontal and vertical timing information</para>
-                <screen><![CDATA[
-             Active                 Front           Sync           Back
-             Region                 Porch                          Porch
-    <-----------------------><----------------><-------------><-------------->
-
-      //////////////////////|
-     ////////////////////// |
-    //////////////////////  |..................               ................
-                                               _______________
-
-    <----- [hv]display ----->
-    <------------- [hv]sync_start ------------>
-    <--------------------- [hv]sync_end --------------------->
-    <-------------------------------- [hv]total ----------------------------->
-]]></screen>
-              </listitem>
-              <listitem>
-                <synopsis>__u16 hskew;
-    __u16 vscan;</synopsis>
-                <para>Unknown</para>
-              </listitem>
-              <listitem>
-                <synopsis>__u32 flags;</synopsis>
-                <para>
-                  Mode flags, a combination of
-                  <variablelist>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PHSYNC</term>
-                      <listitem><para>
-                        Horizontal sync is active high
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_NHSYNC</term>
-                      <listitem><para>
-                        Horizontal sync is active low
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PVSYNC</term>
-                      <listitem><para>
-                        Vertical sync is active high
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_NVSYNC</term>
-                      <listitem><para>
-                        Vertical sync is active low
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_INTERLACE</term>
-                      <listitem><para>
-                        Mode is interlaced
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_DBLSCAN</term>
-                      <listitem><para>
-                        Mode uses doublescan
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_CSYNC</term>
-                      <listitem><para>
-                        Mode uses composite sync
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PCSYNC</term>
-                      <listitem><para>
-                        Composite sync is active high
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_NCSYNC</term>
-                      <listitem><para>
-                        Composite sync is active low
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_HSKEW</term>
-                      <listitem><para>
-                        hskew provided (not used?)
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_BCAST</term>
-                      <listitem><para>
-                        not used?
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_PIXMUX</term>
-                      <listitem><para>
-                        not used?
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_DBLCLK</term>
-                      <listitem><para>
-                        not used?
-                      </para></listitem>
-                    </varlistentry>
-                    <varlistentry>
-                      <term>DRM_MODE_FLAG_CLKDIV2</term>
-                      <listitem><para>
-                        ?
-                      </para></listitem>
-                    </varlistentry>
-                  </variablelist>
-                </para>
-                <para>
-                  Note that modes marked with the INTERLACE or DBLSCAN flags will be
-                  filtered out by
-                  <function>drm_helper_probe_single_connector_modes</function> if
-                  the connector's <structfield>interlace_allowed</structfield> or
-                  <structfield>doublescan_allowed</structfield> field is set to 0.
-                </para>
-              </listitem>
-              <listitem>
-                <synopsis>char name[DRM_DISPLAY_MODE_LEN];</synopsis>
-                <para>
-                  Mode name. The driver must call
-                  <function>drm_mode_set_name</function> to fill the mode name from
-                  <structfield>hdisplay</structfield>,
-                  <structfield>vdisplay</structfield> and interlace flag after
-                  filling the corresponding fields.
-                </para>
-              </listitem>
-            </itemizedlist>
-          </para>
-          <para>
-            The <structfield>vrefresh</structfield> value is computed by
-            <function>drm_helper_probe_single_connector_modes</function>.
-          </para>
-          <para>
-            When parsing EDID data, <function>drm_add_edid_modes</function> fills the
-            connector <structfield>display_info</structfield>
-            <structfield>width_mm</structfield> and
-            <structfield>height_mm</structfield> fields. When creating modes
-            manually the <methodname>get_modes</methodname> helper operation must
-            set the <structfield>display_info</structfield>
-            <structfield>width_mm</structfield> and
-            <structfield>height_mm</structfield> fields if they haven't been set
-            already (for instance at initialization time when a fixed-size panel is
-            attached to the connector). The mode <structfield>width_mm</structfield>
-            and <structfield>height_mm</structfield> fields are only used internally
-            during EDID parsing and should not be set when creating modes manually.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*mode_valid)(struct drm_connector *connector,
-		  struct drm_display_mode *mode);</synopsis>
-          <para>
-            Verify whether a mode is valid for the connector. Return MODE_OK for
-            supported modes and one of the enum drm_mode_status values (MODE_*)
-            for unsupported modes. This operation is optional.
-          </para>
-          <para>
-            As the mode rejection reason is currently not used beside for
-            immediately removing the unsupported mode, an implementation can
-            return MODE_BAD regardless of the exact reason why the mode is not
-            valid.
-          </para>
-          <note><para>
-            Note that the <methodname>mode_valid</methodname> helper operation is
-            only called for modes detected by the device, and
-            <emphasis>not</emphasis> for modes set by the user through the CRTC
-            <methodname>set_config</methodname> operation.
-          </para></note>
-        </listitem>
-      </itemizedlist>
-    </sect2>
     <sect2>
       <title>Atomic Modeset Helper Functions Reference</title>
       <sect3>
@@ -2327,8 +1596,12 @@ void intel_crt_init(struct drm_device *dev)
 !Edrivers/gpu/drm/drm_atomic_helper.c
     </sect2>
     <sect2>
-      <title>Modeset Helper Functions Reference</title>
-!Iinclude/drm/drm_crtc_helper.h
+      <title>Modeset Helper Reference for Common Vtables</title>
+!Iinclude/drm/drm_modeset_helper_vtables.h
+!Pinclude/drm/drm_modeset_helper_vtables.h overview
+    </sect2>
+    <sect2>
+      <title>Legacy CRTC/Modeset Helper Functions Reference</title>
 !Edrivers/gpu/drm/drm_crtc_helper.c
 !Pdrivers/gpu/drm/drm_crtc_helper.c overview
     </sect2>
@@ -4039,92 +3312,6 @@ int num_ioctls;</synopsis>
       <sect2>
         <title>DPIO</title>
 !Pdrivers/gpu/drm/i915/i915_reg.h DPIO
-	<table id="dpiox2">
-	  <title>Dual channel PHY (VLV/CHV/BXT)</title>
-	  <tgroup cols="8">
-	    <colspec colname="c0" />
-	    <colspec colname="c1" />
-	    <colspec colname="c2" />
-	    <colspec colname="c3" />
-	    <colspec colname="c4" />
-	    <colspec colname="c5" />
-	    <colspec colname="c6" />
-	    <colspec colname="c7" />
-	    <spanspec spanname="ch0" namest="c0" nameend="c3" />
-	    <spanspec spanname="ch1" namest="c4" nameend="c7" />
-	    <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" />
-	    <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" />
-	    <spanspec spanname="ch1pcs01" namest="c4" nameend="c5" />
-	    <spanspec spanname="ch1pcs23" namest="c6" nameend="c7" />
-	    <thead>
-	      <row>
-		<entry spanname="ch0">CH0</entry>
-		<entry spanname="ch1">CH1</entry>
-	      </row>
-	    </thead>
-	    <tbody valign="top" align="center">
-	      <row>
-		<entry spanname="ch0">CMN/PLL/REF</entry>
-		<entry spanname="ch1">CMN/PLL/REF</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0pcs01">PCS01</entry>
-		<entry spanname="ch0pcs23">PCS23</entry>
-		<entry spanname="ch1pcs01">PCS01</entry>
-		<entry spanname="ch1pcs23">PCS23</entry>
-	      </row>
-	      <row>
-		<entry>TX0</entry>
-		<entry>TX1</entry>
-		<entry>TX2</entry>
-		<entry>TX3</entry>
-		<entry>TX0</entry>
-		<entry>TX1</entry>
-		<entry>TX2</entry>
-		<entry>TX3</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0">DDI0</entry>
-		<entry spanname="ch1">DDI1</entry>
-	      </row>
-	    </tbody>
-	  </tgroup>
-	</table>
-	<table id="dpiox1">
-	  <title>Single channel PHY (CHV/BXT)</title>
-	  <tgroup cols="4">
-	    <colspec colname="c0" />
-	    <colspec colname="c1" />
-	    <colspec colname="c2" />
-	    <colspec colname="c3" />
-	    <spanspec spanname="ch0" namest="c0" nameend="c3" />
-	    <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" />
-	    <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" />
-	    <thead>
-	      <row>
-		<entry spanname="ch0">CH0</entry>
-	      </row>
-	    </thead>
-	    <tbody valign="top" align="center">
-	      <row>
-		<entry spanname="ch0">CMN/PLL/REF</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0pcs01">PCS01</entry>
-		<entry spanname="ch0pcs23">PCS23</entry>
-	      </row>
-	      <row>
-		<entry>TX0</entry>
-		<entry>TX1</entry>
-		<entry>TX2</entry>
-		<entry>TX3</entry>
-	      </row>
-	      <row>
-		<entry spanname="ch0">DDI2</entry>
-	      </row>
-	    </tbody>
-	  </tgroup>
-	</table>
       </sect2>
 
       <sect2>
@@ -4201,17 +3388,21 @@ int num_ioctls;</synopsis>
       </sect2>
     </sect1>
     <sect1>
-      <title>GuC-based Command Submission</title>
+      <title>GuC</title>
       <sect2>
-        <title>GuC</title>
+        <title>GuC-specific firmware loader</title>
 !Pdrivers/gpu/drm/i915/intel_guc_loader.c GuC-specific firmware loader
 !Idrivers/gpu/drm/i915/intel_guc_loader.c
       </sect2>
       <sect2>
-        <title>GuC Client</title>
-!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submissison
+        <title>GuC-based command submission</title>
+!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submission
 !Idrivers/gpu/drm/i915/i915_guc_submission.c
       </sect2>
+      <sect2>
+        <title>GuC Firmware Layout</title>
+!Pdrivers/gpu/drm/i915/intel_guc_fwif.h GuC Firmware Layout
+      </sect2>
     </sect1>
 
     <sect1>
@@ -4246,41 +3437,63 @@ int num_ioctls;</synopsis>
 
   <chapter id="modes_of_use">
     <title>Modes of Use</title>
-  <sect1>
-    <title>Manual switching and manual power control</title>
+    <sect1>
+      <title>Manual switching and manual power control</title>
 !Pdrivers/gpu/vga/vga_switcheroo.c Manual switching and manual power control
-  </sect1>
-  <sect1>
-    <title>Driver power control</title>
+    </sect1>
+    <sect1>
+      <title>Driver power control</title>
 !Pdrivers/gpu/vga/vga_switcheroo.c Driver power control
-  </sect1>
+    </sect1>
   </chapter>
 
-  <chapter id="pubfunctions">
-    <title>Public functions</title>
+  <chapter id="api">
+    <title>API</title>
+    <sect1>
+      <title>Public functions</title>
 !Edrivers/gpu/vga/vga_switcheroo.c
-  </chapter>
-
-  <chapter id="pubstructures">
-    <title>Public structures</title>
+    </sect1>
+    <sect1>
+      <title>Public structures</title>
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_handler
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_client_ops
-  </chapter>
-
-  <chapter id="pubconstants">
-    <title>Public constants</title>
+    </sect1>
+    <sect1>
+      <title>Public constants</title>
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_client_id
 !Finclude/linux/vga_switcheroo.h vga_switcheroo_state
-  </chapter>
-
-  <chapter id="privstructures">
-    <title>Private structures</title>
+    </sect1>
+    <sect1>
+      <title>Private structures</title>
 !Fdrivers/gpu/vga/vga_switcheroo.c vgasr_priv
 !Fdrivers/gpu/vga/vga_switcheroo.c vga_switcheroo_client
+    </sect1>
+  </chapter>
+
+  <chapter id="handlers">
+    <title>Handlers</title>
+    <sect1>
+      <title>apple-gmux Handler</title>
+!Pdrivers/platform/x86/apple-gmux.c Overview
+!Pdrivers/platform/x86/apple-gmux.c Interrupt
+      <sect2>
+        <title>Graphics mux</title>
+!Pdrivers/platform/x86/apple-gmux.c Graphics mux
+      </sect2>
+      <sect2>
+        <title>Power control</title>
+!Pdrivers/platform/x86/apple-gmux.c Power control
+      </sect2>
+      <sect2>
+        <title>Backlight control</title>
+!Pdrivers/platform/x86/apple-gmux.c Backlight control
+      </sect2>
+    </sect1>
   </chapter>
 
 !Cdrivers/gpu/vga/vga_switcheroo.c
 !Cinclude/linux/vga_switcheroo.h
+!Cdrivers/platform/x86/apple-gmux.c
 </part>
 
 </book>

Documentation/DocBook/iio.tmpl

@@ -458,7 +458,7 @@
             .scan_type = {
               .sign = 's',
               .realbits = 12,
-              .storgebits = 16,
+              .storagebits = 16,
               .shift = 4,
               .endianness = IIO_LE,
             },

Documentation/DocBook/media/Makefile

@@ -199,8 +199,10 @@ DVB_DOCUMENTED = \
 #
 
 install_media_images = \
-	$(Q)-mkdir $(MEDIA_OBJ_DIR)/media_api; \
-	cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)if [ "x$(findstring media_api.xml,$(DOCBOOKS))" != "x" ]; then \
+		mkdir -p $(MEDIA_OBJ_DIR)/media_api; \
+		cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api; \
+	fi
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@

Documentation/DocBook/media/dvb/dvbproperty.xml

@@ -76,7 +76,7 @@ int main(void)
 
 <para>NOTE: While it is possible to directly call the Kernel code like the
     above example, it is strongly recommended to use
-    <ulink url="http://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>,
+    <ulink url="https://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>,
     as it provides abstraction to work with the supported digital TV standards
     and provides methods for usual operations like program scanning and to
     read/write channel descriptor files.</para>

Documentation/DocBook/media/dvb/examples.xml

@@ -3,7 +3,7 @@
 </para>
 <para>NOTE: This section is out of date, and the code below won't even
     compile. Please refer to the
-    <ulink url="http://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>
+    <ulink url="https://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>
     for updated/recommended examples.
 </para>
 

Documentation/DocBook/media/dvb/intro.xml

@@ -32,7 +32,7 @@ and filtering several section and PES data streams at the same time.
 new standard Linux DVB API. As a commitment to the development of
 terminals based on open standards, Nokia and Convergence made it
 available to all Linux developers and published it on
-<ulink url="http://www.linuxtv.org/" /> in September 2000.
+<ulink url="https://linuxtv.org" /> in September 2000.
 Convergence is the maintainer of the Linux DVB API. Together with the
 LinuxTV community (i.e. you, the reader of this document), the Linux DVB
 API will be constantly reviewed and improved. With the Linux driver for

Documentation/DocBook/media/v4l/capture.c.xml

@@ -5,7 +5,7 @@
  *  This program can be used and distributed without restrictions.
  *
  *      This program is provided with the V4L2 API
- * see http://linuxtv.org/docs.php for more information
+ * see https://linuxtv.org/docs.php for more information
  */
 
 #include <stdio.h>

Documentation/DocBook/media/v4l/compat.xml

@@ -2666,7 +2666,7 @@ is useful to display images captured with V4L2 devices.</para>
         <para>V4L2 does not support digital terrestrial, cable or
 satellite broadcast. A separate project aiming at digital receivers
 exists. You can find its homepage at <ulink
-url="http://linuxtv.org">http://linuxtv.org</ulink>. The Linux DVB API
+url="https://linuxtv.org">https://linuxtv.org</ulink>. The Linux DVB API
 has no connection to the V4L2 API except that drivers for hybrid
 hardware may support both.</para>
       </section>

Documentation/DocBook/media/v4l/io.xml

@@ -699,7 +699,7 @@ linkend="v4l2-buf-type" /></entry>
 buffer. It depends on the negotiated data format and may change with
 each buffer for compressed variable size data like JPEG images.
 Drivers must set this field when <structfield>type</structfield>
-refers to an input stream, applications when it refers to an output stream.
+refers to a capture stream, applications when it refers to an output stream.
 If the application sets this to 0 for an output stream, then
 <structfield>bytesused</structfield> will be set to the size of the
 buffer (see the <structfield>length</structfield> field of this struct) by
@@ -720,14 +720,14 @@ linkend="buffer-flags" />.</entry>
 	    <entry>Indicates the field order of the image in the
 buffer, see <xref linkend="v4l2-field" />. This field is not used when
 the buffer contains VBI data. Drivers must set it when
-<structfield>type</structfield> refers to an input stream,
+<structfield>type</structfield> refers to a capture stream,
 applications when it refers to an output stream.</entry>
 	  </row>
 	  <row>
 	    <entry>struct timeval</entry>
 	    <entry><structfield>timestamp</structfield></entry>
 	    <entry></entry>
-	    <entry><para>For input streams this is time when the first data
+	    <entry><para>For capture streams this is time when the first data
 	    byte was captured, as returned by the
 	    <function>clock_gettime()</function> function for the relevant
 	    clock id; see <constant>V4L2_BUF_FLAG_TIMESTAMP_*</constant> in
@@ -866,7 +866,7 @@ must set this to 0.</entry>
 	    <entry></entry>
 	    <entry>The number of bytes occupied by data in the plane
 	      (its payload). Drivers must set this field when <structfield>type</structfield>
-	      refers to an input stream, applications when it refers to an output stream.
+	      refers to a capture stream, applications when it refers to an output stream.
 	      If the application sets this to 0 for an output stream, then
 	      <structfield>bytesused</structfield> will be set to the size of the
 	      plane (see the <structfield>length</structfield> field of this struct)
@@ -919,7 +919,7 @@ must set this to 0.</entry>
 	    <entry></entry>
 	    <entry>Offset in bytes to video data in the plane.
 	      Drivers must set this field when <structfield>type</structfield>
-	      refers to an input stream, applications when it refers to an output stream.
+	      refers to a capture stream, applications when it refers to an output stream.
 	      Note that data_offset is included in <structfield>bytesused</structfield>.
 	      So the size of the image in the plane is
 	      <structfield>bytesused</structfield>-<structfield>data_offset</structfield> at

Documentation/DocBook/media/v4l/media-controller.xml

@@ -58,21 +58,36 @@
     <title>Media device model</title>
     <para>Discovering a device internal topology, and configuring it at runtime,
     is one of the goals of the media controller API. To achieve this, hardware
-    devices are modelled as an oriented graph of building blocks called entities
-    connected through pads.</para>
-    <para>An entity is a basic media hardware or software building block. It can
-    correspond to a large variety of logical blocks such as physical hardware
-    devices (CMOS sensor for instance), logical hardware devices (a building
-    block in a System-on-Chip image processing pipeline), DMA channels or
-    physical connectors.</para>
-    <para>A pad is a connection endpoint through which an entity can interact
-    with other entities. Data (not restricted to video) produced by an entity
-    flows from the entity's output to one or more entity inputs. Pads should not
-    be confused with physical pins at chip boundaries.</para>
-    <para>A link is a point-to-point oriented connection between two pads,
-    either on the same entity or on different entities. Data flows from a source
-    pad to a sink pad.</para>
+    devices and Linux Kernel interfaces are modelled as graph objects on
+    an oriented graph. The object types that constitute the graph are:</para>
+    <itemizedlist>
+    <listitem><para>An <emphasis role="bold">entity</emphasis>
+    is a basic media hardware or software building block. It can correspond to
+    a large variety of logical blocks such as physical hardware devices
+    (CMOS sensor for instance), logical hardware devices (a building block in
+    a System-on-Chip image processing pipeline), DMA channels or physical
+    connectors.</para></listitem>
+    <listitem><para>An <emphasis role="bold">interface</emphasis>
+    is a graph representation of a Linux Kernel userspace API interface,
+    like a device node or a sysfs file that controls one or more entities
+    in the graph.</para></listitem>
+    <listitem><para>A <emphasis role="bold">pad</emphasis>
+    is a data connection endpoint through which an entity can interact with
+    other entities. Data (not restricted to video) produced by an entity
+    flows from the entity's output to one or more entity inputs. Pads should
+    not be confused with physical pins at chip boundaries.</para></listitem>
+    <listitem><para>A <emphasis role="bold">data link</emphasis>
+    is a point-to-point oriented connection between two pads, either on the
+    same entity or on different entities. Data flows from a source pad to a
+    sink pad.</para></listitem>
+    <listitem><para>An <emphasis role="bold">interface link</emphasis>
+    is a point-to-point bidirectional control connection between a Linux
+    Kernel interface and an entity.m</para></listitem>
+    </itemizedlist>
   </section>
+
+  <!-- All non-ioctl specific data types go here. -->
+  &sub-media-types;
 </chapter>
 
 <appendix id="media-user-func">
@@ -83,6 +98,7 @@
   &sub-media-func-ioctl;
   <!-- All ioctls go here. -->
   &sub-media-ioc-device-info;
+  &sub-media-ioc-g-topology;
   &sub-media-ioc-enum-entities;
   &sub-media-ioc-enum-links;
   &sub-media-ioc-setup-link;

Documentation/DocBook/media/v4l/media-ioc-enum-entities.xml

@@ -59,15 +59,6 @@
     <para>Entity IDs can be non-contiguous. Applications must
     <emphasis>not</emphasis> try to enumerate entities by calling
     MEDIA_IOC_ENUM_ENTITIES with increasing id's until they get an error.</para>
-    <para>Two or more entities that share a common non-zero
-    <structfield>group_id</structfield> value are considered as logically
-    grouped. Groups are used to report
-    <itemizedlist>
-      <listitem><para>ALSA, VBI and video nodes that carry the same media
-      stream</para></listitem>
-      <listitem><para>lens and flash controllers associated with a sensor</para></listitem>
-    </itemizedlist>
-    </para>
 
     <table pgwide="1" frame="none" id="media-entity-desc">
       <title>struct <structname>media_entity_desc</structname></title>
@@ -106,7 +97,7 @@
 	    <entry><structfield>revision</structfield></entry>
 	    <entry></entry>
 	    <entry></entry>
-	    <entry>Entity revision in a driver/hardware specific format.</entry>
+	    <entry>Entity revision. Always zero (obsolete)</entry>
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
@@ -120,7 +111,7 @@
 	    <entry><structfield>group_id</structfield></entry>
 	    <entry></entry>
 	    <entry></entry>
-	    <entry>Entity group ID</entry>
+	    <entry>Entity group ID. Always zero (obsolete)</entry>
 	  </row>
 	  <row>
 	    <entry>__u16</entry>
@@ -171,97 +162,6 @@
 	</tbody>
       </tgroup>
     </table>
-
-    <table frame="none" pgwide="1" id="media-entity-type">
-      <title>Media entity types</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE</constant></entry>
-	    <entry>Unknown device node</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_V4L</constant></entry>
-	    <entry>V4L video, radio or vbi device node</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_FB</constant></entry>
-	    <entry>Frame buffer device node</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_ALSA</constant></entry>
-	    <entry>ALSA card</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_FE</constant></entry>
-	    <entry>DVB frontend devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_DEMUX</constant></entry>
-	    <entry>DVB demux devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_DVR</constant></entry>
-	    <entry>DVB DVR devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_CA</constant></entry>
-	    <entry>DVB CAM devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_DEVNODE_DVB_NET</constant></entry>
-	    <entry>DVB network devnode</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV</constant></entry>
-	    <entry>Unknown V4L sub-device</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_SENSOR</constant></entry>
-	    <entry>Video sensor</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_FLASH</constant></entry>
-	    <entry>Flash controller</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_LENS</constant></entry>
-	    <entry>Lens controller</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_DECODER</constant></entry>
-	    <entry>Video decoder, the basic function of the video decoder is to
-	    accept analogue video from a wide variety of sources such as
-	    broadcast, DVD players, cameras and video cassette recorders, in
-	    either NTSC, PAL or HD format and still occasionally SECAM, separate
-	    it into its component parts, luminance and chrominance, and output
-	    it in some digital video standard, with appropriate embedded timing
-	    signals.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_ENT_T_V4L2_SUBDEV_TUNER</constant></entry>
-	    <entry>TV and/or radio tuner</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-
-    <table frame="none" pgwide="1" id="media-entity-flag">
-      <title>Media entity flags</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_ENT_FL_DEFAULT</constant></entry>
-	    <entry>Default entity for its type. Used to discover the default
-	    audio, VBI and video devices, the default camera sensor, ...</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
   </refsect1>
 
   <refsect1>

Documentation/DocBook/media/v4l/media-ioc-enum-links.xml

@@ -118,35 +118,6 @@
       </tgroup>
     </table>
 
-    <table frame="none" pgwide="1" id="media-pad-flag">
-      <title>Media pad flags</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_PAD_FL_SINK</constant></entry>
-	    <entry>Input pad, relative to the entity. Input pads sink data and
-	    are targets of links.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_PAD_FL_SOURCE</constant></entry>
-	    <entry>Output pad, relative to the entity. Output pads source data
-	    and are origins of links.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_PAD_FL_MUST_CONNECT</constant></entry>
-	    <entry>If this flag is set and the pad is linked to any other
-	    pad, then at least one of those links must be enabled for the
-	    entity to be able to stream. There could be temporary reasons
-	    (e.g. device configuration dependent) for the pad to need
-	    enabled links even when this flag isn't set; the absence of the
-	    flag doesn't imply there is none.</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-
     <table pgwide="1" frame="none" id="media-link-desc">
       <title>struct <structname>media_link_desc</structname></title>
       <tgroup cols="3">
@@ -171,33 +142,6 @@
       </tgroup>
     </table>
 
-    <table frame="none" pgwide="1" id="media-link-flag">
-      <title>Media link flags</title>
-      <tgroup cols="2">
-        <colspec colname="c1"/>
-        <colspec colname="c2"/>
-	<tbody valign="top">
-	  <row>
-	    <entry><constant>MEDIA_LNK_FL_ENABLED</constant></entry>
-	    <entry>The link is enabled and can be used to transfer media data.
-	    When two or more links target a sink pad, only one of them can be
-	    enabled at a time.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_LNK_FL_IMMUTABLE</constant></entry>
-	    <entry>The link enabled state can't be modified at runtime. An
-	    immutable link is always enabled.</entry>
-	  </row>
-	  <row>
-	    <entry><constant>MEDIA_LNK_FL_DYNAMIC</constant></entry>
-	    <entry>The link enabled state can be modified during streaming. This
-	    flag is set by drivers and is read-only for applications.</entry>
-	  </row>
-	</tbody>
-      </tgroup>
-    </table>
-    <para>One and only one of <constant>MEDIA_PAD_FL_SINK</constant> and
-    <constant>MEDIA_PAD_FL_SOURCE</constant> must be set for every pad.</para>
   </refsect1>
 
   <refsect1>

Documentation/DocBook/media/v4l/media-ioc-g-topology.xml

@@ -0,0 +1,394 @@
+<refentry id="media-g-topology">
+  <refmeta>
+    <refentrytitle>ioctl MEDIA_IOC_G_TOPOLOGY</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>MEDIA_IOC_G_TOPOLOGY</refname>
+    <refpurpose>Enumerate the graph topology and graph element properties</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 media_v2_topology *<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='media-func-open'><function>open()</function></link>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>MEDIA_IOC_G_TOPOLOGY</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para><emphasis role="bold">NOTE:</emphasis> This new ioctl is programmed to be added on Kernel 4.6. Its definition/arguments may change until its final version.</para>
+
+    <para>The typical usage of this ioctl is to call it twice.
+    On the first call, the structure defined at &media-v2-topology; should
+    be zeroed. At return, if no errors happen, this ioctl will return the
+    <constant>topology_version</constant> and the total number of entities,
+    interfaces, pads and links.</para>
+    <para>Before the second call, the userspace should allocate arrays to
+    store the graph elements that are desired, putting the pointers to them
+    at the ptr_entities, ptr_interfaces, ptr_links and/or ptr_pads, keeping
+    the other values untouched.</para>
+    <para>If the <constant>topology_version</constant> remains the same, the
+    ioctl should fill the desired arrays with the media graph elements.</para>
+
+    <table pgwide="1" frame="none" id="media-v2-topology">
+      <title>struct <structname>media_v2_topology</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>topology_version</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Version of the media graph topology. When the graph is
+		    created, this field starts with zero. Every time a graph
+		    element is added or removed, this field is
+		    incremented.</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_entities</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Number of entities in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_entities</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the entities array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   entities. It will just update
+		   <constant>num_entities</constant></entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_interfaces</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Number of interfaces in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_interfaces</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the interfaces array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   interfaces. It will just update
+		   <constant>num_interfaces</constant></entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_pads</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Total number of pads in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_pads</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the pads array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   pads. It will just update
+		   <constant>num_pads</constant></entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>num_links</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Total number of data and interface links in the graph</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>ptr_links</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>A pointer to a memory area where the links array
+		   will be stored, converted to a 64-bits integer.
+		   It can be zero. if zero, the ioctl won't store the
+		   links. It will just update
+		   <constant>num_links</constant></entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-entity">
+      <title>struct <structname>media_v2_entity</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the entity.</entry>
+	  </row>
+	  <row>
+	    <entry>char</entry>
+	    <entry><structfield>name</structfield>[64]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Entity name as an UTF-8 NULL-terminated string.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>function</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Entity main function, see <xref linkend="media-entity-type" /> for details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[12]</entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-interface">
+      <title>struct <structname>media_v2_interface</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the interface.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>intf_type</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Interface type, see <xref linkend="media-intf-type" /> for details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Interface flags. Currently unused.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[9]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	  <row>
+	    <entry>struct media_v2_intf_devnode</entry>
+	    <entry><structfield>devnode</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Used only for device node interfaces. See <xref linkend="media-v2-intf-devnode" /> for details..</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-intf-devnode">
+      <title>struct <structname>media_v2_interface</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>major</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Device node major number.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>minor</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Device node minor number.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-pad">
+      <title>struct <structname>media_v2_pad</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the pad.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>entity_id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the entity where this pad belongs.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Pad flags, see <xref linkend="media-pad-flag" /> for more details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[9]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="media-v2-link">
+      <title>struct <structname>media_v2_pad</structname></title>
+      <tgroup cols="5">
+	<colspec colname="c1" />
+	<colspec colname="c2" />
+	<colspec colname="c3" />
+	<colspec colname="c4" />
+	<colspec colname="c5" />
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Unique ID for the pad.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>source_id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>
+	       <para>On pad to pad links: unique ID for the source pad.</para>
+	       <para>On interface to entity links: unique ID for the interface.</para>
+	    </entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>sink_id</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>
+	       <para>On pad to pad links: unique ID for the sink pad.</para>
+	       <para>On interface to entity links: unique ID for the entity.</para>
+	    </entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>flags</structfield></entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Link flags, see <xref linkend="media-link-flag" /> for more details.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[5]</entry>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry>Reserved for future extensions. Drivers and applications must
+	    set this array to zero.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>ENOSPC</errorcode></term>
+	<listitem>
+	  <para>This is returned when either one or more of the num_entities,
+	  num_interfaces, num_links or num_pads are non-zero and are smaller
+	  than the actual number of elements inside the graph. This may happen
+	  if the <constant>topology_version</constant> changed when compared
+	  to the last time this ioctl was called. Userspace should usually
+	  free the area for the pointers, zero the struct elements and call
+	  this ioctl again.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>

Documentation/DocBook/media/v4l/media-types.xml

@@ -0,0 +1,240 @@
+<section id="media-controller-types">
+<title>Types and flags used to represent the media graph elements</title>
+
+    <table frame="none" pgwide="1" id="media-entity-type">
+      <title>Media entity types</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_UNKNOWN</constant> and <constant>MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN</constant></entry>
+	    <entry>Unknown entity. That generally indicates that
+	    a driver didn't initialize properly the entity, with is a Kernel bug</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_V4L</constant></entry>
+	    <entry>Data streaming input and/or output entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_VBI</constant></entry>
+	    <entry>V4L VBI streaming input or output entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_SWRADIO</constant></entry>
+	    <entry>V4L Software Digital Radio (SDR) streaming input or output entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IO_DTV</constant></entry>
+	    <entry>DVB Digital TV streaming input or output entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_DTV_DEMOD</constant></entry>
+	    <entry>Digital TV demodulator entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_TS_DEMUX</constant></entry>
+	    <entry>MPEG Transport stream demux entity. Could be implemented on hardware or in Kernelspace by the Linux DVB subsystem.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_DTV_CA</constant></entry>
+	    <entry>Digital TV Conditional Access module (CAM) entity</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_DTV_NET_DECAP</constant></entry>
+	    <entry>Digital TV network ULE/MLE desencapsulation entity. Could be implemented on hardware or in Kernelspace</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CONN_RF</constant></entry>
+	    <entry>Connector for a Radio Frequency (RF) signal.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CONN_SVIDEO</constant></entry>
+	    <entry>Connector for a S-Video signal.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CONN_COMPOSITE</constant></entry>
+	    <entry>Connector for a RGB composite signal.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CONN_TEST</constant></entry>
+	    <entry>Connector for a test generator.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_CAM_SENSOR</constant></entry>
+	    <entry>Camera video sensor entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_FLASH</constant></entry>
+	    <entry>Flash controller entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_LENS</constant></entry>
+	    <entry>Lens controller entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_ATV_DECODER</constant></entry>
+	    <entry>Analog video decoder, the basic function of the video decoder
+	    is to accept analogue video from a wide variety of sources such as
+	    broadcast, DVD players, cameras and video cassette recorders, in
+	    either NTSC, PAL, SECAM or HD format, separating the stream
+	    into its component parts, luminance and chrominance, and output
+	    it in some digital video standard, with appropriate timing
+	    signals.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_TUNER</constant></entry>
+	    <entry>Digital TV, analog TV, radio and/or software radio tuner.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="media-entity-flag">
+      <title>Media entity flags</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_ENT_FL_DEFAULT</constant></entry>
+	    <entry>Default entity for its type. Used to discover the default
+	    audio, VBI and video devices, the default camera sensor, ...</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_FL_CONNECTOR</constant></entry>
+	    <entry>The entity represents a data conector</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="media-intf-type">
+      <title>Media interface types</title>
+      <tgroup cols="3">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<colspec colname="c3"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_FE</constant></entry>
+	    <entry>Device node interface for the Digital TV frontend</entry>
+	    <entry>typically, /dev/dvb/adapter?/frontend?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_DEMUX</constant></entry>
+	    <entry>Device node interface for the Digital TV demux</entry>
+	    <entry>typically, /dev/dvb/adapter?/demux?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_DVR</constant></entry>
+	    <entry>Device node interface for the Digital TV DVR</entry>
+	    <entry>typically, /dev/dvb/adapter?/dvr?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_CA</constant></entry>
+	    <entry>Device node interface for the Digital TV Conditional Access</entry>
+	    <entry>typically, /dev/dvb/adapter?/ca?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_DVB_FE</constant></entry>
+	    <entry>Device node interface for the Digital TV network control</entry>
+	    <entry>typically, /dev/dvb/adapter?/net?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_VIDEO</constant></entry>
+	    <entry>Device node interface for video (V4L)</entry>
+	    <entry>typically, /dev/video?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_VBI</constant></entry>
+	    <entry>Device node interface for VBI (V4L)</entry>
+	    <entry>typically, /dev/vbi?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_RADIO</constant></entry>
+	    <entry>Device node interface for radio (V4L)</entry>
+	    <entry>typically, /dev/vbi?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_SUBDEV</constant></entry>
+	    <entry>Device node interface for a V4L subdevice</entry>
+	    <entry>typically, /dev/v4l-subdev?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_V4L_SWRADIO</constant></entry>
+	    <entry>Device node interface for Software Defined Radio (V4L)</entry>
+	    <entry>typically, /dev/swradio?</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table frame="none" pgwide="1" id="media-pad-flag">
+      <title>Media pad flags</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_PAD_FL_SINK</constant></entry>
+	    <entry>Input pad, relative to the entity. Input pads sink data and
+	    are targets of links.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_PAD_FL_SOURCE</constant></entry>
+	    <entry>Output pad, relative to the entity. Output pads source data
+	    and are origins of links.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_PAD_FL_MUST_CONNECT</constant></entry>
+	    <entry>If this flag is set and the pad is linked to any other
+	    pad, then at least one of those links must be enabled for the
+	    entity to be able to stream. There could be temporary reasons
+	    (e.g. device configuration dependent) for the pad to need
+	    enabled links even when this flag isn't set; the absence of the
+	    flag doesn't imply there is none.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <para>One and only one of <constant>MEDIA_PAD_FL_SINK</constant> and
+    <constant>MEDIA_PAD_FL_SOURCE</constant> must be set for every pad.</para>
+
+    <table frame="none" pgwide="1" id="media-link-flag">
+      <title>Media link flags</title>
+      <tgroup cols="2">
+	<colspec colname="c1"/>
+	<colspec colname="c2"/>
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_ENABLED</constant></entry>
+	    <entry>The link is enabled and can be used to transfer media data.
+	    When two or more links target a sink pad, only one of them can be
+	    enabled at a time.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_IMMUTABLE</constant></entry>
+	    <entry>The link enabled state can't be modified at runtime. An
+	    immutable link is always enabled.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_DYNAMIC</constant></entry>
+	    <entry>The link enabled state can be modified during streaming. This
+	    flag is set by drivers and is read-only for applications.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_LNK_FL_LINK_TYPE</constant></entry>
+	    <entry><para>This is a bitmask that defines the type of the link.
+		   Currently, two types of links are supported:</para>
+	    <para><constant>MEDIA_LNK_FL_DATA_LINK</constant>
+	    if the link is between two pads</para>
+	    <para><constant>MEDIA_LNK_FL_INTERFACE_LINK</constant>
+	    if the link is between an interface and an entity</para></entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+</section>

Documentation/DocBook/media/v4l/v4l2.xml

@@ -151,6 +151,16 @@ Rubli, Andy Walls, Muralidharan Karicheri, Mauro Carvalho Chehab,
 structs, ioctls) must be noted in more detail in the history chapter
 (compat.xml), along with the possible impact on existing drivers and
 applications. -->
+      <revision>
+	<revnumber>4.5</revnumber>
+	<date>2015-10-29</date>
+	<authorinitials>rr</authorinitials>
+	<revremark>Extend vidioc-g-ext-ctrls;. Replace ctrl_class with a new
+union with ctrl_class and which. Which is used to select the current value of
+the control or the default value.
+	</revremark>
+      </revision>
+
       <revision>
 	<revnumber>4.4</revnumber>
 	<date>2015-05-26</date>

Documentation/DocBook/media/v4l/vidioc-create-bufs.xml

@@ -58,7 +58,7 @@
     <para>This ioctl is used to create buffers for <link linkend="mmap">memory
 mapped</link> or <link linkend="userp">user pointer</link> or <link
 linkend="dmabuf">DMA buffer</link> I/O. It can be used as an alternative or in
-addition to the <constant>VIDIOC_REQBUFS</constant> ioctl, when a tighter
+addition to the &VIDIOC-REQBUFS; ioctl, when a tighter
 control over buffers is required. This ioctl can be called multiple times to
 create buffers of different sizes.</para>
 
@@ -71,30 +71,28 @@ zeroed.</para>
 
     <para>The <structfield>format</structfield> field specifies the image format
 that the buffers must be able to handle. The application has to fill in this
-&v4l2-format;. Usually this will be done using the
-<constant>VIDIOC_TRY_FMT</constant> or <constant>VIDIOC_G_FMT</constant> ioctl()
-to ensure that the requested format is supported by the driver. Unsupported
-formats will result in an error.</para>
+&v4l2-format;. Usually this will be done using the &VIDIOC-TRY-FMT; or &VIDIOC-G-FMT; ioctls
+to ensure that the requested format is supported by the driver.
+Based on the format's <structfield>type</structfield> field the requested buffer
+size (for single-planar) or plane sizes (for multi-planar formats) will be
+used for the allocated buffers. The driver may return an error if the size(s)
+are not supported by the hardware (usually because they are too small).</para>
 
     <para>The buffers created by this ioctl will have as minimum size the size
-defined by the <structfield>format.pix.sizeimage</structfield> field. If the
+defined by the <structfield>format.pix.sizeimage</structfield> field (or the
+corresponding fields for other format types). Usually if the
 <structfield>format.pix.sizeimage</structfield> field is less than the minimum
-required for the given format, then <structfield>sizeimage</structfield> will be
-increased by the driver to that minimum to allocate the buffers. If it is
-larger, then the value will be used as-is. The same applies to the
-<structfield>sizeimage</structfield> field of the
-<structname>v4l2_plane_pix_format</structname> structure in the case of
-multiplanar formats.</para>
+required for the given format, then an error will be returned since drivers will
+typically not allow this. If it is larger, then the value will be used as-is.
+In other words, the driver may reject the requested size, but if it is accepted
+the driver will use it unchanged.</para>
 
     <para>When the ioctl is called with a pointer to this structure the driver
 will attempt to allocate up to the requested number of buffers and store the
 actual number allocated and the starting index in the
 <structfield>count</structfield> and the <structfield>index</structfield> fields
 respectively. On return <structfield>count</structfield> can be smaller than
-the number requested. The driver may also increase buffer sizes if required,
-however, it will not update <structfield>sizeimage</structfield> field values.
-The user has to use <constant>VIDIOC_QUERYBUF</constant> to retrieve that
-information.</para>
+the number requested.</para>
 
     <table pgwide="1" frame="none" id="v4l2-create-buffers">
       <title>struct <structname>v4l2_create_buffers</structname></title>

Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml

@@ -99,7 +99,7 @@ if the driver supports writing registers to the device.</para>
     <para>We recommended the <application>v4l2-dbg</application>
 utility over calling this ioctl directly. It is available from the
 LinuxTV v4l-dvb repository; see <ulink
-url="http://linuxtv.org/repo/">http://linuxtv.org/repo/</ulink> for
+url="https://linuxtv.org/repo/">https://linuxtv.org/repo/</ulink> for
 access instructions.</para>
 
     <!-- Note for convenience vidioc-dbg-g-register.sgml

Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml

@@ -117,7 +117,7 @@ However when a driver supports these ioctls it must also support
     <para>We recommended the <application>v4l2-dbg</application>
 utility over calling these ioctls directly. It is available from the
 LinuxTV v4l-dvb repository; see <ulink
-url="http://linuxtv.org/repo/">http://linuxtv.org/repo/</ulink> for
+url="https://linuxtv.org/repo/">https://linuxtv.org/repo/</ulink> for
 access instructions.</para>
 
     <!-- Note for convenience vidioc-dbg-g-chip-info.sgml

Documentation/DocBook/media/v4l/vidioc-enumstd.xml

@@ -198,7 +198,7 @@ video4linux-list@redhat.com on 17 Oct 2002
 <constant>V4L2_STD_ATSC_16_VSB</constant> are U.S. terrestrial digital
 TV standards. Presently the V4L2 API does not support digital TV. See
 also the Linux DVB API at <ulink
-url="http://linuxtv.org">http://linuxtv.org</ulink>.</para>
+url="https://linuxtv.org">https://linuxtv.org</ulink>.</para>
 <para><programlisting>
 #define V4L2_STD_PAL_BG         (V4L2_STD_PAL_B         |\
 				 V4L2_STD_PAL_B1        |\

Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml

@@ -61,7 +61,7 @@ must belong to the same control class.</para>
 
     <para>Applications must always fill in the
 <structfield>count</structfield>,
-<structfield>ctrl_class</structfield>,
+<structfield>which</structfield>,
 <structfield>controls</structfield> and
 <structfield>reserved</structfield> fields of &v4l2-ext-controls;, and
 initialize the &v4l2-ext-control; array pointed to by the
@@ -109,7 +109,7 @@ the driver whether wrong values are automatically adjusted to a valid
 value or if an error is returned.</para>
 
     <para>When the <structfield>id</structfield> or
-<structfield>ctrl_class</structfield> is invalid drivers return an
+<structfield>which</structfield> is invalid drivers return an
 &EINVAL;. When the value is out of bounds drivers can choose to take
 the closest valid value or return an &ERANGE;, whatever seems more
 appropriate. In the first case the new value is set in
@@ -223,7 +223,12 @@ Valid if <constant>V4L2_CTRL_FLAG_HAS_PAYLOAD</constant> is set for this control
       <tgroup cols="3">
 	&cs-str;
 	<tbody valign="top">
+	 <row>
+	    <entry>union</entry>
+	    <entry>(anonymous)</entry>
+	  </row>
 	  <row>
+	    <entry></entry>
 	    <entry>__u32</entry>
 	    <entry><structfield>ctrl_class</structfield></entry>
 	    <entry>The control class to which all controls belong, see
@@ -233,6 +238,23 @@ belong to any control class. Whether drivers support this can be tested by setti
 <structfield>ctrl_class</structfield> to 0 and calling <constant>VIDIOC_TRY_EXT_CTRLS</constant>
 with a <structfield>count</structfield> of 0. If that succeeds, then the driver
 supports this feature.</entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry>__u32</entry>
+	    <entry><structfield>which</structfield></entry>
+	    <entry><para>Which value of the control to get/set/try. <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>
+will return the current value of the control and <constant>V4L2_CTRL_WHICH_DEF_VAL</constant> will
+return the default value of the control. Please note that you can only get the default value of the
+control, you cannot set or try it.</para>
+<para>For backwards compatibility you can also use a control class here (see
+<xref linkend="ctrl-class" />). In that case all controls have to belong to that
+control class. This usage is deprecated, instead just use <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>.
+There are some very old drivers that do not yet support <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>
+and that require a control class here. You can test for such drivers by setting ctrl_class to
+<constant>V4L2_CTRL_WHICH_CUR_VAL</constant> and calling VIDIOC_TRY_EXT_CTRLS with a count of 0.
+If that fails, then the driver does not support <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>.</para>
+</entry>
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
@@ -390,7 +412,7 @@ These controls are described in <xref linkend="rf-tuner-controls" />.</entry>
 	<listitem>
 	  <para>The &v4l2-ext-control; <structfield>id</structfield>
 is invalid, the &v4l2-ext-controls;
-<structfield>ctrl_class</structfield> is invalid, or the &v4l2-ext-control;
+<structfield>which</structfield> is invalid, or the &v4l2-ext-control;
 <structfield>value</structfield> was inappropriate (e.g. the given menu
 index is not supported by the driver). This error code is
 also returned by the <constant>VIDIOC_S_EXT_CTRLS</constant> and

Documentation/DocBook/media_api.tmpl

@@ -19,10 +19,10 @@
 <!ENTITY cs-def                 "<colspec colname='c1' colwidth='3*' /><colspec colname='c2' colwidth='1*' /><colspec colname='c3' colwidth='4*' /><spanspec spanname='hspan' namest='c1' nameend='c3' />">
 
 <!-- Video for Linux mailing list address. -->
-<!ENTITY v4l-ml                 "<ulink url='http://www.linuxtv.org/lists.php'>http://www.linuxtv.org/lists.php</ulink>">
+<!ENTITY v4l-ml                 "<ulink url='https://linuxtv.org/lists.php'>https://linuxtv.org/lists.php</ulink>">
 
 <!-- LinuxTV v4l-dvb repository. -->
-<!ENTITY v4l-dvb		"<ulink url='http://linuxtv.org/repo/'>http://linuxtv.org/repo/</ulink>">
+<!ENTITY v4l-dvb		"<ulink url='https://linuxtv.org/repo/'>https://linuxtv.org/repo/</ulink>">
 <!ENTITY dash-ent-8             "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-10            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-12            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
@@ -91,7 +91,7 @@
 	      components, like mixers, PCM capture, PCM playback, etc, which
 	      are controlled via ALSA API.</para>
 	<para>For additional information and for the latest development code,
-		see: <ulink url="http://linuxtv.org">http://linuxtv.org</ulink>.</para>
+		see: <ulink url="https://linuxtv.org">https://linuxtv.org</ulink>.</para>
 	<para>For discussing improvements, reporting troubles, sending new drivers, etc, please mail to: <ulink url="http://vger.kernel.org/vger-lists.html#linux-media">Linux Media Mailing List (LMML).</ulink>.</para>
 </preface>
 

Documentation/DocBook/mtdnand.tmpl

@@ -162,12 +162,15 @@
 	<sect1 id="Basic_defines">
 		<title>Basic defines</title>
 		<para>
-			At least you have to provide a mtd structure and
-			a storage for the ioremap'ed chip address.
-			You can allocate the mtd structure using kmalloc
-			or you can allocate it statically.
-			In case of static allocation you have to allocate
-			a nand_chip structure too.
+			At least you have to provide a nand_chip structure
+			and a storage for the ioremap'ed chip address.
+			You can allocate the nand_chip structure using
+			kmalloc or you can allocate it statically.
+			The NAND chip structure embeds an mtd structure
+			which will be registered to the MTD subsystem.
+			You can extract a pointer to the mtd structure
+			from a nand_chip pointer using the nand_to_mtd()
+			helper.
 		</para>
 		<para>
 			Kmalloc based example
@@ -180,7 +183,6 @@ static void __iomem *baseaddr;
 			Static example
 		</para>
 		<programlisting>
-static struct mtd_info board_mtd;
 static struct nand_chip board_chip;
 static void __iomem *baseaddr;
 		</programlisting>
@@ -235,7 +237,7 @@ static void board_hwcontrol(struct mtd_info *mtd, int cmd)
 		<programlisting>
 static void board_hwcontrol(struct mtd_info *mtd, int cmd)
 {
-	struct nand_chip *this = (struct nand_chip *) mtd->priv;
+	struct nand_chip *this = mtd_to_nand(mtd);
 	switch(cmd){
 		case NAND_CTL_SETCLE: this->IO_ADDR_W |= CLE_ADRR_BIT;  break;
 		case NAND_CTL_CLRCLE: this->IO_ADDR_W &amp;= ~CLE_ADRR_BIT; break;
@@ -274,13 +276,15 @@ static int __init board_init (void)
 	int err = 0;
 
 	/* Allocate memory for MTD device structure and private data */
-	board_mtd = kzalloc(sizeof(struct mtd_info) + sizeof(struct nand_chip), GFP_KERNEL);
-	if (!board_mtd) {
+	this = kzalloc(sizeof(struct nand_chip), GFP_KERNEL);
+	if (!this) {
 		printk ("Unable to allocate NAND MTD device structure.\n");
 		err = -ENOMEM;
 		goto out;
 	}
 
+	board_mtd = nand_to_mtd(this);
+
 	/* map physical address */
 	baseaddr = ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
 	if (!baseaddr) {
@@ -289,11 +293,6 @@ static int __init board_init (void)
 		goto out_mtd;
 	}
 
-	/* Get pointer to private data */
-	this = (struct nand_chip *) ();
-	/* Link the private data with the MTD structure */
-	board_mtd->priv = this;
-
 	/* Set address of NAND IO lines */
 	this->IO_ADDR_R = baseaddr;
 	this->IO_ADDR_W = baseaddr;
@@ -317,7 +316,7 @@ static int __init board_init (void)
 out_ior:
 	iounmap(baseaddr);
 out_mtd:
-	kfree (board_mtd);
+	kfree (this);
 out:
 	return err;
 }
@@ -343,7 +342,7 @@ static void __exit board_cleanup (void)
 	iounmap(baseaddr);
 	
 	/* Free the MTD device structure */
-	kfree (board_mtd);
+	kfree (mtd_to_nand(board_mtd));
 }
 module_exit(board_cleanup);
 #endif
@@ -399,7 +398,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 		<programlisting>
 static void board_select_chip (struct mtd_info *mtd, int chip)
 {
-	struct nand_chip *this = (struct nand_chip *) mtd->priv;
+	struct nand_chip *this = mtd_to_nand(mtd);
 	
 	/* Deselect all chips */
 	this->IO_ADDR_R &amp;= ~BOARD_NAND_ADDR_MASK;

Documentation/HOWTO

@@ -209,7 +209,7 @@ tools.  One such tool that is particularly recommended is the Linux
 Cross-Reference project, which is able to present source code in a
 self-referential, indexed webpage format. An excellent up-to-date
 repository of the kernel code may be found at:
-	http://lxr.linux.no/+trees
+	http://lxr.free-electrons.com/
 
 
 The development process

Documentation/Makefile

@@ -1,4 +1,4 @@
 subdir-y := accounting auxdisplay blackfin connector \
 	filesystems filesystems ia64 laptops mic misc-devices \
-	networking pcmcia prctl ptp spi timers vDSO video4linux \
+	networking pcmcia prctl ptp timers vDSO video4linux \
 	watchdog

Documentation/accounting/getdelays.c

@@ -375,7 +375,8 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	if ((nl_sd = create_nl_socket(NETLINK_GENERIC)) < 0)
+	nl_sd = create_nl_socket(NETLINK_GENERIC);
+	if (nl_sd < 0)
 		err(1, "error creating Netlink socket\n");
 
 

Documentation/arm/Marvell/README

@@ -233,29 +233,30 @@ MMP/MMP2 family (communication processor)
    Linux kernel mach directory: arch/arm/mach-mmp
    Linux kernel plat directory: arch/arm/plat-pxa
 
-Berlin family (Digital Entertainment)
+Berlin family (Multimedia Solutions)
 -------------------------------------
 
   Flavors:
-	88DE3005, Armada 1500-mini
+	88DE3005, Armada 1500 Mini
 		Design name:	BG2CD
 		Core:		ARM Cortex-A9, PL310 L2CC
-		Homepage:	http://www.marvell.com/digital-entertainment/armada-1500-mini/
+		Homepage:	http://www.marvell.com/multimedia-solutions/armada-1500-mini/
+        88DE3006, Armada 1500 Mini Plus
+                Design name:    BG2CDP
+                Core:           Dual Core ARM Cortex-A7
+                Homepage:       http://www.marvell.com/multimedia-solutions/armada-1500-mini-plus/
 	88DE3100, Armada 1500
 		Design name:	BG2
 		Core:		Marvell PJ4B (ARMv7), Tauros3 L2CC
-		Homepage:	http://www.marvell.com/digital-entertainment/armada-1500/
-		Product Brief:	http://www.marvell.com/digital-entertainment/armada-1500/assets/Marvell-ARMADA-1500-Product-Brief.pdf
+		Product Brief:	http://www.marvell.com/multimedia-solutions/armada-1500/assets/Marvell-ARMADA-1500-Product-Brief.pdf
 	88DE3114, Armada 1500 Pro
-		Design name:	BG2-Q
+		Design name:	BG2Q
 		Core:		Quad Core ARM Cortex-A9, PL310 L2CC
-		Homepage:	http://www.marvell.com/digital-entertainment/armada-1500-pro/
-		Product Brief:	http://www.marvell.com/digital-entertainment/armada-1500-pro/assets/Marvell_ARMADA_1500_PRO-01_product_brief.pdf
 	88DE????
 		Design name:	BG3
 		Core:		ARM Cortex-A15, CA15 integrated L2CC
 
-  Homepage: http://www.marvell.com/digital-entertainment/
+  Homepage: http://www.marvell.com/multimedia-solutions/
   Directory: arch/arm/mach-berlin
 
   Comments:

Documentation/arm/pxa/mfp.txt

@@ -49,7 +49,7 @@ to this new MFP mechanism, here are several key points:
      internal controllers like PWM, SSP and UART, with 128 internal signals
      which can be routed to external through one or more MFPs (e.g. GPIO<0>
      can be routed through either MFP_PIN_GPIO0 as well as MFP_PIN_GPIO0_2,
-     see arch/arm/mach-pxa/mach/include/mfp-pxa300.h)
+     see arch/arm/mach-pxa/mfp-pxa300.h)
 
   2. Alternate function configuration is removed from this GPIO controller,
      the remaining functions are pure GPIO-specific, i.e.
@@ -76,11 +76,11 @@ For board code writers, here are some guidelines:
 
 1. include ONE of the following header files in your <board>.c:
 
-   - #include <mach/mfp-pxa25x.h>
-   - #include <mach/mfp-pxa27x.h>
-   - #include <mach/mfp-pxa300.h>
-   - #include <mach/mfp-pxa320.h>
-   - #include <mach/mfp-pxa930.h>
+   - #include "mfp-pxa25x.h"
+   - #include "mfp-pxa27x.h"
+   - #include "mfp-pxa300.h"
+   - #include "mfp-pxa320.h"
+   - #include "mfp-pxa930.h"
 
    NOTE: only one file in your <board>.c, depending on the processors used,
    because pin configuration definitions may conflict in these file (i.e.
@@ -203,20 +203,20 @@ make them effective there-after.
     1. Unified pin definitions - enum constants for all configurable pins
     2. processor-neutral bit definitions for a possible MFP configuration
 
-  - arch/arm/mach-pxa/include/mach/mfp-pxa3xx.h
+  - arch/arm/mach-pxa/mfp-pxa3xx.h
 
   for PXA3xx specific MFPR register bit definitions and PXA3xx common pin
   configurations
 
-  - arch/arm/mach-pxa/include/mach/mfp-pxa2xx.h
+  - arch/arm/mach-pxa/mfp-pxa2xx.h
 
   for PXA2xx specific definitions and PXA25x/PXA27x common pin configurations
 
-  - arch/arm/mach-pxa/include/mach/mfp-pxa25x.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa27x.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa300.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa320.h
-    arch/arm/mach-pxa/include/mach/mfp-pxa930.h
+  - arch/arm/mach-pxa/mfp-pxa25x.h
+    arch/arm/mach-pxa/mfp-pxa27x.h
+    arch/arm/mach-pxa/mfp-pxa300.h
+    arch/arm/mach-pxa/mfp-pxa320.h
+    arch/arm/mach-pxa/mfp-pxa930.h
 
   for processor specific definitions
 

Documentation/arm64/silicon-errata.txt

@@ -0,0 +1,58 @@
+                Silicon Errata and Software Workarounds
+                =======================================
+
+Author: Will Deacon <will.deacon@arm.com>
+Date  : 27 November 2015
+
+It is an unfortunate fact of life that hardware is often produced with
+so-called "errata", which can cause it to deviate from the architecture
+under specific circumstances.  For hardware produced by ARM, these
+errata are broadly classified into the following categories:
+
+  Category A: A critical error without a viable workaround.
+  Category B: A significant or critical error with an acceptable
+              workaround.
+  Category C: A minor error that is not expected to occur under normal
+              operation.
+
+For more information, consult one of the "Software Developers Errata
+Notice" documents available on infocenter.arm.com (registration
+required).
+
+As far as Linux is concerned, Category B errata may require some special
+treatment in the operating system. For example, avoiding a particular
+sequence of code, or configuring the processor in a particular way. A
+less common situation may require similar actions in order to declassify
+a Category A erratum into a Category C erratum. These are collectively
+known as "software workarounds" and are only required in the minority of
+cases (e.g. those cases that both require a non-secure workaround *and*
+can be triggered by Linux).
+
+For software workarounds that may adversely impact systems unaffected by
+the erratum in question, a Kconfig entry is added under "Kernel
+Features" -> "ARM errata workarounds via the alternatives framework".
+These are enabled by default and patched in at runtime when an affected
+CPU is detected. For less-intrusive workarounds, a Kconfig option is not
+available and the code is structured (preferably with a comment) in such
+a way that the erratum will not be hit.
+
+This approach can make it slightly onerous to determine exactly which
+errata are worked around in an arbitrary kernel source tree, so this
+file acts as a registry of software workarounds in the Linux Kernel and
+will be updated when new workarounds are committed and backported to
+stable kernels.
+
+| Implementor    | Component       | Erratum ID      | Kconfig                 |
++----------------+-----------------+-----------------+-------------------------+
+| ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319    |
+| ARM            | Cortex-A53      | #827319         | ARM64_ERRATUM_827319    |
+| ARM            | Cortex-A53      | #824069         | ARM64_ERRATUM_824069    |
+| ARM            | Cortex-A53      | #819472         | ARM64_ERRATUM_819472    |
+| ARM            | Cortex-A53      | #845719         | ARM64_ERRATUM_845719    |
+| ARM            | Cortex-A53      | #843419         | ARM64_ERRATUM_843419    |
+| ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075    |
+| ARM            | Cortex-A57      | #852523         | N/A                     |
+| ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220    |
+|                |                 |                 |                         |
+| Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
+| Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |

Documentation/block/cfq-iosched.txt

@@ -81,14 +81,13 @@ on higher end storage.
 
 Default value for this parameter is 8ms.
 
-latency
--------
-This parameter is used to enable/disable the latency mode of the CFQ
-scheduler. If latency mode (called low_latency) is enabled, CFQ tries
-to recompute the slice time for each process based on the target_latency set
-for the system. This favors fairness over throughput. Disabling low
-latency (setting it to 0) ignores target latency, allowing each process in the
-system to get a full time slice.
+low_latency
+-----------
+This parameter is used to enable/disable the low latency mode of the CFQ
+scheduler. If enabled, CFQ tries to recompute the slice time for each process
+based on the target_latency set for the system. This favors fairness over
+throughput. Disabling low latency (setting it to 0) ignores target latency,
+allowing each process in the system to get a full time slice.
 
 By default low latency mode is enabled.
 

Documentation/cgroups/00-INDEX → Documentation/cgroup-v1/00-INDEX

@@ -24,7 +24,5 @@ net_prio.txt
 	- Network priority cgroups details and usages.
 pids.txt
 	- Process number cgroups details and usages.
-resource_counter.txt
-	- Resource Counter API.
 unified-hierarchy.txt
 	- Description the new/next cgroup interface.

Documentation/cgroups/blkio-controller.txt → Documentation/cgroup-v1/blkio-controller.txt

@@ -84,8 +84,7 @@ Throttling/Upper Limit policy
 
 - Run dd to read a file and see if rate is throttled to 1MB/s or not.
 
-		# dd if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
-		# iflag=direct
+        # dd iflag=direct if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
         1024+0 records in
         1024+0 records out
         4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s
@@ -374,82 +373,3 @@ One can experience an overall throughput drop if you have created multiple
 groups and put applications in that group which are not driving enough
 IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle
 on individual groups and throughput should improve.
-
-Writeback
-=========
-
-Page cache is dirtied through buffered writes and shared mmaps and
-written asynchronously to the backing filesystem by the writeback
-mechanism.  Writeback sits between the memory and IO domains and
-regulates the proportion of dirty memory by balancing dirtying and
-write IOs.
-
-On traditional cgroup hierarchies, relationships between different
-controllers cannot be established making it impossible for writeback
-to operate accounting for cgroup resource restrictions and all
-writeback IOs are attributed to the root cgroup.
-
-If both the blkio and memory controllers are used on the v2 hierarchy
-and the filesystem supports cgroup writeback, writeback operations
-correctly follow the resource restrictions imposed by both memory and
-blkio controllers.
-
-Writeback examines both system-wide and per-cgroup dirty memory status
-and enforces the more restrictive of the two.  Also, writeback control
-parameters which are absolute values - vm.dirty_bytes and
-vm.dirty_background_bytes - are distributed across cgroups according
-to their current writeback bandwidth.
-
-There's a peculiarity stemming from the discrepancy in ownership
-granularity between memory controller and writeback.  While memory
-controller tracks ownership per page, writeback operates on inode
-basis.  cgroup writeback bridges the gap by tracking ownership by
-inode but migrating ownership if too many foreign pages, pages which
-don't match the current inode ownership, have been encountered while
-writing back the inode.
-
-This is a conscious design choice as writeback operations are
-inherently tied to inodes making strictly following page ownership
-complicated and inefficient.  The only use case which suffers from
-this compromise is multiple cgroups concurrently dirtying disjoint
-regions of the same inode, which is an unlikely use case and decided
-to be unsupported.  Note that as memory controller assigns page
-ownership on the first use and doesn't update it until the page is
-released, even if cgroup writeback strictly follows page ownership,
-multiple cgroups dirtying overlapping areas wouldn't work as expected.
-In general, write-sharing an inode across multiple cgroups is not well
-supported.
-
-Filesystem support for cgroup writeback
----------------------------------------
-
-A filesystem can make writeback IOs cgroup-aware by updating
-address_space_operations->writepage[s]() to annotate bio's using the
-following two functions.
-
-* wbc_init_bio(@wbc, @bio)
-
-  Should be called for each bio carrying writeback data and associates
-  the bio with the inode's owner cgroup.  Can be called anytime
-  between bio allocation and submission.
-
-* wbc_account_io(@wbc, @page, @bytes)
-
-  Should be called for each data segment being written out.  While
-  this function doesn't care exactly when it's called during the
-  writeback session, it's the easiest and most natural to call it as
-  data segments are added to a bio.
-
-With writeback bio's annotated, cgroup support can be enabled per
-super_block by setting MS_CGROUPWB in ->s_flags.  This allows for
-selective disabling of cgroup writeback support which is helpful when
-certain filesystem features, e.g. journaled data mode, are
-incompatible.
-
-wbc_init_bio() binds the specified bio to its cgroup.  Depending on
-the configuration, the bio may be executed at a lower priority and if
-the writeback session is holding shared resources, e.g. a journal
-entry, may lead to priority inversion.  There is no one easy solution
-for the problem.  Filesystems can try to work around specific problem
-cases by skipping wbc_init_bio() or using bio_associate_blkcg()
-directly.

Documentation/cgroup-v2.txt

@@ -0,0 +1,1382 @@
+
+Control Group v2
+
+October, 2015		Tejun Heo <tj@kernel.org>
+
+This is the authoritative documentation on the design, interface and
+conventions of cgroup v2.  It describes all userland-visible aspects
+of cgroup including core and specific controller behaviors.  All
+future changes must be reflected in this document.  Documentation for
+v1 is available under Documentation/cgroup-legacy/.
+
+CONTENTS
+
+1. Introduction
+  1-1. Terminology
+  1-2. What is cgroup?
+2. Basic Operations
+  2-1. Mounting
+  2-2. Organizing Processes
+  2-3. [Un]populated Notification
+  2-4. Controlling Controllers
+    2-4-1. Enabling and Disabling
+    2-4-2. Top-down Constraint
+    2-4-3. No Internal Process Constraint
+  2-5. Delegation
+    2-5-1. Model of Delegation
+    2-5-2. Delegation Containment
+  2-6. Guidelines
+    2-6-1. Organize Once and Control
+    2-6-2. Avoid Name Collisions
+3. Resource Distribution Models
+  3-1. Weights
+  3-2. Limits
+  3-3. Protections
+  3-4. Allocations
+4. Interface Files
+  4-1. Format
+  4-2. Conventions
+  4-3. Core Interface Files
+5. Controllers
+  5-1. CPU
+    5-1-1. CPU Interface Files
+  5-2. Memory
+    5-2-1. Memory Interface Files
+    5-2-2. Usage Guidelines
+    5-2-3. Memory Ownership
+  5-3. IO
+    5-3-1. IO Interface Files
+    5-3-2. Writeback
+P. Information on Kernel Programming
+  P-1. Filesystem Support for Writeback
+D. Deprecated v1 Core Features
+R. Issues with v1 and Rationales for v2
+  R-1. Multiple Hierarchies
+  R-2. Thread Granularity
+  R-3. Competition Between Inner Nodes and Threads
+  R-4. Other Interface Issues
+  R-5. Controller Issues and Remedies
+    R-5-1. Memory
+
+
+1. Introduction
+
+1-1. Terminology
+
+"cgroup" stands for "control group" and is never capitalized.  The
+singular form is used to designate the whole feature and also as a
+qualifier as in "cgroup controllers".  When explicitly referring to
+multiple individual control groups, the plural form "cgroups" is used.
+
+
+1-2. What is cgroup?
+
+cgroup is a mechanism to organize processes hierarchically and
+distribute system resources along the hierarchy in a controlled and
+configurable manner.
+
+cgroup is largely composed of two parts - the core and controllers.
+cgroup core is primarily responsible for hierarchically organizing
+processes.  A cgroup controller is usually responsible for
+distributing a specific type of system resource along the hierarchy
+although there are utility controllers which serve purposes other than
+resource distribution.
+
+cgroups form a tree structure and every process in the system belongs
+to one and only one cgroup.  All threads of a process belong to the
+same cgroup.  On creation, all processes are put in the cgroup that
+the parent process belongs to at the time.  A process can be migrated
+to another cgroup.  Migration of a process doesn't affect already
+existing descendant processes.
+
+Following certain structural constraints, controllers may be enabled or
+disabled selectively on a cgroup.  All controller behaviors are
+hierarchical - if a controller is enabled on a cgroup, it affects all
+processes which belong to the cgroups consisting the inclusive
+sub-hierarchy of the cgroup.  When a controller is enabled on a nested
+cgroup, it always restricts the resource distribution further.  The
+restrictions set closer to the root in the hierarchy can not be
+overridden from further away.
+
+
+2. Basic Operations
+
+2-1. Mounting
+
+Unlike v1, cgroup v2 has only single hierarchy.  The cgroup v2
+hierarchy can be mounted with the following mount command.
+
+  # mount -t cgroup2 none $MOUNT_POINT
+
+cgroup2 filesystem has the magic number 0x63677270 ("cgrp").  All
+controllers which support v2 and are not bound to a v1 hierarchy are
+automatically bound to the v2 hierarchy and show up at the root.
+Controllers which are not in active use in the v2 hierarchy can be
+bound to other hierarchies.  This allows mixing v2 hierarchy with the
+legacy v1 multiple hierarchies in a fully backward compatible way.
+
+A controller can be moved across hierarchies only after the controller
+is no longer referenced in its current hierarchy.  Because per-cgroup
+controller states are destroyed asynchronously and controllers may
+have lingering references, a controller may not show up immediately on
+the v2 hierarchy after the final umount of the previous hierarchy.
+Similarly, a controller should be fully disabled to be moved out of
+the unified hierarchy and it may take some time for the disabled
+controller to become available for other hierarchies; furthermore, due
+to inter-controller dependencies, other controllers may need to be
+disabled too.
+
+While useful for development and manual configurations, moving
+controllers dynamically between the v2 and other hierarchies is
+strongly discouraged for production use.  It is recommended to decide
+the hierarchies and controller associations before starting using the
+controllers after system boot.
+
+
+2-2. Organizing Processes
+
+Initially, only the root cgroup exists to which all processes belong.
+A child cgroup can be created by creating a sub-directory.
+
+  # mkdir $CGROUP_NAME
+
+A given cgroup may have multiple child cgroups forming a tree
+structure.  Each cgroup has a read-writable interface file
+"cgroup.procs".  When read, it lists the PIDs of all processes which
+belong to the cgroup one-per-line.  The PIDs are not ordered and the
+same PID may show up more than once if the process got moved to
+another cgroup and then back or the PID got recycled while reading.
+
+A process can be migrated into a cgroup by writing its PID to the
+target cgroup's "cgroup.procs" file.  Only one process can be migrated
+on a single write(2) call.  If a process is composed of multiple
+threads, writing the PID of any thread migrates all threads of the
+process.
+
+When a process forks a child process, the new process is born into the
+cgroup that the forking process belongs to at the time of the
+operation.  After exit, a process stays associated with the cgroup
+that it belonged to at the time of exit until it's reaped; however, a
+zombie process does not appear in "cgroup.procs" and thus can't be
+moved to another cgroup.
+
+A cgroup which doesn't have any children or live processes can be
+destroyed by removing the directory.  Note that a cgroup which doesn't
+have any children and is associated only with zombie processes is
+considered empty and can be removed.
+
+  # rmdir $CGROUP_NAME
+
+"/proc/$PID/cgroup" lists a process's cgroup membership.  If legacy
+cgroup is in use in the system, this file may contain multiple lines,
+one for each hierarchy.  The entry for cgroup v2 is always in the
+format "0::$PATH".
+
+  # cat /proc/842/cgroup
+  ...
+  0::/test-cgroup/test-cgroup-nested
+
+If the process becomes a zombie and the cgroup it was associated with
+is removed subsequently, " (deleted)" is appended to the path.
+
+  # cat /proc/842/cgroup
+  ...
+  0::/test-cgroup/test-cgroup-nested (deleted)
+
+
+2-3. [Un]populated Notification
+
+Each non-root cgroup has a "cgroup.events" file which contains
+"populated" field indicating whether the cgroup's sub-hierarchy has
+live processes in it.  Its value is 0 if there is no live process in
+the cgroup and its descendants; otherwise, 1.  poll and [id]notify
+events are triggered when the value changes.  This can be used, for
+example, to start a clean-up operation after all processes of a given
+sub-hierarchy have exited.  The populated state updates and
+notifications are recursive.  Consider the following sub-hierarchy
+where the numbers in the parentheses represent the numbers of processes
+in each cgroup.
+
+  A(4) - B(0) - C(1)
+              \ D(0)
+
+A, B and C's "populated" fields would be 1 while D's 0.  After the one
+process in C exits, B and C's "populated" fields would flip to "0" and
+file modified events will be generated on the "cgroup.events" files of
+both cgroups.
+
+
+2-4. Controlling Controllers
+
+2-4-1. Enabling and Disabling
+
+Each cgroup has a "cgroup.controllers" file which lists all
+controllers available for the cgroup to enable.
+
+  # cat cgroup.controllers
+  cpu io memory
+
+No controller is enabled by default.  Controllers can be enabled and
+disabled by writing to the "cgroup.subtree_control" file.
+
+  # echo "+cpu +memory -io" > cgroup.subtree_control
+
+Only controllers which are listed in "cgroup.controllers" can be
+enabled.  When multiple operations are specified as above, either they
+all succeed or fail.  If multiple operations on the same controller
+are specified, the last one is effective.
+
+Enabling a controller in a cgroup indicates that the distribution of
+the target resource across its immediate children will be controlled.
+Consider the following sub-hierarchy.  The enabled controllers are
+listed in parentheses.
+
+  A(cpu,memory) - B(memory) - C()
+                            \ D()
+
+As A has "cpu" and "memory" enabled, A will control the distribution
+of CPU cycles and memory to its children, in this case, B.  As B has
+"memory" enabled but not "CPU", C and D will compete freely on CPU
+cycles but their division of memory available to B will be controlled.
+
+As a controller regulates the distribution of the target resource to
+the cgroup's children, enabling it creates the controller's interface
+files in the child cgroups.  In the above example, enabling "cpu" on B
+would create the "cpu." prefixed controller interface files in C and
+D.  Likewise, disabling "memory" from B would remove the "memory."
+prefixed controller interface files from C and D.  This means that the
+controller interface files - anything which doesn't start with
+"cgroup." are owned by the parent rather than the cgroup itself.
+
+
+2-4-2. Top-down Constraint
+
+Resources are distributed top-down and a cgroup can further distribute
+a resource only if the resource has been distributed to it from the
+parent.  This means that all non-root "cgroup.subtree_control" files
+can only contain controllers which are enabled in the parent's
+"cgroup.subtree_control" file.  A controller can be enabled only if
+the parent has the controller enabled and a controller can't be
+disabled if one or more children have it enabled.
+
+
+2-4-3. No Internal Process Constraint
+
+Non-root cgroups can only distribute resources to their children when
+they don't have any processes of their own.  In other words, only
+cgroups which don't contain any processes can have controllers enabled
+in their "cgroup.subtree_control" files.
+
+This guarantees that, when a controller is looking at the part of the
+hierarchy which has it enabled, processes are always only on the
+leaves.  This rules out situations where child cgroups compete against
+internal processes of the parent.
+
+The root cgroup is exempt from this restriction.  Root contains
+processes and anonymous resource consumption which can't be associated
+with any other cgroups and requires special treatment from most
+controllers.  How resource consumption in the root cgroup is governed
+is up to each controller.
+
+Note that the restriction doesn't get in the way if there is no
+enabled controller in the cgroup's "cgroup.subtree_control".  This is
+important as otherwise it wouldn't be possible to create children of a
+populated cgroup.  To control resource distribution of a cgroup, the
+cgroup must create children and transfer all its processes to the
+children before enabling controllers in its "cgroup.subtree_control"
+file.
+
+
+2-5. Delegation
+
+2-5-1. Model of Delegation
+
+A cgroup can be delegated to a less privileged user by granting write
+access of the directory and its "cgroup.procs" file to the user.  Note
+that resource control interface files in a given directory control the
+distribution of the parent's resources and thus must not be delegated
+along with the directory.
+
+Once delegated, the user can build sub-hierarchy under the directory,
+organize processes as it sees fit and further distribute the resources
+it received from the parent.  The limits and other settings of all
+resource controllers are hierarchical and regardless of what happens
+in the delegated sub-hierarchy, nothing can escape the resource
+restrictions imposed by the parent.
+
+Currently, cgroup doesn't impose any restrictions on the number of
+cgroups in or nesting depth of a delegated sub-hierarchy; however,
+this may be limited explicitly in the future.
+
+
+2-5-2. Delegation Containment
+
+A delegated sub-hierarchy is contained in the sense that processes
+can't be moved into or out of the sub-hierarchy by the delegatee.  For
+a process with a non-root euid to migrate a target process into a
+cgroup by writing its PID to the "cgroup.procs" file, the following
+conditions must be met.
+
+- The writer's euid must match either uid or suid of the target process.
+
+- The writer must have write access to the "cgroup.procs" file.
+
+- The writer must have write access to the "cgroup.procs" file of the
+  common ancestor of the source and destination cgroups.
+
+The above three constraints ensure that while a delegatee may migrate
+processes around freely in the delegated sub-hierarchy it can't pull
+in from or push out to outside the sub-hierarchy.
+
+For an example, let's assume cgroups C0 and C1 have been delegated to
+user U0 who created C00, C01 under C0 and C10 under C1 as follows and
+all processes under C0 and C1 belong to U0.
+
+  ~~~~~~~~~~~~~ - C0 - C00
+  ~ cgroup    ~      \ C01
+  ~ hierarchy ~
+  ~~~~~~~~~~~~~ - C1 - C10
+
+Let's also say U0 wants to write the PID of a process which is
+currently in C10 into "C00/cgroup.procs".  U0 has write access to the
+file and uid match on the process; however, the common ancestor of the
+source cgroup C10 and the destination cgroup C00 is above the points
+of delegation and U0 would not have write access to its "cgroup.procs"
+files and thus the write will be denied with -EACCES.
+
+
+2-6. Guidelines
+
+2-6-1. Organize Once and Control
+
+Migrating a process across cgroups is a relatively expensive operation
+and stateful resources such as memory are not moved together with the
+process.  This is an explicit design decision as there often exist
+inherent trade-offs between migration and various hot paths in terms
+of synchronization cost.
+
+As such, migrating processes across cgroups frequently as a means to
+apply different resource restrictions is discouraged.  A workload
+should be assigned to a cgroup according to the system's logical and
+resource structure once on start-up.  Dynamic adjustments to resource
+distribution can be made by changing controller configuration through
+the interface files.
+
+
+2-6-2. Avoid Name Collisions
+
+Interface files for a cgroup and its children cgroups occupy the same
+directory and it is possible to create children cgroups which collide
+with interface files.
+
+All cgroup core interface files are prefixed with "cgroup." and each
+controller's interface files are prefixed with the controller name and
+a dot.  A controller's name is composed of lower case alphabets and
+'_'s but never begins with an '_' so it can be used as the prefix
+character for collision avoidance.  Also, interface file names won't
+start or end with terms which are often used in categorizing workloads
+such as job, service, slice, unit or workload.
+
+cgroup doesn't do anything to prevent name collisions and it's the
+user's responsibility to avoid them.
+
+
+3. Resource Distribution Models
+
+cgroup controllers implement several resource distribution schemes
+depending on the resource type and expected use cases.  This section
+describes major schemes in use along with their expected behaviors.
+
+
+3-1. Weights
+
+A parent's resource is distributed by adding up the weights of all
+active children and giving each the fraction matching the ratio of its
+weight against the sum.  As only children which can make use of the
+resource at the moment participate in the distribution, this is
+work-conserving.  Due to the dynamic nature, this model is usually
+used for stateless resources.
+
+All weights are in the range [1, 10000] with the default at 100.  This
+allows symmetric multiplicative biases in both directions at fine
+enough granularity while staying in the intuitive range.
+
+As long as the weight is in range, all configuration combinations are
+valid and there is no reason to reject configuration changes or
+process migrations.
+
+"cpu.weight" proportionally distributes CPU cycles to active children
+and is an example of this type.
+
+
+3-2. Limits
+
+A child can only consume upto the configured amount of the resource.
+Limits can be over-committed - the sum of the limits of children can
+exceed the amount of resource available to the parent.
+
+Limits are in the range [0, max] and defaults to "max", which is noop.
+
+As limits can be over-committed, all configuration combinations are
+valid and there is no reason to reject configuration changes or
+process migrations.
+
+"io.max" limits the maximum BPS and/or IOPS that a cgroup can consume
+on an IO device and is an example of this type.
+
+
+3-3. Protections
+
+A cgroup is protected to be allocated upto the configured amount of
+the resource if the usages of all its ancestors are under their
+protected levels.  Protections can be hard guarantees or best effort
+soft boundaries.  Protections can also be over-committed in which case
+only upto the amount available to the parent is protected among
+children.
+
+Protections are in the range [0, max] and defaults to 0, which is
+noop.
+
+As protections can be over-committed, all configuration combinations
+are valid and there is no reason to reject configuration changes or
+process migrations.
+
+"memory.low" implements best-effort memory protection and is an
+example of this type.
+
+
+3-4. Allocations
+
+A cgroup is exclusively allocated a certain amount of a finite
+resource.  Allocations can't be over-committed - the sum of the
+allocations of children can not exceed the amount of resource
+available to the parent.
+
+Allocations are in the range [0, max] and defaults to 0, which is no
+resource.
+
+As allocations can't be over-committed, some configuration
+combinations are invalid and should be rejected.  Also, if the
+resource is mandatory for execution of processes, process migrations
+may be rejected.
+
+"cpu.rt.max" hard-allocates realtime slices and is an example of this
+type.
+
+
+4. Interface Files
+
+4-1. Format
+
+All interface files should be in one of the following formats whenever
+possible.
+
+  New-line separated values
+  (when only one value can be written at once)
+
+	VAL0\n
+	VAL1\n
+	...
+
+  Space separated values
+  (when read-only or multiple values can be written at once)
+
+	VAL0 VAL1 ...\n
+
+  Flat keyed
+
+	KEY0 VAL0\n
+	KEY1 VAL1\n
+	...
+
+  Nested keyed
+
+	KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
+	KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
+	...
+
+For a writable file, the format for writing should generally match
+reading; however, controllers may allow omitting later fields or
+implement restricted shortcuts for most common use cases.
+
+For both flat and nested keyed files, only the values for a single key
+can be written at a time.  For nested keyed files, the sub key pairs
+may be specified in any order and not all pairs have to be specified.
+
+
+4-2. Conventions
+
+- Settings for a single feature should be contained in a single file.
+
+- The root cgroup should be exempt from resource control and thus
+  shouldn't have resource control interface files.  Also,
+  informational files on the root cgroup which end up showing global
+  information available elsewhere shouldn't exist.
+
+- If a controller implements weight based resource distribution, its
+  interface file should be named "weight" and have the range [1,
+  10000] with 100 as the default.  The values are chosen to allow
+  enough and symmetric bias in both directions while keeping it
+  intuitive (the default is 100%).
+
+- If a controller implements an absolute resource guarantee and/or
+  limit, the interface files should be named "min" and "max"
+  respectively.  If a controller implements best effort resource
+  guarantee and/or limit, the interface files should be named "low"
+  and "high" respectively.
+
+  In the above four control files, the special token "max" should be
+  used to represent upward infinity for both reading and writing.
+
+- If a setting has a configurable default value and keyed specific
+  overrides, the default entry should be keyed with "default" and
+  appear as the first entry in the file.
+
+  The default value can be updated by writing either "default $VAL" or
+  "$VAL".
+
+  When writing to update a specific override, "default" can be used as
+  the value to indicate removal of the override.  Override entries
+  with "default" as the value must not appear when read.
+
+  For example, a setting which is keyed by major:minor device numbers
+  with integer values may look like the following.
+
+    # cat cgroup-example-interface-file
+    default 150
+    8:0 300
+
+  The default value can be updated by
+
+    # echo 125 > cgroup-example-interface-file
+
+  or
+
+    # echo "default 125" > cgroup-example-interface-file
+
+  An override can be set by
+
+    # echo "8:16 170" > cgroup-example-interface-file
+
+  and cleared by
+
+    # echo "8:0 default" > cgroup-example-interface-file
+    # cat cgroup-example-interface-file
+    default 125
+    8:16 170
+
+- For events which are not very high frequency, an interface file
+  "events" should be created which lists event key value pairs.
+  Whenever a notifiable event happens, file modified event should be
+  generated on the file.
+
+
+4-3. Core Interface Files
+
+All cgroup core files are prefixed with "cgroup."
+
+  cgroup.procs
+
+	A read-write new-line separated values file which exists on
+	all cgroups.
+
+	When read, it lists the PIDs of all processes which belong to
+	the cgroup one-per-line.  The PIDs are not ordered and the
+	same PID may show up more than once if the process got moved
+	to another cgroup and then back or the PID got recycled while
+	reading.
+
+	A PID can be written to migrate the process associated with
+	the PID to the cgroup.  The writer should match all of the
+	following conditions.
+
+	- Its euid is either root or must match either uid or suid of
+          the target process.
+
+	- It must have write access to the "cgroup.procs" file.
+
+	- It must have write access to the "cgroup.procs" file of the
+	  common ancestor of the source and destination cgroups.
+
+	When delegating a sub-hierarchy, write access to this file
+	should be granted along with the containing directory.
+
+  cgroup.controllers
+
+	A read-only space separated values file which exists on all
+	cgroups.
+
+	It shows space separated list of all controllers available to
+	the cgroup.  The controllers are not ordered.
+
+  cgroup.subtree_control
+
+	A read-write space separated values file which exists on all
+	cgroups.  Starts out empty.
+
+	When read, it shows space separated list of the controllers
+	which are enabled to control resource distribution from the
+	cgroup to its children.
+
+	Space separated list of controllers prefixed with '+' or '-'
+	can be written to enable or disable controllers.  A controller
+	name prefixed with '+' enables the controller and '-'
+	disables.  If a controller appears more than once on the list,
+	the last one is effective.  When multiple enable and disable
+	operations are specified, either all succeed or all fail.
+
+  cgroup.events
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+	The following entries are defined.  Unless specified
+	otherwise, a value change in this file generates a file
+	modified event.
+
+	  populated
+
+		1 if the cgroup or its descendants contains any live
+		processes; otherwise, 0.
+
+
+5. Controllers
+
+5-1. CPU
+
+[NOTE: The interface for the cpu controller hasn't been merged yet]
+
+The "cpu" controllers regulates distribution of CPU cycles.  This
+controller implements weight and absolute bandwidth limit models for
+normal scheduling policy and absolute bandwidth allocation model for
+realtime scheduling policy.
+
+
+5-1-1. CPU Interface Files
+
+All time durations are in microseconds.
+
+  cpu.stat
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+
+	It reports the following six stats.
+
+	  usage_usec
+	  user_usec
+	  system_usec
+	  nr_periods
+	  nr_throttled
+	  throttled_usec
+
+  cpu.weight
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "100".
+
+	The weight in the range [1, 10000].
+
+  cpu.max
+
+	A read-write two value file which exists on non-root cgroups.
+	The default is "max 100000".
+
+	The maximum bandwidth limit.  It's in the following format.
+
+	  $MAX $PERIOD
+
+	which indicates that the group may consume upto $MAX in each
+	$PERIOD duration.  "max" for $MAX indicates no limit.  If only
+	one number is written, $MAX is updated.
+
+  cpu.rt.max
+
+  [NOTE: The semantics of this file is still under discussion and the
+   interface hasn't been merged yet]
+
+	A read-write two value file which exists on all cgroups.
+	The default is "0 100000".
+
+	The maximum realtime runtime allocation.  Over-committing
+	configurations are disallowed and process migrations are
+	rejected if not enough bandwidth is available.  It's in the
+	following format.
+
+	  $MAX $PERIOD
+
+	which indicates that the group may consume upto $MAX in each
+	$PERIOD duration.  If only one number is written, $MAX is
+	updated.
+
+
+5-2. Memory
+
+The "memory" controller regulates distribution of memory.  Memory is
+stateful and implements both limit and protection models.  Due to the
+intertwining between memory usage and reclaim pressure and the
+stateful nature of memory, the distribution model is relatively
+complex.
+
+While not completely water-tight, all major memory usages by a given
+cgroup are tracked so that the total memory consumption can be
+accounted and controlled to a reasonable extent.  Currently, the
+following types of memory usages are tracked.
+
+- Userland memory - page cache and anonymous memory.
+
+- Kernel data structures such as dentries and inodes.
+
+- TCP socket buffers.
+
+The above list may expand in the future for better coverage.
+
+
+5-2-1. Memory Interface Files
+
+All memory amounts are in bytes.  If a value which is not aligned to
+PAGE_SIZE is written, the value may be rounded up to the closest
+PAGE_SIZE multiple when read back.
+
+  memory.current
+
+	A read-only single value file which exists on non-root
+	cgroups.
+
+	The total amount of memory currently being used by the cgroup
+	and its descendants.
+
+  memory.low
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	Best-effort memory protection.  If the memory usages of a
+	cgroup and all its ancestors are below their low boundaries,
+	the cgroup's memory won't be reclaimed unless memory can be
+	reclaimed from unprotected cgroups.
+
+	Putting more memory than generally available under this
+	protection is discouraged.
+
+  memory.high
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Memory usage throttle limit.  This is the main mechanism to
+	control memory usage of a cgroup.  If a cgroup's usage goes
+	over the high boundary, the processes of the cgroup are
+	throttled and put under heavy reclaim pressure.
+
+	Going over the high limit never invokes the OOM killer and
+	under extreme conditions the limit may be breached.
+
+  memory.max
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Memory usage hard limit.  This is the final protection
+	mechanism.  If a cgroup's memory usage reaches this limit and
+	can't be reduced, the OOM killer is invoked in the cgroup.
+	Under certain circumstances, the usage may go over the limit
+	temporarily.
+
+	This is the ultimate protection mechanism.  As long as the
+	high limit is used and monitored properly, this limit's
+	utility is limited to providing the final safety net.
+
+  memory.events
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+	The following entries are defined.  Unless specified
+	otherwise, a value change in this file generates a file
+	modified event.
+
+	  low
+
+		The number of times the cgroup is reclaimed due to
+		high memory pressure even though its usage is under
+		the low boundary.  This usually indicates that the low
+		boundary is over-committed.
+
+	  high
+
+		The number of times processes of the cgroup are
+		throttled and routed to perform direct memory reclaim
+		because the high memory boundary was exceeded.  For a
+		cgroup whose memory usage is capped by the high limit
+		rather than global memory pressure, this event's
+		occurrences are expected.
+
+	  max
+
+		The number of times the cgroup's memory usage was
+		about to go over the max boundary.  If direct reclaim
+		fails to bring it down, the OOM killer is invoked.
+
+	  oom
+
+		The number of times the OOM killer has been invoked in
+		the cgroup.  This may not exactly match the number of
+		processes killed but should generally be close.
+
+  memory.stat
+
+	A read-only flat-keyed file which exists on non-root cgroups.
+
+	This breaks down the cgroup's memory footprint into different
+	types of memory, type-specific details, and other information
+	on the state and past events of the memory management system.
+
+	All memory amounts are in bytes.
+
+	The entries are ordered to be human readable, and new entries
+	can show up in the middle. Don't rely on items remaining in a
+	fixed position; use the keys to look up specific values!
+
+	  anon
+
+		Amount of memory used in anonymous mappings such as
+		brk(), sbrk(), and mmap(MAP_ANONYMOUS)
+
+	  file
+
+		Amount of memory used to cache filesystem data,
+		including tmpfs and shared memory.
+
+	  file_mapped
+
+		Amount of cached filesystem data mapped with mmap()
+
+	  file_dirty
+
+		Amount of cached filesystem data that was modified but
+		not yet written back to disk
+
+	  file_writeback
+
+		Amount of cached filesystem data that was modified and
+		is currently being written back to disk
+
+	  inactive_anon
+	  active_anon
+	  inactive_file
+	  active_file
+	  unevictable
+
+		Amount of memory, swap-backed and filesystem-backed,
+		on the internal memory management lists used by the
+		page reclaim algorithm
+
+	  pgfault
+
+		Total number of page faults incurred
+
+	  pgmajfault
+
+		Number of major page faults incurred
+
+  memory.swap.current
+
+	A read-only single value file which exists on non-root
+	cgroups.
+
+	The total amount of swap currently being used by the cgroup
+	and its descendants.
+
+  memory.swap.max
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Swap usage hard limit.  If a cgroup's swap usage reaches this
+	limit, anonymous meomry of the cgroup will not be swapped out.
+
+
+5-2-2. General Usage
+
+"memory.high" is the main mechanism to control memory usage.
+Over-committing on high limit (sum of high limits > available memory)
+and letting global memory pressure to distribute memory according to
+usage is a viable strategy.
+
+Because breach of the high limit doesn't trigger the OOM killer but
+throttles the offending cgroup, a management agent has ample
+opportunities to monitor and take appropriate actions such as granting
+more memory or terminating the workload.
+
+Determining whether a cgroup has enough memory is not trivial as
+memory usage doesn't indicate whether the workload can benefit from
+more memory.  For example, a workload which writes data received from
+network to a file can use all available memory but can also operate as
+performant with a small amount of memory.  A measure of memory
+pressure - how much the workload is being impacted due to lack of
+memory - is necessary to determine whether a workload needs more
+memory; unfortunately, memory pressure monitoring mechanism isn't
+implemented yet.
+
+
+5-2-3. Memory Ownership
+
+A memory area is charged to the cgroup which instantiated it and stays
+charged to the cgroup until the area is released.  Migrating a process
+to a different cgroup doesn't move the memory usages that it
+instantiated while in the previous cgroup to the new cgroup.
+
+A memory area may be used by processes belonging to different cgroups.
+To which cgroup the area will be charged is in-deterministic; however,
+over time, the memory area is likely to end up in a cgroup which has
+enough memory allowance to avoid high reclaim pressure.
+
+If a cgroup sweeps a considerable amount of memory which is expected
+to be accessed repeatedly by other cgroups, it may make sense to use
+POSIX_FADV_DONTNEED to relinquish the ownership of memory areas
+belonging to the affected files to ensure correct memory ownership.
+
+
+5-3. IO
+
+The "io" controller regulates the distribution of IO resources.  This
+controller implements both weight based and absolute bandwidth or IOPS
+limit distribution; however, weight based distribution is available
+only if cfq-iosched is in use and neither scheme is available for
+blk-mq devices.
+
+
+5-3-1. IO Interface Files
+
+  io.stat
+
+	A read-only nested-keyed file which exists on non-root
+	cgroups.
+
+	Lines are keyed by $MAJ:$MIN device numbers and not ordered.
+	The following nested keys are defined.
+
+	  rbytes	Bytes read
+	  wbytes	Bytes written
+	  rios		Number of read IOs
+	  wios		Number of write IOs
+
+	An example read output follows.
+
+	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
+	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
+
+  io.weight
+
+	A read-write flat-keyed file which exists on non-root cgroups.
+	The default is "default 100".
+
+	The first line is the default weight applied to devices
+	without specific override.  The rest are overrides keyed by
+	$MAJ:$MIN device numbers and not ordered.  The weights are in
+	the range [1, 10000] and specifies the relative amount IO time
+	the cgroup can use in relation to its siblings.
+
+	The default weight can be updated by writing either "default
+	$WEIGHT" or simply "$WEIGHT".  Overrides can be set by writing
+	"$MAJ:$MIN $WEIGHT" and unset by writing "$MAJ:$MIN default".
+
+	An example read output follows.
+
+	  default 100
+	  8:16 200
+	  8:0 50
+
+  io.max
+
+	A read-write nested-keyed file which exists on non-root
+	cgroups.
+
+	BPS and IOPS based IO limit.  Lines are keyed by $MAJ:$MIN
+	device numbers and not ordered.  The following nested keys are
+	defined.
+
+	  rbps		Max read bytes per second
+	  wbps		Max write bytes per second
+	  riops		Max read IO operations per second
+	  wiops		Max write IO operations per second
+
+	When writing, any number of nested key-value pairs can be
+	specified in any order.  "max" can be specified as the value
+	to remove a specific limit.  If the same key is specified
+	multiple times, the outcome is undefined.
+
+	BPS and IOPS are measured in each IO direction and IOs are
+	delayed if limit is reached.  Temporary bursts are allowed.
+
+	Setting read limit at 2M BPS and write at 120 IOPS for 8:16.
+
+	  echo "8:16 rbps=2097152 wiops=120" > io.max
+
+	Reading returns the following.
+
+	  8:16 rbps=2097152 wbps=max riops=max wiops=120
+
+	Write IOPS limit can be removed by writing the following.
+
+	  echo "8:16 wiops=max" > io.max
+
+	Reading now returns the following.
+
+	  8:16 rbps=2097152 wbps=max riops=max wiops=max
+
+
+5-3-2. Writeback
+
+Page cache is dirtied through buffered writes and shared mmaps and
+written asynchronously to the backing filesystem by the writeback
+mechanism.  Writeback sits between the memory and IO domains and
+regulates the proportion of dirty memory by balancing dirtying and
+write IOs.
+
+The io controller, in conjunction with the memory controller,
+implements control of page cache writeback IOs.  The memory controller
+defines the memory domain that dirty memory ratio is calculated and
+maintained for and the io controller defines the io domain which
+writes out dirty pages for the memory domain.  Both system-wide and
+per-cgroup dirty memory states are examined and the more restrictive
+of the two is enforced.
+
+cgroup writeback requires explicit support from the underlying
+filesystem.  Currently, cgroup writeback is implemented on ext2, ext4
+and btrfs.  On other filesystems, all writeback IOs are attributed to
+the root cgroup.
+
+There are inherent differences in memory and writeback management
+which affects how cgroup ownership is tracked.  Memory is tracked per
+page while writeback per inode.  For the purpose of writeback, an
+inode is assigned to a cgroup and all IO requests to write dirty pages
+from the inode are attributed to that cgroup.
+
+As cgroup ownership for memory is tracked per page, there can be pages
+which are associated with different cgroups than the one the inode is
+associated with.  These are called foreign pages.  The writeback
+constantly keeps track of foreign pages and, if a particular foreign
+cgroup becomes the majority over a certain period of time, switches
+the ownership of the inode to that cgroup.
+
+While this model is enough for most use cases where a given inode is
+mostly dirtied by a single cgroup even when the main writing cgroup
+changes over time, use cases where multiple cgroups write to a single
+inode simultaneously are not supported well.  In such circumstances, a
+significant portion of IOs are likely to be attributed incorrectly.
+As memory controller assigns page ownership on the first use and
+doesn't update it until the page is released, even if writeback
+strictly follows page ownership, multiple cgroups dirtying overlapping
+areas wouldn't work as expected.  It's recommended to avoid such usage
+patterns.
+
+The sysctl knobs which affect writeback behavior are applied to cgroup
+writeback as follows.
+
+  vm.dirty_background_ratio
+  vm.dirty_ratio
+
+	These ratios apply the same to cgroup writeback with the
+	amount of available memory capped by limits imposed by the
+	memory controller and system-wide clean memory.
+
+  vm.dirty_background_bytes
+  vm.dirty_bytes
+
+	For cgroup writeback, this is calculated into ratio against
+	total available memory and applied the same way as
+	vm.dirty[_background]_ratio.
+
+
+P. Information on Kernel Programming
+
+This section contains kernel programming information in the areas
+where interacting with cgroup is necessary.  cgroup core and
+controllers are not covered.
+
+
+P-1. Filesystem Support for Writeback
+
+A filesystem can support cgroup writeback by updating
+address_space_operations->writepage[s]() to annotate bio's using the
+following two functions.
+
+  wbc_init_bio(@wbc, @bio)
+
+	Should be called for each bio carrying writeback data and
+	associates the bio with the inode's owner cgroup.  Can be
+	called anytime between bio allocation and submission.
+
+  wbc_account_io(@wbc, @page, @bytes)
+
+	Should be called for each data segment being written out.
+	While this function doesn't care exactly when it's called
+	during the writeback session, it's the easiest and most
+	natural to call it as data segments are added to a bio.
+
+With writeback bio's annotated, cgroup support can be enabled per
+super_block by setting SB_I_CGROUPWB in ->s_iflags.  This allows for
+selective disabling of cgroup writeback support which is helpful when
+certain filesystem features, e.g. journaled data mode, are
+incompatible.
+
+wbc_init_bio() binds the specified bio to its cgroup.  Depending on
+the configuration, the bio may be executed at a lower priority and if
+the writeback session is holding shared resources, e.g. a journal
+entry, may lead to priority inversion.  There is no one easy solution
+for the problem.  Filesystems can try to work around specific problem
+cases by skipping wbc_init_bio() or using bio_associate_blkcg()
+directly.
+
+
+D. Deprecated v1 Core Features
+
+- Multiple hierarchies including named ones are not supported.
+
+- All mount options and remounting are not supported.
+
+- The "tasks" file is removed and "cgroup.procs" is not sorted.
+
+- "cgroup.clone_children" is removed.
+
+- /proc/cgroups is meaningless for v2.  Use "cgroup.controllers" file
+  at the root instead.
+
+
+R. Issues with v1 and Rationales for v2
+
+R-1. Multiple Hierarchies
+
+cgroup v1 allowed an arbitrary number of hierarchies and each
+hierarchy could host any number of controllers.  While this seemed to
+provide a high level of flexibility, it wasn't useful in practice.
+
+For example, as there is only one instance of each controller, utility
+type controllers such as freezer which can be useful in all
+hierarchies could only be used in one.  The issue is exacerbated by
+the fact that controllers couldn't be moved to another hierarchy once
+hierarchies were populated.  Another issue was that all controllers
+bound to a hierarchy were forced to have exactly the same view of the
+hierarchy.  It wasn't possible to vary the granularity depending on
+the specific controller.
+
+In practice, these issues heavily limited which controllers could be
+put on the same hierarchy and most configurations resorted to putting
+each controller on its own hierarchy.  Only closely related ones, such
+as the cpu and cpuacct controllers, made sense to be put on the same
+hierarchy.  This often meant that userland ended up managing multiple
+similar hierarchies repeating the same steps on each hierarchy
+whenever a hierarchy management operation was necessary.
+
+Furthermore, support for multiple hierarchies came at a steep cost.
+It greatly complicated cgroup core implementation but more importantly
+the support for multiple hierarchies restricted how cgroup could be
+used in general and what controllers was able to do.
+
+There was no limit on how many hierarchies there might be, which meant
+that a thread's cgroup membership couldn't be described in finite
+length.  The key might contain any number of entries and was unlimited
+in length, which made it highly awkward to manipulate and led to
+addition of controllers which existed only to identify membership,
+which in turn exacerbated the original problem of proliferating number
+of hierarchies.
+
+Also, as a controller couldn't have any expectation regarding the
+topologies of hierarchies other controllers might be on, each
+controller had to assume that all other controllers were attached to
+completely orthogonal hierarchies.  This made it impossible, or at
+least very cumbersome, for controllers to cooperate with each other.
+
+In most use cases, putting controllers on hierarchies which are
+completely orthogonal to each other isn't necessary.  What usually is
+called for is the ability to have differing levels of granularity
+depending on the specific controller.  In other words, hierarchy may
+be collapsed from leaf towards root when viewed from specific
+controllers.  For example, a given configuration might not care about
+how memory is distributed beyond a certain level while still wanting
+to control how CPU cycles are distributed.
+
+
+R-2. Thread Granularity
+
+cgroup v1 allowed threads of a process to belong to different cgroups.
+This didn't make sense for some controllers and those controllers
+ended up implementing different ways to ignore such situations but
+much more importantly it blurred the line between API exposed to
+individual applications and system management interface.
+
+Generally, in-process knowledge is available only to the process
+itself; thus, unlike service-level organization of processes,
+categorizing threads of a process requires active participation from
+the application which owns the target process.
+
+cgroup v1 had an ambiguously defined delegation model which got abused
+in combination with thread granularity.  cgroups were delegated to
+individual applications so that they can create and manage their own
+sub-hierarchies and control resource distributions along them.  This
+effectively raised cgroup to the status of a syscall-like API exposed
+to lay programs.
+
+First of all, cgroup has a fundamentally inadequate interface to be
+exposed this way.  For a process to access its own knobs, it has to
+extract the path on the target hierarchy from /proc/self/cgroup,
+construct the path by appending the name of the knob to the path, open
+and then read and/or write to it.  This is not only extremely clunky
+and unusual but also inherently racy.  There is no conventional way to
+define transaction across the required steps and nothing can guarantee
+that the process would actually be operating on its own sub-hierarchy.
+
+cgroup controllers implemented a number of knobs which would never be
+accepted as public APIs because they were just adding control knobs to
+system-management pseudo filesystem.  cgroup ended up with interface
+knobs which were not properly abstracted or refined and directly
+revealed kernel internal details.  These knobs got exposed to
+individual applications through the ill-defined delegation mechanism
+effectively abusing cgroup as a shortcut to implementing public APIs
+without going through the required scrutiny.
+
+This was painful for both userland and kernel.  Userland ended up with
+misbehaving and poorly abstracted interfaces and kernel exposing and
+locked into constructs inadvertently.
+
+
+R-3. Competition Between Inner Nodes and Threads
+
+cgroup v1 allowed threads to be in any cgroups which created an
+interesting problem where threads belonging to a parent cgroup and its
+children cgroups competed for resources.  This was nasty as two
+different types of entities competed and there was no obvious way to
+settle it.  Different controllers did different things.
+
+The cpu controller considered threads and cgroups as equivalents and
+mapped nice levels to cgroup weights.  This worked for some cases but
+fell flat when children wanted to be allocated specific ratios of CPU
+cycles and the number of internal threads fluctuated - the ratios
+constantly changed as the number of competing entities fluctuated.
+There also were other issues.  The mapping from nice level to weight
+wasn't obvious or universal, and there were various other knobs which
+simply weren't available for threads.
+
+The io controller implicitly created a hidden leaf node for each
+cgroup to host the threads.  The hidden leaf had its own copies of all
+the knobs with "leaf_" prefixed.  While this allowed equivalent
+control over internal threads, it was with serious drawbacks.  It
+always added an extra layer of nesting which wouldn't be necessary
+otherwise, made the interface messy and significantly complicated the
+implementation.
+
+The memory controller didn't have a way to control what happened
+between internal tasks and child cgroups and the behavior was not
+clearly defined.  There were attempts to add ad-hoc behaviors and
+knobs to tailor the behavior to specific workloads which would have
+led to problems extremely difficult to resolve in the long term.
+
+Multiple controllers struggled with internal tasks and came up with
+different ways to deal with it; unfortunately, all the approaches were
+severely flawed and, furthermore, the widely different behaviors
+made cgroup as a whole highly inconsistent.
+
+This clearly is a problem which needs to be addressed from cgroup core
+in a uniform way.
+
+
+R-4. Other Interface Issues
+
+cgroup v1 grew without oversight and developed a large number of
+idiosyncrasies and inconsistencies.  One issue on the cgroup core side
+was how an empty cgroup was notified - a userland helper binary was
+forked and executed for each event.  The event delivery wasn't
+recursive or delegatable.  The limitations of the mechanism also led
+to in-kernel event delivery filtering mechanism further complicating
+the interface.
+
+Controller interfaces were problematic too.  An extreme example is
+controllers completely ignoring hierarchical organization and treating
+all cgroups as if they were all located directly under the root
+cgroup.  Some controllers exposed a large amount of inconsistent
+implementation details to userland.
+
+There also was no consistency across controllers.  When a new cgroup
+was created, some controllers defaulted to not imposing extra
+restrictions while others disallowed any resource usage until
+explicitly configured.  Configuration knobs for the same type of
+control used widely differing naming schemes and formats.  Statistics
+and information knobs were named arbitrarily and used different
+formats and units even in the same controller.
+
+cgroup v2 establishes common conventions where appropriate and updates
+controllers so that they expose minimal and consistent interfaces.
+
+
+R-5. Controller Issues and Remedies
+
+R-5-1. Memory
+
+The original lower boundary, the soft limit, is defined as a limit
+that is per default unset.  As a result, the set of cgroups that
+global reclaim prefers is opt-in, rather than opt-out.  The costs for
+optimizing these mostly negative lookups are so high that the
+implementation, despite its enormous size, does not even provide the
+basic desirable behavior.  First off, the soft limit has no
+hierarchical meaning.  All configured groups are organized in a global
+rbtree and treated like equal peers, regardless where they are located
+in the hierarchy.  This makes subtree delegation impossible.  Second,
+the soft limit reclaim pass is so aggressive that it not just
+introduces high allocation latencies into the system, but also impacts
+system performance due to overreclaim, to the point where the feature
+becomes self-defeating.
+
+The memory.low boundary on the other hand is a top-down allocated
+reserve.  A cgroup enjoys reclaim protection when it and all its
+ancestors are below their low boundaries, which makes delegation of
+subtrees possible.  Secondly, new cgroups have no reserve per default
+and in the common case most cgroups are eligible for the preferred
+reclaim pass.  This allows the new low boundary to be efficiently
+implemented with just a minor addition to the generic reclaim code,
+without the need for out-of-band data structures and reclaim passes.
+Because the generic reclaim code considers all cgroups except for the
+ones running low in the preferred first reclaim pass, overreclaim of
+individual groups is eliminated as well, resulting in much better
+overall workload performance.
+
+The original high boundary, the hard limit, is defined as a strict
+limit that can not budge, even if the OOM killer has to be called.
+But this generally goes against the goal of making the most out of the
+available memory.  The memory consumption of workloads varies during
+runtime, and that requires users to overcommit.  But doing that with a
+strict upper limit requires either a fairly accurate prediction of the
+working set size or adding slack to the limit.  Since working set size
+estimation is hard and error prone, and getting it wrong results in
+OOM kills, most users tend to err on the side of a looser limit and
+end up wasting precious resources.
+
+The memory.high boundary on the other hand can be set much more
+conservatively.  When hit, it throttles allocations by forcing them
+into direct reclaim to work off the excess, but it never invokes the
+OOM killer.  As a result, a high boundary that is chosen too
+aggressively will not terminate the processes, but instead it will
+lead to gradual performance degradation.  The user can monitor this
+and make corrections until the minimal memory footprint that still
+gives acceptable performance is found.
+
+In extreme cases, with many concurrent allocations and a complete
+breakdown of reclaim progress within the group, the high boundary can
+be exceeded.  But even then it's mostly better to satisfy the
+allocation from the slack available in other groups or the rest of the
+system than killing the group.  Otherwise, memory.max is there to
+limit this type of spillover and ultimately contain buggy or even
+malicious applications.
+
+The combined memory+swap accounting and limiting is replaced by real
+control over swap space.
+
+The main argument for a combined memory+swap facility in the original
+cgroup design was that global or parental pressure would always be
+able to swap all anonymous memory of a child group, regardless of the
+child's own (possibly untrusted) configuration.  However, untrusted
+groups can sabotage swapping by other means - such as referencing its
+anonymous memory in a tight loop - and an admin can not assume full
+swappability when overcommitting untrusted jobs.
+
+For trusted jobs, on the other hand, a combined counter is not an
+intuitive userspace interface, and it flies in the face of the idea
+that cgroup controllers should account and limit specific physical
+resources.  Swap space is a resource like all others in the system,
+and that's why unified hierarchy allows distributing it separately.

Documentation/cgroups/unified-hierarchy.txt

@@ -1,647 +0,0 @@
-
-Cgroup unified hierarchy
-
-April, 2014		Tejun Heo <tj@kernel.org>
-
-This document describes the changes made by unified hierarchy and
-their rationales.  It will eventually be merged into the main cgroup
-documentation.
-
-CONTENTS
-
-1. Background
-2. Basic Operation
-  2-1. Mounting
-  2-2. cgroup.subtree_control
-  2-3. cgroup.controllers
-3. Structural Constraints
-  3-1. Top-down
-  3-2. No internal tasks
-4. Delegation
-  4-1. Model of delegation
-  4-2. Common ancestor rule
-5. Other Changes
-  5-1. [Un]populated Notification
-  5-2. Other Core Changes
-  5-3. Controller File Conventions
-    5-3-1. Format
-    5-3-2. Control Knobs
-  5-4. Per-Controller Changes
-    5-4-1. io
-    5-4-2. cpuset
-    5-4-3. memory
-6. Planned Changes
-  6-1. CAP for resource control
-
-
-1. Background
-
-cgroup allows an arbitrary number of hierarchies and each hierarchy
-can host any number of controllers.  While this seems to provide a
-high level of flexibility, it isn't quite useful in practice.
-
-For example, as there is only one instance of each controller, utility
-type controllers such as freezer which can be useful in all
-hierarchies can only be used in one.  The issue is exacerbated by the
-fact that controllers can't be moved around once hierarchies are
-populated.  Another issue is that all controllers bound to a hierarchy
-are forced to have exactly the same view of the hierarchy.  It isn't
-possible to vary the granularity depending on the specific controller.
-
-In practice, these issues heavily limit which controllers can be put
-on the same hierarchy and most configurations resort to putting each
-controller on its own hierarchy.  Only closely related ones, such as
-the cpu and cpuacct controllers, make sense to put on the same
-hierarchy.  This often means that userland ends up managing multiple
-similar hierarchies repeating the same steps on each hierarchy
-whenever a hierarchy management operation is necessary.
-
-Unfortunately, support for multiple hierarchies comes at a steep cost.
-Internal implementation in cgroup core proper is dazzlingly
-complicated but more importantly the support for multiple hierarchies
-restricts how cgroup is used in general and what controllers can do.
-
-There's no limit on how many hierarchies there may be, which means
-that a task's cgroup membership can't be described in finite length.
-The key may contain any varying number of entries and is unlimited in
-length, which makes it highly awkward to handle and leads to addition
-of controllers which exist only to identify membership, which in turn
-exacerbates the original problem.
-
-Also, as a controller can't have any expectation regarding what shape
-of hierarchies other controllers would be on, each controller has to
-assume that all other controllers are operating on completely
-orthogonal hierarchies.  This makes it impossible, or at least very
-cumbersome, for controllers to cooperate with each other.
-
-In most use cases, putting controllers on hierarchies which are
-completely orthogonal to each other isn't necessary.  What usually is
-called for is the ability to have differing levels of granularity
-depending on the specific controller.  In other words, hierarchy may
-be collapsed from leaf towards root when viewed from specific
-controllers.  For example, a given configuration might not care about
-how memory is distributed beyond a certain level while still wanting
-to control how CPU cycles are distributed.
-
-Unified hierarchy is the next version of cgroup interface.  It aims to
-address the aforementioned issues by having more structure while
-retaining enough flexibility for most use cases.  Various other
-general and controller-specific interface issues are also addressed in
-the process.
-
-
-2. Basic Operation
-
-2-1. Mounting
-
-Currently, unified hierarchy can be mounted with the following mount
-command.  Note that this is still under development and scheduled to
-change soon.
-
- mount -t cgroup -o __DEVEL__sane_behavior cgroup $MOUNT_POINT
-
-All controllers which support the unified hierarchy and are not bound
-to other hierarchies are automatically bound to unified hierarchy and
-show up at the root of it.  Controllers which are enabled only in the
-root of unified hierarchy can be bound to other hierarchies.  This
-allows mixing unified hierarchy with the traditional multiple
-hierarchies in a fully backward compatible way.
-
-A controller can be moved across hierarchies only after the controller
-is no longer referenced in its current hierarchy.  Because per-cgroup
-controller states are destroyed asynchronously and controllers may
-have lingering references, a controller may not show up immediately on
-the unified hierarchy after the final umount of the previous
-hierarchy.  Similarly, a controller should be fully disabled to be
-moved out of the unified hierarchy and it may take some time for the
-disabled controller to become available for other hierarchies;
-furthermore, due to dependencies among controllers, other controllers
-may need to be disabled too.
-
-While useful for development and manual configurations, dynamically
-moving controllers between the unified and other hierarchies is
-strongly discouraged for production use.  It is recommended to decide
-the hierarchies and controller associations before starting using the
-controllers.
-
-
-2-2. cgroup.subtree_control
-
-All cgroups on unified hierarchy have a "cgroup.subtree_control" file
-which governs which controllers are enabled on the children of the
-cgroup.  Let's assume a hierarchy like the following.
-
-  root - A - B - C
-               \ D
-
-root's "cgroup.subtree_control" file determines which controllers are
-enabled on A.  A's on B.  B's on C and D.  This coincides with the
-fact that controllers on the immediate sub-level are used to
-distribute the resources of the parent.  In fact, it's natural to
-assume that resource control knobs of a child belong to its parent.
-Enabling a controller in a "cgroup.subtree_control" file declares that
-distribution of the respective resources of the cgroup will be
-controlled.  Note that this means that controller enable states are
-shared among siblings.
-
-When read, the file contains a space-separated list of currently
-enabled controllers.  A write to the file should contain a
-space-separated list of controllers with '+' or '-' prefixed (without
-the quotes).  Controllers prefixed with '+' are enabled and '-'
-disabled.  If a controller is listed multiple times, the last entry
-wins.  The specific operations are executed atomically - either all
-succeed or fail.
-
-
-2-3. cgroup.controllers
-
-Read-only "cgroup.controllers" file contains a space-separated list of
-controllers which can be enabled in the cgroup's
-"cgroup.subtree_control" file.
-
-In the root cgroup, this lists controllers which are not bound to
-other hierarchies and the content changes as controllers are bound to
-and unbound from other hierarchies.
-
-In non-root cgroups, the content of this file equals that of the
-parent's "cgroup.subtree_control" file as only controllers enabled
-from the parent can be used in its children.
-
-
-3. Structural Constraints
-
-3-1. Top-down
-
-As it doesn't make sense to nest control of an uncontrolled resource,
-all non-root "cgroup.subtree_control" files can only contain
-controllers which are enabled in the parent's "cgroup.subtree_control"
-file.  A controller can be enabled only if the parent has the
-controller enabled and a controller can't be disabled if one or more
-children have it enabled.
-
-
-3-2. No internal tasks
-
-One long-standing issue that cgroup faces is the competition between
-tasks belonging to the parent cgroup and its children cgroups.  This
-is inherently nasty as two different types of entities compete and
-there is no agreed-upon obvious way to handle it.  Different
-controllers are doing different things.
-
-The cpu controller considers tasks and cgroups as equivalents and maps
-nice levels to cgroup weights.  This works for some cases but falls
-flat when children should be allocated specific ratios of CPU cycles
-and the number of internal tasks fluctuates - the ratios constantly
-change as the number of competing entities fluctuates.  There also are
-other issues.  The mapping from nice level to weight isn't obvious or
-universal, and there are various other knobs which simply aren't
-available for tasks.
-
-The io controller implicitly creates a hidden leaf node for each
-cgroup to host the tasks.  The hidden leaf has its own copies of all
-the knobs with "leaf_" prefixed.  While this allows equivalent control
-over internal tasks, it's with serious drawbacks.  It always adds an
-extra layer of nesting which may not be necessary, makes the interface
-messy and significantly complicates the implementation.
-
-The memory controller currently doesn't have a way to control what
-happens between internal tasks and child cgroups and the behavior is
-not clearly defined.  There have been attempts to add ad-hoc behaviors
-and knobs to tailor the behavior to specific workloads.  Continuing
-this direction will lead to problems which will be extremely difficult
-to resolve in the long term.
-
-Multiple controllers struggle with internal tasks and came up with
-different ways to deal with it; unfortunately, all the approaches in
-use now are severely flawed and, furthermore, the widely different
-behaviors make cgroup as whole highly inconsistent.
-
-It is clear that this is something which needs to be addressed from
-cgroup core proper in a uniform way so that controllers don't need to
-worry about it and cgroup as a whole shows a consistent and logical
-behavior.  To achieve that, unified hierarchy enforces the following
-structural constraint:
-
- Except for the root, only cgroups which don't contain any task may
- have controllers enabled in their "cgroup.subtree_control" files.
-
-Combined with other properties, this guarantees that, when a
-controller is looking at the part of the hierarchy which has it
-enabled, tasks are always only on the leaves.  This rules out
-situations where child cgroups compete against internal tasks of the
-parent.
-
-There are two things to note.  Firstly, the root cgroup is exempt from
-the restriction.  Root contains tasks and anonymous resource
-consumption which can't be associated with any other cgroup and
-requires special treatment from most controllers.  How resource
-consumption in the root cgroup is governed is up to each controller.
-
-Secondly, the restriction doesn't take effect if there is no enabled
-controller in the cgroup's "cgroup.subtree_control" file.  This is
-important as otherwise it wouldn't be possible to create children of a
-populated cgroup.  To control resource distribution of a cgroup, the
-cgroup must create children and transfer all its tasks to the children
-before enabling controllers in its "cgroup.subtree_control" file.
-
-
-4. Delegation
-
-4-1. Model of delegation
-
-A cgroup can be delegated to a less privileged user by granting write
-access of the directory and its "cgroup.procs" file to the user.  Note
-that the resource control knobs in a given directory concern the
-resources of the parent and thus must not be delegated along with the
-directory.
-
-Once delegated, the user can build sub-hierarchy under the directory,
-organize processes as it sees fit and further distribute the resources
-it got from the parent.  The limits and other settings of all resource
-controllers are hierarchical and regardless of what happens in the
-delegated sub-hierarchy, nothing can escape the resource restrictions
-imposed by the parent.
-
-Currently, cgroup doesn't impose any restrictions on the number of
-cgroups in or nesting depth of a delegated sub-hierarchy; however,
-this may in the future be limited explicitly.
-
-
-4-2. Common ancestor rule
-
-On the unified hierarchy, to write to a "cgroup.procs" file, in
-addition to the usual write permission to the file and uid match, the
-writer must also have write access to the "cgroup.procs" file of the
-common ancestor of the source and destination cgroups.  This prevents
-delegatees from smuggling processes across disjoint sub-hierarchies.
-
-Let's say cgroups C0 and C1 have been delegated to user U0 who created
-C00, C01 under C0 and C10 under C1 as follows.
-
- ~~~~~~~~~~~~~ - C0 - C00
- ~ cgroup    ~      \ C01
- ~ hierarchy ~
- ~~~~~~~~~~~~~ - C1 - C10
-
-C0 and C1 are separate entities in terms of resource distribution
-regardless of their relative positions in the hierarchy.  The
-resources the processes under C0 are entitled to are controlled by
-C0's ancestors and may be completely different from C1.  It's clear
-that the intention of delegating C0 to U0 is allowing U0 to organize
-the processes under C0 and further control the distribution of C0's
-resources.
-
-On traditional hierarchies, if a task has write access to "tasks" or
-"cgroup.procs" file of a cgroup and its uid agrees with the target, it
-can move the target to the cgroup.  In the above example, U0 will not
-only be able to move processes in each sub-hierarchy but also across
-the two sub-hierarchies, effectively allowing it to violate the
-organizational and resource restrictions implied by the hierarchical
-structure above C0 and C1.
-
-On the unified hierarchy, let's say U0 wants to write the pid of a
-process which has a matching uid and is currently in C10 into
-"C00/cgroup.procs".  U0 obviously has write access to the file and
-migration permission on the process; however, the common ancestor of
-the source cgroup C10 and the destination cgroup C00 is above the
-points of delegation and U0 would not have write access to its
-"cgroup.procs" and thus be denied with -EACCES.
-
-
-5. Other Changes
-
-5-1. [Un]populated Notification
-
-cgroup users often need a way to determine when a cgroup's
-subhierarchy becomes empty so that it can be cleaned up.  cgroup
-currently provides release_agent for it; unfortunately, this mechanism
-is riddled with issues.
-
-- It delivers events by forking and execing a userland binary
-  specified as the release_agent.  This is a long deprecated method of
-  notification delivery.  It's extremely heavy, slow and cumbersome to
-  integrate with larger infrastructure.
-
-- There is single monitoring point at the root.  There's no way to
-  delegate management of a subtree.
-
-- The event isn't recursive.  It triggers when a cgroup doesn't have
-  any tasks or child cgroups.  Events for internal nodes trigger only
-  after all children are removed.  This again makes it impossible to
-  delegate management of a subtree.
-
-- Events are filtered from the kernel side.  A "notify_on_release"
-  file is used to subscribe to or suppress release events.  This is
-  unnecessarily complicated and probably done this way because event
-  delivery itself was expensive.
-
-Unified hierarchy implements "populated" field in "cgroup.events"
-interface file which can be used to monitor whether the cgroup's
-subhierarchy has tasks in it or not.  Its value is 0 if there is no
-task in the cgroup and its descendants; otherwise, 1.  poll and
-[id]notify events are triggered when the value changes.
-
-This is significantly lighter and simpler and trivially allows
-delegating management of subhierarchy - subhierarchy monitoring can
-block further propagation simply by putting itself or another process
-in the subhierarchy and monitor events that it's interested in from
-there without interfering with monitoring higher in the tree.
-
-In unified hierarchy, the release_agent mechanism is no longer
-supported and the interface files "release_agent" and
-"notify_on_release" do not exist.
-
-
-5-2. Other Core Changes
-
-- None of the mount options is allowed.
-
-- remount is disallowed.
-
-- rename(2) is disallowed.
-
-- The "tasks" file is removed.  Everything should at process
-  granularity.  Use the "cgroup.procs" file instead.
-
-- The "cgroup.procs" file is not sorted.  pids will be unique unless
-  they got recycled in-between reads.
-
-- The "cgroup.clone_children" file is removed.
-
-- /proc/PID/cgroup keeps reporting the cgroup that a zombie belonged
-  to before exiting.  If the cgroup is removed before the zombie is
-  reaped, " (deleted)" is appeneded to the path.
-
-
-5-3. Controller File Conventions
-
-5-3-1. Format
-
-In general, all controller files should be in one of the following
-formats whenever possible.
-
-- Values only files
-
-  VAL0 VAL1...\n
-
-- Flat keyed files
-
-  KEY0 VAL0\n
-  KEY1 VAL1\n
-  ...
-
-- Nested keyed files
-
-  KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
-  KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
-  ...
-
-For a writeable file, the format for writing should generally match
-reading; however, controllers may allow omitting later fields or
-implement restricted shortcuts for most common use cases.
-
-For both flat and nested keyed files, only the values for a single key
-can be written at a time.  For nested keyed files, the sub key pairs
-may be specified in any order and not all pairs have to be specified.
-
-
-5-3-2. Control Knobs
-
-- Settings for a single feature should generally be implemented in a
-  single file.
-
-- In general, the root cgroup should be exempt from resource control
-  and thus shouldn't have resource control knobs.
-
-- If a controller implements ratio based resource distribution, the
-  control knob should be named "weight" and have the range [1, 10000]
-  and 100 should be the default value.  The values are chosen to allow
-  enough and symmetric bias in both directions while keeping it
-  intuitive (the default is 100%).
-
-- If a controller implements an absolute resource guarantee and/or
-  limit, the control knobs should be named "min" and "max"
-  respectively.  If a controller implements best effort resource
-  gurantee and/or limit, the control knobs should be named "low" and
-  "high" respectively.
-
-  In the above four control files, the special token "max" should be
-  used to represent upward infinity for both reading and writing.
-
-- If a setting has configurable default value and specific overrides,
-  the default settings should be keyed with "default" and appear as
-  the first entry in the file.  Specific entries can use "default" as
-  its value to indicate inheritance of the default value.
-
-- For events which are not very high frequency, an interface file
-  "events" should be created which lists event key value pairs.
-  Whenever a notifiable event happens, file modified event should be
-  generated on the file.
-
-
-5-4. Per-Controller Changes
-
-5-4-1. io
-
-- blkio is renamed to io.  The interface is overhauled anyway.  The
-  new name is more in line with the other two major controllers, cpu
-  and memory, and better suited given that it may be used for cgroup
-  writeback without involving block layer.
-
-- Everything including stat is always hierarchical making separate
-  recursive stat files pointless and, as no internal node can have
-  tasks, leaf weights are meaningless.  The operation model is
-  simplified and the interface is overhauled accordingly.
-
-  io.stat
-
-	The stat file.  The reported stats are from the point where
-	bio's are issued to request_queue.  The stats are counted
-	independent of which policies are enabled.  Each line in the
-	file follows the following format.  More fields may later be
-	added at the end.
-
-	  $MAJ:$MIN rbytes=$RBYTES wbytes=$WBYTES rios=$RIOS wrios=$WIOS
-
-  io.weight
-
-	The weight setting, currently only available and effective if
-	cfq-iosched is in use for the target device.  The weight is
-	between 1 and 10000 and defaults to 100.  The first line
-	always contains the default weight in the following format to
-	use when per-device setting is missing.
-
-	  default $WEIGHT
-
-	Subsequent lines list per-device weights of the following
-	format.
-
-	  $MAJ:$MIN $WEIGHT
-
-	Writing "$WEIGHT" or "default $WEIGHT" changes the default
-	setting.  Writing "$MAJ:$MIN $WEIGHT" sets per-device weight
-	while "$MAJ:$MIN default" clears it.
-
-	This file is available only on non-root cgroups.
-
-  io.max
-
-	The maximum bandwidth and/or iops setting, only available if
-	blk-throttle is enabled.  The file is of the following format.
-
-	  $MAJ:$MIN rbps=$RBPS wbps=$WBPS riops=$RIOPS wiops=$WIOPS
-
-	${R|W}BPS are read/write bytes per second and ${R|W}IOPS are
-	read/write IOs per second.  "max" indicates no limit.  Writing
-	to the file follows the same format but the individual
-	settings may be omitted or specified in any order.
-
-	This file is available only on non-root cgroups.
-
-
-5-4-2. cpuset
-
-- Tasks are kept in empty cpusets after hotplug and take on the masks
-  of the nearest non-empty ancestor, instead of being moved to it.
-
-- A task can be moved into an empty cpuset, and again it takes on the
-  masks of the nearest non-empty ancestor.
-
-
-5-4-3. memory
-
-- use_hierarchy is on by default and the cgroup file for the flag is
-  not created.
-
-- The original lower boundary, the soft limit, is defined as a limit
-  that is per default unset.  As a result, the set of cgroups that
-  global reclaim prefers is opt-in, rather than opt-out.  The costs
-  for optimizing these mostly negative lookups are so high that the
-  implementation, despite its enormous size, does not even provide the
-  basic desirable behavior.  First off, the soft limit has no
-  hierarchical meaning.  All configured groups are organized in a
-  global rbtree and treated like equal peers, regardless where they
-  are located in the hierarchy.  This makes subtree delegation
-  impossible.  Second, the soft limit reclaim pass is so aggressive
-  that it not just introduces high allocation latencies into the
-  system, but also impacts system performance due to overreclaim, to
-  the point where the feature becomes self-defeating.
-
-  The memory.low boundary on the other hand is a top-down allocated
-  reserve.  A cgroup enjoys reclaim protection when it and all its
-  ancestors are below their low boundaries, which makes delegation of
-  subtrees possible.  Secondly, new cgroups have no reserve per
-  default and in the common case most cgroups are eligible for the
-  preferred reclaim pass.  This allows the new low boundary to be
-  efficiently implemented with just a minor addition to the generic
-  reclaim code, without the need for out-of-band data structures and
-  reclaim passes.  Because the generic reclaim code considers all
-  cgroups except for the ones running low in the preferred first
-  reclaim pass, overreclaim of individual groups is eliminated as
-  well, resulting in much better overall workload performance.
-
-- The original high boundary, the hard limit, is defined as a strict
-  limit that can not budge, even if the OOM killer has to be called.
-  But this generally goes against the goal of making the most out of
-  the available memory.  The memory consumption of workloads varies
-  during runtime, and that requires users to overcommit.  But doing
-  that with a strict upper limit requires either a fairly accurate
-  prediction of the working set size or adding slack to the limit.
-  Since working set size estimation is hard and error prone, and
-  getting it wrong results in OOM kills, most users tend to err on the
-  side of a looser limit and end up wasting precious resources.
-
-  The memory.high boundary on the other hand can be set much more
-  conservatively.  When hit, it throttles allocations by forcing them
-  into direct reclaim to work off the excess, but it never invokes the
-  OOM killer.  As a result, a high boundary that is chosen too
-  aggressively will not terminate the processes, but instead it will
-  lead to gradual performance degradation.  The user can monitor this
-  and make corrections until the minimal memory footprint that still
-  gives acceptable performance is found.
-
-  In extreme cases, with many concurrent allocations and a complete
-  breakdown of reclaim progress within the group, the high boundary
-  can be exceeded.  But even then it's mostly better to satisfy the
-  allocation from the slack available in other groups or the rest of
-  the system than killing the group.  Otherwise, memory.max is there
-  to limit this type of spillover and ultimately contain buggy or even
-  malicious applications.
-
-- The original control file names are unwieldy and inconsistent in
-  many different ways.  For example, the upper boundary hit count is
-  exported in the memory.failcnt file, but an OOM event count has to
-  be manually counted by listening to memory.oom_control events, and
-  lower boundary / soft limit events have to be counted by first
-  setting a threshold for that value and then counting those events.
-  Also, usage and limit files encode their units in the filename.
-  That makes the filenames very long, even though this is not
-  information that a user needs to be reminded of every time they type
-  out those names.
-
-  To address these naming issues, as well as to signal clearly that
-  the new interface carries a new configuration model, the naming
-  conventions in it necessarily differ from the old interface.
-
-- The original limit files indicate the state of an unset limit with a
-  Very High Number, and a configured limit can be unset by echoing -1
-  into those files.  But that very high number is implementation and
-  architecture dependent and not very descriptive.  And while -1 can
-  be understood as an underflow into the highest possible value, -2 or
-  -10M etc. do not work, so it's not consistent.
-
-  memory.low, memory.high, and memory.max will use the string "max" to
-  indicate and set the highest possible value.
-
-6. Planned Changes
-
-6-1. CAP for resource control
-
-Unified hierarchy will require one of the capabilities(7), which is
-yet to be decided, for all resource control related knobs.  Process
-organization operations - creation of sub-cgroups and migration of
-processes in sub-hierarchies may be delegated by changing the
-ownership and/or permissions on the cgroup directory and
-"cgroup.procs" interface file; however, all operations which affect
-resource control - writes to a "cgroup.subtree_control" file or any
-controller-specific knobs - will require an explicit CAP privilege.
-
-This, in part, is to prevent the cgroup interface from being
-inadvertently promoted to programmable API used by non-privileged
-binaries.  cgroup exposes various aspects of the system in ways which
-aren't properly abstracted for direct consumption by regular programs.
-This is an administration interface much closer to sysctl knobs than
-system calls.  Even the basic access model, being filesystem path
-based, isn't suitable for direct consumption.  There's no way to
-access "my cgroup" in a race-free way or make multiple operations
-atomic against migration to another cgroup.
-
-Another aspect is that, for better or for worse, the cgroup interface
-goes through far less scrutiny than regular interfaces for
-unprivileged userland.  The upside is that cgroup is able to expose
-useful features which may not be suitable for general consumption in a
-reasonable time frame.  It provides a relatively short path between
-internal details and userland-visible interface.  Of course, this
-shortcut comes with high risk.  We go through what we go through for
-general kernel APIs for good reasons.  It may end up leaking internal
-details in a way which can exert significant pain by locking the
-kernel into a contract that can't be maintained in a reasonable
-manner.
-
-Also, due to the specific nature, cgroup and its controllers don't
-tend to attract attention from a wide scope of developers.  cgroup's
-short history is already fraught with severely mis-designed
-interfaces, unnecessary commitments to and exposing of internal
-details, broken and dangerous implementations of various features.
-
-Keeping cgroup as an administration interface is both advantageous for
-its role and imperative given its nature.  Some of the cgroup features
-may make sense for unprivileged access.  If deemed justified, those
-must be further abstracted and implemented as a different interface,
-be it a system call or process-private filesystem, and survive through
-the scrutiny that any interface for general consumption is required to
-go through.
-
-Requiring CAP is not a complete solution but should serve as a
-significant deterrent against spraying cgroup usages in non-privileged
-programs.

Documentation/cpu-freq/intel-pstate.txt

@@ -1,61 +1,131 @@
-Intel P-state driver
+Intel P-State driver
 --------------------
 
-This driver provides an interface to control the P state selection for
-SandyBridge+ Intel processors.  The driver can operate two different
-modes based on the processor model, legacy mode and Hardware P state (HWP)
-mode.
-
-In legacy mode, the Intel P-state implements two internal governors,
-performance and powersave, that differ from the general cpufreq governors of
-the same name (the general cpufreq governors implement target(), whereas the
-internal Intel P-state governors implement setpolicy()).  The internal
-performance governor sets the max_perf_pct and min_perf_pct to 100; that is,
-the governor selects the highest available P state to maximize the performance
-of the core.  The internal powersave governor selects the appropriate P state
-based on the current load on the CPU.
-
-In HWP mode P state selection is implemented in the processor
-itself. The driver provides the interfaces between the cpufreq core and
-the processor to control P state selection based on user preferences
-and reporting frequency to the cpufreq core.  In this mode the
-internal Intel P-state governor code is disabled.
-
-In addition to the interfaces provided by the cpufreq core for
-controlling frequency the driver provides sysfs files for
-controlling P state selection. These files have been added to
-/sys/devices/system/cpu/intel_pstate/
-
-      max_perf_pct: limits the maximum P state that will be requested by
-      the driver stated as a percentage of the available performance. The
-      available (P states) performance may be reduced by the no_turbo
+This driver provides an interface to control the P-State selection for the
+SandyBridge+ Intel processors.
+
+The following document explains P-States:
+http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
+As stated in the document, P-State doesn’t exactly mean a frequency. However, for
+the sake of the relationship with cpufreq, P-State and frequency are used
+interchangeably.
+
+Understanding the cpufreq core governors and policies are important before
+discussing more details about the Intel P-State driver. Based on what callbacks
+a cpufreq driver provides to the cpufreq core, it can support two types of
+drivers:
+- with target_index() callback: In this mode, the drivers using cpufreq core
+simply provide the minimum and maximum frequency limits and an additional
+interface target_index() to set the current frequency. The cpufreq subsystem
+has a number of scaling governors ("performance", "powersave", "ondemand",
+etc.). Depending on which governor is in use, cpufreq core will call for
+transitions to a specific frequency using target_index() callback.
+- setpolicy() callback: In this mode, drivers do not provide target_index()
+callback, so cpufreq core can't request a transition to a specific frequency.
+The driver provides minimum and maximum frequency limits and callbacks to set a
+policy. The policy in cpufreq sysfs is referred to as the "scaling governor".
+The cpufreq core can request the driver to operate in any of the two policies:
+"performance: and "powersave". The driver decides which frequency to use based
+on the above policy selection considering minimum and maximum frequency limits.
+
+The Intel P-State driver falls under the latter category, which implements the
+setpolicy() callback. This driver decides what P-State to use based on the
+requested policy from the cpufreq core. If the processor is capable of
+selecting its next P-State internally, then the driver will offload this
+responsibility to the processor (aka HWP: Hardware P-States). If not, the
+driver implements algorithms to select the next P-State.
+
+Since these policies are implemented in the driver, they are not same as the
+cpufreq scaling governors implementation, even if they have the same name in
+the cpufreq sysfs (scaling_governors). For example the "performance" policy is
+similar to cpufreq’s "performance" governor, but "powersave" is completely
+different than the cpufreq "powersave" governor. The strategy here is similar
+to cpufreq "ondemand", where the requested P-State is related to the system load.
+
+Sysfs Interface
+
+In addition to the frequency-controlling interfaces provided by the cpufreq
+core, the driver provides its own sysfs files to control the P-State selection.
+These files have been added to /sys/devices/system/cpu/intel_pstate/.
+Any changes made to these files are applicable to all CPUs (even in a
+multi-package system).
+
+      max_perf_pct: Limits the maximum P-State that will be requested by
+      the driver. It states it as a percentage of the available performance. The
+      available (P-State) performance may be reduced by the no_turbo
       setting described below.
 
-      min_perf_pct: limits the minimum P state that will be  requested by
-      the driver stated as a percentage of the max (non-turbo)
+      min_perf_pct: Limits the minimum P-State that will be requested by
+      the driver. It states it as a percentage of the max (non-turbo)
       performance level.
 
-      no_turbo: limits the driver to selecting P states below the turbo
+      no_turbo: Limits the driver to selecting P-State below the turbo
       frequency range.
 
-      turbo_pct: displays the percentage of the total performance that
-      is supported by hardware that is in the turbo range.  This number
+      turbo_pct: Displays the percentage of the total performance that
+      is supported by hardware that is in the turbo range. This number
       is independent of whether turbo has been disabled or not.
 
-      num_pstates: displays the number of pstates that are supported
-      by hardware.  This number is independent of whether turbo has
+      num_pstates: Displays the number of P-States that are supported
+      by hardware. This number is independent of whether turbo has
       been disabled or not.
 
+For example, if a system has these parameters:
+	Max 1 core turbo ratio: 0x21 (Max 1 core ratio is the maximum P-State)
+	Max non turbo ratio: 0x17
+	Minimum ratio : 0x08 (Here the ratio is called max efficiency ratio)
+
+Sysfs will show :
+	max_perf_pct:100, which corresponds to 1 core ratio
+	min_perf_pct:24, max_efficiency_ratio / max 1 Core ratio
+	no_turbo:0, turbo is not disabled
+	num_pstates:26 = (max 1 Core ratio - Max Efficiency Ratio + 1)
+	turbo_pct:39 = (max 1 core ratio - max non turbo ratio) / num_pstates
+
+Refer to "Intel® 64 and IA-32 Architectures Software Developer’s Manual
+Volume 3: System Programming Guide" to understand ratios.
+
+cpufreq sysfs for Intel P-State
+
+Since this driver registers with cpufreq, cpufreq sysfs is also presented.
+There are some important differences, which need to be considered.
+
+scaling_cur_freq: This displays the real frequency which was used during
+the last sample period instead of what is requested. Some other cpufreq driver,
+like acpi-cpufreq, displays what is requested (Some changes are on the
+way to fix this for acpi-cpufreq driver). The same is true for frequencies
+displayed at /proc/cpuinfo.
+
+scaling_governor: This displays current active policy. Since each CPU has a
+cpufreq sysfs, it is possible to set a scaling governor to each CPU. But this
+is not possible with Intel P-States, as there is one common policy for all
+CPUs. Here, the last requested policy will be applicable to all CPUs. It is
+suggested that one use the cpupower utility to change policy to all CPUs at the
+same time.
+
+scaling_setspeed: This attribute can never be used with Intel P-State.
+
+scaling_max_freq/scaling_min_freq: This interface can be used similarly to
+the max_perf_pct/min_perf_pct of Intel P-State sysfs. However since frequencies
+are converted to nearest possible P-State, this is prone to rounding errors.
+This method is not preferred to limit performance.
+
+affected_cpus: Not used
+related_cpus: Not used
+
 For contemporary Intel processors, the frequency is controlled by the
-processor itself and the P-states exposed to software are related to
+processor itself and the P-State exposed to software is related to
 performance levels.  The idea that frequency can be set to a single
-frequency is fiction for Intel Core processors. Even if the scaling
-driver selects a single P state the actual frequency the processor
+frequency is fictional for Intel Core processors. Even if the scaling
+driver selects a single P-State, the actual frequency the processor
 will run at is selected by the processor itself.
 
-For legacy mode debugfs files have also been added to allow tuning of
-the internal governor algorythm. These files are located at
-/sys/kernel/debug/pstate_snb/ These files are NOT present in HWP mode.
+Tuning Intel P-State driver
+
+When HWP mode is not used, debugfs files have also been added to allow the
+tuning of the internal governor algorithm. These files are located at
+/sys/kernel/debug/pstate_snb/. The algorithm uses a PID (Proportional
+Integral Derivative) controller. The PID tunable parameters are:
 
       deadband
       d_gain_pct
@@ -63,3 +133,90 @@ the internal governor algorythm. These files are located at
       p_gain_pct
       sample_rate_ms
       setpoint
+
+To adjust these parameters, some understanding of driver implementation is
+necessary. There are some tweeks described here, but be very careful. Adjusting
+them requires expert level understanding of power and performance relationship.
+These limits are only useful when the "powersave" policy is active.
+
+-To make the system more responsive to load changes, sample_rate_ms can
+be adjusted  (current default is 10ms).
+-To make the system use higher performance, even if the load is lower, setpoint
+can be adjusted to a lower number. This will also lead to faster ramp up time
+to reach the maximum P-State.
+If there are no derivative and integral coefficients, The next P-State will be
+equal to:
+	current P-State - ((setpoint - current cpu load) * p_gain_pct)
+
+For example, if the current PID parameters are (Which are defaults for the core
+processors like SandyBridge):
+      deadband = 0
+      d_gain_pct = 0
+      i_gain_pct = 0
+      p_gain_pct = 20
+      sample_rate_ms = 10
+      setpoint = 97
+
+If the current P-State = 0x08 and current load = 100, this will result in the
+next P-State = 0x08 - ((97 - 100) * 0.2) = 8.6 (rounded to 9). Here the P-State
+goes up by only 1. If during next sample interval the current load doesn't
+change and still 100, then P-State goes up by one again. This process will
+continue as long as the load is more than the setpoint until the maximum P-State
+is reached.
+
+For the same load at setpoint = 60, this will result in the next P-State
+= 0x08 - ((60 - 100) * 0.2) = 16
+So by changing the setpoint from 97 to 60, there is an increase of the
+next P-State from 9 to 16. So this will make processor execute at higher
+P-State for the same CPU load. If the load continues to be more than the
+setpoint during next sample intervals, then P-State will go up again till the
+maximum P-State is reached. But the ramp up time to reach the maximum P-State
+will be much faster when the setpoint is 60 compared to 97.
+
+Debugging Intel P-State driver
+
+Event tracing
+To debug P-State transition, the Linux event tracing interface can be used.
+There are two specific events, which can be enabled (Provided the kernel
+configs related to event tracing are enabled).
+
+# cd /sys/kernel/debug/tracing/
+# echo 1 > events/power/pstate_sample/enable
+# echo 1 > events/power/cpu_frequency/enable
+# cat trace
+gnome-terminal--4510  [001] ..s.  1177.680733: pstate_sample: core_busy=107
+	scaled=94 from=26 to=26 mperf=1143818 aperf=1230607 tsc=29838618
+		freq=2474476
+cat-5235  [002] ..s.  1177.681723: cpu_frequency: state=2900000 cpu_id=2
+
+
+Using ftrace
+
+If function level tracing is required, the Linux ftrace interface can be used.
+For example if we want to check how often a function to set a P-State is
+called, we can set ftrace filter to intel_pstate_set_pstate.
+
+# cd /sys/kernel/debug/tracing/
+# cat available_filter_functions | grep -i pstate
+intel_pstate_set_pstate
+intel_pstate_cpu_init
+...
+
+# echo intel_pstate_set_pstate > set_ftrace_filter
+# echo function > current_tracer
+# cat trace | head -15
+# tracer: function
+#
+# entries-in-buffer/entries-written: 80/80   #P:4
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+            Xorg-3129  [000] ..s.  2537.644844: intel_pstate_set_pstate <-intel_pstate_timer_func
+ gnome-terminal--4510  [002] ..s.  2537.649844: intel_pstate_set_pstate <-intel_pstate_timer_func
+     gnome-shell-3409  [001] ..s.  2537.650850: intel_pstate_set_pstate <-intel_pstate_timer_func
+          <idle>-0     [000] ..s.  2537.654843: intel_pstate_set_pstate <-intel_pstate_timer_func

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 0. The PCC specification does
-not include a field to expose this value currently.
+The cpuinfo_transition_latency field is CPUFREQ_ETERNAL. The PCC specification
+does not include a field to expose this value currently.
 
 2.3 cpuinfo_cur_freq:
 ---------------------

Documentation/cpu-hotplug.txt

@@ -150,7 +150,7 @@ an entry as shown below in the output.
 
 If this is not mounted, do the following.
 
-	 #mkdir /sysfs
+	#mkdir /sys
 	#mount -t sysfs sys /sys
 
 Now you should see entries for all present cpu, the following is an example

Documentation/device-mapper/verity.txt

@@ -18,11 +18,11 @@ Construction Parameters
 
     0 is the original format used in the Chromium OS.
       The salt is appended when hashing, digests are stored continuously and
-      the rest of the block is padded with zeros.
+      the rest of the block is padded with zeroes.
 
     1 is the current format that should be used for new devices.
       The salt is prepended when hashing and each digest is
-      padded with zeros to the power of two.
+      padded with zeroes to the power of two.
 
 <dev>
     This is the device containing data, the integrity of which needs to be
@@ -79,6 +79,37 @@ restart_on_corruption
     not compatible with ignore_corruption and requires user space support to
     avoid restart loops.
 
+ignore_zero_blocks
+    Do not verify blocks that are expected to contain zeroes and always return
+    zeroes instead. This may be useful if the partition contains unused blocks
+    that are not guaranteed to contain zeroes.
+
+use_fec_from_device <fec_dev>
+    Use forward error correction (FEC) to recover from corruption if hash
+    verification fails. Use encoding data from the specified device. This
+    may be the same device where data and hash blocks reside, in which case
+    fec_start must be outside data and hash areas.
+
+    If the encoding data covers additional metadata, it must be accessible
+    on the hash device after the hash blocks.
+
+    Note: block sizes for data and hash devices must match. Also, if the
+    verity <dev> is encrypted the <fec_dev> should be too.
+
+fec_roots <num>
+    Number of generator roots. This equals to the number of parity bytes in
+    the encoding data. For example, in RS(M, N) encoding, the number of roots
+    is M-N.
+
+fec_blocks <num>
+    The number of encoding data blocks on the FEC device. The block size for
+    the FEC device is <data_block_size>.
+
+fec_start <offset>
+    This is the offset, in <data_block_size> blocks, from the start of the
+    FEC device to the beginning of the encoding data.
+
+
 Theory of operation
 ===================
 
@@ -98,6 +129,11 @@ per-block basis. This allows for a lightweight hash computation on first read
 into the page cache. Block hashes are stored linearly, aligned to the nearest
 block size.
 
+If forward error correction (FEC) support is enabled any recovery of
+corrupted data will be verified using the cryptographic hash of the
+corresponding data. This is why combining error correction with
+integrity checking is essential.
+
 Hash Tree
 ---------
 

Documentation/devicetree/bindings/arm/arm,scpi.txt

@@ -63,7 +63,7 @@ Required properties:
 - compatible : should be "arm,juno-sram-ns" for Non-secure SRAM on Juno
 
 The rest of the properties should follow the generic mmio-sram description
-found in ../../misc/sysram.txt
+found in ../../sram/sram.txt
 
 Each sub-node represents the reserved area for SCPI.
 

Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt

@@ -26,6 +26,10 @@ Raspberry Pi Model B+
 Required root node properties:
 compatible = "raspberrypi,model-b-plus", "brcm,bcm2835";
 
+Raspberry Pi 2 Model B
+Required root node properties:
+compatible = "raspberrypi,2-model-b", "brcm,bcm2836";
+
 Raspberry Pi Compute Module
 Required root node properties:
 compatible = "raspberrypi,compute-module", "brcm,bcm2835";

Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.txt

@@ -5,4 +5,11 @@ Boards with the BCM4708 SoC shall have the following properties:
 
 Required root node property:
 
+bcm4708
 compatible = "brcm,bcm4708";
+
+bcm4709
+compatible = "brcm,bcm4709";
+
+bcm53012
+compatible = "brcm,bcm53012";

Documentation/devicetree/bindings/arm/bcm/brcm,nsp-cpu-method.txt

@@ -0,0 +1,39 @@
+Broadcom Northstar Plus SoC CPU Enable Method
+---------------------------------------------
+This binding defines the enable method used for starting secondary
+CPU in the following Broadcom SoCs:
+  BCM58522, BCM58525, BCM58535, BCM58622, BCM58623, BCM58625, BCM88312
+
+The enable method is specified by defining the following required
+properties in the corresponding secondary "cpu" device tree node:
+  - enable-method = "brcm,bcm-nsp-smp";
+  - secondary-boot-reg = <...>;
+
+The secondary-boot-reg property is a u32 value that specifies the
+physical address of the register which should hold the common
+entry point for a secondary CPU. This entry is cpu node specific
+and should be added per cpu. E.g., in case of NSP (BCM58625) which
+is a dual core CPU SoC, this entry should be added to cpu1 node.
+
+
+Example:
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			next-level-cache = <&L2>;
+			reg = <0>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			next-level-cache = <&L2>;
+			enable-method = "brcm,bcm-nsp-smp";
+			secondary-boot-reg = <0xffff042c>;
+			reg = <1>;
+		};
+	};

Documentation/devicetree/bindings/arm/compulab-boards.txt

@@ -0,0 +1,25 @@
+CompuLab SB-SOM is a multi-module baseboard capable of carrying:
+ - CM-T43
+ - CM-T54
+ - CM-QS600
+ - CL-SOM-AM57x
+ - CL-SOM-iMX7
+modules with minor modifications to the SB-SOM assembly.
+
+Required root node properties:
+    - compatible = should be "compulab,sb-som"
+
+Compulab CL-SOM-iMX7 is a miniature System-on-Module (SoM) based on
+Freescale i.MX7 ARM Cortex-A7 System-on-Chip.
+
+Required root node properties:
+    - compatible = "compulab,cl-som-imx7", "fsl,imx7d";
+
+Compulab SBC-iMX7 is a single board computer based on the
+Freescale i.MX7 system-on-chip. SBC-iMX7 is implemented with
+the CL-SOM-iMX7 System-on-Module providing most of the functions,
+and SB-SOM-iMX7 carrier board providing additional peripheral
+functions and connectors.
+
+Required root node properties:
+    - compatible = "compulab,sbc-imx7", "compulab,cl-som-imx7", "fsl,imx7d";

Documentation/devicetree/bindings/arm/cpus.txt

@@ -157,6 +157,7 @@ nodes to be present and contain the properties described below.
 			    "arm,cortex-a17"
 			    "arm,cortex-a53"
 			    "arm,cortex-a57"
+			    "arm,cortex-a72"
 			    "arm,cortex-m0"
 			    "arm,cortex-m0+"
 			    "arm,cortex-m1"
@@ -190,6 +191,8 @@ nodes to be present and contain the properties described below.
 			    "allwinner,sun6i-a31"
 			    "allwinner,sun8i-a23"
 			    "arm,psci"
+			    "arm,realview-smp"
+			    "brcm,bcm-nsp-smp"
 			    "brcm,brahma-b15"
 			    "marvell,armada-375-smp"
 			    "marvell,armada-380-smp"
@@ -200,6 +203,7 @@ nodes to be present and contain the properties described below.
 			    "qcom,gcc-msm8660"
 			    "qcom,kpss-acc-v1"
 			    "qcom,kpss-acc-v2"
+			    "rockchip,rk3036-smp"
 			    "rockchip,rk3066-smp"
 			    "ste,dbx500-smp"
 
@@ -242,6 +246,23 @@ nodes to be present and contain the properties described below.
 		Definition: Specifies the syscon node controlling the cpu core
 			    power domains.
 
+	- dynamic-power-coefficient
+		Usage: optional
+		Value type: <prop-encoded-array>
+		Definition: A u32 value that represents the running time dynamic
+			    power coefficient in units of mW/MHz/uVolt^2. The
+			    coefficient can either be calculated from power
+			    measurements or derived by analysis.
+
+			    The dynamic power consumption of the CPU  is
+			    proportional to the square of the Voltage (V) and
+			    the clock frequency (f). The coefficient is used to
+			    calculate the dynamic power as below -
+
+			    Pdyn = dynamic-power-coefficient * V^2 * f
+
+			    where voltage is in uV, frequency is in MHz.
+
 Example 1 (dual-cluster big.LITTLE system 32-bit):
 
 	cpus {

Documentation/devicetree/bindings/arm/fsl.txt

@@ -131,6 +131,10 @@ Example:
 Freescale ARMv8 based Layerscape SoC family Device Tree Bindings
 ----------------------------------------------------------------
 
+LS1043A ARMv8 based RDB Board
+Required root node properties:
+    - compatible = "fsl,ls1043a-rdb", "fsl,ls1043a";
+
 LS2080A ARMv8 based Simulator model
 Required root node properties:
     - compatible = "fsl,ls2080a-simu", "fsl,ls2080a";

Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt

@@ -187,6 +187,22 @@ Example:
 		reg = <0xb0000000 0x10000>;
 	};
 
+Hisilicon HiP05 PERISUB system controller
+
+Required properties:
+- compatible : "hisilicon,hip05-perisubc", "syscon";
+- reg : Register address and size
+
+The HiP05 PERISUB system controller is shared by peripheral controllers in
+HiP05 Soc to implement some basic configurations. The peripheral
+controllers include mdio, ddr, iic, uart, timer and so on.
+
+Example:
+	/* for HiP05 perisub-ctrl-c system */
+	peri_c_subctrl: syscon@80000000 {
+		compatible = "hisilicon,hip05-perisubc", "syscon";
+		reg = <0x0 0x80000000 0x0 0x10000>;
+	};
 -----------------------------------------------------------------------
 Hisilicon CPU controller
 

Documentation/devicetree/bindings/arm/l2cc.txt → Documentation/devicetree/bindings/arm/l2c2x0.txt

@@ -1,7 +1,8 @@
 * ARM L2 Cache Controller
 
-ARM cores often have a separate level 2 cache controller. There are various
-implementations of the L2 cache controller with compatible programming models.
+ARM cores often have a separate L2C210/L2C220/L2C310 (also known as PL210/PL220/
+PL310 and variants) based level 2 cache controller. All these various implementations
+of the L2 cache controller have compatible programming models (Note 1).
 Some of the properties that are just prefixed "cache-*" are taken from section
 3.7.3 of the ePAPR v1.1 specification which can be found at:
 https://www.power.org/wp-content/uploads/2012/06/Power_ePAPR_APPROVED_v1.1.pdf
@@ -67,12 +68,17 @@ Optional properties:
   disable if zero.
 - arm,prefetch-offset : Override prefetch offset value. Valid values are
   0-7, 15, 23, and 31.
-- arm,shared-override : The default behavior of the pl310 cache controller with
-  respect to the shareable attribute is to transform "normal memory
-  non-cacheable transactions" into "cacheable no allocate" (for reads) or
-  "write through no write allocate" (for writes).
+- arm,shared-override : The default behavior of the L220 or PL310 cache
+  controllers with respect to the shareable attribute is to transform "normal
+  memory non-cacheable transactions" into "cacheable no allocate" (for reads)
+  or "write through no write allocate" (for writes).
   On systems where this may cause DMA buffer corruption, this property must be
   specified to indicate that such transforms are precluded.
+- arm,parity-enable : enable parity checking on the L2 cache (L220 or PL310).
+- arm,parity-disable : disable parity checking on the L2 cache (L220 or PL310).
+- arm,outer-sync-disable : disable the outer sync operation on the L2 cache.
+  Some core tiles, especially ARM PB11MPCore have a faulty L220 cache that
+  will randomly hang unless outer sync operations are disabled.
 - prefetch-data : Data prefetch. Value: <0> (forcibly disable), <1>
   (forcibly enable), property absent (retain settings set by firmware)
 - prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
@@ -91,3 +97,9 @@ L2: cache-controller {
         cache-level = <2>;
 	interrupts = <45>;
 };
+
+Note 1: The description in this document doesn't apply to integrated L2
+	cache controllers as found in e.g. Cortex-A15/A7/A57/A53. These
+	integrated L2 controllers are assumed to be all preconfigured by
+	early secure boot code. Thus no need to deal with their configuration
+	in the kernel at all.

Documentation/devicetree/bindings/arm/marvell,kirkwood.txt

@@ -24,6 +24,8 @@ board. Currently known boards are:
 "buffalo,lswxl"
 "buffalo,lsxhl"
 "buffalo,lsxl"
+"cloudengines,pogo02"
+"cloudengines,pogoplugv4"
 "dlink,dns-320"
 "dlink,dns-320-a1"
 "dlink,dns-325"

Documentation/devicetree/bindings/arm/mediatek.txt

@@ -6,6 +6,7 @@ following property:
 Required root node property:
 
 compatible: Must contain one of
+   "mediatek,mt2701"
    "mediatek,mt6580"
    "mediatek,mt6589"
    "mediatek,mt6592"
@@ -17,6 +18,9 @@ compatible: Must contain one of
 
 Supported boards:
 
+- Evaluation board for MT2701:
+    Required root node properties:
+      - compatible = "mediatek,mt2701-evb", "mediatek,mt2701";
 - Evaluation board for MT6580:
     Required root node properties:
       - compatible = "mediatek,mt6580-evbp1", "mediatek,mt6580";

Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt

@@ -18,7 +18,7 @@ The available clocks are defined in dt-bindings/clock/mt*-clk.h.
 Also it uses the common reset controller binding from
 Documentation/devicetree/bindings/reset/reset.txt.
 The available reset outputs are defined in
-dt-bindings/reset-controller/mt*-resets.h
+dt-bindings/reset/mt*-resets.h
 
 Example:
 

Documentation/devicetree/bindings/arm/mediatek/mediatek,pericfg.txt

@@ -18,7 +18,7 @@ The available clocks are defined in dt-bindings/clock/mt*-clk.h.
 Also it uses the common reset controller binding from
 Documentation/devicetree/bindings/reset/reset.txt.
 The available reset outputs are defined in
-dt-bindings/reset-controller/mt*-resets.h
+dt-bindings/reset/mt*-resets.h
 
 Example:
 

Documentation/devicetree/bindings/arm/omap/omap.txt

@@ -138,9 +138,21 @@ Boards:
 - AM335X phyBOARD-WEGA: Single Board Computer dev kit
   compatible = "phytec,am335x-wega", "phytec,am335x-phycore-som", "ti,am33xx"
 
+- AM335X CM-T335 : System On Module, built around the Sitara AM3352/4
+  compatible = "compulab,cm-t335", "ti,am33xx"
+
+- AM335X SBC-T335 : single board computer, built around the Sitara AM3352/4
+  compatible = "compulab,sbc-t335", "compulab,cm-t335", "ti,am33xx"
+
 - OMAP5 EVM : Evaluation Module
   compatible = "ti,omap5-evm", "ti,omap5"
 
+- AM437x CM-T43
+  compatible = "compulab,am437x-cm-t43", "ti,am4372", "ti,am43"
+
+- AM437x SBC-T43
+  compatible = "compulab,am437x-sbc-t43", "compulab,am437x-cm-t43", "ti,am4372", "ti,am43"
+
 - AM43x EPOS EVM
   compatible = "ti,am43x-epos-evm", "ti,am4372", "ti,am43"
 
@@ -150,6 +162,12 @@ Boards:
 - AM437x SK EVM: AM437x StarterKit Evaluation Module
   compatible = "ti,am437x-sk-evm", "ti,am4372", "ti,am43"
 
+- AM57XX CL-SOM-AM57x
+  compatible = "compulab,cl-som-am57x", "ti,am5728", "ti,dra742", "ti,dra74", "ti,dra7"
+
+- AM57XX SBC-AM57x
+  compatible = "compulab,sbc-am57x", "compulab,cl-som-am57x", "ti,am5728", "ti,dra742", "ti,dra74", "ti,dra7"
+
 - DRA742 EVM:  Software Development Board for DRA742
   compatible = "ti,dra7-evm", "ti,dra742", "ti,dra74", "ti,dra7"
 

Documentation/devicetree/bindings/arm/pmu.txt

@@ -9,8 +9,9 @@ Required properties:
 - compatible : should be one of
 	"apm,potenza-pmu"
 	"arm,armv8-pmuv3"
-	"arm.cortex-a57-pmu"
-	"arm.cortex-a53-pmu"
+	"arm,cortex-a72-pmu"
+	"arm,cortex-a57-pmu"
+	"arm,cortex-a53-pmu"
 	"arm,cortex-a17-pmu"
 	"arm,cortex-a15-pmu"
 	"arm,cortex-a12-pmu"

Documentation/devicetree/bindings/arm/psci.txt

@@ -23,17 +23,20 @@ Main node required properties:
 
  - compatible    : should contain at least one of:
 
-				 * "arm,psci" : for implementations complying to PSCI versions prior to
-					0.2. For these cases function IDs must be provided.
-
-				 * "arm,psci-0.2" : for implementations complying to PSCI 0.2. Function
-					IDs are not required and should be ignored by an OS with PSCI 0.2
-					support, but are permitted to be present for compatibility with
-					existing software when "arm,psci" is later in the compatible list.
-
-				* "arm,psci-1.0" : for implementations complying to PSCI 1.0. PSCI 1.0 is
-					backward compatible with PSCI 0.2 with minor specification updates,
-					as defined in the PSCI specification[2].
+     * "arm,psci"     : For implementations complying to PSCI versions prior
+			to 0.2.
+			For these cases function IDs must be provided.
+
+     * "arm,psci-0.2" : For implementations complying to PSCI 0.2.
+			Function IDs are not required and should be ignored by
+			an OS with PSCI 0.2 support, but are permitted to be
+			present for compatibility with existing software when
+			"arm,psci" is later in the compatible list.
+
+     * "arm,psci-1.0" : For implementations complying to PSCI 1.0.
+			PSCI 1.0 is backward compatible with PSCI 0.2 with
+			minor specification updates, as defined in the PSCI
+			specification[2].
 
  - method        : The method of calling the PSCI firmware. Permitted
                    values are:

Documentation/devicetree/bindings/arm/rockchip.txt

@@ -1,6 +1,10 @@
 Rockchip platforms device tree bindings
 ---------------------------------------
 
+- Kylin RK3036 board:
+    Required root node properties:
+      - compatible = "rockchip,kylin-rk3036", "rockchip,rk3036";
+
 - MarsBoard RK3066 board:
     Required root node properties:
       - compatible = "haoyu,marsboard-rk3066", "rockchip,rk3066a";
@@ -35,6 +39,11 @@ Rockchip platforms device tree bindings
     Required root node properties:
       - compatible = "netxeon,r89", "rockchip,rk3288";
 
+- Google Brain (dev-board):
+    Required root node properties:
+      - compatible = "google,veyron-brain-rev0", "google,veyron-brain",
+		     "google,veyron", "rockchip,rk3288";
+
 - Google Jaq (Haier Chromebook 11 and more):
     Required root node properties:
       - compatible = "google,veyron-jaq-rev5", "google,veyron-jaq-rev4",
@@ -49,6 +58,15 @@ Rockchip platforms device tree bindings
 		     "google,veyron-jerry-rev3", "google,veyron-jerry",
 		     "google,veyron", "rockchip,rk3288";
 
+- Google Mickey (Asus Chromebit CS10):
+    Required root node properties:
+      - compatible = "google,veyron-mickey-rev8", "google,veyron-mickey-rev7",
+		     "google,veyron-mickey-rev6", "google,veyron-mickey-rev5",
+		     "google,veyron-mickey-rev4", "google,veyron-mickey-rev3",
+		     "google,veyron-mickey-rev2", "google,veyron-mickey-rev1",
+		     "google,veyron-mickey-rev0", "google,veyron-mickey",
+		     "google,veyron", "rockchip,rk3288";
+
 - Google Minnie (Asus Chromebook Flip C100P):
     Required root node properties:
       - compatible = "google,veyron-minnie-rev4", "google,veyron-minnie-rev3",
@@ -69,6 +87,14 @@ Rockchip platforms device tree bindings
 		     "google,veyron-speedy-rev3", "google,veyron-speedy-rev2",
 		     "google,veyron-speedy", "google,veyron", "rockchip,rk3288";
 
+- Rockchip RK3368 evb:
+    Required root node properties:
+      - compatible = "rockchip,rk3368-evb-act8846", "rockchip,rk3368";
+
 - Rockchip R88 board:
     Required root node properties:
       - compatible = "rockchip,r88", "rockchip,rk3368";
+
+- Rockchip RK3228 Evaluation board:
+    Required root node properties:
+      - compatible = "rockchip,rk3228-evb", "rockchip,rk3228";

Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt

@@ -47,6 +47,9 @@ Required properties:
 
 - samsung,syscon-phandle Contains the PMU system controller node
 			(To access the ADC_PHY register on Exynos5250/5420/5800/3250)
+Optional properties:
+- has-touchscreen:	If present, indicates that a touchscreen is
+			connected an usable.
 
 Note: child nodes can be added for auto probing from device tree.
 

Documentation/devicetree/bindings/arm/scu.txt

@@ -10,10 +10,13 @@ References:
   Revision r2p0
 - Cortex-A5: see DDI0434B Cortex-A5 MPCore Technical Reference Manual
   Revision r0p1
+- ARM11 MPCore: see DDI0360F ARM 11 MPCore Processor Technical Reference
+  Manial Revision r2p0
 
 - compatible : Should be:
 	"arm,cortex-a9-scu"
 	"arm,cortex-a5-scu"
+	"arm,arm11mp-scu"
 
 - reg : Specify the base address and the size of the SCU register window.
 

Documentation/devicetree/bindings/arm/secure.txt

@@ -0,0 +1,53 @@
+* ARM Secure world bindings
+
+ARM CPUs with TrustZone support have two distinct address spaces,
+"Normal" and "Secure". Most devicetree consumers (including the Linux
+kernel) are not TrustZone aware and run entirely in either the Normal
+world or the Secure world. However some devicetree consumers are
+TrustZone aware and need to be able to determine whether devices are
+visible only in the Secure address space, only in the Normal address
+space, or visible in both. (One example of that situation would be a
+virtual machine which boots Secure firmware and wants to tell the
+firmware about the layout of the machine via devicetree.)
+
+The general principle of the naming scheme for Secure world bindings
+is that any property that needs a different value in the Secure world
+can be supported by prefixing the property name with "secure-". So for
+instance "secure-foo" would override "foo". For property names with
+a vendor prefix, the Secure variant of "vendor,foo" would be
+"vendor,secure-foo". If there is no "secure-" property then the Secure
+world value is the same as specified for the Normal world by the
+non-prefixed property. However, only the properties listed below may
+validly have "secure-" versions; this list will be enlarged on a
+case-by-case basis.
+
+Defining the bindings in this way means that a device tree which has
+been annotated to indicate the presence of Secure-only devices can
+still be processed unmodified by existing Non-secure software (and in
+particular by the kernel).
+
+Note that it is still valid for bindings intended for purely Secure
+world consumers (like kernels that run entirely in Secure) to simply
+describe the view of Secure world using the standard bindings. These
+secure- bindings only need to be used where both the Secure and Normal
+world views need to be described in a single device tree.
+
+Valid Secure world properties:
+
+- secure-status : specifies whether the device is present and usable
+  in the secure world. The combination of this with "status" allows
+  the various possible combinations of device visibility to be
+  specified. If "secure-status" is not specified it defaults to the
+  same value as "status"; if "status" is not specified either then
+  both default to "okay". This means the following combinations are
+  possible:
+
+   /* Neither specified: default to visible in both S and NS */
+   secure-status = "okay";                          /* visible in both */
+   status = "okay";                                 /* visible in both */
+   status = "okay"; secure-status = "okay";         /* visible in both */
+   secure-status = "disabled";                      /* NS-only */
+   status = "okay"; secure-status = "disabled";     /* NS-only */
+   status = "disabled"; secure-status = "okay";     /* S-only */
+   status = "disabled";                             /* disabled in both */
+   status = "disabled"; secure-status = "disabled"; /* disabled in both */

Documentation/devicetree/bindings/arm/shmobile.txt

@@ -27,6 +27,8 @@ SoCs:
     compatible = "renesas,r8a7793"
   - R-Car E2 (R8A77940)
     compatible = "renesas,r8a7794"
+  - R-Car H3 (R8A77950)
+    compatible = "renesas,r8a7795"
 
 
 Boards:
@@ -57,5 +59,7 @@ Boards:
     compatible = "renesas,marzen", "renesas,r8a7779"
   - Porter (M2-LCDP)
     compatible = "renesas,porter", "renesas,r8a7791"
+  - Salvator-X (RTP0RC7795SIPB0010S)
+    compatible = "renesas,salvator-x", "renesas,r8a7795";
   - SILK (RTP0RC7794LCB00011S)
     compatible = "renesas,silk", "renesas,r8a7794"

Documentation/devicetree/bindings/arm/technologic.txt

@@ -0,0 +1,6 @@
+Technologic Systems Platforms Device Tree Bindings
+--------------------------------------------------
+
+TS-4800 board
+Required root node properties:
+	- compatible = "technologic,imx51-ts4800", "fsl,imx51";

Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt

@@ -4,7 +4,9 @@ SATA nodes are defined to describe on-chip Serial ATA controllers.
 Each SATA controller should have its own node.
 
 Required properties:
-- compatible         : compatible list, may contain "brcm,bcm7445-ahci" and/or
+- compatible         : should be one or more of
+                       "brcm,bcm7425-ahci"
+                       "brcm,bcm7445-ahci"
                        "brcm,sata3-ahci"
 - reg                : register mappings for AHCI and SATA_TOP_CTRL
 - reg-names          : "ahci" and "top-ctrl"

Documentation/devicetree/bindings/ata/sata_rcar.txt

@@ -8,6 +8,7 @@ Required properties:
 			  - "renesas,sata-r8a7790" for R-Car H2 other than ES1
 			  - "renesas,sata-r8a7791" for R-Car M2-W
 			  - "renesas,sata-r8a7793" for R-Car M2-N
+			  - "renesas,sata-r8a7795" for R-Car H3
 - reg			: address and length of the SATA registers;
 - interrupts		: must consist of one interrupt specifier.
 - clocks		: must contain a reference to the functional clock.

Documentation/devicetree/bindings/bus/uniphier-system-bus.txt

@@ -0,0 +1,66 @@
+UniPhier System Bus
+
+The UniPhier System Bus is an external bus that connects on-board devices to
+the UniPhier SoC.  It is a simple (semi-)parallel bus with address, data, and
+some control signals.  It supports up to 8 banks (chip selects).
+
+Before any access to the bus, the bus controller must be configured; the bus
+controller registers provide the control for the translation from the offset
+within each bank to the CPU-viewed address.  The needed setup includes the base
+address, the size of each bank.  Optionally, some timing parameters can be
+optimized for faster bus access.
+
+Required properties:
+- compatible: should be "socionext,uniphier-system-bus".
+- reg: offset and length of the register set for the bus controller device.
+- #address-cells: should be 2.  The first cell is the bank number (chip select).
+  The second cell is the address offset within the bank.
+- #size-cells: should be 1.
+- ranges: should provide a proper address translation from the System Bus to
+  the parent bus.
+
+Note:
+The address region(s) that can be assigned for the System Bus is implementation
+defined.  Some SoCs can use 0x00000000-0x0fffffff and 0x40000000-0x4fffffff,
+while other SoCs can only use 0x40000000-0x4fffffff.  There might be additional
+limitations depending on SoCs and the boot mode.  The address translation is
+arbitrary as long as the banks are assigned in the supported address space with
+the required alignment and they do not overlap one another.
+For example, it is possible to map:
+  bank 0 to 0x42000000-0x43ffffff, bank 5 to 0x46000000-0x46ffffff
+It is also possible to map:
+  bank 0 to 0x48000000-0x49ffffff, bank 5 to 0x44000000-0x44ffffff
+There is no reason to stick to a particular translation mapping, but the
+"ranges" property should provide a "reasonable" default that is known to work.
+The software should initialize the bus controller according to it.
+
+Example:
+
+	system-bus {
+		compatible = "socionext,uniphier-system-bus";
+		reg = <0x58c00000 0x400>;
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <1 0x00000000 0x42000000 0x02000000
+			  5 0x00000000 0x46000000 0x01000000>;
+
+		ethernet@1,01f00000 {
+			compatible = "smsc,lan9115";
+			reg = <1 0x01f00000 0x1000>;
+			interrupts = <0 48 4>
+			phy-mode = "mii";
+		};
+
+		uart@5,00200000 {
+			compatible = "ns16550a";
+			reg = <5 0x00200000 0x20>;
+			interrupts = <0 49 4>
+			clock-frequency = <12288000>;
+		};
+	};
+
+In this example,
+ - the Ethernet device is connected at the offset 0x01f00000 of CS1 and
+   mapped to 0x43f00000 of the parent bus.
+ - the UART device is connected at the offset 0x00200000 of CS5 and
+   mapped to 0x46200000 of the parent bus.

Documentation/devicetree/bindings/clock/arm-syscon-icst.txt

@@ -0,0 +1,40 @@
+ARM System Controller ICST clocks
+
+The ICS525 and ICS307 oscillators are produced by Integrated Devices
+Technology (IDT). ARM integrated these oscillators deeply into their
+reference designs by adding special control registers that manage such
+oscillators to their system controllers.
+
+The ARM system controller contains logic to serialize and initialize
+an ICST clock request after a write to the 32 bit register at an offset
+into the system controller. Furthermore, to even be able to alter one of
+these frequencies, the system controller must first be unlocked by
+writing a special token to another offset in the system controller.
+
+The ICST oscillator must be provided inside a system controller node.
+
+Required properties:
+- lock-offset: the offset address into the system controller where the
+  unlocking register is located
+- vco-offset: the offset address into the system controller where the
+  ICST control register is located (even 32 bit address)
+- compatible: must be one of "arm,syscon-icst525" or "arm,syscon-icst307"
+- #clock-cells: must be <0>
+- clocks: parent clock, since the ICST needs a parent clock to derive its
+  frequency from, this attribute is compulsory.
+
+Example:
+
+syscon: syscon@10000000 {
+	compatible = "syscon";
+	reg = <0x10000000 0x1000>;
+
+	oscclk0: osc0@0c {
+		compatible = "arm,syscon-icst307";
+		#clock-cells = <0>;
+		lock-offset = <0x20>;
+		vco-offset = <0x0c>;
+		clocks = <&xtal24mhz>;
+	};
+	(...)
+};

Documentation/devicetree/bindings/clock/brcm,bcm2835-aux-clock.txt

@@ -0,0 +1,31 @@
+Broadcom BCM2835 auxiliary peripheral support
+
+This binding uses the common clock binding:
+    Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+The auxiliary peripherals (UART, SPI1, and SPI2) have a small register
+area controlling clock gating to the peripherals, and providing an IRQ
+status register.
+
+Required properties:
+- compatible:	Should be "brcm,bcm2835-aux"
+- #clock-cells:	Should be <1>. The permitted clock-specifier values can be
+		  found in include/dt-bindings/clock/bcm2835-aux.h
+- reg:		Specifies base physical address and size of the registers
+- clocks:	The parent clock phandle
+
+Example:
+
+	clocks: cprman@7e101000 {
+		compatible = "brcm,bcm2835-cprman";
+		#clock-cells = <1>;
+		reg = <0x7e101000 0x2000>;
+		clocks = <&clk_osc>;
+	};
+
+	aux: aux@0x7e215004 {
+		compatible = "brcm,bcm2835-aux";
+		#clock-cells = <1>;
+		reg = <0x7e215000 0x8>;
+		clocks = <&clocks BCM2835_CLOCK_VPU>;
+	};

Documentation/devicetree/bindings/clock/brcm,iproc-clocks.txt

@@ -208,3 +208,8 @@ These clock IDs are defined in:
     ch3_unused	lcpll_ports	4	BCM_NS2_LCPLL_PORTS_CH3_UNUSED
     ch4_unused	lcpll_ports	5	BCM_NS2_LCPLL_PORTS_CH4_UNUSED
     ch5_unused	lcpll_ports	6	BCM_NS2_LCPLL_PORTS_CH5_UNUSED
+
+BCM63138
+--------
+PLL and leaf clock compatible strings for BCM63138 are:
+    "brcm,bcm63138-armpll"

Documentation/devicetree/bindings/clock/cs2000-cp.txt

@@ -0,0 +1,22 @@
+CIRRUS LOGIC Fractional-N Clock Synthesizer & Clock Multiplier
+
+Required properties:
+
+- compatible:		"cirrus,cs2000-cp"
+- reg:			The chip select number on the I2C bus
+- clocks:		common clock binding for CLK_IN, XTI/REF_CLK
+- clock-names:		CLK_IN : clk_in, XTI/REF_CLK : ref_clk
+- #clock-cells:		must be <0>
+
+Example:
+
+&i2c2 {
+	...
+	cs2000: clk_multiplier@4f {
+		#clock-cells = <0>;
+		compatible = "cirrus,cs2000-cp";
+		reg = <0x4f>;
+		clocks = <&rcar_sound 0>, <&x12_clk>;
+		clock-names = "clk_in", "ref_clk";
+	};
+};

Documentation/devicetree/bindings/clock/dove-divider-clock.txt

@@ -0,0 +1,28 @@
+PLL divider based Dove clocks
+
+Marvell Dove has a 2GHz PLL, which feeds into a set of dividers to provide
+high speed clocks for a number of peripherals.  These dividers are part of
+the PMU, and thus this node should be a child of the PMU node.
+
+The following clocks are provided:
+
+ID	Clock
+-------------
+0	AXI bus clock
+1	GPU clock
+2	VMeta clock
+3	LCD clock
+
+Required properties:
+- compatible : shall be "marvell,dove-divider-clock"
+- reg : shall be the register address of the Core PLL and Clock Divider
+   Control 0 register.  This will cover that register, as well as the
+   Core PLL and Clock Divider Control 1 register.  Thus, it will have
+   a size of 8.
+- #clock-cells : from common clock binding; shall be set to 1
+
+divider_clk: core-clock@0064 {
+	compatible = "marvell,dove-divider-clock";
+	reg = <0x0064 0x8>;
+	#clock-cells = <1>;
+};

Documentation/devicetree/bindings/clock/nvidia,tegra210-car.txt

@@ -0,0 +1,56 @@
+NVIDIA Tegra210 Clock And Reset Controller
+
+This binding uses the common clock binding:
+Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+The CAR (Clock And Reset) Controller on Tegra is the HW module responsible
+for muxing and gating Tegra's clocks, and setting their rates.
+
+Required properties :
+- compatible : Should be "nvidia,tegra210-car"
+- reg : Should contain CAR registers location and length
+- clocks : Should contain phandle and clock specifiers for two clocks:
+  the 32 KHz "32k_in".
+- #clock-cells : Should be 1.
+  In clock consumers, this cell represents the clock ID exposed by the
+  CAR. The assignments may be found in header file
+  <dt-bindings/clock/tegra210-car.h>.
+- #reset-cells : Should be 1.
+  In clock consumers, this cell represents the bit number in the CAR's
+  array of CLK_RST_CONTROLLER_RST_DEVICES_* registers.
+
+Example SoC include file:
+
+/ {
+	tegra_car: clock {
+		compatible = "nvidia,tegra210-car";
+		reg = <0x60006000 0x1000>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+	usb@c5004000 {
+		clocks = <&tegra_car TEGRA210_CLK_USB2>;
+	};
+};
+
+Example board file:
+
+/ {
+	clocks {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		clk_32k: clock@1 {
+			compatible = "fixed-clock";
+			reg = <1>;
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+		};
+	};
+
+	&tegra_car {
+		clocks = <&clk_32k>;
+	};
+};

Documentation/devicetree/bindings/clock/nxp,lpc3220-clk.txt

@@ -0,0 +1,30 @@
+NXP LPC32xx Clock Controller
+
+Required properties:
+- compatible: should be "nxp,lpc3220-clk"
+- reg:  should contain clock controller registers location and length
+- #clock-cells: must be 1, the cell holds id of a clock provided by the
+  clock controller
+- clocks: phandles of external oscillators, the list must contain one
+  32768 Hz oscillator and may have one optional high frequency oscillator
+- clock-names: list of external oscillator clock names, must contain
+  "xtal_32k" and may have optional "xtal"
+
+Examples:
+
+	/* System Control Block */
+	scb {
+		compatible = "simple-bus";
+		ranges = <0x0 0x040004000 0x00001000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		clk: clock-controller@0 {
+			compatible = "nxp,lpc3220-clk";
+			reg = <0x00 0x114>;
+			#clock-cells = <1>;
+
+			clocks = <&xtal_32k>, <&xtal>;
+			clock-names = "xtal_32k", "xtal";
+		};
+	};