Merge branch 'linus' into x86/urgent

Merge reason: We want to queue up a dependent fix.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/ABI/testing/sysfs-ata

@@ -0,0 +1,99 @@
+What:		/sys/class/ata_...
+Date:		August 2008
+Contact:	Gwendal Grignou<gwendal@google.com>
+Description:
+
+Provide a place in sysfs for storing the ATA topology of the system.  This allows
+retrieving various information about ATA objects.
+
+Files under /sys/class/ata_port
+-------------------------------
+
+	For each port, a directory ataX is created where X is the ata_port_id of
+	the port. The device parent is the ata host device.
+
+idle_irq (read)
+
+	Number of IRQ received by the port while idle [some ata HBA only].
+
+nr_pmp_links (read)
+
+	If a SATA Port Multiplier (PM) is connected, number of link behind it.
+
+Files under /sys/class/ata_link
+-------------------------------
+
+	Behind each port, there is a ata_link. If there is a SATA PM in the
+	topology, 15 ata_link objects are created.
+
+	If a link is behind a port, the directory name is linkX, where X is
+	ata_port_id of the port.
+	If a link is behind a PM, its name is linkX.Y where X is ata_port_id
+	of the parent port and Y the PM port.
+
+hw_sata_spd_limit
+
+	Maximum speed supported by the connected SATA device.
+
+sata_spd_limit
+
+	Maximum speed imposed by libata.
+
+sata_spd
+
+	Current speed of the link [1.5, 3Gps,...].
+
+Files under /sys/class/ata_device
+---------------------------------
+
+	Behind each link, up to two ata device are created.
+	The name of the directory is devX[.Y].Z where:
+	- X is ata_port_id of the port where the device is connected,
+	- Y the port of the PM if any, and
+	- Z the device id: for PATA, there is usually 2 devices [0,1],
+	only 1 for SATA.
+
+class
+	Device class. Can be "ata" for disk, "atapi" for packet device,
+	"pmp" for PM, or "none" if no device was found behind the link.
+
+dma_mode
+
+	Transfer modes supported by the device when in DMA mode.
+	Mostly used by PATA device.
+
+pio_mode
+
+	Transfer modes supported by the device when in PIO mode.
+	Mostly used by PATA device.
+
+xfer_mode
+
+	Current transfer mode.
+
+id
+
+	Cached result of IDENTIFY command, as described in ATA8 7.16 and 7.17.
+	Only valid if the device is not a PM.
+
+gscr
+
+	Cached result of the dump of PM GSCR register.
+	Valid registers are:
+	0: 	SATA_PMP_GSCR_PROD_ID,
+	1: 	SATA_PMP_GSCR_REV,
+	2: 	SATA_PMP_GSCR_PORT_INFO,
+	32:	SATA_PMP_GSCR_ERROR,
+	33:	SATA_PMP_GSCR_ERROR_EN,
+	64:	SATA_PMP_GSCR_FEAT,
+	96:	SATA_PMP_GSCR_FEAT_EN,
+	130:	SATA_PMP_GSCR_SII_GPIO
+	Only valid if the device is a PM.
+
+spdn_cnt
+
+	Number of time libata decided to lower the speed of link due to errors.
+
+ering
+
+	Formatted output of the error ring of the device.

Documentation/ABI/testing/sysfs-devices-power

@@ -77,3 +77,91 @@ Description:
 		devices this attribute is set to "enabled" by bus type code or
 		device drivers and in that cases it should be safe to leave the
 		default value.
+
+What:		/sys/devices/.../power/wakeup_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_count attribute contains the number
+		of signaled wakeup events associated with the device.  This
+		attribute is read-only.  If the device is not enabled to wake up
+		the system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_active_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_active_count attribute contains the
+		number of times the processing of wakeup events associated with
+		the device was completed (at the kernel level).  This attribute
+		is read-only.  If the device is not enabled to wake up the
+		system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_hit_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_hit_count attribute contains the
+		number of times the processing of a wakeup event associated with
+		the device might prevent the system from entering a sleep state.
+		This attribute is read-only.  If the device is not enabled to
+		wake up the system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_active
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_active attribute contains either 1,
+		or 0, depending on whether or not a wakeup event associated with
+		the device is being processed (1).  This attribute is read-only.
+		If the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_total_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_total_time_ms attribute contains
+		the total time of processing wakeup events associated with the
+		device, in milliseconds.  This attribute is read-only.  If the
+		device is not enabled to wake up the system from sleep states,
+		this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_max_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_max_time_ms attribute contains
+		the maximum time of processing a single wakeup event associated
+		with the device, in milliseconds.  This attribute is read-only.
+		If the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_last_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_last_time_ms attribute contains
+		the value of the monotonic clock corresponding to the time of
+		signaling the last wakeup event associated with the device, in
+		milliseconds.  This attribute is read-only.  If the device is
+		not enabled to wake up the system from sleep states, this
+		attribute is empty.
+
+What:		/sys/devices/.../power/autosuspend_delay_ms
+Date:		September 2010
+Contact:	Alan Stern <stern@rowland.harvard.edu>
+Description:
+		The /sys/devices/.../power/autosuspend_delay_ms attribute
+		contains the autosuspend delay value (in milliseconds).  Some
+		drivers do not want their device to suspend as soon as it
+		becomes idle at run time; they want the device to remain
+		inactive for a certain minimum period of time first.  That
+		period is called the autosuspend delay.  Negative values will
+		prevent the device from being suspended at run time (similar
+		to writing "on" to the power/control attribute).  Values >=
+		1000 will cause the autosuspend timer expiration to be rounded
+		up to the nearest second.
+
+		Not all drivers support this attribute.  If it isn't supported,
+		attempts to read or write it will yield I/O errors.

Documentation/ABI/testing/sysfs-driver-hid-roccat-pyra

@@ -0,0 +1,98 @@
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_cpi
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	It is possible to switch the cpi setting of the mouse with the
+		press of a button.
+		When read, this file returns the raw number of the actual cpi
+		setting reported by the mouse. This number has to be further
+		processed to receive the real dpi value.
+
+		VALUE DPI
+		1     400
+		2     800
+		4     1600
+
+		This file is readonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/actual_profile
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	When read, this file returns the number of the actual profile in
+		range 0-4.
+		This file is readonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/firmware_version
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	When read, this file returns the raw integer version number of the
+		firmware reported by the mouse. Using the integer value eases
+		further usage in other programs. To receive the real version
+		number the decimal point has to be shifted 2 positions to the
+		left. E.g. a returned value of 138 means 1.38
+		This file is readonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile_settings
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	The mouse can store 5 profiles which can be switched by the
+		press of a button. A profile is split in settings and buttons.
+		profile_settings holds informations like resolution, sensitivity
+		and light effects.
+		When written, this file lets one write the respective profile
+		settings back to the mouse. The data has to be 13 bytes long.
+		The mouse will reject invalid data.
+		Which profile to write is determined by the profile number
+		contained in the data.
+		This file is writeonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5]_settings
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	The mouse can store 5 profiles which can be switched by the
+		press of a button. A profile is split in settings and buttons.
+		profile_settings holds informations like resolution, sensitivity
+		and light effects.
+		When read, these files return the respective profile settings.
+		The returned data is 13 bytes in size.
+		This file is readonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile_buttons
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	The mouse can store 5 profiles which can be switched by the
+		press of a button. A profile is split in settings and buttons.
+		profile_buttons holds informations about button layout.
+		When written, this file lets one write the respective profile
+		buttons back to the mouse. The data has to be 19 bytes long.
+		The mouse will reject invalid data.
+		Which profile to write is determined by the profile number
+		contained in the data.
+		This file is writeonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/profile[1-5]_buttons
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	The mouse can store 5 profiles which can be switched by the
+		press of a button. A profile is split in settings and buttons.
+		profile_buttons holds informations about button layout.
+		When read, these files return the respective profile buttons.
+		The returned data is 19 bytes in size.
+		This file is readonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/startup_profile
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	The integer value of this attribute ranges from 0-4.
+                When read, this attribute returns the number of the profile
+                that's active when the mouse is powered on.
+		This file is readonly.
+
+What:		/sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/settings
+Date:		August 2010
+Contact:	Stefan Achatz <erazor_de@users.sourceforge.net>
+Description:	When read, this file returns the settings stored in the mouse.
+		The size of the data is 3 bytes and holds information on the
+		startup_profile.
+		When written, this file lets write settings back to the mouse.
+		The data has to be 3 bytes long. The mouse will reject invalid
+		data.

Documentation/ABI/testing/sysfs-module

@@ -0,0 +1,12 @@
+What:		/sys/module/pch_phub/drivers/.../pch_mac
+Date:		August 2010
+KernelVersion:	2.6.35
+Contact:	masa-korg@dsn.okisemi.com
+Description:	Write/read GbE MAC address.
+
+What:		/sys/module/pch_phub/drivers/.../pch_firmware
+Date:		August 2010
+KernelVersion:	2.6.35
+Contact:	masa-korg@dsn.okisemi.com
+Description:	Write/read Option ROM data.
+

Documentation/ABI/testing/sysfs-power

@@ -99,9 +99,38 @@ Description:
 
 		dmesg -s 1000000 | grep 'hash matches'
 
+		If you do not get any matches (or they appear to be false
+		positives), it is possible that the last PM event point
+		referred to a device created by a loadable kernel module.  In
+		this case cat /sys/power/pm_trace_dev_match (see below) after
+		your system is started up and the kernel modules are loaded.
+
 		CAUTION: Using it will cause your machine's real-time (CMOS)
 		clock to be set to a random invalid time after a resume.
 
+What;		/sys/power/pm_trace_dev_match
+Date:		October 2010
+Contact:	James Hogan <james@albanarts.com>
+Description:
+		The /sys/power/pm_trace_dev_match file contains the name of the
+		device associated with the last PM event point saved in the RTC
+		across reboots when pm_trace has been used.  More precisely it
+		contains the list of current devices (including those
+		registered by loadable kernel modules since boot) which match
+		the device hash in the RTC at boot, with a newline after each
+		one.
+
+		The advantage of this file over the hash matches printed to the
+		kernel log (see /sys/power/pm_trace), is that it includes
+		devices created after boot by loadable kernel modules.
+
+		Due to the small hash size necessary to fit in the RTC, it is
+		possible that more than one device matches the hash, in which
+		case further investigation is required to determine which
+		device is causing the problem.  Note that genuine RTC clock
+		values (such as when pm_trace has not been used), can still
+		match a device and output it's name here.
+
 What:		/sys/power/pm_async
 Date:		January 2009
 Contact:	Rafael J. Wysocki <rjw@sisk.pl>

Documentation/DocBook/80211.tmpl

@@ -0,0 +1,495 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE set PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+<set>
+  <setinfo>
+    <title>The 802.11 subsystems &ndash; for kernel developers</title>
+    <subtitle>
+      Explaining wireless 802.11 networking in the Linux kernel
+    </subtitle>
+
+    <copyright>
+      <year>2007-2009</year>
+      <holder>Johannes Berg</holder>
+    </copyright>
+
+    <authorgroup>
+      <author>
+        <firstname>Johannes</firstname>
+        <surname>Berg</surname>
+        <affiliation>
+          <address><email>johannes@sipsolutions.net</email></address>
+        </affiliation>
+      </author>
+    </authorgroup>
+
+    <legalnotice>
+      <para>
+        This documentation is free software; you can redistribute
+        it and/or modify it under the terms of the GNU General Public
+        License version 2 as published by the Free Software Foundation.
+      </para>
+      <para>
+        This documentation is distributed in the hope that it will be
+        useful, but WITHOUT ANY WARRANTY; without even the implied
+        warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+        See the GNU General Public License for more details.
+      </para>
+      <para>
+        You should have received a copy of the GNU General Public
+        License along with this documentation; if not, write to the Free
+        Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+        MA 02111-1307 USA
+      </para>
+      <para>
+        For more details see the file COPYING in the source
+        distribution of Linux.
+      </para>
+    </legalnotice>
+
+    <abstract>
+      <para>
+        These books attempt to give a description of the
+        various subsystems that play a role in 802.11 wireless
+        networking in Linux. Since these books are for kernel
+        developers they attempts to document the structures
+        and functions used in the kernel as well as giving a
+        higher-level overview.
+      </para>
+      <para>
+	The reader is expected to be familiar with the 802.11
+	standard as published by the IEEE in 802.11-2007 (or
+	possibly later versions). References to this standard
+	will be given as "802.11-2007 8.1.5".
+      </para>
+    </abstract>
+  </setinfo>
+  <book id="cfg80211-developers-guide">
+    <bookinfo>
+      <title>The cfg80211 subsystem</title>
+
+      <abstract>
+!Pinclude/net/cfg80211.h Introduction
+      </abstract>
+    </bookinfo>
+      <chapter>
+      <title>Device registration</title>
+!Pinclude/net/cfg80211.h Device registration
+!Finclude/net/cfg80211.h ieee80211_band
+!Finclude/net/cfg80211.h ieee80211_channel_flags
+!Finclude/net/cfg80211.h ieee80211_channel
+!Finclude/net/cfg80211.h ieee80211_rate_flags
+!Finclude/net/cfg80211.h ieee80211_rate
+!Finclude/net/cfg80211.h ieee80211_sta_ht_cap
+!Finclude/net/cfg80211.h ieee80211_supported_band
+!Finclude/net/cfg80211.h cfg80211_signal_type
+!Finclude/net/cfg80211.h wiphy_params_flags
+!Finclude/net/cfg80211.h wiphy_flags
+!Finclude/net/cfg80211.h wiphy
+!Finclude/net/cfg80211.h wireless_dev
+!Finclude/net/cfg80211.h wiphy_new
+!Finclude/net/cfg80211.h wiphy_register
+!Finclude/net/cfg80211.h wiphy_unregister
+!Finclude/net/cfg80211.h wiphy_free
+
+!Finclude/net/cfg80211.h wiphy_name
+!Finclude/net/cfg80211.h wiphy_dev
+!Finclude/net/cfg80211.h wiphy_priv
+!Finclude/net/cfg80211.h priv_to_wiphy
+!Finclude/net/cfg80211.h set_wiphy_dev
+!Finclude/net/cfg80211.h wdev_priv
+      </chapter>
+      <chapter>
+      <title>Actions and configuration</title>
+!Pinclude/net/cfg80211.h Actions and configuration
+!Finclude/net/cfg80211.h cfg80211_ops
+!Finclude/net/cfg80211.h vif_params
+!Finclude/net/cfg80211.h key_params
+!Finclude/net/cfg80211.h survey_info_flags
+!Finclude/net/cfg80211.h survey_info
+!Finclude/net/cfg80211.h beacon_parameters
+!Finclude/net/cfg80211.h plink_actions
+!Finclude/net/cfg80211.h station_parameters
+!Finclude/net/cfg80211.h station_info_flags
+!Finclude/net/cfg80211.h rate_info_flags
+!Finclude/net/cfg80211.h rate_info
+!Finclude/net/cfg80211.h station_info
+!Finclude/net/cfg80211.h monitor_flags
+!Finclude/net/cfg80211.h mpath_info_flags
+!Finclude/net/cfg80211.h mpath_info
+!Finclude/net/cfg80211.h bss_parameters
+!Finclude/net/cfg80211.h ieee80211_txq_params
+!Finclude/net/cfg80211.h cfg80211_crypto_settings
+!Finclude/net/cfg80211.h cfg80211_auth_request
+!Finclude/net/cfg80211.h cfg80211_assoc_request
+!Finclude/net/cfg80211.h cfg80211_deauth_request
+!Finclude/net/cfg80211.h cfg80211_disassoc_request
+!Finclude/net/cfg80211.h cfg80211_ibss_params
+!Finclude/net/cfg80211.h cfg80211_connect_params
+!Finclude/net/cfg80211.h cfg80211_pmksa
+!Finclude/net/cfg80211.h cfg80211_send_rx_auth
+!Finclude/net/cfg80211.h cfg80211_send_auth_timeout
+!Finclude/net/cfg80211.h __cfg80211_auth_canceled
+!Finclude/net/cfg80211.h cfg80211_send_rx_assoc
+!Finclude/net/cfg80211.h cfg80211_send_assoc_timeout
+!Finclude/net/cfg80211.h cfg80211_send_deauth
+!Finclude/net/cfg80211.h __cfg80211_send_deauth
+!Finclude/net/cfg80211.h cfg80211_send_disassoc
+!Finclude/net/cfg80211.h __cfg80211_send_disassoc
+!Finclude/net/cfg80211.h cfg80211_ibss_joined
+!Finclude/net/cfg80211.h cfg80211_connect_result
+!Finclude/net/cfg80211.h cfg80211_roamed
+!Finclude/net/cfg80211.h cfg80211_disconnected
+!Finclude/net/cfg80211.h cfg80211_ready_on_channel
+!Finclude/net/cfg80211.h cfg80211_remain_on_channel_expired
+!Finclude/net/cfg80211.h cfg80211_new_sta
+!Finclude/net/cfg80211.h cfg80211_rx_mgmt
+!Finclude/net/cfg80211.h cfg80211_mgmt_tx_status
+!Finclude/net/cfg80211.h cfg80211_cqm_rssi_notify
+!Finclude/net/cfg80211.h cfg80211_michael_mic_failure
+      </chapter>
+      <chapter>
+      <title>Scanning and BSS list handling</title>
+!Pinclude/net/cfg80211.h Scanning and BSS list handling
+!Finclude/net/cfg80211.h cfg80211_ssid
+!Finclude/net/cfg80211.h cfg80211_scan_request
+!Finclude/net/cfg80211.h cfg80211_scan_done
+!Finclude/net/cfg80211.h cfg80211_bss
+!Finclude/net/cfg80211.h cfg80211_inform_bss_frame
+!Finclude/net/cfg80211.h cfg80211_inform_bss
+!Finclude/net/cfg80211.h cfg80211_unlink_bss
+!Finclude/net/cfg80211.h cfg80211_find_ie
+!Finclude/net/cfg80211.h ieee80211_bss_get_ie
+      </chapter>
+      <chapter>
+      <title>Utility functions</title>
+!Pinclude/net/cfg80211.h Utility functions
+!Finclude/net/cfg80211.h ieee80211_channel_to_frequency
+!Finclude/net/cfg80211.h ieee80211_frequency_to_channel
+!Finclude/net/cfg80211.h ieee80211_get_channel
+!Finclude/net/cfg80211.h ieee80211_get_response_rate
+!Finclude/net/cfg80211.h ieee80211_hdrlen
+!Finclude/net/cfg80211.h ieee80211_get_hdrlen_from_skb
+!Finclude/net/cfg80211.h ieee80211_radiotap_iterator
+      </chapter>
+      <chapter>
+      <title>Data path helpers</title>
+!Pinclude/net/cfg80211.h Data path helpers
+!Finclude/net/cfg80211.h ieee80211_data_to_8023
+!Finclude/net/cfg80211.h ieee80211_data_from_8023
+!Finclude/net/cfg80211.h ieee80211_amsdu_to_8023s
+!Finclude/net/cfg80211.h cfg80211_classify8021d
+      </chapter>
+      <chapter>
+      <title>Regulatory enforcement infrastructure</title>
+!Pinclude/net/cfg80211.h Regulatory enforcement infrastructure
+!Finclude/net/cfg80211.h regulatory_hint
+!Finclude/net/cfg80211.h wiphy_apply_custom_regulatory
+!Finclude/net/cfg80211.h freq_reg_info
+      </chapter>
+      <chapter>
+      <title>RFkill integration</title>
+!Pinclude/net/cfg80211.h RFkill integration
+!Finclude/net/cfg80211.h wiphy_rfkill_set_hw_state
+!Finclude/net/cfg80211.h wiphy_rfkill_start_polling
+!Finclude/net/cfg80211.h wiphy_rfkill_stop_polling
+      </chapter>
+      <chapter>
+      <title>Test mode</title>
+!Pinclude/net/cfg80211.h Test mode
+!Finclude/net/cfg80211.h cfg80211_testmode_alloc_reply_skb
+!Finclude/net/cfg80211.h cfg80211_testmode_reply
+!Finclude/net/cfg80211.h cfg80211_testmode_alloc_event_skb
+!Finclude/net/cfg80211.h cfg80211_testmode_event
+      </chapter>
+  </book>
+  <book id="mac80211-developers-guide">
+    <bookinfo>
+      <title>The mac80211 subsystem</title>
+      <abstract>
+!Pinclude/net/mac80211.h Introduction
+!Pinclude/net/mac80211.h Warning
+      </abstract>
+    </bookinfo>
+
+    <toc></toc>
+
+  <!--
+  Generally, this document shall be ordered by increasing complexity.
+  It is important to note that readers should be able to read only
+  the first few sections to get a working driver and only advanced
+  usage should require reading the full document.
+  -->
+
+    <part>
+      <title>The basic mac80211 driver interface</title>
+      <partintro>
+        <para>
+          You should read and understand the information contained
+          within this part of the book while implementing a driver.
+          In some chapters, advanced usage is noted, that may be
+          skipped at first.
+        </para>
+        <para>
+          This part of the book only covers station and monitor mode
+          functionality, additional information required to implement
+          the other modes is covered in the second part of the book.
+        </para>
+      </partintro>
+
+      <chapter id="basics">
+        <title>Basic hardware handling</title>
+        <para>TBD</para>
+        <para>
+          This chapter shall contain information on getting a hw
+          struct allocated and registered with mac80211.
+        </para>
+        <para>
+          Since it is required to allocate rates/modes before registering
+          a hw struct, this chapter shall also contain information on setting
+          up the rate/mode structs.
+        </para>
+        <para>
+          Additionally, some discussion about the callbacks and
+          the general programming model should be in here, including
+          the definition of ieee80211_ops which will be referred to
+          a lot.
+        </para>
+        <para>
+          Finally, a discussion of hardware capabilities should be done
+          with references to other parts of the book.
+        </para>
+  <!-- intentionally multiple !F lines to get proper order -->
+!Finclude/net/mac80211.h ieee80211_hw
+!Finclude/net/mac80211.h ieee80211_hw_flags
+!Finclude/net/mac80211.h SET_IEEE80211_DEV
+!Finclude/net/mac80211.h SET_IEEE80211_PERM_ADDR
+!Finclude/net/mac80211.h ieee80211_ops
+!Finclude/net/mac80211.h ieee80211_alloc_hw
+!Finclude/net/mac80211.h ieee80211_register_hw
+!Finclude/net/mac80211.h ieee80211_get_tx_led_name
+!Finclude/net/mac80211.h ieee80211_get_rx_led_name
+!Finclude/net/mac80211.h ieee80211_get_assoc_led_name
+!Finclude/net/mac80211.h ieee80211_get_radio_led_name
+!Finclude/net/mac80211.h ieee80211_unregister_hw
+!Finclude/net/mac80211.h ieee80211_free_hw
+      </chapter>
+
+      <chapter id="phy-handling">
+        <title>PHY configuration</title>
+        <para>TBD</para>
+        <para>
+          This chapter should describe PHY handling including
+          start/stop callbacks and the various structures used.
+        </para>
+!Finclude/net/mac80211.h ieee80211_conf
+!Finclude/net/mac80211.h ieee80211_conf_flags
+      </chapter>
+
+      <chapter id="iface-handling">
+        <title>Virtual interfaces</title>
+        <para>TBD</para>
+        <para>
+          This chapter should describe virtual interface basics
+          that are relevant to the driver (VLANs, MGMT etc are not.)
+          It should explain the use of the add_iface/remove_iface
+          callbacks as well as the interface configuration callbacks.
+        </para>
+        <para>Things related to AP mode should be discussed there.</para>
+        <para>
+          Things related to supporting multiple interfaces should be
+          in the appropriate chapter, a BIG FAT note should be here about
+          this though and the recommendation to allow only a single
+          interface in STA mode at first!
+        </para>
+!Finclude/net/mac80211.h ieee80211_vif
+      </chapter>
+
+      <chapter id="rx-tx">
+        <title>Receive and transmit processing</title>
+        <sect1>
+          <title>what should be here</title>
+          <para>TBD</para>
+          <para>
+            This should describe the receive and transmit
+            paths in mac80211/the drivers as well as
+            transmit status handling.
+          </para>
+        </sect1>
+        <sect1>
+          <title>Frame format</title>
+!Pinclude/net/mac80211.h Frame format
+        </sect1>
+        <sect1>
+          <title>Packet alignment</title>
+!Pnet/mac80211/rx.c Packet alignment
+        </sect1>
+        <sect1>
+          <title>Calling into mac80211 from interrupts</title>
+!Pinclude/net/mac80211.h Calling mac80211 from interrupts
+        </sect1>
+        <sect1>
+          <title>functions/definitions</title>
+!Finclude/net/mac80211.h ieee80211_rx_status
+!Finclude/net/mac80211.h mac80211_rx_flags
+!Finclude/net/mac80211.h ieee80211_tx_info
+!Finclude/net/mac80211.h ieee80211_rx
+!Finclude/net/mac80211.h ieee80211_rx_irqsafe
+!Finclude/net/mac80211.h ieee80211_tx_status
+!Finclude/net/mac80211.h ieee80211_tx_status_irqsafe
+!Finclude/net/mac80211.h ieee80211_rts_get
+!Finclude/net/mac80211.h ieee80211_rts_duration
+!Finclude/net/mac80211.h ieee80211_ctstoself_get
+!Finclude/net/mac80211.h ieee80211_ctstoself_duration
+!Finclude/net/mac80211.h ieee80211_generic_frame_duration
+!Finclude/net/mac80211.h ieee80211_wake_queue
+!Finclude/net/mac80211.h ieee80211_stop_queue
+!Finclude/net/mac80211.h ieee80211_wake_queues
+!Finclude/net/mac80211.h ieee80211_stop_queues
+        </sect1>
+      </chapter>
+
+      <chapter id="filters">
+        <title>Frame filtering</title>
+!Pinclude/net/mac80211.h Frame filtering
+!Finclude/net/mac80211.h ieee80211_filter_flags
+      </chapter>
+    </part>
+
+    <part id="advanced">
+      <title>Advanced driver interface</title>
+      <partintro>
+        <para>
+         Information contained within this part of the book is
+         of interest only for advanced interaction of mac80211
+         with drivers to exploit more hardware capabilities and
+         improve performance.
+        </para>
+      </partintro>
+
+      <chapter id="hardware-crypto-offload">
+        <title>Hardware crypto acceleration</title>
+!Pinclude/net/mac80211.h Hardware crypto acceleration
+  <!-- intentionally multiple !F lines to get proper order -->
+!Finclude/net/mac80211.h set_key_cmd
+!Finclude/net/mac80211.h ieee80211_key_conf
+!Finclude/net/mac80211.h ieee80211_key_flags
+      </chapter>
+
+      <chapter id="powersave">
+        <title>Powersave support</title>
+!Pinclude/net/mac80211.h Powersave support
+      </chapter>
+
+      <chapter id="beacon-filter">
+        <title>Beacon filter support</title>
+!Pinclude/net/mac80211.h Beacon filter support
+!Finclude/net/mac80211.h ieee80211_beacon_loss
+      </chapter>
+
+      <chapter id="qos">
+        <title>Multiple queues and QoS support</title>
+        <para>TBD</para>
+!Finclude/net/mac80211.h ieee80211_tx_queue_params
+      </chapter>
+
+      <chapter id="AP">
+        <title>Access point mode support</title>
+        <para>TBD</para>
+        <para>Some parts of the if_conf should be discussed here instead</para>
+        <para>
+          Insert notes about VLAN interfaces with hw crypto here or
+          in the hw crypto chapter.
+        </para>
+!Finclude/net/mac80211.h ieee80211_get_buffered_bc
+!Finclude/net/mac80211.h ieee80211_beacon_get
+      </chapter>
+
+      <chapter id="multi-iface">
+        <title>Supporting multiple virtual interfaces</title>
+        <para>TBD</para>
+        <para>
+          Note: WDS with identical MAC address should almost always be OK
+        </para>
+        <para>
+          Insert notes about having multiple virtual interfaces with
+          different MAC addresses here, note which configurations are
+          supported by mac80211, add notes about supporting hw crypto
+          with it.
+        </para>
+      </chapter>
+
+      <chapter id="hardware-scan-offload">
+        <title>Hardware scan offload</title>
+        <para>TBD</para>
+!Finclude/net/mac80211.h ieee80211_scan_completed
+      </chapter>
+    </part>
+
+    <part id="rate-control">
+      <title>Rate control interface</title>
+      <partintro>
+        <para>TBD</para>
+        <para>
+         This part of the book describes the rate control algorithm
+         interface and how it relates to mac80211 and drivers.
+        </para>
+      </partintro>
+      <chapter id="dummy">
+        <title>dummy chapter</title>
+        <para>TBD</para>
+      </chapter>
+    </part>
+
+    <part id="internal">
+      <title>Internals</title>
+      <partintro>
+        <para>TBD</para>
+        <para>
+         This part of the book describes mac80211 internals.
+        </para>
+      </partintro>
+
+      <chapter id="key-handling">
+        <title>Key handling</title>
+        <sect1>
+          <title>Key handling basics</title>
+!Pnet/mac80211/key.c Key handling basics
+        </sect1>
+        <sect1>
+          <title>MORE TBD</title>
+          <para>TBD</para>
+        </sect1>
+      </chapter>
+
+      <chapter id="rx-processing">
+        <title>Receive processing</title>
+        <para>TBD</para>
+      </chapter>
+
+      <chapter id="tx-processing">
+        <title>Transmit processing</title>
+        <para>TBD</para>
+      </chapter>
+
+      <chapter id="sta-info">
+        <title>Station info handling</title>
+        <sect1>
+          <title>Programming information</title>
+!Fnet/mac80211/sta_info.h sta_info
+!Fnet/mac80211/sta_info.h ieee80211_sta_info_flags
+        </sect1>
+        <sect1>
+          <title>STA information lifetime rules</title>
+!Pnet/mac80211/sta_info.c STA information lifetime rules
+        </sect1>
+      </chapter>
+
+      <chapter id="synchronisation">
+        <title>Synchronisation</title>
+        <para>TBD</para>
+        <para>Locking, lots of RCU</para>
+      </chapter>
+    </part>
+  </book>
+</set>

Documentation/DocBook/Makefile

@@ -12,7 +12,7 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
 	    kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-	    mac80211.xml debugobjects.xml sh.xml regulator.xml \
+	    80211.xml debugobjects.xml sh.xml regulator.xml \
 	    alsa-driver-api.xml writing-an-alsa-driver.xml \
 	    tracepoint.xml media.xml drm.xml
 

Documentation/DocBook/drm.tmpl

@@ -136,6 +136,7 @@
 #ifdef CONFIG_COMPAT
 		.compat_ioctl = i915_compat_ioctl,
 #endif
+		.llseek = noop_llseek,
 		},
 	.pci_driver = {
 		.name = DRIVER_NAME,

Documentation/DocBook/genericirq.tmpl

@@ -28,7 +28,7 @@
   </authorgroup>
 
   <copyright>
-   <year>2005-2006</year>
+   <year>2005-2010</year>
    <holder>Thomas Gleixner</holder>
   </copyright>
   <copyright>
@@ -100,6 +100,10 @@
 	  <listitem><para>Edge type</para></listitem>
 	  <listitem><para>Simple type</para></listitem>
 	</itemizedlist>
+	During the implementation we identified another type:
+	<itemizedlist>
+	  <listitem><para>Fast EOI type</para></listitem>
+	</itemizedlist>
 	In the SMP world of the __do_IRQ() super-handler another type
 	was identified:
 	<itemizedlist>
@@ -153,6 +157,7 @@
 	is still available. This leads to a kind of duality for the time
 	being. Over time the new model should be used in more and more
 	architectures, as it enables smaller and cleaner IRQ subsystems.
+	It's deprecated for three years now and about to be removed.
 	</para>
   </chapter>
   <chapter id="bugs">
@@ -217,6 +222,7 @@
 	  <itemizedlist>
 	  <listitem><para>handle_level_irq</para></listitem>
 	  <listitem><para>handle_edge_irq</para></listitem>
+	  <listitem><para>handle_fasteoi_irq</para></listitem>
 	  <listitem><para>handle_simple_irq</para></listitem>
 	  <listitem><para>handle_percpu_irq</para></listitem>
 	  </itemizedlist>
@@ -233,33 +239,33 @@
 		are used by the default flow implementations.
 		The following helper functions are implemented (simplified excerpt):
 		<programlisting>
-default_enable(irq)
+default_enable(struct irq_data *data)
 {
-	desc->chip->unmask(irq);
+	desc->chip->irq_unmask(data);
 }
 
-default_disable(irq)
+default_disable(struct irq_data *data)
 {
-	if (!delay_disable(irq))
-		desc->chip->mask(irq);
+	if (!delay_disable(data))
+		desc->chip->irq_mask(data);
 }
 
-default_ack(irq)
+default_ack(struct irq_data *data)
 {
-	chip->ack(irq);
+	chip->irq_ack(data);
 }
 
-default_mask_ack(irq)
+default_mask_ack(struct irq_data *data)
 {
-	if (chip->mask_ack) {
-		chip->mask_ack(irq);
+	if (chip->irq_mask_ack) {
+		chip->irq_mask_ack(data);
 	} else {
-		chip->mask(irq);
-		chip->ack(irq);
+		chip->irq_mask(data);
+		chip->irq_ack(data);
 	}
 }
 
-noop(irq)
+noop(struct irq_data *data))
 {
 }
 
@@ -278,12 +284,27 @@ noop(irq)
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->start();
+desc->chip->irq_mask();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+desc->chip->irq_unmask();
 		</programlisting>
 		</para>
-   	    </sect3>
+	    </sect3>
+	    <sect3 id="Default_FASTEOI_IRQ_flow_handler">
+		<title>Default Fast EOI IRQ flow handler</title>
+		<para>
+		handle_fasteoi_irq provides a generic implementation
+		for interrupts, which only need an EOI at the end of
+		the handler
+		</para>
+		<para>
+		The following control flow is implemented (simplified excerpt):
+		<programlisting>
+handle_IRQ_event(desc->action);
+desc->chip->irq_eoi();
+		</programlisting>
+		</para>
+	    </sect3>
 	    <sect3 id="Default_Edge_IRQ_flow_handler">
 	 	<title>Default Edge IRQ flow handler</title>
 		<para>
@@ -294,20 +315,19 @@ desc->chip->end();
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
 if (desc->status &amp; running) {
-	desc->chip->hold();
+	desc->chip->irq_mask();
 	desc->status |= pending | masked;
 	return;
 }
-desc->chip->start();
+desc->chip->irq_ack();
 desc->status |= running;
 do {
 	if (desc->status &amp; masked)
-		desc->chip->enable();
+		desc->chip->irq_unmask();
 	desc->status &amp;= ~pending;
 	handle_IRQ_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
-desc->chip->end();
 		</programlisting>
 		</para>
    	    </sect3>
@@ -342,9 +362,9 @@ handle_IRQ_event(desc->action);
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->start();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+if (desc->chip->irq_eoi)
+        desc->chip->irq_eoi();
 		</programlisting>
 		</para>
    	    </sect3>
@@ -375,8 +395,7 @@ desc->chip->end();
 	mechanism. (It's necessary to enable CONFIG_HARDIRQS_SW_RESEND when
 	you want to use the delayed interrupt disable feature and your
 	hardware is not capable of retriggering	an interrupt.)
-	The delayed interrupt disable can be runtime enabled, per interrupt,
-	by setting the IRQ_DELAYED_DISABLE flag in the irq_desc status field.
+	The delayed interrupt disable is not configurable.
 	</para>
 	</sect2>
     </sect1>
@@ -387,13 +406,13 @@ desc->chip->end();
 	contains all the direct chip relevant functions, which
 	can be utilized by the irq flow implementations.
 	  <itemizedlist>
-	  <listitem><para>ack()</para></listitem>
-	  <listitem><para>mask_ack() - Optional, recommended for performance</para></listitem>
-	  <listitem><para>mask()</para></listitem>
-	  <listitem><para>unmask()</para></listitem>
-	  <listitem><para>retrigger() - Optional</para></listitem>
-	  <listitem><para>set_type() - Optional</para></listitem>
-	  <listitem><para>set_wake() - Optional</para></listitem>
+	  <listitem><para>irq_ack()</para></listitem>
+	  <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
+	  <listitem><para>irq_mask()</para></listitem>
+	  <listitem><para>irq_unmask()</para></listitem>
+	  <listitem><para>irq_retrigger() - Optional</para></listitem>
+	  <listitem><para>irq_set_type() - Optional</para></listitem>
+	  <listitem><para>irq_set_wake() - Optional</para></listitem>
 	  </itemizedlist>
 	These primitives are strictly intended to mean what they say: ack means
 	ACK, masking means masking of an IRQ line, etc. It is up to the flow
@@ -458,6 +477,7 @@ desc->chip->end();
      <para>
      This chapter contains the autogenerated documentation of the internal functions.
      </para>
+!Ikernel/irq/irqdesc.c
 !Ikernel/irq/handle.c
 !Ikernel/irq/chip.c
   </chapter>

Documentation/DocBook/kernel-api.tmpl

@@ -257,7 +257,8 @@ X!Earch/x86/kernel/mca_32.c
 !Iblock/blk-sysfs.c
 !Eblock/blk-settings.c
 !Eblock/blk-exec.c
-!Eblock/blk-barrier.c
+!Eblock/blk-flush.c
+!Eblock/blk-lib.c
 !Eblock/blk-tag.c
 !Iblock/blk-tag.c
 !Eblock/blk-integrity.c

Documentation/DocBook/kernel-locking.tmpl

@@ -1645,7 +1645,9 @@ the amount of locking which needs to be done.
       all the readers who were traversing the list when we deleted the
       element are finished.  We use <function>call_rcu()</function> to
       register a callback which will actually destroy the object once
-      the readers are finished.
+      all pre-existing readers are finished.  Alternatively,
+      <function>synchronize_rcu()</function> may be used to block until
+      all pre-existing are finished.
     </para>
     <para>
       But how does Read Copy Update know when the readers are
@@ -1714,7 +1716,7 @@ the amount of locking which needs to be done.
 -        object_put(obj);
 +        list_del_rcu(&amp;obj-&gt;list);
          cache_num--;
-+        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu, obj);
++        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu);
  }
 
  /* Must be holding cache_lock */
@@ -1725,14 +1727,6 @@ the amount of locking which needs to be done.
          if (++cache_num > MAX_CACHE_SIZE) {
                  struct object *i, *outcast = NULL;
                  list_for_each_entry(i, &amp;cache, list) {
-@@ -85,6 +94,7 @@
-         obj-&gt;popularity = 0;
-         atomic_set(&amp;obj-&gt;refcnt, 1); /* The cache holds a reference */
-         spin_lock_init(&amp;obj-&gt;lock);
-+        INIT_RCU_HEAD(&amp;obj-&gt;rcu);
-
-         spin_lock_irqsave(&amp;cache_lock, flags);
-         __cache_add(obj);
 @@ -104,12 +114,11 @@
  struct object *cache_find(int id)
  {

Documentation/DocBook/mac80211.tmpl

@@ -1,337 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-
-<book id="mac80211-developers-guide">
-  <bookinfo>
-    <title>The mac80211 subsystem for kernel developers</title>
-
-    <authorgroup>
-      <author>
-        <firstname>Johannes</firstname>
-        <surname>Berg</surname>
-        <affiliation>
-          <address><email>johannes@sipsolutions.net</email></address>
-        </affiliation>
-      </author>
-    </authorgroup>
-
-    <copyright>
-      <year>2007-2009</year>
-      <holder>Johannes Berg</holder>
-    </copyright>
-
-    <legalnotice>
-      <para>
-        This documentation is free software; you can redistribute
-        it and/or modify it under the terms of the GNU General Public
-        License version 2 as published by the Free Software Foundation.
-      </para>
-
-      <para>
-        This documentation is distributed in the hope that it will be
-        useful, but WITHOUT ANY WARRANTY; without even the implied
-        warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-        See the GNU General Public License for more details.
-      </para>
-
-      <para>
-        You should have received a copy of the GNU General Public
-        License along with this documentation; if not, write to the Free
-        Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
-        MA 02111-1307 USA
-      </para>
-
-      <para>
-        For more details see the file COPYING in the source
-        distribution of Linux.
-      </para>
-    </legalnotice>
-
-    <abstract>
-!Pinclude/net/mac80211.h Introduction
-!Pinclude/net/mac80211.h Warning
-    </abstract>
-  </bookinfo>
-
-  <toc></toc>
-
-<!--
-Generally, this document shall be ordered by increasing complexity.
-It is important to note that readers should be able to read only
-the first few sections to get a working driver and only advanced
-usage should require reading the full document.
--->
-
-  <part>
-    <title>The basic mac80211 driver interface</title>
-    <partintro>
-      <para>
-        You should read and understand the information contained
-        within this part of the book while implementing a driver.
-        In some chapters, advanced usage is noted, that may be
-        skipped at first.
-      </para>
-      <para>
-        This part of the book only covers station and monitor mode
-        functionality, additional information required to implement
-        the other modes is covered in the second part of the book.
-      </para>
-    </partintro>
-
-    <chapter id="basics">
-      <title>Basic hardware handling</title>
-      <para>TBD</para>
-      <para>
-        This chapter shall contain information on getting a hw
-        struct allocated and registered with mac80211.
-      </para>
-      <para>
-        Since it is required to allocate rates/modes before registering
-        a hw struct, this chapter shall also contain information on setting
-        up the rate/mode structs.
-      </para>
-      <para>
-        Additionally, some discussion about the callbacks and
-        the general programming model should be in here, including
-        the definition of ieee80211_ops which will be referred to
-        a lot.
-      </para>
-      <para>
-        Finally, a discussion of hardware capabilities should be done
-        with references to other parts of the book.
-      </para>
-<!-- intentionally multiple !F lines to get proper order -->
-!Finclude/net/mac80211.h ieee80211_hw
-!Finclude/net/mac80211.h ieee80211_hw_flags
-!Finclude/net/mac80211.h SET_IEEE80211_DEV
-!Finclude/net/mac80211.h SET_IEEE80211_PERM_ADDR
-!Finclude/net/mac80211.h ieee80211_ops
-!Finclude/net/mac80211.h ieee80211_alloc_hw
-!Finclude/net/mac80211.h ieee80211_register_hw
-!Finclude/net/mac80211.h ieee80211_get_tx_led_name
-!Finclude/net/mac80211.h ieee80211_get_rx_led_name
-!Finclude/net/mac80211.h ieee80211_get_assoc_led_name
-!Finclude/net/mac80211.h ieee80211_get_radio_led_name
-!Finclude/net/mac80211.h ieee80211_unregister_hw
-!Finclude/net/mac80211.h ieee80211_free_hw
-    </chapter>
-
-    <chapter id="phy-handling">
-      <title>PHY configuration</title>
-      <para>TBD</para>
-      <para>
-        This chapter should describe PHY handling including
-        start/stop callbacks and the various structures used.
-      </para>
-!Finclude/net/mac80211.h ieee80211_conf
-!Finclude/net/mac80211.h ieee80211_conf_flags
-    </chapter>
-
-    <chapter id="iface-handling">
-      <title>Virtual interfaces</title>
-      <para>TBD</para>
-      <para>
-        This chapter should describe virtual interface basics
-        that are relevant to the driver (VLANs, MGMT etc are not.)
-        It should explain the use of the add_iface/remove_iface
-        callbacks as well as the interface configuration callbacks.
-      </para>
-      <para>Things related to AP mode should be discussed there.</para>
-      <para>
-        Things related to supporting multiple interfaces should be
-        in the appropriate chapter, a BIG FAT note should be here about
-        this though and the recommendation to allow only a single
-        interface in STA mode at first!
-      </para>
-!Finclude/net/mac80211.h ieee80211_vif
-    </chapter>
-
-    <chapter id="rx-tx">
-      <title>Receive and transmit processing</title>
-      <sect1>
-        <title>what should be here</title>
-        <para>TBD</para>
-        <para>
-          This should describe the receive and transmit
-          paths in mac80211/the drivers as well as
-          transmit status handling.
-        </para>
-      </sect1>
-      <sect1>
-        <title>Frame format</title>
-!Pinclude/net/mac80211.h Frame format
-      </sect1>
-      <sect1>
-        <title>Packet alignment</title>
-!Pnet/mac80211/rx.c Packet alignment
-      </sect1>
-      <sect1>
-        <title>Calling into mac80211 from interrupts</title>
-!Pinclude/net/mac80211.h Calling mac80211 from interrupts
-      </sect1>
-      <sect1>
-        <title>functions/definitions</title>
-!Finclude/net/mac80211.h ieee80211_rx_status
-!Finclude/net/mac80211.h mac80211_rx_flags
-!Finclude/net/mac80211.h ieee80211_tx_info
-!Finclude/net/mac80211.h ieee80211_rx
-!Finclude/net/mac80211.h ieee80211_rx_irqsafe
-!Finclude/net/mac80211.h ieee80211_tx_status
-!Finclude/net/mac80211.h ieee80211_tx_status_irqsafe
-!Finclude/net/mac80211.h ieee80211_rts_get
-!Finclude/net/mac80211.h ieee80211_rts_duration
-!Finclude/net/mac80211.h ieee80211_ctstoself_get
-!Finclude/net/mac80211.h ieee80211_ctstoself_duration
-!Finclude/net/mac80211.h ieee80211_generic_frame_duration
-!Finclude/net/mac80211.h ieee80211_wake_queue
-!Finclude/net/mac80211.h ieee80211_stop_queue
-!Finclude/net/mac80211.h ieee80211_wake_queues
-!Finclude/net/mac80211.h ieee80211_stop_queues
-      </sect1>
-    </chapter>
-
-    <chapter id="filters">
-      <title>Frame filtering</title>
-!Pinclude/net/mac80211.h Frame filtering
-!Finclude/net/mac80211.h ieee80211_filter_flags
-    </chapter>
-  </part>
-
-  <part id="advanced">
-    <title>Advanced driver interface</title>
-    <partintro>
-      <para>
-       Information contained within this part of the book is
-       of interest only for advanced interaction of mac80211
-       with drivers to exploit more hardware capabilities and
-       improve performance.
-      </para>
-    </partintro>
-
-    <chapter id="hardware-crypto-offload">
-      <title>Hardware crypto acceleration</title>
-!Pinclude/net/mac80211.h Hardware crypto acceleration
-<!-- intentionally multiple !F lines to get proper order -->
-!Finclude/net/mac80211.h set_key_cmd
-!Finclude/net/mac80211.h ieee80211_key_conf
-!Finclude/net/mac80211.h ieee80211_key_alg
-!Finclude/net/mac80211.h ieee80211_key_flags
-    </chapter>
-
-    <chapter id="powersave">
-      <title>Powersave support</title>
-!Pinclude/net/mac80211.h Powersave support
-    </chapter>
-
-    <chapter id="beacon-filter">
-      <title>Beacon filter support</title>
-!Pinclude/net/mac80211.h Beacon filter support
-!Finclude/net/mac80211.h ieee80211_beacon_loss
-    </chapter>
-
-    <chapter id="qos">
-      <title>Multiple queues and QoS support</title>
-      <para>TBD</para>
-!Finclude/net/mac80211.h ieee80211_tx_queue_params
-    </chapter>
-
-    <chapter id="AP">
-      <title>Access point mode support</title>
-      <para>TBD</para>
-      <para>Some parts of the if_conf should be discussed here instead</para>
-      <para>
-        Insert notes about VLAN interfaces with hw crypto here or
-        in the hw crypto chapter.
-      </para>
-!Finclude/net/mac80211.h ieee80211_get_buffered_bc
-!Finclude/net/mac80211.h ieee80211_beacon_get
-    </chapter>
-
-    <chapter id="multi-iface">
-      <title>Supporting multiple virtual interfaces</title>
-      <para>TBD</para>
-      <para>
-        Note: WDS with identical MAC address should almost always be OK
-      </para>
-      <para>
-        Insert notes about having multiple virtual interfaces with
-        different MAC addresses here, note which configurations are
-        supported by mac80211, add notes about supporting hw crypto
-        with it.
-      </para>
-    </chapter>
-
-    <chapter id="hardware-scan-offload">
-      <title>Hardware scan offload</title>
-      <para>TBD</para>
-!Finclude/net/mac80211.h ieee80211_scan_completed
-    </chapter>
-  </part>
-
-  <part id="rate-control">
-    <title>Rate control interface</title>
-    <partintro>
-      <para>TBD</para>
-      <para>
-       This part of the book describes the rate control algorithm
-       interface and how it relates to mac80211 and drivers.
-      </para>
-    </partintro>
-    <chapter id="dummy">
-      <title>dummy chapter</title>
-      <para>TBD</para>
-    </chapter>
-  </part>
-
-  <part id="internal">
-    <title>Internals</title>
-    <partintro>
-      <para>TBD</para>
-      <para>
-       This part of the book describes mac80211 internals.
-      </para>
-    </partintro>
-
-    <chapter id="key-handling">
-      <title>Key handling</title>
-      <sect1>
-        <title>Key handling basics</title>
-!Pnet/mac80211/key.c Key handling basics
-      </sect1>
-      <sect1>
-        <title>MORE TBD</title>
-        <para>TBD</para>
-      </sect1>
-    </chapter>
-
-    <chapter id="rx-processing">
-      <title>Receive processing</title>
-      <para>TBD</para>
-    </chapter>
-
-    <chapter id="tx-processing">
-      <title>Transmit processing</title>
-      <para>TBD</para>
-    </chapter>
-
-    <chapter id="sta-info">
-      <title>Station info handling</title>
-      <sect1>
-        <title>Programming information</title>
-!Fnet/mac80211/sta_info.h sta_info
-!Fnet/mac80211/sta_info.h ieee80211_sta_info_flags
-      </sect1>
-      <sect1>
-        <title>STA information lifetime rules</title>
-!Pnet/mac80211/sta_info.c STA information lifetime rules
-      </sect1>
-    </chapter>
-
-    <chapter id="synchronisation">
-      <title>Synchronisation</title>
-      <para>TBD</para>
-      <para>Locking, lots of RCU</para>
-    </chapter>
-  </part>
-</book>

Documentation/RCU/checklist.txt

@@ -218,13 +218,22 @@ over a rather long period of time, but improvements are always welcome!
 	include:
 
 	a.	Keeping a count of the number of data-structure elements
-		used by the RCU-protected data structure, including those
-		waiting for a grace period to elapse.  Enforce a limit
-		on this number, stalling updates as needed to allow
-		previously deferred frees to complete.
-
-		Alternatively, limit only the number awaiting deferred
-		free rather than the total number of elements.
+		used by the RCU-protected data structure, including
+		those waiting for a grace period to elapse.  Enforce a
+		limit on this number, stalling updates as needed to allow
+		previously deferred frees to complete.	Alternatively,
+		limit only the number awaiting deferred free rather than
+		the total number of elements.
+
+		One way to stall the updates is to acquire the update-side
+		mutex.	(Don't try this with a spinlock -- other CPUs
+		spinning on the lock could prevent the grace period
+		from ever ending.)  Another way to stall the updates
+		is for the updates to use a wrapper function around
+		the memory allocator, so that this wrapper function
+		simulates OOM when there is too much memory awaiting an
+		RCU grace period.  There are of course many other
+		variations on this theme.
 
 	b.	Limiting update rate.  For example, if updates occur only
 		once per hour, then no explicit rate limiting is required,
@@ -365,3 +374,26 @@ over a rather long period of time, but improvements are always welcome!
 	and the compiler to freely reorder code into and out of RCU
 	read-side critical sections.  It is the responsibility of the
 	RCU update-side primitives to deal with this.
+
+17.	Use CONFIG_PROVE_RCU, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and
+	the __rcu sparse checks to validate your RCU code.  These
+	can help find problems as follows:
+
+	CONFIG_PROVE_RCU: check that accesses to RCU-protected data
+		structures are carried out under the proper RCU
+		read-side critical section, while holding the right
+		combination of locks, or whatever other conditions
+		are appropriate.
+
+	CONFIG_DEBUG_OBJECTS_RCU_HEAD: check that you don't pass the
+		same object to call_rcu() (or friends) before an RCU
+		grace period has elapsed since the last time that you
+		passed that same object to call_rcu() (or friends).
+
+	__rcu sparse checks: tag the pointer to the RCU-protected data
+		structure with __rcu, and sparse will warn you if you
+		access that pointer without the services of one of the
+		variants of rcu_dereference().
+
+	These debugging aids can help you find problems that are
+	otherwise extremely difficult to spot.

Documentation/RCU/stallwarn.txt

@@ -80,6 +80,24 @@ o	A CPU looping with bottom halves disabled.  This condition can
 o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
 	without invoking schedule().
 
+o	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+	happen to preempt a low-priority task in the middle of an RCU
+	read-side critical section.   This is especially damaging if
+	that low-priority task is not permitted to run on any other CPU,
+	in which case the next RCU grace period can never complete, which
+	will eventually cause the system to run out of memory and hang.
+	While the system is in the process of running itself out of
+	memory, you might see stall-warning messages.
+
+o	A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
+	is running at a higher priority than the RCU softirq threads.
+	This will prevent RCU callbacks from ever being invoked,
+	and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
+	RCU grace periods from ever completing.  Either way, the
+	system will eventually run out of memory and hang.  In the
+	CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
+	messages.
+
 o	A bug in the RCU implementation.
 
 o	A hardware failure.  This is quite unlikely, but has occurred

Documentation/RCU/trace.txt

@@ -125,6 +125,17 @@ o	"b" is the batch limit for this CPU.  If more than this number
 	of RCU callbacks is ready to invoke, then the remainder will
 	be deferred.
 
+o	"ci" is the number of RCU callbacks that have been invoked for
+	this CPU.  Note that ci+ql is the number of callbacks that have
+	been registered in absence of CPU-hotplug activity.
+
+o	"co" is the number of RCU callbacks that have been orphaned due to
+	this CPU going offline.
+
+o	"ca" is the number of RCU callbacks that have been adopted due to
+	other CPUs going offline.  Note that ci+co-ca+ql is the number of
+	RCU callbacks registered on this CPU.
+
 There is also an rcu/rcudata.csv file with the same information in
 comma-separated-variable spreadsheet format.
 
@@ -180,7 +191,7 @@ o	"s" is the "signaled" state that drives force_quiescent_state()'s
 
 o	"jfq" is the number of jiffies remaining for this grace period
 	before force_quiescent_state() is invoked to help push things
-	along.  Note that CPUs in dyntick-idle mode thoughout the grace
+	along.  Note that CPUs in dyntick-idle mode throughout the grace
 	period will not report on their own, but rather must be check by
 	some other CPU via force_quiescent_state().
 

Documentation/arm/00-INDEX

@@ -6,6 +6,8 @@ Interrupts
 	- ARM Interrupt subsystem documentation
 IXP2000
 	- Release Notes for Linux on Intel's IXP2000 Network Processor
+msm
+	- MSM specific documentation
 Netwinder
 	- Netwinder specific documentation
 Porting

Documentation/arm/SA1100/FreeBird

@@ -1,6 +1,6 @@
-Freebird-1.1 is produced by Legned(C) ,Inc.
+Freebird-1.1 is produced by Legend(C), Inc.
 http://web.archive.org/web/*/http://www.legend.com.cn
-and software/linux mainatined by Coventive(C),Inc.
+and software/linux maintained by Coventive(C), Inc.
 (http://www.coventive.com)
 
 Based on the Nicolas's strongarm kernel tree.

Documentation/arm/msm/gpiomux.txt

@@ -0,0 +1,176 @@
+This document provides an overview of the msm_gpiomux interface, which
+is used to provide gpio pin multiplexing and configuration on mach-msm
+targets.
+
+History
+=======
+
+The first-generation API for gpio configuration & multiplexing on msm
+is the function gpio_tlmm_config().  This function has a few notable
+shortcomings, which led to its deprecation and replacement by gpiomux:
+
+The 'disable' parameter:  Setting the second parameter to
+gpio_tlmm_config to GPIO_CFG_DISABLE tells the peripheral
+processor in charge of the subsystem to perform a look-up into a
+low-power table and apply the low-power/sleep setting for the pin.
+As the msm family evolved this became problematic. Not all pins
+have sleep settings, not all peripheral processors will accept requests
+to apply said sleep settings, and not all msm targets have their gpio
+subsystems managed by a peripheral processor. In order to get consistent
+behavior on all targets, drivers are forced to ignore this parameter,
+rendering it useless.
+
+The 'direction' flag: for all mux-settings other than raw-gpio (0),
+the output-enable bit of a gpio is hard-wired to a known
+input (usually VDD or ground).  For those settings, the direction flag
+is meaningless at best, and deceptive at worst.  In addition, using the
+direction flag to change output-enable (OE) directly can cause trouble in
+gpiolib, which has no visibility into gpio direction changes made
+in this way.  Direction control in gpio mode should be made through gpiolib.
+
+Key Features of gpiomux
+=======================
+
+- A consistent interface across all generations of msm.  Drivers can expect
+the same results on every target.
+- gpiomux plays nicely with gpiolib.  Functions that should belong to gpiolib
+are left to gpiolib and not duplicated here.  gpiomux is written with the
+intent that gpio_chips will call gpiomux reference-counting methods
+from their request() and free() hooks, providing full integration.
+- Tabular configuration.  Instead of having to call gpio_tlmm_config
+hundreds of times, gpio configuration is placed in a single table.
+- Per-gpio sleep.  Each gpio is individually reference counted, allowing only
+those lines which are in use to be put in high-power states.
+- 0 means 'do nothing': all flags are designed so that the default memset-zero
+equates to a sensible default of 'no configuration', preventing users
+from having to provide hundreds of 'no-op' configs for unused or
+unwanted lines.
+
+Usage
+=====
+
+To use gpiomux, provide configuration information for relevant gpio lines
+in the msm_gpiomux_configs table.  Since a 0 equates to "unconfigured",
+only those lines to be managed by gpiomux need to be specified.  Here
+is a completely fictional example:
+
+struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS] = {
+	[12] = {
+		.active = GPIOMUX_VALID | GPIOMUX_DRV_8MA | GPIOMUX_FUNC_1,
+		.suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+	},
+	[34] = {
+		.suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+	},
+};
+
+To indicate that a gpio is in use, call msm_gpiomux_get() to increase
+its reference count.  To decrease the reference count, call msm_gpiomux_put().
+
+The effect of this configuration is as follows:
+
+When the system boots, gpios 12 and 34 will be initialized with their
+'suspended' configurations.  All other gpios, which were left unconfigured,
+will not be touched.
+
+When msm_gpiomux_get() is called on gpio 12 to raise its reference count
+above 0, its active configuration will be applied.  Since no other gpio
+line has a valid active configuration, msm_gpiomux_get() will have no
+effect on any other line.
+
+When msm_gpiomux_put() is called on gpio 12 or 34 to drop their reference
+count to 0, their suspended configurations will be applied.
+Since no other gpio line has a valid suspended configuration, no other
+gpio line will be effected by msm_gpiomux_put().  Since gpio 34 has no valid
+active configuration, this is effectively a no-op for gpio 34 as well,
+with one small caveat, see the section "About Output-Enable Settings".
+
+All of the GPIOMUX_VALID flags may seem like unnecessary overhead, but
+they address some important issues.  As unused entries (all those
+except 12 and 34) are zero-filled, gpiomux needs a way to distinguish
+the used fields from the unused.  In addition, the all-zero pattern
+is a valid configuration!  Therefore, gpiomux defines an additional bit
+which is used to indicate when a field is used.  This has the pleasant
+side-effect of allowing calls to msm_gpiomux_write to use '0' to indicate
+that a value should not be changed:
+
+  msm_gpiomux_write(0, GPIOMUX_VALID, 0);
+
+replaces the active configuration of gpio 0 with an all-zero configuration,
+but leaves the suspended configuration as it was.
+
+Static Configurations
+=====================
+
+To install a static configuration, which is applied at boot and does
+not change after that, install a configuration with a suspended component
+but no active component, as in the previous example:
+
+	[34] = {
+		.suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+	},
+
+The suspended setting is applied during boot, and the lack of any valid
+active setting prevents any other setting from being applied at runtime.
+If other subsystems attempting to access the line is a concern, one could
+*really* anchor the configuration down by calling msm_gpiomux_get on the
+line at initialization to move the line into active mode.  With the line
+held, it will never be re-suspended, and with no valid active configuration,
+no new configurations will be applied.
+
+But then, if having other subsystems grabbing for the line is truly a concern,
+it should be reserved with gpio_request instead, which carries an implicit
+msm_gpiomux_get.
+
+gpiomux and gpiolib
+===================
+
+It is expected that msm gpio_chips will call msm_gpiomux_get() and
+msm_gpiomux_put() from their request and free hooks, like this fictional
+example:
+
+static int request(struct gpio_chip *chip, unsigned offset)
+{
+        return msm_gpiomux_get(chip->base + offset);
+}
+
+static void free(struct gpio_chip *chip, unsigned offset)
+{
+        msm_gpiomux_put(chip->base + offset);
+}
+
+	...somewhere in a gpio_chip declaration...
+	.request = request,
+	.free    = free,
+
+This provides important functionality:
+- It guarantees that a gpio line will have its 'active' config applied
+  when the line is requested, and will not be suspended while the line
+  remains requested; and
+- It guarantees that gpio-direction settings from gpiolib behave sensibly.
+  See "About Output-Enable Settings."
+
+This mechanism allows for "auto-request" of gpiomux lines via gpiolib
+when it is suitable.  Drivers wishing more exact control are, of course,
+free to also use msm_gpiomux_set and msm_gpiomux_get.
+
+About Output-Enable Settings
+============================
+
+Some msm targets do not have the ability to query the current gpio
+configuration setting.  This means that changes made to the output-enable
+(OE) bit by gpiolib cannot be consistently detected and preserved by gpiomux.
+Therefore, when gpiomux applies a configuration setting, any direction
+settings which may have been applied by gpiolib are lost and the default
+input settings are re-applied.
+
+For this reason, drivers should not assume that gpio direction settings
+continue to hold if they free and then re-request a gpio.  This seems like
+common sense - after all, anybody could have obtained the line in the
+meantime - but it needs saying.
+
+This also means that calls to msm_gpiomux_write will reset the OE bit,
+which means that if the gpio line is held by a client of gpiolib and
+msm_gpiomux_write is called, the direction setting has been lost and
+gpiolib's internal state has been broken.
+Release gpio lines before reconfiguring them.

Documentation/block/00-INDEX

@@ -1,7 +1,5 @@
 00-INDEX
 	- This file
-barrier.txt
-	- I/O Barriers
 biodoc.txt
 	- Notes on the Generic Block Layer Rewrite in Linux 2.5
 capability.txt
@@ -16,3 +14,5 @@ stat.txt
 	- Block layer statistics in /sys/block/<dev>/stat
 switching-sched.txt
 	- Switching I/O schedulers at runtime
+writeback_cache_control.txt
+	- Control of volatile write back caches

Documentation/block/barrier.txt

@@ -1,261 +0,0 @@
-I/O Barriers
-============
-Tejun Heo <htejun@gmail.com>, July 22 2005
-
-I/O barrier requests are used to guarantee ordering around the barrier
-requests.  Unless you're crazy enough to use disk drives for
-implementing synchronization constructs (wow, sounds interesting...),
-the ordering is meaningful only for write requests for things like
-journal checkpoints.  All requests queued before a barrier request
-must be finished (made it to the physical medium) before the barrier
-request is started, and all requests queued after the barrier request
-must be started only after the barrier request is finished (again,
-made it to the physical medium).
-
-In other words, I/O barrier requests have the following two properties.
-
-1. Request ordering
-
-Requests cannot pass the barrier request.  Preceding requests are
-processed before the barrier and following requests after.
-
-Depending on what features a drive supports, this can be done in one
-of the following three ways.
-
-i. For devices which have queue depth greater than 1 (TCQ devices) and
-support ordered tags, block layer can just issue the barrier as an
-ordered request and the lower level driver, controller and drive
-itself are responsible for making sure that the ordering constraint is
-met.  Most modern SCSI controllers/drives should support this.
-
-NOTE: SCSI ordered tag isn't currently used due to limitation in the
-      SCSI midlayer, see the following random notes section.
-
-ii. For devices which have queue depth greater than 1 but don't
-support ordered tags, block layer ensures that the requests preceding
-a barrier request finishes before issuing the barrier request.  Also,
-it defers requests following the barrier until the barrier request is
-finished.  Older SCSI controllers/drives and SATA drives fall in this
-category.
-
-iii. Devices which have queue depth of 1.  This is a degenerate case
-of ii.  Just keeping issue order suffices.  Ancient SCSI
-controllers/drives and IDE drives are in this category.
-
-2. Forced flushing to physical medium
-
-Again, if you're not gonna do synchronization with disk drives (dang,
-it sounds even more appealing now!), the reason you use I/O barriers
-is mainly to protect filesystem integrity when power failure or some
-other events abruptly stop the drive from operating and possibly make
-the drive lose data in its cache.  So, I/O barriers need to guarantee
-that requests actually get written to non-volatile medium in order.
-
-There are four cases,
-
-i. No write-back cache.  Keeping requests ordered is enough.
-
-ii. Write-back cache but no flush operation.  There's no way to
-guarantee physical-medium commit order.  This kind of devices can't to
-I/O barriers.
-
-iii. Write-back cache and flush operation but no FUA (forced unit
-access).  We need two cache flushes - before and after the barrier
-request.
-
-iv. Write-back cache, flush operation and FUA.  We still need one
-flush to make sure requests preceding a barrier are written to medium,
-but post-barrier flush can be avoided by using FUA write on the
-barrier itself.
-
-
-How to support barrier requests in drivers
-------------------------------------------
-
-All barrier handling is done inside block layer proper.  All low level
-drivers have to are implementing its prepare_flush_fn and using one
-the following two functions to indicate what barrier type it supports
-and how to prepare flush requests.  Note that the term 'ordered' is
-used to indicate the whole sequence of performing barrier requests
-including draining and flushing.
-
-typedef void (prepare_flush_fn)(struct request_queue *q, struct request *rq);
-
-int blk_queue_ordered(struct request_queue *q, unsigned ordered,
-		      prepare_flush_fn *prepare_flush_fn);
-
-@q			: the queue in question
-@ordered		: the ordered mode the driver/device supports
-@prepare_flush_fn	: this function should prepare @rq such that it
-			  flushes cache to physical medium when executed
-
-For example, SCSI disk driver's prepare_flush_fn looks like the
-following.
-
-static void sd_prepare_flush(struct request_queue *q, struct request *rq)
-{
-	memset(rq->cmd, 0, sizeof(rq->cmd));
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->timeout = SD_TIMEOUT;
-	rq->cmd[0] = SYNCHRONIZE_CACHE;
-	rq->cmd_len = 10;
-}
-
-The following seven ordered modes are supported.  The following table
-shows which mode should be used depending on what features a
-device/driver supports.  In the leftmost column of table,
-QUEUE_ORDERED_ prefix is omitted from the mode names to save space.
-
-The table is followed by description of each mode.  Note that in the
-descriptions of QUEUE_ORDERED_DRAIN*, '=>' is used whereas '->' is
-used for QUEUE_ORDERED_TAG* descriptions.  '=>' indicates that the
-preceding step must be complete before proceeding to the next step.
-'->' indicates that the next step can start as soon as the previous
-step is issued.
-
-	    write-back cache	ordered tag	flush		FUA
------------------------------------------------------------------------
-NONE		yes/no		N/A		no		N/A
-DRAIN		no		no		N/A		N/A
-DRAIN_FLUSH	yes		no		yes		no
-DRAIN_FUA	yes		no		yes		yes
-TAG		no		yes		N/A		N/A
-TAG_FLUSH	yes		yes		yes		no
-TAG_FUA		yes		yes		yes		yes
-
-
-QUEUE_ORDERED_NONE
-	I/O barriers are not needed and/or supported.
-
-	Sequence: N/A
-
-QUEUE_ORDERED_DRAIN
-	Requests are ordered by draining the request queue and cache
-	flushing isn't needed.
-
-	Sequence: drain => barrier
-
-QUEUE_ORDERED_DRAIN_FLUSH
-	Requests are ordered by draining the request queue and both
-	pre-barrier and post-barrier cache flushings are needed.
-
-	Sequence: drain => preflush => barrier => postflush
-
-QUEUE_ORDERED_DRAIN_FUA
-	Requests are ordered by draining the request queue and
-	pre-barrier cache flushing is needed.  By using FUA on barrier
-	request, post-barrier flushing can be skipped.
-
-	Sequence: drain => preflush => barrier
-
-QUEUE_ORDERED_TAG
-	Requests are ordered by ordered tag and cache flushing isn't
-	needed.
-
-	Sequence: barrier
-
-QUEUE_ORDERED_TAG_FLUSH
-	Requests are ordered by ordered tag and both pre-barrier and
-	post-barrier cache flushings are needed.
-
-	Sequence: preflush -> barrier -> postflush
-
-QUEUE_ORDERED_TAG_FUA
-	Requests are ordered by ordered tag and pre-barrier cache
-	flushing is needed.  By using FUA on barrier request,
-	post-barrier flushing can be skipped.
-
-	Sequence: preflush -> barrier
-
-
-Random notes/caveats
---------------------
-
-* SCSI layer currently can't use TAG ordering even if the drive,
-controller and driver support it.  The problem is that SCSI midlayer
-request dispatch function is not atomic.  It releases queue lock and
-switch to SCSI host lock during issue and it's possible and likely to
-happen in time that requests change their relative positions.  Once
-this problem is solved, TAG ordering can be enabled.
-
-* Currently, no matter which ordered mode is used, there can be only
-one barrier request in progress.  All I/O barriers are held off by
-block layer until the previous I/O barrier is complete.  This doesn't
-make any difference for DRAIN ordered devices, but, for TAG ordered
-devices with very high command latency, passing multiple I/O barriers
-to low level *might* be helpful if they are very frequent.  Well, this
-certainly is a non-issue.  I'm writing this just to make clear that no
-two I/O barrier is ever passed to low-level driver.
-
-* Completion order.  Requests in ordered sequence are issued in order
-but not required to finish in order.  Barrier implementation can
-handle out-of-order completion of ordered sequence.  IOW, the requests
-MUST be processed in order but the hardware/software completion paths
-are allowed to reorder completion notifications - eg. current SCSI
-midlayer doesn't preserve completion order during error handling.
-
-* Requeueing order.  Low-level drivers are free to requeue any request
-after they removed it from the request queue with
-blkdev_dequeue_request().  As barrier sequence should be kept in order
-when requeued, generic elevator code takes care of putting requests in
-order around barrier.  See blk_ordered_req_seq() and
-ELEVATOR_INSERT_REQUEUE handling in __elv_add_request() for details.
-
-Note that block drivers must not requeue preceding requests while
-completing latter requests in an ordered sequence.  Currently, no
-error checking is done against this.
-
-* Error handling.  Currently, block layer will report error to upper
-layer if any of requests in an ordered sequence fails.  Unfortunately,
-this doesn't seem to be enough.  Look at the following request flow.
-QUEUE_ORDERED_TAG_FLUSH is in use.
-
- [0] [1] [2] [3] [pre] [barrier] [post] < [4] [5] [6] ... >
-					  still in elevator
-
-Let's say request [2], [3] are write requests to update file system
-metadata (journal or whatever) and [barrier] is used to mark that
-those updates are valid.  Consider the following sequence.
-
- i.	Requests [0] ~ [post] leaves the request queue and enters
-	low-level driver.
- ii.	After a while, unfortunately, something goes wrong and the
-	drive fails [2].  Note that any of [0], [1] and [3] could have
-	completed by this time, but [pre] couldn't have been finished
-	as the drive must process it in order and it failed before
-	processing that command.
- iii.	Error handling kicks in and determines that the error is
-	unrecoverable and fails [2], and resumes operation.
- iv.	[pre] [barrier] [post] gets processed.
- v.	*BOOM* power fails
-
-The problem here is that the barrier request is *supposed* to indicate
-that filesystem update requests [2] and [3] made it safely to the
-physical medium and, if the machine crashes after the barrier is
-written, filesystem recovery code can depend on that.  Sadly, that
-isn't true in this case anymore.  IOW, the success of a I/O barrier
-should also be dependent on success of some of the preceding requests,
-where only upper layer (filesystem) knows what 'some' is.
-
-This can be solved by implementing a way to tell the block layer which
-requests affect the success of the following barrier request and
-making lower lever drivers to resume operation on error only after
-block layer tells it to do so.
-
-As the probability of this happening is very low and the drive should
-be faulty, implementing the fix is probably an overkill.  But, still,
-it's there.
-
-* In previous drafts of barrier implementation, there was fallback
-mechanism such that, if FUA or ordered TAG fails, less fancy ordered
-mode can be selected and the failed barrier request is retried
-automatically.  The rationale for this feature was that as FUA is
-pretty new in ATA world and ordered tag was never used widely, there
-could be devices which report to support those features but choke when
-actually given such requests.
-
- This was removed for two reasons 1. it's an overkill 2. it's
-impossible to implement properly when TAG ordering is used as low
-level drivers resume after an error automatically.  If it's ever
-needed adding it back and modifying low level drivers accordingly
-shouldn't be difficult.

Documentation/block/writeback_cache_control.txt

@@ -0,0 +1,86 @@
+
+Explicit volatile write back cache control
+=====================================
+
+Introduction
+------------
+
+Many storage devices, especially in the consumer market, come with volatile
+write back caches.  That means the devices signal I/O completion to the
+operating system before data actually has hit the non-volatile storage.  This
+behavior obviously speeds up various workloads, but it means the operating
+system needs to force data out to the non-volatile storage when it performs
+a data integrity operation like fsync, sync or an unmount.
+
+The Linux block layer provides two simple mechanisms that let filesystems
+control the caching behavior of the storage device.  These mechanisms are
+a forced cache flush, and the Force Unit Access (FUA) flag for requests.
+
+
+Explicit cache flushes
+----------------------
+
+The REQ_FLUSH flag can be OR ed into the r/w flags of a bio submitted from
+the filesystem and will make sure the volatile cache of the storage device
+has been flushed before the actual I/O operation is started.  This explicitly
+guarantees that previously completed write requests are on non-volatile
+storage before the flagged bio starts. In addition the REQ_FLUSH flag can be
+set on an otherwise empty bio structure, which causes only an explicit cache
+flush without any dependent I/O.  It is recommend to use
+the blkdev_issue_flush() helper for a pure cache flush.
+
+
+Forced Unit Access
+-----------------
+
+The REQ_FUA flag can be OR ed into the r/w flags of a bio submitted from the
+filesystem and will make sure that I/O completion for this request is only
+signaled after the data has been committed to non-volatile storage.
+
+
+Implementation details for filesystems
+--------------------------------------
+
+Filesystems can simply set the REQ_FLUSH and REQ_FUA bits and do not have to
+worry if the underlying devices need any explicit cache flushing and how
+the Forced Unit Access is implemented.  The REQ_FLUSH and REQ_FUA flags
+may both be set on a single bio.
+
+
+Implementation details for make_request_fn based block drivers
+--------------------------------------------------------------
+
+These drivers will always see the REQ_FLUSH and REQ_FUA bits as they sit
+directly below the submit_bio interface.  For remapping drivers the REQ_FUA
+bits need to be propagated to underlying devices, and a global flush needs
+to be implemented for bios with the REQ_FLUSH bit set.  For real device
+drivers that do not have a volatile cache the REQ_FLUSH and REQ_FUA bits
+on non-empty bios can simply be ignored, and REQ_FLUSH requests without
+data can be completed successfully without doing any work.  Drivers for
+devices with volatile caches need to implement the support for these
+flags themselves without any help from the block layer.
+
+
+Implementation details for request_fn based block drivers
+--------------------------------------------------------------
+
+For devices that do not support volatile write caches there is no driver
+support required, the block layer completes empty REQ_FLUSH requests before
+entering the driver and strips off the REQ_FLUSH and REQ_FUA bits from
+requests that have a payload.  For devices with volatile write caches the
+driver needs to tell the block layer that it supports flushing caches by
+doing:
+
+	blk_queue_flush(sdkp->disk->queue, REQ_FLUSH);
+
+and handle empty REQ_FLUSH requests in its prep_fn/request_fn.  Note that
+REQ_FLUSH requests with a payload are automatically turned into a sequence
+of an empty REQ_FLUSH request followed by the actual write by the block
+layer.  For devices that also support the FUA bit the block layer needs
+to be told to pass through the REQ_FUA bit using:
+
+	blk_queue_flush(sdkp->disk->queue, REQ_FLUSH | REQ_FUA);
+
+and the driver must handle write requests that have the REQ_FUA bit set
+in prep_fn/request_fn.  If the FUA bit is not natively supported the block
+layer turns it into an empty REQ_FLUSH request after the actual write.

Documentation/cgroups/blkio-controller.txt

@@ -8,12 +8,17 @@ both at leaf nodes as well as at intermediate nodes in a storage hierarchy.
 Plan is to use the same cgroup based management interface for blkio controller
 and based on user options switch IO policies in the background.
 
-In the first phase, this patchset implements proportional weight time based
-division of disk policy. It is implemented in CFQ. Hence this policy takes
-effect only on leaf nodes when CFQ is being used.
+Currently two IO control policies are implemented. First one is proportional
+weight time based division of disk policy. It is implemented in CFQ. Hence
+this policy takes effect only on leaf nodes when CFQ is being used. The second
+one is throttling policy which can be used to specify upper IO rate limits
+on devices. This policy is implemented in generic block layer and can be
+used on leaf nodes as well as higher level logical devices like device mapper.
 
 HOWTO
 =====
+Proportional Weight division of bandwidth
+-----------------------------------------
 You can do a very simple testing of running two dd threads in two different
 cgroups. Here is what you can do.
 
@@ -55,6 +60,35 @@ cgroups. Here is what you can do.
   group dispatched to the disk. We provide fairness in terms of disk time, so
   ideally io.disk_time of cgroups should be in proportion to the weight.
 
+Throttling/Upper Limit policy
+-----------------------------
+- Enable Block IO controller
+	CONFIG_BLK_CGROUP=y
+
+- Enable throttling in block layer
+	CONFIG_BLK_DEV_THROTTLING=y
+
+- Mount blkio controller
+        mount -t cgroup -o blkio none /cgroup/blkio
+
+- Specify a bandwidth rate on particular device for root group. The format
+  for policy is "<major>:<minor>  <byes_per_second>".
+
+        echo "8:16  1048576" > /cgroup/blkio/blkio.read_bps_device
+
+  Above will put a limit of 1MB/second on reads happening for root group
+  on device having major/minor number 8:16.
+
+- 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
+        1024+0 records in
+        1024+0 records out
+        4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s
+
+ Limits for writes can be put using blkio.write_bps_device file.
+
 Various user visible config options
 ===================================
 CONFIG_BLK_CGROUP
@@ -68,8 +102,13 @@ CONFIG_CFQ_GROUP_IOSCHED
 	- Enables group scheduling in CFQ. Currently only 1 level of group
 	  creation is allowed.
 
+CONFIG_BLK_DEV_THROTTLING
+	- Enable block device throttling support in block layer.
+
 Details of cgroup files
 =======================
+Proportional weight policy files
+--------------------------------
 - blkio.weight
 	- Specifies per cgroup weight. This is default weight of the group
 	  on all the devices until and unless overridden by per device rule.
@@ -210,6 +249,67 @@ Details of cgroup files
 	  and minor number of the device and third field specifies the number
 	  of times a group was dequeued from a particular device.
 
+Throttling/Upper limit policy files
+-----------------------------------
+- blkio.throttle.read_bps_device
+	- Specifies upper limit on READ rate from the device. IO rate is
+	  specified in bytes per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.read_bps_device
+
+- blkio.throttle.write_bps_device
+	- Specifies upper limit on WRITE rate to the device. IO rate is
+	  specified in bytes per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.write_bps_device
+
+- blkio.throttle.read_iops_device
+	- Specifies upper limit on READ rate from the device. IO rate is
+	  specified in IO per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.read_iops_device
+
+- blkio.throttle.write_iops_device
+	- Specifies upper limit on WRITE rate to the device. IO rate is
+	  specified in io per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.write_iops_device
+
+Note: If both BW and IOPS rules are specified for a device, then IO is
+      subjectd to both the constraints.
+
+- blkio.throttle.io_serviced
+	- Number of IOs (bio) completed to/from the disk by the group (as
+	  seen by throttling policy). These are further divided by the type
+	  of operation - read or write, sync or async. First two fields specify
+	  the major and minor number of the device, third field specifies the
+	  operation type and the fourth field specifies the number of IOs.
+
+	  blkio.io_serviced does accounting as seen by CFQ and counts are in
+	  number of requests (struct request). On the other hand,
+	  blkio.throttle.io_serviced counts number of IO in terms of number
+	  of bios as seen by throttling policy.  These bios can later be
+	  merged by elevator and total number of requests completed can be
+	  lesser.
+
+- blkio.throttle.io_service_bytes
+	- Number of bytes transferred to/from the disk by the group. These
+	  are further divided by the type of operation - read or write, sync
+	  or async. First two fields specify the major and minor number of the
+	  device, third field specifies the operation type and the fourth field
+	  specifies the number of bytes.
+
+	  These numbers should roughly be same as blkio.io_service_bytes as
+	  updated by CFQ. The difference between two is that
+	  blkio.io_service_bytes will not be updated if CFQ is not operating
+	  on request queue.
+
+Common files among various policies
+-----------------------------------
 - blkio.reset_stats
 	- Writing an int to this file will result in resetting all the stats
 	  for that cgroup.

Documentation/cputopology.txt

@@ -14,25 +14,39 @@ to /proc/cpuinfo.
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+
+	the book ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).	The actual value is
+	architecture and platform dependent.
+
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internel kernel map of cpuX's hardware threads within the same
 	core as cpuX
 
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
+
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").

Documentation/devices.txt

@@ -239,6 +239,7 @@ Your cooperation is appreciated.
 		  0 = /dev/tty		Current TTY device
 		  1 = /dev/console	System console
 		  2 = /dev/ptmx		PTY master multiplex
+		  3 = /dev/ttyprintk	User messages via printk TTY device
 		 64 = /dev/cua0		Callout device for ttyS0
 		    ...
 		255 = /dev/cua191	Callout device for ttyS191
@@ -2553,7 +2554,10 @@ Your cooperation is appreciated.
 		175 = /dev/usb/legousbtower15	16th USB Legotower device
 		176 = /dev/usb/usbtmc1	First USB TMC device
 		   ...
-		192 = /dev/usb/usbtmc16	16th USB TMC device
+		191 = /dev/usb/usbtmc16	16th USB TMC device
+		192 = /dev/usb/yurex1	First USB Yurex device
+		   ...
+		209 = /dev/usb/yurex16	16th USB Yurex device
 		240 = /dev/usb/dabusb0	First daubusb device
 		    ...
 		243 = /dev/usb/dabusb3	Fourth dabusb device

Documentation/dynamic-debug-howto.txt

@@ -24,7 +24,7 @@ Dynamic debug has even more useful features:
    read to display the complete list of known debug statements, to help guide you
 
 Controlling dynamic debug Behaviour
-===============================
+===================================
 
 The behaviour of pr_debug()/dev_debug()s are controlled via writing to a
 control file in the 'debugfs' filesystem. Thus, you must first mount the debugfs
@@ -212,6 +212,26 @@ Note the regexp ^[-+=][scp]+$ matches a flags specification.
 Note also that there is no convenient syntax to remove all
 the flags at once, you need to use "-psc".
 
+
+Debug messages during boot process
+==================================
+
+To be able to activate debug messages during the boot process,
+even before userspace and debugfs exists, use the boot parameter:
+ddebug_query="QUERY"
+
+QUERY follows the syntax described above, but must not exceed 1023
+characters. The enablement of debug messages is done as an arch_initcall.
+Thus you can enable debug messages in all code processed after this
+arch_initcall via this boot parameter.
+On an x86 system for example ACPI enablement is a subsys_initcall and
+ddebug_query="file ec.c +p"
+will show early Embedded Controller transactions during ACPI setup if
+your machine (typically a laptop) has an Embedded Controller.
+PCI (or other devices) initialization also is a hot candidate for using
+this boot parameter for debugging purposes.
+
+
 Examples
 ========
 

Documentation/feature-removal-schedule.txt

@@ -386,34 +386,6 @@ Who:	Tejun Heo <tj@kernel.org>
 
 ----------------------------
 
-What:	Support for VMware's guest paravirtuliazation technique [VMI] will be
-	dropped.
-When:	2.6.37 or earlier.
-Why:	With the recent innovations in CPU hardware acceleration technologies
-	from Intel and AMD, VMware ran a few experiments to compare these
-	techniques to guest paravirtualization technique on VMware's platform.
-	These hardware assisted virtualization techniques have outperformed the
-	performance benefits provided by VMI in most of the workloads. VMware
-	expects that these hardware features will be ubiquitous in a couple of
-	years, as a result, VMware has started a phased retirement of this
-	feature from the hypervisor. We will be removing this feature from the
-	Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
-	technical reasons (read opportunity to remove major chunk of pvops)
-	arise.
-
-	Please note that VMI has always been an optimization and non-VMI kernels
-	still work fine on VMware's platform.
-	Latest versions of VMware's product which support VMI are,
-	Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
-	releases for these products will continue supporting VMI.
-
-	For more details about VMI retirement take a look at this,
-	http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
-
-Who:	Alok N Kataria <akataria@vmware.com>
-
-----------------------------
-
 What:	Support for lcd_switch and display_get in asus-laptop driver
 When:	March 2010
 Why:	These two features use non-standard interfaces. There are the
@@ -564,3 +536,12 @@ Who:	FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
 
 ----------------------------
 
+What:	iwlwifi disable_hw_scan module parameters
+When:	2.6.40
+Why:	Hareware scan is the prefer method for iwlwifi devices for
+	scanning operation. Remove software scan support for all the
+	iwlwifi devices.
+
+Who:	Wey-Yi Guy <wey-yi.w.guy@intel.com>
+
+----------------------------

Documentation/filesystems/ocfs2.txt

@@ -87,3 +87,10 @@ dir_resv_level=	(*)	By default, directory reservations will scale with file
 			reservations - users should rarely need to change this
 			value. If allocation reservations are turned off, this
 			option will have no effect.
+coherency=full  (*)	Disallow concurrent O_DIRECT writes, cluster inode
+			lock will be taken to force other nodes drop cache,
+			therefore full cluster coherency is guaranteed even
+			for O_DIRECT writes.
+coherency=buffered	Allow concurrent O_DIRECT writes without EX lock among
+			nodes, which gains high performance at risk of getting
+			stale data on other nodes.

Documentation/input/ntrig.txt

@@ -0,0 +1,126 @@
+N-Trig touchscreen Driver
+-------------------------
+	Copyright (c) 2008-2010 Rafi Rubin <rafi@seas.upenn.edu>
+	Copyright (c) 2009-2010 Stephane Chatty
+
+This driver provides support for N-Trig pen and multi-touch sensors.  Single
+and multi-touch events are translated to the appropriate protocols for
+the hid and input systems.  Pen events are sufficiently hid compliant and
+are left to the hid core.  The driver also provides additional filtering
+and utility functions accessible with sysfs and module parameters.
+
+This driver has been reported to work properly with multiple N-Trig devices
+attached.
+
+
+Parameters
+----------
+
+Note: values set at load time are global and will apply to all applicable
+devices.  Adjusting parameters with sysfs will override the load time values,
+but only for that one device.
+
+The following parameters are used to configure filters to reduce noise:
+
+activate_slack		number of fingers to ignore before processing events
+
+activation_height	size threshold to activate immediately
+activation_width
+
+min_height		size threshold bellow which fingers are ignored
+min_width		both to decide activation and during activity
+
+deactivate_slack	the number of "no contact" frames to ignore before
+			propagating the end of activity events
+
+When the last finger is removed from the device, it sends a number of empty
+frames.  By holding off on deactivation for a few frames we can tolerate false
+erroneous disconnects, where the sensor may mistakenly not detect a finger that
+is still present.  Thus deactivate_slack addresses problems where a users might
+see breaks in lines during drawing, or drop an object during a long drag.
+
+
+Additional sysfs items
+----------------------
+
+These nodes just provide easy access to the ranges reported by the device.
+sensor_logical_height	the range for positions reported during activity
+sensor_logical_width
+
+sensor_physical_height	internal ranges not used for normal events but
+sensor_physical_width	useful for tuning
+
+All N-Trig devices with product id of 1 report events in the ranges of
+X: 0-9600
+Y: 0-7200
+However not all of these devices have the same physical dimensions.  Most
+seem to be 12" sensors (Dell Latitude XT and XT2 and the HP TX2), and
+at least one model (Dell Studio 17) has a 17" sensor.  The ratio of physical
+to logical sizes is used to adjust the size based filter parameters.
+
+
+Filtering
+---------
+
+With the release of the early multi-touch firmwares it became increasingly
+obvious that these sensors were prone to erroneous events.  Users reported
+seeing both inappropriately dropped contact and ghosts, contacts reported
+where no finger was actually touching the screen.
+
+Deactivation slack helps prevent dropped contact for single touch use, but does
+not address the problem of dropping one of more contacts while other contacts
+are still active.  Drops in the multi-touch context require additional
+processing and should be handled in tandem with tacking.
+
+As observed ghost contacts are similar to actual use of the sensor, but they
+seem to have different profiles.  Ghost activity typically shows up as small
+short lived touches.  As such, I assume that the longer the continuous stream
+of events the more likely those events are from a real contact, and that the
+larger the size of each contact the more likely it is real.  Balancing the
+goals of preventing ghosts and accepting real events quickly (to minimize
+user observable latency), the filter accumulates confidence for incoming
+events until it hits thresholds and begins propagating.  In the interest in
+minimizing stored state as well as the cost of operations to make a decision,
+I've kept that decision simple.
+
+Time is measured in terms of the number of fingers reported, not frames since
+the probability of multiple simultaneous ghosts is expected to drop off
+dramatically with increasing numbers.  Rather than accumulate weight as a
+function of size, I just use it as a binary threshold.  A sufficiently large
+contact immediately overrides the waiting period and leads to activation.
+
+Setting the activation size thresholds to large values will result in deciding
+primarily on activation slack.  If you see longer lived ghosts, turning up the
+activation slack while reducing the size thresholds may suffice to eliminate
+the ghosts while keeping the screen quite responsive to firm taps.
+
+Contacts continue to be filtered with min_height and min_width even after
+the initial activation filter is satisfied.  The intent is to provide
+a mechanism for filtering out ghosts in the form of an extra finger while
+you actually are using the screen.  In practice this sort of ghost has
+been far less problematic or relatively rare and I've left the defaults
+set to 0 for both parameters, effectively turning off that filter.
+
+I don't know what the optimal values are for these filters.  If the defaults
+don't work for you, please play with the parameters.  If you do find other
+values more comfortable, I would appreciate feedback.
+
+The calibration of these devices does drift over time.  If ghosts or contact
+dropping worsen and interfere with the normal usage of your device, try
+recalibrating it.
+
+
+Calibration
+-----------
+
+The N-Trig windows tools provide calibration and testing routines.  Also an
+unofficial unsupported set of user space tools including a calibrator is
+available at:
+http://code.launchpad.net/~rafi-seas/+junk/ntrig_calib
+
+
+Tracking
+--------
+
+As of yet, all tested N-Trig firmwares do not track fingers.  When multiple
+contacts are active they seem to be sorted primarily by Y position.

Documentation/kernel-parameters.txt

@@ -43,10 +43,11 @@ parameter is applicable:
 	AVR32	AVR32 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	BLACKFIN Blackfin architecture is enabled.
-	DRM	Direct Rendering Management support is enabled.
 	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
 	EFI	EFI Partitioning (GPT) is enabled
 	EIDE	EIDE/ATAPI support is enabled.
+	DRM	Direct Rendering Management support is enabled.
+	DYNAMIC_DEBUG Build in debug messages and enable them at runtime
 	FB	The frame buffer device is enabled.
 	GCOV	GCOV profiling is enabled.
 	HW	Appropriate hardware is enabled.
@@ -455,7 +456,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			[ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
 				pxa_timer,timer3,32k_counter,timer0_1
 			[AVR32] avr32
-			[X86-32] pit,hpet,tsc,vmi-timer;
+			[X86-32] pit,hpet,tsc;
 				scx200_hrt on Geode; cyclone on IBM x440
 			[MIPS] MIPS
 			[PARISC] cr16
@@ -570,6 +571,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format: <port#>,<type>
 			See also Documentation/input/joystick-parport.txt
 
+	ddebug_query=   [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
+			time. See Documentation/dynamic-debug-howto.txt for
+			details.
+
 	debug		[KNL] Enable kernel debugging (events log level).
 
 	debug_locks_verbose=
@@ -1126,9 +1131,13 @@ and is between 256 and 4096 characters. It is defined in the file
 	kvm.oos_shadow=	[KVM] Disable out-of-sync shadow paging.
 			Default is 1 (enabled)
 
-	kvm-amd.nested=	[KVM,AMD] Allow nested virtualization in KVM/SVM.
+	kvm.mmu_audit=	[KVM] This is a R/W parameter which allows audit
+			KVM MMU at runtime.
 			Default is 0 (off)
 
+	kvm-amd.nested=	[KVM,AMD] Allow nested virtualization in KVM/SVM.
+			Default is 1 (enabled)
+
 	kvm-amd.npt=	[KVM,AMD] Disable nested paging (virtualized MMU)
 			for all guests.
 			Default is 1 (enabled) if in 64bit or 32bit-PAE mode
@@ -1693,6 +1702,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nojitter	[IA64] Disables jitter checking for ITC timers.
 
+	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
+
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
@@ -1713,7 +1724,7 @@ and is between 256 and 4096 characters. It is defined in the file
 	norandmaps	Don't use address space randomization.  Equivalent to
 			echo 0 > /proc/sys/kernel/randomize_va_space
 
-	noreplace-paravirt	[X86-32,PV_OPS] Don't patch paravirt_ops
+	noreplace-paravirt	[X86,IA-64,PV_OPS] Don't patch paravirt_ops
 
 	noreplace-smp	[X86-32,SMP] Don't replace SMP instructions
 			with UP alternatives
@@ -2153,6 +2164,11 @@ and is between 256 and 4096 characters. It is defined in the file
 			Reserves a hole at the top of the kernel virtual
 			address space.
 
+	reservelow=	[X86]
+			Format: nn[K]
+			Set the amount of memory to reserve for BIOS at
+			the bottom of the address space.
+
 	reset_devices	[KNL] Force drivers to reset the underlying device
 			during initialization.
 
@@ -2165,6 +2181,11 @@ and is between 256 and 4096 characters. It is defined in the file
 			in <PAGE_SIZE> units (needed only for swap files).
 			See  Documentation/power/swsusp-and-swap-files.txt
 
+	hibernate=	[HIBERNATION]
+		noresume	Don't check if there's a hibernation image
+				present during boot.
+		nocompress	Don't compress/decompress hibernation images.
+
 	retain_initrd	[RAM] Keep initrd memory after extraction
 
 	rhash_entries=	[KNL,NET]
@@ -2360,6 +2381,15 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	switches=	[HW,M68k]
 
+	sysfs.deprecated=0|1 [KNL]
+			Enable/disable old style sysfs layout for old udev
+			on older distributions. When this option is enabled
+			very new udev will not work anymore. When this option
+			is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
+			in older udev will not work anymore.
+			Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
+			the kernel configuration.
+
 	sysrq_always_enabled
 			[KNL]
 			Ignore sysrq setting - this boot parameter will
@@ -2435,6 +2465,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			disables clocksource verification at runtime.
 			Used to enable high-resolution timer mode on older
 			hardware, and in virtualized environment.
+			[x86] noirqtime: Do not use TSC to do irq accounting.
+			Used to run time disable IRQ_TIME_ACCOUNTING on any
+			platforms where RDTSC is slow and this accounting
+			can add overhead.
 
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface

Documentation/kprobes.txt

@@ -542,9 +542,11 @@ Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
 Probe handlers are run with preemption disabled.  Depending on the
-architecture, handlers may also run with interrupts disabled.  In any
-case, your handler should not yield the CPU (e.g., by attempting to
-acquire a semaphore).
+architecture and optimization state, handlers may also run with
+interrupts disabled (e.g., kretprobe handlers and optimized kprobe
+handlers run without interrupt disabled on x86/x86-64).  In any case,
+your handler should not yield the CPU (e.g., by attempting to acquire
+a semaphore).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls

Documentation/kvm/api.txt

@@ -320,13 +320,13 @@ struct kvm_translation {
 4.15 KVM_INTERRUPT
 
 Capability: basic
-Architectures: x86
+Architectures: x86, ppc
 Type: vcpu ioctl
 Parameters: struct kvm_interrupt (in)
 Returns: 0 on success, -1 on error
 
 Queues a hardware interrupt vector to be injected.  This is only
-useful if in-kernel local APIC is not used.
+useful if in-kernel local APIC or equivalent is not used.
 
 /* for KVM_INTERRUPT */
 struct kvm_interrupt {
@@ -334,8 +334,37 @@ struct kvm_interrupt {
 	__u32 irq;
 };
 
+X86:
+
 Note 'irq' is an interrupt vector, not an interrupt pin or line.
 
+PPC:
+
+Queues an external interrupt to be injected. This ioctl is overleaded
+with 3 different irq values:
+
+a) KVM_INTERRUPT_SET
+
+  This injects an edge type external interrupt into the guest once it's ready
+  to receive interrupts. When injected, the interrupt is done.
+
+b) KVM_INTERRUPT_UNSET
+
+  This unsets any pending interrupt.
+
+  Only available with KVM_CAP_PPC_UNSET_IRQ.
+
+c) KVM_INTERRUPT_SET_LEVEL
+
+  This injects a level type external interrupt into the guest context. The
+  interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
+  is triggered.
+
+  Only available with KVM_CAP_PPC_IRQ_LEVEL.
+
+Note that any value for 'irq' other than the ones stated above is invalid
+and incurs unexpected behavior.
+
 4.16 KVM_DEBUG_GUEST
 
 Capability: basic
@@ -1013,8 +1042,9 @@ number is just right, the 'nent' field is adjusted to the number of valid
 entries in the 'entries' array, which is then filled.
 
 The entries returned are the host cpuid as returned by the cpuid instruction,
-with unknown or unsupported features masked out.  The fields in each entry
-are defined as follows:
+with unknown or unsupported features masked out.  Some features (for example,
+x2apic), may not be present in the host cpu, but are exposed by kvm if it can
+emulate them efficiently. The fields in each entry are defined as follows:
 
   function: the eax value used to obtain the entry
   index: the ecx value used to obtain the entry (for entries that are
@@ -1032,6 +1062,29 @@ are defined as follows:
    eax, ebx, ecx, edx: the values returned by the cpuid instruction for
          this function/index combination
 
+4.46 KVM_PPC_GET_PVINFO
+
+Capability: KVM_CAP_PPC_GET_PVINFO
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_ppc_pvinfo (out)
+Returns: 0 on success, !0 on error
+
+struct kvm_ppc_pvinfo {
+	__u32 flags;
+	__u32 hcall[4];
+	__u8  pad[108];
+};
+
+This ioctl fetches PV specific information that need to be passed to the guest
+using the device tree or other means from vm context.
+
+For now the only implemented piece of information distributed here is an array
+of 4 instructions that make up a hypercall.
+
+If any additional field gets added to this structure later on, a bit for that
+additional piece of information will be set in the flags bitmap.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by

Documentation/kvm/ppc-pv.txt

@@ -0,0 +1,196 @@
+The PPC KVM paravirtual interface
+=================================
+
+The basic execution principle by which KVM on PowerPC works is to run all kernel
+space code in PR=1 which is user space. This way we trap all privileged
+instructions and can emulate them accordingly.
+
+Unfortunately that is also the downfall. There are quite some privileged
+instructions that needlessly return us to the hypervisor even though they
+could be handled differently.
+
+This is what the PPC PV interface helps with. It takes privileged instructions
+and transforms them into unprivileged ones with some help from the hypervisor.
+This cuts down virtualization costs by about 50% on some of my benchmarks.
+
+The code for that interface can be found in arch/powerpc/kernel/kvm*
+
+Querying for existence
+======================
+
+To find out if we're running on KVM or not, we leverage the device tree. When
+Linux is running on KVM, a node /hypervisor exists. That node contains a
+compatible property with the value "linux,kvm".
+
+Once you determined you're running under a PV capable KVM, you can now use
+hypercalls as described below.
+
+KVM hypercalls
+==============
+
+Inside the device tree's /hypervisor node there's a property called
+'hypercall-instructions'. This property contains at most 4 opcodes that make
+up the hypercall. To call a hypercall, just call these instructions.
+
+The parameters are as follows:
+
+	Register	IN			OUT
+
+	r0		-			volatile
+	r3		1st parameter		Return code
+	r4		2nd parameter		1st output value
+	r5		3rd parameter		2nd output value
+	r6		4th parameter		3rd output value
+	r7		5th parameter		4th output value
+	r8		6th parameter		5th output value
+	r9		7th parameter		6th output value
+	r10		8th parameter		7th output value
+	r11		hypercall number	8th output value
+	r12		-			volatile
+
+Hypercall definitions are shared in generic code, so the same hypercall numbers
+apply for x86 and powerpc alike with the exception that each KVM hypercall
+also needs to be ORed with the KVM vendor code which is (42 << 16).
+
+Return codes can be as follows:
+
+	Code		Meaning
+
+	0		Success
+	12		Hypercall not implemented
+	<0		Error
+
+The magic page
+==============
+
+To enable communication between the hypervisor and guest there is a new shared
+page that contains parts of supervisor visible register state. The guest can
+map this shared page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE.
+
+With this hypercall issued the guest always gets the magic page mapped at the
+desired location in effective and physical address space. For now, we always
+map the page to -4096. This way we can access it using absolute load and store
+functions. The following instruction reads the first field of the magic page:
+
+	ld	rX, -4096(0)
+
+The interface is designed to be extensible should there be need later to add
+additional registers to the magic page. If you add fields to the magic page,
+also define a new hypercall feature to indicate that the host can give you more
+registers. Only if the host supports the additional features, make use of them.
+
+The magic page has the following layout as described in
+arch/powerpc/include/asm/kvm_para.h:
+
+struct kvm_vcpu_arch_shared {
+	__u64 scratch1;
+	__u64 scratch2;
+	__u64 scratch3;
+	__u64 critical;		/* Guest may not get interrupts if == r1 */
+	__u64 sprg0;
+	__u64 sprg1;
+	__u64 sprg2;
+	__u64 sprg3;
+	__u64 srr0;
+	__u64 srr1;
+	__u64 dar;
+	__u64 msr;
+	__u32 dsisr;
+	__u32 int_pending;	/* Tells the guest if we have an interrupt */
+};
+
+Additions to the page must only occur at the end. Struct fields are always 32
+or 64 bit aligned, depending on them being 32 or 64 bit wide respectively.
+
+Magic page features
+===================
+
+When mapping the magic page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE,
+a second return value is passed to the guest. This second return value contains
+a bitmap of available features inside the magic page.
+
+The following enhancements to the magic page are currently available:
+
+  KVM_MAGIC_FEAT_SR		Maps SR registers r/w in the magic page
+
+For enhanced features in the magic page, please check for the existence of the
+feature before using them!
+
+MSR bits
+========
+
+The MSR contains bits that require hypervisor intervention and bits that do
+not require direct hypervisor intervention because they only get interpreted
+when entering the guest or don't have any impact on the hypervisor's behavior.
+
+The following bits are safe to be set inside the guest:
+
+  MSR_EE
+  MSR_RI
+  MSR_CR
+  MSR_ME
+
+If any other bit changes in the MSR, please still use mtmsr(d).
+
+Patched instructions
+====================
+
+The "ld" and "std" instructions are transormed to "lwz" and "stw" instructions
+respectively on 32 bit systems with an added offset of 4 to accomodate for big
+endianness.
+
+The following is a list of mapping the Linux kernel performs when running as
+guest. Implementing any of those mappings is optional, as the instruction traps
+also act on the shared page. So calling privileged instructions still works as
+before.
+
+From			To
+====			==
+
+mfmsr	rX		ld	rX, magic_page->msr
+mfsprg	rX, 0		ld	rX, magic_page->sprg0
+mfsprg	rX, 1		ld	rX, magic_page->sprg1
+mfsprg	rX, 2		ld	rX, magic_page->sprg2
+mfsprg	rX, 3		ld	rX, magic_page->sprg3
+mfsrr0	rX		ld	rX, magic_page->srr0
+mfsrr1	rX		ld	rX, magic_page->srr1
+mfdar	rX		ld	rX, magic_page->dar
+mfdsisr	rX		lwz	rX, magic_page->dsisr
+
+mtmsr	rX		std	rX, magic_page->msr
+mtsprg	0, rX		std	rX, magic_page->sprg0
+mtsprg	1, rX		std	rX, magic_page->sprg1
+mtsprg	2, rX		std	rX, magic_page->sprg2
+mtsprg	3, rX		std	rX, magic_page->sprg3
+mtsrr0	rX		std	rX, magic_page->srr0
+mtsrr1	rX		std	rX, magic_page->srr1
+mtdar	rX		std	rX, magic_page->dar
+mtdsisr	rX		stw	rX, magic_page->dsisr
+
+tlbsync			nop
+
+mtmsrd	rX, 0		b	<special mtmsr section>
+mtmsr	rX		b	<special mtmsr section>
+
+mtmsrd	rX, 1		b	<special mtmsrd section>
+
+[Book3S only]
+mtsrin	rX, rY		b	<special mtsrin section>
+
+[BookE only]
+wrteei	[0|1]		b	<special wrteei section>
+
+
+Some instructions require more logic to determine what's going on than a load
+or store instruction can deliver. To enable patching of those, we keep some
+RAM around where we can live translate instructions to. What happens is the
+following:
+
+	1) copy emulation code to memory
+	2) patch that code to fit the emulated instruction
+	3) patch that code to return to the original pc + 4
+	4) patch the original instruction to branch to the new code
+
+That way we can inject an arbitrary amount of code as replacement for a single
+instruction. This allows us to check for pending interrupts when setting EE=1
+for example.

Documentation/kvm/timekeeping.txt

@@ -0,0 +1,612 @@
+
+	Timekeeping Virtualization for X86-Based Architectures
+
+	Zachary Amsden <zamsden@redhat.com>
+	Copyright (c) 2010, Red Hat.  All rights reserved.
+
+1) Overview
+2) Timing Devices
+3) TSC Hardware
+4) Virtualization Problems
+
+=========================================================================
+
+1) Overview
+
+One of the most complicated parts of the X86 platform, and specifically,
+the virtualization of this platform is the plethora of timing devices available
+and the complexity of emulating those devices.  In addition, virtualization of
+time introduces a new set of challenges because it introduces a multiplexed
+division of time beyond the control of the guest CPU.
+
+First, we will describe the various timekeeping hardware available, then
+present some of the problems which arise and solutions available, giving
+specific recommendations for certain classes of KVM guests.
+
+The purpose of this document is to collect data and information relevant to
+timekeeping which may be difficult to find elsewhere, specifically,
+information relevant to KVM and hardware-based virtualization.
+
+=========================================================================
+
+2) Timing Devices
+
+First we discuss the basic hardware devices available.  TSC and the related
+KVM clock are special enough to warrant a full exposition and are described in
+the following section.
+
+2.1) i8254 - PIT
+
+One of the first timer devices available is the programmable interrupt timer,
+or PIT.  The PIT has a fixed frequency 1.193182 MHz base clock and three
+channels which can be programmed to deliver periodic or one-shot interrupts.
+These three channels can be configured in different modes and have individual
+counters.  Channel 1 and 2 were not available for general use in the original
+IBM PC, and historically were connected to control RAM refresh and the PC
+speaker.  Now the PIT is typically integrated as part of an emulated chipset
+and a separate physical PIT is not used.
+
+The PIT uses I/O ports 0x40 - 0x43.  Access to the 16-bit counters is done
+using single or multiple byte access to the I/O ports.  There are 6 modes
+available, but not all modes are available to all timers, as only timer 2
+has a connected gate input, required for modes 1 and 5.  The gate line is
+controlled by port 61h, bit 0, as illustrated in the following diagram.
+
+ --------------             ----------------
+|              |           |                |
+|  1.1932 MHz  |---------->| CLOCK      OUT | ---------> IRQ 0
+|    Clock     |   |       |                |
+ --------------    |    +->| GATE  TIMER 0  |
+                   |        ----------------
+                   |
+                   |        ----------------
+                   |       |                |
+                   |------>| CLOCK      OUT | ---------> 66.3 KHZ DRAM
+                   |       |                |            (aka /dev/null)
+                   |    +->| GATE  TIMER 1  |
+                   |        ----------------
+                   |
+                   |        ----------------
+                   |       |                |
+                   |------>| CLOCK      OUT | ---------> Port 61h, bit 5
+                           |                |      |
+Port 61h, bit 0 ---------->| GATE  TIMER 2  |       \_.----   ____
+                            ----------------         _|    )--|LPF|---Speaker
+                                                    / *----   \___/
+Port 61h, bit 1 -----------------------------------/
+
+The timer modes are now described.
+
+Mode 0: Single Timeout.   This is a one-shot software timeout that counts down
+ when the gate is high (always true for timers 0 and 1).  When the count
+ reaches zero, the output goes high.
+
+Mode 1: Triggered One-shot.  The output is intially set high.  When the gate
+ line is set high, a countdown is initiated (which does not stop if the gate is
+ lowered), during which the output is set low.  When the count reaches zero,
+ the output goes high.
+
+Mode 2: Rate Generator.  The output is initially set high.  When the countdown
+ reaches 1, the output goes low for one count and then returns high.  The value
+ is reloaded and the countdown automatically resumes.  If the gate line goes
+ low, the count is halted.  If the output is low when the gate is lowered, the
+ output automatically goes high (this only affects timer 2).
+
+Mode 3: Square Wave.   This generates a high / low square wave.  The count
+ determines the length of the pulse, which alternates between high and low
+ when zero is reached.  The count only proceeds when gate is high and is
+ automatically reloaded on reaching zero.  The count is decremented twice at
+ each clock to generate a full high / low cycle at the full periodic rate.
+ If the count is even, the clock remains high for N/2 counts and low for N/2
+ counts; if the clock is odd, the clock is high for (N+1)/2 counts and low
+ for (N-1)/2 counts.  Only even values are latched by the counter, so odd
+ values are not observed when reading.  This is the intended mode for timer 2,
+ which generates sine-like tones by low-pass filtering the square wave output.
+
+Mode 4: Software Strobe.  After programming this mode and loading the counter,
+ the output remains high until the counter reaches zero.  Then the output
+ goes low for 1 clock cycle and returns high.  The counter is not reloaded.
+ Counting only occurs when gate is high.
+
+Mode 5: Hardware Strobe.  After programming and loading the counter, the
+ output remains high.  When the gate is raised, a countdown is initiated
+ (which does not stop if the gate is lowered).  When the counter reaches zero,
+ the output goes low for 1 clock cycle and then returns high.  The counter is
+ not reloaded.
+
+In addition to normal binary counting, the PIT supports BCD counting.  The
+command port, 0x43 is used to set the counter and mode for each of the three
+timers.
+
+PIT commands, issued to port 0x43, using the following bit encoding:
+
+Bit 7-4: Command (See table below)
+Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined)
+Bit 0  : Binary (0) / BCD (1)
+
+Command table:
+
+0000 - Latch Timer 0 count for port 0x40
+	sample and hold the count to be read in port 0x40;
+	additional commands ignored until counter is read;
+	mode bits ignored.
+
+0001 - Set Timer 0 LSB mode for port 0x40
+	set timer to read LSB only and force MSB to zero;
+	mode bits set timer mode
+
+0010 - Set Timer 0 MSB mode for port 0x40
+	set timer to read MSB only and force LSB to zero;
+	mode bits set timer mode
+
+0011 - Set Timer 0 16-bit mode for port 0x40
+	set timer to read / write LSB first, then MSB;
+	mode bits set timer mode
+
+0100 - Latch Timer 1 count for port 0x41 - as described above
+0101 - Set Timer 1 LSB mode for port 0x41 - as described above
+0110 - Set Timer 1 MSB mode for port 0x41 - as described above
+0111 - Set Timer 1 16-bit mode for port 0x41 - as described above
+
+1000 - Latch Timer 2 count for port 0x42 - as described above
+1001 - Set Timer 2 LSB mode for port 0x42 - as described above
+1010 - Set Timer 2 MSB mode for port 0x42 - as described above
+1011 - Set Timer 2 16-bit mode for port 0x42 as described above
+
+1101 - General counter latch
+	Latch combination of counters into corresponding ports
+	Bit 3 = Counter 2
+	Bit 2 = Counter 1
+	Bit 1 = Counter 0
+	Bit 0 = Unused
+
+1110 - Latch timer status
+	Latch combination of counter mode into corresponding ports
+	Bit 3 = Counter 2
+	Bit 2 = Counter 1
+	Bit 1 = Counter 0
+
+	The output of ports 0x40-0x42 following this command will be:
+
+	Bit 7 = Output pin
+	Bit 6 = Count loaded (0 if timer has expired)
+	Bit 5-4 = Read / Write mode
+	    01 = MSB only
+	    10 = LSB only
+	    11 = LSB / MSB (16-bit)
+	Bit 3-1 = Mode
+	Bit 0 = Binary (0) / BCD mode (1)
+
+2.2) RTC
+
+The second device which was available in the original PC was the MC146818 real
+time clock.  The original device is now obsolete, and usually emulated by the
+system chipset, sometimes by an HPET and some frankenstein IRQ routing.
+
+The RTC is accessed through CMOS variables, which uses an index register to
+control which bytes are read.  Since there is only one index register, read
+of the CMOS and read of the RTC require lock protection (in addition, it is
+dangerous to allow userspace utilities such as hwclock to have direct RTC
+access, as they could corrupt kernel reads and writes of CMOS memory).
+
+The RTC generates an interrupt which is usually routed to IRQ 8.  The interrupt
+can function as a periodic timer, an additional once a day alarm, and can issue
+interrupts after an update of the CMOS registers by the MC146818 is complete.
+The type of interrupt is signalled in the RTC status registers.
+
+The RTC will update the current time fields by battery power even while the
+system is off.  The current time fields should not be read while an update is
+in progress, as indicated in the status register.
+
+The clock uses a 32.768kHz crystal, so bits 6-4 of register A should be
+programmed to a 32kHz divider if the RTC is to count seconds.
+
+This is the RAM map originally used for the RTC/CMOS:
+
+Location    Size    Description
+------------------------------------------
+00h         byte    Current second (BCD)
+01h         byte    Seconds alarm (BCD)
+02h         byte    Current minute (BCD)
+03h         byte    Minutes alarm (BCD)
+04h         byte    Current hour (BCD)
+05h         byte    Hours alarm (BCD)
+06h         byte    Current day of week (BCD)
+07h         byte    Current day of month (BCD)
+08h         byte    Current month (BCD)
+09h         byte    Current year (BCD)
+0Ah         byte    Register A
+                       bit 7   = Update in progress
+                       bit 6-4 = Divider for clock
+                                  000 = 4.194 MHz
+                                  001 = 1.049 MHz
+                                  010 = 32 kHz
+                                  10X = test modes
+                                  110 = reset / disable
+                                  111 = reset / disable
+                       bit 3-0 = Rate selection for periodic interrupt
+                                  000 = periodic timer disabled
+                                  001 = 3.90625 uS
+                                  010 = 7.8125 uS
+                                  011 = .122070 mS
+                                  100 = .244141 mS
+                                     ...
+                                 1101 = 125 mS
+                                 1110 = 250 mS
+                                 1111 = 500 mS
+0Bh         byte    Register B
+                       bit 7   = Run (0) / Halt (1)
+                       bit 6   = Periodic interrupt enable
+                       bit 5   = Alarm interrupt enable
+                       bit 4   = Update-ended interrupt enable
+                       bit 3   = Square wave interrupt enable
+                       bit 2   = BCD calendar (0) / Binary (1)
+                       bit 1   = 12-hour mode (0) / 24-hour mode (1)
+                       bit 0   = 0 (DST off) / 1 (DST enabled)
+OCh         byte    Register C (read only)
+                       bit 7   = interrupt request flag (IRQF)
+                       bit 6   = periodic interrupt flag (PF)
+                       bit 5   = alarm interrupt flag (AF)
+                       bit 4   = update interrupt flag (UF)
+                       bit 3-0 = reserved
+ODh         byte    Register D (read only)
+                       bit 7   = RTC has power
+                       bit 6-0 = reserved
+32h         byte    Current century BCD (*)
+  (*) location vendor specific and now determined from ACPI global tables
+
+2.3) APIC
+
+On Pentium and later processors, an on-board timer is available to each CPU
+as part of the Advanced Programmable Interrupt Controller.  The APIC is
+accessed through memory-mapped registers and provides interrupt service to each
+CPU, used for IPIs and local timer interrupts.
+
+Although in theory the APIC is a safe and stable source for local interrupts,
+in practice, many bugs and glitches have occurred due to the special nature of
+the APIC CPU-local memory-mapped hardware.  Beware that CPU errata may affect
+the use of the APIC and that workarounds may be required.  In addition, some of
+these workarounds pose unique constraints for virtualization - requiring either
+extra overhead incurred from extra reads of memory-mapped I/O or additional
+functionality that may be more computationally expensive to implement.
+
+Since the APIC is documented quite well in the Intel and AMD manuals, we will
+avoid repetition of the detail here.  It should be pointed out that the APIC
+timer is programmed through the LVT (local vector timer) register, is capable
+of one-shot or periodic operation, and is based on the bus clock divided down
+by the programmable divider register.
+
+2.4) HPET
+
+HPET is quite complex, and was originally intended to replace the PIT / RTC
+support of the X86 PC.  It remains to be seen whether that will be the case, as
+the de facto standard of PC hardware is to emulate these older devices.  Some
+systems designated as legacy free may support only the HPET as a hardware timer
+device.
+
+The HPET spec is rather loose and vague, requiring at least 3 hardware timers,
+but allowing implementation freedom to support many more.  It also imposes no
+fixed rate on the timer frequency, but does impose some extremal values on
+frequency, error and slew.
+
+In general, the HPET is recommended as a high precision (compared to PIT /RTC)
+time source which is independent of local variation (as there is only one HPET
+in any given system).  The HPET is also memory-mapped, and its presence is
+indicated through ACPI tables by the BIOS.
+
+Detailed specification of the HPET is beyond the current scope of this
+document, as it is also very well documented elsewhere.
+
+2.5) Offboard Timers
+
+Several cards, both proprietary (watchdog boards) and commonplace (e1000) have
+timing chips built into the cards which may have registers which are accessible
+to kernel or user drivers.  To the author's knowledge, using these to generate
+a clocksource for a Linux or other kernel has not yet been attempted and is in
+general frowned upon as not playing by the agreed rules of the game.  Such a
+timer device would require additional support to be virtualized properly and is
+not considered important at this time as no known operating system does this.
+
+=========================================================================
+
+3) TSC Hardware
+
+The TSC or time stamp counter is relatively simple in theory; it counts
+instruction cycles issued by the processor, which can be used as a measure of
+time.  In practice, due to a number of problems, it is the most complicated
+timekeeping device to use.
+
+The TSC is represented internally as a 64-bit MSR which can be read with the
+RDMSR, RDTSC, or RDTSCP (when available) instructions.  In the past, hardware
+limitations made it possible to write the TSC, but generally on old hardware it
+was only possible to write the low 32-bits of the 64-bit counter, and the upper
+32-bits of the counter were cleared.  Now, however, on Intel processors family
+0Fh, for models 3, 4 and 6, and family 06h, models e and f, this restriction
+has been lifted and all 64-bits are writable.  On AMD systems, the ability to
+write the TSC MSR is not an architectural guarantee.
+
+The TSC is accessible from CPL-0 and conditionally, for CPL > 0 software by
+means of the CR4.TSD bit, which when enabled, disables CPL > 0 TSC access.
+
+Some vendors have implemented an additional instruction, RDTSCP, which returns
+atomically not just the TSC, but an indicator which corresponds to the
+processor number.  This can be used to index into an array of TSC variables to
+determine offset information in SMP systems where TSCs are not synchronized.
+The presence of this instruction must be determined by consulting CPUID feature
+bits.
+
+Both VMX and SVM provide extension fields in the virtualization hardware which
+allows the guest visible TSC to be offset by a constant.  Newer implementations
+promise to allow the TSC to additionally be scaled, but this hardware is not
+yet widely available.
+
+3.1) TSC synchronization
+
+The TSC is a CPU-local clock in most implementations.  This means, on SMP
+platforms, the TSCs of different CPUs may start at different times depending
+on when the CPUs are powered on.  Generally, CPUs on the same die will share
+the same clock, however, this is not always the case.
+
+The BIOS may attempt to resynchronize the TSCs during the poweron process and
+the operating system or other system software may attempt to do this as well.
+Several hardware limitations make the problem worse - if it is not possible to
+write the full 64-bits of the TSC, it may be impossible to match the TSC in
+newly arriving CPUs to that of the rest of the system, resulting in
+unsynchronized TSCs.  This may be done by BIOS or system software, but in
+practice, getting a perfectly synchronized TSC will not be possible unless all
+values are read from the same clock, which generally only is possible on single
+socket systems or those with special hardware support.
+
+3.2) TSC and CPU hotplug
+
+As touched on already, CPUs which arrive later than the boot time of the system
+may not have a TSC value that is synchronized with the rest of the system.
+Either system software, BIOS, or SMM code may actually try to establish the TSC
+to a value matching the rest of the system, but a perfect match is usually not
+a guarantee.  This can have the effect of bringing a system from a state where
+TSC is synchronized back to a state where TSC synchronization flaws, however
+small, may be exposed to the OS and any virtualization environment.
+
+3.3) TSC and multi-socket / NUMA
+
+Multi-socket systems, especially large multi-socket systems are likely to have
+individual clocksources rather than a single, universally distributed clock.
+Since these clocks are driven by different crystals, they will not have
+perfectly matched frequency, and temperature and electrical variations will
+cause the CPU clocks, and thus the TSCs to drift over time.  Depending on the
+exact clock and bus design, the drift may or may not be fixed in absolute
+error, and may accumulate over time.
+
+In addition, very large systems may deliberately slew the clocks of individual
+cores.  This technique, known as spread-spectrum clocking, reduces EMI at the
+clock frequency and harmonics of it, which may be required to pass FCC
+standards for telecommunications and computer equipment.
+
+It is recommended not to trust the TSCs to remain synchronized on NUMA or
+multiple socket systems for these reasons.
+
+3.4) TSC and C-states
+
+C-states, or idling states of the processor, especially C1E and deeper sleep
+states may be problematic for TSC as well.  The TSC may stop advancing in such
+a state, resulting in a TSC which is behind that of other CPUs when execution
+is resumed.  Such CPUs must be detected and flagged by the operating system
+based on CPU and chipset identifications.
+
+The TSC in such a case may be corrected by catching it up to a known external
+clocksource.
+
+3.5) TSC frequency change / P-states
+
+To make things slightly more interesting, some CPUs may change frequency.  They
+may or may not run the TSC at the same rate, and because the frequency change
+may be staggered or slewed, at some points in time, the TSC rate may not be
+known other than falling within a range of values.  In this case, the TSC will
+not be a stable time source, and must be calibrated against a known, stable,
+external clock to be a usable source of time.
+
+Whether the TSC runs at a constant rate or scales with the P-state is model
+dependent and must be determined by inspecting CPUID, chipset or vendor
+specific MSR fields.
+
+In addition, some vendors have known bugs where the P-state is actually
+compensated for properly during normal operation, but when the processor is
+inactive, the P-state may be raised temporarily to service cache misses from
+other processors.  In such cases, the TSC on halted CPUs could advance faster
+than that of non-halted processors.  AMD Turion processors are known to have
+this problem.
+
+3.6) TSC and STPCLK / T-states
+
+External signals given to the processor may also have the effect of stopping
+the TSC.  This is typically done for thermal emergency power control to prevent
+an overheating condition, and typically, there is no way to detect that this
+condition has happened.
+
+3.7) TSC virtualization - VMX
+
+VMX provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
+instructions, which is enough for full virtualization of TSC in any manner.  In
+addition, VMX allows passing through the host TSC plus an additional TSC_OFFSET
+field specified in the VMCS.  Special instructions must be used to read and
+write the VMCS field.
+
+3.8) TSC virtualization - SVM
+
+SVM provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
+instructions, which is enough for full virtualization of TSC in any manner.  In
+addition, SVM allows passing through the host TSC plus an additional offset
+field specified in the SVM control block.
+
+3.9) TSC feature bits in Linux
+
+In summary, there is no way to guarantee the TSC remains in perfect
+synchronization unless it is explicitly guaranteed by the architecture.  Even
+if so, the TSCs in multi-sockets or NUMA systems may still run independently
+despite being locally consistent.
+
+The following feature bits are used by Linux to signal various TSC attributes,
+but they can only be taken to be meaningful for UP or single node systems.
+
+X86_FEATURE_TSC 		: The TSC is available in hardware
+X86_FEATURE_RDTSCP		: The RDTSCP instruction is available
+X86_FEATURE_CONSTANT_TSC 	: The TSC rate is unchanged with P-states
+X86_FEATURE_NONSTOP_TSC		: The TSC does not stop in C-states
+X86_FEATURE_TSC_RELIABLE	: TSC sync checks are skipped (VMware)
+
+4) Virtualization Problems
+
+Timekeeping is especially problematic for virtualization because a number of
+challenges arise.  The most obvious problem is that time is now shared between
+the host and, potentially, a number of virtual machines.  Thus the virtual
+operating system does not run with 100% usage of the CPU, despite the fact that
+it may very well make that assumption.  It may expect it to remain true to very
+exacting bounds when interrupt sources are disabled, but in reality only its
+virtual interrupt sources are disabled, and the machine may still be preempted
+at any time.  This causes problems as the passage of real time, the injection
+of machine interrupts and the associated clock sources are no longer completely
+synchronized with real time.
+
+This same problem can occur on native harware to a degree, as SMM mode may
+steal cycles from the naturally on X86 systems when SMM mode is used by the
+BIOS, but not in such an extreme fashion.  However, the fact that SMM mode may
+cause similar problems to virtualization makes it a good justification for
+solving many of these problems on bare metal.
+
+4.1) Interrupt clocking
+
+One of the most immediate problems that occurs with legacy operating systems
+is that the system timekeeping routines are often designed to keep track of
+time by counting periodic interrupts.  These interrupts may come from the PIT
+or the RTC, but the problem is the same: the host virtualization engine may not
+be able to deliver the proper number of interrupts per second, and so guest
+time may fall behind.  This is especially problematic if a high interrupt rate
+is selected, such as 1000 HZ, which is unfortunately the default for many Linux
+guests.
+
+There are three approaches to solving this problem; first, it may be possible
+to simply ignore it.  Guests which have a separate time source for tracking
+'wall clock' or 'real time' may not need any adjustment of their interrupts to
+maintain proper time.  If this is not sufficient, it may be necessary to inject
+additional interrupts into the guest in order to increase the effective
+interrupt rate.  This approach leads to complications in extreme conditions,
+where host load or guest lag is too much to compensate for, and thus another
+solution to the problem has risen: the guest may need to become aware of lost
+ticks and compensate for them internally.  Although promising in theory, the
+implementation of this policy in Linux has been extremely error prone, and a
+number of buggy variants of lost tick compensation are distributed across
+commonly used Linux systems.
+
+Windows uses periodic RTC clocking as a means of keeping time internally, and
+thus requires interrupt slewing to keep proper time.  It does use a low enough
+rate (ed: is it 18.2 Hz?) however that it has not yet been a problem in
+practice.
+
+4.2) TSC sampling and serialization
+
+As the highest precision time source available, the cycle counter of the CPU
+has aroused much interest from developers.  As explained above, this timer has
+many problems unique to its nature as a local, potentially unstable and
+potentially unsynchronized source.  One issue which is not unique to the TSC,
+but is highlighted because of its very precise nature is sampling delay.  By
+definition, the counter, once read is already old.  However, it is also
+possible for the counter to be read ahead of the actual use of the result.
+This is a consequence of the superscalar execution of the instruction stream,
+which may execute instructions out of order.  Such execution is called
+non-serialized.  Forcing serialized execution is necessary for precise
+measurement with the TSC, and requires a serializing instruction, such as CPUID
+or an MSR read.
+
+Since CPUID may actually be virtualized by a trap and emulate mechanism, this
+serialization can pose a performance issue for hardware virtualization.  An
+accurate time stamp counter reading may therefore not always be available, and
+it may be necessary for an implementation to guard against "backwards" reads of
+the TSC as seen from other CPUs, even in an otherwise perfectly synchronized
+system.
+
+4.3) Timespec aliasing
+
+Additionally, this lack of serialization from the TSC poses another challenge
+when using results of the TSC when measured against another time source.  As
+the TSC is much higher precision, many possible values of the TSC may be read
+while another clock is still expressing the same value.
+
+That is, you may read (T,T+10) while external clock C maintains the same value.
+Due to non-serialized reads, you may actually end up with a range which
+fluctuates - from (T-1.. T+10).  Thus, any time calculated from a TSC, but
+calibrated against an external value may have a range of valid values.
+Re-calibrating this computation may actually cause time, as computed after the
+calibration, to go backwards, compared with time computed before the
+calibration.
+
+This problem is particularly pronounced with an internal time source in Linux,
+the kernel time, which is expressed in the theoretically high resolution
+timespec - but which advances in much larger granularity intervals, sometimes
+at the rate of jiffies, and possibly in catchup modes, at a much larger step.
+
+This aliasing requires care in the computation and recalibration of kvmclock
+and any other values derived from TSC computation (such as TSC virtualization
+itself).
+
+4.4) Migration
+
+Migration of a virtual machine raises problems for timekeeping in two ways.
+First, the migration itself may take time, during which interrupts cannot be
+delivered, and after which, the guest time may need to be caught up.  NTP may
+be able to help to some degree here, as the clock correction required is
+typically small enough to fall in the NTP-correctable window.
+
+An additional concern is that timers based off the TSC (or HPET, if the raw bus
+clock is exposed) may now be running at different rates, requiring compensation
+in some way in the hypervisor by virtualizing these timers.  In addition,
+migrating to a faster machine may preclude the use of a passthrough TSC, as a
+faster clock cannot be made visible to a guest without the potential of time
+advancing faster than usual.  A slower clock is less of a problem, as it can
+always be caught up to the original rate.  KVM clock avoids these problems by
+simply storing multipliers and offsets against the TSC for the guest to convert
+back into nanosecond resolution values.
+
+4.5) Scheduling
+
+Since scheduling may be based on precise timing and firing of interrupts, the
+scheduling algorithms of an operating system may be adversely affected by
+virtualization.  In theory, the effect is random and should be universally
+distributed, but in contrived as well as real scenarios (guest device access,
+causes of virtualization exits, possible context switch), this may not always
+be the case.  The effect of this has not been well studied.
+
+In an attempt to work around this, several implementations have provided a
+paravirtualized scheduler clock, which reveals the true amount of CPU time for
+which a virtual machine has been running.
+
+4.6) Watchdogs
+
+Watchdog timers, such as the lock detector in Linux may fire accidentally when
+running under hardware virtualization due to timer interrupts being delayed or
+misinterpretation of the passage of real time.  Usually, these warnings are
+spurious and can be ignored, but in some circumstances it may be necessary to
+disable such detection.
+
+4.7) Delays and precision timing
+
+Precise timing and delays may not be possible in a virtualized system.  This
+can happen if the system is controlling physical hardware, or issues delays to
+compensate for slower I/O to and from devices.  The first issue is not solvable
+in general for a virtualized system; hardware control software can't be
+adequately virtualized without a full real-time operating system, which would
+require an RT aware virtualization platform.
+
+The second issue may cause performance problems, but this is unlikely to be a
+significant issue.  In many cases these delays may be eliminated through
+configuration or paravirtualization.
+
+4.8) Covert channels and leaks
+
+In addition to the above problems, time information will inevitably leak to the
+guest about the host in anything but a perfect implementation of virtualized
+time.  This may allow the guest to infer the presence of a hypervisor (as in a
+red-pill type detection), and it may allow information to leak between guests
+by using CPU utilization itself as a signalling channel.  Preventing such
+problems would require completely isolated virtual time which may not track
+real time any longer.  This may be useful in certain security or QA contexts,
+but in general isn't recommended for real-world deployment scenarios.

Documentation/lguest/lguest.c

@@ -1639,15 +1639,6 @@ static void blk_request(struct virtqueue *vq)
 	 */
 	off = out->sector * 512;
 
-	/*
-	 * The block device implements "barriers", where the Guest indicates
-	 * that it wants all previous writes to occur before this write.  We
-	 * don't have a way of asking our kernel to do a barrier, so we just
-	 * synchronize all the data in the file.  Pretty poor, no?
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
 	/*
 	 * In general the virtio block driver is allowed to try SCSI commands.
 	 * It'd be nice if we supported eject, for example, but we don't.
@@ -1680,6 +1671,13 @@ static void blk_request(struct virtqueue *vq)
 			/* Die, bad Guest, die. */
 			errx(1, "Write past end %llu+%u", off, ret);
 		}
+
+		wlen = sizeof(*in);
+		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+	} else if (out->type & VIRTIO_BLK_T_FLUSH) {
+		/* Flush */
+		ret = fdatasync(vblk->fd);
+		verbose("FLUSH fdatasync: %i\n", ret);
 		wlen = sizeof(*in);
 		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
 	} else {
@@ -1703,15 +1701,6 @@ static void blk_request(struct virtqueue *vq)
 		}
 	}
 
-	/*
-	 * OK, so we noted that it was pretty poor to use an fdatasync as a
-	 * barrier.  But Christoph Hellwig points out that we need a sync
-	 * *afterwards* as well: "Barriers specify no reordering to the front
-	 * or the back."  And Jens Axboe confirmed it, so here we are:
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
 	/* Finished that request. */
 	add_used(vq, head, wlen);
 }
@@ -1736,8 +1725,8 @@ static void setup_block_file(const char *filename)
 	vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
 	vblk->len = lseek64(vblk->fd, 0, SEEK_END);
 
-	/* We support barriers. */
-	add_feature(dev, VIRTIO_BLK_F_BARRIER);
+	/* We support FLUSH. */
+	add_feature(dev, VIRTIO_BLK_F_FLUSH);
 
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);

Documentation/networking/bonding.txt

@@ -765,6 +765,14 @@ xmit_hash_policy
 	does not exist, and the layer2 policy is the only policy.  The
 	layer2+3 value was added for bonding version 3.2.2.
 
+resend_igmp
+
+	Specifies the number of IGMP membership reports to be issued after
+	a failover event. One membership report is issued immediately after
+	the failover, subsequent packets are sent in each 200ms interval.
+
+	The valid range is 0 - 255; the default value is 1. This option
+	was added for bonding version 3.7.0.
 
 3. Configuring Bonding Devices
 ==============================

Documentation/networking/can.txt

@@ -22,6 +22,7 @@ This file contains
       4.1.2 RAW socket option CAN_RAW_ERR_FILTER
       4.1.3 RAW socket option CAN_RAW_LOOPBACK
       4.1.4 RAW socket option CAN_RAW_RECV_OWN_MSGS
+      4.1.5 RAW socket returned message flags
     4.2 Broadcast Manager protocol sockets (SOCK_DGRAM)
     4.3 connected transport protocols (SOCK_SEQPACKET)
     4.4 unconnected transport protocols (SOCK_DGRAM)
@@ -471,6 +472,17 @@ solution for a couple of reasons:
     setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
                &recv_own_msgs, sizeof(recv_own_msgs));
 
+  4.1.5 RAW socket returned message flags
+
+  When using recvmsg() call, the msg->msg_flags may contain following flags:
+
+    MSG_DONTROUTE: set when the received frame was created on the local host.
+
+    MSG_CONFIRM: set when the frame was sent via the socket it is received on.
+      This flag can be interpreted as a 'transmission confirmation' when the
+      CAN driver supports the echo of frames on driver level, see 3.2 and 6.2.
+      In order to receive such messages, CAN_RAW_RECV_OWN_MSGS must be set.
+
   4.2 Broadcast Manager protocol sockets (SOCK_DGRAM)
   4.3 connected transport protocols (SOCK_SEQPACKET)
   4.4 unconnected transport protocols (SOCK_DGRAM)

Documentation/networking/dccp.txt

@@ -1,18 +1,20 @@
 DCCP protocol
-============
+=============
 
 
 Contents
 ========
-
 - Introduction
 - Missing features
 - Socket options
+- Sysctl variables
+- IOCTLs
+- Other tunables
 - Notes
 
+
 Introduction
 ============
-
 Datagram Congestion Control Protocol (DCCP) is an unreliable, connection
 oriented protocol designed to solve issues present in UDP and TCP, particularly
 for real-time and multimedia (streaming) traffic.
@@ -29,9 +31,9 @@ It has a base protocol and pluggable congestion control IDs (CCIDs).
 DCCP is a Proposed Standard (RFC 2026), and the homepage for DCCP as a protocol
 is at http://www.ietf.org/html.charters/dccp-charter.html
 
+
 Missing features
 ================
-
 The Linux DCCP implementation does not currently support all the features that are
 specified in RFCs 4340...42.
 
@@ -45,7 +47,6 @@ http://linux-net.osdl.org/index.php/DCCP_Testing#Experimental_DCCP_source_tree
 
 Socket options
 ==============
-
 DCCP_SOCKOPT_SERVICE sets the service. The specification mandates use of
 service codes (RFC 4340, sec. 8.1.2); if this socket option is not set,
 the socket will fall back to 0 (which means that no meaningful service code
@@ -112,6 +113,7 @@ DCCP_SOCKOPT_CCID_TX_INFO
 On unidirectional connections it is useful to close the unused half-connection
 via shutdown (SHUT_WR or SHUT_RD): this will reduce per-packet processing costs.
 
+
 Sysctl variables
 ================
 Several DCCP default parameters can be managed by the following sysctls
@@ -155,15 +157,30 @@ sync_ratelimit = 125 ms
 	sequence-invalid packets on the same socket (RFC 4340, 7.5.4). The unit
 	of this parameter is milliseconds; a value of 0 disables rate-limiting.
 
+
 IOCTLS
 ======
 FIONREAD
 	Works as in udp(7): returns in the `int' argument pointer the size of
 	the next pending datagram in bytes, or 0 when no datagram is pending.
 
+
+Other tunables
+==============
+Per-route rto_min support
+	CCID-2 supports the RTAX_RTO_MIN per-route setting for the minimum value
+	of the RTO timer. This setting can be modified via the 'rto_min' option
+	of iproute2; for example:
+		> ip route change 10.0.0.0/24   rto_min 250j dev wlan0
+		> ip route add    10.0.0.254/32 rto_min 800j dev wlan0
+		> ip route show dev wlan0
+	CCID-3 also supports the rto_min setting: it is used to define the lower
+	bound for the expiry of the nofeedback timer. This can be useful on LANs
+	with very low RTTs (e.g., loopback, Gbit ethernet).
+
+
 Notes
 =====
-
 DCCP does not travel through NAT successfully at present on many boxes. This is
 because the checksum covers the pseudo-header as per TCP and UDP. Linux NAT
 support for DCCP has been added.

Documentation/networking/ip-sysctl.txt

@@ -1014,6 +1014,12 @@ conf/interface/*:
 accept_ra - BOOLEAN
 	Accept Router Advertisements; autoconfigure using them.
 
+	Possible values are:
+		0 Do not accept Router Advertisements.
+		1 Accept Router Advertisements if forwarding is disabled.
+		2 Overrule forwarding behaviour. Accept Router Advertisements
+		  even if forwarding is enabled.
+
 	Functional default: enabled if local forwarding is disabled.
 			    disabled if local forwarding is enabled.
 
@@ -1075,7 +1081,12 @@ forwarding - BOOLEAN
 	Note: It is recommended to have the same setting on all
 	interfaces; mixed router/host scenarios are rather uncommon.
 
-	FALSE:
+	Possible values are:
+		0 Forwarding disabled
+		1 Forwarding enabled
+		2 Forwarding enabled (Hybrid Mode)
+
+	FALSE (0):
 
 	By default, Host behaviour is assumed.  This means:
 
@@ -1085,18 +1096,24 @@ forwarding - BOOLEAN
 	   Advertisements (and do autoconfiguration).
 	4. If accept_redirects is TRUE (default), accept Redirects.
 
-	TRUE:
+	TRUE (1):
 
 	If local forwarding is enabled, Router behaviour is assumed.
 	This means exactly the reverse from the above:
 
 	1. IsRouter flag is set in Neighbour Advertisements.
 	2. Router Solicitations are not sent.
-	3. Router Advertisements are ignored.
+	3. Router Advertisements are ignored unless accept_ra is 2.
 	4. Redirects are ignored.
 
-	Default: FALSE if global forwarding is disabled (default),
-		 otherwise TRUE.
+	TRUE (2):
+
+	Hybrid mode. Same behaviour as TRUE, except for:
+
+	2. Router Solicitations are being sent when necessary.
+
+	Default: 0 (disabled) if global forwarding is disabled (default),
+		 otherwise 1 (enabled).
 
 hop_limit - INTEGER
 	Default Hop Limit to set.

Documentation/networking/phonet.txt

@@ -112,6 +112,22 @@ However, connect() and getpeername() are not supported, as they did
 not seem useful with Phonet usages (could be added easily).
 
 
+Resource subscription
+---------------------
+
+A Phonet datagram socket can be subscribed to any number of 8-bits
+Phonet resources, as follow:
+
+  uint32_t res = 0xXX;
+  ioctl(fd, SIOCPNADDRESOURCE, &res);
+
+Subscription is similarly cancelled using the SIOCPNDELRESOURCE I/O
+control request, or when the socket is closed.
+
+Note that no more than one socket can be subcribed to any given
+resource at a time. If not, ioctl() will return EBUSY.
+
+
 Phonet Pipe protocol
 --------------------
 
@@ -166,6 +182,46 @@ The pipe protocol provides two socket options at the SOL_PNPIPE level:
     or zero if encapsulation is off.
 
 
+Phonet Pipe-controller Implementation
+-------------------------------------
+
+Phonet Pipe-controller is enabled by selecting the CONFIG_PHONET_PIPECTRLR Kconfig
+option. It is useful when communicating with those Nokia Modems which do not
+implement Pipe controller in them e.g. Nokia Slim Modem used in ST-Ericsson
+U8500 platform.
+
+The implementation is based on the Data Connection Establishment Sequence
+depicted in 'Nokia Wireless Modem API - Wireless_modem_user_guide.pdf'
+document.
+
+It allows a phonet sequenced socket (host-pep) to initiate a Pipe connection
+between itself and a remote pipe-end point (e.g. modem).
+
+The implementation adds socket options at SOL_PNPIPE level:
+
+ PNPIPE_PIPE_HANDLE
+	It accepts an integer argument for setting value of pipe handle.
+
+  PNPIPE_ENABLE accepts one integer value (int). If set to zero, the pipe
+    is disabled. If the value is non-zero, the pipe is enabled. If the pipe
+    is not (yet) connected, ENOTCONN is error is returned.
+
+The implementation also adds socket 'connect'. On calling the 'connect', pipe
+will be created between the source socket and the destination, and the pipe
+state will be set to PIPE_DISABLED.
+
+After a pipe has been created and enabled successfully, the Pipe data can be
+exchanged between the host-pep and remote-pep (modem).
+
+User-space would typically follow below sequence with Pipe controller:-
+-socket
+-bind
+-setsockopt for PNPIPE_PIPE_HANDLE
+-connect
+-setsockopt for PNPIPE_ENCAP_IP
+-setsockopt for PNPIPE_ENABLE
+
+
 Authors
 -------
 

Documentation/networking/timestamping.txt

@@ -172,15 +172,19 @@ struct skb_shared_hwtstamps {
 };
 
 Time stamps for outgoing packets are to be generated as follows:
-- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero.
-  If yes, then the driver is expected to do hardware time stamping.
+- In hard_start_xmit(), check if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)
+  is set no-zero. If yes, then the driver is expected to do hardware time
+  stamping.
 - If this is possible for the skb and requested, then declare
-  that the driver is doing the time stamping by setting the field
-  skb_tx(skb)->in_progress non-zero. You might want to keep a pointer
-  to the associated skb for the next step and not free the skb. A driver
-  not supporting hardware time stamping doesn't do that. A driver must
-  never touch sk_buff::tstamp! It is used to store software generated
-  time stamps by the network subsystem.
+  that the driver is doing the time stamping by setting the flag
+  SKBTX_IN_PROGRESS in skb_shinfo(skb)->tx_flags , e.g. with
+
+      skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+  You might want to keep a pointer to the associated skb for the next step
+  and not free the skb. A driver not supporting hardware time stamping doesn't
+  do that. A driver must never touch sk_buff::tstamp! It is used to store
+  software generated time stamps by the network subsystem.
 - As soon as the driver has sent the packet and/or obtained a
   hardware time stamp for it, it passes the time stamp back by
   calling skb_hwtstamp_tx() with the original skb, the raw
@@ -191,6 +195,6 @@ Time stamps for outgoing packets are to be generated as follows:
   this would occur at a later time in the processing pipeline than other
   software time stamping and therefore could lead to unexpected deltas
   between time stamps.
-- If the driver did not call set skb_tx(skb)->in_progress, then
+- If the driver did not set the SKBTX_IN_PROGRESS flag (see above), then
   dev_hard_start_xmit() checks whether software time stamping
   is wanted as fallback and potentially generates the time stamp.

Documentation/pcmcia/driver-changes.txt

@@ -1,4 +1,29 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
+* pcmcia_loop_config() and autoconfiguration (as of 2.6.36)
+   If struct pcmcia_device *p_dev->config_flags is set accordingly,
+   pcmcia_loop_config() now sets up certain configuration values
+   automatically, though the driver may still override the settings
+   in the callback function. The following autoconfiguration options
+   are provided at the moment:
+	CONF_AUTO_CHECK_VCC : check for matching Vcc
+	CONF_AUTO_SET_VPP   : set Vpp
+	CONF_AUTO_AUDIO     : auto-enable audio line, if required
+	CONF_AUTO_SET_IO    : set ioport resources (->resource[0,1])
+	CONF_AUTO_SET_IOMEM : set first iomem resource (->resource[2])
+
+* pcmcia_request_configuration -> pcmcia_enable_device (as of 2.6.36)
+   pcmcia_request_configuration() got renamed to pcmcia_enable_device(),
+   as it mirrors pcmcia_disable_device(). Configuration settings are now
+   stored in struct pcmcia_device, e.g. in the fields config_flags,
+   config_index, config_base, vpp.
+
+* pcmcia_request_window changes (as of 2.6.36)
+   Instead of win_req_t, drivers are now requested to fill out
+   struct pcmcia_device *p_dev->resource[2,3,4,5] for up to four ioport
+   ranges. After a call to pcmcia_request_window(), the regions found there
+   are reserved and may be used immediately -- until pcmcia_release_window()
+   is called.
+
 * pcmcia_request_io changes (as of 2.6.36)
    Instead of io_req_t, drivers are now requested to fill out
    struct pcmcia_device *p_dev->resource[0,1] for up to two ioport

Documentation/power/00-INDEX

@@ -14,6 +14,8 @@ interface.txt
 	- Power management user interface in /sys/power
 notifiers.txt
 	- Registering suspend notifiers in device drivers
+opp.txt
+	- Operating Performance Point library
 pci.txt
 	- How the PCI Subsystem Does Power Management
 pm_qos_interface.txt

Documentation/power/interface.txt

@@ -57,7 +57,7 @@ smallest image possible.  In particular, if "0" is written to this file, the
 suspend image will be as small as possible.
 
 Reading from this file will display the current image size limit, which
-is set to 500 MB by default.
+is set to 2/5 of available RAM by default.
 
 /sys/power/pm_trace controls the code which saves the last PM event point in
 the RTC across reboots, so that you can debug a machine that just hangs

Documentation/power/opp.txt

@@ -0,0 +1,375 @@
+*=============*
+* OPP Library *
+*=============*
+
+(C) 2009-2010 Nishanth Menon <nm@ti.com>, Texas Instruments Incorporated
+
+Contents
+--------
+1. Introduction
+2. Initial OPP List Registration
+3. OPP Search Functions
+4. OPP Availability Control Functions
+5. OPP Data Retrieval Functions
+6. Cpufreq Table Generation
+7. Data Structures
+
+1. Introduction
+===============
+Complex SoCs of today consists of a multiple sub-modules working in conjunction.
+In an operational system executing varied use cases, not all modules in the SoC
+need to function at their highest performing frequency all the time. To
+facilitate this, sub-modules in a SoC are grouped into domains, allowing some
+domains to run at lower voltage and frequency while other domains are loaded
+more. The set of discrete tuples consisting of frequency and voltage pairs that
+the device will support per domain are called Operating Performance Points or
+OPPs.
+
+OPP library provides a set of helper functions to organize and query the OPP
+information. The library is located in drivers/base/power/opp.c and the header
+is located in include/linux/opp.h. OPP library can be enabled by enabling
+CONFIG_PM_OPP from power management menuconfig menu. OPP library depends on
+CONFIG_PM as certain SoCs such as Texas Instrument's OMAP framework allows to
+optionally boot at a certain OPP without needing cpufreq.
+
+Typical usage of the OPP library is as follows:
+(users)		-> registers a set of default OPPs		-> (library)
+SoC framework	-> modifies on required cases certain OPPs	-> OPP layer
+		-> queries to search/retrieve information	->
+
+OPP layer expects each domain to be represented by a unique device pointer. SoC
+framework registers a set of initial OPPs per device with the OPP layer. This
+list is expected to be an optimally small number typically around 5 per device.
+This initial list contains a set of OPPs that the framework expects to be safely
+enabled by default in the system.
+
+Note on OPP Availability:
+------------------------
+As the system proceeds to operate, SoC framework may choose to make certain
+OPPs available or not available on each device based on various external
+factors. Example usage: Thermal management or other exceptional situations where
+SoC framework might choose to disable a higher frequency OPP to safely continue
+operations until that OPP could be re-enabled if possible.
+
+OPP library facilitates this concept in it's implementation. The following
+operational functions operate only on available opps:
+opp_find_freq_{ceil, floor}, opp_get_voltage, opp_get_freq, opp_get_opp_count
+and opp_init_cpufreq_table
+
+opp_find_freq_exact is meant to be used to find the opp pointer which can then
+be used for opp_enable/disable functions to make an opp available as required.
+
+WARNING: Users of OPP library should refresh their availability count using
+get_opp_count if opp_enable/disable functions are invoked for a device, the
+exact mechanism to trigger these or the notification mechanism to other
+dependent subsystems such as cpufreq are left to the discretion of the SoC
+specific framework which uses the OPP library. Similar care needs to be taken
+care to refresh the cpufreq table in cases of these operations.
+
+WARNING on OPP List locking mechanism:
+-------------------------------------------------
+OPP library uses RCU for exclusivity. RCU allows the query functions to operate
+in multiple contexts and this synchronization mechanism is optimal for a read
+intensive operations on data structure as the OPP library caters to.
+
+To ensure that the data retrieved are sane, the users such as SoC framework
+should ensure that the section of code operating on OPP queries are locked
+using RCU read locks. The opp_find_freq_{exact,ceil,floor},
+opp_get_{voltage, freq, opp_count} fall into this category.
+
+opp_{add,enable,disable} are updaters which use mutex and implement it's own
+RCU locking mechanisms. opp_init_cpufreq_table acts as an updater and uses
+mutex to implment RCU updater strategy. These functions should *NOT* be called
+under RCU locks and other contexts that prevent blocking functions in RCU or
+mutex operations from working.
+
+2. Initial OPP List Registration
+================================
+The SoC implementation calls opp_add function iteratively to add OPPs per
+device. It is expected that the SoC framework will register the OPP entries
+optimally- typical numbers range to be less than 5. The list generated by
+registering the OPPs is maintained by OPP library throughout the device
+operation. The SoC framework can subsequently control the availability of the
+OPPs dynamically using the opp_enable / disable functions.
+
+opp_add - Add a new OPP for a specific domain represented by the device pointer.
+	The OPP is defined using the frequency and voltage. Once added, the OPP
+	is assumed to be available and control of it's availability can be done
+	with the opp_enable/disable functions. OPP library internally stores
+	and manages this information in the opp struct. This function may be
+	used by SoC framework to define a optimal list as per the demands of
+	SoC usage environment.
+
+	WARNING: Do not use this function in interrupt context.
+
+	Example:
+	 soc_pm_init()
+	 {
+		/* Do things */
+		r = opp_add(mpu_dev, 1000000, 900000);
+		if (!r) {
+			pr_err("%s: unable to register mpu opp(%d)\n", r);
+			goto no_cpufreq;
+		}
+		/* Do cpufreq things */
+	 no_cpufreq:
+		/* Do remaining things */
+	 }
+
+3. OPP Search Functions
+=======================
+High level framework such as cpufreq operates on frequencies. To map the
+frequency back to the corresponding OPP, OPP library provides handy functions
+to search the OPP list that OPP library internally manages. These search
+functions return the matching pointer representing the opp if a match is
+found, else returns error. These errors are expected to be handled by standard
+error checks such as IS_ERR() and appropriate actions taken by the caller.
+
+opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
+	availability. This function is especially useful to enable an OPP which
+	is not available by default.
+	Example: In a case when SoC framework detects a situation where a
+	higher frequency could be made available, it can use this function to
+	find the OPP prior to call the opp_enable to actually make it available.
+	 rcu_read_lock();
+	 opp = opp_find_freq_exact(dev, 1000000000, false);
+	 rcu_read_unlock();
+	 /* dont operate on the pointer.. just do a sanity check.. */
+	 if (IS_ERR(opp)) {
+		pr_err("frequency not disabled!\n");
+		/* trigger appropriate actions.. */
+	 } else {
+		opp_enable(dev,1000000000);
+	 }
+
+	NOTE: This is the only search function that operates on OPPs which are
+	not available.
+
+opp_find_freq_floor - Search for an available OPP which is *at most* the
+	provided frequency. This function is useful while searching for a lesser
+	match OR operating on OPP information in the order of decreasing
+	frequency.
+	Example: To find the highest opp for a device:
+	 freq = ULONG_MAX;
+	 rcu_read_lock();
+	 opp_find_freq_floor(dev, &freq);
+	 rcu_read_unlock();
+
+opp_find_freq_ceil - Search for an available OPP which is *at least* the
+	provided frequency. This function is useful while searching for a
+	higher match OR operating on OPP information in the order of increasing
+	frequency.
+	Example 1: To find the lowest opp for a device:
+	 freq = 0;
+	 rcu_read_lock();
+	 opp_find_freq_ceil(dev, &freq);
+	 rcu_read_unlock();
+	Example 2: A simplified implementation of a SoC cpufreq_driver->target:
+	 soc_cpufreq_target(..)
+	 {
+		/* Do stuff like policy checks etc. */
+		/* Find the best frequency match for the req */
+		rcu_read_lock();
+		opp = opp_find_freq_ceil(dev, &freq);
+		rcu_read_unlock();
+		if (!IS_ERR(opp))
+			soc_switch_to_freq_voltage(freq);
+		else
+			/* do something when we cant satisfy the req */
+		/* do other stuff */
+	 }
+
+4. OPP Availability Control Functions
+=====================================
+A default OPP list registered with the OPP library may not cater to all possible
+situation. The OPP library provides a set of functions to modify the
+availability of a OPP within the OPP list. This allows SoC frameworks to have
+fine grained dynamic control of which sets of OPPs are operationally available.
+These functions are intended to *temporarily* remove an OPP in conditions such
+as thermal considerations (e.g. don't use OPPx until the temperature drops).
+
+WARNING: Do not use these functions in interrupt context.
+
+opp_enable - Make a OPP available for operation.
+	Example: Lets say that 1GHz OPP is to be made available only if the
+	SoC temperature is lower than a certain threshold. The SoC framework
+	implementation might choose to do something as follows:
+	 if (cur_temp < temp_low_thresh) {
+		/* Enable 1GHz if it was disabled */
+		rcu_read_lock();
+		opp = opp_find_freq_exact(dev, 1000000000, false);
+		rcu_read_unlock();
+		/* just error check */
+		if (!IS_ERR(opp))
+			ret = opp_enable(dev, 1000000000);
+		else
+			goto try_something_else;
+	 }
+
+opp_disable - Make an OPP to be not available for operation
+	Example: Lets say that 1GHz OPP is to be disabled if the temperature
+	exceeds a threshold value. The SoC framework implementation might
+	choose to do something as follows:
+	 if (cur_temp > temp_high_thresh) {
+		/* Disable 1GHz if it was enabled */
+		rcu_read_lock();
+		opp = opp_find_freq_exact(dev, 1000000000, true);
+		rcu_read_unlock();
+		/* just error check */
+		if (!IS_ERR(opp))
+			ret = opp_disable(dev, 1000000000);
+		else
+			goto try_something_else;
+	 }
+
+5. OPP Data Retrieval Functions
+===============================
+Since OPP library abstracts away the OPP information, a set of functions to pull
+information from the OPP structure is necessary. Once an OPP pointer is
+retrieved using the search functions, the following functions can be used by SoC
+framework to retrieve the information represented inside the OPP layer.
+
+opp_get_voltage - Retrieve the voltage represented by the opp pointer.
+	Example: At a cpufreq transition to a different frequency, SoC
+	framework requires to set the voltage represented by the OPP using
+	the regulator framework to the Power Management chip providing the
+	voltage.
+	 soc_switch_to_freq_voltage(freq)
+	 {
+		/* do things */
+		rcu_read_lock();
+		opp = opp_find_freq_ceil(dev, &freq);
+		v = opp_get_voltage(opp);
+		rcu_read_unlock();
+		if (v)
+			regulator_set_voltage(.., v);
+		/* do other things */
+	 }
+
+opp_get_freq - Retrieve the freq represented by the opp pointer.
+	Example: Lets say the SoC framework uses a couple of helper functions
+	we could pass opp pointers instead of doing additional parameters to
+	handle quiet a bit of data parameters.
+	 soc_cpufreq_target(..)
+	 {
+		/* do things.. */
+		 max_freq = ULONG_MAX;
+		 rcu_read_lock();
+		 max_opp = opp_find_freq_floor(dev,&max_freq);
+		 requested_opp = opp_find_freq_ceil(dev,&freq);
+		 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
+			r = soc_test_validity(max_opp, requested_opp);
+		 rcu_read_unlock();
+		/* do other things */
+	 }
+	 soc_test_validity(..)
+	 {
+		 if(opp_get_voltage(max_opp) < opp_get_voltage(requested_opp))
+			 return -EINVAL;
+		 if(opp_get_freq(max_opp) < opp_get_freq(requested_opp))
+			 return -EINVAL;
+		/* do things.. */
+	 }
+
+opp_get_opp_count - Retrieve the number of available opps for a device
+	Example: Lets say a co-processor in the SoC needs to know the available
+	frequencies in a table, the main processor can notify as following:
+	 soc_notify_coproc_available_frequencies()
+	 {
+		/* Do things */
+		rcu_read_lock();
+		num_available = opp_get_opp_count(dev);
+		speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
+		/* populate the table in increasing order */
+		freq = 0;
+		while (!IS_ERR(opp = opp_find_freq_ceil(dev, &freq))) {
+			speeds[i] = freq;
+			freq++;
+			i++;
+		}
+		rcu_read_unlock();
+
+		soc_notify_coproc(AVAILABLE_FREQs, speeds, num_available);
+		/* Do other things */
+	 }
+
+6. Cpufreq Table Generation
+===========================
+opp_init_cpufreq_table - cpufreq framework typically is initialized with
+	cpufreq_frequency_table_cpuinfo which is provided with the list of
+	frequencies that are available for operation. This function provides
+	a ready to use conversion routine to translate the OPP layer's internal
+	information about the available frequencies into a format readily
+	providable to cpufreq.
+
+	WARNING: Do not use this function in interrupt context.
+
+	Example:
+	 soc_pm_init()
+	 {
+		/* Do things */
+		r = opp_init_cpufreq_table(dev, &freq_table);
+		if (!r)
+			cpufreq_frequency_table_cpuinfo(policy, freq_table);
+		/* Do other things */
+	 }
+
+	NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
+	addition to CONFIG_PM as power management feature is required to
+	dynamically scale voltage and frequency in a system.
+
+7. Data Structures
+==================
+Typically an SoC contains multiple voltage domains which are variable. Each
+domain is represented by a device pointer. The relationship to OPP can be
+represented as follows:
+SoC
+ |- device 1
+ |	|- opp 1 (availability, freq, voltage)
+ |	|- opp 2 ..
+ ...	...
+ |	`- opp n ..
+ |- device 2
+ ...
+ `- device m
+
+OPP library maintains a internal list that the SoC framework populates and
+accessed by various functions as described above. However, the structures
+representing the actual OPPs and domains are internal to the OPP library itself
+to allow for suitable abstraction reusable across systems.
+
+struct opp - The internal data structure of OPP library which is used to
+	represent an OPP. In addition to the freq, voltage, availability
+	information, it also contains internal book keeping information required
+	for the OPP library to operate on.  Pointer to this structure is
+	provided back to the users such as SoC framework to be used as a
+	identifier for OPP in the interactions with OPP layer.
+
+	WARNING: The struct opp pointer should not be parsed or modified by the
+	users. The defaults of for an instance is populated by opp_add, but the
+	availability of the OPP can be modified by opp_enable/disable functions.
+
+struct device - This is used to identify a domain to the OPP layer. The
+	nature of the device and it's implementation is left to the user of
+	OPP library such as the SoC framework.
+
+Overall, in a simplistic view, the data structure operations is represented as
+following:
+
+Initialization / modification:
+            +-----+        /- opp_enable
+opp_add --> | opp | <-------
+  |         +-----+        \- opp_disable
+  \-------> domain_info(device)
+
+Search functions:
+             /-- opp_find_freq_ceil  ---\   +-----+
+domain_info<---- opp_find_freq_exact -----> | opp |
+             \-- opp_find_freq_floor ---/   +-----+
+
+Retrieval functions:
++-----+     /- opp_get_voltage
+| opp | <---
++-----+     \- opp_get_freq
+
+domain_info <- opp_get_opp_count

Documentation/power/runtime_pm.txt

@@ -1,6 +1,7 @@
 Run-time Power Management Framework for I/O Devices
 
 (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+(C) 2010 Alan Stern <stern@rowland.harvard.edu>
 
 1. Introduction
 
@@ -157,7 +158,8 @@ rules:
     to execute it, the other callbacks will not be executed for the same device.
 
   * A request to execute ->runtime_resume() will cancel any pending or
-    scheduled requests to execute the other callbacks for the same device.
+    scheduled requests to execute the other callbacks for the same device,
+    except for scheduled autosuspends.
 
 3. Run-time PM Device Fields
 
@@ -165,7 +167,7 @@ The following device run-time PM fields are present in 'struct dev_pm_info', as
 defined in include/linux/pm.h:
 
   struct timer_list suspend_timer;
-    - timer used for scheduling (delayed) suspend request
+    - timer used for scheduling (delayed) suspend and autosuspend requests
 
   unsigned long timer_expires;
     - timer expiration time, in jiffies (if this is different from zero, the
@@ -230,6 +232,28 @@ defined in include/linux/pm.h:
       interface; it may only be modified with the help of the pm_runtime_allow()
       and pm_runtime_forbid() helper functions
 
+  unsigned int no_callbacks;
+    - indicates that the device does not use the run-time PM callbacks (see
+      Section 8); it may be modified only by the pm_runtime_no_callbacks()
+      helper function
+
+  unsigned int use_autosuspend;
+    - indicates that the device's driver supports delayed autosuspend (see
+      Section 9); it may be modified only by the
+      pm_runtime{_dont}_use_autosuspend() helper functions
+
+  unsigned int timer_autosuspends;
+    - indicates that the PM core should attempt to carry out an autosuspend
+      when the timer expires rather than a normal suspend
+
+  int autosuspend_delay;
+    - the delay time (in milliseconds) to be used for autosuspend
+
+  unsigned long last_busy;
+    - the time (in jiffies) when the pm_runtime_mark_last_busy() helper
+      function was last called for this device; used in calculating inactivity
+      periods for autosuspend
+
 All of the above fields are members of the 'power' member of 'struct device'.
 
 4. Run-time PM Device Helper Functions
@@ -255,6 +279,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       error code on failure, where -EAGAIN or -EBUSY means it is safe to attempt
       to suspend the device again in future
 
+  int pm_runtime_autosuspend(struct device *dev);
+    - same as pm_runtime_suspend() except that the autosuspend delay is taken
+      into account; if pm_runtime_autosuspend_expiration() says the delay has
+      not yet expired then an autosuspend is scheduled for the appropriate time
+      and 0 is returned
+
   int pm_runtime_resume(struct device *dev);
     - execute the subsystem-level resume callback for the device; returns 0 on
       success, 1 if the device's run-time PM status was already 'active' or
@@ -267,6 +297,11 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       device (the request is represented by a work item in pm_wq); returns 0 on
       success or error code if the request has not been queued up
 
+  int pm_request_autosuspend(struct device *dev);
+    - schedule the execution of the subsystem-level suspend callback for the
+      device when the autosuspend delay has expired; if the delay has already
+      expired then the work item is queued up immediately
+
   int pm_schedule_suspend(struct device *dev, unsigned int delay);
     - schedule the execution of the subsystem-level suspend callback for the
       device in future, where 'delay' is the time to wait before queuing up a
@@ -298,12 +333,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
     - decrement the device's usage counter
 
   int pm_runtime_put(struct device *dev);
-    - decrement the device's usage counter, run pm_request_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_idle(dev) and return its result
+
+  int pm_runtime_put_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_autosuspend(dev) and return its result
 
   int pm_runtime_put_sync(struct device *dev);
-    - decrement the device's usage counter, run pm_runtime_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_idle(dev) and return its result
+
+  int pm_runtime_put_sync_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_autosuspend(dev) and return its result
 
   void pm_runtime_enable(struct device *dev);
     - enable the run-time PM helper functions to run the device bus type's
@@ -349,19 +392,51 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       counter (used by the /sys/devices/.../power/control interface to
       effectively prevent the device from being power managed at run time)
 
+  void pm_runtime_no_callbacks(struct device *dev);
+    - set the power.no_callbacks flag for the device and remove the run-time
+      PM attributes from /sys/devices/.../power (or prevent them from being
+      added when the device is registered)
+
+  void pm_runtime_mark_last_busy(struct device *dev);
+    - set the power.last_busy field to the current time
+
+  void pm_runtime_use_autosuspend(struct device *dev);
+    - set the power.use_autosuspend flag, enabling autosuspend delays
+
+  void pm_runtime_dont_use_autosuspend(struct device *dev);
+    - clear the power.use_autosuspend flag, disabling autosuspend delays
+
+  void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
+    - set the power.autosuspend_delay value to 'delay' (expressed in
+      milliseconds); if 'delay' is negative then run-time suspends are
+      prevented
+
+  unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
+    - calculate the time when the current autosuspend delay period will expire,
+      based on power.last_busy and power.autosuspend_delay; if the delay time
+      is 1000 ms or larger then the expiration time is rounded up to the
+      nearest second; returns 0 if the delay period has already expired or
+      power.use_autosuspend isn't set, otherwise returns the expiration time
+      in jiffies
+
 It is safe to execute the following helper functions from interrupt context:
 
 pm_request_idle()
+pm_request_autosuspend()
 pm_schedule_suspend()
 pm_request_resume()
 pm_runtime_get_noresume()
 pm_runtime_get()
 pm_runtime_put_noidle()
 pm_runtime_put()
+pm_runtime_put_autosuspend()
+pm_runtime_enable()
 pm_suspend_ignore_children()
 pm_runtime_set_active()
 pm_runtime_set_suspended()
-pm_runtime_enable()
+pm_runtime_suspended()
+pm_runtime_mark_last_busy()
+pm_runtime_autosuspend_expiration()
 
 5. Run-time PM Initialization, Device Probing and Removal
 
@@ -524,3 +599,141 @@ poweroff and run-time suspend callback, and similarly for system resume, thaw,
 restore, and run-time resume, can achieve this with the help of the
 UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
 last argument to NULL).
+
+8. "No-Callback" Devices
+
+Some "devices" are only logical sub-devices of their parent and cannot be
+power-managed on their own.  (The prototype example is a USB interface.  Entire
+USB devices can go into low-power mode or send wake-up requests, but neither is
+possible for individual interfaces.)  The drivers for these devices have no
+need of run-time PM callbacks; if the callbacks did exist, ->runtime_suspend()
+and ->runtime_resume() would always return 0 without doing anything else and
+->runtime_idle() would always call pm_runtime_suspend().
+
+Subsystems can tell the PM core about these devices by calling
+pm_runtime_no_callbacks().  This should be done after the device structure is
+initialized and before it is registered (although after device registration is
+also okay).  The routine will set the device's power.no_callbacks flag and
+prevent the non-debugging run-time PM sysfs attributes from being created.
+
+When power.no_callbacks is set, the PM core will not invoke the
+->runtime_idle(), ->runtime_suspend(), or ->runtime_resume() callbacks.
+Instead it will assume that suspends and resumes always succeed and that idle
+devices should be suspended.
+
+As a consequence, the PM core will never directly inform the device's subsystem
+or driver about run-time power changes.  Instead, the driver for the device's
+parent must take responsibility for telling the device's driver when the
+parent's power state changes.
+
+9. Autosuspend, or automatically-delayed suspends
+
+Changing a device's power state isn't free; it requires both time and energy.
+A device should be put in a low-power state only when there's some reason to
+think it will remain in that state for a substantial time.  A common heuristic
+says that a device which hasn't been used for a while is liable to remain
+unused; following this advice, drivers should not allow devices to be suspended
+at run-time until they have been inactive for some minimum period.  Even when
+the heuristic ends up being non-optimal, it will still prevent devices from
+"bouncing" too rapidly between low-power and full-power states.
+
+The term "autosuspend" is an historical remnant.  It doesn't mean that the
+device is automatically suspended (the subsystem or driver still has to call
+the appropriate PM routines); rather it means that run-time suspends will
+automatically be delayed until the desired period of inactivity has elapsed.
+
+Inactivity is determined based on the power.last_busy field.  Drivers should
+call pm_runtime_mark_last_busy() to update this field after carrying out I/O,
+typically just before calling pm_runtime_put_autosuspend().  The desired length
+of the inactivity period is a matter of policy.  Subsystems can set this length
+initially by calling pm_runtime_set_autosuspend_delay(), but after device
+registration the length should be controlled by user space, using the
+/sys/devices/.../power/autosuspend_delay_ms attribute.
+
+In order to use autosuspend, subsystems or drivers must call
+pm_runtime_use_autosuspend() (preferably before registering the device), and
+thereafter they should use the various *_autosuspend() helper functions instead
+of the non-autosuspend counterparts:
+
+	Instead of: pm_runtime_suspend    use: pm_runtime_autosuspend;
+	Instead of: pm_schedule_suspend   use: pm_request_autosuspend;
+	Instead of: pm_runtime_put        use: pm_runtime_put_autosuspend;
+	Instead of: pm_runtime_put_sync   use: pm_runtime_put_sync_autosuspend.
+
+Drivers may also continue to use the non-autosuspend helper functions; they
+will behave normally, not taking the autosuspend delay into account.
+Similarly, if the power.use_autosuspend field isn't set then the autosuspend
+helper functions will behave just like the non-autosuspend counterparts.
+
+The implementation is well suited for asynchronous use in interrupt contexts.
+However such use inevitably involves races, because the PM core can't
+synchronize ->runtime_suspend() callbacks with the arrival of I/O requests.
+This synchronization must be handled by the driver, using its private lock.
+Here is a schematic pseudo-code example:
+
+	foo_read_or_write(struct foo_priv *foo, void *data)
+	{
+		lock(&foo->private_lock);
+		add_request_to_io_queue(foo, data);
+		if (foo->num_pending_requests++ == 0)
+			pm_runtime_get(&foo->dev);
+		if (!foo->is_suspended)
+			foo_process_next_request(foo);
+		unlock(&foo->private_lock);
+	}
+
+	foo_io_completion(struct foo_priv *foo, void *req)
+	{
+		lock(&foo->private_lock);
+		if (--foo->num_pending_requests == 0) {
+			pm_runtime_mark_last_busy(&foo->dev);
+			pm_runtime_put_autosuspend(&foo->dev);
+		} else {
+			foo_process_next_request(foo);
+		}
+		unlock(&foo->private_lock);
+		/* Send req result back to the user ... */
+	}
+
+	int foo_runtime_suspend(struct device *dev)
+	{
+		struct foo_priv foo = container_of(dev, ...);
+		int ret = 0;
+
+		lock(&foo->private_lock);
+		if (foo->num_pending_requests > 0) {
+			ret = -EBUSY;
+		} else {
+			/* ... suspend the device ... */
+			foo->is_suspended = 1;
+		}
+		unlock(&foo->private_lock);
+		return ret;
+	}
+
+	int foo_runtime_resume(struct device *dev)
+	{
+		struct foo_priv foo = container_of(dev, ...);
+
+		lock(&foo->private_lock);
+		/* ... resume the device ... */
+		foo->is_suspended = 0;
+		pm_runtime_mark_last_busy(&foo->dev);
+		if (foo->num_pending_requests > 0)
+			foo_process_requests(foo);
+		unlock(&foo->private_lock);
+		return 0;
+	}
+
+The important point is that after foo_io_completion() asks for an autosuspend,
+the foo_runtime_suspend() callback may race with foo_read_or_write().
+Therefore foo_runtime_suspend() has to check whether there are any pending I/O
+requests (while holding the private lock) before allowing the suspend to
+proceed.
+
+In addition, the power.autosuspend_delay field can be changed by user space at
+any time.  If a driver cares about this, it can call
+pm_runtime_autosuspend_expiration() from within the ->runtime_suspend()
+callback while holding its private lock.  If the function returns a nonzero
+value then the delay has not yet expired and the callback should return
+-EAGAIN.

Documentation/power/s2ram.txt

@@ -49,6 +49,13 @@ machine that doesn't boot) is:
    device (lspci and /sys/devices/pci* is your friend), and see if you can
    fix it, disable it, or trace into its resume function.
 
+   If no device matches the hash (or any matches appear to be false positives),
+   the culprit may be a device from a loadable kernel module that is not loaded
+   until after the hash is checked. You can check the hash against the current
+   devices again after more modules are loaded using sysfs:
+
+	cat /sys/power/pm_trace_dev_match
+
 For example, the above happens to be the VGA device on my EVO, which I
 used to run with "radeonfb" (it's an ATI Radeon mobility). It turns out
 that "radeonfb" simply cannot resume that device - it tries to set the

Documentation/power/swsusp.txt

@@ -66,7 +66,8 @@ swsusp saves the state of the machine into active swaps and then reboots or
 powerdowns.  You must explicitly specify the swap partition to resume from with
 ``resume='' kernel option. If signature is found it loads and restores saved
 state. If the option ``noresume'' is specified as a boot parameter, it skips
-the resuming.
+the resuming.  If the option ``hibernate=nocompress'' is specified as a boot
+parameter, it saves hibernation image without compression.
 
 In the meantime while the system is suspended you should not add/remove any
 of the hardware, write to the filesystems, etc.

Documentation/powerpc/dts-bindings/fsl/spi.txt

@@ -1,7 +1,9 @@
 * SPI (Serial Peripheral Interface)
 
 Required properties:
-- cell-index : SPI controller index.
+- cell-index : QE SPI subblock index.
+		0: QE subblock SPI1
+		1: QE subblock SPI2
 - compatible : should be "fsl,spi".
 - mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
 - reg : Offset and length of the register set for the device
@@ -29,3 +31,23 @@ Example:
 		gpios = <&gpio 18 1	// device reg=<0>
 			 &gpio 19 1>;	// device reg=<1>
 	};
+
+
+* eSPI (Enhanced Serial Peripheral Interface)
+
+Required properties:
+- compatible : should be "fsl,mpc8536-espi".
+- reg : Offset and length of the register set for the device.
+- interrupts : should contain eSPI interrupt, the device has one interrupt.
+- fsl,espi-num-chipselects : the number of the chipselect signals.
+
+Example:
+	spi@110000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,mpc8536-espi";
+		reg = <0x110000 0x1000>;
+		interrupts = <53 0x2>;
+		interrupt-parent = <&mpic>;
+		fsl,espi-num-chipselects = <4>;
+	};

Documentation/powerpc/dts-bindings/fsl/usb.txt

@@ -8,6 +8,7 @@ and additions :
 Required properties :
  - compatible : Should be "fsl-usb2-mph" for multi port host USB
    controllers, or "fsl-usb2-dr" for dual role USB controllers
+   or "fsl,mpc5121-usb2-dr" for dual role USB controllers of MPC5121
  - phy_type : For multi port host USB controllers, should be one of
    "ulpi", or "serial". For dual role USB controllers, should be
    one of "ulpi", "utmi", "utmi_wide", or "serial".
@@ -33,6 +34,12 @@ Recommended properties :
  - interrupt-parent : the phandle for the interrupt controller that
    services interrupts for this device.
 
+Optional properties :
+ - fsl,invert-drvvbus : boolean; for MPC5121 USB0 only. Indicates the
+   port power polarity of internal PHY signal DRVVBUS is inverted.
+ - fsl,invert-pwr-fault : boolean; for MPC5121 USB0 only. Indicates
+   the PWR_FAULT signal polarity is inverted.
+
 Example multi port host USB controller device node :
 	usb@22000 {
 		compatible = "fsl-usb2-mph";
@@ -57,3 +64,18 @@ Example dual role USB controller device node :
 		dr_mode = "otg";
 		phy = "ulpi";
 	};
+
+Example dual role USB controller device node for MPC5121ADS:
+
+	usb@4000 {
+		compatible = "fsl,mpc5121-usb2-dr";
+		reg = <0x4000 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		interrupt-parent = < &ipic >;
+		interrupts = <44 0x8>;
+		dr_mode = "otg";
+		phy_type = "utmi_wide";
+		fsl,invert-drvvbus;
+		fsl,invert-pwr-fault;
+	};

Documentation/scsi/st.txt

@@ -2,7 +2,7 @@ This file contains brief information about the SCSI tape driver.
 The driver is currently maintained by Kai Mäkisara (email
 Kai.Makisara@kolumbus.fi)
 
-Last modified: Sun Feb 24 21:59:07 2008 by kai.makisara
+Last modified: Sun Aug 29 18:25:47 2010 by kai.makisara
 
 
 BASICS
@@ -85,6 +85,17 @@ writing and the last operation has been a write. Two filemarks can be
 optionally written. In both cases end of data is signified by
 returning zero bytes for two consecutive reads.
 
+Writing filemarks without the immediate bit set in the SCSI command block acts
+as a synchronization point, i.e., all remaining data form the drive buffers is
+written to tape before the command returns. This makes sure that write errors
+are caught at that point, but this takes time. In some applications, several
+consecutive files must be written fast. The MTWEOFI operation can be used to
+write the filemarks without flushing the drive buffer. Writing filemark at
+close() is always flushing the drive buffers. However, if the previous
+operation is MTWEOFI, close() does not write a filemark. This can be used if
+the program wants to close/open the tape device between files and wants to
+skip waiting.
+
 If rewind, offline, bsf, or seek is done and previous tape operation was
 write, a filemark is written before moving tape.
 
@@ -301,6 +312,8 @@ MTBSR   Space backward over count records.
 MTFSS   Space forward over count setmarks.
 MTBSS   Space backward over count setmarks.
 MTWEOF  Write count filemarks.
+MTWEOFI	Write count filemarks with immediate bit set (i.e., does not
+	wait until data is on tape)
 MTWSM   Write count setmarks.
 MTREW   Rewind tape.
 MTOFFL  Set device off line (often rewind plus eject).

Documentation/usb/proc_usb_info.txt

@@ -1,12 +1,17 @@
 /proc/bus/usb filesystem output
 ===============================
-(version 2003.05.30)
+(version 2010.09.13)
 
 
 The usbfs filesystem for USB devices is traditionally mounted at
 /proc/bus/usb.  It provides the /proc/bus/usb/devices file, as well as
 the /proc/bus/usb/BBB/DDD files.
 
+In many modern systems the usbfs filsystem isn't used at all.  Instead
+USB device nodes are created under /dev/usb/ or someplace similar.  The
+"devices" file is available in debugfs, typically as
+/sys/kernel/debug/usb/devices.
+
 
 **NOTE**: If /proc/bus/usb appears empty, and a host controller
 	  driver has been linked, then you need to mount the
@@ -106,8 +111,8 @@ Legend:
 
 Topology info:
 
-T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=ddd MxCh=dd
-|   |      |      |       |       |      |        |       |__MaxChildren
+T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=dddd MxCh=dd
+|   |      |      |       |       |      |        |        |__MaxChildren
 |   |      |      |       |       |      |        |__Device Speed in Mbps
 |   |      |      |       |       |      |__DeviceNumber
 |   |      |      |       |       |__Count of devices at this level
@@ -120,8 +125,13 @@ T:  Bus=dd Lev=dd Prnt=dd Port=dd Cnt=dd Dev#=ddd Spd=ddd MxCh=dd
     Speed may be:
     	1.5	Mbit/s for low speed USB
 	12	Mbit/s for full speed USB
-	480	Mbit/s for high speed USB (added for USB 2.0)
+	480	Mbit/s for high speed USB (added for USB 2.0);
+		  also used for Wireless USB, which has no fixed speed
+	5000	Mbit/s for SuperSpeed USB (added for USB 3.0)
 
+    For reasons lost in the mists of time, the Port number is always
+    too low by 1.  For example, a device plugged into port 4 will
+    show up with "Port=03".
 
 Bandwidth info:
 B:  Alloc=ddd/ddd us (xx%), #Int=ddd, #Iso=ddd
@@ -291,7 +301,7 @@ Here's an example, from a system which has a UHCI root hub,
 an external hub connected to the root hub, and a mouse and
 a serial converter connected to the external hub.
 
-T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12  MxCh= 2
+T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
 B:  Alloc= 28/900 us ( 3%), #Int=  2, #Iso=  0
 D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=0000 ProdID=0000 Rev= 0.00
@@ -301,21 +311,21 @@ C:* #Ifs= 1 Cfg#= 1 Atr=40 MxPwr=  0mA
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
 E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=255ms
 
-T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12  MxCh= 4
+T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
 D:  Ver= 1.00 Cls=09(hub  ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=0451 ProdID=1446 Rev= 1.00
 C:* #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=100mA
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
 E:  Ad=81(I) Atr=03(Int.) MxPS=   1 Ivl=255ms
 
-T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5 MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
 D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=04b4 ProdID=0001 Rev= 0.00
 C:* #Ifs= 1 Cfg#= 1 Atr=80 MxPwr=100mA
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
 E:  Ad=81(I) Atr=03(Int.) MxPS=   3 Ivl= 10ms
 
-T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12  MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
 D:  Ver= 1.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
 P:  Vendor=0565 ProdID=0001 Rev= 1.08
 S:  Manufacturer=Peracom Networks, Inc.
@@ -330,12 +340,12 @@ E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=  8ms
 Selecting only the "T:" and "I:" lines from this (for example, by using
 "procusb ti"), we have:
 
-T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12  MxCh= 2
-T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12  MxCh= 4
+T:  Bus=00 Lev=00 Prnt=00 Port=00 Cnt=00 Dev#=  1 Spd=12   MxCh= 2
+T:  Bus=00 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=12   MxCh= 4
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=09(hub  ) Sub=00 Prot=00 Driver=hub
-T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5 MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=1.5  MxCh= 0
 I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=mouse
-T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12  MxCh= 0
+T:  Bus=00 Lev=02 Prnt=02 Port=02 Cnt=02 Dev#=  4 Spd=12   MxCh= 0
 I:  If#= 0 Alt= 0 #EPs= 3 Cls=00(>ifc ) Sub=00 Prot=00 Driver=serial
 
 

Documentation/vm/numa_memory_policy.txt

@@ -424,7 +424,7 @@ a command line tool, numactl(8), exists that allows one to:
 
 + set the shared policy for a shared memory segment via mbind(2)
 
-The numactl(8) tool is packages with the run-time version of the library
+The numactl(8) tool is packaged with the run-time version of the library
 containing the memory policy system call wrappers.  Some distributions
 package the headers and compile-time libraries in a separate development
 package.

Documentation/workqueue.txt

@@ -196,11 +196,11 @@ resources, scheduled and executed.
 	suspend operations.  Work items on the wq are drained and no
 	new work item starts execution until thawed.
 
-  WQ_RESCUER
+  WQ_MEM_RECLAIM
 
 	All wq which might be used in the memory reclaim paths _MUST_
-	have this flag set.  This reserves one worker exclusively for
-	the execution of this wq under memory pressure.
+	have this flag set.  The wq is guaranteed to have at least one
+	execution context regardless of memory pressure.
 
   WQ_HIGHPRI
 
@@ -356,11 +356,11 @@ If q1 has WQ_CPU_INTENSIVE set,
 
 6. Guidelines
 
-* Do not forget to use WQ_RESCUER if a wq may process work items which
-  are used during memory reclaim.  Each wq with WQ_RESCUER set has one
-  rescuer thread reserved for it.  If there is dependency among
-  multiple work items used during memory reclaim, they should be
-  queued to separate wq each with WQ_RESCUER.
+* Do not forget to use WQ_MEM_RECLAIM if a wq may process work items
+  which are used during memory reclaim.  Each wq with WQ_MEM_RECLAIM
+  set has an execution context reserved for it.  If there is
+  dependency among multiple work items used during memory reclaim,
+  they should be queued to separate wq each with WQ_MEM_RECLAIM.
 
 * Unless strict ordering is required, there is no need to use ST wq.
 
@@ -368,12 +368,13 @@ If q1 has WQ_CPU_INTENSIVE set,
   recommended.  In most use cases, concurrency level usually stays
   well under the default limit.
 
-* A wq serves as a domain for forward progress guarantee (WQ_RESCUER),
-  flush and work item attributes.  Work items which are not involved
-  in memory reclaim and don't need to be flushed as a part of a group
-  of work items, and don't require any special attribute, can use one
-  of the system wq.  There is no difference in execution
-  characteristics between using a dedicated wq and a system wq.
+* A wq serves as a domain for forward progress guarantee
+  (WQ_MEM_RECLAIM, flush and work item attributes.  Work items which
+  are not involved in memory reclaim and don't need to be flushed as a
+  part of a group of work items, and don't require any special
+  attribute, can use one of the system wq.  There is no difference in
+  execution characteristics between using a dedicated wq and a system
+  wq.
 
 * Unless work items are expected to consume a huge amount of CPU
   cycles, using a bound wq is usually beneficial due to the increased

Documentation/x86/x86_64/kernel-stacks

@@ -18,9 +18,9 @@ specialized stacks contain no useful data.  The main CPU stacks are:
   Used for external hardware interrupts.  If this is the first external
   hardware interrupt (i.e. not a nested hardware interrupt) then the
   kernel switches from the current task to the interrupt stack.  Like
-  the split thread and interrupt stacks on i386 (with CONFIG_4KSTACKS),
-  this gives more room for kernel interrupt processing without having
-  to increase the size of every per thread stack.
+  the split thread and interrupt stacks on i386, this gives more room
+  for kernel interrupt processing without having to increase the size
+  of every per thread stack.
 
   The interrupt stack is also used when processing a softirq.
 

Kbuild

@@ -53,6 +53,7 @@ targets += arch/$(SRCARCH)/kernel/asm-offsets.s
 # Default sed regexp - multiline due to syntax constraints
 define sed-y
 	"/^->/{s:->#\(.*\):/* \1 */:; \
+	s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 (\2) /* \3 */:; \
 	s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
 	s:->::; p;}"
 endef

MAINTAINERS

@@ -157,9 +157,11 @@ S:	Maintained
 F:	drivers/net/r8169.c
 
 8250/16?50 (AND CLONE UARTS) SERIAL DRIVER
+M:	Greg Kroah-Hartman <gregkh@suse.de>
 L:	linux-serial@vger.kernel.org
 W:	http://serial.sourceforge.net
-S:	Orphan
+S:	Maintained
+T:	quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
 F:	drivers/serial/8250*
 F:	include/linux/serial_8250.h
 
@@ -990,11 +992,23 @@ S:	Supported
 F:	arch/arm/mach-shmobile/
 F:	drivers/sh/
 
+ARM/TELECHIPS ARM ARCHITECTURE
+M:	"Hans J. Koch" <hjk@linutronix.de>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/plat-tcc/
+F:	arch/arm/mach-tcc8k/
+
 ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
+ARM/TETON BGA MACHINE SUPPORT
+M:	Mark F. Brown <mark.brown314@gmail.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+
 ARM/THECUS N2100 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1137,6 +1151,13 @@ W:	http://wireless.kernel.org/en/users/Drivers/ar9170
 S:	Maintained
 F:	drivers/net/wireless/ath/ar9170/
 
+CARL9170 LINUX COMMUNITY WIRELESS DRIVER
+M:	Christian Lamparter <chunkeey@googlemail.com>
+L:	linux-wireless@vger.kernel.org
+W:	http://wireless.kernel.org/en/users/Drivers/carl9170
+S:	Maintained
+F:	drivers/net/wireless/ath/carl9170/
+
 ATK0110 HWMON DRIVER
 M:	Luca Tettamanti <kronos.it@gmail.com>
 L:	lm-sensors@lm-sensors.org
@@ -1361,16 +1382,19 @@ F:	drivers/mtd/devices/block2mtd.c
 
 BLUETOOTH DRIVERS
 M:	Marcel Holtmann <marcel@holtmann.org>
+M:	Gustavo F. Padovan <padovan@profusion.mobi>
 L:	linux-bluetooth@vger.kernel.org
 W:	http://www.bluez.org/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/padovan/bluetooth-2.6.git
 S:	Maintained
 F:	drivers/bluetooth/
 
 BLUETOOTH SUBSYSTEM
 M:	Marcel Holtmann <marcel@holtmann.org>
+M:	Gustavo F. Padovan <padovan@profusion.mobi>
 L:	linux-bluetooth@vger.kernel.org
 W:	http://www.bluez.org/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/holtmann/bluetooth-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/padovan/bluetooth-2.6.git
 S:	Maintained
 F:	net/bluetooth/
 F:	include/net/bluetooth/
@@ -1415,6 +1439,13 @@ L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/bfa/
 
+BROCADE BNA 10 GIGABIT ETHERNET DRIVER
+M:	Rasesh Mody <rmody@brocade.com>
+M:	Debashis Dutt <ddutt@brocade.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/bna/
+
 BSG (block layer generic sg v4 driver)
 M:	FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
 L:	linux-scsi@vger.kernel.org
@@ -1527,6 +1558,8 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 S:	Supported
 F:	Documentation/filesystems/ceph.txt
 F:	fs/ceph
+F:	net/ceph
+F:	include/linux/ceph
 
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 M:	David Vrabel <david.vrabel@csr.com>
@@ -1570,9 +1603,9 @@ S:	Supported
 F:	scripts/checkpatch.pl
 
 CISCO VIC ETHERNET NIC DRIVER
-M:	Scott Feldman <scofeldm@cisco.com>
 M:	Vasanthy Kolluri <vkolluri@cisco.com>
 M:	Roopa Prabhu <roprabhu@cisco.com>
+M:	David Wang <dwang2@cisco.com>
 S:	Supported
 F:	drivers/net/enic/
 
@@ -2050,14 +2083,16 @@ F:	drivers/block/drbd/
 F:	lib/lru_cache.c
 F:	Documentation/blockdev/drbd/
 
-DRIVER CORE, KOBJECTS, AND SYSFS
+DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
 M:	Greg Kroah-Hartman <gregkh@suse.de>
 T:	quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
 S:	Supported
 F:	Documentation/kobject.txt
 F:	drivers/base/
 F:	fs/sysfs/
+F:	fs/debugfs/
 F:	include/linux/kobj*
+F:	include/linux/debugfs.h
 F:	lib/kobj*
 
 DRM DRIVERS
@@ -2177,6 +2212,13 @@ W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i5400_edac.c
 
+EDAC-I7300
+M:	Mauro Carvalho Chehab <mchehab@redhat.com>
+L:	linux-edac@vger.kernel.org
+W:	bluesmoke.sourceforge.net
+S:	Maintained
+F:	drivers/edac/i7300_edac.c
+
 EDAC-I7CORE
 M:	Mauro Carvalho Chehab <mchehab@redhat.com>
 L:	linux-edac@vger.kernel.org
@@ -2904,6 +2946,12 @@ M:	Brian King <brking@us.ibm.com>
 S:	Supported
 F:	drivers/scsi/ipr.*
 
+IBM Power Virtual Ethernet Device Driver
+M:	Santiago Leon <santil@linux.vnet.ibm.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ibmveth.*
+
 IBM ServeRAID RAID DRIVER
 P:	Jack Hammer
 M:	Dave Jeffery <ipslinux@adaptec.com>
@@ -3162,7 +3210,7 @@ F:	drivers/net/ioc3-eth.c
 
 IOC3 SERIAL DRIVER
 M:	Pat Gefre <pfg@sgi.com>
-L:	linux-mips@linux-mips.org
+L:	linux-serial@vger.kernel.org
 S:	Maintained
 F:	drivers/serial/ioc3_serial.c
 
@@ -3239,6 +3287,12 @@ F:	drivers/net/irda/
 F:	include/net/irda/
 F:	net/irda/
 
+IRQ SUBSYSTEM
+M:	Thomas Gleixner <tglx@linutronix.de>
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core
+F:	kernel/irq/
+
 ISAPNP
 M:	Jaroslav Kysela <perex@perex.cz>
 S:	Maintained
@@ -3331,6 +3385,12 @@ F:	fs/jbd*/
 F:	include/linux/ext*jbd*.h
 F:	include/linux/jbd*.h
 
+JSM Neo PCI based serial card
+M:	Breno Leitao <leitao@linux.vnet.ibm.com>
+L:	linux-serial@vger.kernel.org
+S:	Maintained
+F:	drivers/serial/jsm/
+
 K8TEMP HARDWARE MONITORING DRIVER
 M:	Rudolf Marek <r.marek@assembler.cz>
 L:	lm-sensors@lm-sensors.org
@@ -3381,7 +3441,7 @@ F:	scripts/package/
 
 KERNEL JANITORS
 L:	kernel-janitors@vger.kernel.org
-W:	http://janitor.kernelnewbies.org/
+W:	http://kernelnewbies.org/KernelJanitors
 S:	Odd Fixes
 
 KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
@@ -4362,13 +4422,12 @@ F:	Documentation/filesystems/dlmfs.txt
 F:	fs/ocfs2/
 
 ORINOCO DRIVER
-M:	Pavel Roskin <proski@gnu.org>
-M:	David Gibson <hermes@gibson.dropbear.id.au>
 L:	linux-wireless@vger.kernel.org
 L:	orinoco-users@lists.sourceforge.net
 L:	orinoco-devel@lists.sourceforge.net
+W:	http://linuxwireless.org/en/users/Drivers/orinoco
 W:	http://www.nongnu.org/orinoco/
-S:	Maintained
+S:	Orphan
 F:	drivers/net/wireless/orinoco/
 
 OSD LIBRARY and FILESYSTEM
@@ -4401,6 +4460,15 @@ L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-pasemi.c
 
+PADATA PARALLEL EXECUTION MECHANISM
+M:	Steffen Klassert <steffen.klassert@secunet.com>
+L:	linux-kernel@vger.kernel.org
+L:	linux-crypto@vger.kernel.org
+S:	Maintained
+F:	kernel/padata.c
+F:	include/linux/padata.h
+F:	Documentation/padata.txt
+
 PANASONIC LAPTOP ACPI EXTRAS DRIVER
 M:	Harald Welte <laforge@gnumonks.org>
 L:	platform-driver-x86@vger.kernel.org
@@ -4480,6 +4548,12 @@ S:	Maintained
 F:	drivers/leds/leds-pca9532.c
 F:	include/linux/leds-pca9532.h
 
+PCA9541 I2C BUS MASTER SELECTOR DRIVER
+M:	Guenter Roeck <guenter.roeck@ericsson.com>
+L:	linux-i2c@vger.kernel.org
+S:	Maintained
+F:	drivers/i2c/muxes/pca9541.c
+
 PCA9564/PCA9665 I2C BUS DRIVER
 M:	Wolfram Sang <w.sang@pengutronix.de>
 L:	linux-i2c@vger.kernel.org
@@ -4528,6 +4602,13 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/pcnet32.c
 
+PCRYPT PARALLEL CRYPTO ENGINE
+M:	Steffen Klassert <steffen.klassert@secunet.com>
+L:	linux-crypto@vger.kernel.org
+S:	Maintained
+F:	crypto/pcrypt.c
+F:	include/crypto/pcrypt.h
+
 PER-TASK DELAY ACCOUNTING
 M:	Balbir Singh <balbir@linux.vnet.ibm.com>
 S:	Maintained
@@ -4556,6 +4637,14 @@ L:	linux-abi-devel@lists.sourceforge.net
 S:	Maintained
 F:	include/linux/personality.h
 
+PHONET PROTOCOL
+M:	Remi Denis-Courmont <remi.denis-courmont@nokia.com>
+S:	Supported
+F:	Documentation/networking/phonet.txt
+F:	include/linux/phonet.h
+F:	include/net/phonet/
+F:	net/phonet/
+
 PHRAM MTD DRIVER
 M:	Joern Engel <joern@lazybastard.org>
 L:	linux-mtd@lists.infradead.org
@@ -4805,6 +4894,15 @@ F:	fs/qnx4/
 F:	include/linux/qnx4_fs.h
 F:	include/linux/qnxtypes.h
 
+RADOS BLOCK DEVICE (RBD)
+F:	include/linux/qnxtypes.h
+M:	Yehuda Sadeh <yehuda@hq.newdream.net>
+M:	Sage Weil <sage@newdream.net>
+M:	ceph-devel@vger.kernel.org
+S:	Supported
+F:	drivers/block/rbd.c
+F:	drivers/block/rbd_types.h
+
 RADEON FRAMEBUFFER DISPLAY DRIVER
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 L:	linux-fbdev@vger.kernel.org
@@ -5934,6 +6032,14 @@ S:	Maintained
 F:	Documentation/usb/acm.txt
 F:	drivers/usb/class/cdc-acm.*
 
+USB ATTACHED SCSI
+M:	Matthew Wilcox <willy@linux.intel.com>
+M:	Sarah Sharp <sarah.a.sharp@linux.intel.com>
+L:	linux-usb@vger.kernel.org
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/usb/storage/uas.c
+
 USB BLOCK DRIVER (UB ub)
 M:	Pete Zaitcev <zaitcev@redhat.com>
 L:	linux-usb@vger.kernel.org
@@ -6442,21 +6548,21 @@ S:	Maintained
 F:	drivers/input/misc/wistron_btns.c
 
 WL1251 WIRELESS DRIVER
-M:	Kalle Valo <kalle.valo@iki.fi>
+M:	Kalle Valo <kvalo@adurom.com>
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Maintained
-F:	drivers/net/wireless/wl12xx/*
-X:	drivers/net/wireless/wl12xx/wl1271*
+F:	drivers/net/wireless/wl1251/*
 
 WL1271 WIRELESS DRIVER
 M:	Luciano Coelho <luciano.coelho@nokia.com>
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git
 S:	Maintained
 F:	drivers/net/wireless/wl12xx/wl1271*
+F:	include/linux/wl12xx.h
 
 WL3501 WIRELESS PCMCIA CARD DRIVER
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
@@ -6603,6 +6709,20 @@ M:	"Maciej W. Rozycki" <macro@linux-mips.org>
 S:	Maintained
 F:	drivers/serial/zs.*
 
+GRE DEMULTIPLEXER DRIVER
+M:	Dmitry Kozlov <xeb@mail.ru>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	net/ipv4/gre.c
+F:	include/net/gre.h
+
+PPTP DRIVER
+M:	Dmitry Kozlov <xeb@mail.ru>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/pptp.c
+W:	http://sourceforge.net/projects/accel-pptp
+
 THE REST
 M:	Linus Torvalds <torvalds@linux-foundation.org>
 L:	linux-kernel@vger.kernel.org

Makefile

@@ -1,8 +1,8 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 36
-EXTRAVERSION = -rc7
-NAME = Sheep on Meth
+EXTRAVERSION =
+NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -554,8 +554,15 @@ endif
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else
+# Some targets (ARM with Thumb2, for example), can't be built with frame
+# pointers.  For those, we don't have FUNCTION_TRACER automatically
+# select FRAME_POINTER.  However, FUNCTION_TRACER adds -pg, and this is
+# incompatible with -fomit-frame-pointer with current GCC, so we don't use
+# -fomit-frame-pointer with FUNCTION_TRACER.
+ifndef CONFIG_FUNCTION_TRACER
 KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
+endif
 
 ifdef CONFIG_DEBUG_INFO
 KBUILD_CFLAGS	+= -g
@@ -568,6 +575,12 @@ endif
 
 ifdef CONFIG_FUNCTION_TRACER
 KBUILD_CFLAGS	+= -pg
+ifdef CONFIG_DYNAMIC_FTRACE
+	ifdef CONFIG_HAVE_C_RECORDMCOUNT
+		BUILD_C_RECORDMCOUNT := y
+		export BUILD_C_RECORDMCOUNT
+	endif
+endif
 endif
 
 # We trigger additional mismatches with less inlining
@@ -591,6 +604,11 @@ KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
 # But warn user when we do so
 warn-assign = \

arch/Kconfig

@@ -158,4 +158,7 @@ config HAVE_PERF_EVENTS_NMI
 	  subsystem.  Also has support for calculating CPU cycle events
 	  to determine how many clock cycles in a given period.
 
+config HAVE_ARCH_JUMP_LABEL
+	bool
+
 source "kernel/gcov/Kconfig"

arch/alpha/Kconfig

@@ -9,6 +9,7 @@ config ALPHA
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_DMA_ATTRS
 	help

arch/alpha/include/asm/irqflags.h

@@ -0,0 +1,67 @@
+#ifndef __ALPHA_IRQFLAGS_H
+#define __ALPHA_IRQFLAGS_H
+
+#include <asm/system.h>
+
+#define IPL_MIN		0
+#define IPL_SW0		1
+#define IPL_SW1		2
+#define IPL_DEV0	3
+#define IPL_DEV1	4
+#define IPL_TIMER	5
+#define IPL_PERF	6
+#define IPL_POWERFAIL	6
+#define IPL_MCHECK	7
+#define IPL_MAX		7
+
+#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK
+#undef IPL_MIN
+#define IPL_MIN		__min_ipl
+extern int __min_ipl;
+#endif
+
+#define getipl()		(rdps() & 7)
+#define setipl(ipl)		((void) swpipl(ipl))
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	return rdps();
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	setipl(IPL_MAX);
+	barrier();
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = swpipl(IPL_MAX);
+	barrier();
+	return flags;
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	barrier();
+	setipl(IPL_MIN);
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	barrier();
+	setipl(flags);
+	barrier();
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags == IPL_MAX;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(getipl());
+}
+
+#endif /* __ALPHA_IRQFLAGS_H */

arch/alpha/include/asm/perf_event.h

@@ -1,11 +1,6 @@
 #ifndef __ASM_ALPHA_PERF_EVENT_H
 #define __ASM_ALPHA_PERF_EVENT_H
 
-/* Alpha only supports software events through this interface. */
-extern void set_perf_event_pending(void);
-
-#define PERF_EVENT_INDEX_OFFSET 0
-
 #ifdef CONFIG_PERF_EVENTS
 extern void init_hw_perf_events(void);
 #else

arch/alpha/include/asm/system.h

@@ -259,34 +259,6 @@ __CALL_PAL_RW2(wrperfmon, unsigned long, unsigned long, unsigned long);
 __CALL_PAL_W1(wrusp, unsigned long);
 __CALL_PAL_W1(wrvptptr, unsigned long);
 
-#define IPL_MIN		0
-#define IPL_SW0		1
-#define IPL_SW1		2
-#define IPL_DEV0	3
-#define IPL_DEV1	4
-#define IPL_TIMER	5
-#define IPL_PERF	6
-#define IPL_POWERFAIL	6
-#define IPL_MCHECK	7
-#define IPL_MAX		7
-
-#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK
-#undef IPL_MIN
-#define IPL_MIN		__min_ipl
-extern int __min_ipl;
-#endif
-
-#define getipl()		(rdps() & 7)
-#define setipl(ipl)		((void) swpipl(ipl))
-
-#define local_irq_disable()			do { setipl(IPL_MAX); barrier(); } while(0)
-#define local_irq_enable()			do { barrier(); setipl(IPL_MIN); } while(0)
-#define local_save_flags(flags)	((flags) = rdps())
-#define local_irq_save(flags)	do { (flags) = swpipl(IPL_MAX); barrier(); } while(0)
-#define local_irq_restore(flags)	do { barrier(); setipl(flags); barrier(); } while(0)
-
-#define irqs_disabled()	(getipl() == IPL_MAX)
-
 /*
  * TB routines..
  */

arch/alpha/kernel/perf_event.c

@@ -307,7 +307,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count  - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
+	delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
 
 	/* It is possible on very rare occasions that the PMC has overflowed
 	 * but the interrupt is yet to come.  Detect and fix this situation.
@@ -402,14 +402,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
 		struct hw_perf_event *hwc = &pe->hw;
 		int idx = hwc->idx;
 
-		if (cpuc->current_idx[j] != PMC_NO_INDEX) {
-			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
-			continue;
+		if (cpuc->current_idx[j] == PMC_NO_INDEX) {
+			alpha_perf_event_set_period(pe, hwc, idx);
+			cpuc->current_idx[j] = idx;
 		}
 
-		alpha_perf_event_set_period(pe, hwc, idx);
-		cpuc->current_idx[j] = idx;
-		cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
+		if (!(hwc->state & PERF_HES_STOPPED))
+			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
 	}
 	cpuc->config = cpuc->event[0]->hw.config_base;
 }
@@ -420,12 +419,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static int alpha_pmu_enable(struct perf_event *event)
+static int alpha_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	/*
 	 * The Sparc code has the IRQ disable first followed by the perf
@@ -435,8 +435,8 @@ static int alpha_pmu_enable(struct perf_event *event)
 	 * nevertheless we disable the PMCs first to enable a potential
 	 * final PMI to occur before we disable interrupts.
 	 */
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	/* Default to error to be returned */
 	ret = -EAGAIN;
@@ -455,8 +455,12 @@ static int alpha_pmu_enable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	hwc->state = PERF_HES_UPTODATE;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_STOPPED;
+
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 
 	return ret;
 }
@@ -467,15 +471,15 @@ static int alpha_pmu_enable(struct perf_event *event)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static void alpha_pmu_disable(struct perf_event *event)
+static void alpha_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	unsigned long flags;
+	unsigned long irq_flags;
 	int j;
 
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	for (j = 0; j < cpuc->n_events; j++) {
 		if (event == cpuc->event[j]) {
@@ -501,8 +505,8 @@ static void alpha_pmu_disable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 }
 
 
@@ -514,13 +518,44 @@ static void alpha_pmu_read(struct perf_event *event)
 }
 
 
-static void alpha_pmu_unthrottle(struct perf_event *event)
+static void alpha_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		cpuc->idx_mask &= ~(1UL<<hwc->idx);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		alpha_perf_event_update(event, hwc, hwc->idx, 0);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_DISABLE, (1UL<<hwc->idx));
+}
+
+
+static void alpha_pmu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+		alpha_perf_event_set_period(event, hwc, hwc->idx);
+	}
+
+	hwc->state = 0;
+
 	cpuc->idx_mask |= 1UL<<hwc->idx;
-	wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
 }
 
 
@@ -642,39 +677,36 @@ static int __hw_perf_event_init(struct perf_event *event)
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= alpha_pmu_enable,
-	.disable	= alpha_pmu_disable,
-	.read		= alpha_pmu_read,
-	.unthrottle	= alpha_pmu_unthrottle,
-};
-
-
 /*
  * Main entry point to initialise a HW performance event.
  */
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!alpha_pmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	/* Do the real initialisation work. */
 	err = __hw_perf_event_init(event);
 
-	if (err)
-		return ERR_PTR(err);
-
-	return &pmu;
+	return err;
 }
 
-
-
 /*
  * Main entry point - enable HW performance counters.
  */
-void hw_perf_enable(void)
+static void alpha_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -700,7 +732,7 @@ void hw_perf_enable(void)
  * Main entry point - disable HW performance counters.
  */
 
-void hw_perf_disable(void)
+static void alpha_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -713,6 +745,17 @@ void hw_perf_disable(void)
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= alpha_pmu_enable,
+	.pmu_disable	= alpha_pmu_disable,
+	.event_init	= alpha_pmu_event_init,
+	.add		= alpha_pmu_add,
+	.del		= alpha_pmu_del,
+	.start		= alpha_pmu_start,
+	.stop		= alpha_pmu_stop,
+	.read		= alpha_pmu_read,
+};
+
 
 /*
  * Main entry point - don't know when this is called but it
@@ -766,7 +809,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 
 	/* la_ptr is the counter that overflowed. */
-	if (unlikely(la_ptr >= perf_max_events)) {
+	if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) {
 		/* This should never occur! */
 		irq_err_count++;
 		pr_warning("PMI: silly index %ld\n", la_ptr);
@@ -807,7 +850,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 			/* Interrupts coming too quickly; "throttle" the
 			 * counter, i.e., disable it for a little while.
 			 */
-			cpuc->idx_mask &= ~(1UL<<idx);
+			alpha_pmu_stop(event, 0);
 		}
 	}
 	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
@@ -837,6 +880,7 @@ void __init init_hw_perf_events(void)
 
 	/* And set up PMU specification */
 	alpha_pmu = &ev67_pmu;
-	perf_max_events = alpha_pmu->num_pmcs;
+
+	perf_pmu_register(&pmu);
 }
 

arch/alpha/kernel/time.c

@@ -41,7 +41,7 @@
 #include <linux/init.h>
 #include <linux/bcd.h>
 #include <linux/profile.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -83,25 +83,25 @@ static struct {
 
 unsigned long est_cycle_freq;
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
 
-DEFINE_PER_CPU(u8, perf_event_pending);
+DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_perf_event_pending_flag()  __get_cpu_var(perf_event_pending) = 1
-#define test_perf_event_pending()      __get_cpu_var(perf_event_pending)
-#define clear_perf_event_pending()     __get_cpu_var(perf_event_pending) = 0
+#define set_irq_work_pending_flag()  __get_cpu_var(irq_work_pending) = 1
+#define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
+#define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
 
-void set_perf_event_pending(void)
+void set_irq_work_pending(void)
 {
-	set_perf_event_pending_flag();
+	set_irq_work_pending_flag();
 }
 
-#else  /* CONFIG_PERF_EVENTS */
+#else  /* CONFIG_IRQ_WORK */
 
-#define test_perf_event_pending()      0
-#define clear_perf_event_pending()
+#define test_irq_work_pending()      0
+#define clear_irq_work_pending()
 
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_IRQ_WORK */
 
 
 static inline __u32 rpcc(void)
@@ -191,9 +191,9 @@ irqreturn_t timer_interrupt(int irq, void *dev)
 
 	write_sequnlock(&xtime_lock);
 
-	if (test_perf_event_pending()) {
-		clear_perf_event_pending();
-		perf_event_do_pending();
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
 	}
 
 #ifndef CONFIG_SMP

arch/arm/Kconfig

@@ -19,13 +19,17 @@ config ARM
 	select HAVE_KPROBES if (!XIP_KERNEL)
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
+	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
+	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL)
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V7))
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -145,6 +149,9 @@ config ARCH_HAS_CPUFREQ
 	  and that the relevant menu configurations are displayed for
 	  it.
 
+config ARCH_HAS_CPU_IDLE_WAIT
+       def_bool y
+
 config GENERIC_HWEIGHT
 	bool
 	default y
@@ -510,6 +517,7 @@ config ARCH_MMP
 	select GENERIC_CLOCKEVENTS
 	select TICK_ONESHOT
 	select PLAT_PXA
+	select SPARSE_IRQ
 	help
 	  Support for Marvell's PXA168/PXA910(MMP) and MMP2 processor line.
 
@@ -587,6 +595,7 @@ config ARCH_PXA
 	select GENERIC_CLOCKEVENTS
 	select TICK_ONESHOT
 	select PLAT_PXA
+	select SPARSE_IRQ
 	help
 	  Support for Intel/Marvell's PXA2xx/PXA3xx processor line.
 
@@ -678,8 +687,8 @@ config ARCH_S3C64XX
 	help
 	  Samsung S3C64XX series based systems
 
-config ARCH_S5P6440
-	bool "Samsung S5P6440"
+config ARCH_S5P64X0
+	bool "Samsung S5P6440 S5P6450"
 	select CPU_V6
 	select GENERIC_GPIO
 	select HAVE_CLK
@@ -688,7 +697,8 @@ config ARCH_S5P6440
 	select HAVE_S3C2410_I2C
 	select HAVE_S3C_RTC
 	help
-	  Samsung S5P6440 CPU based systems
+	  Samsung S5P64X0 CPU based systems, such as the Samsung SMDK6440,
+	  SMDK6450.
 
 config ARCH_S5P6442
 	bool "Samsung S5P6442"
@@ -747,6 +757,15 @@ config ARCH_SHARK
 	  Support for the StrongARM based Digital DNARD machine, also known
 	  as "Shark" (<http://www.shark-linux.de/shark.html>).
 
+config ARCH_TCC_926
+	bool "Telechips TCC ARM926-based systems"
+	select CPU_ARM926T
+	select HAVE_CLK
+	select COMMON_CLKDEV
+	select GENERIC_CLOCKEVENTS
+	help
+	  Support for Telechips TCC ARM926-based systems.
+
 config ARCH_LH7A40X
 	bool "Sharp LH7A40X"
 	select CPU_ARM922T
@@ -915,6 +934,8 @@ source "arch/arm/plat-s5p/Kconfig"
 
 source "arch/arm/plat-spear/Kconfig"
 
+source "arch/arm/plat-tcc/Kconfig"
+
 if ARCH_S3C2410
 source "arch/arm/mach-s3c2400/Kconfig"
 source "arch/arm/mach-s3c2410/Kconfig"
@@ -928,7 +949,7 @@ if ARCH_S3C64XX
 source "arch/arm/mach-s3c64xx/Kconfig"
 endif
 
-source "arch/arm/mach-s5p6440/Kconfig"
+source "arch/arm/mach-s5p64x0/Kconfig"
 
 source "arch/arm/mach-s5p6442/Kconfig"
 
@@ -1002,7 +1023,7 @@ endif
 
 config ARM_ERRATA_411920
 	bool "ARM errata: Invalidation of the Instruction Cache operation can fail"
-	depends on CPU_V6 && !SMP
+	depends on CPU_V6
 	help
 	  Invalidation of the Instruction Cache operation can
 	  fail. This erratum is present in 1136 (before r1p4), 1156 and 1176.
@@ -1181,13 +1202,13 @@ source "kernel/time/Kconfig"
 
 config SMP
 	bool "Symmetric Multi-Processing (EXPERIMENTAL)"
-	depends on EXPERIMENTAL && (REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP ||\
-		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
-		 ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4)
+	depends on EXPERIMENTAL
 	depends on GENERIC_CLOCKEVENTS
+	depends on REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP || \
+		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
+		 ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4
 	select USE_GENERIC_SMP_HELPERS
-	select HAVE_ARM_SCU if ARCH_REALVIEW || ARCH_OMAP4 || ARCH_S5PV310 ||\
-		 ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4
+	select HAVE_ARM_SCU
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
@@ -1201,10 +1222,23 @@ config SMP
 
 	  See also <file:Documentation/i386/IO-APIC.txt>,
 	  <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
-	  <http://www.linuxdoc.org/docs.html#howto>.
+	  <http://tldp.org/HOWTO/SMP-HOWTO.html>.
 
 	  If you don't know what to do here, say N.
 
+config SMP_ON_UP
+	bool "Allow booting SMP kernel on uniprocessor systems (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on SMP && !XIP && !THUMB2_KERNEL
+	default y
+	help
+	  SMP kernels contain instructions which fail on non-SMP processors.
+	  Enabling this option allows the kernel to modify itself to make
+	  these instructions safe.  Disabling it allows about 1K of space
+	  savings.
+
+	  If you don't know what to do here, say Y.
+
 config HAVE_ARM_SCU
 	bool
 	depends on SMP
@@ -1255,12 +1289,9 @@ config HOTPLUG_CPU
 
 config LOCAL_TIMERS
 	bool "Use local timer interrupts"
-	depends on SMP && (REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || \
-		REALVIEW_EB_A9MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
-		ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4)
+	depends on SMP
 	default y
-	select HAVE_ARM_TWD if ARCH_REALVIEW || ARCH_OMAP4 || ARCH_S5PV310 || \
-		ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS
+	select HAVE_ARM_TWD
 	help
 	  Enable support for local timers on SMP platforms, rather then the
 	  legacy IPI broadcast method.  Local timers allows the system
@@ -1271,7 +1302,7 @@ source kernel/Kconfig.preempt
 
 config HZ
 	int
-	default 200 if ARCH_EBSA110 || ARCH_S3C2410 || ARCH_S5P6440 || \
+	default 200 if ARCH_EBSA110 || ARCH_S3C2410 || ARCH_S5P64X0 || \
 		ARCH_S5P6442 || ARCH_S5PV210 || ARCH_S5PV310
 	default OMAP_32K_TIMER_HZ if ARCH_OMAP && OMAP_32K_TIMER
 	default AT91_TIMER_HZ if ARCH_AT91
@@ -1477,6 +1508,20 @@ config UACCESS_WITH_MEMCPY
 	  However, if the CPU data cache is using a write-allocate mode,
 	  this option is unlikely to provide any performance gain.
 
+config SECCOMP
+	bool
+	prompt "Enable seccomp to safely compute untrusted bytecode"
+	---help---
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
 config CC_STACKPROTECTOR
 	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
 	help

arch/arm/Kconfig.debug

@@ -2,6 +2,20 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
+config STRICT_DEVMEM
+	bool "Filter access to /dev/mem"
+	depends on MMU
+	---help---
+	  If this option is disabled, you allow userspace (root) access to all
+	  of memory, including kernel and userspace memory. Accidental
+	  access to this is obviously disastrous, but specific access can
+	  be used by people debugging the kernel.
+
+	  If this option is switched on, the /dev/mem file only allows
+	  userspace access to memory mapped peripherals.
+
+          If in doubt, say Y.
+
 # RMK wants arm kernels compiled with frame pointers or stack unwinding.
 # If you know what you are doing and are willing to live without stack
 # traces, you can get a slightly smaller kernel by setting this option to
@@ -27,6 +41,11 @@ config ARM_UNWIND
 	  the performance is not affected. Currently, this feature
 	  only works with EABI compilers. If unsure say Y.
 
+config OLD_MCOUNT
+	bool
+	depends on FUNCTION_TRACER && FRAME_POINTER
+	default y
+
 config DEBUG_USER
 	bool "Verbose user fault messages"
 	help

arch/arm/Makefile

@@ -173,7 +173,7 @@ machine-$(CONFIG_ARCH_RPC)		:= rpc
 machine-$(CONFIG_ARCH_S3C2410)		:= s3c2410 s3c2400 s3c2412 s3c2416 s3c2440 s3c2443
 machine-$(CONFIG_ARCH_S3C24A0)		:= s3c24a0
 machine-$(CONFIG_ARCH_S3C64XX)		:= s3c64xx
-machine-$(CONFIG_ARCH_S5P6440)		:= s5p6440
+machine-$(CONFIG_ARCH_S5P64X0)		:= s5p64x0
 machine-$(CONFIG_ARCH_S5P6442)		:= s5p6442
 machine-$(CONFIG_ARCH_S5PC100)		:= s5pc100
 machine-$(CONFIG_ARCH_S5PV210)		:= s5pv210
@@ -183,6 +183,7 @@ machine-$(CONFIG_ARCH_SHARK)		:= shark
 machine-$(CONFIG_ARCH_SHMOBILE) 	:= shmobile
 machine-$(CONFIG_ARCH_STMP378X)		:= stmp378x
 machine-$(CONFIG_ARCH_STMP37XX)		:= stmp37xx
+machine-$(CONFIG_ARCH_TCC8K)		:= tcc8k
 machine-$(CONFIG_ARCH_TEGRA)		:= tegra
 machine-$(CONFIG_ARCH_U300)		:= u300
 machine-$(CONFIG_ARCH_U8500)		:= ux500
@@ -202,6 +203,7 @@ plat-$(CONFIG_ARCH_MXC)		:= mxc
 plat-$(CONFIG_ARCH_OMAP)	:= omap
 plat-$(CONFIG_ARCH_S3C64XX)	:= samsung
 plat-$(CONFIG_ARCH_STMP3XXX)	:= stmp3xxx
+plat-$(CONFIG_ARCH_TCC_926)	:= tcc
 plat-$(CONFIG_PLAT_IOP)		:= iop
 plat-$(CONFIG_PLAT_NOMADIK)	:= nomadik
 plat-$(CONFIG_PLAT_ORION)	:= orion
@@ -245,13 +247,14 @@ ifeq ($(FASTFPE),$(wildcard $(FASTFPE)))
 FASTFPE_OBJ	:=$(FASTFPE)/
 endif
 
-# If we have a machine-specific directory, then include it in the build.
-core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
-core-y				+= $(machdirs) $(platdirs)
 core-$(CONFIG_FPE_NWFPE)	+= arch/arm/nwfpe/
 core-$(CONFIG_FPE_FASTFPE)	+= $(FASTFPE_OBJ)
 core-$(CONFIG_VFP)		+= arch/arm/vfp/
 
+# If we have a machine-specific directory, then include it in the build.
+core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
+core-y				+= $(machdirs) $(platdirs)
+
 drivers-$(CONFIG_OPROFILE)      += arch/arm/oprofile/
 
 libs-y				:= arch/arm/lib/ $(libs-y)

arch/arm/common/gic.c

@@ -67,25 +67,11 @@ static inline unsigned int gic_irq(unsigned int irq)
 
 /*
  * Routines to acknowledge, disable and enable interrupts
- *
- * Linux assumes that when we're done with an interrupt we need to
- * unmask it, in the same way we need to unmask an interrupt when
- * we first enable it.
- *
- * The GIC has a separate notion of "end of interrupt" to re-enable
- * an interrupt after handling, in order to support hardware
- * prioritisation.
- *
- * We can make the GIC behave in the way that Linux expects by making
- * our "acknowledge" routine disable the interrupt, then mark it as
- * complete.
  */
 static void gic_ack_irq(unsigned int irq)
 {
-	u32 mask = 1 << (irq % 32);
 
 	spin_lock(&irq_controller_lock);
-	writel(mask, gic_dist_base(irq) + GIC_DIST_ENABLE_CLEAR + (gic_irq(irq) / 32) * 4);
 	writel(gic_irq(irq), gic_cpu_base(irq) + GIC_CPU_EOI);
 	spin_unlock(&irq_controller_lock);
 }

arch/arm/common/icst.c

@@ -8,7 +8,7 @@
  * published by the Free Software Foundation.
  *
  *  Support functions for calculating clocks/divisors for the ICST307
- *  clock generators.  See http://www.icst.com/ for more information
+ *  clock generators.  See http://www.idt.com/ for more information
  *  on these devices.
  *
  *  This is an almost identical implementation to the ICST525 clock generator.

arch/arm/common/pl330.c

@@ -146,8 +146,7 @@
 #define DESIGNER	0x41
 #define REVISION	0x0
 #define INTEG_CFG	0x0
-#define PERIPH_ID_VAL	((PART << 0) | (DESIGNER << 12) \
-			  | (REVISION << 20) | (INTEG_CFG << 24))
+#define PERIPH_ID_VAL	((PART << 0) | (DESIGNER << 12))
 
 #define PCELL_ID_VAL	0xb105f00d
 
@@ -1859,10 +1858,10 @@ int pl330_add(struct pl330_info *pi)
 	regs = pi->base;
 
 	/* Check if we can handle this DMAC */
-	if (get_id(pi, PERIPH_ID) != PERIPH_ID_VAL
+	if ((get_id(pi, PERIPH_ID) & 0xfffff) != PERIPH_ID_VAL
 	   || get_id(pi, PCELL_ID) != PCELL_ID_VAL) {
 		dev_err(pi->dev, "PERIPH_ID 0x%x, PCELL_ID 0x%x !\n",
-			readl(regs + PERIPH_ID), readl(regs + PCELL_ID));
+			get_id(pi, PERIPH_ID), get_id(pi, PCELL_ID));
 		return -EINVAL;
 	}
 

arch/arm/common/sa1111.c

@@ -678,7 +678,7 @@ out:
  *	%-EBUSY		physical address already marked in-use.
  *	%0		successful.
  */
-static int
+static int __devinit
 __sa1111_probe(struct device *me, struct resource *mem, int irq)
 {
 	struct sa1111 *sachip;

arch/arm/common/scoop.c

@@ -44,12 +44,12 @@ void reset_scoop(struct device *dev)
 {
 	struct scoop_dev *sdev = dev_get_drvdata(dev);
 
-	iowrite16(0x0100, sdev->base + SCOOP_MCR);  // 00
-	iowrite16(0x0000, sdev->base + SCOOP_CDR);  // 04
-	iowrite16(0x0000, sdev->base + SCOOP_CCR);  // 10
-	iowrite16(0x0000, sdev->base + SCOOP_IMR);  // 18
-	iowrite16(0x00FF, sdev->base + SCOOP_IRM);  // 14
-	iowrite16(0x0000, sdev->base + SCOOP_ISR);  // 1C
+	iowrite16(0x0100, sdev->base + SCOOP_MCR);  /* 00 */
+	iowrite16(0x0000, sdev->base + SCOOP_CDR);  /* 04 */
+	iowrite16(0x0000, sdev->base + SCOOP_CCR);  /* 10 */
+	iowrite16(0x0000, sdev->base + SCOOP_IMR);  /* 18 */
+	iowrite16(0x00FF, sdev->base + SCOOP_IRM);  /* 14 */
+	iowrite16(0x0000, sdev->base + SCOOP_ISR);  /* 1C */
 	iowrite16(0x0000, sdev->base + SCOOP_IRM);
 }
 

arch/arm/common/uengine.c

@@ -312,16 +312,16 @@ static void generate_ucode(u8 *ucode, u32 *gpr_a, u32 *gpr_b)
 		b1 = (gpr_a[i] >> 8) & 0xff;
 		b0 = gpr_a[i] & 0xff;
 
-		// immed[@ai, (b1 << 8) | b0]
-		// 11110000 0000VVVV VVVV11VV VVVVVV00 1IIIIIII
+		/* immed[@ai, (b1 << 8) | b0] */
+		/* 11110000 0000VVVV VVVV11VV VVVVVV00 1IIIIIII */
 		ucode[offset++] = 0xf0;
 		ucode[offset++] = (b1 >> 4);
 		ucode[offset++] = (b1 << 4) | 0x0c | (b0 >> 6);
 		ucode[offset++] = (b0 << 2);
 		ucode[offset++] = 0x80 | i;
 
-		// immed_w1[@ai, (b3 << 8) | b2]
-		// 11110100 0100VVVV VVVV11VV VVVVVV00 1IIIIIII
+		/* immed_w1[@ai, (b3 << 8) | b2] */
+		/* 11110100 0100VVVV VVVV11VV VVVVVV00 1IIIIIII */
 		ucode[offset++] = 0xf4;
 		ucode[offset++] = 0x40 | (b3 >> 4);
 		ucode[offset++] = (b3 << 4) | 0x0c | (b2 >> 6);
@@ -340,16 +340,16 @@ static void generate_ucode(u8 *ucode, u32 *gpr_a, u32 *gpr_b)
 		b1 = (gpr_b[i] >> 8) & 0xff;
 		b0 = gpr_b[i] & 0xff;
 
-		// immed[@bi, (b1 << 8) | b0]
-		// 11110000 0000VVVV VVVV001I IIIIII11 VVVVVVVV
+		/* immed[@bi, (b1 << 8) | b0] */
+		/* 11110000 0000VVVV VVVV001I IIIIII11 VVVVVVVV */
 		ucode[offset++] = 0xf0;
 		ucode[offset++] = (b1 >> 4);
 		ucode[offset++] = (b1 << 4) | 0x02 | (i >> 6);
 		ucode[offset++] = (i << 2) | 0x03;
 		ucode[offset++] = b0;
 
-		// immed_w1[@bi, (b3 << 8) | b2]
-		// 11110100 0100VVVV VVVV001I IIIIII11 VVVVVVVV
+		/* immed_w1[@bi, (b3 << 8) | b2] */
+		/* 11110100 0100VVVV VVVV001I IIIIII11 VVVVVVVV */
 		ucode[offset++] = 0xf4;
 		ucode[offset++] = 0x40 | (b3 >> 4);
 		ucode[offset++] = (b3 << 4) | 0x02 | (i >> 6);
@@ -357,7 +357,7 @@ static void generate_ucode(u8 *ucode, u32 *gpr_a, u32 *gpr_b)
 		ucode[offset++] = b2;
 	}
 
-	// ctx_arb[kill]
+	/* ctx_arb[kill] */
 	ucode[offset++] = 0xe0;
 	ucode[offset++] = 0x00;
 	ucode[offset++] = 0x01;

arch/arm/configs/at91sam9g20ek_defconfig

@@ -13,6 +13,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_AT91=y
 CONFIG_ARCH_AT91SAM9G20=y
 CONFIG_MACH_AT91SAM9G20EK=y
+CONFIG_MACH_AT91SAM9G20EK_2MMC=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 # CONFIG_ARM_THUMB is not set
 CONFIG_AEABI=y

arch/arm/configs/kirkwood_defconfig

@@ -15,6 +15,7 @@ CONFIG_MACH_MV88F6281GTW_GE=y
 CONFIG_MACH_SHEEVAPLUG=y
 CONFIG_MACH_ESATA_SHEEVAPLUG=y
 CONFIG_MACH_GURUPLUG=y
+CONFIG_MACH_DOCKSTAR=y
 CONFIG_MACH_TS219=y
 CONFIG_MACH_TS41X=y
 CONFIG_MACH_OPENRD_BASE=y

arch/arm/configs/mx27_defconfig

@@ -21,8 +21,14 @@ CONFIG_ARCH_MX2=y
 CONFIG_MACH_MX27=y
 CONFIG_MACH_MX27ADS=y
 CONFIG_MACH_PCM038=y
+CONFIG_MACH_CPUIMX27=y
+CONFIG_MACH_EUKREA_CPUIMX27_USESDHC2=y
+CONFIG_MACH_EUKREA_CPUIMX27_USEUART4=y
 CONFIG_MACH_MX27_3DS=y
+CONFIG_MACH_IMX27_VISSTRIM_M10=y
 CONFIG_MACH_IMX27LITE=y
+CONFIG_MACH_PCA100=y
+CONFIG_MACH_MXT_TD60=y
 CONFIG_MXC_IRQ_PRIOR=y
 CONFIG_MXC_PWM=y
 CONFIG_NO_HZ=y
@@ -76,7 +82,9 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=m
 # CONFIG_SERIO is not set
+CONFIG_SERIAL_8250=m
 CONFIG_SERIAL_IMX=y
 CONFIG_SERIAL_IMX_CONSOLE=y
 # CONFIG_LEGACY_PTYS is not set
@@ -85,19 +93,20 @@ CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_IMX=y
 CONFIG_SPI=y
-CONFIG_SPI_BITBANG=y
+CONFIG_SPI_IMX=y
 CONFIG_W1=y
 CONFIG_W1_MASTER_MXC=y
 CONFIG_W1_SLAVE_THERM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_IMX=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 # CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB=m
+# CONFIG_USB_DEVICE_CLASS is not set
+CONFIG_USB_ULPI=y
 CONFIG_MMC=y
 CONFIG_MMC_MXC=y
 CONFIG_RTC_CLASS=y

arch/arm/configs/mx31pdk_defconfig

@@ -1,44 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-# CONFIG_SWAP is not set
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_COMPAT_BRK is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_MXC=y
-# CONFIG_MACH_MX31ADS is not set
-CONFIG_MACH_MX31_3DS=y
-CONFIG_AEABI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_INET_LRO is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
-# CONFIG_BLK_DEV is not set
-# CONFIG_MISC_DEVICES is not set
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_IMX=y
-CONFIG_SERIAL_IMX_CONSOLE=y
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
-# CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
-# CONFIG_DNOTIFY is not set
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRC32 is not set

arch/arm/configs/mx3_defconfig

@@ -24,6 +24,7 @@ CONFIG_MACH_PCM043=y
 CONFIG_MACH_ARMADILLO5X0=y
 CONFIG_MACH_MX35_3DS=y
 CONFIG_MACH_KZM_ARM11_01=y
+CONFIG_MACH_EUKREA_CPUIMX35=y
 CONFIG_MXC_IRQ_PRIOR=y
 CONFIG_MXC_PWM=y
 CONFIG_NO_HZ=y
@@ -108,7 +109,6 @@ CONFIG_MMC=y
 CONFIG_MMC_MXC=y
 CONFIG_DMADEVICES=y
 # CONFIG_DNOTIFY is not set
-CONFIG_INOTIFY=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_UBIFS_FS=y

arch/arm/configs/mx51_defconfig

@@ -15,6 +15,8 @@ CONFIG_MODULE_SRCVERSION_ALL=y
 CONFIG_ARCH_MXC=y
 CONFIG_ARCH_MX5=y
 CONFIG_MACH_MX51_BABBAGE=y
+CONFIG_MACH_MX51_3DS=y
+CONFIG_MACH_EUKREA_CPUIMX51=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -69,7 +71,6 @@ CONFIG_REALTEK_PHY=y
 CONFIG_NATIONAL_PHY=y
 CONFIG_STE10XP=y
 CONFIG_LSI_ET1011C_PHY=y
-CONFIG_FIXED_PHY=y
 CONFIG_MDIO_BITBANG=y
 CONFIG_MDIO_GPIO=y
 CONFIG_NET_ETHERNET=y
@@ -100,7 +101,6 @@ CONFIG_I2C_ALGOPCF=m
 CONFIG_I2C_ALGOPCA=m
 CONFIG_GPIO_SYSFS=y
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID_SUPPORT is not set
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
@@ -117,13 +117,11 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT3_FS=y
-CONFIG_EXT3_DEFAULTS_TO_ORDERED=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_INOTIFY=y
 CONFIG_QUOTA=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -136,6 +134,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -151,7 +150,6 @@ CONFIG_NLS_UTF8=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
-# CONFIG_DETECT_SOFTLOCKUP is not set
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_BUGVERBOSE is not set
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
@@ -159,7 +157,6 @@ CONFIG_DEBUG_KERNEL=y
 # CONFIG_ARM_UNWIND is not set
 CONFIG_DEBUG_LL=y
 CONFIG_EARLY_PRINTK=y
-CONFIG_KEYS=y
 CONFIG_SECURITYFS=y
 CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y

arch/arm/configs/realview-smp_defconfig

@@ -39,6 +39,7 @@ CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_ARM_INTEGRATOR=y
+CONFIG_ARM_CHARLCD=y
 CONFIG_NETDEVICES=y
 CONFIG_SMSC_PHY=y
 CONFIG_NET_ETHERNET=y
@@ -52,10 +53,13 @@ CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_VERSATILE=y
+CONFIG_SPI=y
+CONFIG_GPIOLIB=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_ARMCLCD=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
@@ -70,7 +74,13 @@ CONFIG_SND_ARMAACI=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
-CONFIG_INOTIFY=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS1307=y
+CONFIG_RTC_DRV_PL031=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
@@ -80,6 +90,7 @@ CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set

arch/arm/configs/realview_defconfig

@@ -38,6 +38,7 @@ CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_ARM_INTEGRATOR=y
+CONFIG_ARM_CHARLCD=y
 CONFIG_NETDEVICES=y
 CONFIG_SMSC_PHY=y
 CONFIG_NET_ETHERNET=y
@@ -51,10 +52,13 @@ CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_VERSATILE=y
+CONFIG_SPI=y
+CONFIG_GPIOLIB=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_ARMCLCD=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
@@ -69,7 +73,13 @@ CONFIG_SND_ARMAACI=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
-CONFIG_INOTIFY=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS1307=y
+CONFIG_RTC_DRV_PL031=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
@@ -79,6 +89,7 @@ CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set

arch/arm/configs/s5p6440_defconfig → arch/arm/configs/s5p64x0_defconfig

@@ -5,10 +5,11 @@ CONFIG_KALLSYMS_ALL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-CONFIG_ARCH_S5P6440=y
+CONFIG_ARCH_S5P64X0=y
 CONFIG_S3C_BOOT_ERROR_RESET=y
 CONFIG_S3C_LOWLEVEL_UART_PORT=1
 CONFIG_MACH_SMDK6440=y
+CONFIG_MACH_SMDK6450=y
 CONFIG_CPU_32v6K=y
 CONFIG_AEABI=y
 CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x20800000,8M console=ttySAC1,115200 init=/linuxrc"

arch/arm/configs/u300_defconfig

@@ -28,26 +28,9 @@ CONFIG_CPU_IDLE=y
 CONFIG_FPE_NWFPE=y
 CONFIG_PM=y
 # CONFIG_SUSPEND is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-# CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ECC_SMC=y
+# CONFIG_MISC_DEVICES is not set
 # CONFIG_INPUT_MOUSEDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
@@ -58,7 +41,6 @@ CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
-CONFIG_POWER_SUPPLY=y
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_REGULATOR=y
@@ -66,24 +48,10 @@ CONFIG_FB=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-# CONFIG_SND_DRIVERS is not set
-# CONFIG_SND_ARM is not set
-# CONFIG_SND_SPI is not set
-CONFIG_SND_SOC=y
 # CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
-CONFIG_MMC_DEBUG=y
 CONFIG_MMC_ARMMMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_BACKLIGHT=y
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_RTC_DRV_COH901331=y
@@ -93,12 +61,11 @@ CONFIG_COH901318=y
 CONFIG_FUSE_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
-# CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
-# CONFIG_DETECT_SOFTLOCKUP is not set
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_TIMER_STATS=y
 # CONFIG_DEBUG_PREEMPT is not set

arch/arm/include/asm/assembler.h

@@ -154,16 +154,39 @@
 	.long	9999b,9001f;			\
 	.popsection
 
+#ifdef CONFIG_SMP
+#define ALT_SMP(instr...)					\
+9998:	instr
+#define ALT_UP(instr...)					\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	instr							;\
+	.popsection
+#define ALT_UP_B(label)					\
+	.equ	up_b_offset, label - 9998b			;\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	b	. + up_b_offset					;\
+	.popsection
+#else
+#define ALT_SMP(instr...)
+#define ALT_UP(instr...) instr
+#define ALT_UP_B(label) b label
+#endif
+
 /*
  * SMP data memory barrier
  */
 	.macro	smp_dmb
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
-	dmb
+	ALT_SMP(dmb)
 #elif __LINUX_ARM_ARCH__ == 6
-	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
+#else
+#error Incompatible SMP platform
 #endif
+	ALT_UP(nop)
 #endif
 	.endm
 

arch/arm/include/asm/cacheflush.h

@@ -137,10 +137,10 @@
 #endif
 
 /*
- * This flag is used to indicate that the page pointed to by a pte
- * is dirty and requires cleaning before returning it to the user.
+ * This flag is used to indicate that the page pointed to by a pte is clean
+ * and does not require cleaning before returning it to the user.
  */
-#define PG_dcache_dirty PG_arch_1
+#define PG_dcache_clean PG_arch_1
 
 /*
  *	MM Cache Management
@@ -156,6 +156,12 @@
  *	Please note that the implementation of these, and the required
  *	effects are cache-type (VIVT/VIPT/PIPT) specific.
  *
+ *	flush_icache_all()
+ *
+ *		Unconditionally clean and invalidate the entire icache.
+ *		Currently only needed for cache-v6.S and cache-v7.S, see
+ *		__flush_icache_all for the generic implementation.
+ *
  *	flush_kern_all()
  *
  *		Unconditionally clean and invalidate the entire cache.
@@ -206,6 +212,7 @@
  */
 
 struct cpu_cache_fns {
+	void (*flush_icache_all)(void);
 	void (*flush_kern_all)(void);
 	void (*flush_user_all)(void);
 	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
@@ -227,6 +234,7 @@ struct cpu_cache_fns {
 
 extern struct cpu_cache_fns cpu_cache;
 
+#define __cpuc_flush_icache_all		cpu_cache.flush_icache_all
 #define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
 #define __cpuc_flush_user_all		cpu_cache.flush_user_all
 #define __cpuc_flush_user_range		cpu_cache.flush_user_range
@@ -246,6 +254,7 @@ extern struct cpu_cache_fns cpu_cache;
 
 #else
 
+#define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
 #define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
 #define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
 #define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
@@ -253,6 +262,7 @@ extern struct cpu_cache_fns cpu_cache;
 #define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
 #define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
 
+extern void __cpuc_flush_icache_all(void);
 extern void __cpuc_flush_kern_all(void);
 extern void __cpuc_flush_user_all(void);
 extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
@@ -291,6 +301,37 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 /*
  * Convert calls to our calling convention.
  */
+
+/* Invalidate I-cache */
+#define __flush_icache_all_generic()					\
+	asm("mcr	p15, 0, %0, c7, c5, 0"				\
+	    : : "r" (0));
+
+/* Invalidate I-cache inner shareable */
+#define __flush_icache_all_v7_smp()					\
+	asm("mcr	p15, 0, %0, c7, c1, 0"				\
+	    : : "r" (0));
+
+/*
+ * Optimized __flush_icache_all for the common cases. Note that UP ARMv7
+ * will fall through to use __flush_icache_all_generic.
+ */
+#if (defined(CONFIG_CPU_V7) && defined(CONFIG_CPU_V6)) ||		\
+	defined(CONFIG_SMP_ON_UP)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+#define __flush_icache_preferred	__flush_icache_all_v7_smp
+#elif __LINUX_ARM_ARCH__ == 6 && defined(CONFIG_ARM_ERRATA_411920)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#else
+#define __flush_icache_preferred	__flush_icache_all_generic
+#endif
+
+static inline void __flush_icache_all(void)
+{
+	__flush_icache_preferred();
+}
+
 #define flush_cache_all()		__cpuc_flush_kern_all()
 
 static inline void vivt_flush_cache_mm(struct mm_struct *mm)
@@ -366,21 +407,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
-static inline void __flush_icache_all(void)
-{
-#ifdef CONFIG_ARM_ERRATA_411920
-	extern void v6_icache_inval_all(void);
-	v6_icache_inval_all();
-#elif defined(CONFIG_SMP) && __LINUX_ARM_ARCH__ >= 7
-	asm("mcr	p15, 0, %0, c7, c1, 0	@ invalidate I-cache inner shareable\n"
-	    :
-	    : "r" (0));
-#else
-	asm("mcr	p15, 0, %0, c7, c5, 0	@ invalidate I-cache\n"
-	    :
-	    : "r" (0));
-#endif
-}
 static inline void flush_kernel_vmap_range(void *addr, int size)
 {
 	if ((cache_is_vivt() || cache_is_vipt_aliasing()))
@@ -405,9 +431,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 static inline void flush_kernel_dcache_page(struct page *page)
 {
-	/* highmem pages are always flushed upon kunmap already */
-	if ((cache_is_vivt() || cache_is_vipt_aliasing()) && !PageHighMem(page))
-		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
 
 #define flush_dcache_mmap_lock(mapping) \

arch/arm/include/asm/cachetype.h

@@ -6,6 +6,7 @@
 #define CACHEID_VIPT_ALIASING		(1 << 2)
 #define CACHEID_VIPT			(CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING)
 #define CACHEID_ASID_TAGGED		(1 << 3)
+#define CACHEID_VIPT_I_ALIASING		(1 << 4)
 
 extern unsigned int cacheid;
 
@@ -14,15 +15,18 @@ extern unsigned int cacheid;
 #define cache_is_vipt_nonaliasing()	cacheid_is(CACHEID_VIPT_NONALIASING)
 #define cache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_ALIASING)
 #define icache_is_vivt_asid_tagged()	cacheid_is(CACHEID_ASID_TAGGED)
+#define icache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_I_ALIASING)
 
 /*
  * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture
  * Mask out support which will never be present on newer CPUs.
  * - v6+ is never VIVT
- * - v7+ VIPT never aliases
+ * - v7+ VIPT never aliases on D-side
  */
 #if __LINUX_ARM_ARCH__ >= 7
-#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING | CACHEID_ASID_TAGGED)
+#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING |\
+				 CACHEID_ASID_TAGGED |\
+				 CACHEID_VIPT_I_ALIASING)
 #elif __LINUX_ARM_ARCH__ >= 6
 #define	__CACHEID_ARCH_MIN	(~CACHEID_VIVT)
 #else

arch/arm/include/asm/elf.h

@@ -127,4 +127,8 @@ struct mm_struct;
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
+extern int vectors_user_mapping(void);
+#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping()
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+
 #endif

arch/arm/include/asm/ftrace.h

@@ -2,12 +2,30 @@
 #define _ASM_ARM_FTRACE
 
 #ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR		((long)(mcount))
+#define MCOUNT_ADDR		((unsigned long)(__gnu_mcount_nc))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
 extern void __gnu_mcount_nc(void);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+struct dyn_arch_ftrace {
+#ifdef CONFIG_OLD_MCOUNT
+	bool	old_mcount;
+#endif
+};
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* With Thumb-2, the recorded addresses have the lsb set */
+	return addr & ~1;
+}
+
+extern void ftrace_caller_old(void);
+extern void ftrace_call_old(void);
+#endif
+
 #endif
 
 #endif

arch/arm/include/asm/hardware/coresight.h

@@ -21,18 +21,6 @@
 #define TRACER_RUNNING		BIT(TRACER_RUNNING_BIT)
 #define TRACER_CYCLE_ACC	BIT(TRACER_CYCLE_ACC_BIT)
 
-struct tracectx {
-	unsigned int	etb_bufsz;
-	void __iomem	*etb_regs;
-	void __iomem	*etm_regs;
-	unsigned long	flags;
-	int		ncmppairs;
-	int		etm_portsz;
-	struct device	*dev;
-	struct clk	*emu_clk;
-	struct mutex	mutex;
-};
-
 #define TRACER_TIMEOUT 10000
 
 #define etm_writel(t, v, x) \
@@ -112,10 +100,10 @@ struct tracectx {
 
 /* ETM status register, "ETM Architecture", 3.3.2 */
 #define ETMR_STATUS		(0x10)
-#define ETMST_OVERFLOW		(1 << 0)
-#define ETMST_PROGBIT		(1 << 1)
-#define ETMST_STARTSTOP		(1 << 2)
-#define ETMST_TRIGGER		(1 << 3)
+#define ETMST_OVERFLOW		BIT(0)
+#define ETMST_PROGBIT		BIT(1)
+#define ETMST_STARTSTOP		BIT(2)
+#define ETMST_TRIGGER		BIT(3)
 
 #define etm_progbit(t)		(etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT)
 #define etm_started(t)		(etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP)
@@ -123,7 +111,7 @@ struct tracectx {
 
 #define ETMR_TRACEENCTRL2	0x1c
 #define ETMR_TRACEENCTRL	0x24
-#define ETMTE_INCLEXCL		(1 << 24)
+#define ETMTE_INCLEXCL		BIT(24)
 #define ETMR_TRACEENEVT		0x20
 #define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT | \
 				ETMCTRL_DATA_DO_ADDR | \
@@ -146,12 +134,12 @@ struct tracectx {
 #define ETBR_CTRL		0x20
 #define ETBR_FORMATTERCTRL	0x304
 #define ETBFF_ENFTC		1
-#define ETBFF_ENFCONT		(1 << 1)
-#define ETBFF_FONFLIN		(1 << 4)
-#define ETBFF_MANUAL_FLUSH	(1 << 6)
-#define ETBFF_TRIGIN		(1 << 8)
-#define ETBFF_TRIGEVT		(1 << 9)
-#define ETBFF_TRIGFL		(1 << 10)
+#define ETBFF_ENFCONT		BIT(1)
+#define ETBFF_FONFLIN		BIT(4)
+#define ETBFF_MANUAL_FLUSH	BIT(6)
+#define ETBFF_TRIGIN		BIT(8)
+#define ETBFF_TRIGEVT		BIT(9)
+#define ETBFF_TRIGFL		BIT(10)
 
 #define etb_writel(t, v, x) \
 	(__raw_writel((v), (t)->etb_regs + (x)))

arch/arm/include/asm/hardware/icst.h

@@ -8,7 +8,7 @@
  * published by the Free Software Foundation.
  *
  *  Support functions for calculating clocks/divisors for the ICST
- *  clock generators.  See http://www.icst.com/ for more information
+ *  clock generators.  See http://www.idt.com/ for more information
  *  on these devices.
  */
 #ifndef ASMARM_HARDWARE_ICST_H

arch/arm/include/asm/hw_breakpoint.h

@@ -0,0 +1,133 @@
+#ifndef _ARM_HW_BREAKPOINT_H
+#define _ARM_HW_BREAKPOINT_H
+
+#ifdef __KERNEL__
+
+struct task_struct;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+
+struct arch_hw_breakpoint_ctrl {
+		u32 __reserved	: 9,
+		mismatch	: 1,
+				: 9,
+		len		: 8,
+		type		: 2,
+		privilege	: 2,
+		enabled		: 1;
+};
+
+struct arch_hw_breakpoint {
+	u32	address;
+	u32	trigger;
+	struct perf_event *suspended_wp;
+	struct arch_hw_breakpoint_ctrl ctrl;
+};
+
+static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
+{
+	return (ctrl.mismatch << 22) | (ctrl.len << 5) | (ctrl.type << 3) |
+		(ctrl.privilege << 1) | ctrl.enabled;
+}
+
+static inline void decode_ctrl_reg(u32 reg,
+				   struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	ctrl->enabled	= reg & 0x1;
+	reg >>= 1;
+	ctrl->privilege	= reg & 0x3;
+	reg >>= 2;
+	ctrl->type	= reg & 0x3;
+	reg >>= 2;
+	ctrl->len	= reg & 0xff;
+	reg >>= 17;
+	ctrl->mismatch	= reg & 0x1;
+}
+
+/* Debug architecture numbers. */
+#define ARM_DEBUG_ARCH_RESERVED	0	/* In case of ptrace ABI updates. */
+#define ARM_DEBUG_ARCH_V6	1
+#define ARM_DEBUG_ARCH_V6_1	2
+#define ARM_DEBUG_ARCH_V7_ECP14	3
+#define ARM_DEBUG_ARCH_V7_MM	4
+
+/* Breakpoint */
+#define ARM_BREAKPOINT_EXECUTE	0
+
+/* Watchpoints */
+#define ARM_BREAKPOINT_LOAD	1
+#define ARM_BREAKPOINT_STORE	2
+
+/* Privilege Levels */
+#define ARM_BREAKPOINT_PRIV	1
+#define ARM_BREAKPOINT_USER	2
+
+/* Lengths */
+#define ARM_BREAKPOINT_LEN_1	0x1
+#define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_8	0xff
+
+/* Limits */
+#define ARM_MAX_BRP		16
+#define ARM_MAX_WRP		16
+#define ARM_MAX_HBP_SLOTS	(ARM_MAX_BRP + ARM_MAX_WRP)
+
+/* DSCR method of entry bits. */
+#define ARM_DSCR_MOE(x)			((x >> 2) & 0xf)
+#define ARM_ENTRY_BREAKPOINT		0x1
+#define ARM_ENTRY_ASYNC_WATCHPOINT	0x2
+#define ARM_ENTRY_SYNC_WATCHPOINT	0xa
+
+/* DSCR monitor/halting bits. */
+#define ARM_DSCR_HDBGEN		(1 << 14)
+#define ARM_DSCR_MDBGEN		(1 << 15)
+
+/* opcode2 numbers for the co-processor instructions. */
+#define ARM_OP2_BVR		4
+#define ARM_OP2_BCR		5
+#define ARM_OP2_WVR		6
+#define ARM_OP2_WCR		7
+
+/* Base register numbers for the debug registers. */
+#define ARM_BASE_BVR		64
+#define ARM_BASE_BCR		80
+#define ARM_BASE_WVR		96
+#define ARM_BASE_WCR		112
+
+/* Accessor macros for the debug registers. */
+#define ARM_DBG_READ(M, OP2, VAL) do {\
+	asm volatile("mrc p14, 0, %0, c0," #M ", " #OP2 : "=r" (VAL));\
+} while (0)
+
+#define ARM_DBG_WRITE(M, OP2, VAL) do {\
+	asm volatile("mcr p14, 0, %0, c0," #M ", " #OP2 : : "r" (VAL));\
+} while (0)
+
+struct notifier_block;
+struct perf_event;
+struct pmu;
+
+extern struct pmu perf_ops_bp;
+extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
+				  int *gen_len, int *gen_type);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					   unsigned long val, void *data);
+
+extern u8 arch_get_debug_arch(void);
+extern u8 arch_get_max_wp_len(void);
+extern void clear_ptrace_hw_breakpoint(struct task_struct *tsk);
+
+int arch_install_hw_breakpoint(struct perf_event *bp);
+void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void hw_breakpoint_pmu_read(struct perf_event *bp);
+int hw_breakpoint_slots(int type);
+
+#else
+static inline void clear_ptrace_hw_breakpoint(struct task_struct *tsk) {}
+
+#endif	/* CONFIG_HAVE_HW_BREAKPOINT */
+#endif	/* __KERNEL__ */
+#endif	/* _ARM_HW_BREAKPOINT_H */

arch/arm/include/asm/hw_irq.h

@@ -24,4 +24,6 @@ void set_irq_flags(unsigned int irq, unsigned int flags);
 #define IRQF_PROBE	(1 << 1)
 #define IRQF_NOAUTOEN	(1 << 2)
 
+#define ARCH_IRQ_INIT_FLAGS	(IRQ_NOREQUEST | IRQ_NOPROBE)
+
 #endif

arch/arm/include/asm/io.h

@@ -294,6 +294,7 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern int valid_phys_addr_range(unsigned long addr, size_t size);
 extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+extern int devmem_is_allowed(unsigned long pfn);
 #endif
 
 /*

arch/arm/include/asm/ioctls.h

@@ -1,89 +1,8 @@
 #ifndef __ASM_ARM_IOCTLS_H
 #define __ASM_ARM_IOCTLS_H
 
-#include <asm/ioctl.h>
-
-/* 0x54 is just a magic number to make these relatively unique ('T') */
-
-#define TCGETS		0x5401
-#define TCSETS		0x5402
-#define TCSETSW		0x5403
-#define TCSETSF		0x5404
-#define TCGETA		0x5405
-#define TCSETA		0x5406
-#define TCSETAW		0x5407
-#define TCSETAF		0x5408
-#define TCSBRK		0x5409
-#define TCXONC		0x540A
-#define TCFLSH		0x540B
-#define TIOCEXCL	0x540C
-#define TIOCNXCL	0x540D
-#define TIOCSCTTY	0x540E
-#define TIOCGPGRP	0x540F
-#define TIOCSPGRP	0x5410
-#define TIOCOUTQ	0x5411
-#define TIOCSTI		0x5412
-#define TIOCGWINSZ	0x5413
-#define TIOCSWINSZ	0x5414
-#define TIOCMGET	0x5415
-#define TIOCMBIS	0x5416
-#define TIOCMBIC	0x5417
-#define TIOCMSET	0x5418
-#define TIOCGSOFTCAR	0x5419
-#define TIOCSSOFTCAR	0x541A
-#define FIONREAD	0x541B
-#define TIOCINQ		FIONREAD
-#define TIOCLINUX	0x541C
-#define TIOCCONS	0x541D
-#define TIOCGSERIAL	0x541E
-#define TIOCSSERIAL	0x541F
-#define TIOCPKT		0x5420
-#define FIONBIO		0x5421
-#define TIOCNOTTY	0x5422
-#define TIOCSETD	0x5423
-#define TIOCGETD	0x5424
-#define TCSBRKP		0x5425	/* Needed for POSIX tcsendbreak() */
-#define TIOCSBRK	0x5427  /* BSD compatibility */
-#define TIOCCBRK	0x5428  /* BSD compatibility */
-#define TIOCGSID	0x5429  /* Return the session ID of FD */
-#define TCGETS2		_IOR('T',0x2A, struct termios2)
-#define TCSETS2		_IOW('T',0x2B, struct termios2)
-#define TCSETSW2	_IOW('T',0x2C, struct termios2)
-#define TCSETSF2	_IOW('T',0x2D, struct termios2)
-#define TIOCGPTN	_IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
-#define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
-
-#define TIOCGRS485      0x542E
-#define TIOCSRS485      0x542F
-
-#define FIONCLEX	0x5450  /* these numbers need to be adjusted. */
-#define FIOCLEX		0x5451
-#define FIOASYNC	0x5452
-#define TIOCSERCONFIG	0x5453
-#define TIOCSERGWILD	0x5454
-#define TIOCSERSWILD	0x5455
-#define TIOCGLCKTRMIOS	0x5456
-#define TIOCSLCKTRMIOS	0x5457
-#define TIOCSERGSTRUCT	0x5458 /* For debugging only */
-#define TIOCSERGETLSR   0x5459 /* Get line status register */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT	0x545C	/* wait for a change on serial input line(s) */
-#define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
 #define FIOQSIZE	0x545E
 
-/* Used for packet mode */
-#define TIOCPKT_DATA		 0
-#define TIOCPKT_FLUSHREAD	 1
-#define TIOCPKT_FLUSHWRITE	 2
-#define TIOCPKT_STOP		 4
-#define TIOCPKT_START		 8
-#define TIOCPKT_NOSTOP		16
-#define TIOCPKT_DOSTOP		32
-#define TIOCPKT_IOCTL		64
-
-#define TIOCSER_TEMT	0x01	/* Transmitter physically empty */
+#include <asm-generic/ioctls.h>
 
 #endif

arch/arm/include/asm/irqflags.h

@@ -10,66 +10,85 @@
  */
 #if __LINUX_ARM_ARCH__ >= 6
 
-#define raw_local_irq_save(x)					\
-	({							\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_save\n"	\
-	"cpsid	i"						\
-	: "=r" (x) : : "memory", "cc");				\
-	})
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_save\n"
+		"	cpsid	i"
+		: "=r" (flags) : : "memory", "cc");
+	return flags;
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile(
+		"	cpsie i			@ arch_local_irq_enable"
+		:
+		:
+		: "memory", "cc");
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile(
+		"	cpsid i			@ arch_local_irq_disable"
+		:
+		:
+		: "memory", "cc");
+}
 
-#define raw_local_irq_enable()  __asm__("cpsie i	@ __sti" : : : "memory", "cc")
-#define raw_local_irq_disable() __asm__("cpsid i	@ __cli" : : : "memory", "cc")
 #define local_fiq_enable()  __asm__("cpsie f	@ __stf" : : : "memory", "cc")
 #define local_fiq_disable() __asm__("cpsid f	@ __clf" : : : "memory", "cc")
-
 #else
 
 /*
  * Save the current interrupt enable state & disable IRQs
  */
-#define raw_local_irq_save(x)					\
-	({							\
-		unsigned long temp;				\
-		(void) (&temp == &x);				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_save\n"	\
-"	orr	%1, %0, #128\n"					\
-"	msr	cpsr_c, %1"					\
-	: "=r" (x), "=r" (temp)					\
-	:							\
-	: "memory", "cc");					\
-	})
-	
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags, temp;
+
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_save\n"
+		"	orr	%1, %0, #128\n"
+		"	msr	cpsr_c, %1"
+		: "=r" (flags), "=r" (temp)
+		:
+		: "memory", "cc");
+	return flags;
+}
+
 /*
  * Enable IRQs
  */
-#define raw_local_irq_enable()					\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_enable\n"	\
-"	bic	%0, %0, #128\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long temp;
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_enable\n"
+		"	bic	%0, %0, #128\n"
+		"	msr	cpsr_c, %0"
+		: "=r" (temp)
+		:
+		: "memory", "cc");
+}
 
 /*
  * Disable IRQs
  */
-#define raw_local_irq_disable()					\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_disable\n"	\
-"	orr	%0, %0, #128\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long temp;
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_disable\n"
+		"	orr	%0, %0, #128\n"
+		"	msr	cpsr_c, %0"
+		: "=r" (temp)
+		:
+		: "memory", "cc");
+}
 
 /*
  * Enable FIQs
@@ -106,27 +125,31 @@
 /*
  * Save the current interrupt enable state.
  */
-#define raw_local_save_flags(x)					\
-	({							\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_save_flags"	\
-	: "=r" (x) : : "memory", "cc");				\
-	})
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile(
+		"	mrs	%0, cpsr	@ local_save_flags"
+		: "=r" (flags) : : "memory", "cc");
+	return flags;
+}
 
 /*
  * restore saved IRQ & FIQ state
  */
-#define raw_local_irq_restore(x)				\
-	__asm__ __volatile__(					\
-	"msr	cpsr_c, %0		@ local_irq_restore\n"	\
-	:							\
-	: "r" (x)						\
-	: "memory", "cc")
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile(
+		"	msr	cpsr_c, %0	@ local_irq_restore"
+		:
+		: "r" (flags)
+		: "memory", "cc");
+}
 
-#define raw_irqs_disabled_flags(flags)	\
-({					\
-	(int)((flags) & PSR_I_BIT);	\
-})
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags & PSR_I_BIT;
+}
 
 #endif
 #endif

arch/arm/include/asm/mach/arch.h

@@ -16,18 +16,15 @@ struct sys_timer;
 
 struct machine_desc {
 	/*
-	 * Note! The first four elements are used
+	 * Note! The first two elements are used
 	 * by assembler code in head.S, head-common.S
 	 */
 	unsigned int		nr;		/* architecture number	*/
-	unsigned int		nr_irqs;	/* number of IRQs */
-	unsigned int		phys_io;	/* start of physical io	*/
-	unsigned int		io_pg_offst;	/* byte offset for io 
-						 * page tabe entry	*/
-
 	const char		*name;		/* architecture name	*/
 	unsigned long		boot_params;	/* tagged list		*/
 
+	unsigned int		nr_irqs;	/* number of IRQs */
+
 	unsigned int		video_start;	/* start of video RAM	*/
 	unsigned int		video_end;	/* end of video RAM	*/
 

arch/arm/include/asm/mmu_context.h

@@ -18,7 +18,6 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
-#include <asm-generic/mm_hooks.h>
 
 void __check_kvm_seq(struct mm_struct *mm);
 
@@ -134,4 +133,32 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 #define deactivate_mm(tsk,mm)	do { } while (0)
 #define activate_mm(prev,next)	switch_mm(prev, next, NULL)
 
+/*
+ * We are inserting a "fake" vma for the user-accessible vector page so
+ * gdb and friends can get to it through ptrace and /proc/<pid>/mem.
+ * But we also want to remove it before the generic code gets to see it
+ * during process exit or the unmapping of it would  cause total havoc.
+ * (the macro is used as remove_vma() is static to mm/mmap.c)
+ */
+#define arch_exit_mmap(mm) \
+do { \
+	struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \
+	if (high_vma) { \
+		BUG_ON(high_vma->vm_next);  /* it should be last */ \
+		if (high_vma->vm_prev) \
+			high_vma->vm_prev->vm_next = NULL; \
+		else \
+			mm->mmap = NULL; \
+		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
+		mm->mmap_cache = NULL; \
+		mm->map_count--; \
+		remove_vma(high_vma); \
+	} \
+} while (0)
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+}
+
 #endif

arch/arm/include/asm/module.h

@@ -7,20 +7,27 @@
 
 struct unwind_table;
 
-struct mod_arch_specific
-{
 #ifdef CONFIG_ARM_UNWIND
-	Elf_Shdr *unw_sec_init;
-	Elf_Shdr *unw_sec_devinit;
-	Elf_Shdr *unw_sec_core;
-	Elf_Shdr *sec_init_text;
-	Elf_Shdr *sec_devinit_text;
-	Elf_Shdr *sec_core_text;
-	struct unwind_table *unwind_init;
-	struct unwind_table *unwind_devinit;
-	struct unwind_table *unwind_core;
-#endif
+struct arm_unwind_mapping {
+	Elf_Shdr *unw_sec;
+	Elf_Shdr *sec_text;
+	struct unwind_table *unwind;
+};
+enum {
+	ARM_SEC_INIT,
+	ARM_SEC_DEVINIT,
+	ARM_SEC_CORE,
+	ARM_SEC_EXIT,
+	ARM_SEC_DEVEXIT,
+	ARM_SEC_MAX,
+};
+struct mod_arch_specific {
+	struct arm_unwind_mapping map[ARM_SEC_MAX];
 };
+#else
+struct mod_arch_specific {
+};
+#endif
 
 /*
  * Include the ARM architecture version.

arch/arm/include/asm/perf_event.h

@@ -12,18 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/*
- * NOP: on *most* (read: all supported) ARM platforms, the performance
- * counter interrupts are regular interrupts and not an NMI. This
- * means that when we receive the interrupt we can call
- * perf_event_do_pending() that handles all of the work with
- * interrupts disabled.
- */
-static inline void
-set_perf_event_pending(void)
-{
-}
-
 /* ARM performance counters start from 1 (in the cp15 accesses) so use the
  * same indexes here for consistency. */
 #define PERF_EVENT_INDEX_OFFSET 1

arch/arm/include/asm/pgtable.h

@@ -278,9 +278,24 @@ extern struct page *empty_zero_page;
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 
-#define set_pte_at(mm,addr,ptep,pteval) do { \
-	set_pte_ext(ptep, pteval, (addr) >= TASK_SIZE ? 0 : PTE_EXT_NG); \
- } while (0)
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	if (addr >= TASK_SIZE)
+		set_pte_ext(ptep, pteval, 0);
+	else {
+		__sync_icache_dcache(pteval);
+		set_pte_ext(ptep, pteval, PTE_EXT_NG);
+	}
+}
 
 /*
  * The following only work if pte_present() is true.
@@ -290,8 +305,13 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(pte_val(pte) & L_PTE_WRITE)
 #define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+#define pte_exec(pte)		(pte_val(pte) & L_PTE_EXEC)
 #define pte_special(pte)	(0)
 
+#define pte_present_user(pte) \
+	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+	 (L_PTE_PRESENT | L_PTE_USER))
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }